Accelerometer-Based Gait Segmentation: Simultaneously User and Adversary Identification

TL;DR

This paper presents a novel accelerometer-based gait segmentation method that uses geometric features and a new similarity metric to accurately identify users and adversaries simultaneously, enhancing cybersecurity applications.

Contribution

The paper introduces a new gait segmentation approach with a novel distance function, enabling effective simultaneous user and adversary identification using accelerometer data.

Findings

Achieves 98.79% accuracy in 6-class classification

Achieves 99.06% accuracy in binary user identification

Works on various walking signals including up, down, and mixed

Abstract

In this paper, we introduce a new gait segmentation method based on accelerometer data and develop a new distance function between two time series, showing novel and effectiveness in simultaneously identifying user and adversary. Comparing with the normally used Neural Network methods, our approaches use geometric features to extract walking cycles more precisely and employ a new similarity metric to conduct user-adversary identification. This new technology for simultaneously identify user and adversary contributes to cybersecurity beyond user-only identification. In particular, the new technology is being applied to cell phone recorded walking data and performs an accuracy of $98.79\%$ for 6 classes classification (user-adversary identification) and $99.06\%$ for binary classification (user only identification). In addition to walking signal, our approach works on walking up, walking down and mixed walking signals. This technology is feasible for both large and small data set, overcoming the current challenges facing to Neural Networks such as tuning large number of hyper-parameters for large data sets and lacking of training data for small data sets. In addition, the new distance function developed here can be applied in any signal analysis.