Real-time processing of temporal data
The group would deal with design of a system that can perform tasks such as ECG (Echo-cardiogram) pattern classification or EMG (Electromyogram) classification.
The focus would to think of a system-level architecture with a necessary software and hardware framework that can implement a pattern recognition task in real-time. A candidate application is monitoring of ECG data. The complete system needs to be implantable. The design constraints are low-power, reliability, and on-chip computation because it may not be possible to transmit data off-chip.
Some of the issues to be considered are:
1. What kind of adaptive and/or learning algorithms should be implemented on the chip?
2. The division of labor between the hardware and software sub-systems on the chip.
3. Can we implement a pre-trained network that can adapt to changing environmental conditions?
4. How much of the processing can be done on-line?
5. What are the circuits and hardware subsystems required?
No timetable published yet.