User Recognition System Based on Spectrogram Image Conversion Using EMG Signals

Recently, user recognition methods to authenticate personal identity has attracted significant attention especially with increased availability of various internet things (IoT) services through fifth-generation technology (5G) based mobile devices. The EMG signals generated inside the body unique individual characteristics are being studied as a part next-generation methods. However, there is limitation when applying systems same operation needs be repeated while maintaining constant strength muscle over time. Hence, it necessary conduct research on multidimensional feature transformation that includes changes in frequency features In this paper, we propose system applies short-time fourier transform (STFT), and converts into spectrogram images adjusting time-frequency resolution extract features. proposed composed data pre-processing normalization process, image conversion final classification process. experimental results revealed image-based 95.4% accuracy performance, which 13% higher than signal-based system. Such improvement was achieved by using features, domain.