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

• Published in: IEEE transactions on biomedical circuits and systems Vol. 13; no. 6; pp. 1324 - 1337
• Main Authors: Elhosary, Heba, Zakhari, Michael H., Elgammal, Mohamed A., Abd El Ghany, Mohamed A., Salama, Khaled N., Mostafa, Hassan
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.12.2019; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Accelerator IP; Acidity; Algorithms; Application specific integrated circuits; ASIC; Classification; CMOS; Early Diagnosis; Electrodes, Implanted; Electroencephalography; Electroencephalography - instrumentation; Feature extraction; Field programmable gate arrays; FPGA; Hardware; Humans; Integrated circuits; Intellectual property; low power; Optimization; Platforms; Power consumption; Seizures; Seizures - diagnosis; Semiconductors; Sensitivity; Sensitivity and Specificity; sequential minimal optimization (SMO); Signal Processing, Computer-Assisted; Sodium channels; Support Vector Machine; support vector machine (SVM); Support vector machines; Training
• ISSN: 1932-4545; 1940-9990
• DOI: 10.1109/TBCAS.2019.2947044

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.