Post Date
Mar 1 2021

Neurological Disorders and Efficient Hardware

Written by Dr. Awais Bin Altaf, who is Assistant Professor at the Department of Electrical Engineering, SBASSE, LUMS.

Dr. Awais Bin Altaf, and his PhD student Abdul Rehman Aslam, at the SBASSE Department of Electrical Engineering, have recently published their research in IEEE Transactions on Biomedical Circuits and Systems, one of the leading journals in the field.

The team came up with an idea of developing efficient hardware for the classification of Chronic Neurological Disorders (CND’s) in a non-invasive fashion. The method involves long term continuous monitoring with neurofeedback of human emotions for patients with CND’s to mitigate its harmful effect. This work presents hardware-efficient and dedicated human emotion classification processor for CND’s.

The scalp Electroencephalogram (EEG), also known in common parlance as a “brain wave,” is used for the emotion’s classification using the valence and arousal scales. A machine learning classifier is used along with carefully selected temporal and spectral features suitable for a wearable non-invasive classification system.

This work is among one of the first digital integrated circuit (IC) processor designed and implemented in

Pakistan with indigenous grant and the results are based on actual silicon measurement after fabrication. The team first presented the initial idea of the system at the IEEE International Symposium on Circuits and Systems organised in Japan in 2019 on a field programming gate array (FPGA).

The research team is now working on the second generation of the system and plans to integrate the processor with an analog front end making the overall system miniaturized to fit onto a patch sensor for long term continuous monitoring, recording, and neuro feedback onto a single chip and performing a real-time measurement on CND patients.


A. R. Aslam, T. Iqbal, M. Aftab, W. Saadeh and M. A. Bin Altaf, “A10.13uJ/classification 2-channel Deep Neural Network-based SoC for Emotion Detection of Autistic Children,” 2020 IEEE Custom Integrated Circuits Conference (CICC), Boston, MA, USA, 2020, pp. 1-4, doi: 10.1109/CICC48029.2020.9075952.