A Preliminary Study on Hyperparameter Configuration for Human Activity Recognition

TL;DR

This paper investigates how hyperparameter tuning, such as window size and overlap, affects human activity recognition accuracy using sensor data, highlighting the potential for adaptive systems to improve performance.

Contribution

It presents a study on hyperparameter influence in HAR systems and demonstrates that adjusting parameters can maintain accuracy across users and activities.

Findings

Hyperparameter adjustments can sustain classification accuracy.

Sensor data and user variability influence optimal hyperparameter settings.

Adaptive hyperparameter tuning can improve HAR system robustness.

Abstract

Human activity recognition (HAR) is a classification task that aims to classify human activities or predict human behavior by means of features extracted from sensors data. Typical HAR systems use wearable sensors and/or handheld and mobile devices with built-in sensing capabilities. Due to the widespread use of smartphones and to the inclusion of various sensors in all contemporary smartphones (e.g., accelerometers and gyroscopes), they are commonly used for extracting and collecting data from sensors and even for implementing HAR systems. When using mobile devices, e.g., smartphones, HAR systems need to deal with several constraints regarding battery, computation and memory. These constraints enforce the need of a system capable of managing its resources and maintain acceptable levels of classification accuracy. Moreover, several factors can influence activity recognition, such as classification models, sensors availability and size of data window for feature extraction, making stable accuracy a difficult task. In this paper, we present a semi-supervised classifier and a study regarding the influence of hyperparameter configuration in classification accuracy, depending on the user and the activities performed by each user. This study focuses on sensing data provided by the PAMAP2 dataset. Experimental results show that it is possible to maintain classification accuracy by adjusting hyperparameters, like window size and windows overlap factor, depending on user and activity performed. These experiments motivate the development of a system able to automatically adapt hyperparameter settings for the activity performed by each user.