Abstract

The wide spread usage of wearable sensors such as in smart watches has provided continuous access to valuable user generated data such as human motion that could be used to identify an individual based on his/her motion patterns such as, gait. Several methods have been suggested to extract various heuristic and high-level features from gait motion data to identify discriminative gait signatures and distinguish the target individual from others. However, the manual and hand crafted feature extraction is error prone and subjective. Furthermore, the motion data collected from inertial sensors have complex structure and the detachment between manual feature extraction module and the predictive learning models might limit the generalization capabilities. In this paper, we propose a novel approach for human gait identification using time-frequency (TF) expansion of human gait cycles in order to capture joint 2 dimensional (2D) spectral and temporal patterns of gait cycles. Then, we design a deep convolutional neural network (DCNN) learning to extract discriminative features from the 2D expanded gait cycles and jointly optimize the identification model and the spectro-temporal features in a discriminative fashion. We collect raw motion data from five inertial sensors placed at the chest, lower-back, right hand wrist, right knee, and right ankle of each human subject synchronously in order to investigate the impact of sensor location on the gait identification performance. We then present two methods for early (input level) and late (decision score level) multi-sensor fusion to improve the gait identification generalization performance. We specifically propose the minimum error score fusion (MESF) method that discriminatively learns the linear fusion weights of individual DCNN scores at the decision level by minimizing the error rate on the training data in an iterative manner. 10 subjects participated in this study and hence, the problem is a 10-class identification task. Based on our experimental results, 91% subject identification accuracy was achieved using the best individual IMU and 2DTF-DCNN. We then investigated our proposed early and late sensor fusion approaches, which improved the gait identification accuracy of the system to 93.36% and 97.06%, respectively.

Highlights

  • Gait refers to the manner of stepping or walking of an individual

  • We propose the minimum error score fusion (MESF) method that discriminatively learns the linear fusion weights of individual deep convolutional neural network (DCNN) scores at the decision level by minimizing the error rate on the training data in an iterative manner. 10 subjects participated in this study and the problem is a 10-class identification task

  • We aim to investigate multi-sensor fusion in order to enhance the gait identification performance using complementary information among various sensors

Read more

Summary

Introduction

Gait refers to the manner of stepping or walking of an individual. Human gait analysis research dates to the 1960s [1] when it was used for medical purposes for early diagnosis of various disorders such as neurological disorders such as Cerebral Palsy, Parkinson’s or Rett syndrome [2], musculoskeletal disorders such as spinalstenosis [3], and disorders caused by aging, affecting large percentage of population [4].Reliable monitoring of gait characteristics over time was shown to be helpful in early diagnosis of diseases and their complexities. Gait refers to the manner of stepping or walking of an individual. Human gait analysis research dates to the 1960s [1] when it was used for medical purposes for early diagnosis of various disorders such as neurological disorders such as Cerebral Palsy, Parkinson’s or Rett syndrome [2], musculoskeletal disorders such as spinalstenosis [3], and disorders caused by aging, affecting large percentage of population [4]. Reliable monitoring of gait characteristics over time was shown to be helpful in early diagnosis of diseases and their complexities. Gait analysis has been employed to identify an individual from others. Gait has the potential to be used for biometric identification

Objectives
Methods
Results
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call