BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Software Center - ECPv6.16.2//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Software Center
X-ORIGINAL-URL:https://www.software-center.se
X-WR-CALDESC:Events for Software Center
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:Europe/Stockholm
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20230326T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20231029T010000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20240331T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20241027T010000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20250330T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20251026T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Europe/Stockholm:20241206T140000
DTEND;TZID=Europe/Stockholm:20241206T160000
DTSTAMP:20260524T093223
CREATED:20240128T211026Z
LAST-MODIFIED:20240128T211026Z
UID:6328-1733493600-1733500800@www.software-center.se
SUMMARY:Deadline sprint 28 project proposals
DESCRIPTION:
URL:https://www.software-center.se/event/deadline-sprint-28-project-proposals/
CATEGORIES:Deadline
ORGANIZER;CN="Jan Bosch":MAILTO:jan.bosch@chalmers.se
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Europe/Stockholm:20241211T130000
DTEND;TZID=Europe/Stockholm:20241211T170000
DTSTAMP:20260524T093223
CREATED:20241007T084448Z
LAST-MODIFIED:20241211T122934Z
UID:7145-1733922000-1733936400@www.software-center.se
SUMMARY:Technical workshop with Software Center projects
DESCRIPTION:In Software Center\, companies and universities work together to accelerate the adoption of novel approaches to software engineering. This one-day technical workshop aims at sharing and discussing results from joint projects within Software Center. This event is for Software Center partners only. \nRegistration:\nPlease register at this link: https://forms.gle/HuqJJmjojqJszepc7 \nChoose your workshop track:\nTo be able to plan for the day we ask you to indicate which track you plan to attend\, please choose you track for the workshop at this link:  https://forms.gle/sgJKm2A5J5UWmtw58 \nThe tracks:\n\nAutomation of Regulatory Compliance\nDigital twins\nAssurance & regulatory compliance\, architecture and testing\nEngineering Generative AI Software\n\nLate registrations?\nIf you want to bring a colleague there is still room for more participants\, registration here: https://forms.gle/HuqJJmjojqJszepc7 \n  \nDate & time:   December 12\, 13:00 – 17:00\nPlace:              SVEA\, Forskningsgången 4\, 417 56 Göteborg\nAgenda:          https://www.software-center.se/event/technical-ws/ \n  \nAgenda:\n12.30 – 13.00: Registration and coffee\n13.00 – 13.15: Introduction: Jan Bosch (Room: SVEA 241)\n13.15 – 14.45: Parallell workshop sessions:\nTrack 1: Automation of Regulatory Compliance (Room: SVEA 241)\nMicrosoft Teams Need help?\nJoin the meeting now\nMeeting ID: 352 629 839 902\nPasscode: Va7sw9JK\n\nThe question we ask is: ‘What if you could have a “Regulatory Agent” and use artificial intelligence (AI) to help you satisfy regulatory compliance’? Such an agent could continuously track and monitor the system and help ensure that no inconsistencies are introduced. \nTo address this\, and to explore effective ways to work with regulatory compliance\, this session focuses on automation of tasks and processes necessary for regulatory compliance. What we seek to achieve is ways in which we can remove the human efforts that goes into these processes. \nAgenda: \n13:15 – 13:30: Welcome and introduction to the session (Jan and Helena) \n13:30 – 13:50: How automation and CRA can work together\nPresenter: Christian Nord\, Senior Engineering Manager\, Advenica \n13:50 – 14:10: Do legal and engineering mix? – Using tools in the context of regulatory compliance: challenges and opportunities\nPresenter: Liina Savolainen\, EE Roadmap Leader at GTT (AB Volvo) \n14:10 – 14:30: Automating Extraction of Information for a Compliance Argument based on the Textual Requirements System (TReqS)\nPresenter: Eric Knauss (University of Gothenburg) \n14:30 – 14:45: Master student presentation/pitch to Software Center companies \n14:45 – 15:15 Coffee break \n15:15 – 16:30: Discussion \n15:15 – 16:10: Discussion \n\nIdentification of key themes\nBreakout groups assigned to themes\nReport out\n\n16:10 – 16:30: Reflections and closing \n\nSummary of key learnings\nAgreement on next steps\nFeedback (one thing you liked/wished for)\nClosing\n\nBackground:\nIn recent discussions with representatives from the Software Center companies\, many people have brought up the many new regulations that will\, and are already\, affecting the companies. As only a few examples\, there is the Cybersecurity Act\, GDPR\, the Data Act\, the AI Act and the Product Liability Act. \nIn a workshop earlier this sprint\, we explored some of these new regulations and the challenges associated with how to strategically prepare for these and how to organize for complying with these. In these discussions\, it became clear that currently\, many companies are spending an enormous amount of resources and manual effort into the process of understanding\, preparing\, and organizing for regulatory compliance. The risk\, as we see it\, is that resources and efforts are spent on processes and tasks that will only increase in number and that\, over time\, R&D and innovation activities might suffer. \nSession format:\nThe session is interactive in nature with a mix of presentations from research and industry\, and with group discussions/exercises. \nSession organizers: Helena Holmström Olsson and Jan Bosch \nTrack 2: Digital twins (Room: SVEA 240)\nBackground:\nIn recent discussions with representatives from the Software Center companies\, several companies have indicated interest in more in-depth discussions and research-activities regarding digital twins. \nSession focus:\nThe session will focus on identifying existing and missing technologies and competences that are needed to better utilize the concepts and ideas behind the digital-twin paradigm. We will look at questions like “How are different actors working with digital twins today?”\, “How would we like to work with digital twins in the future?”\, “What are the challenges you see to pursue such approach to system operation?”\, “What are the technology gaps that need to be filled?” \nSession format:\nThe session is interactive in nature with a mix of presentations from research and industry\, and with group discussions. \nSession goals:\nOur goal is to identify how the Software Centre community could support advances in utilizing digital-twin technology at the partner companies. This could include need for Software Center research-project and/or other supporting activities such as seminars or development of courses. \nSession organizers: Mikael Sjödin and Tiberiu Seceleanu \nTrack 3: Assurance & regulatory compliance\, architecture and testing (Room: SVEA 228)\nChairs: Jan Carlson\, Mälardalen University\, Daniel Varro\, Linköping university \nTentative link for online participation: Join the meeting\nMS Teams Meeting ID: 342 545 598 082 Passcode: ck6qz6Ve \n13.15 – 14.00 Assurance & regulatory compliance \n\n\nOntology-based representation for assurance and compliance (projects #49 & #50): Barbara Gallina\n\nTowards Automated Multi-concern Assurance and Regulatory Compliance of Battery Management Systems (projects #49\, #50 & #60): Barbara Gallina\n\n14.00 – 14.45 Architecture \n\n\nCommunication and documentation of architectural changes (project #35): Ifrah Qaisar\n\n\nAdopting the C4 model for visualizing software architecture (project #35): Robbert Jongeling\n\n\n14.45 – 15.15 Coffee break \n15.15 – 16.30 Testing \n\n\nUse of Generative AI in test generation\, optimization\, and automation (project #63): Gregory Gay and Azeem Ahmad\n\n\nTrack 4: Engineering Generative AI Software – project presentations (Room: SVEA 215)\nChair: Miroslaw Staron\, University of Gothenburg and Chalmers University of Technology \nLink to online participation: Join the meeting now \nMS Teams Meeting ID: 372 030 783 546   Passcode: JM3mJ3BA \nSession format: Project presentations and discussions \n\n\n13.15 – 13.45: Wilhelm Meding/Miroslaw Staron – requirements from standards\n\n\n13.45 – 14.05: Simin Sun – preliminary survey on CI\n\n\n14.05 – 14.25: Yi Peng – Data Challenges for Machine Learning Systems — Towards Data Requirements\n\n\n14.25 – 14.45: Habib – Maintainability Definition and Measurement for ML System Components.\nCoffee break\n\n\n15.15 – 15.35: Nataliya Berbyuk Lindström – Stakeholder Information Needs\n\n\n15.35 – 15.55: Nataliya Berbyuk Lindström – Generative AI\n\n\n15.55 – 16:15: Srijita Basu – Automotive CWE analysis\n\n\n16.15 – 16.30: Yiran Wang\, Willem Meijer – Why ML code crashes and what we are going to do about it\n\n\n14.45 – 15.15: Coffee & mingle\n15.15 – 16.30: Parallell workshop sessions (continued)\n16.30: Reflections in plenary: theme leaders\n16.50 – 17.00: Summary and closing: Jan Bosch\n  \nDecember 11th: Post technical workshop & Pre-reporting workshop mingle\nWe meet for an informal warming up for the reporting workshop (at own cost):\n18.00 at OGBG Bar & Restaurang\, Comfort Hotel\, Skeppsbroplatsen 1411 21 Göteborg \nDecember 12th: Software center reporting workshop\nThe day after the technical workshop we are arranging the December Software Center reporting workshop where you have the opportunity to meet partners in Software Center\, more information here: https://www.software-center.se/event/rws_dec2024/
URL:https://www.software-center.se/event/technical-ws/
LOCATION:SVEA building\, Lindholmen\, Forskningsgången 4\, Gothenburg\, 41756\, Sweden
CATEGORIES:Workshop
ORGANIZER;CN="Jan Bosch":MAILTO:jan.bosch@chalmers.se
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Europe/Stockholm:20241212T100000
DTEND;TZID=Europe/Stockholm:20241212T170000
DTSTAMP:20260524T093223
CREATED:20240613T142822Z
LAST-MODIFIED:20241212T125506Z
UID:6822-1733997600-1734022800@www.software-center.se
SUMMARY:Reporting workshop: The end of Software Engineering - as we know it
DESCRIPTION:In Software Center\, companies and universities work together to accelerate the adoption of novel approaches to software engineering. The reporting workshop takes place twice a year\, in June and December. \nThis event aims at sharing results from research and cooperation within Software Center\, including activities in the competence center CoDig\, hosted by Software Center. The day before the reporting workshop there is an additional interactive workshop where you have the opportunity to discuss technical challenges with the Software Center projects\, more information here >> \nThe agenda for the reporting workshop ranges from keynote presentations to in-depth sessions for themes and projects. The cooperation between academia and companies in Software Center creates the software engineering success stories that industry needs. \nRegistration:\nPlease register at this link: https://forms.gle/HuqJJmjojqJszepc7 \nLink for virtual participation – all plenary sessions:\nYou can join the meeting over Teams\, but the digital solution will not offer an opportunity to interact with speakers:\nLink to the Teams townhall meeting >> \n  \nDec 11th: Pre-reporting workshop mingle\nWe meet for an informal warming up for the reporting workshop (at own cost):\n18.00 at OGBG Bar & Restaurang\, Comfort Hotel\, Skeppsbroplatsen 1411 21 Göteborg \nAgenda:\n09.30 – 10.00: Registration and coffee\n10:00-10:15: Opening: Jan Bosch\n10:15-10:45: Digital twins: keynote presentation by Mark van den Brand\,  Eindhoven University of Technology\, Software Engineering and Technology\nHigh-tech systems are becoming increasingly complex and more difficult to design\, manufacture and maintain. The DIGITAL TWIN program develops methods to make accurate digital twins of these types of systems: virtual software versions that allow you to run simulations to predict\, for example\, how changes in the design affect performance\, how control can be improved\, or which part on which needs maintenance at the moment. Digital twins are still mostly based on static theoretical models that assume normal behavior. By linking these models to measurement data that indicate how the system actually functions and combining this data with artificial intelligence\, the researchers make digital copies that continuously improve and adapt themselves. The research focuses on a number of exemplary systems provided by the Dutch high-tech companies involved in the program. \n10.45-11.00: The impact of SDV and AI on Next-Generation Tier1 ADAS development\nCompany presentation by Tobias Aderum\, Director Research & Innovation at Magna Electronics\nRead more at: https://www.magna.com/products/electrical-electronics/adas-automated-driving \n11:00-11:30: Community updates and introduction to poster session:\n\nTheme 1: Daniel Varro\, Linköping university\nTheme 2: Jan Carlson\, Mälardalen University\nTheme 3: Miroslaw Staron\, University of Gothenburg\nTheme 4: Helena H Olsson\, Malmö University\n\n11.30 – 12.15: Poster & mingle session\n12:15 – 13:00 Lunch break (lunch at own expense)\nRecommended lunch restaurant: https://www.facebook.com/wastegbg/ \n13:00 – 13.40: The AI maturity journey: how to scale up value from data and AI in an organization:\nIndustrial keynote presentation by Anders Arpteg\,  Senior director\, Head of AI and Data CoE\, Global Connect group.\n\nMany companies struggle to fully capture the value of data and AI\, often finding themselves stuck in isolated AI initiatives without broader impact or even completely failing to take advantage of the possibilities. Unlocking value from AI is a journey\, requiring a strategic approach to move from small-scale AI projects to a company-wide adoption that drives real transformation. The potential of data and data and AI is immense\, but to climb the AI maturity scale and achieve meaningful results\, organizations must have a well-defined strategy guiding their progress. \n13.40-14.00: Software architecture and AI: presentation by Antonio Martini\, University if Oslo \nAI took the world by storm\, fundamentally changing the way we architect traditional systems\, but also the way we need to architect novel AI (sub)systems. For example\, how do we integrate AI modules in traditional software with a long-term perspective\, including maintainability and evolvability? How do we use AI to assess our architecture\, for example its modularity or if there are performance anomalies? Do architects need to fundamentally evolve their role and competences? \n14:00 – 16.00: Parallel tracks (incl coffee break)\n1: Data: Dare to Dream (Room: the Studio\, same as plenary)\n\nSession organizers: Helena Holmström Olsson and Jan Bosch\nSpeakers: Ingmar Bengtsson\, Volvo Group Truck Technology\nBackground: In our research on data practices\, we see that people are often more focused on the constraints associated with data than exploring the opportunities that data can bring. In most situations\, we want the data\, we know it has value\, but we don’t dare to fully use and exploit it due to e.g.\, regulations\, ownership constraints\, ways-of-working that are not well-established\, costs associated with storage\, processing etc.\, and lack of quality to mention a few.\nSession focus: In this session\, we look for ideas and discussions on: “What if there were no constraints? What if we didn’t have these challenges and uncertainties? What if we could not fail? If so\, what are the things we would do with data?\nSession format: The session is interactive in nature with a mix of presentations from research and industry\, and with group discussions/exercises.\n\n2. AI-supported digitalization – Quantum and generative AI (Room: Workshoprummet\, 1st floor)\nLink to online participation: Join the meeting now \nMS Teams meeting ID: 341 402 358 630\npasscode: GF3n7iF6\n\nSession organizer: Miroslaw Staron\nSession focus: Quantum & Generative AI – how can we utilize quantum computing in software products? Are we ready for large-scale adoption yet? When will Quantum Computers be available like datacenters for AI?\nSpeakers:\n\nMikael Haglund & Henrik Sjöstrand\, IBM Sweden\nPontus Vikstål\, Mårten Skogh\, Chalmers NextLabs\nPetter Sutton\, Boeing\n\n\n\n3. The future of software and system modelling (Room: Wonderwoman)\n\nJoin the meeting now \nMeeting ID: 393 818 596 770\nPasscode: d4R7ff9U \n\nSession organizer: Jan Carlson\, Mälardalen University\, & Daniel Varro\, Linköping University\nSession focus: What is the role of models and modeling when building the software-intensive systems of the future? Should we still model? If so\, what? And how much is enough? Can models still be a useful tool in AI-supported development\, or is modeling becoming an outdated way of working?\n\n16.00: The end of Software Engineering as we know it\nPresentation and fishbowl discussion \n16.45 – 17:00 Plans\, reflections & closing: Jan Bosch\n  \nSpeakers:\n\n\n\n\nMark van den Brand: professor of Software Engineering and Technology\, Technical University of Eindhoven\, the Netherlands\n\n\n\n\n.\n  \nMark van den Brand is a full professor of Software Engineering and Technology in the Department of Mathematics and Computer Science\, and a visiting professor at Royal Holloway\, University of London. His current research activities are on model driven engineering\, domain specific languages\, meta-modeling\, model management\, digital twins\, and automotive software engineering. His research is industry inspired; he works with most of the high-tech companies in the Eindhoven region\, the Netherlands. He has been an invited lecturer and keynote speaker at various conferences\, workshops and doctoral schools. He was and is member of PCs on workshops and conferences related to software engineering\, language engineering\, rewriting\, reverse engineering\, and software maintenance. \nMark initiated the special issues of Science of Computer Programming devoted to academic software development (Experimental Software and Toolkits)\, and since 2007 has been guest editor of six of these. He is on the editorial board of the journals Science of Computer Programming\, Open Computer Science\, and Computer Languages (COLA). He is Editor-in-Chief of the Journal on Automotive Software Engineering. He is associate Editor-in-Chief of the Software Section of the Science of Computer Programming. He is deputy Editor-in-Chief of platinum open access journal JOT.\n\n\n\nAnders Arpteg: Senior director\, Head of AI and Data CoE\, Global Connect Group\n\n\n\n\n\n  \nAnders Arpteg is AI director\, engineer\, scientist\, and investor with 25+ years of AI experience in both academia and industry\, with a Ph.D. in AI from Linköping University\, Sweden. Previously heading up research at Spotify\, Peltarion\, and data science at the Swedish Security Service\, now heading up a Center of Excellence for AI and data at GlobalConnect. \nAnders has also been part of starting up national AI initiatives such as AI Sweden and the Swedish AI Agenda\, member of the European AI Alliance\, AI reviewer for ICML\, ICLR\, JCP\, and the Swedish innovation agency Vinnova\, and host of the AI After Work podcast\, and received awards such as Lifetime achievement in AI from the Nordic DAIR Awards in 2021.\n\n\n\nAntonio Martini\, Professor\, University of Oslo\n\n\n\n\n\n  \nI am Professor at University of Oslo. My latest interests are on using AI for software engineering\, specifically for technical debt and software architecture\, and to improve software engineering practices for AI. In general\, my research focus is on managing Technical Debt\, Architecture\, Technical Leadership\, and Agile software development. I’m very keen to work with software companies and improve the state of art and practice together. My experience covers Software Engineering and Management in several contexts: large\, embedded software companies\, small\, web companies\, business to business companies\, startups. \nI’ve collaborated with several large companies such as Ericsson\, Volvo\, Saab\, Axis\, Grundfos\, Siemens\, Bosch\, Jeppesen\, Siemens\, Visma\, AKVA Group\, Knowit\, and more. I’ve also worked with my own company and I’ve run consultancy projects to manage and visualize Technical Debt. I’ve obtained a PhD in Software Engineering at Chalmers University of Technology\, Sweden in 2015.
URL:https://www.software-center.se/event/rws_dec2024/
LOCATION:A Working Lab (AWL)\, Sven Hultins plats 5\, Gothenburg\, 41258\, Sweden
CATEGORIES:Conference,Promoted
ORGANIZER;CN="Jan Bosch":MAILTO:jan.bosch@chalmers.se
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Europe/Stockholm:20241213T100000
DTEND;TZID=Europe/Stockholm:20241213T120000
DTSTAMP:20260524T093223
CREATED:20240128T211344Z
LAST-MODIFIED:20240128T211344Z
UID:6332-1734084000-1734091200@www.software-center.se
SUMMARY:Task force meeting for planning sprint 28
DESCRIPTION:
URL:https://www.software-center.se/event/task-force-meeting-for-planning-sprint-28/
LOCATION:Chalmers\, Lindholmen\, Hörselgången 5\, Gothenburg\, 41756\, Sweden
CATEGORIES:Meeting
ORGANIZER;CN="Jan Bosch":MAILTO:jan.bosch@chalmers.se
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Europe/Stockholm:20241216T090000
DTEND;TZID=Europe/Stockholm:20241216T093000
DTSTAMP:20260524T093223
CREATED:20240128T211452Z
LAST-MODIFIED:20240128T211452Z
UID:6334-1734339600-1734341400@www.software-center.se
SUMMARY:Coordination team meeting
DESCRIPTION:
URL:https://www.software-center.se/event/coordination-team-meeting-82/
LOCATION:Virtual meeting\, Sweden
CATEGORIES:Meeting
ORGANIZER;CN="Jan Bosch":MAILTO:jan.bosch@chalmers.se
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Europe/Stockholm:20241216T093000
DTEND;TZID=Europe/Stockholm:20241216T120000
DTSTAMP:20260524T093223
CREATED:20240128T211600Z
LAST-MODIFIED:20240128T211600Z
UID:6336-1734341400-1734350400@www.software-center.se
SUMMARY:Steering committee meeting
DESCRIPTION:
URL:https://www.software-center.se/event/steering-committee-meeting-17/
LOCATION:Chalmers\, Lindholmen\, Hörselgången 5\, Gothenburg\, 41756\, Sweden
CATEGORIES:Meeting
ORGANIZER;CN="Jan Bosch":MAILTO:jan.bosch@chalmers.se
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Europe/Stockholm:20241218T140000
DTEND;TZID=Europe/Stockholm:20241218T170000
DTSTAMP:20260524T093223
CREATED:20241114T092501Z
LAST-MODIFIED:20241114T201651Z
UID:7426-1734530400-1734541200@www.software-center.se
SUMMARY:PhD defense: Advancing Edge Intelligence - Federated and Reinforcement Learning for Smarter Embedded Systems
DESCRIPTION:. .\n\nCandidate: Hongyi Zhang\nVenue: Jupiter 473\, Chalmers University of Technology \nOpponent:\nXavier Franch\, Professor Informatics\, UPC\, Spain. https://www.upc.edu/gessi/personalpages/xfranch/ \nCommittee: \n\n\nChristian Kästner\, Associate Professor of CS\, CMU\, USA.\n\n\nHenry Muccini\, Professor CS\, University L’Aquila\, Italy.\n\n\nLuis Cruz\, Assistant professor CS\, TU Delft\, Netherlands\n\n\n\n\n\n\n\nAbstract:\nContext: The rapid growth of embedded devices and edge computing has brought new opportunities for creating intelligent systems. However\, these systems face challenges such as limited computational power and the need to protect user privacy. As a result\, there is a need for machine learning methods that can scale effectively\, maintain privacy\, and adapt to changing conditions in embedded applications.\n \nObjective: This thesis focuses on improving the performance of machine learning models in embedded systems by using federated learning and reinforcement learning. The main goal is to develop methods that allow edge devices to work together without sharing raw data\, which helps maintain privacy. Another goal is to make these systems more adaptable to dynamic environments\, so they can perform better under changing conditions. Additionally\, the research seeks to improve the efficiency of communication and computation across devices.\n \nMethod: The research uses a mix of case studies\, simulations and real-world experiments. Federated learning is applied to allow edge devices to train models without centralizing the data\, keeping sensitive information local. Reinforcement learning is used to help devices learn how to make better decisions by interacting with their environment. These two methods is tested in different scenarios to evaluate improvements in model accuracy\, resource use\, and adaptability.\n \nResults: The results of this thesis highlight significant advancements in federated learning (FL) and reinforcement learning (RL) for embedded systems. A comprehensive literature review identified six key challenges and open research questions in FL\, emphasizing the need for efficient communication\, scalability\, and privacy preservation. Case studies in telecommunications and automotive applications demonstrated that FL\, particularly with asynchronous aggregation protocols\, improves model performance\, reduces communication overhead\, and speeds up training in real-time\, dynamic environments. Novel algorithms\, such as AF-DNDF and deep RL approaches\, further enhanced decision-making capabilities and adaptability in applications like autonomous driving and UAV base station deployment for disaster scenarios. The development of frameworks like EdgeFL provided practical solutions to overcome FL’s implementation challenges\, offering scalable\, low-effort alternatives. Overall\, the integration of FL and RL into embedded systems resulted in improved model accuracy\, resource utilization\, and adaptability\, making these approaches highly suitable for real-world industrial use cases.\n \nConclusion: This research advances the field of edge intelligence by providing a practical approach to deploying machine learning models that are scalable\, privacy-focused\, and adaptive in embedded systems. The work demonstrates clear improvements in performance and offers a foundation for future research\, which could explore more complex learning approaches and apply these techniques to a wider range of embedded systems.
URL:https://www.software-center.se/event/smarter-embedded-systems/
LOCATION:EDIT Jupiter 473\, Hörselgången 5\, Hörselgången 5\, Gothenburg
CATEGORIES:PhD defense
ORGANIZER;CN="Helena Holmstr%C3%B6m Olsson":MAILTO:helena.holmstrom.olsson@mau.se
END:VEVENT
END:VCALENDAR