J Shanghai Jiaotong Univ Sci ›› 2022, Vol. 27 ›› Issue (4): 463-472.doi: 10.1007/s12204-022-2426-5

• • 上一篇    下一篇

  

  • 收稿日期:2020-08-01 出版日期:2022-07-28 发布日期:2022-08-11

Gram Matrix-Based Convolutional Neural Network for Biometric Identification Using Photoplethysmography Signal

WU Caiyu1,2 (吴彩钰), SABOR Nabil1,2,3, ZHOU Shihong1,2 (周世鸿), WANG Min1,2 (王 敏), YING Liang4 (应 亮), WANG Guoxing1,2∗ (王国兴)   

  1. (1. Department of Micro-Nano Electronics, Shanghai Jiao Tong University, Shanghai 200240, China; 2. MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai 200240, China; 3. Electrical Engineering Department, Assiut University, Assiut 71516, Egypt; 4. Department of Urology, Renji Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai 200127, China)
  • Received:2020-08-01 Online:2022-07-28 Published:2022-08-11

Abstract: As a kind of physical signals that could be easily acquired in daily life, photoplethysmography (PPG) signal becomes a promising solution to biometric identification for daily access management system (AMS). State- of-the-art PPG-based identification systems are susceptible to the form of motions and physical conditions of the subjects. In this work, to exploit the advantage of deep learning, we developed an improved deep convolutional neural network (CNN) architecture by using the Gram matrix (GM) technique to convert time-serial PPG signals to two-dimensional images with a temporal dependency to improve accuracy under different forms of motions. To ensure a fair evaluation, we have adopted cross-validation method and “training and testing” dataset splitting method on the TROIKA dataset collected in ambulatory conditions. As a result, the proposed GM-CNN method achieved accuracy improvement from 69.5% to 92.4%, which is the best result in terms of multi-class classification compared with state-of-the-art models. Based on average five-fold cross-validation, we achieved an accuracy of 99.2%, improved the accuracy by 3.3% compared with the best existing method for the binary-class.

中图分类号: