معرفی
Sebastian Hönel is a postdoctoral researcher at Linnaeus University, affiliated with the Faculty of Technology and the Department of Computer Science and Media Technology. He is an active member of the Data Intensive Software Technologies and Applications (DISTA) research group and currently serves as a co-Principal Investigator in the project "In-line visual inspection using unsupervised learning" focused on manufacturing defect detection using machine learning techniques.
Hönel completed his Doctoral Thesis in 2023 titled "Quantifying Process Quality: The Role of Effective Organizational Learning in Software Evolution" and earned his Licentiate Thesis in 2020 on "Efficient Automatic Change Detection in Software Maintenance and Evolutionary Processes," both from Linnaeus University. His educational background demonstrates a strong foundation in software engineering and data analysis.
Hönel's research spans software engineering, machine learning, and data science. Initially focusing on applying Machine Learning and Deep Learning to software evolutionary processes and organizational learning, his current work emphasizes unsupervised and zero/few-shot learning techniques for industrial anomaly detection. He has particular expertise in Deep Density Estimation (especially Normalizing Flows) and Representation Learning, with applications in manufacturing quality assessment and software maintenance. His research interests include anomaly detection methodologies, architectural innovations in autoencoders, and methodological considerations for evaluation metrics in machine learning applications.
An analysis of his publication record reveals a consistent focus on bridging software engineering with advanced machine learning techniques. His most recent work shows a strategic shift toward industrial applications of unsupervised learning, particularly in manufacturing defect detection, while maintaining his foundational work in software metrics and quality assessment. The publications demonstrate progression from theoretical software metrics to practical applications of deep learning in quality inspection systems.
Hönel actively contributes to academic education by teaching (Deep) Machine Learning courses (4DV652, 4DV660, 4DV661) and previously served as a teaching assistant for agile product development courses (1DV508, 4DV611). His role as co-PI on the visual inspection project indicates successful research funding and leadership capabilities. While specific grant details aren't provided in the available information, his position suggests ongoing research support.
As part of the DISTA research group, Hönel collaborates extensively with colleagues including Ericsson, Löwe, and Wingkvist on projects that combine software engineering with advanced data analysis techniques. His work environment supports interdisciplinary research at the intersection of computer science, software engineering, and machine learning applications, with particular emphasis on practical implementations in both software development contexts and manufacturing quality control systems.
