Identifying user traits by mining smart phone accelerometer data

Abstract

Smart phones are quite sophisticated and increasingly incorporate diverse and powerful sensors. One such sensor is the tri-axial accelerometer, which measures acceleration in all three spatial dimensions. The accelerometer was initially included for screen rotation and advanced game play, but can support other applications. In prior work we showed how the accelerometer could be used to identify and/or authenticate a smart phone user [11]. In this paper we extend that prior work to identify user traits such as sex, height, and weight, by building predictive models from labeled accelerometer data using supervised learning methods. The identification of such traits is often referred to as -soft biometrics‖ because these traits are not sufficiently distinctive or invariant to uniquely identify an individual-but they can be used in conjunction with other information for identification purposes. While our work can be used for biometric identification, our primary goal is to learn as much as possible about the smart phone user. This mined knowledge can be then be used for a number of purposes, such as marketing or making an application more intelligent (e.g., a fitness app could consider a user's weight when calculating calories burned).

Accelerometer-based on-body sensor localization for health and medical monitoring applications

“…Gait related studies [12, 45, 17] have shown that there are gender differences in human gait; females walk with lesser step width and more pelvic movement, while males move their shoulders more often. In our current experiments, in light of the gender imbalance among our participants, we were unable to articulate this problem.…”

Motion-To-BMI: Using Motion Sensors to Predict the Body Mass Index of Smartphone Users

“…Gait information captured by the smartphone's built-in or wearable sensors can decode plenty of useful information about human traits. Weiss et al [10] collected the accelerometer data of 70 participants for sex, height, and weight prediction tasks using conventional feature-based approaches. Sex prediction involved classifying a smartphone user as either male or female, while the height and weight prediction tasks included predicting the user's height in inches and his/her weight in pounds.…”

“…Data from motion sensors are also multi-dimensional with a special temporal-spatial structure for conventional feature-based approaches [10,11]. Furthermore, the design of a specific feature extractor that transforms raw data into feature vectors relies on heuristic hand-crafted feature engineering and considerable domain expertise.…”

“…(2) We define motion entropy (MEn), which is a measure of the regularity and complexity of the motion sensor, and propose a novel MEn-based filtering strategy to select parts of these sub-sequences for training the prediction model. (3) We evaluate the hybrid deep neural network model with the MEn-based filtering strategy using two public datasets in comparison with baseline conventional feature-based approaches that have been applied to infer simple human traits from gaits [10,11]. Experimental results show that the proposed model significantly outperforms the baseline methods.…”

Styx: Design and Evaluation of a New Privacy Risk Communication Method for Smartphones

“…Kwapisz et al show how collected accelerometer data can be used to uniquely identify the user [24]. Weiss et al [33] show how the same source of information can even be used to identify user traits such as sex, height, and weight of the user. Similar results can be found in [8], [28], [11], [30], and [19].…”