Examensarbeten för masterexamen

Browse

Senast publicerade

Visar 1 - 5 av 1737
  • Post
    Wireless Monitoring Tool for BLE Mesh Networks
    (2024) PULS, TOMASS; Chalmers tekniska högskola / Institutionen för data och informationsteknik; Chalmers University of Technology / Department of Computer Science and Engineering; Larsson-Edefors, Per; Linde, Arne
    This thesis aims to address the limitations of existing wired monitoring solutions for Bluetooth Low Energy (BLE) mesh networks by developing a wireless monitoring tool. The tool is designed to simplify network management and provide performance insights. The thesis focuses on the development of a dedicated hardware tool using the nRF5340 DK, implementation of data analysis software, and creation of a userfriendly graphical user interface (GUI) to monitor and visualize key performance metrics such as Message Delivery Ratio (MDR), throughput, and latency in BLE mesh networks. The methodology involved constructing a hardware tool for wireless data capture, developing Python-based software for data analysis, and designing a GUI for realtime data visualization. Extensive testing was conducted in various mesh network topologies to evaluate the tool’s performance. The tool demonstrated robust performance in accurately measuring MDR and latency across different network setups. The wireless monitoring tool successfully provides a non-intrusive, user-friendly solution for real-time analysis of BLE mesh networks. It offers valuable insights into network performance and health, making it a practical tool for both academic research and industrial applications. Future work could extend the tool’s capabilities to multiple measurement points and multi-channel analysis.
  • Post
    Improving Artificial Intelligence Through User Feedback in eXplainable Artificial Intelligence (XAI) Systems - Design Recommendations for Sustaining Long-Term Human- XAI Interaction in Industry 4.0
    (2024) Hashmati, Negin; Wärnberg, Hugo; Chalmers tekniska högskola / Institutionen för data och informationsteknik; Chalmers University of Technology / Department of Computer Science and Engineering; Dahlstedt, Palle; Obaid, Mohammad
    This thesis explores Human-XAI interaction and the vital role of user motivation in providing feedback to XAI systems in industrial settings, focusing on the design of Incremental Explanatory Training (IET) components that enable feedback. A welladjusted XAI interface is necessary for feedback provision and in turn, the feedback is used to improve the accuracy of the Artificial Intelligence. Drawing from the interdisciplinary field of XAI, the industry 4.0 context, and User-Centered Design (UCD) practices, it investigates the motivations required for sustained user engagement, identifies interface components that enhance feedback provision, and offers design recommendations for optimizing the user experience and sustaining motivation for feedback provision. This research addresses three key questions: 1) the types of motivations necessary for user feedback, 2) the interface components fostering motivation, and 3) design recommendations for effective feedback mechanisms adhering to motivation. As a result of this research, it was shown that both extrinsic and intrinsic motivations are necessary to encourage sustained feedback provision and that interface components with XAI improvement statistics and effective interaction modalities are vital for fostering motivation. Eight design recommendations were identified that offer generalized insights into important considerations for IET components to contribute to sustained motivation and user engagement for feedback provision.
  • Post
    UI for Remote Operation of Drones - Designing a user interface for simultaneously operating multiple automated drones remotely in support of sea rescue missions
    (2024) Holmqvist, Alicia; Olsson, Stina; Chalmers tekniska högskola / Institutionen för data och informationsteknik; Chalmers University of Technology / Department of Computer Science and Engineering; Björk, Staffan; Samuelsson Gamboa, Mafalda
    Drones are increasingly used as tools across various domains, and the Swedish Sea Rescue Society (SSRS) sees potential in utilizing them to aid sea rescue missions. Their Eyes-On-Scene project aims to streamline their rescue missions by deploying a drone immediately upon receiving an alarm, providing real-time footage of the site to the crew who can prepare according to the situation. In cases where multiple alarms are received simultaneously, it would be advantageous if a single remote operator could manage multiple drones – a possibility explored through this thesis. In response, the project followed an iterative design and evaluation process, incorporating interaction design methodology within phases of research, analysis, synthesis, and realisation. Findings from the process resulted in a set of nine key considerations, highlighting factors of user control, customisability and personalisation, cognitive load, situational awareness, and system transparency and feedback. The considerations are a product of the design process, which additionally produced a high-fidelity prototype of an interface adhering to these principles. The prototype is paired with annotations and is a direct deliverable to SSRS as well as a contribution to design practitioners. Additionally, this thesis provides valuable insights for researching or developing a multi-control drone UI in a sea rescue context. Potential future work is discussed in the report, highlighting the need to further evaluate the considerations.
  • Post
    Real-time physically based snake scale rendering
    (2024) Bie , Yuanshan; Jiang, Mingxiao; Chalmers tekniska högskola / Institutionen för data och informationsteknik; Chalmers University of Technology / Department of Computer Science and Engineering; Assarsson, Ulf; Sintorn, Erik
    There are thousands of types of snakes in the world, and many of them have a unique snake skin appearance caused by the complex structure on their surface. To create and render physically realistic snake skins in application in real time, we need to efficiently and accurately express the visual effects that snake skins should have. In our work, we model the complex multi-layer structure of the snake skin surface as a multi-layer BRDF and integrate it into a physically based rendering model. We show the results of using this lighting model to render snakes under different parameters and configurations, and show that our model can match the appearance of real-life snake skin to a certain extent. We also implement a procedural texture generation model that can synthesize various textured skin patterns of snakes and efficiently provide the special texture required for our proposed model. The generator uses image processing to generate textures. The results show good visual similarity to the real snake skins.
  • Post
    Designing with AI - Assessing the state of play of AI co-creation in web design
    (2024) HELDTANDER, CLARA; Chalmers tekniska högskola / Institutionen för data och informationsteknik; Chalmers University of Technology / Department of Computer Science and Engineering; Björk, Staffan; Ljungblad, Sara
    Given the growing use of AI-supported design tools and the existing research-practice gap in Human-Computer Interaction (HCI), there are valid reasons to assess the state of play of AI co-creation in design. By surveying design practitioners, experiences, fears, and perceived benefits may be learned to help guide future research and create a starting point for the shaping of practical recommendations for leveraging of AI tools within the design domain. This study applied a mixed-method approach, surveying 71 design practitioners and interviewing seven to identify the perceived impact, risks, benefits, and concerns regarding AI co-creation. It was found that 76 percent of design practitioners engage in AI co-creation, extending over virtually the entire design process. Practitioners enjoy the perceived expedition of task initiation and the iterative work method that AI co-creation offers; however, they also raise several concerns such as data privacy, copyright, and potential knowledge loss. In addition, some experience a struggle to keep up with the rapid development of AI services, adding pressure on design practitioners. In conclusion, seven recommendations for designers, three for employers of design practitioners, and two for AI services were derived from the study results. Additionally, it was found that company culture regarding AI, the impact of AI co-creation on knowledge sharing in collaborative settings, and AI’s ability to reinforce, prevent, and be biased towards itself simultaneously are viable topics for future research.