Low-Power Hardware Implementation of a Support Vector Machine Training and Classification for Neural Seizure Detection

In this paper, a low power support vector machine (SVM) training, feature extraction, and classification algorithm are hardware implemented in a neural seizure detection application. The training algorithm used is the sequential minimal optimization (SMO) algorithm. The system is implemented on different platforms: such as field programmable gate array (FPGA), Xilinx Virtex-7 and application specific integrated circuit (ASIC) using hardware-calibrated UMC 65 nm CMOS technology. The implemented training hardware is introduced as an accelerator intellectual property (IP), especially in the case of large number of training sets, such as neural seizure detection. Feature extraction and classification blocks are implemented to achieve the best trade-off between sensitivity and power consumption. The proposed seizure detection system achieves a sensitivity around 96.77% when tested with the implemented linear kernel classifier. A power consumption evaluation is performed on both the ASIC and FPGA platforms showing that the ASIC power consumption is improved by a factor of 2X when compared with the FPGA counterpart.

I. Introduction

Epilepsy is a neurological disorder characterized by recurrent seizures as a result of abnormal electrical discharges in the brain. The condition affects approximately 1–2% of the world’ s population [1]. The sudden and unpredictable nature of seizures is one of the most disabling aspects of epilepsy disease [2]. Anti-epileptic drugs (AEDs) are used to affect the brain's chemistry to reduce epilepsy. AEDs’ main disadvantage is that they are utterly experimental; AED type and concentration are adopted for each case individually [3]. Electrical stimulation is used to overcome this problem by reducing the effects of epilepsy. The stimulation is applied only when a seizure takes place. Accordingly, seizure detection and prediction become very important. In this paper, a hardware implemented system that uses EEG signals to aid seizure detection is proposed.