无监督的猕猴运动皮层锋电位信号CKF解码

Unsupervised CKF Decoding for Macaque Motor Cortical Spikes

如何通过猕猴运动皮层的神经元锋电位信号估计其手指移动位置是一神经解码问题,现存方法解决该问题大多采用有监督训练,需要通过训练数据得到神经元锋电位信号与手指移动位置的关系,因此其估计性能依赖于训练数据.本文提出了一种无监督解码方法,该方法基于状态空间模型(State space model,SSM),利用神经网络得到神经元锋电位数与手指移动位置的关系权值,再用逐次状态估计方法去估计手指移动的位置.为减少训练的复杂度和提高估计准确度,采用一种非线性的积分卡尔曼滤波(Cubature Kalman filtering,CKF)来完成神经网络的训练和手指位置的逐次状态估计.与传统方法相比,该方法的最大特点是无监督,可以由神经元锋电位簇向量直接估计手指移动位置,而无需有监督训练.实验结果显示,当采用较少的有监督数据,现存方法与本文方法相比有较大的估计误差;当采用较多的有监督数据,现存方法才具有与本文方法相近似的估计误差.

How to estimate macaque＇s moving finger position through neuron spikes in his mortor cortex is a problem about neural decoding. For the problem, most of existing methods use a supervised training algorithm and require supervised data to obtain the relationship between the spikes and the finger＇s moving position. Therefore, the performance of the existing methods depends on the training data. This paper proposes an unsupervised decoding method, which, based on a state space model （SSM）, adopts neural networks to obtain the weights between the neuron spikes and the finger＇s moving position, and then estimates the finger＇s position through sequential state estimators. To reduce computational complexity and enhance estimation accuracy, a nonlinear cubature Kalman filter （CKF） is used to train the neural network and estimate the sequential moving positions. Compared with the existing methods, the proposed method＇s advantage is to be unsupervised. It could estimate the finger＇s position only through the spike vector instead of the supervised training data. Experiment results show that the existing methods have more estimation errors than the proposed method when a small amount of supervised data is adopted, and that the existing ones have similar estimation errors only when more supervised data adopted.