A 95% accurate EEG-connectome processor for a mental health monitoring system

Abstract

An electroencephalogram (EEG)-connectome processor is proposed for a mental health monitoring system. The proposed processor computes synchronization likelihood (SL) as the connectome feature. A sparse matrix inscription (SMI) scheme is proposed to reduce the memory size to 1/24 during SL calculation. From the calculated SL information, radial basis function (RBF) kernel-based support vector machine (SVM) diagnoses user's mental health condition. For RBF kernels, lookup-tables (LUTs) are used to replace the floating-point operations, decreasing the required operation by 54%. The EEG-connectome processor improves the diagnosis accuracy from 89% to 95% in Alzheimer's disease case. The proposed processor occupies 3.8 mm2 and consumes 1.71mW with 0.18μm CMOS technology.