Vi utbildar för framtiden och skapar samhällsnytta genom vår forskning som levandegörs i nära samarbete med näringslivet. Vi bedriver forskning inom computer science, datateknik, software engineering och interaktionsdesign - från grundforskning till direkta tillämpningar. Institutionen har en stark internationell prägel och är delad mellan Chalmers och Göteborgs universitet.
We are engaged in research and education across the full spectrum of computer science, computer engineering, software engineering, and interaction design, from foundations to applications. We educate for the future, conduct research with high international visibility, and create societal benefits through close cooperation with businesses and industry. The department is joint between Chalmers and the University of Gothenburg.
(2022) Davidsson, Adam; Larsson, Simon; Chalmers tekniska högskola / Institutionen för data och informationsteknik; Angelov, Krasimir; Abd Alrahman, Yehia
The automotive industry is a promising environment for machine learning. However,
current machine learning techniques do not meet all the requirements of many possible
applications. Requirement such as privacy preservation, limited communication
and semi-supervision. To satisfy these requirements, this thesis proposes a simple
distributed semi-supervised algorithm (distributed FixMatch). Furthermore, we apply
this algorithm to a real-world problem, detecting road surface types from audio.
In applying the semi-supervised algorithm to this problem, we also propose a simple
augmentation technique for audio features. The proposed algorithm was tested on
two real datasets, where the algorithm was compared to a supervised training algorithm.
The results suggest that the algorithm successfully leveraged unlabeled data.
Furthermore, a theoretical analysis and a simulation show that the communication
cost of the proposed algorithm was lower than federated or centralized alternatives.
(2023) Bergman, Frans; Choudhari, Shubhankar; Chalmers tekniska högskola / Institutionen för data och informationsteknik; Chalmers University of Technology / Department of Computer Science and Engineering; Ahrendt, Wolfgang; Abd Alrahman, Yehia
Complex network layouts, currently used by internet service providers and large corporate networks, have lead to a phenomenon known as asymmetric routing. That is, the two directions of a traffic flow take different paths through the network. This poses a challenge for network management systems, which typically require knowledge of both directions of traffic to perform classification and statistics collection. In this thesis, we apply formal methods to identify and suggest solutions to issues in such a system. The system is called FlowSync, and has been developed at Sandvine for use in its internet traffic management product. The latter is an international company providing systems for classifying and managing internet traffic. We model three distinct components of FlowSync; classifier sharing, statistics synchronization and link redundancy, and identify potential issues and limitations in all three. Two of these limitations are consequences of known problems in distributed system design, and the relation to these problems is discussed, as well as known techniques for working around them.