Benchmarking Classical, Deep, and Generative Models for Human Activity Recognition

TL;DR

This paper compares classical, deep, and generative models for Human Activity Recognition across five datasets, highlighting CNNs as the most effective, with insights into model strengths and limitations for different data complexities.

Contribution

It provides a comprehensive benchmarking of classical, deep, and generative models for HAR, guiding researchers in selecting suitable models based on dataset characteristics.

Findings

CNN models outperform others across datasets

Classical models excel on smaller datasets

RBMs show promise in feature learning

Abstract

Human Activity Recognition (HAR) has gained significant importance with the growing use of sensor-equipped devices and large datasets. This paper evaluates the performance of three categories of models : classical machine learning, deep learning architectures, and Restricted Boltzmann Machines (RBMs) using five key benchmark datasets of HAR (UCI-HAR, OPPORTUNITY, PAMAP2, WISDM, and Berkeley MHAD). We assess various models, including Decision Trees, Random Forests, Convolutional Neural Networks (CNN), and Deep Belief Networks (DBNs), using metrics such as accuracy, precision, recall, and F1-score for a comprehensive comparison. The results show that CNN models offer superior performance across all datasets, especially on the Berkeley MHAD. Classical models like Random Forest do well on smaller datasets but face challenges with larger, more complex data. RBM-based models also show notable potential, particularly for feature learning. This paper offers a detailed comparison to help researchers choose the most suitable model for HAR tasks.