Computer Science Professor Jason Cong and coauthors Zhe Chen, Andrew Howe, and Hugh T. Blair has received the best paper award at the 2018 ACM/IEEE International Symposium on Low Power Electronics and Design. Their paper, CLINK: Compact LSTM Inference Kernel for Energy Efficient Neurofeedback Devices, received this award at the ISLPED Symposium held in Seattle, WA, July 23-25, 2018. Dr. Zhe Chen is a postdoctoral researcher jointly supervised by Prof. Jason Cong from the Computer Science Department and Prof. Tad Blair from the Psychology Department. This paper presents a highly energy-efficient electroencephalography (EEG) signal processing accelerator for neurofeedback devices using the long short-term memory (LSTM) based neural network model. It has potential applications for treating neurological diseases such as Parkinsonism and epilepsy using neurofeedback deep brain stimulation.
ISLPED is the premier forum for presentation of innovative research in all aspects of low power electronics and design, ranging from process technologies and analog/digital circuits, simulation and synthesis tools, system-level design and optimization, to system software and applications. It is co-sponsored by the IEEE Circuits and Systems (CAS) Society and the ACM SIGDA. This year two papers (out of 150 submissions) were selected for the best paper award.