Josef Spillner

SSBD Basel 2024 Speakers - Josef Spillner

Dr.-Ing. habil. Josef Spillner is a senior lecturer / associate professor for computer science at Zurich University of Applied Sciences, Switzerland. His research activity focuses on distributed application computing paradigms. Particular emphasis is on technological support for emerging digitalisation needs of industry and society, such as smart cities, mobility and the environment. In these application fields he investigates technologies such as cloud/edge computing, big data and cyber-physical systems. His research projects are funded by the SNSF, Innosuisse, SERI, European Commission and directly by industry partners. In recent years, he has served in various roles (advisor, expert, evaluator) in Horizon Europe, CHIST-ERA, and national funding agencies. He is a senior member of IEEE, member of ACM and national professional societies, member of the Swiss Informatics Research Association, alumnus of the Marie Skłodowska-Curie Actions (MSCA), and fellow of the digitalisation initiative of the canton of Zurich (DIZH).

Data Science and Artificial Intelligence supporting Product Design

Physical products design is concerned with ingredients, formulations, quantities, sourcing, manufacturing and packaging processes, and foreseeing the path of the product along the lifecycle from design over production to the customers including logistics and marketing. Through complete specifications and digital twins, a lot of data has increasingly become available about all of these product design and lifecycle aspects. Exploiting that data for the benefit of reduced health hazards and improved environmental footprint can lead to safer and more sustainable designs of new products, but also greener redesigns of existing products. In addition to that, it also helps manufacturers to comply with new regulations around digital product passports, reports generation, and export opportunities.

This talk first gives an overview about the data perspective related to product design. It proceeds to explain a distributed systems perspective on how such data could be organised and used to achieve this goal. For that matter, it introduces the concepts of linked data and large-scale distributed data processing, and explains how confidential product design data can be linked up with open government data such as regulatory limits. Moreover, it dives into subsequent graph mining and other data science techniques to get insights and to produce actionable advice for decision makers. Those include product designers, customers and regulators, all of whom have a different perspective. Tolerance thresholds differ and customers are sometimes less concerned, sometimes more concerned than regulators about the implication of substances and effects. Hence, producing meaningful statements for those target groups while protecting business interests around confidential information remains a key challenge in this regard. But likewise, the internal insights for the manufacturer need to be effectively collected and conveyed. In the final part of the talk, the readiness of today's data science infrastructure for data-driven product design is discussed in conjunction with a view on available data in the health and environmental domains. This discussion encompasses an applied view on similar data-driven decision support systems built in Switzerland, and motivates to build a domain-specific product design platform with built-in data aggregation and exploitation capabilities.