Energy Efficient Embedded Systems (EEES) Lab - DEI, University of Bologna, Italy.
Center for Mind/Brain Sciences, University of Trento, Italy.
Methods. 2017 Oct 1;129:96-107. doi: 10.1016/j.ymeth.2017.06.019. Epub 2017 Jun 22.
EEG is a standard non-invasive technique used in neural disease diagnostics and neurosciences. Frequency-tagging is an increasingly popular experimental paradigm that efficiently tests brain function by measuring EEG responses to periodic stimulation. Recently, frequency-tagging paradigms have proven successful with low stimulation frequencies (0.5-6Hz), but the EEG signal is intrinsically noisy in this frequency range, requiring heavy signal processing and significant human intervention for response estimation. This limits the possibility to process the EEG on resource-constrained systems and to design smart EEG based devices for automated diagnostic. We propose an algorithm for artifact removal and automated detection of frequency tagging responses in a wide range of stimulation frequencies, which we test on a visual stimulation protocol. The algorithm is rooted on machine learning based pattern recognition techniques and it is tailored for a new generation parallel ultra low power processing platform (PULP), reaching performance of more that 90% accuracy in the frequency detection even for very low stimulation frequencies (<1Hz) with a power budget of 56mW.
脑电图 (EEG) 是神经疾病诊断和神经科学中常用的一种标准非侵入性技术。频率标记是一种越来越流行的实验范式，通过测量大脑对周期性刺激的 EEG 反应来有效地测试大脑功能。最近，频率标记范式在低刺激频率（0.5-6Hz）下已被证明是成功的，但在这个频率范围内，EEG 信号本质上是嘈杂的，需要进行大量的信号处理和大量的人工干预来进行响应估计。这限制了在资源受限系统上处理 EEG 的可能性，也限制了设计基于智能 EEG 的自动化诊断设备的可能性。我们提出了一种在广泛刺激频率下用于去除伪迹和自动检测频率标记响应的算法，并在视觉刺激协议上对其进行了测试。该算法基于机器学习的模式识别技术，并针对新一代并行超低功耗处理平台 (PULP) 进行了定制，即使在非常低的刺激频率（<1Hz）下，其功率预算为 56mW，也能达到超过 90%的频率检测准确性。
