Avi Presents SPIRIT Seizure Prediction SoC at VLSI 2024

Rikky Muller, Aviral Pandey, and Adelson Chua pictured at the 2024 IEEE VLSI Circuits Symposium in Honoloulu, Hawaii.

Graduate student Aviral Pandey and former graduate student Dr. Adelson Chua authored “SPIRIT: A Seizure Prediction SoC with a 17.2 nJ/cls Unsupervised Online-Learning Classifier and Zoom Analog Frontends,” which was presented by Avi at the 2024 VLSI Circuits Symposium. The paper was selected as the highlighted paper in biomedical circuits for the conference. Co-authors include former and current lab members Dr. Ryan Kaveh, Dr. Sina Faraji Alamouti, and Justin Doong.

SPIRIT is an SoC integrating an unsupervised online-learning seizure prediction classifier with eight 14.4μW, 0.057mm2, 90.5dB dynamic range, Zoom Analog Frontends. SPIRIT achieves, on average, 97.5%/96.2% sensitivity/specificity, predicting seizures an average of 8.4 minutes before they occur. Its classifier consumes 17.2μW and occupies 0.14mm2, the lowest reported for a prediction classifier by >134x in power and >5x in area.

Read the paper here.