Aghazadeh Roghayeh, Frounchi Javad, Montagna Fabio, Benatti Simone
Microelectronic and Micro-Sensor Laboratory, Electrical and Computer Engineering Department, University of Tabriz, Tabriz, Iran.
DEI, University of Bologna, Italy.
Comput Biol Med. 2020 Oct;125:104004. doi: 10.1016/j.compbiomed.2020.104004. Epub 2020 Sep 17.
Extracting information from dense multi-channel neural sensors for accurate diagnosis of brain disorders necessitates computationally expensive and advanced signal processing approaches to analyze the massive volume of recorded data. Compressive Sensing (CS) is an efficient method for reducing the computational complexity and power consumption in the resource-constrained multi-site neural systems. However, reconstructing the signal from compressed measurements is computationally intensive, making it unsuitable for real-time applications such as seizure detection. In this paper, a seizure detection algorithm is proposed to overcome these limitations by circumventing the reconstruction phase and directly processing the compressively sampled EEG signals. The Lomb-Scargle Periodogram (LSP) is used to extract the spectral energy features of the compressed data. Performance of the seizure detector using non-linear support vector machine (SVM) classifier, tested on 24 patients of the CHB-MIT data-set for compression ratios (CR) of 1-64x, is 96-93%, 92-87%, 0.95-0.91, and <1 s for sensitivity, accuracy, the area under the curve, and latency, respectively. A power-efficient classification method based on the utilization of dual linear SVM classifiers is proposed. The proposed classification method based on the dual linear SVM classification achieved better classification performance compared to commonly used classifiers, such as K-nearest neighbor, random forest, artificial neural network, and linear SVM, while consuming low power in comparison to non-linear SVM kernels. The hardware-optimized implementation of this algorithm is proposed on a low-power multi-core SoC for near-sensor data analytics: Mr. Wolf. Optimized implementation of this algorithm on Mr. Wolf platform leads to detecting a seizure with an energy budget of 18.4 μJ and 3.9 μJ for a compression ratio of 24x using non-linear SVM classifier and the dual linear SVM based classification method, respectively.
从密集多通道神经传感器中提取信息以准确诊断脑部疾病，需要采用计算成本高昂且先进的信号处理方法来分析大量记录数据。压缩感知（CS）是一种有效的方法，可降低资源受限的多部位神经系统中的计算复杂度和功耗。然而，从压缩测量中重建信号计算量很大，使其不适用于诸如癫痫发作检测等实时应用。本文提出一种癫痫发作检测算法，通过规避重建阶段并直接处理压缩采样的脑电图信号来克服这些限制。采用Lomb-Scargle周期图（LSP）提取压缩数据的频谱能量特征。使用非线性支持向量机（SVM）分类器的癫痫发作检测器，在CHB-MIT数据集的24名患者上针对1 - 64倍的压缩率（CR）进行测试，其灵敏度、准确率、曲线下面积和延迟分别为96 - 93%、92 - 87%、0.95 - 0.91和<1秒。提出了一种基于双线性SVM分类器的低功耗分类方法。与常用分类器（如K近邻、随机森林、人工神经网络和线性SVM）相比，基于双线性SVM分类的所提出分类方法实现了更好的分类性能，同时与非线性SVM内核相比功耗更低。针对近传感器数据分析，在低功耗多核片上系统Mr. Wolf上提出了该算法的硬件优化实现。在Mr. Wolf平台上对该算法进行优化实现，对于24倍压缩率，使用非线性SVM分类器和基于双线性SVM的分类方法分别以18.4 μJ和3.9 μJ的能量预算检测到癫痫发作。
