- Monday, 14 -- Wednesday, 16 May 2018
27th Workshop on Advances in Analog Circuit Design
The AACD workshops are a high-quality series of events held all over the world. They have been held annually since 1992 with the aim of bringing together a large group of people working at the forefront of analog circuit design. The workshops offer the opportunity to discuss new possibilities and future developments whilst networking with key figures from across the analog design community.Additional information ...
Dutch Ultra Low Power Conference
- Wednesday, 7 March 2018
- Novio Tech Campus, Nijmegen, NL
The medicine of the future you’ll need to take only once, and it’s a bioelectronic oneWouter Serdijn
The Dutch Ultra Low Power Conference brings together Belgian and Dutch professionals and companies involved in the development and application of devices with ultra low power technologies. It targets engineers, designers and technical managers in the advanced field of energy harvesting and ultra low power and energy-efficient designs. The keynote will be given by Wouter Serdijn, professor of bioelectronics at Delft University of Technology.Additional information ...
MSc CE Thesis Presentation
- Friday, 23 February 2018
- EWI HB 17.150
Energy Efficient Feature Extraction for Single-Lead ECG Classification Based On Spiking Neural NetworksEralp Kolagasioglu
Cardiovascular diseases are the leading cause of death in the developed world. Preventing these deaths, require long term monitoring and manual inspection of ECG signals, which is a very time consuming process. Consequently, a wearable system that can automatically categorize beats is essential.
Neuromorphic machines have been introduced relatively recently in the science community. The aim of these machines is to emulate the brain. Their low power design makes them an optimal choice for a low power wearable ECG classifier.
As features are crucial in any machine learning system, this thesis aims at proposing an energy efficient feature extraction algorithm for ECG arrhythmia classification using neuromorphic machines. The feature extraction algorithm proposed in this thesis consists of the merger of a low power feature detection and a feature selection algorithm. Also, different network configurations have been investigated to achieve classification using an LSM architecture. The resulting system can accurately cluster seven beat types, has an overall classification rate of 95.5%, and consumes an estimate of 803.62 nW.
MSc SS Thesis Presentation
- Friday, 16 February 2018
- EWI Room Electron, (HB first floor, behind the kitchen)
The cocktail party problem: GSVD-beamformers in reverberant environmentsDerk-Jan Hulsinga
Hearing aids as a form of audio preprocessing is increasingly common in everyday life. The goal of this thesis is to implement a blind approach to the cocktail party problem and challenge some of the regular assumptions made in literature. We approach the problem as wideband FD-BSS. From this field of research, the common assumption of continuous activity is dropped. Instead a number of users detection is implemented as a preprocessing step and ensure the appropriate number of demixing vectors for each time frequency bin. The validity of the standard mixing model used for STFT’s is challenged by looking at the response of a linear array.
Source separation is achieved by demixing vectors based on the GSVD, derived in a model-based approach. While most permutation solvers offer an a posteriori solution for all users, we looked at finding local solutions for a single user. Combining this with the user identification called the alignment step, we conclude that the permutation problem can be reduced to selecting a demixing vector for each discrete time-frequency instance. The correlation coefficient proves to be a sufficient metric to couple reconstructions to the original data as it selects most of the active time-frequency bins.
In simulations, our demixing vectors achieve comparable inteligibility, measured by STOI, as the compared techniques and it is more robust against smaller sample sizes than the theoretically SINR optimal MVDR.Additional information ...