12 1 - 20 of 33
rss atomLink 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
  • Public defence: 2024-04-12 10:15 Karlskrona
    Iftikhar, Umar
    Blekinge Institute of Technology, Faculty of Computing, Department of Software Engineering.
    Towards Measuring & Improving Source Code Quality2024Licentiate thesis, comprehensive summary (Other academic)
    Abstract [en]

    Context: Software quality has a multi-faceted description encompassing several quality attributes. Central to our efforts to enhance software quality is to improve the quality of the source code. Poor source code quality impacts the quality of the delivered product. Empirical studies have investigated how to improve source code quality and how to quantify the source code improvement. However, the reported evidence linking internal code structure information and quality attributes observed by users is varied and, at times, conflicting. Furthermore, there is a further need for research to improve source code quality by understanding trends in feedback from code review comments.

    Objective: This thesis contributes towards improving source code quality and synthesizes metrics to measure improvement in source code quality. Hence, our objectives are 1) To synthesize evidence of links between source code metrics and external quality attributes, & identify source code metrics, and 2) To identify areas to improve source code quality by identifying recurring code quality issues using the analysis of code review comments.

    Method: We conducted a tertiary study to achieve the first objective, an archival analysis and a case study to investigate the latter two objectives.

    Results: To quantify source code quality improvement, we reported a comprehensive catalog of source code metrics and a small set of source code metrics consistently linked with maintainability, reliability, and security. To improve source code quality using analysis of code review comments, our explored methodology improves the state-of-the-art with interesting results.

    Conclusions: The thesis provides a promising way to analyze themes in code review comments. Researchers can use the source code metrics provided to estimate these quality attributes reliably. In future work, we aim to derive a software improvement checklist based on the analysis of trends in code review comments.

    Download full text (pdf)
    fulltext
  • Bodduluri, Kailash Chowdary
    et al.
    Linnaeus University.
    Palma, Francis
    University of New Brunswick, Canada.
    Kurti, Arianit
    Linnaeus University.
    Jusufi, Ilir
    Blekinge Institute of Technology, Faculty of Computing, Department of Computer Science.
    Löwenadler, Henrik
    HL Design, Växjö, Sweden.
    Exploring the Landscape of Hybrid Recommendation Systems in E-Commerce: A Systematic Literature Review2024In: IEEE Access, E-ISSN 2169-3536, Vol. 12, p. 28273-28296Article, review/survey (Refereed)
    Abstract [en]

    This article presents a systematic literature review on hybrid recommendation systems (HRS) in the e-commerce sector, a field characterized by constant innovation and rapid growth. As the complexity and volume of digital data increases, recommendation systems have become essential in guiding customers to services or products that align with their interests. However, the effectiveness of single-architecture recommendation algorithms is often limited by issues such as data sparsity, challenges in understanding user needs, and the cold start problem. Hybridization, which combines multiple algorithms in different methods, has emerged as a dominant solution to these limitations. This approach is utilized in various domains, including e-commerce, where it significantly improves user experience and sales. To capture the recent trends and advancements in HRS within e-commerce over the past six years, we review the state-of-the-art overview of HRS within e-commerce. This review meticulously evaluates existing research, addressing primary inquiries and presenting findings that contribute to evidence-based decision-making, understanding research gaps, and maintaining transparency. The review begins by establishing fundamental concepts, followed by detailed methodologies, findings from addressing the research questions, and exploration of critical aspects of HRS. In summarizing and incorporating existing research, this paper offers valuable insights for researchers and outlines potential avenues for future research, ultimately providing a comprehensive overview of the current state and prospects of HRS in e-commerce.

    Download full text (pdf)
    fulltext
  • Fakhouri, Hussam N.
    et al.
    University of Petra, Jordan.
    Alawadi, Sadi
    Blekinge Institute of Technology, Faculty of Computing, Department of Computer Science.
    Awaysheh, Feras M.
    University of Tartu, Estonia.
    Alkhabbas, Fahed
    Malmö University.
    Zraqou, Jamal
    University of Petra, Jordan.
    A cognitive deep learning approach for medical image processing2024In: Scientific Reports, E-ISSN 2045-2322, Vol. 14, no 1, article id 4539Article in journal (Refereed)
    Abstract [en]

    In ophthalmic diagnostics, achieving precise segmentation of retinal blood vessels is a critical yet challenging task, primarily due to the complex nature of retinal images. The intricacies of these images often hinder the accuracy and efficiency of segmentation processes. To overcome these challenges, we introduce the cognitive DL retinal blood vessel segmentation (CoDLRBVS), a novel hybrid model that synergistically combines the deep learning capabilities of the U-Net architecture with a suite of advanced image processing techniques. This model uniquely integrates a preprocessing phase using a matched filter (MF) for feature enhancement and a post-processing phase employing morphological techniques (MT) for refining the segmentation output. Also, the model incorporates multi-scale line detection and scale space methods to enhance its segmentation capabilities. Hence, CoDLRBVS leverages the strengths of these combined approaches within the cognitive computing framework, endowing the system with human-like adaptability and reasoning. This strategic integration enables the model to emphasize blood vessels, accurately segment effectively, and proficiently detect vessels of varying sizes. CoDLRBVS achieves a notable mean accuracy of 96.7%, precision of 96.9%, sensitivity of 99.3%, and specificity of 80.4% across all of the studied datasets, including DRIVE, STARE, HRF, retinal blood vessel and Chase-DB1. CoDLRBVS has been compared with different models, and the resulting metrics surpass the compared models and establish a new benchmark in retinal vessel segmentation. The success of CoDLRBVS underscores its significant potential in advancing medical image processing, particularly in the realm of retinal blood vessel segmentation. © 2024. The Author(s).

    Download full text (pdf)
    fulltext
  • Minhas, Nasir Mehmood
    et al.
    Blekinge Institute of Technology, Faculty of Computing, Department of Software Engineering.
    Bilal, Ahmad
    Mälardalen University.
    Nasir, Nayla
    Blekinge Institute of Technology, Faculty of Computing, Department of Software Engineering.
    A framework to support requirements validation in global software development2023In: Proceedings - 2023 International Conference on Frontiers of Information Technology, FIT 2023, Institute of Electrical and Electronics Engineers (IEEE), 2023, p. 244-249Conference paper (Refereed)
    Abstract [en]

    Requirements validation ensures that the defined requirements conform to the description of the system and are consistent and complete. It is a complex activity that becomes more complicated for global software development (GSD). This study presents the issues associated with requirements validation in GSD and proposes a solution (RVGSD) to overcome these issues. We conducted a literature review and developed a prototype tool to implement RVGSD. The evaluation results show that RVGSD is easy to adopt in the industry and can potentially overcome various issues in the GSD context. Practitioners were satisfied with our framework in all aspects, including validation of requirements, fixing GSD issues, and overall performance. © 2023 IEEE.

    Download full text (pdf)
    fulltext
  • Lövestad, Solveig
    et al.
    University of Gothenburg.
    Örmon, Karin
    Blekinge Institute of Technology, Faculty of Engineering, Department of Health.
    Enander, Viveka
    Västra Götaland Region Competence Centre on Intimate Partner Violence (VKV).
    Krantz, Gunilla
    University of Gothenburg.
    Health care utilization, mental disorders and behavioural disorders among perpetrators of intimate partner homicide in 2000–2016: A registry-based case-control study from Sweden2024In: PLOS ONE, E-ISSN 1932-6203, Vol. 19, no 2, article id e0298693Article in journal (Refereed)
    Abstract [en]

    Little is known about intimate partner homicide (IPH) perpetrator´s healthcare contacts and mental health problems before the killing. The aim was to compare male and female IPH perpetrators with matched controls from the general population by analysing differences in healthcare utilization and mental and behavioural disorders. This study includes 48 males and 10 females who perpetrated IPH between 2000 and 2016 in the Västra Götaland Region of Sweden. Controls (n = 458) were randomly selected from the general population and matched for sex, birth year and residential area. Data were retrieved from the Swedish National Patient Register and the Western Swedish Healthcare Register. Mental and behavioural disorders were classified according to ICD-10 (F00-F99). The Mann-Whitney U test was used to test for differences in health care utilization and mental and behavioural disorders. Compared to their controls, male perpetrators had more registered contacts with primary care ≤ 30 (p = < .001) and ≤ 365 days (p = .019), respectively, before the homicide; with specialist outpatient care ≤ 30 (p = < .001) and ≤ 365 days (p = < .001), respectively, before the homicide: and with inpatient care ≤ 30 (p = < .001) and ≤ 365 days (p = .024), respectively, before the homicide. Female perpetrators had more specialized outpatient care (p = .040) and inpatient care (p = .003) contacts ≤ 365 days before the homicide, compared to controls. Male perpetrators had at least one mental or behavioral disorder diagnosed in any studied healthcare setting except in inpatient care ≤ 30 days before homicide. Female perpetrators had more mental health disorders diagnosed in specialized outpatient care ≤ 365 days before the homicide (p < .001). Perpetrators had more healthcare contacts and mental disorders one year and one month prior to the homicide compared to their controls. Health care professionals should obtain necessary skills in routinely enquiring about intimate partner violence perpetration. Copyright: © 2024 Lövestad et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

    Download full text (pdf)
    fulltext
  • Eklund, Johan
    et al.
    Blekinge Institute of Technology, Faculty of Engineering, Department of Industrial Economics.
    Deiaco, Enrico
    Blekinge Institute of Technology, Faculty of Engineering, Department of Industrial Economics.
    Ageberg, Erik
    Företagarna.
    Wiberg, Daniel
    Företaganra.
    Återstart, lägre arbetslöshet och högre självförsörjningsgrad: vilka hinder ser företagen för att anställa?2021Report (Other academic)
    Abstract [sv]

    Entreprenörskap medför fler arbetstillfällen, ökat välstånd och nya varor och tjänster som underlättar vardagen för alla. Dessvärre dras Sverige med en rad strukturella problem som hindrar ekonomisk utveckling, bland annat saknar en stor grupp människor i dagsläget självförsörjning genom arbete. Samtidigt har arbetsgivare svårt att hitta personal med rätt kompetens. Dessutom skapar regleringar och skatter barriärer som hindrar företag att anställa. Vilka reformer krävs för att påskynda den ekonomiska återstarten efter pandemin och lägga grunden för framtida svenskt välstånd?I rapporten Återstart, lägre arbetslöshet och högre självförsörjningsgrad – Vilka hinder ser företagen för att anställa? går författarna igenom angelägna ekonomipolitiska reformområden och lämnar policyförslag som kan lägga grunden till fortsatt svenskt välstånd. 

    Download full text (pdf)
    fulltext
  • Eklund, Johan
    et al.
    Blekinge Institute of Technology, Faculty of Engineering, Department of Industrial Economics.
    Thulin, Per
    Entreprenörskapsforum.
    Vad förklarar Sveriges fall i välståndsligan?2020In: Svensk konkurrenskraft: Hur kan Sverige säkerställa ett långsiktigt välstånd? / [ed] Johan Eklund, Per Thulin, Entreprenörskapsforum , 2020, p. 49-65Chapter in book (Other academic)
    Download full text (pdf)
    fulltext
  • Eklund, Johan
    et al.
    Blekinge Institute of Technology, Faculty of Engineering, Department of Industrial Economics.
    Thulin, Per
    Entreprenörskapsforum.
    Svensk konkurrenskraft: Hur kan Sverige säkerställa ett långsiktigt välstånd?2020In: Svensk konkurrenskraft: Hur kan Sverige säkerställa ett långsiktigt välstånd? / [ed] Johan Eklund, Per Thulin, Entreprenörskapsforum , 2020, p. 7-21Chapter in book (Other academic)
    Download full text (pdf)
    fulltext
  • Karlsson, Charlie
    et al.
    Blekinge Institute of Technology, Faculty of Engineering, Department of Industrial Economics.
    Andersson, Martin
    Blekinge Institute of Technology, Faculty of Engineering, Department of Industrial Economics.
    Norman, Therese
    Högskolan i Jönköping.
    Introduction2015In: Handbook of Research Methods and Applications in Economic Geography / [ed] Charlie Karlsson, Martin Andersson, Therese Norman, Northampton: Edward Elgar Publishing, 2015, p. 1-20Chapter in book (Other academic)
    Download full text (pdf)
    fulltext
  • Braunerhjelm, Pontus
    et al.
    Blekinge Institute of Technology, Faculty of Engineering, Department of Industrial Economics.
    Andersson, Martin
    Blekinge Institute of Technology, Faculty of Engineering, Department of Industrial Economics.
    Blind, Knut
    Technische Universität Berlin, Germany.
    Eklund, Johan
    Blekinge Institute of Technology, Faculty of Engineering, Department of Industrial Economics.
    Handbook of Innovation and Regulation: introductory chapter2023In: Handbook of Innovation and Regulation / [ed] Pontus Braunerhjelm, Martin Andersson, Knut Blind, and Johan E. Eklund, Northampton: Edward Elgar Publishing, 2023, p. 1-20Chapter in book (Other academic)
    Download full text (pdf)
    fulltext
  • Eklund, Johan
    et al.
    Blekinge Institute of Technology, Faculty of Engineering, Department of Industrial Economics.
    Pettersson, Lars
    Jönköping International Business School.
    Hur får vi  bättre regleringar?: Rekommendationer för samhällsekonomiskt effektivare regelgivning2024Report (Other academic)
    Abstract [sv]

    I rapporten analyserar författarna hur arbetet med regelutformning i Sverige skulle kunna utvecklas. De pekar på att regelutformning inte primärt är ett juridiskt problem, utan en samhällsekonomisk analysfråga där samhällsekonomisk effektivitet måste genomsyra och prägla arbetet med regelutvärdering och regelgivning.

    Download full text (pdf)
    fulltext
  • Villamil Velasquez, Carolina
    Blekinge Institute of Technology, Faculty of Engineering, Department of Strategic Sustainable Development.
    A Gamified Approach to Engage Sustainable User Behavior in Product Service System Solutions2023In: European Journal of Sustainable Development, ISSN 2239-5938, E-ISSN 2239-6101, Vol. 12, no 3, p. 152-164Article in journal (Refereed)
    Abstract [en]

    Product service system solutions encourage to share products, reducing manufacturing processes and increasing the product life. Therefore, this might contribute to offer more sustainable solutions to users, by considering the complete socio-ecological system, the context, the stakeholder relationship, among other aspects. Where the sustainability behavior of consumers and the data provided for new information and technology (ICT) devices are key factors in the development of solutions with a higher sustainability performance. Moreover, game elements and ICT have been used in different fields to engage users. The aim of this research is to investigate if a gamified approach motivates a substantiable behavior change in users of product service system solutions. Based on a literature review, a model is proposed and applied to a product service system case of a shared laundry facility in Sweden. The model was evaluated with experts semi-structured interviews and a survey with users of the shared laundry facility. Concluding that a gamified approach has a potential to motivate behavior change towards sustainability in product service system. In future research, the proposed model will be adapted to be tested in other product service system cases, with the purpose to improve it for its application in industry and education.

    Download full text (pdf)
    fulltext
  • Svensson, Markus
    et al.
    Lund University.
    Elmståhl, Sölve
    Lund University.
    Sanmartin Berglund, Johan
    Blekinge Institute of Technology, Faculty of Engineering, Department of Health.
    Rosso, Aldana
    Lund University.
    Association of systemic anticholinergic medication use and accelerated decrease in lung function in older adults2024In: Scientific Reports, E-ISSN 2045-2322, Vol. 14, no 1, article id 4362Article in journal (Refereed)
    Abstract [en]

    Older adults are frequently exposed to medicines with systemic anticholinergic properties, which are linked to increased risk of negative health outcomes. The association between systemic anticholinergics and lung function has not been reported. The aim of this study was to investigate if exposure to systemic anticholinergics influences lung function in older adults. Participants of the southernmost centres of the Swedish National study on Aging and Care (SNAC) were followed from 2001 to 2021. In total, 2936 subjects (2253 from Good Aging in Skåne and 683 from SNAC-B) were included. An extensive medical examination including spirometry assessments was performed during the study visits. The systemic anticholinergic burden was described using the anticholinergic cognitive burden scale. The effect of new use of systemic anticholinergics on the annual change in forced expiratory volume (FEV1s) was estimated using mixed models. During follow-up, 802 (27.3%) participants were exposed to at least one systemic anticholinergic medicine. On average, the FEV1s of participants without systemic anticholinergic exposure decreased 37.2 ml/year (95% CI [33.8; 40.6]) while participants with low and high exposure lose 47.2 ml/year (95% CI [42.4; 52.0]) and 43.7 ml/year (95% CI [25.4; 62.0]). A novel association between new use of medicines with systemic anticholinergic properties and accelerated decrease in lung function in older adults was found. The accelerated decrease is comparable to that observed in smokers. Studies are needed to further explore this potential side effect of systemic anticholinergics. © The Author(s) 2024.

    Download full text (pdf)
    fulltext
  • Niklasson, Joakim
    et al.
    Linnaeus University.
    Backåberg, Sofia
    Linnaeus University.
    Lindberg, Terese
    Blekinge Institute of Technology, Faculty of Engineering, Department of Health.
    Bergman, Patrick
    Linnaeus University.
    Fagerström, Cecilia
    Linnaeus University.
    Embodied navigation: the influence of lived experience on physical activity and sedentary behavior among older adults2024In: International Journal of Qualitative Studies on Health and Well-being, ISSN 1748-2623, E-ISSN 1748-2631, Vol. 19, no 1, article id 2313657Article in journal (Refereed)
    Abstract [en]

    PurposeThe impact of a sedentary lifestyle on health and well-being is well recognized. However, there is limited understanding of how a lifetime of physical activity and sedentary behaviour influences an active lifestyle in older adults. The aim of this study was to describe how lived experience of physical activity and sedentary behaviour impacts daily activities among older adults, from a life course perspective.MethodsQualitative content analysis was used; individual telephone interviews were conducted with fourteen older adults aged 71 to 92 years. The participants received initial support from community care and lived in ordinary housing in southern Sweden.ResultsThe interviews yielded one theme, "Navigating with an embodied activity compass," and two sub-themes: "Being guided by the past" and "Unveiling pathways through body awareness."ConclusionsOur study highlights how older adults' lived experiences of physical activity, with their connections to body awareness and acceptance, impact daily physical activity. These findings offer new knowledge for clinical practitioners balancing recommendations of sedentary behaviour and physical activity, to promote healthy daily physical activity among older adults. Future research and policies should consider the lived experiences of older adults when addressing public health matters related to sedentary behaviour and physical activity.

    Download full text (pdf)
    fulltext
  • Tsiporkova, Elena
    et al.
    EluciDATA Lab of Sirris, Belgium.
    De Vis, Micheil
    EluciDATA Lab of Sirris, Belgium.
    Klein, Sarah
    EluciDATA Lab of Sirris, Belgium.
    Hristoskova, Aanna
    Digital Services Lab of Sirris, Belgium.
    Boeva, Veselka
    Blekinge Institute of Technology, Faculty of Computing, Department of Computer Science.
    Mitigating Concept Drift in Distributed Contexts with Dynamic Repository of Federated Models2023In: Proceedings - 2023 IEEE International Conference on Big Data, BigData 2023, Institute of Electrical and Electronics Engineers (IEEE), 2023, p. 2690-2699Conference paper (Refereed)
    Abstract [en]

    This paper proposes a novel federated learning methodology, called FedRepo, that copes with concept drift issues in a statistically heterogeneous distributed learning environment. The proposed horizontal federated learning methodology, based on random forest (RF), can be used for collaborative training and maintenance of a dynamic repository of federated RF models, each one customized to a group of clients/devices. The clients are grouped together if their performance patterns with respect to the global RF model are similar. The performance of the customized RF global models is continuously monitored during the inference phase and the repository is accordingly adapted to mitigate the detected concept drift. The proposed methodology is studied and evaluated against an electricity consumption forecasting use case. The evaluation results demonstrate clearly that the proposed methodology is able to deal with concept drift issues in an efficient and adequate fashion without compromising the overall performance of the distributed environment. © 2023 IEEE.

    Download full text (pdf)
    fulltext
  • Wiecher, Carsten
    et al.
    Kostal Automobil Elektrik GmbH & Co. KG, Germany.
    Mandel, Constantin
    IPEK – Institute of Product Engineering at Karlsruhe Institute of Technology (KIT), Germany.
    Günther, Matthias
    Fraunhofer IEM, Germany.
    Fischbach, Jannik
    fortiss GmbH, Germany.
    Greenyer, Joel
    FHDW Hannover, Germany.
    Greinert, Matthias
    Two Pillars GmbH, Germany.
    Wolff, Carsten
    FH Dortmund, Germany.
    Dumitrescu, Roman
    Fraunhofer IEM, Germany.
    Mendez, Daniel
    Blekinge Institute of Technology, Faculty of Computing, Department of Software Engineering.
    Albers, Albert
    IPEK – Institute of Product Engineering at Karlsruhe Institute of Technology (KIT), Germany.
    Model-based analysis and specification of functional requirements and tests for complex automotive systems2024In: Systems Engineering, ISSN 1098-1241, E-ISSN 1520-6858Article in journal (Refereed)
    Abstract [en]

    The specification of requirements and tests are crucial activities in automotive development projects. However, due to the increasing complexity of automotive systems, practitioners fail to specify requirements and tests for distributed and evolving systems with complex interactions when following traditional development processes. To address this research gap, we propose a technique that starts with the early identification of validation concerns from a stakeholder perspective, which we use to systematically design tests that drive a scenario-based modeling and analysis of system requirements. To ensure complete and consistent requirements and test specifications in a form that is required in automotive development projects, we develop a Model-Based Systems Engineering (MBSE) methodology. This methodology supports system architects and test designers in the collaborative application of our technique and in maintaining a central system model, in order to automatically derive the required specifications. We evaluate our methodology by applying it at KOSTAL (Tier1 supplier) and within student projects as part of the masters program Embedded Systems Engineering. Our study corroborates that our methodology is applicable and improves existing requirements and test specification processes by supporting the integrated and stakeholder-focused modeling of product and validation systems, where the early definition of stakeholder and validation concerns fosters a problem-oriented, iterative and test-driven requirements modeling. © 2024 Wiley Periodicals, Inc.

    Download full text (pdf)
    fulltext
  • Dozio, Nicolò
    et al.
    Politecnico di Milano, Italy.
    Bertoni, Marco
    Blekinge Institute of Technology, Faculty of Engineering, Department of Mechanical Engineering.
    Ferrise, Francesco
    Politecnico di Milano, Italy.
    Driving emotions: using virtual reality to explore the effect of low and high arousal on driver’s attention2024In: Virtual Reality, ISSN 1359-4338, E-ISSN 1434-9957, Vol. 28, no 51Article in journal (Refereed)
    Abstract [en]

    The role played by emotions and attention is crucial for the development of advanced driver assistance systems that improve safety by flexibly adapting to the current state of the driver. In the present study, we used immersive virtual reality as a testing tool to investigate how different emotional states affect drivers’ attention in a divided attention task. Two different emotional states, diversified by valence and arousal, were induced before performing a divided attention task in a driving simulation. The experimental task developed for this study allowed us to explore if and how two different emotional states can affect the way drivers divide their attention between a central driving-related task and a peripheral visual task. Our results showed that scared drivers presented lower reaction times at the central task compared to relaxed drivers. On the contrary, the emotional state did not affect the performance at the peripheral task, which revealed instead a significant effect of the eccentricity at which the visual stimuli were presented, influencing both the accuracy of targets’ perception and participants’ reaction times.

    Download full text (pdf)
    fulltext
  • Simaremare, Mario
    et al.
    Blekinge Institute of Technology, Faculty of Computing, Department of Software Engineering.
    Edison, Henry
    Blekinge Institute of Technology, Faculty of Computing, Department of Software Engineering.
    AI Assistant to Improve Experimentation in Software Startups Using Large Language Model and Prompt Engineering2024In: CEUR Workshop Proceedings / [ed] Saltan A., Santos R., Wang X., Baiyere A., Peltonen E., Kemell K.-K.Saltan A., Santos R., Wang X., Baiyere A., Peltonen E., Kemell K.-K., Technical University of Aachen , 2024, Vol. 3621Conference paper (Refereed)
    Abstract [en]

    Software startup is a unique type of company with unique characteristics. On the one hand, they must offer innovative products appealing to customers to generate revenue and survive, but on the other hand, they are limited in resources, time, and experience. During the new product development, it is important to experiment with their original ideas. However, doing a meaningful experiment requires resources and challenges. A study on failed software startups shows that, despite its importance, many software startups skipped or did not experiment with their ideas. The study identifies 25 inhibitors spread in five experimentation stages. In the last few years, Large Language Models (LLMs) have become a popular technology. The advancement of LLM has made it adopted into many parts of the software development cycle. Studies show that LLM also has been used to generate new innovative product ideas and to manage innovation. However, there is no investigation into the possibility of utilizing the power of LLM to help software startups do experimentation. Interactions to an LLM are done through prompts. During the interaction or session, a user will send one or more prompts in a zero-, one-, or few-shots to an LLM agent. Unfortunately, learning and using prompts effectively requires time and resources, things that software startups are scarce with. In this project, we aim to help improve the experimentation process and address the inhibitors by leveraging the power of LLMs. There are five initial research questions and studies planned in the project. In the first step, we will investigate current experimentation practices, challenges, inhibitors, and the strategies used to circumvent them. Secondly, we will investigate how AI has been used in today's experimentation. Then, we will investigate the set of measurements available to measure the success of an experiment. The next step is to investigate how to support experimentation using LLMs followed by a validation sequence. The first form of support is a prompt guidebook to help software startups use an LLM agent to help their experimentation. The second form is an LLM-based assistant tailored specifically to guide the experimentation process. © 2006 Gesellschaft für Informatik, Bonn.

    Download full text (pdf)
    fulltext
  • Casalicchio, Emiliano
    et al.
    Sapienza University, Italy.
    Esposito, Simone
    Sapienza University, Italy.
    Al-Saedi, Ahmed Abbas Mohsin
    Blekinge Institute of Technology, Faculty of Computing, Department of Computer Science.
    FLWB: a Workbench Platform for Performance Evaluation of Federated Learning Algorithms2023In: 2023 IEEE International Workshop on Technologies for Defense and Security, TechDefense 2023 - Proceedings, Institute of Electrical and Electronics Engineers (IEEE), 2023, p. 401-405Conference paper (Refereed)
    Abstract [en]

    Federated learning is a technique that allows to collaboratively train a shared machine learning model across distributed devices, where the data are stored locally on devices. Most innovations the research community proposes in federated learning are tested through custom simulators. An analysis of the literature shows the lack of workbench platforms for the performance evaluation of FL projects. This paper aims to fill the gap by presenting FLWB, a general-purpose, configurable, and scalable workbench platform for easy deployment and performance evaluation of Federated Learning projects. Through experiments, we demonstrated the ease with which a FL system can be implemented and deployed with FLWB. © 2023 IEEE.

    Download full text (pdf)
    fulltext
  • Yang, Fan
    et al.
    Universiti Teknologi Malaysia (UTM), Malaysia.
    Ismail, Nor Azman
    Universiti Teknologi Malaysia (UTM), Malaysia.
    Pang, Yee Yong
    Universiti Teknologi Malaysia (UTM), Malaysia.
    Kebande, Victor R.
    Blekinge Institute of Technology, Faculty of Computing, Department of Computer Science.
    Al-Dhaqm, Arafat
    Universiti Teknologi PETRONAS, Malaysia.
    Koh, Tieng Wei
    Universiti Teknologi PETRONAS, Malaysia.
    A Systematic Literature Review of Deep Learning Approaches for Sketch-Based Image Retrieval: Datasets, Metrics, and Future Directions2024In: IEEE Access, E-ISSN 2169-3536, Vol. 12, p. 14847-14869Article, review/survey (Refereed)
    Abstract [en]

    Sketch-based image retrieval (SBIR) utilizes sketches to search for images containing similar objects or scenes. Due to the proliferation of touch-screen devices, sketching has become more accessible and therefore has received increasing attention. Deep learning has emerged as a potential tool for SBIR, allowing models to automatically extract image features and learn from large amounts of data. To the best of our knowledge, there is currently no systematic literature review (SLR) of SBIR with deep learning. Therefore, the aim of this review is to incorporate related works into a systematic study, highlighting the main contributions of individual researchers over the years, with a focus on past, present and future trends. To achieve the purpose of this study, 90 studies from 2016 to June 2023 in 4 databases were collected and analyzed using the Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) framework. The specific models, datasets, evaluation metrics, and applications of deep learning in SBIR are discussed in detail. This study found that Convolutional Neural Networks (CNN) and Generative Adversarial Networks (GAN) are the most widely used deep learning methods for SBIR. A commonly used dataset is Sketchy, especially in the latest Zero-shot sketch-based image retrieval (ZS-SBIR) task. The results show that Mean Average Precision (mAP) is the most commonly used metric for quantitative evaluation of SBIR. Finally, we provide some future directions and guidance for researchers based on the results of this review. © 2013 IEEE.

    Download full text (pdf)
    fulltext