Human activity recognition improved using ultra-wideband radar data
Human Activity Recognition via Ultra-Wideband Data: A Framework for Dimensionality Reduction, Pattern Discovery, and Predictive Modeling
Machine Learning
Summary
Recognizing human activities from sensor data is hard because the data is very complex and noisy. The authors present a new way to shrink this data into fewer, important parts while keeping almost all information. They also find useful patterns and use smart classifiers to identify six activities with nearly perfect accuracy. This method works quickly and could help make devices that monitor people’s movements in healthcare or smart homes.
What this means in practice
- •For healthcare technology teams: Create real-time systems that accurately monitor patient activities using compact and noise-robust radar data processing.
- •For smart home developers: Integrate efficient activity recognition algorithms into devices for assisted living to improve safety and convenience.
Authors
Nahid Sahel Gozin, Reza Sedaghat, Prathap Siddavaatam
Abstract
Recent advances in sensor technology have enabled more effective human activity recognition (HAR), particularly in real-time systems with limited computational resources. However, Ultra-Wideband (UWB) radar data remain challenging due to high dimensionality, noise, complexity, and nonlinear characteristics. This research proposes a framework to efficiently reduce data size, uncover significant patterns, and classify six activity types (Standff, Liedown, Noactivity, Sit, Stand, and Walk) from UWB signals with high accuracy. Two novel dimensionality reduction techniques are introduced in this paper. The first, Clustered Polynomial Expansion with Incremental PCA (CPE-IPCA), combines clustering and polynomial feature expansion with Incremental PCA, preserving 100% of the variance in only 50 components. The second, Post-PCA Standardization Approach (PPSA), standardizes data after PCA and retains 99.1% of the variance in 80 components, achieving superior compression and computational efficiency compared to conventional nonlinear methods. Frequent patterns are identified using Apriori and FP-Growth, which are then classified with Random Forest and a Vector Space Model (VSM). The framework achieves 100% accuracy with Random Forest on CPE-IPCA and 99% on PPSA, while VSM attains 100% precision, recall, and F1 on PPSA and near-perfect performance on CPE-IPCA (precision 1.00, recall 0.98-1.00, F1 0.99-1.00), demonstrating a fast, interpretable, and robust HAR system suitable for healthcare, assisted living, and smart environments.