Change search
Refine search result
1234567 1 - 50 of 867
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • 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.
    Abbasi, Bushra Qazi
    et al.
    Jönköping University, School of Engineering, JTH, Department of Computer Science and Informatics.
    Awais, Samrah
    Jönköping University, School of Engineering, JTH, Department of Computer Science and Informatics.
    Playing mind gamification: Theoretical evidence of addictive nature of gamification and identification of addictive game elements used in mobile application design2022Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
    Abstract [en]

    Gamification is a modern concept that makes physical and digital activities engaging and enjoyable just like games. Game elements are added to mobile applications for user retention and engagement. One of the dark sides of gamification i.e., addiction is explored in this novel study in the context of mobile application design. It uses a mixed-method approach to lay the foundation of the relation between gamification and Smartphone Addiction, which is critically explained in a limited literature review using existing theories and studies on gamification. Interviews with behavioral experts confirm the psychological aspects of the research. The study also identifies game elements that contribute to smartphone addiction by a survey analysis of 269 participants. Results reveal Scrolling and Tapping as most addictive game elements. Some elements also show a statistically significant relationship with daily smartphone usage in hours. There are many effective applications of gamification, and in the context of mobile application design, it indeed helps to increase user engagement, however, there is an ethical need to reflect on what the exaggerated form of this engagement can lead to. As future research, a longitudinal study and experiments are suggested to find out this relationship with the use of empirical data.

    Download full text (pdf)
    fulltext
  • 2.
    Abdelhadi, Ahmed
    et al.
    Jönköping University, School of Engineering, JTH, Department of Computer Science and Informatics.
    Fadda, Mohammed Raoof
    Jönköping University, School of Engineering, JTH, Department of Computer Science and Informatics.
    Exploring Software-Defined Networking Challenges in Sweden: IT Team Knowledge and Skills Gap2022Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    Software-Defined Networking (SDN) is a new evolving approach within the networking domain. The concept is based on decoupling and abstracting the control and data plane of the traditional network devices. This separation facilitates the network operations with many benefits such as faster delivery, better segmentation, scalability, programmability, enhancing the quality of service and the quality of experience. Despite all the benefits, SDN has its own set of challenges. 

    The purpose of this study is to explore the main challenges in adopting SDN architecture in Swedish organizations. The focus is on the skills gap as one of the main challenges and how Swedish organizations were able to manage it.

    A qualitative approach has been chosen to conduct this research using semi-structured interviews to collect the data from seven different organizations, using a mixture of a purposive and snowball sampling selection. A thematic approach was then used to generate categories and themes from the collected data.

    The results are consistent with previous studies when it comes to technical, financial and security challenges. The technical challenges, however, were fewer in comparison with previous studies. A new way of working was presented as a new challenge when implementing SDN solutions. Furthermore, the knowledge gap was mentioned as a key challenge within Swedish organizations when implementing/operating SDN. 

    Finally, clear recommendations were made to overcome the knowledge gap challenge, from consulting a third-party expert, having a detailed plan, employing a multiphase process for SDN implementation, to having an online learning platform available to the IT team. 

    Download full text (pdf)
    Exploring SDN Challenges in Sweden
  • 3.
    Abghari, Shahrooz
    et al.
    Blekinge Tekniska Högskola, Institutionen för datalogi och datorsystemteknik.
    Boeva, Veselka
    Blekinge Tekniska Högskola, Institutionen för datalogi och datorsystemteknik.
    Lavesson, Niklas
    Jönköping University, School of Engineering, JTH, Computer Science and Informatics, JTH, Jönköping AI Lab (JAIL). Blekinge Tekniska Högskola, Institutionen för datalogi och datorsystemteknik.
    Grahn, Håkan
    Blekinge Tekniska Högskola, Institutionen för datalogi och datorsystemteknik.
    Gustafsson, Jörgen
    Ericsson AB.
    Shaikh, Junaid
    Ericsson AB.
    Outlier Detection for Video Session Data Using Sequential Pattern Mining2018In: ACM SIGKDD Workshop On Outlier Detection De-constructed, 2018Conference paper (Refereed)
    Abstract [en]

    The growth of Internet video and over-the-top transmission techniqueshas enabled online video service providers to deliver highquality video content to viewers. To maintain and improve thequality of experience, video providers need to detect unexpectedissues that can highly affect the viewers’ experience. This requiresanalyzing massive amounts of video session data in order to findunexpected sequences of events. In this paper we combine sequentialpattern mining and clustering to discover such event sequences.The proposed approach applies sequential pattern mining to findfrequent patterns by considering contextual and collective outliers.In order to distinguish between the normal and abnormal behaviorof the system, we initially identify the most frequent patterns. Thena clustering algorithm is applied on the most frequent patterns.The generated clustering model together with Silhouette Index areused for further analysis of less frequent patterns and detectionof potential outliers. Our results show that the proposed approachcan detect outliers at the system level.

    Download full text (pdf)
    FULLTEXT01
  • 4.
    Abghari, Shahrooz
    et al.
    Blekinge Tekniska Högskola, Institutionen för datalogi och datorsystemteknik.
    Boeva, Veselka
    Blekinge Tekniska Högskola, Institutionen för datalogi och datorsystemteknik.
    Lavesson, Niklas
    Jönköping University, School of Engineering, JTH, Computer Science and Informatics, JTH, Jönköping AI Lab (JAIL). Blekinge Tekniska Högskola, Institutionen för datalogi och datorsystemteknik.
    Grahn, Håkan
    Blekinge Tekniska Högskola, Institutionen för datalogi och datorsystemteknik.
    Ickin, Selim
    Ericsson, SWE.
    Gustafsson, Jörgen
    Ericsson, SWE.
    A Minimum Spanning Tree Clustering Approach for Outlier Detection in Event Sequences2018In: The 17th IEEE International Conference on Machine Learning and Applications Special Session on Machine Learning Algorithms, Systems and Applications, IEEE, 2018Conference paper (Refereed)
    Abstract [en]

    Outlier detection has been studied in many domains. Outliers arise due to different reasons such as mechanical issues, fraudulent behavior, and human error. In this paper, we propose an unsupervised approach for outlier detection in a sequence dataset. The proposed approach combines sequential pattern mining, cluster analysis, and a minimum spanning tree algorithm in order to identify clusters of outliers. Initially, the sequential pattern mining is used to extract frequent sequential patterns. Next, the extracted patterns are clustered into groups of similar patterns. Finally, the minimum spanning tree algorithm is used to find groups of outliers. The proposed approach has been evaluated on two different real datasets, i.e., smart meter data and video session data. The obtained results have shown that our approach can be applied to narrow down the space of events to a set of potential outliers and facilitate domain experts in further analysis and identification of system level issues.

  • 5.
    Abghari, Shahrooz
    et al.
    Blekinge Tekniska Högskola, Institutionen för datalogi och datorsystemteknik.
    García Martín, Eva
    Blekinge Tekniska Högskola, Institutionen för datalogi och datorsystemteknik.
    Johansson, Christian
    NODA Intelligent Systems AB, Sweden.
    Lavesson, Niklas
    Jönköping University, School of Engineering, JTH, Computer Science and Informatics, JTH, Jönköping AI Lab (JAIL). Blekinge Tekniska Högskola, Institutionen för datalogi och datorsystemteknik.
    Grahn, Håkan
    Blekinge Tekniska Högskola, Institutionen för datalogi och datorsystemteknik.
    Trend analysis to automatically identify heat program changes2017In: Energy Procedia, Elsevier, 2017, p. 407-415Conference paper (Refereed)
    Abstract [en]

    The aim of this study is to improve the monitoring and controlling of heating systems located at customer buildings through the use of a decision support system. To achieve this, the proposed system applies a two-step classifier to detect manual changes of the temperature of the heating system. We apply data from the Swedish company NODA, active in energy optimization and services for energy efficiency, to train and test the suggested system. The decision support system is evaluated through an experiment and the results are validated by experts at NODA. The results show that the decision support system can detect changes within three days after their occurrence and only by considering daily average measurements.

    Download full text (pdf)
    fulltext
  • 6.
    Adlemo, Anders
    Jönköping University, School of Engineering, JTH, Department of Computer Science and Informatics.
    A FRAMEWORK FOR A SUSTAINABILITY TRANSITION OF TWO ENGINEERING MASTER’S COURSES2023In: Proceedings of the International CDIO Conference, Norges teknisk-naturvitenskapelige universitet , 2023, p. 67-83Conference paper (Refereed)
    Abstract [en]

    Sustainability, as a concept, is permeating most of today’s human activities, including higher education. The increased importance put on sustainability depends largely on the increased awareness of the huge environmental, social, and economic challenges that humanity is currently facing. As is the case with most complex themes, the route towards the application of appropriate actions starts with enlightenment developed within education, where different engineering programs form important subareas. To address this, CDIO Syllabus 3.0 in general, but optional standard 1 in specific, does now to an even greater extent handle sustainability issues. This paper presents a framework that is built upon several key concepts that are strongly related to education for sustainable development (ESD) at the university level, such as key sustainability concepts (as defined by UNESCO), sustainability development goals (as defined by the United Nations) and constructive alignment (as defined by Biggs and Tang). The framework is applied to two engineering master’s courses where sustainability concepts and development goals are integrated and constructively aligned in the learning outcomes, teaching and learning activities, and assessments. Through the analysis of the two courses concerning sustainability, the framework is shown to provide a means for the analysis of how sustainability is currently incorporated in a course, highlight what possible teaching/learning shortcomings exist, and help identify actions that can be taken to overcome these shortcomings. The objective of the framework is thus to support course managers in the development of appropriate actions related to sustainability.

  • 7.
    Adlemo, Anders
    Jönköping University, School of Engineering, JTH, Department of Computer Science and Informatics.
    Higher education thesis supervision: A new, hybrid supervisory model2022In: Proceedings of the 18th International CDIO Conference / [ed] M. S. Guðjónsdóttir et al., Reykjavík: Reykjavík University , 2022, Vol. 18, p. 160-173Conference paper (Refereed)
    Abstract [en]

    One of the final courses, if not the last course at university level in Sweden, and especially within the engineering programs, is a thesis course where the students demonstrate their accumulated knowledge and skills. One, or sometimes two students, identifies a topic of interest within his/her main field of study and is guided through the process by a supervisor. Preferably the supervisor has a lot of experience, both within the main field of study and as a thesis supervisor. Many times, however, the latter is not always the case. Hence, some form of recording of the supervisory process would be of importance, to be able to assess the supervisory competence of the supervisor. Through this recording, potential weak supervisory spots can be identified, and a special focus could be put on these.

    In literature several supervisory models have been proposed over the years. The goal of this paper is to demonstrate, through a case study, how three of these models can be successfully combined to a hybrid model around the supervisory process building on grounded theory. A combination of the three models together identifies the individual supervisory process of a thesis supervisor. An analysis is then performed, and weak spots in the supervisory process of a novice supervisor can thus be identified and addressed. The results presented in this paper are based on a case where an experienced thesis supervisor was observed during asupervisory session. Hence, the case forms a baseline of what a “good” supervisory session looks like. By applying the hybrid supervisory model on a novice thesis supervisor, possible weaknesses in the process can be identified.

    As both students and teachers are involved in a one-to-one teaching-learning activity during the thesis process, CDIO standards such as number 8 (active learning) is important from the students’ point-of-view, but especially standard number 10 (enhancement of faculty teaching competence) is of high importance as the competence of the novice supervisor, or the lack thereof, becomes evident and can be appropriately addressed through especially designed activities.

    Download full text (pdf)
    Proceedings
  • 8.
    Adlemo, Anders
    et al.
    Jönköping University, School of Engineering, JTH, Department of Computer Science and Informatics.
    Almusaed, Amjad
    Jönköping University, School of Engineering, JTH, Construction Engineering and Lighting Science.
    Conway, Patrick L. J.
    Jönköping University, School of Engineering, JTH, Materials and Manufacturing.
    Hansen, Åsa
    Jönköping University, School of Engineering, JTH, Physics and Mathematics and Chemical Engineering.
    Rico-Cortez, Marisol
    Jönköping University, School of Engineering, JTH, Industrial Product Development, Production and Design.
    Hybrid education: A critical review into challenges and opportunities2023In: Proceedings of the International CDIO Conference, Norges teknisk-naturvitenskapelige universitet , 2023, p. 857-865Conference paper (Refereed)
    Abstract [en]

    Hybrid education is a complex combination of simultaneous face-to-face and online teaching. This model of teaching comes with a wide range of benefits, primarily being able to offer the same content to a wider audience. Hybrid education became an effective form of teaching during the COVID-19 pandemic. In these post pandemic years, the benefit of hybrid education can still be utilized, allowing for improved flexibility in teaching schedules, engaging students in interactive learning, bringing online students closer to the teacher and face-to-face students, and offering education to students who could not otherwise participate. However, with all the benefits of hybrid education, there are some significant challenges which restrict the implementation or hinder the full potential of hybrid education. Some key challenges are student engagement from the online students with the teacher as well as with other students, technological requirements, physical classroom set-up, education of the teachers, and time investment in re-structuring courses. In this article, we review the challenges of hybrid education, strategies to address these challenges focusing on implementation and effectiveness, as well as evaluating student feedback from students at Jönköping University that have been a part of hybrid education. 

  • 9.
    Adlemo, Anders
    et al.
    Jönköping University, School of Engineering, JTH, Computer Science and Informatics.
    Hilletofth, Per
    Jönköping University, School of Engineering, JTH, Supply Chain and Operations Management.
    Automatic generation of fuzzy inference rules in a reshoring decision context2019In: Proceedings of the 9th International Conference on Operations and Supply Chain Management, Vietnam, 2019, OSCM , 2019Conference paper (Refereed)
    Abstract [en]

    This paper presents a decision-support system for reshoring decision-making based on fuzzy logic. The construction and functionality of the decision-support system is briefly outlined and evaluated in a highcost environment contemplating six specific decision criteria, namely cost, quality, time, flexibility, innovation and sustainability. A major challenge with fuzzy logic solutions has to do with the construction of the fuzzy inference rules. In the relocation domain, the fuzzy inference rules represent the knowledge and competence of relocation experts and they are usually created manually by the same experts. One obstacle is that the complexity of the fuzzy inference rules increases with the number of decision criteria. To overcome this complexity issue, this paper presents a solution whereby the fuzzy inference rules are automatically generated by applying one hundred reshoring scenarios as input data. The reshoring decision recommendations produced by the fuzzy logic decision-support system are demonstrated to be close to those of human reshoring domain experts.

  • 10.
    Adlemo, Anders
    et al.
    Jönköping University, School of Engineering, JTH, Computer Science and Informatics.
    Hilletofth, Per
    Jönköping University, School of Engineering, JTH, Industrial Product Development, Production and Design. Jönköping University, School of Engineering, JTH, Supply Chain and Operations Management.
    Semi-Automatic Generation of a Fuzzy Inference System in a Reshoring Context2020In: SPS2020: Proceedings of the Swedish Production Symposium, October 7–8, 2020 / [ed] K. Säfsten & F. Elgh, IOS Press, 2020, Vol. 13, p. 599-609Conference paper (Refereed)
    Abstract [en]

    Reshoring can be regarded as offshoring in reverse. While offshoring mainly has been driven by cost aspects, reshoring considers multiple aspects, such as higher quality demands, faster product delivery and product mass-customization. Where to locate manufacturing is usually a purely manual activity that relies on relocation experts, hence, an automated decision-support system would be extremely useful. This paper presents a decision-support system for reshoring decision-making building a fuzzy inference system. The construction and functionality of the fuzzy inference system is briefly outlined and evaluated within a high-cost environment considering six specific reshoring decision criteria, namely cost, quality, time, flexibility, innovation and sustainability. A challenge in fuzzy logic relates to the construction of the so called fuzzy inference rules. In the relocation domain, fuzzy inference rules represent the knowledge and competence of relocation experts and are usually generated manually by the same experts. This paper presents a solution where fuzzy inference rules are automatically generated applying one hundred reshoring scenarios as input data. Another important aspect in fuzzy logic relates to the membership functions. These are mostly manually defined but, in this paper, a semi-Automatic approach is presented. The reshoring decision recommendations produced by the semi-Automatically configured fuzzy inference system are shown to be as accurate as those of a manually configured fuzzy inference system. 

  • 11.
    Adlemo, Anders
    et al.
    Jönköping University, School of Engineering, JTH, Computer Science and Informatics.
    Hilletofth, Per
    Jönköping University, School of Engineering, JTH, Supply Chain and Operations Management.
    Tarasov, Vladimir
    Jönköping University, School of Engineering, JTH, Computer Science and Informatics, JTH, Jönköping AI Lab (JAIL).
    Fuzzy logic based decision-support for reshoring decisions2018In: Proceedings of the 8th International Conference on Operations and Supply Chain Management, 2018Conference paper (Refereed)
  • 12.
    Adlemo, Anders
    et al.
    Jönköping University, School of Engineering, JTH, Computer Science and Informatics. Jönköping University / School of Engineering.
    Tan, He
    Jönköping University, School of Engineering, JTH, Computer Science and Informatics, JTH, Jönköping AI Lab (JAIL).
    Tarasov, Vladimir
    Jönköping University, School of Engineering, JTH, Computer Science and Informatics, JTH, Jönköping AI Lab (JAIL).
    Test case quality as perceived in Sweden2018In: Proceedings - International Conference on Software Engineering / [ed] Michael Unterkalmsteiner, ACM Digital Library, 2018, p. 9-12Conference paper (Refereed)
    Abstract [en]

    In order to reach an acceptable level of confidence in the quality of a software product, testing of the software is paramount. To obtain "good" quality software it is essential to rely on "good" test cases. To define the criteria for what make up for a "good" test case is not a trivial task. Over the past 15 years, a short list of publications have presented criteria for "good" test cases but without ranking them based on their importance. This paper presents a non-exhaustive and non-authoritative tentative list of 15 criteria and a ranking of their relative importance. A number of the criteria come from previous publications but also from discussions with our industrial partners. The ranking is based on results collected via a questionnaire that was sent out to a limited number of randomly chosen respondents in the Swedish software industry. This means that the results are more indicative than conclusive.

  • 13.
    Adlemo, Anders
    et al.
    Jönköping University, School of Engineering, JTH, Computer Science and Informatics.
    Tarasov, Vladimir
    Jönköping University, School of Engineering, JTH, Computer Science and Informatics, JTH, Jönköping AI Lab (JAIL).
    Hilletofth, Per
    Jönköping University, School of Engineering, JTH, Supply Chain and Operations Management.
    Eriksson, David
    Jönköping University, School of Engineering, JTH, Supply Chain and Operations Management.
    Knowledge intensive decision support for reshoring decisions2018In: Proceedings of the 30th Annual NOFOMA Conference: Relevant Logistics and Supply Chain Management Research, Kolding, 2018Conference paper (Refereed)
  • 14.
    Adlemo, Anders
    et al.
    Jönköping University, School of Engineering, JTH, Computer Science and Informatics.
    Tarasov, Vladimir
    Jönköping University, School of Engineering, JTH, Computer Science and Informatics, JTH, Jönköping AI Lab (JAIL).
    Hilletofth, Per
    Jönköping University, School of Engineering, JTH, Supply Chain and Operations Management.
    Eriksson, David
    Jönköping University, School of Engineering, JTH, Supply Chain and Operations Management.
    Reshoring decision support in a Swedish context2018Conference paper (Refereed)
    Abstract [en]

    This paper presents a decision-support system for reshoring decision-making based on fuzzy logic. The construction and functionality of the decision-support system are described, and the functionality is evaluated in a high cost environment exemplified through a Swedish context. Ten different reshoring scenarios, provided by Swedish reshoring experts, are entered into the decision-support system and the decision recommendations provided by the system are presented. The confidence that can be put on the recommendations is demonstrated by comparing them with those of the reshoring experts. The positive results obtained indicate that fuzzy logic is both feasible and that the quality of the results are sufficiently good for reshoring decision-making.

  • 15.
    Adnan Abdullah, Ahmad
    et al.
    Jönköping University, School of Engineering, JTH, Department of Computer Science and Informatics.
    Alshehada, Essa
    Jönköping University, School of Engineering, JTH, Department of Computer Science and Informatics.
    IoT-Based DigitalTwin Frameworkfor environmentalmonitoring in theIndoor Environment:Design and Implementation2022Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    Purpose: This thesis aims to describe how to design and implement an IoT-Based digital twin framework for environmental monitoring in the indoor environment.  To fulfill the purpose of the study, the following research question is answered. How to create a digital twin solution utilizing AWS to establish interaction and convergence between the physical environment in a classroom and the virtual environment? 

    Method: As a research method, the research has conducted design science research (DSR). DSR is a new method, and it is an effective tool for enhancing engineering education research methods.

     Results: The study describes in detail the steps required to create the framework. The framework enabled interaction and convergence between the physical and virtual environments in a particular location.

     Implications: The research contributes to broadening the knowledge on using the Internet of things (IoT), digital twin (DT), and Amazon web services (AWS). The study provides future research with reference data and a framework to build upon. 

    Research Limitation: Due to time constraints, the study's scope and limitations are limited to the technologies that the participating company, Knowit, provides. Knowit AB is a Swedish IT consulting company that supports companies and organizations with services in digital transformation and system development. The study aims to create an AWS-based IoT framework, not improve the digital twin concept. The framework was implemented at Jönköping University. This work is also limited to temperature and light intensity as environmental parameters.

    Download full text (pdf)
    fulltext
  • 16.
    Ahlberg, Ernst
    et al.
    Predictive Compound ADME & Safety, Drug Safety & Metabolism, AstraZeneca IMED Biotech Unit, Mölndal, Sweden.
    Winiwarter, Susanne
    Predictive Compound ADME & Safety, Drug Safety & Metabolism, AstraZeneca IMED Biotech Unit, Mölndal, Sweden.
    Boström, Henrik
    Department of Computer and Systems Sciences, Stockholm University, Sweden.
    Linusson, Henrik
    Department of Information Technology, University of Borås, Sweden.
    Löfström, Tuve
    Jönköping University, School of Engineering, JTH, Computer Science and Informatics, JTH, Jönköping AI Lab (JAIL). Department of Information Technology, University of Borås, Sweden.
    Norinder, Ulf
    Swetox, Karolinska Institutet, Unit of Toxicology Sciences, Sweden.
    Johansson, Ulf
    Jönköping University, School of Engineering, JTH, Computer Science and Informatics, JTH, Jönköping AI Lab (JAIL). Department of Information Technology, University of Borås, Sweden.
    Engkvist, Ola
    External Sciences, Discovery Sciences, AstraZeneca IMED Biotech Unit, Mölndal, Sweden.
    Hammar, Oscar
    Quantitative Biology, Discovery Sciences, AstraZeneca IMED Biotech Unit, Mölndal, Sweden.
    Bendtsen, Claus
    Quantitative Biology, Discovery Sciences, AstraZeneca IMED Biotech Unit, Cambridge, UK.
    Carlsson, Lars
    Quantitative Biology, Discovery Sciences, AstraZeneca IMED Biotech Unit, Mölndal, Sweden.
    Using conformal prediction to prioritize compound synthesis in drug discovery2017In: Proceedings of Machine Learning Research: Volume 60: Conformal and Probabilistic Prediction and Applications, 13-16 June 2017, Stockholm, Sweden / [ed] Alex Gammerman, Vladimir Vovk, Zhiyuan Luo, and Harris Papadopoulos, Machine Learning Research , 2017, p. 174-184Conference paper (Refereed)
    Abstract [en]

    The choice of how much money and resources to spend to understand certain problems is of high interest in many areas. This work illustrates how computational models can be more tightly coupled with experiments to generate decision data at lower cost without reducing the quality of the decision. Several different strategies are explored to illustrate the trade off between lowering costs and quality in decisions.

    AUC is used as a performance metric and the number of objects that can be learnt from is constrained. Some of the strategies described reach AUC values over 0.9 and outperforms strategies that are more random. The strategies that use conformal predictor p-values show varying results, although some are top performing.

    The application studied is taken from the drug discovery process. In the early stages of this process compounds, that potentially could become marketed drugs, are being routinely tested in experimental assays to understand the distribution and interactions in humans.

    Download full text (pdf)
    Fulltext
  • 17.
    Ahlin, K.
    et al.
    Ctf, The Service Research Center, Karlstad University, Karlstad, Sweden.
    Kitkowska, Agnieszka
    Jönköping University, School of Engineering, JTH, Department of Computer Science and Informatics.
    Wästlund, E.
    Ctf, The Service Research Center, Karlstad University, Karlstad, Sweden.
    IoT for Health and Well-being: A case study and call for action2023In: PETRA '23: Proceedings of the 16th International Conference on PErvasive Technologies Related to Assistive Environments, Association for Computing Machinery (ACM), 2023, Vol. 16, p. 465-467Conference paper (Refereed)
    Abstract [en]

    In this short paper we describe the implementation of an IoT test-bed in an elementary school. We argue that by adding additional IoT senors to an existing IoT system it is possible to evolve an indoor climate control system into a indoor milieu control system aimed at improving the health and well-being for both pupils and staff who spend their days working in the school environment. Lastly, we call for multidisciplinary action as the domain IoT for health and well-being spans across several different knowledge domains.

  • 18.
    Ahmad, Hanna
    et al.
    Jönköping University, School of Engineering, JTH, Computer Science and Informatics.
    Asmelash, Simon
    Jönköping University, School of Engineering, JTH, Computer Science and Informatics.
    Business Intelligence: Framtagning av kriterier innan val av BI-system för mindre företag2017Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    Purpose – The purpose of this thesis was to investigate which criteria that are vital before the choice of BI-system for small companies with 10-30 employees. Furthermore, to find an appropriate BI-tool that is applicable for small companies with 10-30 employees.

     

    Method – The authors have used semi-structured interviews and literature studies. The qualitative interviews have been conducted by interviewing BI-experts from five smaller companies. The literature review consisted of scientific articles, course literature, and relevant web-pages.

     

    Findings – The findings of this thesis are a production of criteria and a proposal on BI-tool, in the choice of BI-system for smaller companies with 10-30 employees.

     

    Implications – The produced findings of this thesis indicate that there are gaps in what are essential to think of, before a future investment of a BI-system that is suitable for smaller companies with 10-30 employees. Furthermore, there is limited research about which BI-tool that is appropriate for smaller companies with 10-30 employees. This thesis is directed towards smaller companies that are interested in acquiring a BI-system to their organization.

     

    Limitations – This thesis was limited by time constraints, that is why the authors remained their focus on companies with 10-30 employees.

     

    Keywords – Business Intelligence, decision-making, criteria, smaller companies, system.

    Download full text (pdf)
    fulltext
  • 19.
    Ahola, Johannes
    et al.
    Jönköping University, School of Engineering, JTH, Department of Computer Science and Informatics.
    Gunnarsson, Olivia
    Jönköping University, School of Engineering, JTH, Department of Computer Science and Informatics.
    Exploring Young Male Perspectives on Gender-Stereotyped Instagram Ads: A qualitative study on Swedish men's engagement towards gender-stereotyped advertisements in the digital context of Instagram2023Independent thesis Basic level (degree of Bachelor), 180 HE creditsStudent thesis
    Abstract [en]

    This paper examined male engagement towards gender stereotypes online. We specifically sought to address how men engage with gender-stereotyped advertisements on Instagram, and which interactions they utilize to do so. We aimed to understand how men engage with gender stereotypes in Instagram advertisements by answering the following research question:

    [RQ1] How do men engage with gender-stereotyped advertisements on Instagram?

    Data were collected from 10 male participants through semi-structured interviews using photo elicitation. The data was further obtained through thematic analysis using the Theory of Planned Behaviour. The findings resulted in 26 codes and 6 themes. The results demonstrated that exposure to masculine content receives more attention and recognition than feminine, non-sexualized content. The findings argued that men are hesitant to engage with sexualized and provocative content due to societal norms and fear of being judged by others. In contradiction, men believe that other men are more likely to engage with sexualised, gender-stereotyped content that idealizes masculinity. The study identified the most common engagement interactions utilized when engaging with gender-stereotyped content: liking, visiting the account or website, and sharing content with a friend.

    The findings supported previous research claims that accepting a feminine image puts men at risk of violating gender roles, resulting in men preserving a masculine persona by distancing themselves from this type of material (Elliot & Elliot, 2005). Additionally, we concluded that fear of judgement from peers and society results in social pressure to conform to masculine gender norms, which may influence men’s online behaviour.

    The results may be delimited by social desirability and sampling bias due to the designated scope. Nevertheless, we have implemented measures to ensure the trustworthiness of this study.

    Download full text (pdf)
    fulltext
  • 20.
    Akerlund, Matilda
    et al.
    Jönköping University, School of Engineering, JTH, Department of Computer Science and Informatics.
    Alaranji, Louai
    Jönköping University, School of Engineering, JTH, Department of Computer Science and Informatics.
    A dynamically adaptive Bluetooth system: Improving the range of Bluetooth classic 4.2 using Forward Error Correction2023Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    Wireless technology has increased in popularity since its invention, being embedded in many devices, such as smartphones, laptops, earphones etcetera. One of those technologies is Bluetooth, which is a short-range technology that is widely used worldwide. While being a popular and important technology, it is not as optimized as it could be, especially the standard Bluetooth 4.2. According to (Bluetooth, 2023)Bluetooth version 5 has four times the range of Bluetooth version 4.2 which is one area of improvement in Bluetooth. While limited Forward Error Correction (FEC)functionality in terms of (15,10) Hamming codes is present in the Bluetooth classic4.2 stack, however, it is not utilized in that version of Bluetooth. This thesis aims to implement a functionality in Bluetooth that uses FEC to increase the range. Before the experiments were conducted, multiple measurements were done in order to check if the hardware, such as the Bluetooth modules, antennas, air sniffer, could provide reliable and valid data. The experiments were conducted by streaming an audio sample of 48 kHz via Bluetooth and increasing the range until a certain percentage of fail rate in data transmission has occurred. FEC was then enabled, and the same experiment was repeated. The results from the experiments show that the range can be increased up to a few meters. Not only that, but the transmission without FEC allows a high level of errors without a connection cut-off. With FEC, the connection does not allow high levels of errors which means that the audio quality would not drop as low as it would have without FEC which means that a certain audio quality is preserved. This also makes the case for the implementation of higher modes of FEC into the Bluetooth stack to potentially increase the range of Bluetooth classic multiple times, but that implementation is beyond the scope of this thesis. 

    Download full text (pdf)
    fulltext
  • 21.
    Al-Areqi, Nadera
    et al.
    Jönköping University, School of Engineering, JTH, Department of Computing, Jönköping AI Lab (JAIL). Jönköping University, School of Engineering, JTH, Department of Computer Science and Informatics.
    Hanke, Martin
    Jönköping University, School of Engineering, JTH, Department of Computing, Jönköping AI Lab (JAIL). Jönköping University, School of Engineering, JTH, Department of Computer Science and Informatics.
    Thermal Estimation of Electric Machine Rotor using ML for Volvo Cars2024Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
    Abstract [en]

    This thesis investigates the application of machine learning techniques to predict rotor temperature in induction motors, a crucial parameter for enhancing the safety, efficiency, and longevity of electric machines. It focuses on the development, training, and evaluation of three neural network models: Multilayer Perceptron (MLP), Thermal Neural Network (TNN), and 1-D Convolutional Neural Network (1-D CNN). These models are assessed for their ability to predict rotor temperature using measurable inputs such as rotor speed, slip speed, current, voltage, and cooling conditions, both with and without stator temperature measurements.

    Experimental results show that the TNN model, which incorporates heat-transfer principles, outperforms other models in terms of accuracy and reliability. The analysis is based on a comprehensive dataset comprising 2,876,126 data points collected over approximately 82 hours, covering various operational scenarios represented by 87 profile IDs. The models were trained on rotor temperatures ranging from 21.6°C to 259.6°C, with 22°C representing idle room temperature and 250°C the rotor's critical threshold.

    The findings suggest that machine learning models offer a more adaptable and precise approach to temperature estimation in electric motors, with significant potential to improve operational efficiency and safety protocols in the automotive and industrial sectors. The TNN model was particularly effective, achieving mean squared errors of 4.2 and 23.3 in two different normal driving scenarios. Additionally, including motor housing temperature data, both inside and outside, significantly enhanced rotor temperature prediction accuracy, potentially reducing costs by eliminating the need for stator temperature sensors.

    Data collection and preprocessing were done in collaboration with Volvo Cars. Including motor housing temperature significantly improved rotor temperature estimation accuracy, suggesting cost savings by eliminating the need for stator temperature sensors. This research highlights the superiority of ML models over deterministic models for predicting EM temperature, enhancing safety, efficiency, and reliability. The TNN model’s versatility in various driving conditions sets the groundwork for future ML integration into real-time Motor Control Systems.

    This research demonstrates the superiority of machine learning models over deterministic models for induction motor temperature prediction, improving safety, efficiency, and reliability. The TNN model's ability to accurately predict rotor temperature under various conditions highlights the potential for integrating machine learning into real-time motor control systems, setting the stage for future advancements in this field.

    Download full text (pdf)
    fulltext
  • 22.
    Albaaj, Hassan
    et al.
    Jönköping University, School of Engineering, JTH, Computer Science and Informatics.
    Berggren, Victor
    Jönköping University, School of Engineering, JTH, Computer Science and Informatics.
    Benchmark av Containers och Unikernels2020Independent thesis Basic level (degree of Bachelor), 180 HE creditsStudent thesis
    Abstract [en]

    Purpose – The purpose of this paper is to explore the possibility to effectivize local networks and databases using unikernels and compare this to containers. This could also apply to reliability of executing programs the same way on different hardware in software development.

    Method – Two experiments have been performed to explore if the purpose could be realized, quantitative data have been gatheredand displayed in both cases. Python-scripts have been used to start C-scripts, acting client and server. Algorithms have been timed running in unikernels as well as in containers along with compared measurements of memory in multiple simultaneous instantiations.

    Findings – Intermittent response times spiked made the data hard to parse correctly. Containers had a lower average response time when running lighter algorithms. The average response times of unikernels dives below that of containers when heavier programs are simulated. Few minor bugs were discovered in Unikraft unikernels.

    Implications – unikernels havecharacteristics that make them more suitable for certain tasks compared to their counterpart, this is also true for containers. Unikraft unikernels are unstable which makes it seem like containers are faster during lighter simulations. Unikernels are onlyfaster and more secure if the tools used to build them does so in a manner that makes them stable.

    Limitations – The lack of standards, the lack of a support community together with the fact that unikernels is a small and niche field means that unikernels have a relatively high learning curve.

    Keywords – Unikraft, Unikernels, Docker, Container

    Download full text (pdf)
    fulltext
  • 23.
    Albazi, sogeta
    Jönköping University, School of Engineering, JTH, Department of Computer Science and Informatics.
    Evaluation of essay text analysis tool2021Independent thesis Basic level (degree of Bachelor), 180 HE creditsStudent thesis
    Abstract [en]

    Scoring essays in upper secondary schools in Sweden is a demanding process and requires time and effort by teachers. Teachers have some scoring criteria that they should fulfill while scoring the essay.  The existing automated essay scoring systems cannot be used by the teachers since they do not fulfill all these criteria. Therefore, a tool is needed to assist teachers in scoring the essays by highlighting the important parts of the essay that teachers should consider. A text analysis tool is developed in order to assist teachers in scoring essays by analyzing the text and providing the weakness of the essays. The tool makes use of natural language processing, machine learning, probabilistic and rule-based methods to detect the grammatical errors in the essays. The aim of the thesis is to evaluate the efficiency of the tool in reducing the time spent on scoring essays. The methodology used is design science research to achieve the aim of the thesis. For the evaluation of the tool, in total 20 essays were scored using the text analysis tool. The results of the evaluation, 80 showed a significant difference in the time spent on scoring essays with using the tool.

  • 24.
    Albertsen, Thomas
    et al.
    Jönköping University, School of Engineering, JTH. Research area Information Engineering.
    Sandkuhl, Kurt
    Jönköping University, School of Engineering, JTH. Research area Information Engineering.
    Seigerroth, Ulf
    Jönköping University, School of Engineering, JTH. Research area Information Engineering.
    Tarasov, Vladimir
    Jönköping University, School of Engineering, JTH. Research area Information Engineering. Jönköping University, School of Engineering, JTH, Computer Science and Informatics, JTH, Jönköping AI Lab (JAIL).
    Modelling Network-based Defence: Success and Failure of an Enterprise Modelling Endeavour2010In: The Practice of Enterprise Modeling: Third IFIP WG 8.1 Working Conference / [ed] Patrick Van Bommel, Stijn Hoppenbrouwers, Sietse Overbeek, Erik Proper, Joseph Barjis, Berlin: Springer , 2010, p. 121-129Conference paper (Refereed)
    Abstract [en]

    Research projects have an inherent risk of failure, and learning howto cope with the risk is an important task for everyone involved. In order to doso it is necessary to share the knowledge of the experiences done during andafter the project. This paper investigates a recently completed enterprisemodeling research project and contributes with lessons learned andrecommendations for future enterprise modeling projects.

  • 25.
    Albertsen, Thomas
    et al.
    Jönköping University, School of Engineering, JTH. Research area Information Engineering.
    Sandkuhl, Kurt
    Jönköping University, School of Engineering, JTH. Research area Information Engineering.
    Seigerroth, Ulf
    Jönköping University, School of Engineering, JTH. Research area Information Engineering.
    Tarasov, Vladimir
    Jönköping University, School of Engineering, JTH. Research area Information Engineering. Jönköping University, School of Engineering, JTH, Computer Science and Informatics, JTH, Jönköping AI Lab (JAIL).
    The Practice of Competence Modelling2010In: The Practice of Enterprise Modeling: Third IFIP WG 8.1 Working Conference / [ed] Patrick Van Bommel, Stijn Hoppenbrouwers, Sietse Overbeek, Erik Proper, Joseph Barjis, Berlin: Springer , 2010, p. 106-120Conference paper (Refereed)
    Abstract [en]

    A clear understanding of the organizational competences of anenterprise and the underlying individual competences and the competencedevelopment needs has become more and more important for many industrialareas as a foundation for competence supply processes and adjustment tochanging market conditions. Competence modelling, i.e. the use of enterprisemodelling techniques for capturing existing and describing desiredorganisational and individual competences in enterprises, offers importantcontributions to this. In the last years, the authors of the paper have performed anumber of competence modelling cases, which revealed different characteristicsand resulted in lessons learned. This paper presents an examination of differentcharacteristics of competence modelling cases, and recommendations andlessons learned from these cases for the practice of competence modelling.

  • 26.
    Albertsen, Thomas
    et al.
    Jönköping University, School of Engineering, JTH. Research area Information Engineering.
    Sandkuhl, Kurt
    Jönköping University, School of Engineering, JTH. Research area Information Engineering.
    Tarasov, Vladimir
    Jönköping University, School of Engineering, JTH. Research area Information Engineering. Jönköping University, School of Engineering, JTH, Computer Science and Informatics, JTH, Jönköping AI Lab (JAIL).
    Towards Competence Modeling and Competence Matching for Network-based Defense2007In: Proc. The 3rd International Conference on Military Technology, MilTech3, June 2007, Stockholm, 2007Conference paper (Other academic)
  • 27.
    Albertsen, Thomas
    et al.
    Jönköping University, School of Engineering, JTH. Research area Information Engineering.
    Sandkuhl, Kurt
    Jönköping University, School of Engineering, JTH. Research area Information Engineering.
    Tarasov, Vladimir
    Jönköping University, School of Engineering, JTH. Research area Information Engineering. Jönköping University, School of Engineering, JTH, Computer Science and Informatics, JTH, Jönköping AI Lab (JAIL).
    Towards Competence Modeling and Competence Matching for Network-Based Defense2008In: Stockholm contributions in Military-Technology 2007 / [ed] M. Norsell, Stockholm: Swedish National Defence College , 2008, p. 9-22Chapter in book (Other academic)
  • 28.
    Albertsen, Thomas
    et al.
    Jönköping University, School of Engineering, JTH. Research area Information Engineering.
    Seigerroth, Ulf
    Jönköping University, School of Engineering, JTH. Research area Information Engineering.
    Sandkuhl, Kurt
    Jönköping University, School of Engineering, JTH. Research area Information Engineering.
    Tarasov, Vladimir
    Jönköping University, School of Engineering, JTH. Research area Information Engineering. Jönköping University, School of Engineering, JTH, Computer Science and Informatics, JTH, Jönköping AI Lab (JAIL).
    Competence demand modeling: case study2009Report (Other academic)
  • 29.
    Albertsen, Thomas
    et al.
    Jönköping University, School of Engineering, JTH. Research area Information Engineering.
    Tarasov, Vladimir
    Jönköping University, School of Engineering, JTH. Research area Information Engineering. Jönköping University, School of Engineering, JTH, Computer Science and Informatics, JTH, Jönköping AI Lab (JAIL).
    Sandkuhl, Kurt
    Jönköping University, School of Engineering, JTH. Research area Information Engineering.
    Seigerroth, Ulf
    Jönköping University, School of Engineering, JTH. Research area Information Engineering.
    Competence modeling and matching: frame concept2009Report (Other academic)
  • 30.
    Albertsen, Thomas
    et al.
    Jönköping University, School of Engineering, JTH. Research area Information Engineering.
    Tarasov, Vladimir
    Jönköping University, School of Engineering, JTH. Research area Information Engineering. Jönköping University, School of Engineering, JTH, Computer Science and Informatics, JTH, Jönköping AI Lab (JAIL).
    Sandkuhl, Kurt
    Jönköping University, School of Engineering, JTH. Research area Information Engineering.
    Seigerroth, Ulf
    Jönköping University, School of Engineering, JTH. Research area Information Engineering.
    Modellering av 312. luftburna kompaniet: KOMO - Projektrapport2009Report (Other academic)
  • 31.
    Alexandersson, Josua
    et al.
    Jönköping University, School of Engineering, JTH, Department of Computer Science and Informatics.
    Persson, Jesper
    Jönköping University, School of Engineering, JTH, Department of Computer Science and Informatics.
    Utforskning utav Linux roll i att Accelerera Tid till Marknaden för Inbyggda System2023Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    How can Linux reduce the time required for development in embedded systems, and what makes Linux appealing to embedded developers despite the loss in overall control? Through qualitative interviews with industry professionals and a systematic literature review, challenges and benefits of using Linux in embedded systems development were identified and discussed. Three hypotheses were formulated based on recurring topic agreement among the interview subjects: Reduced development time through the use of open-source solutions, struggles with real-time and security requirements, and challenges within troubleshooting and dependency management. The empirical data observed primarily aligned with the professional perception indicating the potential for development time reduction leveraging resources properly. However also highlighting additional challenges that are not present in traditional embedded system development. Several trade-offs were observed from the findings, including increased overhead and licensing concerns. Further research is required to fully understand the advantages, challenges and limits associated with Linux in an embedded system environment. This study provides valuable insights for future exploration within the field. 

    Download full text (pdf)
    fulltext
  • 32.
    Alfvén, Mikaela
    et al.
    Jönköping University, School of Engineering, JTH, Department of Computer Science and Informatics.
    Creutz, Amanda
    Jönköping University, School of Engineering, JTH, Department of Computer Science and Informatics.
    Web Accessibility and Search Engine Optimization: an investigation on the implementation and its effect within e-commerce websites in Sweden2021Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    With the digital world we live in today, inclusion on the web is crucial. Ensuring all who want to access the web can do so is a responsibility that can be vague. As prior research has shown that making a website accessible is a low prioritized matter because of time and money, but also lack of knowledge, the purpose with this thesis was to find out if factors used for search engine optimization could cater to web accessibility. There is a general understanding that there are overlapping factors between the two concepts. Since search engine optimization is a desired and successful part of providing a website with traffic, an overlap should improve accessibility. To understand in what way the search engine optimization factors could affect the accessibility of a webpage as a whole, with this thesis we go into the context of implementation by interviewing web professionals. As this thesis will show, there are multiple aspects needed to be taken into consideration when measuring to what extent the overlapping factors affect website performance in regards to accessibility. Factors like the clients, thoughts about responsibility, experience and even personal interest come into play. The method used was qualitative where we analysed the data with a thematic analysis and descriptive statistics. The data collection had three parts: a survey, an in-depth interview with a few of the participants from the survey, and finally a web performance test. The latter was performed by Siteimprove crawl, which administers one of the top accessibility ranking tools online. The general indication was that we cannot draw a conclusion to the benefit of it being enough to just implement the SEO factors that overlap. Although, this investigation provides an insight into to what extent web professionals are implementing the overlapping factors between search engine optimization and web accessibility, and what other aspects may influence web performance.

    Download full text (pdf)
    fulltext
  • 33.
    Al-Ghareeb, Meelad
    Jönköping University, School of Engineering, JTH, Computer Science and Informatics.
    Vibration exposure model for human operators working with chainsaw equipment.2018Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
    Download full text (pdf)
    fulltext
  • 34.
    Al-Ghareeb, Meelad
    et al.
    Jönköping University, School of Engineering, JTH, Computer Science and Informatics.
    Antranik, Sevag
    Riktlinjer för grafiska användargränssnitt för lagersystem2016Independent thesis Basic level (university diploma), 10 credits / 15 HE creditsStudent thesis
    Abstract [sv]

    Syftet med denna rapport är att undersöka och sammanställa riktlinjer för att utveckla ett grafiskt användargränssnitt för ett lagersystem. För att uppnå syftet med rapporten litteraturstudier, intervjuer, observationer och en prototyputveckling utfördes. Utifrån litteraturstudier visade det sig att det inte fanns specifika designriktlinjer för utveckling av lagersystem fast det fanns allmänna riktlinjer som kan användas för design av olika system. Intervjuer med utvecklare och en utvecklingschef på företaget Qsys hjälpte till att hitta befintliga riktlinjer som företaget använder. Det visade sig att de använder allmänna riktlinjer som inte är specifika för lagersystem. För att hitta mer specifika riktlinjer observerade vi några lagerarbetare för att bättre förstå hur de integrerar med det befintliga systemet som de använder. Utifrån analysen av observationerna, upptäcktes det nya riktlinjer. Med hjälp av de allmänna riktlinjer som hittades i litteraturen och riktlinjer som upptäckes efter analysen av observationer, utvecklade vi en prototyp som sedan testades. Resultatet vi fick utifrån analysen av intervjuerna med lagerarbetarna efter prototyptestning, hjälpte med att hitta ytterligare specifika riktlinjer.För att utveckla ett användarvänligt lagersystem, behöver man ett användarvänligt gränssnitt. I denna rapport presenterar vi några riktlinjer som man kan använda sig av för att utveckla ett användarvänligt gränssnitt för lagersystem.

    Download full text (pdf)
    fulltext
  • 35.
    Alhaj Kasem, Mustafa
    et al.
    Jönköping University, School of Engineering, JTH, Department of Computer Science and Informatics.
    Andersson, Daniel
    Jönköping University, School of Engineering, JTH, Department of Computer Science and Informatics.
    Locating faults in boundary wires for autonomous lawn mowers: An investigative study on methods used to locate faults in underground, low-voltage cables with focus on implementing Time Domain Reflectometer (TDR)2021Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    Purpose:The purpose of this thesis was to identify a useful solution to find the location of a broken boundary wire. By useful we mean that the solution should be inexpensive, user friendly and accurate. However, this thesis will only investigate the accuracy of the method where the hypothesis is that an investigated method is applicable for all underground wires.

    Method:This study conducted a literature research in order to investigate what methods that are used in other industries to locate faults in underground, low-voltage electrical wires. After the research, the most commonly used fault locating methods were described and the one that seemed most useful was chosen as a possible solution.For the solution to be useful the accuracy was investigated. The method used to conduct an experiment and gather data to validate the solution was Design Science Research.

    Result:Three methods were investigated as possible solutions:Time Domain Reflectometry (TDR), Frequency Domain Reflectometry (FDR) and Murray bridge where experiments were conducted using TDR.TDR proved to be unapplicable in locating faults in boundary wires, although it was confirmed to be a valid solution to locate faults in coaxial cables with <1% error margin.What makes TDR and other reflectometry methods unsuitable methods within the autonomous lawn mower industry is the lack of characteristic impedance in the used boundary wires. The hypothesis that an investigated method is applicable for all underground wires is thereby refuted.

    Limitations:Experiments were conducted in laboratory environment with a signal generator and an oscilloscope. One experiment was conducted on a boundary wire in the ground which provided no reflected signal.

    Download full text (pdf)
    Locating faults in boundary wire.
  • 36.
    Al-Hufah Al-Otaibi, Abdulmalek
    et al.
    Jönköping University, School of Engineering, JTH, Department of Computer Science and Informatics.
    Kiaee, Kiarash
    Jönköping University, School of Engineering, JTH, Department of Computer Science and Informatics.
    Exploring the Impact of Dynamic Design Elements on User Experience in Digital Interfaces: Understanding the Role of Dynamic Elements2024Independent thesis Basic level (degree of Bachelor), 180 HE creditsStudent thesis
    Abstract [en]

    This study seeks to investigate the subtle impact that dynamic design elements in web interfaces have on users, particularly on users' decision-making and engagement. In contrast to most current research efforts, which predominantly address mobile applications, the current study aims to direct the focus on web-based environments to reveal special behavioral responses evoked by dynamic design features.

    The study adopts a comprehensive mixed-methods approach that encompasses qualitative and quantitative data collection techniques. This includes A/B testing on the prototypes of web interfaces, which provides the base for measuring engagement objectively from users. A very salient point here is that animations increase user retention by 30%, which shows that well-applied dynamic elements can advance the stickiness and interaction users would have with a digital platform.

    On the other hand, the thesis also mentions the risks related to such design elements, like the ability to cause cognitive overload and distraction in case of non-judicious use of these elements. Through the account of user behavioral analysis in response to various implementations, the research provides useful insights to web designers and developers about how to use animations and transitions judiciously for navigational intuitiveness and responsiveness without hampering web interface usability.

    The present research also adds to theories for UX and user interface design (UID) by promoting the balanced integration of dynamic design elements. What was brought to the forefront was that research to understand the specific impacts of these elements can lead to more effective digital environments, tailored to foster user engagement that could support efficient processes of decision making. This thesis not only fills the academic gap related to digital interaction but also provides a practical guideline for the improvement of web interface design given user behavior and technology.

    Download full text (pdf)
    fulltext
  • 37.
    Ali Fareedi, Abid
    et al.
    Jönköping University, School of Engineering, JTH, Computer and Electrical Engineering.
    Tarasov, Vladimir
    Jönköping University, School of Engineering, JTH. Research area Information Engineering. Jönköping University, School of Engineering, JTH, Computer Science and Informatics, JTH, Jönköping AI Lab (JAIL).
    Modelling of the Ward Round Process in a Healthcare Unit2011In: The Practice of Enterprise Modeling: 4th IFIP WG 8.1 Working Conference, PoEM 2011 Oslo, Norway, November 2-3, 2011 Proceedings / [ed] Paul Johannesson, John Krogstie and Andreas L. Opdahl, Springer Berlin/Heidelberg, 2011, Vol. 92, p. 223-237Conference paper (Refereed)
    Abstract [en]

    Information systems (IS) are nowadays extensively used to support all kinds of activities in healthcare organisations. Enterprise modelling can help to make the use of IS in healthcare more effective by providing process and domain models reflecting a particular healthcare unit. This paper proposes a model of the ward round process in a healthcare unit. The proposed model identifies the roles of medical professionals, tasks that can be performed according to the personnel’s competences, and activities that are carried out as part of the tasks to achieve goals of the ward round process. A formal approach has been used to implement the modelling results in the form of an ontology. Such formal ontologies can support improvement and development of IS in healthcare. We learned that modelling workshops are important for development of models that can be formalized in a machine-readable form.

    Download full text (pdf)
    Publisher's PDF
  • 38.
    Alirezaie, Marjan
    et al.
    Örebro University.
    Hammar, Karl
    Jönköping University, School of Engineering, JTH, Computer Science and Informatics, JTH, Jönköping AI Lab (JAIL).
    Blomqvist, Eva
    SICS - East Swedish ICT.
    SmartEnv as a Network of Ontology Patterns2018In: Semantic Web, ISSN 1570-0844, E-ISSN 2210-4968, Vol. 9, no 6, p. 903-918Article in journal (Refereed)
    Abstract [en]

    In this article we outline the details of an ontology, called SmartEnv, proposed as a representational model to assist the development process of smart (i.e., sensorized) environments. The SmartEnv ontology is described in terms of its modules representing different aspects including physical and conceptual aspects of a smart environment. We propose the use of the Ontology Design Pattern (ODP) paradigm in order to modularize our proposed solution, while at the same time avoiding strong dependencies between the modules in order to manage the representational complexity of the ontology. The ODP paradigm and related methodologies enable incremental construction of ontologies by first creating and then linking small modules. Most modules (patterns) of the SmartEnv ontology are inspired by, and aligned with, the Semantic Sensor Network (SSN) ontology, however with extra interlinks to provide further precision and cover more representational aspects. The result is a network of 8 ontology patterns together forming a generic representation for a smart environment. The patterns have been submitted to the ODP portal and are available on-line at stable URIs.

    Download full text (pdf)
    fulltext
  • 39.
    Alirezaie, Marjan
    et al.
    Örebro Universitet.
    Hammar, Karl
    Jönköping University, School of Engineering, JTH, Computer Science and Informatics, JTH, Jönköping AI Lab (JAIL). RISE SICS East AB, Linköping, Sweden.
    Blomqvist, Eva
    Linköpings Universitet.
    Nyström, Mikael
    Linköpings Universitet.
    Ivanova, Valentina
    Linköpings Universitet.
    SmartEnv Ontology in E-care@home2018In: SSN 2018 - Semantic Sensor Networks Workshop: Proceedings of the 9th International Semantic Sensor Networks Workshopco-located with 17th International Semantic Web Conference (ISWC 2018) / [ed] Maxime Lefrançois, Raúl Garcia Castro, Amélie Gyrard, Kerry Taylor, CEUR-WS , 2018, Vol. 2213, p. 72-79Conference paper (Refereed)
    Abstract [en]

    In this position paper we briefly introduce SmartEnv ontology which relies on SEmantic Sensor Network (SSN) ontology and is used to represent different aspects of smart and sensorized environments. We will also talk about E-carehome project aiming at providing an IoT-based health-care system for elderly people at their homes. Furthermore, we refer to the role of SmartEnv in Ecarehome and how it needs to be further extended to achieve semantic interoperability as one of the challenges in development of autonomous health care systems at home.

    Download full text (pdf)
    fulltext
  • 40.
    Alklind Taylor, A. -S
    et al.
    School of Informatics, University of Skövde, Skövde, Sweden.
    Nalin, K.
    School of Informatics, University of Skövde, Skövde, Sweden.
    Holgersson, J.
    School of Informatics, University of Skövde, Skövde, Sweden.
    Gising, A.
    RISE Research Institutes of Sweden, Gothenburg, Sweden.
    Ferwerda, Bruce
    Jönköping University, School of Engineering, JTH, Department of Computer Science and Informatics.
    Chen, L.
    RISE Research Institutes of Sweden, Gothenburg, Sweden.
    Guardian Angel: Using Lighting Drones to Improve Traffic Safety, Sense of Security, and Comfort for Cyclists2023In: Lecture Notes in Computer Science: 25th International Conference on Human-Computer Interaction, HCII 2023 / [ed] Duffy, V.G., Krömker, H., A. Streitz, N., Konomi, S., Springer, 2023, Vol. 14057, p. 209-223Conference paper (Refereed)
    Abstract [en]

    Active mobility, such as biking, faces a common challenge in Swedish municipalities due to the lack of adequate lighting during the dark winter months. Insufficient lighting infrastructure hinders individuals from choosing bicycles, despite the presence of well-maintained bike paths and a willingness to cycle. To address this issue, a project has been undertaken in the Swedish municipality of Skara for an alternative lighting solution using drones. A series of tests have been conducted based on drone prototypes developed for the selected bike paths. Participants were invited to cycle in darkness illuminated by drone lighting and share their mobility preferences and perception. This paper summarizes the users’ perception of drone lighting as an alternative to fixed lighting on bike paths, with a special focus on the impact on travel habits and the perceived sense of security and comfort. Most participants were regular cyclists who cited bad weather, time, and darkness as significant factors that deterred them from using bicycles more frequently, reducing their sense of security. With drone lighting, the participants appreciated the illumination’s moonlight-like quality and its ability to enhance their sense of security by illuminating the surroundings. On the technology side, they gave feedback on reducing the drone’s sound and addressing lighting stability issues. In summary, the test results showcase the potential of drone lighting as a viable alternative to traditional fixed lighting infrastructure, offering improved traffic safety, sense of security, and comfort. The results show the feasibility and effectiveness of this innovative approach, supporting transformation towards active and sustainable mobility, particularly in regions facing lighting challenges.

  • 41.
    Alnervik, Tilda
    et al.
    Jönköping University, School of Engineering, JTH, Computer Science and Informatics.
    Ma, Gerui
    Jönköping University, School of Engineering, JTH, Computer Science and Informatics.
    Success factors in an introductory programming course in a non-CS major2020Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    Purpose – The contradiction of the increased demand for IT specialists and the decrease of the enrollment in programming courses at universities worldwide has been discussed over the years. To tackle the problem, researchers and teachers in computing education have investigated various success factors in introductory programming courses, mostly within the context of computer science. This paper focuses on the investigation of success factors for students that are not majoring in computer science (non-CS) in an introductory programming course, to report on the results of student's performance and analysis of the most relevant success factors, also provide suggestions that could be considered for the course design and teaching method.

     

    Method – The methods used to carry out the study are a survey with 36 participants, conducted before the start of an introductory programming course, and qualitative interviews conducted with twelve students after the end of the course. The interviews were then analysed thematically to find common patterns for five success factors between the students with different grades. The success factors that were examined are math background, previous programming experience, comfort level, motivation and attribution to success.

     

    Findings – Math background could not be proved as a success factor in this study due to the lack of a standardized assessment of the students’ math levels. Previous programming experience could be regarded as a success factor but not as dominant as the success factor motivation, which has shown clear patterns in the data. Comfort level could be seen as one of the success factors as well, as most of the data in this study support this conclusion. Lastly, attribution to success as a success factor could not be supported by this study; the qualitative data showed variety which makes it hard to draw a conclusion directly.

     

    Implications – The study suggest increasing the motivation for the non-CS students in introductory programming by combining programming with other subjects in the programme. The lecturer could customize the course for students with different interests so they could select a path and adapt the knowledge to their needs. Bridging courses and various forms of mentoring are also recommended to offer.

     

    Limitations – The time frame of the study limited the amount of data that could be collected. The study was conducted with students from only one university and one non-CS programme, with a small data sample for analysis, which is limiting in the way the results can be generalized.

    Download full text (pdf)
    fulltext
  • 42.
    Al-Nuaimi, Ibraheem
    et al.
    Jönköping University, School of Engineering, JTH, Computer Science and Informatics.
    Andersson, Emil
    Jönköping University, School of Engineering, JTH, Computer Science and Informatics.
    Vehicle Classification Using Point Cloud & Deep Learning2020Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    AI and machine learning have grown exponentially over the last couple of years. Today, many problems can be solved or improved using this technology. For instance, neural networks have proven to be highly efficient in regard to classifying objects in video sequences or images. Most often, 2D data is used in these applications. In recent years, major advancements have been made in equipment that can generate 3D data. Thus, adding an additional dimension which could potentially help improve tasks like object classification. This thesis evaluates 3D data in the form of point clouds generated by stereo cameras, we present two vehicle classification neural networks, both based on point clouds. Our first network is referred to as the 3D model. This model uses raw point cloud data as input, thus fully utilizing the information point clouds provides. The second network is referred to as the 2D model and bases its input on projections from point clouds. The 3D model is based on the architecture of PointNet: a network developed by the pioneers of deep neural networks on raw point cloud data. We utilize their approach on applying deep learning directly over irregular point clouds without any conversion. In particular, applying a Multi-Layer-Perceptron network and a symmetric function on each point. The 2D model is based on the architecture of another well-known network called VGG16. This model uses 2D images as input. The images are generated by converting point clouds into voxels and calculating a density value in each voxel. We evaluate the performance of each created model separately to identify strength and weaknesses. Moreover, we assess whether raw point clouds can achieve on par or better performance than projected point clouds. Empirically, both proposed models show strong performance in the task of classifying vehicles, exceeding an accuracy of 98%. Furthermore, both models are lightweight in terms of network parameters and fast in regard to inference time. In this thesis, we show that raw 3D point cloud data is as effective as 2D image data when used as input and requires less pre-processing. Furthermore, we show that relatively few points are required as input to ensure reliable classifications. We conclude that no model is superior to the other as evaluation shows that both models are relatively equal in performance.

  • 43.
    Alsaadi, Anas
    Jönköping University, School of Engineering, JTH, Department of Computer Science and Informatics.
    User Experience of Web-based vs. Desktop-based Microsoft Excel Applications.: Comparative thesis between two platforms within a single application.2024Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
    Download full text (pdf)
    fulltext
  • 44.
    Alsaadi, Noor Aldin
    et al.
    Jönköping University, School of Engineering, JTH, Department of Computer Science and Informatics.
    Ahmadi, Milad
    Jönköping University, School of Engineering, JTH, Department of Computer Science and Informatics.
    Harnessing IMU Data for Enhanced Exoskeletons in Professional Forestry Operations2024Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    This thesis aims to enhance analysis of Inertial Measurement Unit (IMU) data in context of professional forestry operations. The experiment involved mounting an IMU on a passive exoskeleton, capturing real-time movement data during forestry activity, and then the data was analysed both with and without machine learning.

    As a result, different back angle movement patterns has been identified using graphs on Euler angles which came from IMU sensor. And also AI model had over 60% of accuracy for all movements except for one, indicating a need for refinement, through more participants, better sensor attachment and combining other sensors. The findings from this thesis will guide future research, particularly for ergonomic specialist students and also mechanical students to develop an active exoskeleton. In conclusion, using IMU data with exoskeletons can improve worker safety and reduce ergonomic risks in forestry by informing the user of  their posture.

    Download full text (pdf)
    Thesis
  • 45.
    Amin, Skorupan
    Jönköping University, School of Engineering, JTH, Computer Science and Informatics.
    Eyetracking som interaktions-hjälpmedel i fordon: Utveckling och utvärdering av ett ögonstyrt infotainmentsystem2018Independent thesis Basic level (degree of Bachelor), 12 HE creditsStudent thesis
    Abstract [en]

    The purpose of this study was to develop and evaluate a new eye-controlled infotainmentsystem that worked differently compared to similar systems. What differs this new system is that personal calibration is not necessary to be performed before each time the system is to be used.

    The method Design Science Research (DSR) has been used where an artifact has been developed and then investigated. Experiments have been conducted to find out how well the infotainment system works when it uses a relative gaze towards an absolute, but also to find out how users should confirm their gaze in the best way. For confirmation of gaze, three different methods have been used; button press, blink, and gazing. The collected data from the experiments have been matched to evaluate how well they stand against each other.

    The result of the study shows that when the infotainment system used relative gaze, it worked in as many attempts as it did using absolute. The result times were very similar to each other which shows that the both methods works well even when face calibration is not used, but the collected data was uneven which made it difficult to draw conclusions about which one was faster. The study also shows that keystroke was the best-suited method to use to confirm gaze.This method was much faster than other methods.

    A limitation of the study has been that data collection was only done on two occasions. On more occasions more data could have been generated, which would have made it easier to draw more conclusions about the response times.

    Download full text (pdf)
    fulltext
  • 46.
    Anders, Angrén
    et al.
    Jönköping University, School of Engineering, JTH, Computer Science and Informatics.
    Jonathan, Pettersson
    Jönköping University, School of Engineering, JTH, Computer Science and Informatics.
    Att skydda BLDC motorer mot oaktsam användning: Övervakning av temperatur i statorlindningar för handhållna produkter2020Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    Purpose – The purpose of this study was to develop a sensorless model that calculates anestimated temperature in a stator winding of a BLDC motor, to investigate how well it is possibleto protect handheld products from inadvertent use and to be able to counteract operation underhigh temperatures, which could prolong service life of the handheld products.

    Method – This study has used the research method Design Science Research to develop anartifact that sensorlessly estimates temperature in a BLDC motor's stator windings. Theperformance of the artifact for the estimated temperature is accuracy, precision, andconvergence time, which was evaluated by analysing quantitative data collected during differentexperiments.

    Findings – The artifact developed in the study is based on a combination of Current Injectionand Lumped Parameter Thermal Network and a Kalman Filter, the performance of the artifactdid not meet Husqvarna AB's requirements.

    The precision and accuracy of the artifact for estimating temperature in a statorwinding of a BLDC motor was 7,2 °C ± 23,8 °C and its convergence time was 7,3 sfor its mean and 18,4 s for its precision.

    Implications – This study and its results can be used as a reference regarding how well acombination of Current Injection, Lumped Parameter Thermal Network and Kalman Filter canestimate the temperature in stator windings for non-salient BLDC motors with a resistance of20 mΩ, inductance of 10 uH, nominal speed of ~20 000 RPM with termination of the Deltatype.

    Limitations – The limitations of the study are listed below.

    1. The development time for the artifact was performed for a limited time.
      • Which has contributed to less optimization of the artifacts.
      • Which has contributed to fewer iterations of artifacts.
    2. The artifact is evaluated only on VESC hardware and its software as a basis.
      • The performance of the artifact is affected by the accuracy and precision inmeasuring current and voltage.
    3. The experiments performed were limited.
      • Had the intervals at which the experiments were performed regardingtemperature, speed and dynamic load been greater, the performance of theartifact could have been examined in more real conditions. A better brakebench and a climate chamber would be used.
    4. Only one BLDC motor was evaluated.
      • Evaluation of more motors could show differences in the performance of theartifact between different smaller motors, that is, show its general applicability.
    5. Analysis of the performance of the artifact in convergent states alone was notperformed.
      • Which could show if the performance of the artifact could fulfill HusqvarnaAB's requirements if the analysis were only performed in convergingconditions.

    Keywords – Estimate Temperature, BLDC Motor, Stator Windings, Current Injection,Lumped Parameter Thermal Network, Kalman Filter, VESC

    Download full text (pdf)
    fulltext
  • 47.
    Andersson, Adam
    Jönköping University, School of Engineering, JTH, Computer Science and Informatics.
    Utveckling av testverktyg för mjukvara med fysiska komponenter2018Independent thesis Basic level (university diploma), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    A lot of time is spent on manual software testing. When software can interact with exponentially more and more components the number of tests required will increase at the same rate. Automation of these manual tests has been previously shown that a time-saving can occur with test automation. When tests need to be done on software that interacts with physical components the results of testing automation are harder to predict. This thesis aims to explain the impact of physical components on the development and the result of test tools developed for use on automated tests on objects with physical components. In this work, a test tool for automatic regression testing for height adjustable table legs were developed. The method used to design the tool was Design Science Research where, for example, TESLA was adapted for use in automated tests with physical components. TESLA is a language for specifying test cases and allowing test automation with embedded systems that was implemented in the test tool's design which could be used to automatically generate scripts and automatically executes test cases. With the development and design of the testing tool, the thesis attempted to answer how a test tool should be designed when physical components are included in the test object and how the measurement accuracy of the tool may affect the test result. Experiments have been carried out during the development process where regression tests have been performed according to a test protocol. During these experiments a test protocol is executed. One manually by hand and one is done automatically with the testing tool. The results of the experiments show that the execution of the test protocol execution with the test tool gave a time saving of 35% compared to the manual tests. The physical components of the test object were shown to affect the automatic execution time negative and further analysis of previous research has shown that this result is insufficient to justify the large initial time that is required to automate tests.

    Download full text (pdf)
    fulltext
  • 48.
    Andersson, Adam
    et al.
    Jönköping University, School of Engineering, JTH, Computer Science and Informatics.
    Gårdenheim, Simon
    Jönköping University, School of Engineering, JTH, Computer Science and Informatics.
    Josefsson, Anton
    Jönköping University, School of Engineering, JTH, Computer Science and Informatics.
    Informationssäkerhet: Informell säkerhet inom informationssäkerhetsrevisioner2020Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    Informal security is a subcategory of information security that includes people's attitudes, perceptions and values. Although information security audits are regularly performed towards organizations, it is unclear how much informal security is applied in these audits. The purpose of this study is to examine informal security and how it is applied in information security audits by organizations. This is done through thematic analysis of semi-structured interviews. The results of the study show that there is a lack of awareness regarding informal security in organizations. The priorities of these organizations are instead technical security. What the study highlights is the importance of informal security and that it should be given the same amount of attention as the technical safety aspects. The study concludes that more research is needed about the subject informal security but also how informal security relates to organizational culture. There are several areas of improvement within the study, mostly linked to awareness and educational efforts. However, the fundamental area of improvement was identified as organizations realizing the importance of informal security.

    Download full text (pdf)
    Informationssäkerhet - Informell säkerhet inom informationssäkerhetsrevisioner
  • 49.
    Andersson, Albin
    et al.
    Jönköping University, School of Engineering, JTH, Computer Science and Informatics.
    Arfvidsson, Olle
    Jönköping University, School of Engineering, JTH, Computer Science and Informatics.
    Hantering av legacy-system vid migreringar till molnet: Kvalitativ intervjustudie angående utmaningar vid migreringarav äldre IT-system till molnlösningar inom svenska IT-sektorn2020Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    This study investigates the phenomenon legacy-system migration to cloud solutions.Legacy-systems are described as an outdated IT-system which still uses older types oftechnology even though more modern technology is available. These systems areusually found in older ERP-systems, as well as in warehouses and productionenvironments.

    Based on previous research in the field, a gap was identified in the literature on howSwedish consulting companies in the IT-sector handle and implement migrations oflegacy-systems to cloud solutions. This study applied a qualitative interview study withsemi-structured interview form and a thematic analysis was conducted. Literature wasalso collected around previously documented challenges and methods for creating basicunderstanding of the subject.

    The study aims to identify challenges, methods, and the management of challenges IT consultants face in their work. The study presents a total of three different methods,first a feasibility study on migration, then two different method choices, Rehost andReplace. Furthermore, a total of nine different challenges are presented, as well as whattechnical measures consultants perform in handling them. The study also contributes toincreasing the number of studies towards the industry by examining in more dept thework of Swedish consultants on the migration of legacy-systems.

    Download full text (pdf)
    fulltext
  • 50.
    Andersson, Andreas
    et al.
    Jönköping University, School of Engineering, JTH, Computer Science and Informatics.
    Ottehall, Henrik
    Jönköping University, School of Engineering, JTH, Computer Science and Informatics.
    Rekommendationssystem för riktad annonsering: En studie av innehållsbaserad rekommendation i system med användare, element och annonser kopplade till en gemensam uppsättning diskreta metadata2017Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    Advertising in mobile apps are increasing and so is the need to show the right ad to the right user. This study was conducted in cooperation with Seekly AB, a company whose app displays a feed with upcoming events in a users immediate area. In this app, every event is associated with an interest and users can choose interests to follow in a list. Seekly wanted to use so called behavioral targeting to show ads in their feed. The solution that was developed is useful for all Seekly-like systems and consists of a content based recommender system that chooses ads based on the interests a user has selected and events and ads that the user has shown an interest in. Apps that in some way or another resembles the Seekly app are not uncommon and recommender systems for behavioral targeting suited for this kind of system are to the best of our knowledge not described in the literature. The resulting recommender system has been implemented and shown to be able to recommend ads that has been associated with interests that match the interests selected by the user and/or amplified by his or her behavior. There are also indications that the system would be able to increase the number of ad clicks compared to randomly selected ads, but no statistically significant proof was found.

    Download full text (pdf)
    fulltext
1234567 1 - 50 of 867
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf