Two-Step Biometrics Using Electromyogram Signal Based on Convolutional Neural Network-Long Short-Term Memory Networks

Electromyogram (EMG) signals cannot be forged and have the advantage of being able to change registered data as they are characterized by waveform, which varies depending on gesture. In this paper, a two-step biometrics method was proposed using EMG based convolutional neural network–long short-term memory (CNN-LSTM) network. After preprocessing signals, time domain features LSTM network were used examine whether gesture matched, single performed if matched. biometrics, converted into two-dimensional spectrogram, training classification through CNN-LSTM Data fusion recognition in form an AND. The experiment Ninapro signal method, results showed 83.91% performance 99.17% performance. addition, false acceptance rate (FAR) observed been reduced 64.7% fusion.