An EMG-Based Personal Identification Method Using Continuous Wavelet Transform and Convolutional Neural Networks

Abstract

With the increasing development of internet, the security of personal information becomes more and more important. Thus, variety of personal identification methods have been introduced to ensure persons’ information security. Traditional identification methods such as Personal Identification Number (PIN), or Identification tag (ID) are vulnerable to hackers. Then the biometric technology, which uses the unique physiological characteristics of human body to identify user information has come into being. But the biometrics widely used at present such as human face, fingerprint and iris can also be forged and falsified. Thus, the biometric with living body features such as electromyography (EMG) signal is a good method to achieve aliveness detection and prevent the spoofing attacks. However, there are few studies on personal identification based on EMG signal. In this paper, an EMG-based personal identification method using continuous wavelet transform (CWT) and convolutional neural networks (CNN) is proposed. First, the EMG signal is collected from different subjects by MYO armbands. Then, the collected one-dimensional EMG data is transformed into two-dimensional data by using the CWT method. Finally, the CNN algorithm is employed to identify the subjects. Experiments with 21 subjects show that the recognition accuracy of this method can achieve 99.203%, proving the feasibility of using EMG signal for personal identification.