IEEE Finland Workshop on Signal Processing and Circuits and Systems
05.10.2022.
Click here for a free registration.
This one-day workshop is organized by the IEEE Finland Jt. Chapter SP/CAS. It consists of expert talks as well as presentations of candidates for the chapter best paper award. The list of candidates for the best paper award can be found here: click me.
The workshop is organized as a hybrid event, with the in-person component taking place in the lecture hall Lumituuli in the Dipoli building of Aalto University, Otaniemi, Espoo.
Schedule (times are EEST, local Helsinki time)
09:00 - 09:15 am
Arrival and Coffee.
09:15 - 10:00 am
Chapter Report.
Chapter Chair Alexander Jung
zoom link: TBA
10:00 – 11:00 am
Title: Neighborhood Representative for Improving Outlier Detectors
Speaker: Dr. Jiawei Yang
Abstract:
Over the decades, traditional outlier detectors have ignored the group-level factor when calculating
outlier scores for objects in data by evaluating only the object-level factor, failing to capture the
collective outliers. To mitigate this issue, we present a method called neighbourhood representative (NR),
which empowers all the existing outlier detectors to efficiently detect outliers, including collective
outliers, while maintaining their computational integrity. It achieves this by selecting representative
objects, scoring these objects, then applies the score of the representative objects to its collective
objects. Without altering existing detectors, NR is compatible with existing detectors, while improving
performance on eleven real world datasets with +8% (0.72 to 0.78 AUC) on average relative to twelve
state-of-the-art outlier detectors.
zoom link: TBA
11:00 - 12:00 am
Best Paper Award Candidate Presentation
Dr. Zitong Yu (website)
12:00 - 13:00 am
Lunch in Restaurant Metso (Dipoli)
13:00 - 14:00 am
Best Paper Award Candidate Presentation
Dr. Rui Gao (website)
14:00 - 16:00 pm
Title: Deep-Learning for the Physical Layer with Sionna
Speaker: Dr. Jakob Hoydis (website)
Abstract: Sionna is an open-source, GPU-accelerated, and fully differentiable link-level simulator for 6G
research. One of its main features is automatic gradient computation through an entire end-to-end system
which allows for seamless integration and training of neural networks. After a short introduction explaining
the motivation behind Sionna, its features and design principles, I will discuss several of our recent
research results, including synchronization for NB-IoT as well as GNN-based channel decoding.
16:00 - 17:00 pm
Best Paper Award Candidate Presentation
Dr. Robin Rajamäki (website)
talk recording: click here.
offline
Best Paper Award Candidate Presentation
Dr. Andreas Hauptmann (website)
talk recording: click here.
Acknowledgment
This workshop is supported by the IEEE Signal Processing Society and the Department of Computer Science at Aalto University and TalTech Industrial project (European Union’s Horizon 2020 research and innovation programme under grant agreement No 952410). We also acknowledge support received from the Academy of Finland, via the project ‘‘Intelligent Techniques in Condition Monitoring of Electromechanical Energy Conversion Systems,’’ (decision number 331197).
