Personal Authentication Based on Wrist EMG Analysis by a Convolutional Neural Network

Abstract

Recent years, biological signals have attracted much attention as a tool of human interface. Electromyogram (EMG) has been used in a variety of situations in particular. We measure EMG of arms or shoulders in many cases. In addition, we often use expensive wet type sensors. However, they are inconvenient and high-cost. On the one hand, there have been few works of personal authentication using EMG. Therefore, in this paper we measure EMG by attaching dry type sensors to wrist, and carry out personal authentication. The conventional method in this paper is divided into three units such as a measuring, a feature extraction, and a discrimination units. We measure EMG signals with eight dry type sensors on the wrist. After that, we identify a motion opening our hands. We use a convolutional neural network (CNN) to learning and authentication. We collected 40 data for each subject. The average accuracy of two-class separation was 94.9 % by CNN. In addition to the conventional method, the proposed method in this paper preprocesses the data. Large noise was removed using a high path filter. By this preprocessing, identification accuracy (Two-class classification using CNN) improved by 1.5%. The true acceptance rate improved by 7.2%, and the false acceptance rate improved by 0.0067%.

Biometrics Verification Modality Using Multi-Channel sEMG Wearable Bracelet

“…The data collected by the authors were from eight individuals over a four-day period resulting in a total of 960 data captures. The average accuracy of the two-class separation was 94.9% by CNN [18].…”

“…al. [18] used eight dry sensors to measure EMG from the wrist and carry out a personal authentication approach. A convolutional neural network (CNN) was used in the learning phase for authentication.…”

Human posture tracking with flexible sensors for motion recognition

“…In addition to these conventional biometric technologies, recent years saw emerging modalities for authentication, such as ear imaging, 23 movements of arm, 24 head, 25 and gait. 26,27 Especially, Gait recognition has attracted extensive attention from institutes and researchers, 28,29 activity (step counts) and physiological data (heart rate, calorie burn, and the metabolic equivalent of task) for the task of user authentication. 30 Although there is a large collection of works on body part movement recognition for authentication, the existing equipment is expensive or not small enough to be convenient.…”

Recent Trends in Electromyography Signal Processing of Neuromuscular Diseases: An Outlook

“…The CNN is also robust to muscle fatigue, inter-subject variability, displacement of electrodes, and long-term use. Shioji et al [26] proposed a CNN network of two-class separation, which resulted with an accuracy of 94.9% for accessing wrist kinematics. This method preprocess the EMG data by employing a high-pass filter at the input to CNN.…”