Sensor Data for Human Activity Recognition: Feature Representation and Benchmarking

TL;DR

This paper introduces a new feature representation for sensor-based human activity recognition, demonstrating improved accuracy over existing methods through extensive benchmarking and analysis of feature and preprocessing effects.

Contribution

It proposes a novel feature representation based on consecutive observations and benchmarks it against existing features across multiple machine learning models.

Findings

Proposed features outperform baseline representations in accuracy.

Enhanced feature and preprocessing techniques achieve state-of-the-art results.

New representation improves recognition of both frequent and infrequent activities.

Abstract

The field of Human Activity Recognition (HAR) focuses on obtaining and analysing data captured from monitoring devices (e.g. sensors). There is a wide range of applications within the field; for instance, assisted living, security surveillance, and intelligent transportation. In HAR, the development of Activity Recognition models is dependent upon the data captured by these devices and the methods used to analyse them, which directly affect performance metrics. In this work, we address the issue of accurately recognising human activities using different Machine Learning (ML) techniques. We propose a new feature representation based on consecutive occurring observations and compare it against previously used feature representations using a wide range of classification methods. Experimental results demonstrate that techniques based on the proposed representation outperform the baselines and a better accuracy was achieved for both highly and less frequent actions. We also investigate how the addition of further features and their pre-processing techniques affect performance results leading to state-of-the-art accuracy on a Human Activity Recognition dataset.