hig.sePublications
Change search
Refine search result
12 1 - 50 of 92
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • harvard-cite-them-right
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • sv-SE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • de-DE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Rows per page
  • 5
  • 10
  • 20
  • 50
  • 100
  • 250
Sort
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
Select
The maximal number of hits you can export is 250. When you want to export more records please use the Create feeds function.
  • 1.
    Aalbers, Anouschka
    et al.
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Öberg, Linn
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Agil Kravprioritering: En kvalitativ studie om prioriteringsprocesser inom agil mjukvaruutveckling hos Monitor ERP System AB2021Independent thesis Basic level (professional degree), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    Prioritizing requirements is one of the most important and influential steps in the creation of a software product. The process is iterative; it takes place during the entire agile software development. Through prioritizing requirements, it is decided which requirements are to be developed, in which order, and why. 

    The aim of this study is to investigate how companies that design software prioritize requirements and to identify which prioritization methods they might use during this process. The purpose of this study is to gain an understanding for why a well-balanced prioritization is important, which specific prioritization factors give value to a product, as well as identifying how these factors are related to the result. The purpose is also to investigate the difficulties that exist in a prioritization process, and to create an overview of some of the most used prioritization methods in agile software development. 

    This study is conducted in collaboration with the software company Monitor ERP in order to analyze the company's prioritization processes used to develop their business management system Monitor. The method used is a qualitative study that consists of observations of meetings about prioritization processes, and semi-structured interviews. Processing of collected material was done by organizing, analyzing, and compiling results according to concepts and categories that emerged from the literature study. The results documents work processes, common goals, prioritization aspects and challenges in the requirements prioritization at Monitor ERP. 

    A well-balanced prioritization proved to be important to be able to deliver the right functionality on time and to be able to provide dependable estimates of development, which in turn leads to customers gaining confidence in both the product and the company. A number of prioritization factors that give value to the Monitor software were identified, many of which contribute to increasing customer satisfaction and product quality. Monitor ERP does not use any specific prioritization methods, but the development philosophy Minimum Viable Product is used as a basis for their prioritization choices. During the prioritization process, challenges such as limited resources, unpredictable tasks, difficulties with time estimation, and a challenge in balancing customer value and customer focus were experienced.

    Download full text (pdf)
    Agil_Kravprioritering_Aalbers_Öberg
  • 2.
    Abad, Shayan
    et al.
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Gholamy, Hassan
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Evaluation of machine learning models for classifying malicious URLs2023Independent thesis Basic level (professional degree), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    Millions of new websites are created daily, making it challenging to determine which ones are safe. Cybersecurity involves protecting companies and users from cyberattacks. Cybercriminals exploit various methods, including phishing attacks, to trick users into revealing sensitive information. In Australia alone, there were over 74,000 reported phishing attacks in 2022, resulting in a financial loss of over $24 million. Artificial intelligence (AI) and machine learning are effective tools in various domains, such as cancer detection, financial fraud detection, and chatbot development. Machine learning models, such as Random Forest and Support Vector Machines, are commonly used for classification tasks. With the rise of cybercrime, it is crucial to use machine learning to identify both known and new malicious URLs. The purpose of the study is to compare different instance selection methods and machine learning models for classifying malicious URLs.

    In this study, a dataset containing approximately 650,000 URLs from Kaggle was used. The dataset consisted of four categories: phishing, defacement, malware, and benign URLs. Three datasets, each consisting of around 170,000 URLs, were generated using instance selection methods (DRLSH, BPLSH, and random selection) implemented in MATLAB. Machine learning models, including SVM, DT, KNNs, and RF, were employed. The study applied these instance selection methods to a dataset of malicious URLs, trained the machine learning models on the resulting datasets, and evaluated their performance using 16 features and one output feature.

    In the process of hyperparameter tuning, the training dataset was used to train four models with different hyperparameter settings. Bayesian optimization was employed to find the best hyperparameters for each model. The classification process was then conducted, and the results were compared. The study found that the random instance selection method outperformed the other two methods, BPLSH and DRLSH, in terms of both accuracy and elapsed time for data selection. The lower accuracies achieved by the DRLSH and BPLSH methods may be attributed to the imbalanced dataset, which led to poor sample selection.

    Download full text (pdf)
    Evaluation of machine learning models for classifying malicious URLs
  • 3.
    Abad, Shayan
    et al.
    Department of Computer and Geo-Spatial Sciences, University of Gävle, 801 76 Gävle, Sweden.
    Gholamy, Hassan
    Department of Computer and Geo-Spatial Sciences, University of Gävle, 801 76 Gävle, Sweden.
    Aslani, Mohammad
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Classification of Malicious URLs Using Machine Learning2023In: Sensors, E-ISSN 1424-8220, Vol. 23, no 18, article id 7760Article in journal (Refereed)
    Abstract [en]

    Amid the rapid proliferation of thousands of new websites daily, distinguishing safe ones from potentially harmful ones has become an increasingly complex task. These websites often collect user data, and, without adequate cybersecurity measures such as the efficient detection and classification of malicious URLs, users’ sensitive information could be compromised. This study aims to develop models based on machine learning algorithms for the efficient identification and classification of malicious URLs, contributing to enhanced cybersecurity. Within this context, this study leverages support vector machines (SVMs), random forests (RFs), decision trees (DTs), and k-nearest neighbors (KNNs) in combination with Bayesian optimization to accurately classify URLs. To improve computational efficiency, instance selection methods are employed, including data reduction based on locality-sensitive hashing (DRLSH), border point extraction based on locality-sensitive hashing (BPLSH), and random selection. The results show the effectiveness of RFs in delivering high precision, recall, and F1 scores, with SVMs also providing competitive performance at the expense of increased training time. The results also emphasize the substantial impact of the instance selection method on the performance of these models, indicating its significance in the machine learning pipeline for malicious URL classification

    Download full text (pdf)
    fulltext
  • 4.
    Ahmed, Husain
    et al.
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Bajo, Hozan
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Improved U-Net architecture for Crack Detection in Sand Moulds2023Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    The detection of cracks in sand moulds has long been a challenge for both safety and maintenance purposes. Traditional image processing techniques have been employed to identify and quantify these defects but have often proven to be inefficient, labour-intensive, and time-consuming. To address this issue, we sought to develop a more effective approach using deep learning techniques, specifically semantic segmentation. We initially examined three different architectures—U-Net, SegNet, and DeepCrack—to evaluate their performance in crack detection. Through testing and comparison, U-Net emerged as the most suitable choice for our project. To further enhance the model's accuracy, we combined U-Net with VGG-19, VGG-16, and ResNet architectures. However, these combinations did not yield the expected improvements in performance. Consequently, we introduced a new layer to the U-Net architecture, which significantly increased its accuracy and F1 score, making it more efficient for crack detection. Throughout the project, we conducted extensive comparisons between models to better understand the effects of various techniques such as batch normalization and dropout. To evaluate and compare the performance of the different models, we employed the loss function, accuracy, Adam optimizer, and F1 score as evaluation metrics. Some tables and figures explain the differences between models by using image comparison and evaluation metrics comparison; to show which model is better than the other. The conducted evaluations revealed that the U-Net architecture, when enhanced with an extra layer, proved superior to other models, demonstrating the highest scores and accuracy. This architecture has shown itself to be the most effective model for crack detection, thereby laying the foundation for a more cost-efficient and trustworthy approach to detecting and monitoring structural deficiencies.

    Download full text (pdf)
    fulltext
  • 5.
    Andersson, Claes
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Generering och testning av geografiskt data inom GIS2021Independent thesis Basic level (professional degree), 10 credits / 15 HE creditsStudent thesis
    Abstract [sv]

    Enhetstestning mot databaser inriktade mot geografiska informationssystem kan vara ett komplicerat arbete att utföra. Det innebär både att ha tillgång till användbart data samt att använda verktyg för att utföra dessa tester på. Denna studie har undersökt hur data bestående av ytor kan genereras och hur verktyg inriktade på enhetstestning mot databaser kan användas för att uppnå en förbättrad arbetsmetodik för enhetstestning mot databaser. Arbetet har resulterat i förslag på metoder som kan användas för att generera geografiska data. En applikation har utvecklats för att generera dessa data. Dessutom har en metod för att genomföra enhetstester mot en postgreSQL databas, baserad på verktyget pgTAP, presenterats. Föreslagna metoder kan möjliggöra en förbättring av arbetsmetodiken vid enhetstestning mot databasermen det finns fortfarande många förbättringar att utforska.

    Download full text (pdf)
    fulltext
  • 6.
    Andrée, Martin
    et al.
    Sandviken kommun.
    Larsson, Karolina
    Stockholms stad.
    Paasch, Jesper M.
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Geospatial Sciences.
    Paulsson, Jenny
    Kungliga Tekniska Högskolan (KTH).
    Seipel, Stefan
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Smarta plan-, bygg- och förvaltningsprocesser över hela livscykeln: AP3 Visualisering av 3D-fastigheter2020Report (Other academic)
    Download full text (pdf)
    fulltext
  • 7.
    Aslani, Mohammad
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Computational and spatial analyses of rooftops for urban solar energy planning2022Doctoral thesis, comprehensive summary (Other academic)
    Abstract [en]

    In cities where land availability is limited, rooftop photovoltaic panels (RPVs) offer high potential for satisfying concentrated urban energy demand by using only rooftop areas. However, accurate estimation of RPVs potential in relation to their spatial distribution is indispensable for successful energy planning. Classification, plane segmentation, and spatial analysis are three important aspects in this context. Classification enables extracting rooftops and allows for estimating solar energy potential based on existing training samples. Plane segmentation helps to characterize rooftops by extracting their planar patches. Additionally, spatial analyses enable the identification of rooftop utilizable areas for placing RPVs. This dissertation aims to address some issues associated with these three aspects, particularly (a) training support vector machines (SVMs) in large datasets, (b) plane segmentation of rooftops, and (c) identification of utilizable areas for RPVs. SVMs are among the most potent classifiers and have a solid theoretical foundation. However, they have high time complexity in their training phase, making them inapplicable in large datasets. Two new instance selection methods were proposed to accelerate the training phase of SVMs. The methods are based on locality-sensitive hashing and are capable of handling large datasets. As an application, they were incorporated into a rooftop extraction procedure, followed by plane segmentation. Plane segmentation of rooftops for the purpose of solar energy potential estimation should have a low risk of overlooking superstructures, which play an essential role in the placement of RPVs. Two new methods for plane segmentation in high-resolution digital surface models were thus developed. They have an acceptable level of accuracy and can successfully extract planar segments by considering superstructures. Not all areas of planar segments are utilizable for mounting RPVs, and some factors may further limit their useability. Two spatial methods for identifying RPV-utilizable areas were developed in this realm. They scrutinize extracted planar segments by considering panel installation regulations, solar irradiation, roof geometry, and occlusion, which are necessary for a realistic assessment of RPVs potential. All six proposed methods in this thesis were thoroughly evaluated, and the experimental results show that they can successfully achieve the objectives for which they were designed.

    Download full text (pdf)
    fulltext
    Download (jpg)
    presentationsbild
  • 8.
    Aslani, Mohammad
    et al.
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Seipel, Stefan
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science. Uppsala universitet.
    A fast instance selection method for support vector machines in building extraction2020In: Applied Soft Computing, ISSN 1568-4946, E-ISSN 1872-9681, Vol. 97, no B, article id 106716Article in journal (Refereed)
    Abstract [en]

    Training support vector machines (SVMs) for pixel-based feature extraction purposes from aerial images requires selecting representative pixels (instances) as a training dataset. In this research, locality-sensitive hashing (LSH) is adopted for developing a new instance selection method which is referred to as DR.LSH. The intuition of DR.LSH rests on rapidly finding similar and redundant training samples and excluding them from the original dataset. The simple idea of this method alongside its linear computational complexity make it expeditious in coping with massive training data (millions of pixels). DR.LSH is benchmarked against two recently proposed methods on a dataset for building extraction with 23,750,000 samples obtained from the fusion of aerial images and point clouds. The results reveal that DR.LSH outperforms them in terms of both preservation rate and maintaining the generalization ability (classification loss). The source code of DR.LSH can be found in https://github.com/mohaslani/DR.LSH.

    Download full text (pdf)
    fulltext
  • 9.
    Aslani, Mohammad
    et al.
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Seipel, Stefan
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science. Uppsala universitet.
    A Spatially Detailed Approach to the Assessment of Rooftop Solar Energy Potential based on LiDAR Data2022In: Proceedings of the 8th International Conference on Geographical Information Systems Theory, Applications and Management - GISTAM, ScitePress , 2022, p. 56-63Conference paper (Refereed)
    Abstract [en]

    Rooftop solar energy has long been regarded as a promising solution to cities’ growing energy demand and environmental problems. A reliable estimate of rooftop solar energy facilitates the deployment of photovoltaics and helps formulate renewable-related policies. This reliable estimate underpins the necessity of accurately pinpointing the areas utilizable for mounting photovoltaics. The size, shape, and superstructures of rooftops as well as shadow effects are the important factors that have a considerable impact on utilizable areas. In this study, the utilizable areas and solar energy potential of rooftops are estimated by considering the mentioned factors using a three-step methodology. The first step involves training PointNet++, a deep network for object detection in point clouds, to recognize rooftops in LiDAR data. Second, planar segments of rooftops are extracted using clustering. Finally, areas that receive sufficient solar irradiation, have an appropriate size, and fulfill photovoltaic installation requirements are identified using morphological operations and predefined thresholds. The obtained results show high accuracy for rooftop extraction (93%) and plane segmentation (99%). Moreover, the spatially detailed analysis indicates that 17% of rooftop areas are usable for photovoltaics.

  • 10.
    Aslani, Mohammad
    et al.
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Seipel, Stefan
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science. Uppsala universitet.
    Automatic identification of utilizable rooftop areas in digital surface models for photovoltaics potential assessment2022In: Applied Energy, ISSN 0306-2619, E-ISSN 1872-9118, Vol. 306, article id 118033Article in journal (Refereed)
    Abstract [en]

    The considerable potential of rooftop photovoltaics (RPVs) for alleviating the high energy demand of cities has made them a proven technology in local energy networks. Identification of rooftop areas suitable for installing RPVs is of importance for energy planning. Having these suitable areas referred to as utilizable areas greatly assists in a reliable estimate of RPVs energy production. Within such a context, this research aims to propose a spatially detailed methodology that involves (a) automatic extraction of buildings footprint, (b) automatic segmentation of roof faces, and (c) automatic identification of utilizable areas of roof faces for solar infrastructure installation. Specifically, the innovations of this work are a new method for roof face segmentation and a new method for the identification of utilizable rooftop areas. The proposed methodology only requires digital surface models (DSMs) as input, and it is independent of other auxiliary spatial data to become more functional. A part of downtown Gothenburg composed of vegetation and high-rise buildings with complex shapes was selected to demonstrate the methodology performance. According to the experimental results, the proposed methodology has a high success rate in building extraction (about 95% correctness and completeness) and roof face segmentation (about 85% completeness and correctness). Additionally, the results suggest that the effects of roof occlusions and roof superstructures are satisfactorily considered in the identification of utilizable rooftop areas. Thus, the methodology is practically effective and relevant for the detailed RPVs assessments in arbitrary urban regions where only DSMs are accessible.

    Download full text (pdf)
    fulltext
  • 11.
    Aslani, Mohammad
    et al.
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Seipel, Stefan
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science. Uppsala universitet.
    Efficient and decision boundary aware instance selection for support vector machines2021In: Information Sciences, ISSN 0020-0255, E-ISSN 1872-6291, Vol. 577, p. 579-598Article in journal (Refereed)
    Abstract [en]

    Support vector machines (SVMs) are powerful classifiers that have high computational complexity in the training phase, which can limit their applicability to large datasets. An effective approach to address this limitation is to select a small subset of the most representative training samples such that desirable results can be obtained. In this study, a novel instance selection method called border point extraction based on locality-sensitive hashing (BPLSH) is designed. BPLSH preserves instances that are near the decision boundaries and eliminates nonessential ones. The performance of BPLSH is benchmarked against four approaches on different classification problems. The experimental results indicate that BPLSH outperforms the other methods in terms of classification accuracy, preservation rate, and execution time. The source code of BPLSH can be found in https://github.com/mohaslani/BPLSH. 

    Download full text (pdf)
    fulltext
  • 12.
    Aslani, Mohammad
    et al.
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Seipel, Stefan
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science. Uppsala universitet.
    Rooftop segmentation and optimization of photovoltaic panel layouts in digital surface models2023In: Computers, Environment and Urban Systems, ISSN 0198-9715, E-ISSN 1873-7587, Vol. 105, article id 102026Article in journal (Refereed)
    Abstract [en]

    Rooftop photovoltaic panels (RPVs) are being increasingly used in urban areas as a promising means of achieving energy sustainability. Determining proper layouts of RPVs that make the best use of rooftop areas is of importance as they have a considerable impact on the RPVs performance in efficiently producing energy. In this study, a new spatial methodology for automatically determining the proper layouts of RPVs is proposed. It aims to both extract planar rooftop segments and identify feasible layouts with the highest number of RPVs in highly irradiated areas. It leverages digital surface models (DSMs) to consider roof shapes and occlusions in placing RPVs. The innovations of the work are twofold: (a) a new method for plane segmentation, and (b) a new method for optimally placing RPVs based on metaheuristic optimization, which best utilizes the limited rooftop areas. The proposed methodology is evaluated on two test sites that differ in urban morphology, building size, and spatial resolution. The results show that the plane segmentation method can accurately extract planar segments, achieving 88.7% and 99.5% precision in the test sites. In addition, the results indicate that complex rooftops are adequately handled for placing RPVs, and overestimation of solar energy potential is avoided if detailed analysis based on panel placement is employed.

    Download full text (pdf)
    fulltext
  • 13.
    Aslani, Mohammad
    et al.
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Seipel, Stefan
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Solar Energy Assessment: From Rooftop Extraction to Identifying Utilizable Areas2023In: Geographical Information Systems Theory, Applications and Management, 7th International Conference, GISTAM 2021, Virtual Event, April 23–25, 2021, and 8th International Conference, GISTAM 2022, Virtual Event, April 27-29, 2022, Revised Selected Papers / [ed] Grueau, C., Laurini, R., Ragia, L., Springer , 2023, p. 102-115Conference paper (Refereed)
    Abstract [en]

    Rooftop photovoltaics have been acknowledged as a critical component in cities’ efforts to reduce their reliance on fossil fuels and move towards energy sustainability. Identifying rooftop areas suitable for installing rooftop photovoltaics-referred to as utilizable areas-is essential for effective energy planning and developing policies related to renewable energies. Utilizable areas are greatly affected by the size, shape, superstructures of rooftops, and shadow effects. This study estimates utilizable areas and solar energy potential of rooftops by considering the mentioned factors. First, rooftops are extracted from LiDAR data by training PointNet++, a neural network architecture for processing 3D point clouds. The second step involves extracting planar segments of rooftops using a combination of clustering and region growing. Finally, utilizable areas of planar segments are identified by removing areas that do not have a suitable size and do not receive sufficient solar irradiation. Additionally, in this step, areas reserved for accessibility to photovoltaics are removed. According to the experimental results, the methods have a high success rate in rooftop extraction, plane segmentation, and, consequently, estimating utilizable areas for photovoltaics.

  • 14.
    Aula, Lara
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Improvement of Optical Character Recognition on Scanned Historical Documents Using Image Processing2021Independent thesis Basic level (professional degree), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    As an effort to improve accessibility to historical documents, digitization of historical archives has been an ongoing process at many institutions since the origination of Optical Character Recognition. The old, scanned documents can contain deteriorations acquired over time or caused by old printing methods. Common visual attributes seen on the documents are variations in style and font, broken characters, ink intensity, noise levels and damage caused by folding or ripping and more. Many of these attributes are disfavoring for modern Optical Character Recognition tools and can lead to failed character recognition. This study approaches stated problem by using image processing methods to improve the result of character recognition. Furthermore, common image quality characteristics of scanned historical documents with unidentifiable text are analyzed. The Optical Character Recognition tool used to conduct this research was the open-source Tesseract software. Image processing methods like Gaussian lowpass filtering, Otsu’s optimum thresholding method and morphological operations were used to prepare the historical documents for Tesseract. Using the Precision and Recall classification method, the OCR output was evaluated, and it was seen that the recall improved by 63 percentage points and the precision by 18 percentage points. This shows that using image pre-processing methods as an approach to increase the readability of historical documents for Optical Character Recognition tools is effective. Further it was seen that common characteristics that are especially disadvantageous for Tesseract are font deviations, occurrence of non-belonging objects, character fading, broken characters, and Poisson noise.

    Download full text (pdf)
    fulltext
  • 15.
    Bergkvist, Linda
    et al.
    Karlstad University.
    Ahlin, Karin
    Karlstad University.
    Humble, Niklas
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Mozelius, Peter
    Mid Sweden University.
    Johansson, John
    Karlstad University.
    Redesigning Professional Development on Digital Transformation Using Andragogy as a Theoretical Lens2023In: Proceedings of the 22nd European Conference on e-Learning (ECEL 2023) / [ed] Dr Sarah Jane Johnston & Dr Shawren Singh, ACI Academic Conferences International, 2023, Vol. 22, p. 25-32Conference paper (Refereed)
    Abstract [en]

    Regarding the ongoing digitalisation in the knowledge society, professional development seems more crucial than ever. The need for upskilling and reskilling is described as continuous lifelong learning, which must be combined and synchronised with the life of full-time working learners. Content, pedagogical models and instructional design in university courses are often created for students in Bachelor's and Master's programs instead of tailored for adults working full-time. This study describes and discusses andragogy as a potential knowledge base for redesigning professional development courses on digital transformation. Evaluations from two instances of a course for professionals on digital transformation showed that the course participants overall are satisfied with the course. However, only a few course participants take the exam to get credits. Therefore, the research question that guided this study was, "What redesign options for increased pass rates and learner satisfaction in professional development for adult learners can be identified using andragogy as a theoretical lens?" The course is on distance and contains four modules with synchronous and asynchronous learning activities, resulting in five European Credit Transfer System (ECTS). The empirical material consisted of course participants' check-in presentation before the course started, mid-term evaluation, final evaluations, and a learning diary containing 58 entries. The data was deductively analysed using the theory of andragogy as an analytical lens. The findings imply that instructors should put effort into how different parts of the course are connected, supporting learners' need to know. Further, to enhance the course participants' prior experience as a resource for learning by adding learning activities, they exchange experiences and examples with each other, adding to their learning process and networking. The pedagogic parts of understanding the theoretical course material could be split into pieces through exercises where the participants apply conceptual models and concepts to real-situation problems. The learning diary could help the participants align the new knowledge with their prior knowledge with a focus on professional roles and work situations. The identified redesign options create opportunities to increase pedagogical parts like readiness, orientation, and motivation to learn according to the current higher education system. 

    Download full text (pdf)
    fulltext
  • 16.
    Bergqvist, Christian
    et al.
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Olsson, Fredrik
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Integrering av Deep Learning i webbapplikation2022Independent thesis Basic level (professional degree), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    This work examines how Deep Learning(DL) are integrated with a specific web application. It is performed by creating various artifacts that examine the integration of a specific web application with DL. This is done with regards to future expansion of functionality and the value it offers to the stakeholders. The insights that arise during the work are communicated to the stakeholders through weekly meetings throughout the process. The paper ends with a conclusion that is based on the insight’s that are gained during the work. The conclusion is that the best method is the combination of two of the artifacts. A REST service developed in the Python language that can determine if an image contains animals or not. This REST service I used in an external program that works towards the same object storage that the system does. The program reads images from the storage and tests whether they are empty or not with through the REST-service. Pictures that are classified as empty will be removed from the systems object storage. 

    Download full text (pdf)
    fulltext
  • 17.
    Blomqvist, Sven
    et al.
    University of Gävle, Faculty of Health and Occupational Studies, Department of Public Health and Sport Science, Sports Science.
    Seipel, Stefan
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science. Uppsala universitet.
    Engström, Maria
    University of Gävle, Faculty of Health and Occupational Studies, Department of Caring Science, Caring Science.
    Using augmented reality technology for balance training in the older adults: a feasibility pilot study2021In: BMC Geriatrics, ISSN 1471-2318, E-ISSN 1471-2318, Vol. 21, article id 144Article in journal (Refereed)
    Abstract [en]

    Background: Impaired balance leading to falls is common in the older adults, and there is strong evidence that balance training reduces falls and increases independence. Reduced resources in health care will result in fewer people getting help with rehabilitation training. In this regard, the new technology augmented reality (AR) could be helpful. With AR, the older adults can receive help with instructions and get feedback on their progression in balance training. The purpose of this pilot study was to examine the feasibility of using AR-based visual-interactive tools in balance training of the older adults.; Methods: Seven older adults (66-88 years old) with impaired balance trained under supervision of a physiotherapist twice a week for six weeks using AR-based visual-interactive guidance, which was facilitated through a Microsoft HoloLens holographic display. Afterwards, participants and physiotherapists were interviewed about the new technology and their experience of the training. Also, fear of falling and balance ability were measured before and after training.; Results: Five participants experienced the new technology as positive in terms of increased motivation and feedback. Experiences were mixed regarding the physical and technical aspects of the HoloLens and the design of the HoloLens application. Participants also described issues that needed to be further improved, for example, the training program was difficult and monotonous. Further, the HoloLens hardware was felt to be heavy, the application's menu was difficult to control with different hand manoeuvres, and the calibration took a long time. Suggestions for improvements were described. Results of the balance tests and self-assessment instruments indicated no improvements in balance performance after AR training.; Conclusions: The study showed that training with the new technology is, to some extent, feasible for the older adults, but needs further development. Also, the technology seemed to stimulate increased motivation, which is a prerequisite for adherence to training. However, the new technology and training requires further development and testing in a larger context.

    Download full text (pdf)
    fulltext
  • 18.
    Boberg, Julia
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Analys av navigering och dess påverkanberoende av webbdesign: UX experiment med hjälp av Google Analytics2022Independent thesis Basic level (professional degree), 10 credits / 15 HE creditsStudent thesis
    Abstract [sv]

    Växande närvaro på Internet med utökade funktioner av webbsidor medför problematik för företagen. Problematiken grundar sig ofta i design av webbsidan. Webbdesignen har genom forskning visat sig vara en stor byggsten för företagens framgång. Framgången ligger i antalet unika besökaren och dess varaktighet påwebbsidan. Vi har genom följande arbete utfört ett experiment baserat på forskning inom User Experience med webbutveckling i åtanke. Analysering av användare och dess navigering på webbsidorna i experimentet samlas in och analyseras med hjälp av Google Analytics. Google Analytics presenterar insamlat data med möjlighet till anpassning i form av diagramtyp. Det insamlade data stödjer forskningens slutsats att färgen har en signifikant betydelse i webbdesign. Experimentet hade 32 testare där den optimala färgen utmärkte sig med kortare tid spenderad i navigering på webbsidan.

    Download full text (pdf)
    fulltext
  • 19.
    Boström, Erik
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Taligenkänning i fabriksmiljö: Påverkan av bakgrundsljudets frekvens & typ av ljud2022Independent thesis Basic level (university diploma), 10 credits / 15 HE creditsStudent thesis
    Abstract [sv]

    Detta arbete, som utförts i samband med Monitor ERP är en undersökning av potentiell användning av Automatic speech recognition (ASR) i deras system.Delen av Monitor där ASR skulle vara intressant stämplingsterminalen, används ofta i miljöer med högt bakgrundsljud. Syftet är att ta reda på hur högt bakgrundsljud får vara för att ASR ska fungera samt undersöka hur faktorer som frekvens och typ av ljud påverkar denna gräns. För att göra detta har ljud spelats in på plats i fabriker samt hämtats online, dessa ljud har sedan överlappats med ett inläst manus med olika volymer på bakgrundsljudet. Resultatet av detta visar att för högt ljud gör det omöjligt att använda ASR men vid 80 dB börjar korrektheten nå nivåer som är användbara. Det framgår att frekvens har större betydelse än typ av ljud.

    Download full text (pdf)
    fulltext
  • 20.
    Brodén, Karin
    et al.
    Karlstads Universitet.
    Bergkvist, Linda
    Karlstads Universitet.
    Humble, Niklas
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Mozelius, Peter
    Mittuniversitetet.
    Johansson, John
    Karlstads Universitet.
    Redesigning technology-enhanced professional development to facilitate lifelong learning2023In: ICERI2023 Proceedings, The International Academy of Technology, Education and Development, 2023, Vol. 16Conference paper (Refereed)
    Abstract [en]

    Professional development is more crucial than ever, especially in supporting ongoing digitalisation in the knowledge society. The need for upskilling and reskilling is described as continuous lifelong learning, which must be combined and synchronised with the lives of full-time working learners. Content, pedagogical models and instructional design in university courses are often centred on students in their early twenties with little to no work experience instead of tailored for experienced professionals working full-time. One such course is the foundation for this study: a course on digitalisation and digital transformation targeting professionals with at least two years of work experience in digital transformation. Therefore, the research question that guided this study was: "How can a distance course for professionals be redesigned to facilitate lifelong learning?" The redesign aims to increase satisfaction with the course and the number of participants taking their exams. 

    The course contains four modules with synchronous and asynchronous learning activities, resulting in 5 ECTS credits (the European Credit Transfer System). The analysed empirical material consists of course participants' check-in presentation before the course started, mid-term evaluation, final evaluation, and a learning diary containing 58 entries. The empirical material was inductively and iteratively analysed following the main steps of thematic analysis. Two of the researchers conducted the first steps of the analysis individually. The following steps were a joint coding procedure to reach a consensus. This part of the analysis included several discussions with the other researchers. The inductive analysis identified 70 initial codes that reflected issues related to course design, learning activities, course information, and instructions. The initial codes were clustered into seventeen more abstract themes based on similarities. The themes related to strengths and weaknesses/challenges with the course. The strengths were analysed as, among others, discussions with course participants in other domains, recordings introducing scientific articles, focused and direct instructions on the learning management system (LMS), and the course is held online at the same weekly time. Perceived challenges were, for example, reading scientific articles and understanding and transferring the content to their work situation, lack of correspondence among the modules, not all modules being published simultaneously on the LMS, and the general problem of mixing work and studies. 

    Despite that, the material showed satisfied course participants, where only a few ended the course by taking the exam to get their credits, which is one of academia’s ways to quantify learning. Based on the data analysis, course and learning activities will be redesigned and developed to be tested and evaluated in a forthcoming course instance in autumn 2023.

  • 21.
    Brändeskär, Simon
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Förbättrad användarupplevelse för sökning i Min Karta2021Independent thesis Basic level (professional degree), 10 credits / 15 HE creditsStudent thesis
    Abstract [sv]

    Detta arbete kommer att undersöka användarupplevelsen för Lantmäteriets applikation Min Karta. Undersökningen kommer att fokusera på sökningen inom tjänsten både på presentation av resultat och presentation när användaren inte får något resultat. Antalet sökningar som inte ger resultat kan vara upp till en tredjedel av alla sökningar som görs en viss dag och ett mål med arbetet är att minska antalet av dessa sökningar. Detta mål kan uppnås genom en förbättrad användarkommunikation när en användare inte får någon träff i sin sökning. Arbetet kommer även fokusera på vilka delar av applikationen som kan förbättras för att höja användarupplevelsen och ge sällananvändare en bättre förståelse för hur applikationen används. Genom dessa förbättringar är förhoppningen att färre sällananvändare lämnar efter en sökning utan resultat utan istället förstår och förändrar söktermen till att ge ett resultat.Arbetets syfte är både att hjälpa användare att använda tjänsten på rätt sätt och även att identifiera problem hos tjänsten för framtida lösningar som kan hjälpa tjänsten att bli mer användarvänlig.

    Download full text (pdf)
    fulltext
  • 22.
    Calamaras, Stefan
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Effektivisering av synergierna mellan manuella och automatiserade mjukvarutester: En kvalitativ fallstudie hos Monitor ERP System2022Independent thesis Basic level (university diploma), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    An increasing number of products and systems in the human environment contain software that must work flawlessly. Consequences of software errors can be enormous, and it is therefore important to perform tests to prevent them. Performing tests can be difficult as there is often a limited time or budget, which makes it important to perform efficient tests. Semi-structured interviews, studies of documentation and observations of workflows were performed in a case study at Monitor ERP System to get a better insight into how software tests are performed, and whether their efficiency can be further improved. The case study shows that communication and documentation are important aspects to keep in mind when it comes to developing software tests.

  • 23.
    Carlström, Daniel
    et al.
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Englin, Dennis
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Tillgänglighet på kulturarvsgårdar med telepresence2020Independent thesis Basic level (professional degree), 10 credits / 15 HE creditsStudent thesis
    Abstract [sv]

    Den här studien har undersökt möjligheten att implementera tekniken telepresence för att låta funktionshindrade uppleva svåråtkomliga platser. De svenska hälsingegårdarna kan i många fall klassas som en svåråtkomlig plats då de har höga trösklar, branta trappor, smala dörrar mm. Eftersom en del av gårdarna är klassificerade som världsarv går det inte att tillgänglighetsanpassa byggnaderna då de måste bevaras i deras befintliga skick. Begränsad framkomlighet som leder till att inte alla personer kan besöka platsen kan vara diskriminerande då ett kulturarv ska hållas tillgängligt för allmänheten. Genom att kombinera olika tekniska lösningar har det här arbetet undersökt hur telepresence kan implementeras för att hjälpa personer med rörelsehinder att uppleva hälsingegårdarna.Olika produkter som förekommer i handeln har testats och en prototyp har tagits fram. Resultatet är ett “proof of concept” som visar att VR headset tillsammans med telepresence kan tillämpas för att låta en användare uppleva dessa gårdar i realtid.

    Download full text (pdf)
    fulltext
  • 24.
    Chandel, Kuhelee
    et al.
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Geospatial Sciences.
    Åhlén, Julia
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Seipel, Stefan
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science. Department of Information Technology, Uppsala University.
    Augmented Reality and Indoor Positioning in Context of Smart Industry: A Review2022In: Management and Production Engineering Review, ISSN 2080-8208, E-ISSN 2082-1344, Vol. 13, no 4, p. 72-87Article, review/survey (Refereed)
    Abstract [en]

    Presently, digitalization is causing continuous transformation of industrial processes. However, it does pose challenges like spatially contextualizing data from industrial processes. There are various methods for calculating and delivering real-time location data. Indoor positioning systems (IPS) are one such method, used to locate objects and people within buildings. They have the potential to improve digital industrial processes, but they are currently under utilized. In addition, augmented reality (AR) is a critical technology in today’s digital industrial transformation. This article aims to investigate the use of IPS and AR in manufacturing, the methodologies and technologies employed, the issues and limitations encountered, and identify future research opportunities. This study concludes that, while there have been many studies on IPS and navigation AR, there has been a dearth of research efforts in combining the two. Furthermore, because controlled environments may not expose users to the practical issues they may face, more research in a real-world manufacturing environment is required to produce more reliable and sustainable results

    Download full text (pdf)
    fulltext
  • 25.
    Chandel, Kuhelee
    et al.
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Geospatial Sciences.
    Åhlén, Julia
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science. University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Geospatial Sciences.
    Seipel, Stefan
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Evaluating the Tracking Abilities of Microsoft HoloLens-1 for Small-Scale Industrial Processes2023Conference paper (Refereed)
    Abstract [en]

    This study evaluates the accuracy of Microsoft HoloLens (Version 1) for small-scale industrial activities, comparingits measurements to ground truth data from a Kuka Robotics arm. Two experiments were conducted to assess its positiontracking capabilities, revealing that the HoloLens device is effective for measuring the position of dynamic objects with smalldimensions. However, its precision is affected by the velocity of the trajectory and its position within the device's field of view.While the HoloLens device may be suitable for small-scale tasks, its limitations for more complex and demanding applicationsrequiring high precision and accuracy must be considered. The findings can guide the use of HoloLens devices in industrialapplications and contribute to the development of more effective and reliable position-tracking systems.

    Download full text (pdf)
    abstract
  • 26.
    Edberg, Simon
    et al.
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Mellquist, Anton
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Prototyp av karttjänst för identifiering av folksamlingar2021Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
    Download full text (pdf)
    fulltext
  • 27.
    Eid, Najm Eddin
    et al.
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Jakobsson, Petter
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Tidig detektering avgranbarkborreangrepp med hjälp avfjärranalys via Sentinel-22022Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    The spruce bark beetle is one of Sweden's most destructive pests that attack spruceforests. The insect has had devastating consequences for spruce forests, especiallysince 2018 where large areas of spruce forest have been almost eliminated. The insect thrives in warm and dry climates. The greenhouse effect in the form of heatwaves and periods of reduced rainfall is believed to favor this harmful insect as theycan reproduce several times and conquer new areas in a single summer season.

    A vital and necessary measure in combating pests is to remove infested trees beforethe spruce bark beetle leaves the bark. However, it is almost impossible to examineall the spruce forest in the traditional way, which is on foot, because it is time- andresource-consuming. In the early stage, the infested tree shows no significant colorchanges in the visible spectrum in remote sensing, which makes early detection difficult. To try to make this possible, this work intends to investigate the differences inhealthy and infested trees in time, where bands in the invisible spectrum such asShortWave Infrared were used. This was used, among other things, in the form ofband combinations, such as Atmospheric Penetration and Agriculture. In addition,empirical experiments were performed on different vegetation indices (VI) whichwere Normalized Simple Ratio, Enhanced Vegetation Index, Green ChlorophyllVegetation Index, Normalized Difference Vegetation Index, Normalized DifferenceMoisture Index and Normalized Distance RED and SWIR.

    In this study, satellite images from Sentinel-2 were used over the study area in central Sweden during the months of May-September from 2020 to July 2022. Reported data for attacks by the spruce bark beetle in the study area were retrievedfrom the Global Biodiversity Information Facility and Holmen AB database archives.The Forestry Agency's open map service was used to obtain data on Sweden's forestspecies, to ensure that the study area consisted of spruce forest.

    By performing empirical experiments of the different VI and band combinationspresented in this study, some indications could be distinguished. Due to the problems with the various influencing factors, such as local climate in combination withthreshold values, it was difficult to establish a complete assessment. Our conclusionshows that the used vegetation indices and the two band combinations together withthe spatial resolution offered by Sentinel-2 do not achieve what is sought in thisstudy. The reason for this was that the possibility of identifying individual diseasedtrees in the study area was missing.

    Download full text (pdf)
    fulltext
  • 28.
    Fackel, Edvin
    et al.
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Kolmodin, Robin
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Webbapplikation för felsökning på nätverksnoder2020Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    Handling of alarms on network nodes is a process that requires network technicians to visit several sources of information before they can draw a conclusion on the reason behind the alarm. By visiting several different sources of information, it may be difficult to establish a good overview of the problem.

    This study is made on request by the Swedish traffic authority Trafikverket to ease the workload of the co-workers at the department network operations center (NOC). A web application has been developed to amalgamate the most common sources a network technician visits. The web application presents the amalgamated information in a way that eases the troubleshooting process for the network technicians. The web application also indicates what the most common reasons are, depending on which kind of alarm that is being handled.

    Due to the large availability of different software it can be difficult for a developer to choose a suitable software. Even if some are excluded based on the purpose of the development there are still many choices. This study emphasizes that the software NodeJS, PostgreSQL and PostGIS works well together and is a suitable choice when creating a web application that needs to use spatial functions.

    To evaluate the web application a user test was conducted were nine participants, 47% of the personnel at Trafikverket NOC participated. The result shows positive results in both how well the web application filled its purpose by indicating possible reasons for a network alarm as well as the participants experiences with the web application. In the user test 100% of the participants claim that the web application would save them time and the three most popular features were polygons of electricity distributors, real time weather data and an amalgamation of internal data in one place.

    Download full text (pdf)
    fulltext
    Download (zip)
    Bilaga D
  • 29.
    Folkegård, Niklas
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    3D-grafik med Blender: Modellering, rendering och animation2022 (ed. 1)Book (Other (popular science, discussion, etc.))
    Abstract [sv]

    Boken riktar sig till studenter vid universitet, yrkeshögskola och gymnasium och ger en praktisk introduktion till 3D-grafik med Blender för dig som vill kunna skapa egen 3D-animerad film. Praktiska övningar varvas med teori, begrepp och resonemang kring viktiga konstnärliga och tekniska hänsyn inom modellering, rendering och animation.

    I boken lär du dig bland annat att

    •  skapa 3D-modeller med enkla objekt, polygoner och modifiers

    •  ljussätta objekt och scener

    •  skapa material med filtexturer och materialnoder

    •  rendera bilder, bildsekvenser och videofiler

    •  rigga modeller för animation

    •  animera med keyframes och constraints

    •  strukturera arbetsmaterial för produktion

    •  klippa animation

    •  efterbehandla renderade bilder (Post processing)

    Blender är ett fritt och öppet program för bland annat modellering, rendering och animation i 3D. Bokens övningar är anpassade för Blender 3.3 LTS.

  • 30.
    Friström, Alex
    et al.
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Wallén, Daniel
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Chattbotar inom mjukvaruutveckling2023Independent thesis Basic level (professional degree), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    This work examines the utilization of chatbots in programming and their effects ondeveloper productivity, code quality, and problem-solving. The surge in AI technologyand the popularity of chatbots has been remarkable since the end of 2022, whenOpenAI introduced ChatGPT, capable of providing rapid and accurate responses toinquiries. This introduces novel opportunities for information accessibility withouthuman interactions.Previous research within this domain has explored the usability of earlier chatbots indesign-related professions, revealing a certain degree of utility. Now, with the advancementof AI, new prospects arise for investigating their utility. Emerging technologiesoften imbue functionalities that facilitate or simplify specific tasks. Therefore,the aim of this study is to explore and analyze how chatbots such as ChatGPTand GitHub Copilot can function as interactive aids to streamline programming andsystems development.Conducted as a qualitative study within the realms of programming and systems development,this work employs interviews as its primary methodology. Semi-structuredqualitative interviews are employed for data collection. To analyze the informationgathered from these interviews, a thematic analysis approach is adopted, facilitatingthe identification of commonalities and disparities in the responses.The findings of this study demonstrate that AI tools have proven to be effective andbeneficial in areas like information retrieval or fundamental programming tasks, yetexhibit limitations in advanced programming endeavors and complex problem-solving.The study encompasses respondents who have employed these tools in theirwork, possessing the expertise and experience to offer insights into developers' utilizationof these tools in software development.

    Download full text (pdf)
    fulltext
  • 31.
    Fuentes-Martinez, Ana
    et al.
    Högskolan Väst.
    Ekström, Sara
    Högskolan Väst.
    Humble, Niklas
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Why do children learn programming?: A literature review of contemporary research2023In: Proceeding of the 17th annual International Technology, Education and Development Conference (INTED 2023), Valencia, SPAIN, 2023Conference paper (Refereed)
    Abstract [en]

    The discourses that we create around our present will shape our future. This is particularly true in education where today's students are being equipped to handle and forge the society of tomorrow. One widespread trend sweeping school curricula all over the world is the idea that children and young adults should learn the fundamentals of programming. Increasing efforts are being devoted to this endeavour reaching schools with varying results. Along with these changes in policies and practices, the field of programming education has received growing attention from other stakeholders, not least researchers. The visions and assumptions of those who study and develop this phenomenon are likely to impact its outcome. The purpose of the review is therefore to explore the perceived significance of programming in future society, through the lenses of how researchers frame its introduction in schools. The study was carried out as a literature review surveying open-source journal papers that reported on initiatives related to programming in education in the last five years. The material was collected in a three-step process, including database search, screening, and selection. The search rendered 1089 potentially relevant research papers. Further screening shortened the list to 26 articles featuring 91 individual researchers from 15 different countries. The selected papers were analysed with content analysis to identify codes pertinent to research question, which were later grouped in categories for presentation in this study.

    Results show that mainly positive outcomes are anticipated as a consequence of introducing programming in education. The benefits include filling the needs of a future labour market and preparing students for active participation in an increasingly digitalised society. There were also papers emphasising how learning programming could bring improvements in problem-solving and analytical thinking but also provide space for self-expression and creativeness. Programming in education was believed to enhance social interactions and teamwork skills and to boost motivation and intersectional engagement. However, more critical notions regarding the introduction of programming in education were largely absent, which should be addressed in future research. While programming was seen as a way to raise awareness of the risks associated with a digital society, few authors broadened the discussion to include other less beneficial aspects of programming literacy. Researchers' perceptions in the context of programming in education are compared to previous research on 21st century skills. The findings provide a deeper understanding of the expectations that guide contemporary research and should be of interest not only to the research community but also to teachers and policymakers, in an attempt to spark a discussion that will yield more nuanced implementation of this and future educational initiatives.

  • 32.
    Grindebäck, Max
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Fingerbaserad navigering i virtuella 3D-miljöer: En utvärdering av fingerstyrning som alternativ till tangentbordet2023Independent thesis Basic level (professional degree), 10 credits / 15 HE creditsStudent thesis
    Abstract [sv]

    Navigering i virtuella 3D-miljöer har varit möjligt i många år och sker vanligtvis i samband med till exempel spel och 3D-modellering. Till en persondator används nästan alltid en datormus och ett tangentbord. Musen har visats vara lätthanterlig vid rotering av vyn och kommer inte att vara fokuset i studien. Tangentbordet däremot, som styr vyns position, skulle möjligtvis kunna bytas ut mot något bättre. Vanligtvis används tangenterna W, A, S, och D för förflyttningar, och sedan behövs två tangenter till om det ska vara möjligt att ”flyga” upp och ner. Sex olika tangenter för att styra förflyttningen i tre dimensioner kan vara svårt att lära sig. Trots att vana användare kan hantera det bra, skulle ett mer naturligt sätt att styra på kunna vara enklare för nybörjare, och kanske också för de erfarna. Det begränsade antalet tangenter som används tillåter inte heller finjustering av riktningen. Studien föreslår en alternativ form av 3D-navigering där användaren styr med sitt finger. En Leap Motion kamera ligger på bordet under för att mäta fingrets position, och översätter det till en vektor som kontrollerar vyns hastighet och riktning. Detta är tänkt att vara ett mer naturligt sätt att styra på, då människor har så bra kontroll över sin egen kropp. Utöver det kan även hastigheten justeras genom att dra fingret längre eller kortare sträckor. Vid styrning med tangentbord är justering av hastigheten inte möjligt; undantaget är om användaren kan hålla ner en tangent för att springa, vilket gör att det finns två val av hastigheter. Fingerstyrningen testades och jämfördes direkt mot tangentbordet i ett antal olika experiment. Testerna visar att det går snabbare när tangentbordet används, och ge-nerellt sker färre misstag. När fingerstyrningen används så blir färdsträckorna ofta kortare, speciellt när det krävs mer precision, dock kan detta bero på den lägre has-tigheten som deltagarna hade när de använde fingret. En inmatningsmetod testades bara sju gånger. Under denna period blev fingerstyrningen betydligt snabbare mellan varje försök jämfört med tangentbordet, därför finns anledning att tro att fingerstyr-ningen kommer att förbättras med mer träning. För att få pålitliga resultat skulle en längre studie behöva utföras där deltagarna verkligen hinner lära sig att styra med fingret. Författaren har under utvecklingen av fingerstyrningen blivit snabbare med den än med tangentbordet. Detta är en ytterligare indikation på att det finns potential hos fingerstyrningen som deltagarna aldrig hann uppnå i denna preliminära studie, och att ytterligare experiment krävs.

    Download full text (pdf)
    fulltext
  • 33.
    Hall, Melvin
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Utveckling av applikation för röststyrning vid inventering2023Independent thesis Basic level (professional degree), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    The manufacturing industry has an important role in Sweden's economy and has been producing high quality goods that are exported all over the world for a long time. By using modern technologies such as advanced warehouse systems and digital tools, companies can increase productivity and reduce costs.

    An example of such modern technology is Automatic Speech Recognition (ASR). Most of the previous research conducted in the field of ASR has focused on analyzing and addressing various kind of problems related to the performance of an ASR-system. Furthermore, there are also a number of studies regarding how ASR has been used in the manufacturing industry, and more specifically, to facilitate order picking.

    In this work, the use of speech recognition was investigated as a possible method to facilitate and streamline the inventory process. To investigate this, a prototype for a web application has been developed. The application enables a user, through speech recognition, to speech the article number together with the available quantity in the warehouse. Subsequently, the user receives a confirmation both visually and through sound of which the application automatically registers it in the Monitor ERP software.

    Data has been collected by observing user tests and conducting interviews with indi-viduals who all have some connection to the warehouse at different manufacturing companies. The results indicated that the inventory process could become more ef-fective by using the application. However, some deficiencies were identified during the user tests, which means that the prototype needs further development and increased robustness to be used as a tool during inventory management. 

    Download full text (pdf)
    Utveckling av applikation för röststyrning vid inventering
  • 34.
    Hellstadius, Dennis
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Automatisk detektering av kretskorts position inom in-circuit testning2023Independent thesis Basic level (professional degree), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    This study has attempted to create a program that can be used to calculate the position and orientation of printed circuit boards to help automate Bed-of-Nails testing. The requirements of the program were to be able to calculate the position of PCBs on a plate, calculate the orientation of PCBs relative to the plate and to calculate the amount of PCBs on the plate. The method used to accomplish this was a mixture of traditional image processing methods like filtering, segmentation via edge maps, morphology, watershed and Hough-transformation. This study resulted in a program that works as expected for pictures that have an added source of light. The program is however inadequate for pictures that only contains ambient lighting. The method developed in this study lays a good foundation that can be developed further in order to use in a automatic Bed-of-Nails test system.

    Download full text (pdf)
    fulltext
  • 35.
    Humble, Niklas
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    A lifelong learning perspective on artificial intelligence: What do we need to know?2023In: ICERI2023 Proceedings, The International Academy of Technology, Education and Development, 2023, Vol. 16Conference paper (Refereed)
    Abstract [en]

    Artificial Intelligence (AI) and Artificial Intelligence in Education (AIED) are two fields of research that have been increasingly actualized with recent developments in AI technology. In November 2022 OpenAI released ChatGPT, a chatbot with impressive capabilities of generating seemingly novel content such as poems, lesson plans, exams, and programming code for computer programs. Previous research has highlighted potential opportunities and threats with AI, both for education and society in general, such as privacy, copyright, biases, fairness, and trustworthiness. Further, AI is expected to play an increasingly important role in future work and everyday life, and with that both professionals and citizens in general will have to continuously update their knowledge in the field of AI. The aim of this study has been to develop a framework for lifelong learning courses on Artificial Intelligence. 

    The study was conducted as a scoping literature review to explore previous research and map findings on the topic of Artificial Intelligence for lifelong learning. Google scholar was used as the main search engine for identifying relevant papers, and the aggregation of collected databases at the University library was used for accessing papers that were not Open Access. The search combined keywords such as Artificial Intelligence, Lifelong learning, and Adult learning, with Boolean operators AND and OR. Papers published between 2019 and 2023, and relevant for answering the aim of the study, were collected in a spreadsheet document, and analyzed with thematic analysis. 

    Findings of the literature review identifies both important opportunities and threats of Artificial Intelligence and relate these to different professions and aspects of society. These findings provide a bedrock for development of a lifelong learning framework for courses on Artificial Intelligence, highlighting what we need to know. The conclusion of the study is that courses on Artificial Intelligence that is aimed for lifelong learning should seek a balance between understanding the technology and discussing the potential consequences. Too much focus on either could lead to fear or ignorance.

  • 36.
    Humble, Niklas
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Future paths for GIS in K-12 education: A review of possibilities and constraints2023In: European Journal of Geography, ISSN 1792-1341, Vol. 14, no 3, p. 79-88Article in journal (Refereed)
    Abstract [en]

    Geographic information systems (GIS) have been highlighted as essential future knowledge and are increasingly integrated in people’s everyday lives through applications, tracking, and global positioning systems (GPS). Still, applications and research of GIS technology for teaching and learning in kindergarten to grade 12 (K-12) education are limited. Through a scoping review of contemporary literature, this study identifies and discuss possibilities and constraints for GIS in K-12 education. Data were collected and analyzed with directed content analysis, using affordances as a theoretical lens, to identify possibilities and constraints of GIS for K-12 education. The study highlight themes of possibilities and constraints for further investigation. The possibilities of GIS for K-12 education include accessibility, transdisciplinary, and beyond classroom; and the constraints include skills and attitude, higher education and support, and teachers’ knowledge. The theoretical contribution of the study is a conceptual model for how possibilities and constraints of GIS for K-12 education relates to reaching educational goals. Findings of the study have practical implications for teachers and other stakeholders on the use of GIS in K-12 classrooms. The study also provides several suggestions for future research on GIS in K-12 education.

    Download full text (pdf)
    fulltext
  • 37.
    Humble, Niklas
    et al.
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Boustedt, Jonas
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Holmgren, Hanna
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Milutinovic, Goran
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Seipel, Stefan
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Östberg, Ann-Sofie
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Cheaters or AI-Enhanced Learners: Consequences of ChatGPT for Programming Education2023In: Electronic Journal of e-Learning, E-ISSN 1479-4403Article in journal (Refereed)
    Abstract [en]

    Artificial Intelligence (AI) and related technologies have a long history of being used in education for motivating learners and enhancing learning. However, there have also been critiques for a too uncritical and naïve implementation of AI in education (AIED) and the potential misuse of the technology. With the release of the virtual assistant ChatGPT from OpenAI, many educators and stakeholders were both amazed and horrified by the potential consequences for education. One field with a potential high impact of ChatGPT is programming education in Computer Science (CS), where creating assessments has long been a challenging task due to the vast amount of programming solutions and support on the Internet. This now appears to have been made even more challenging with ChatGPT’s ability to produce both complex and seemingly novel solutions to programming questions. With the support of data collected from interactions with ChatGPT during the spring semester of 2023, this position paper investigates the potential opportunities and threats of ChatGPT for programming education, guided by the question: What could the potential consequences of ChatGPT be for programming education? This paper applies a methodological approach inspired by analytic autoethnography to investigate, experiment, and understand a novel technology through personal experiences. Through this approach, the authors have documented their interactions with ChatGPT in field diaries during the spring semester of 2023. Topics for the questions have related to content and assessment in higher education programming courses. A total of 6 field diaries, with 82 interactions (1 interaction = 1 question + 1 answer) and additional reflection notes, have been collected and analysed with thematic analysis. The study finds that there are several opportunities and threats of ChatGPT for programming education. Some are to be expected, such as that the quality of the question and the details provided highly impact the quality of the answer. However, other findings were unexpected, such as that ChatGPT appears to be “lying” in some answers and to an extent passes the Turing test, although the intelligence of ChatGPT should be questioned. The conclusion of the study is that ChatGPT have potential for a significant impact on higher education programming courses, and probably on education in general. The technology seems to facilitate both cheating and enhanced learning. What will it be? Cheating or AI-enhanced learning? This will be decided by our actions now since the technology is already here and expanding fast.

    Download full text (pdf)
    fulltext
  • 38.
    Humble, Niklas
    et al.
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Boustedt, Jonas
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Holmgren, Hanna
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Milutinovic, Goran
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Seipel, Stefan
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Östberg, Ann-Sofie
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    The consequences of ChatGPT for programming education: Cheating or AI-enhanced learning?2023In: Symposium on AI Opportunities and Challenges: Education will never be the same again, ACI Academic Conferences International, 2023, Vol. 1, p. 15-16Conference paper (Other academic)
    Abstract [en]

    Artificial Intelligence (AI) and related technologies have a long history of being used in education for motivating learners and enhancing learning. However, there have also been critiques for a too uncritical and naïve implementation of AI in education (AIED) and the potential misuse of the technology. With the release of the virtual assistant ChatGPT from OpenAI, many educators and stakeholders were both amazed and horrified by the potential consequences for education. One field with a potential high impact of ChatGPT is programming education in Computer Science (CS), where assessments have long been challenging due to the vast amount of programming solutions and support on the Internet. This now appears to have been made even more challenging with ChatGPT’s ability to produce both complex and seemingly novel solutions to programming questions. With the support of data collected from interactions with ChatGPT during the spring semester of 2023, a study was conducted where potential opportunities and threats of ChatGPT for programming education were investigated. The question to answer was: What will the consequences be for programming education? 

    The study applied a methodological approach inspired by action research and analytic autoethnography to investigate, experiment and understand a novel technology through personal experiences. Through this approach, the authors have documented their interactions with ChatGPT in field diaries during the spring semester of 2023. Topics for the questions have related to content and assessment in higher education programming courses. A total of 6 field diaries, with 82 interactions (1 interaction = 1 question + 1 answer) and additional reflection notes, have been collected and analysed with thematic analysis. 

    Findings of the study include several opportunities and threats of ChatGPT for programming education. Some are to be expected, such as that the quality of the question and the details provided highly impact the quality of the answer. However, other findings were unexpected, such as that ChatGPT appears to be lying in some answers and to an extent passes the Turing test, although the intelligence of ChatGPT should be questioned. The conclusion of the study is that ChatGPT will have a significant impact on higher education programming courses, and probably on education in general. The technology seems to facilitate both cheating and enhanced learning. What will it be? Cheating or AI-enhanced learning? This will be decided by our actions now since the technology is already here and expanding fast. 

  • 39.
    Humble, Niklas
    et al.
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Mozelius, Peter
    Mittuniversitetet.
    Design science for small scale studies: Recommendations for undergraduates and junior researchers2023In: Proceedings of the 22nd European Conference on Research Methodology for Business and Management Studies ECRM 2023 / [ed] Prof Florinda Matos & Prof Álvaro Rosa, Reading (UK): ACI Academic Conferences International, 2023, p. 87-92Conference paper (Refereed)
    Abstract [en]

    Design science is a research methodology that can be applied for both small scale studies at undergraduate level and for large scale application in the industry. Design science is a research methodology with several branches, with slightly different processes built around a common foundation. This paper has a focus on the branch developed by Johannesson and Perjons, and the five-phase model that is included in this branch: 1) explicate problem, 2) define requirements, 3) design and develop artefact, 4) demonstrate artefact, and 5) evaluate artefact. All these five phases must of course be carried out in a complete large-scale project in many real-world developments. However, the problem with applying a design science research project for undergraduates is that a thorough implementation of all the five phases is often too demanding for a Bachelor’s or a Master's thesis. A reason for this is that several of the phases are better carried out in an iterative manner to obtain a quality result, which is time-consuming. The aim of this paper is to discuss the challenges and opportunities in applying design science for small scale studies, such as those conducted by undergraduates in their theses or by researchers new to the field. Based on this discussion, the paper concludes with a set of recommendations for how the design science methodology can be modified and applied to accommodate these smaller studies. The main recommendation is, as the principle for quality research, to delimit and to choose a specific focus that is carried out in depth. Some examples of focuses, that also are recommended by Johannesson and Perjons, are requirements and development focused design science research or evaluation focused design science research. An interesting follow-up to this position paper would be to study the application of design science in Bachelor’s theses and where the emphasis is placed? Moreover, it would be interesting to investigate how design science is applied by researchers and compare if their emphasis in the design science methodology differs from that of undergraduates.

    Download full text (pdf)
    fulltext
  • 40.
    Humble, Niklas
    et al.
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Mozelius, Peter
    Mittuniversitetet.
    Sällvin, Lisa
    Mittuniversitetet.
    Need-Based Game Design: Developing a CT Game Based on Educational Needs2023In: Proceedings of the 17th European Conference on Games Based Learning (ECGBL 2023), ACI Academic Conferences International, 2023, Vol. 17, p. 269-277, article id 1Conference paper (Refereed)
    Abstract [en]

    According to reports and previous research, present and future society show a high need for citizens with technical skills, such as computer programming. The need for technical competent citizens can however be challenging for higher education institutions to accommodate due to low numbers of students in higher education computer science. But also due to the high drop-out rates and low pass rates in introductory programming courses. With that said, it is important to both recruit new students to computer science and to support those who already study the subject, to meet the demands of the present and the future. An approach that has shown great promise in motivating students while still keeping focus on the learning aspects in education, is game-based learning (GBL). To facilitate support in higher education computer science, more specifically courses in fundamental programming, this study had the aim of identifying important design concepts in the development of a need-based educational game on computational thinking (CT). Skills related to programming have commonly been organized as part of the CT concept. To identify the educational needs, e-mail interviews were conducted with teachers that teach higher education courses on computer programming in Swedish universities. Based in an on-going design science project to create a learning game on computational thinking for higher education, the study discusses and compares the identified needs with design theories, such as affordances, emotional design, and sustainable design. The conclusion is a conceptual design of the educational game with a set of recommendations for a need-based game design in educational context.

    Download full text (pdf)
    fulltext
  • 41.
    Ismyren, Fredrik
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    En jämförelse mellan Javas och C++ mekanismer för parallell programkörning2022Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
    Abstract [sv]

    I syfte att skapa beslutsunderlag vid val av programmeringsspråk granskas och utvärderas Javas och C++ mekanismer för parallell programkörning.

    Åtta testprogram skapas i syfte att undersöka vilka prestandamässiga skillnader som visar sig i tre testmiljöer. Resultatet visar att kompilerade språk överlag är snabbare än interpreterade diton med vissa intressanta avvikelser.

    Download full text (pdf)
    fulltext
  • 42.
    Jabali, Aghyad
    et al.
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Mohammedbrhan, Husein Abdelkadir
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Tyre sound classification with machine learning2021Independent thesis Basic level (professional degree), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    Having enough data about the usage of tyre types on the road can lead to a better understanding of the consequences of studded tyres on the environment. This paper is focused on training and testing a machine learning model which can be further integrated into a larger system for automation of the data collection process. Different machine learning algorithms, namely CNN, SVM, and Random Forest, were compared in this experiment. The method used in this paper is an empirical method. First, sound data for studded and none-studded tyres was collected from three different locations in the city of Gävle/Sweden. A total of 760 Mel spectrograms from both classes was generated to train and test a well-known CNN model (AlexNet) on MATLAB. Sound features for both classes were extracted using JAudio to train and test models that use SVM and Random Forest classifi-ers on Weka. Unnecessary features were removed one by one from the list of features to improve the performance of the classifiers. The result shows that CNN achieved accuracy of 84%, SVM has the best performance both with and without removing some audio features (i.e 94% and 92%, respectively), while Random Forest has 89 % accuracy. The test data is comprised of 51% of the studded class and 49% of the none-studded class and the result of the SVM model has achieved more than 94 %. Therefore, it can be considered as an acceptable result that can be used in practice.

    Download full text (pdf)
    fulltext
  • 43.
    Johansson, Ann
    et al.
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Bergman, Emil
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Utmaningar i informationshantering hos ett litet företag2023Independent thesis Basic level (professional degree), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    Since the industrial revolution, today's manufacturing industry has developed a focus on adaptable, efficient, and sustainable manufacturing. At the same time, administrative work has been digitized through information systems. Small companies may face challenges in finding suitable information systems tailored to their needs. Flexible and adaptable information systems are important to support even smaller companies. The purpose of this study is to identify which challenges faced by a small manufacturing company in terms of information management.

    This study was conducted using the research strategy of Design Science. A total of eight semi-structured interviews were conducted, where four employees from Föllinge Hälsoprodukter AB were interviewed in two rounds: requirement collection and evaluation. The Technology Acceptance Model 3 (TAM3) was used as support to construct the interview guide for each round and support the thematic analysis of the data collection. An information system prototype was developed with functionality and design based on the requirements collection.

    The results of the study include problems, requirements and evaluation of the prototype, which is aligned with the design science research strategy. The results showed that an information system with consolidated information and clear interface design would improve communication and efficiency for companies. In addition to these results, it was observed that the time aspect can have an impact on technical acceptance. This was discovered when one of the respondents changed their attitude about implementing an information system in their work, between the requirement collection and evaluation stages. Environmental and sustainability aspects were considered by utilizing technology and systems that can streamline company processes and contribute to reduced paper usage and resource wastage.

    Download full text (pdf)
    fulltext
  • 44.
    Jonsson, Max
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Deep Learning för klassificering av kundsupport-ärenden2020Independent thesis Basic level (professional degree), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    Companies and organizations providing customer support via email will over

    time grow a big corpus of text documents. With advances made in Machine

    Learning the possibilities to use this data to improve the customer support

    efficiency is steadily increasing. The aim of this study is to analyze and evaluate

    the use of Deep Learning methods for automizing the process of classifying

    support errands. This study is based on a Swedish company’s domain where

    the classification was made within the company’s predefined categories. A

    dataset was built by obtaining email support errands (subject and body pairs)

    from the company’s support database. The dataset consisted of data belonging

    to one of nine separate categories. The evaluation was done by analyzing the

    alteration in classification accuracy when using different methods for data

    cleaning and by using different network architectures. A delimitation was set

    to only examine the effects by using different combinations of Convolutional

    Neural Networks (CNN) and Recurrent Neural Networks (RNN) in the shape

    of both unidirectional and bidirectional Long Short Time Memory (LSTM)

    cells. The results of this study show no increase in classification accuracy by

    any of the examined data cleaning methods. However, a feature reduction of

    the used vocabulary is proven to neither have any negative impact on the

    accuracy. A feature reduction might still be beneficial to minimize other side

    effects such as the time required to train a network, and possibly to help

    prevent overfitting. Among the examined network architectures CNN were

    proven to outperform RNN on the used dataset. The most accurate network

    architecture was a single convolutional network which on two different test

    sets reached classification rates of 79,3 and 75,4 percent respectively. The

    results also show some categories to be harder to classify than others, due to

    them not being distinct enough towards the rest of the categories in the

    dataset.

    Download full text (pdf)
    fulltext
  • 45.
    Kazan, Baran
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Additional Classes Effect on Model Accuracy using Transfer Learning2020Independent thesis Basic level (university diploma), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    This empirical research study discusses how much the model’s accuracy changes when adding a new image class by using a pre-trained model with the same labels and measuring the precision of the previous classes to observe the changes. The purpose is to determine if using transfer learning is beneficial for users that do not have enough data to train a model. The pre-trained model that was used to create a new model was the Inception V3. It has the same labels as the eight different classes that were used to train the model. To test this model, classes of wild and non-wild animals were taken as samples. The algorithm used to train the model was implemented in a single class programmed in Python programming language with PyTorch and TensorBoard library. The Tensorboard library was used to collect and represent the result. Research results showed that the accuracy of the first two classes was 94.96% in training and 97.07% in validation. When training the model with a total of eight classes, the accuracy was 91.89% in training and 95.40 in validation. The precision of both classes was detected at 100% when the model solely had cat and dog classes. After adding six additional classes in the model, the precision changed to 95.82% of the cats and 97.16% of the dogs. 

    Download full text (pdf)
    BaranKazan
  • 46.
    Kristiansson, Albin
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Serverless Computing som Function-as-a-Service: Skillnader i prestanda mellan GCP, Azure och AWS2022Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    The pace of digitalization is ever-increasing. To fill societies need for digitalization adigital workforce is needed, as well as the infrastructure to support said workforce.In the wake of digitalization, cloud computing and cloud providers have become anintegrated part of software production. An abstraction layer that builds on top ofcloud computing has gained traction over the last couple of years, serverless computing.This is an abstraction layer that cloud providers provide, which takes away theresponsibility of scaling and maintaining servers.

    This study constructs a framework to benchmark performance for serverless infrastructurefor three large cloud providers. The framework is a grey-box implementationof a recursive algorithm to calculate the 45th number in a Fibonacci series. Saidalgorithm will be tested in Python, Java and NodeJS. The tests will be conducted onthe cloud providers Google Cloud Platform, Amazon Web Service and Microsoft Azure.The purpose of the study is to show any differences in execution time andmemory consumption, for the given algorithm, on all three platforms and betweeneach programming language.

    The study shows that there are statistically significant differences for execution timeas well as memory consumption, for all coding languages, between all three platforms.The biggest difference is observed for NodeJS, followed by Java and lastly Python.On an aggregated level there are greater differences in memory consumptionrather than execution time.

    Download full text (pdf)
    AlbiKristiansson-Kandidatuppsats
  • 47.
    Lindberg, Rebecca
    et al.
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Kranse, Mattias
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Tidsloggningssystem för ambulanshelikopterpiloter2019Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    Active duty time is strictly regulated for ambulance helicopter pilots. Departures and arrivals are determined by incoming alarms, which can make active duty time calculations complicated. These calculations are currently done manually, which can generate uncertainty and unnecessary denial of incoming alarms as a result.

    In this work, a pilot study is made for a time management system for ambulance helicopter pilots, with the main purpose to decrease unnecessary denial of incoming alarms. An IT-system is created where a smartphone collects time data which in turn is presented in a web application.

    As a part of the system, the ability to automatically log flight time with a smartphone is explored. A smartphone application with the purpose of automatically logging flight time is made with its basis and ideas retrieved from previous research and data collection. The test result shows that the application logs the same flight time as the helicopter in 5 times out of 6, with the accuracy of one minute.

    For presenting the collected time data, a visualization model is made in the form of a web application based on previous research and established design principles. Testing of the visualization model shows, for the pilots, that it is easier to make an accurate decision under time pressure with the developed visualization model than with a numerical format of the same data. The result is analyzed with a t-test which concludes that the difference between the graphical and table presentation is statistically significant.

    Download full text (pdf)
    fulltext
  • 48.
    Liu, Fei
    et al.
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Jonsson, Torsten
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Geospatial Sciences.
    Seipel, Stefan
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science. Uppsala universitet.
    Evaluation of augmented reality-based building diagnostics using third person perspective2020In: ISPRS International Journal of Geo-Information, ISSN 2220-9964, Vol. 9, no 1, article id 53Article in journal (Refereed)
    Abstract [en]

    Comprehensive user evaluations of outdoor augmented reality (AR) applications in the architecture, engineering, construction and facilities management (AEC/FM) industry are rarely reported in the literature. This paper presents an AR prototype system for infrared thermographic façade inspection and its evaluation. The system employs markerless tracking based on image registration using natural features and a third person perspective (TPP) augmented view displayed on a hand-held smart device. We focus on evaluating the system in user experiments with the task of designating positions of heat spots on an actual façade as if acquired through thermographic inspection. User and system performance were both assessed with respect to target designation errors. The main findings of this study show that positioning accuracy using this system is adequate for objects of the size of one decimeter. After ruling out the system inherent errors, which mainly stem from our application-specific image registration procedure, we find that errors due to a human’s limited visual-motoric and cognitive performance, which have a more general implication for using TPP AR for target designation, are only a few centimeters.

  • 49.
    Ljunggren, Anton
    et al.
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Nordgren, Niklas
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    Dataanalys och visualisering för optimering av skärande bearbetning2020Independent thesis Basic level (professional degree), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    Sandvik Coromant and their customers have cutting machines that generate data during production. The payload of the data generated contains various measurement values from sensors inside the machineas, well as events that occur in the machine during production.

    In this work, the data collected from the machines has been analyzed to try to increase the machines’ productivity by assisting technicians and machine operators with relevant information. To communicate the information, a software system was developed that analyzes and visualizes machine data.

    The data analysis was done using artificial intelligence trained on sequential data to predict tool failure. When identifying a data sequence that could potentially lead to a tool failure, the machine operator is notified via a mobile application installed on a portable device.

    The data visualizations consist of interactive line charts and time-sorted lists of machine events. The interactive line diagrams are two-dimensional and show measurement values originating from any machine's sensors along the y axis and time along the x axis. The interactivity available to users in the line graphs is zooming, panning, and clickable data points.

    Download full text (pdf)
    Examensarbete AL NN 2020
  • 50.
    Loubier, Michael
    University of Gävle, Faculty of Engineering and Sustainable Development, Department of Computer and Geospatial Sciences, Computer Science.
    ChatGPT: A Good Computer Engineering Student?: An Experiment on its Ability to Answer Programming Questions from Exams2023Independent thesis Basic level (professional degree), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    The release of ChatGPT has really set new standards for what an artificial intelligence chatbot should be. It has even shown its potential in answering university-level exam questions from different subjects. This research is focused on evaluating its capabilities in programming subjects. To achieve this, coding questions taken from software engineering exams were posed to the AI (N = 23) through an experiment. Then, statistical analysis was done to find out how good of a student ChatGPT is by analyzing its answer’s correctness, degree of completion, diversity of response, speed of response, extraneity, number of errors, length of response and confidence levels. GPT-3.5 is the version analyzed.

    The experiment was done using questions from three different programming subjects. Afterwards, results showed a 93% rate of correct answer generation, demonstrating its competence. However, it was found that the AI occasionally produces unnecessary lines of code that were not asked for and thus treated as extraneity. The confidence levels given by ChatGPT, which were always high, also didn't always align with response quality which showed the subjectiveness of the AI’s self-assessment. Answer diversity was also a concern, where most answers were repeatedly written nearly the same way. Moreover, when there was diversity in the answers, it also caused much more extraneous code.

    If ChatGPT was to be blind tested for a software engineering exam containing a good number of coding questions, unnecessary lines of code and comments could be what gives it away as being an AI.

    Nonetheless, ChatGPT was found to have great potential as a learning tool. It can offer explanations, debugging help, and coding guidance just as any other tool or person could. It is not perfect though, so it should be used with caution.

    Download full text (pdf)
    ChatGPT - A Good Computer Engineering Student
12 1 - 50 of 92
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • harvard-cite-them-right
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • sv-SE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • de-DE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf