IBIS: A Hybrid Inception-BiLSTM and SVM Ensemble for Robust Doppler-based Human Activity Recognition

TL;DR

This paper introduces IBIS, an ensemble framework combining deep learning and SVM to improve Wi-Fi Doppler-based human activity recognition, especially in unseen environments, achieving high accuracy and robustness.

Contribution

IBIS is a novel ensemble approach that enhances generalization in Wi-Fi HAR by integrating Inception-BiLSTM features with SVM classification.

Findings

Achieves 95.40% accuracy on multiple datasets.

Outperforms standard architectures with a 7.58% performance gain.

Effectively mitigates environmental dependency in Wi-Fi HAR.

Abstract

Wi-Fi sensing is a leading technology for Human Activity Recognition (HAR), offering a non-intrusive and cost-effective solution for healthcare and smart environments. Despite its potential, existing methods struggle with domain shift issues, often failing to generalize to unseen environments due to overfitting. This paper proposes IBIS, a robust ensemble framework combining Inception-Bidirectional Long Short-Term Memory (BiLSTM) for feature extraction and Support Vector Machine (SVM) for classification of Doppler signatures. The proposed architecture specifically targets generalization capabilities. Experimental results on multiple datasets show that IBIS achieves 95.40% accuracy, delivering a 7.58% performance gain compared to standard architectures in cross-scenario evaluations on external datasets. The analysis confirms that IBIS effectively mitigates environmental dependency in Wi-Fi-based HAR.