Classification of electromyogram using vertical visibility algorithm with support vector machine

Analyzing the electromyogram is an important issue on diagnosis of neuromuscular diseases. The classification of electromyogram signal plays a significant role in this issue. Since the characteristic of the signals is complex and non-stationary, so the complex network is an appropriate tool in extracting feature of the signal. In this paper we propose a novel feature extraction technique based on transforming the signal to complex network via vertical visibility algorithm. Characteristic on the measurements of community structure and distance property are examined. The pattern on the relationship of nodes in the network is investigated. Support vector machine was employed for classification. The proposed method can classify the signals into 3 cases, i.e., healthy, myopathy, and neuropathy, with remarkable experimental results.