Smart Sensor Systems 2018

Smart Sensor Systems 2018

This course addresses the design and development of smart sensor systems. After a general overview, various key aspects of sensor systems are discussed: measurement and calibration techniques, the design of precision sensor interfaces, analog-to-digital conversion techniques, and sensing principles for the measurement of magnetic fields, temperature, capacitance, acceleration and rotation. The state-of-the-art smart sensor systems covered by the course include smart magnetic-field sensors, smart temperature sensors, physical chemosensors, multi-electrode capacitive sensors, implantable smart sensors, DNA microarrays, smart inertial sensors, smart optical microsystems and CMOS image sensors. A systematic approach towards the design of smart sensor systems is presented. The lectures are augmented by case studies and hands-on demonstrations.

Additional information ...

MSc CE Thesis Presentation

Energy Efficient Feature Extraction for Single-Lead ECG Classification Based On Spiking Neural Networks

Eralp 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.