Walking Fingerprinting Using Wrist Accelerometry During Activities of Daily Living in NHANES

TL;DR

This study introduces a novel wrist accelerometry-based method for individual identification during daily activities, leveraging walking patterns and image transformation techniques on large-scale NHANES data.

Contribution

The paper presents a new approach combining ADEPT and image transformation for walking fingerprinting, applied to a large, unlabeled, real-world dataset.

Findings

High accuracy in participant identification, with 96% in top 1% predictions.

Method effective on large, heterogeneous, unlabeled dataset.

Demonstrates feasibility of individual identification using wrist accelerometry in free-living conditions.

Abstract

We propose a method for identifying individuals based on their continuously monitored wrist-worn accelerometry during activities of daily living. The method consists of three steps: (1) using Adaptive Empirical Pattern Transformation (ADEPT), a highly specific method to identify walking; (2) transforming the accelerometry time series into an image that corresponds to the joint distribution of the time series and its lags; and (3) using the resulting images to construct a person-specific walking fingerprint. The method is applied to 15,000 individuals from the National Health and Nutrition Examination Survey (NHANES) with up to 7 days of wrist accelerometry data collected at 80 Hertz. The resulting dataset contains more than 10 terabytes, is roughly 2 to 3 orders of magnitude larger than previous datasets used for activity recognition, is collected in the free living environment, and does not contain labels for walking periods. Using extensive cross-validation studies, we show that our method is highly predictive and can be successfully extended to a large, heterogeneous sample representative of the U.S. population: in the highest-performing model, the correct participant is in the top 1% of predictions 96% of the time.