Marjaninejad Ali, Taherian Babak, Valero-Cuevas Francisco J
Annu Int Conf IEEE Eng Med Biol Soc. 2017 Jul;2017:986-989. doi: 10.1109/EMBC.2017.8036991.
Electrocardiogram (ECoG) recordings are very attractive for Brain Machine Interface (BMI) applications due to their balance between good signal to noise ratio and minimal invasiveness. The design of ECoG signal decoders is an open research area to date which requires a better understanding of the nature of these signals and how information is encoded in them. In this study, a linear and a non-linear method, Linear Regression Model (LRM) and Artificial Neural Network (ANN) respectively, were used to decode finger movements from energy in band-specific ECoG signals. It is shown that the ANN only slightly outperformed the LRM, which suggests that finger movements are mainly represented by a linear transformation of energy in band-specific ECoG signals. In addition, comparing our results to similar Electroencephalogram (EEG) studies illustrated that the spatio-temporal summation of multiple neural signals is itself linearly correlated with movement, and is not an artifact introduced by the scalp or cranium. Furthermore, a new algorithm was employed to reduce the number of spectral features of the input signals required for either of the decoding methods.
由于脑电图（ECoG）记录在良好的信噪比和最小侵入性之间取得了平衡，因此在脑机接口（BMI）应用中非常具有吸引力。迄今为止，ECoG信号解码器的设计仍是一个开放的研究领域，这需要更好地理解这些信号的本质以及信息在其中的编码方式。在本研究中，分别使用线性和非线性方法，即线性回归模型（LRM）和人工神经网络（ANN），从特定频段的ECoG信号能量中解码手指运动。结果表明，ANN仅略优于LRM，这表明手指运动主要由特定频段的ECoG信号能量的线性变换表示。此外，将我们的结果与类似的脑电图（EEG）研究进行比较表明，多个神经信号的时空总和本身与运动呈线性相关，而不是由头皮或颅骨引入的伪影。此外，还采用了一种新算法来减少两种解码方法所需的输入信号的频谱特征数量。
