Walking fingerprinting
Lily Koffman (1), Ciprian Crainiceanu (1), Andrew Leroux (2) ((1), Department of Biostatistics, Johns Hopkins Bloomberg School of Public Health, (2) Department of Biostatistics, Bioinformatics, Colorado School of Public, Health)

TL;DR
This paper advances walking fingerprinting by implementing machine learning, screening predictive features, and developing a multivariate functional regression model to identify individuals from accelerometry data with high accuracy.
Contribution
It introduces a novel multivariate functional regression approach and inferential methods for feature screening in walking fingerprinting, improving prediction accuracy and interpretability.
Findings
All methods achieved at least 95% accuracy in a 32-individual study.
Prediction accuracy ranged from 41% to 98% in a 153-individual study.
Insights into factors influencing individual predictability were obtained.
Abstract
We consider the problem of predicting an individual's identity from accelerometry data collected during walking. In a previous paper we introduced an approach that transforms the accelerometry time series into an image by constructing its complete empirical autocorrelation distribution. Predictors derived by partitioning this image into grid cells were used in logistic regression to predict individuals. Here we: (1) implement machine learning methods for prediction using the grid cell-derived predictors; (2) derive inferential methods to screen for the most predictive grid cells; and (3) develop a novel multivariate functional regression model that avoids partitioning of the predictor space into cells. Prediction methods are compared on two open source data sets: (1) accelerometry data collected from individuals walking on a kilometer path; and (2) accelerometry data…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsBalance, Gait, and Falls Prevention · Body Composition Measurement Techniques · Sports Performance and Training
MethodsLogistic Regression
