{"slug": "wise-har-a-generalizable-ensemble-deep-learning-framework-for-wifi-based-human", "title": "WISE-HAR: A Generalizable Ensemble Deep Learning Framework for WiFi-Based Human Activity Recognition", "summary": "Researchers have developed WISE-HAR, an ensemble deep learning framework that uses WiFi signals to recognize human activities including walking and arm-waving with 94.87% accuracy. The framework, tested on the Wallhack1.8k dataset, combines five CNN architectures and aggressive data augmentation to overcome performance variance and small dataset limitations. The system demonstrated strong real-world generalization with minimal accuracy drops of 1-2% when tested across different scenarios and antenna types.", "body_md": "arXiv:2606.02974v1 Announce Type: new\nAbstract: Human Activity Recognition (HAR) using WiFi signals has emerged as a transformative technology for smart homes, healthcare monitoring, security systems, and ambient assisted living. Unlike traditional camera-based systems that raise significant privacy concerns and fail in low-light conditions, or wearable sensors that require user compliance, WiFi-based HAR is non-intrusive, privacy-preserving, cost-effective, and works seamlessly in any lighting condition. This paper presents a comprehensive approach to recognize three distinct human activities: \"No Presence\" (empty room), \"Walking\", and \"Walking + Arm-waving\" using the Wallhack1.8k WiFi spectrogram dataset. We propose three key improvements to address the main challenges in WiFi-based HAR. First, to address high performance variance, we implement ensemble learning with five different CNN architectures (Deep CNN, Wide CNN, MobileNetV2, ResNet50V2, and EfficientNetB0). Second, to address the small dataset size limitation, we apply aggressive data augmentation techniques including time-warping, frequency masking, and noise addition. Third, to evaluate real-world generalization capability, we perform cross-scenario evaluation (training on Line-of-Sight and testing on Non-Line-of-Sight) and cross-antenna evaluation (training on Biquad antenna and testing on PIFA antenna). Our ensemble model achieved a test accuracy of 94.87% on the LOS scenario with Biquad antenna, outperforming the best individual model by 0.66%. Data augmentation improved Random Forest performance from 60% to 95%. Cross-scenario evaluation showed minimal accuracy drops of only 1.37% and 2.07%, demonstrating strong generalization capabilities. The results indicate that the proposed approach is robust, reliable, and suitable for real-world deployment in diverse environments with different hardware configurations.", "url": "https://wpnews.pro/news/wise-har-a-generalizable-ensemble-deep-learning-framework-for-wifi-based-human", "canonical_source": "https://arxiv.org/abs/2606.02974", "published_at": "2026-06-03 04:00:00+00:00", "updated_at": "2026-06-03 04:17:55.985113+00:00", "lang": "en", "topics": ["machine-learning", "neural-networks", "artificial-intelligence", "computer-vision"], "entities": ["Wallhack1.8k", "Deep CNN", "Wide CNN", "MobileNetV2", "ResNet50V2", "EfficientNetB0", "Biquad antenna", "PIFA antenna"], "alternates": {"html": "https://wpnews.pro/news/wise-har-a-generalizable-ensemble-deep-learning-framework-for-wifi-based-human", "markdown": "https://wpnews.pro/news/wise-har-a-generalizable-ensemble-deep-learning-framework-for-wifi-based-human.md", "text": "https://wpnews.pro/news/wise-har-a-generalizable-ensemble-deep-learning-framework-for-wifi-based-human.txt", "jsonld": "https://wpnews.pro/news/wise-har-a-generalizable-ensemble-deep-learning-framework-for-wifi-based-human.jsonld"}}