Natan Lubman
Head of Algorithms, CardiacSense
Biosensing – Application and Possibilities of Long-term Monitoring on Healthcare
In this talk we will discuss the unique opportunities that different biosensors give us in different health applications. What separates the different types of signals acquired from these sensors and the tools we can use to analyze them. Lastly, how new developments in machine learning can help make long and short term predictions.
Ori Bryt
Research and teaching assisant at SIPL
Review of SIPL activity in “Smart Imaging” consortium
A MAGNET program - Israel Innovation Authority, Ministry of Innovation, Science and Technology, 2019-2023
1. Sensor-level compression of infra-red video signals (in collaboration with SCD).
2. Denoising and enhancing of depth video signals (in collaboration with NSI).
Amitay Bar
Ph.D. candidate under the supervision of Prof. Ronen Talmon
Riemannian Geometry in Array Signal Processing
In this talk, I will address the problem of estimating the direction of arrival of desired acoustic sources in the presence of multiple acoustic interference sources. All the sources are located in noisy and reverberant environments and are received by a microphone array. I will present a new approach for designing beamformers based on the Riemannian geometry of the manifold of Hermitian positive definite matrices. Specifically, I will show that incorporating the Riemannian mean of the spatial correlation matrices into frequently-used beamformers gives rise to beam patterns that reject the directions of interference sources and result in a higher signal-to-interference ratio. Throughout the talk, I will experimentally demonstrate the advantages of our approach in designing several beamformers in the presence of simultaneously active multiple interference sources.