{"slug": "memory-augmented-lstm-autoencoder-for-unsupervised-activity-recognition-with-imu", "title": "Memory-Augmented LSTM Autoencoder for Unsupervised Activity Recognition with IMU Sensor Fusion", "summary": "Researchers propose a memory-augmented LSTM autoencoder for unsupervised human activity recognition using IMU sensor fusion, achieving 96.6% and 98.4% accuracy on DaLiAc and PAMAP2 datasets, outperforming supervised baselines and unsupervised methods.", "body_md": "arXiv:2606.28377v1 Announce Type: new\nAbstract: HAR using Inertial Measurement Unit (IMU) sensors is vital for healthcare monitoring and rehabilitation. Despite deep learning advancements, major challenges remain: reliance on labeled data, multi-sensor fusion complexity, and the limited ability of unsupervised methods to capture spatiotemporal dependencies. These issues are pronounced in real-world scenarios with noisy data, overlapping activities, and missing labels. We propose a fully unsupervised spatiotemporal feature fusion framework using a memory-augmented autoencoder. It enhances activity representations via short temporal windows of multi-sensor IMU data, enabling real-time applications. Our framework extracts hierarchical static features via a Stacked Autoencoder, fusing them within and across sensors. A sequence-to-sequence LSTM Autoencoder then temporally refines these features, incorporating historical motion patterns without labels. We analyze key hyperparameters to identify configurations that maximize feature separability under short-window constraints. Evaluated on DaLiAc and PAMAP2 using realistic inter-class window segmentation, our method achieves 96.6% and 98.4% accuracy, respectively, surpassing supervised baselines and unsupervised approaches. Our method improves feature separability by up to 9% despite shorter temporal windows. While our realistic inter-class segmentation reduces accuracy by ~7%, it was intentionally adopted to better reflect real-world activity transitions and practical relevance.", "url": "https://wpnews.pro/news/memory-augmented-lstm-autoencoder-for-unsupervised-activity-recognition-with-imu", "canonical_source": "https://arxiv.org/abs/2606.28377", "published_at": "2026-06-30 04:00:00+00:00", "updated_at": "2026-06-30 04:24:14.973371+00:00", "lang": "en", "topics": ["machine-learning", "neural-networks", "ai-research"], "entities": ["DaLiAc", "PAMAP2"], "alternates": {"html": "https://wpnews.pro/news/memory-augmented-lstm-autoencoder-for-unsupervised-activity-recognition-with-imu", "markdown": "https://wpnews.pro/news/memory-augmented-lstm-autoencoder-for-unsupervised-activity-recognition-with-imu.md", "text": "https://wpnews.pro/news/memory-augmented-lstm-autoencoder-for-unsupervised-activity-recognition-with-imu.txt", "jsonld": "https://wpnews.pro/news/memory-augmented-lstm-autoencoder-for-unsupervised-activity-recognition-with-imu.jsonld"}}