https://scholars.lib.ntu.edu.tw/handle/123456789/634609
標題: | A 96.2-nJ/class Neural Signal Processor with Adaptable Intelligence for Seizure Prediction | 作者: | Hsieh, Yi Yen Lin, Yu Cheng CHIA-HSIANG YANG |
關鍵字: | Closed-loop system | digital CMOS integrated circuits | neuromodulation | seizure prediction | support vector machine (SVM) | 公開日期: | 1-一月-2023 | 卷: | 58 | 期: | 1 | 來源出版物: | IEEE Journal of Solid-State Circuits | 摘要: | This work presents the world's first neural signal processor for seizure prediction, which includes a preprocessing unit, a feature extractor, a reconfigurable support vector machine (SVM) kernel, and a postprocessing unit. Seizure prediction performance is enhanced by on-chip training for model adaptation. Design optimization is applied across the layers of abstraction to minimize the area and energy. The area of the feature extractor is reduced by 28% with an approximated energy operator (AEO). The proposed scaling-based Newton-Raphson (NR) divider reduces the required number of iterations for division by 62.5%. For alternating direction method of multipliers (ADMM)- based SVM training, the computational complexity is reduced by up to 99.9% through pointer-based matrix multiplication. By leveraging the LDL decomposition, 80% multiplications for updating weights are saved. The chip achieves a seizure prediction performance with a 92.0% sensitivity and a 0.57/h false alarm rate (FAR). The training latency is 8.44 ms with a power dissipation of 2.31 mW at 6.05 MHz. Compared with an ARM Cortex-M3 microcontroller, this work achieves a 124× higher area efficiency and a 299× higher energy efficiency. The chip also supports seizure detection and achieves a sensitivity of 98.6% and an FAR of 0.18/h, exceeding the state-of-the-art designs. |
URI: | https://scholars.lib.ntu.edu.tw/handle/123456789/634609 | ISSN: | 00189200 | DOI: | 10.1109/JSSC.2022.3218240 |
顯示於: | 電機工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。