Determining patterns in neural activity for reaching movements using nonnegative matrix factorization
Determining patterns in neural activity for reaching movements using nonnegative matrix factorization
复制标题
DOI：
10.1155/asp.2005.3113
复制
发表时间：
2005-01-01
期刊：
影响因子：
--
通讯作者：
Principe, JC
中科院分区：
文献类型：
--
作者：
Kim, SP;Rao, YN;Principe, JC
我们建议使用非负矩阵分解（NMF）作为一种模型独立的方法来分析神经活动。我们证明，使用这种技术，它是可能的，以稀疏基向量的形式来识别局部时空模式的神经活动。此外，这些基础的稀疏性可以帮助推断皮质放电模式和行为之间的相关性。我们证明了这种方法的实用性，使用脑机接口（BMI）设置中收集的神经记录。结果表明，使用NMF分析，它是可能的，以改善BMI模型的性能，通过适当的修剪输入。
We propose the use of nonnegative matrix factorization (NMF) as a model-independent methodology to analyze neural activity. We demonstrate that, using this technique, it is possible to identify local spatiotemporal patterns of neural activity in the form of sparse basis vectors. In addition, the sparseness of these bases can help infer correlations between cortical firing patterns and behavior. We demonstrate the utility of this approach using neural recordings collected in a brain-machine interface (BMI) setting. The results indicate that, using the NMF analysis, it is possible to improve the performance of BMI models through appropriate pruning of inputs.