Design of a Sleep Modulation System with FPGA-Accelerated Deep Learning for Closed-loop Stage-Specific In-Phase Auditory Stimulation.
Design of a Sleep Modulation System with FPGA-Accelerated Deep Learning for Closed-loop Stage-Specific In-Phase Auditory Stimulation.
复制标题
采用 FPGA 加速深度学习的睡眠调制系统设计，用于闭环特定阶段同相听觉刺激。
DOI：
10.1109/iscas46773.2023.10181356
复制
发表时间：
2023
期刊：
影响因子：
--
通讯作者：
Liu,Xilin
中科院分区：
文献类型：
--
作者：
Sun,Mingzhe;Zhou,Aaron;Yang,Naize;Xu,Yaqian;Hou,Yuhan;Richardson,AndrewG;Liu,Xilin
闭环睡眠调节是一种新兴的研究范式，用于治疗睡眠障碍和提高睡眠益处。然而，两大障碍阻碍了这一研究范式的广泛应用。首先，受试者通常需要通过电线连接到机架式仪器来获取数据，这对睡眠质量产生了负面影响。其次，传统的实时睡眠阶段分类算法性能有限。在这项工作中，我们通过开发支持器件闭环操作的睡眠调制系统来克服这两个限制。睡眠阶段分类使用轻量级深度学习（DL）模型进行，该模型由低功耗现场可编程门阵列（FPGA）器件加速。DL模型使用单通道脑电图（EEG）作为输入。使用两个卷积神经网络（cnn）捕获一般和详细特征，使用双向长短期记忆（LSTM）网络捕获时变序列特征。采用8位量化，在不影响性能的情况下降低了计算成本。DL模型已经使用包含81个受试者的公共睡眠数据库进行了验证，达到了最先进的分类准确率85.8%和f1得分79%。所开发的模型也显示出推广到不同通道和输入数据长度的潜力。闭环同相听觉刺激已在实验台上得到验证。
Closed-loop sleep modulation is an emerging research paradigm to treat sleep disorders and enhance sleep benefits. However, two major barriers hinder the widespread application of this research paradigm. First, subjects often need to be wire-connected to rack-mount instrumentation for data acquisition, which negatively affects sleep quality. Second, conventional real-time sleep stage classification algorithms give limited performance. In this work, we conquer these two limitations by developing a sleep modulation system that supports closed-loop operations on the device. Sleep stage classification is performed using a lightweight deep learning (DL) model accelerated by a low-power field-programmable gate array (FPGA) device. The DL model uses a single channel electroencephalogram (EEG) as input. Two convolutional neural networks (CNNs) are used to capture general and detailed features, and a bidirectional long-short-term memory (LSTM) network is used to capture time-variant sequence features. An 8-bit quantization is used to reduce the computational cost without compromising performance. The DL model has been validated using a public sleep database containing 81 subjects, achieving a state-of-the-art classification accuracy of 85.8% and a F1-score of 79%. The developed model has also shown the potential to be generalized to different channels and input data lengths. Closed-loop in-phase auditory stimulation has been demonstrated on the test bench.