IBIS: A Powerful Hybrid Architecture for Human Activity Recognition

2025-10-28

AI Summary

To address poor generalization and overfitting in human activity recognition (HAR) models for Wi-Fi sensing, this paper proposes IBIS—a hybrid architecture integrating Inception-BiLSTM with Support Vector Machine (SVM). IBIS innovatively combines Inception modules with bidirectional LSTM to enable adaptive multi-scale temporal feature extraction from raw Wi-Fi Doppler shift signals; the resulting deep features are then fed into an SVM for discriminative classification, thereby mitigating the strong dependence of end-to-end deep models on training data distribution. Evaluated on Wi-Fi Doppler-based HAR tasks, IBIS achieves 98.9% accuracy. Confusion matrix analysis and cross-scenario validation demonstrate its superior robustness over pure deep learning baselines. This work establishes a new paradigm for resource-constrained, small-sample Wi-Fi sensing applications—balancing high accuracy with strong generalization capability.

Technology Category

• Planning, Routing, and Scheduling: Activity and Plan Recognition
• Machine Learning: Multi-instance/Multi-view Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

The increasing interest in Wi-Fi sensing stems from its potential to capture environmental data in a low-cost, non-intrusive way, making it ideal for applications like healthcare, space occupancy analysis, and gesture-based IoT control. However, a major limitation in this field is the common problem of overfitting, where models perform well on training data but fail to generalize to new data. To overcome this, we introduce a novel hybrid architecture that integrates Inception-BiLSTM with a Support Vector Machine (SVM), which we refer to as IBIS. Our IBIS approach is uniquely engineered to improve model generalization and create more robust classification boundaries. By applying this method to Doppler-derived data, we achieve a movement recognition accuracy of nearly 99%. Comprehensive performance metrics and confusion matrices confirm the significant effectiveness of our proposed solution.

Problem

• Overcoming overfitting in Wi-Fi sensing models
• Improving generalization for human activity recognition
• Enhancing robustness of classification boundaries

Innovation

• Hybrid Inception-BiLSTM with SVM architecture
• Improves model generalization and classification robustness
• Achieves 99% accuracy using Doppler-derived data