基于深度学习的癫痫识别软硬件协同设计
Co-Design of Software and Hardware for EEG Epilepsy Recognition Based on Deep Learning
DOI: 10.12677/AIRR.2022.111008, PDF,   
作者: 谈宇轩：南开大学人工智能学院，天津；涂淑琴*：华南农业大学数学与信息学院，广东 广州
关键词: 深度学习；脑电癫痫识别；软硬件协同设计；Deep Learning； EEG Epilepsy Recognition； Co-Design of Software and Hardware
摘要: 针对人工识别脑电图(EEG)的癫痫发作的低效以及现有自动识别算法的高开销等问题，本文提出了一种基于深度学习的癫痫识别的软硬件协同设计。软件部分提出了一种基于深度学习的癫痫识别模型，该模型的正确率在CHB-MIT数据集上能够达到97.08%的同时，尺寸与运算量仅为现有同类方案的20%。硬件部分提出了一种卷积神经网络处理器结构，该结构能够有效提升运算效率，在FPGA平台上完成一次癫痫识别过程仅需要0.6 ms。
Abstract: To cope with the low efficiency by artificial cognition of epileptic seizure whilst high expense by current automatic recognition algorithm, this work proposes the co-design of software and hardware for EEG epilepsy recognition on basis of deep learning. The software provided a recognition model of EEG epilepsy based on deep learning. The corresponding accuracy reached 97.08% in CHB-MIT data set, yet the size and computation is only 20% of the existing scheme. In the hardware part, an efficient convolutional neural network hardware accelerator structure is proposed, which can effectively improve the computing efficiency. It only takes 0.6 ms to complete one EEG Epilepsy recognition process on the FPGA platform.
文章引用：谈宇轩, 涂淑琴. 基于深度学习的癫痫识别软硬件协同设计[J]. 人工智能与机器人研究, 2022, 11(1): 65-72. https://doi.org/10.12677/AIRR.2022.111008

参考文献

[1] 姬哨晗. 基于深度学习的脑电波异常检测的研究与实现[D]: [硕士学位论文]. 北京: 北京邮电大学, 2021.
[2] 汤立汉. 基于脑电的癫痫监测关键技术研究[D]: [博士学位论文]. 杭州: 浙江大学, 2021.
[3] 穆建秋. 基于深度主动学习的癫痫检测[D]: [硕士学位论文]. 贵阳: 贵州师范大学, 2021.
[4] Tian, X., Deng, Z., Ying, W., Choi, K.-S., Wu, D., Qin, B., et al. (2019) Deep Multi-View Feature Learning for EEG-Based Epileptic Seizure Detection. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 27, 1962-1972. [Google Scholar] [CrossRef] 
[5] Liu, Z., Meng, L., Zhang, X., Fang, W. and Wu, D. (2021) Universal Adversarial Perturbations for CNN Classifiers in EEG-Based BCIs. Journal of Neural Engineering, 18, Article No. 0460a4. [Google Scholar] [CrossRef] [PubMed]
[6] Ranjan, J. and Mukherjee, I. (2021) Deep Learning Based Efficient Epileptic Seizure Prediction with EEG Channel Optimization. Biomedical Signal Processing and Control, 68, Article ID: 102767. [Google Scholar] [CrossRef] 
[7] Lin, Z., Qiu, T., Liu, P., Zhang, L., Zhang, S. and Mu, Z. (2021) Fatigue Driving Recognition Based on Deep Learning and Graph Neural Network. Biomedical Signal Processing and Control, 68, Article ID: 102598. [Google Scholar] [CrossRef] 
[8] Andreas, B., Schneider, M., Francis, M.A., Lehmann, H.M., Barg, I., Buschhoff, A.-S., et al. (2021) Epileptic Seizure Detection on an Ultra-Low-Power Embedded RISC-V Processor Using a Convolutional Neural Network. Biosensors, 11, Article No. 203. [Google Scholar] [CrossRef] [PubMed]
[9] Al Saegh, A., Dawwd, S.A. and Abdul-Jabbar, J.M. (2021) An Augmentation Method for EEG Classification. Neural Networks, 141, 433-443. [Google Scholar] [CrossRef] [PubMed]
[10] 费洪磊. 基于深层神经网络的癫痫脑电不平衡分类研究[D]: [硕士学位论文]. 济南: 山东师范大学, 2021.
[11] 程鹏. 基于EEG的癫痫检测系统[D]: [硕士学位论文]. 成都: 电子科技大学, 2021.
[12] 曾笛飞. 基于层次图卷积神经网络的EEG癫痫检测[D]: [硕士学位论文]. 杭州: 浙江大学, 2020.
[13] 侯金泽. 基于EEG时空特性的癫痫发作预测算法研究[D]: [硕士学位论文]. 北京: 北京工业大学, 2020.
[14] 王耀民. 基于深度神经网络迁移特征学习的癫痫发作检测研究[D]: [硕士学位论文]. 杭州: 杭州电子科技大学, 2020.
[15] 龚旭辉. 基于机器学习的癫痫EEG信号分类算法探究[D]: [硕士学位论文]. 广州: 广东工业大学, 2020.

为你推荐