Self-supervised New Activity Detection in Sensor-based Smart Environments

2024-01-17

AI Summary

Unsupervised detection of unknown human activities in intelligent sensing environments remains challenging due to pattern diversity and feature sharing between known and unknown activities, compounded by cross-dataset heterogeneity in sensor attributes. Method: This paper proposes CLAN, a dual-tower model that jointly leverages time-frequency domain representation learning, contrastive learning with multi-type strong perturbation–based negative samples, and a dataset-adaptive augmentation selection mechanism—eliminating reliance on predefined activity categories inherent in supervised approaches. Contribution/Results: Evaluated on real-world sensing datasets, CLAN achieves a 9.24% improvement in AUROC over the state-of-the-art unsupervised baseline. It establishes a novel, transferable, and robust paradigm for activity novelty detection in open-world settings.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Unsupervised & Self-Supervised Learning
• Data Mining & Knowledge Management: Anomaly/Outlier Detection

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

With the rapid advancement of ubiquitous computing technology, human activity analysis based on time series data from a diverse range of sensors enables the delivery of more intelligent services. Despite the importance of exploring new activities in real-world scenarios, existing human activity recognition studies generally rely on predefined known activities and often overlook detecting new patterns (novelties) that have not been previously observed during training. Novelty detection in human activities becomes even more challenging due to (1) diversity of patterns within the same known activity, (2) shared patterns between known and new activities, and (3) differences in sensor properties of each activity dataset. We introduce CLAN, a two-tower model that leverages Contrastive Learning with diverse data Augmentation for New activity detection in sensor-based environments. CLAN simultaneously and explicitly utilizes multiple types of strongly shifted data as negative samples in contrastive learning, effectively learning invariant representations that adapt to various pattern variations within the same activity. To enhance the ability to distinguish between known and new activities that share common features, CLAN incorporates both time and frequency domains, enabling the learning of multi-faceted discriminative representations. Additionally, we design an automatic selection mechanism of data augmentation methods tailored to each dataset's properties, generating appropriate positive and negative pairs for contrastive learning. Comprehensive experiments on real-world datasets show that CLAN achieves a 9.24% improvement in AUROC compared to the best-performing baseline model.

Problem

• Detecting new activities in sensor-based environments
• Overcoming challenges in novelty detection due to pattern diversity
• Improving recognition of shared patterns between known and new activities

Innovation

• Contrastive Learning with diverse data Augmentation
• Utilizes time and frequency domains for discrimination
• Automatic selection of data augmentation methods