Tureis: Transformer-based Unified Resilience for IoT Devices in Smart Homes

2026-03-05

AI Summary

This work addresses the challenge of unsupervised, fine-grained fault detection and localization in smart homes, where low-cost heterogeneous sensors are highly susceptible to environmental interference, especially in multi-occupant settings with concurrent faults. To this end, we propose Tureis, a self-supervised, context-aware, and lightweight approach that leverages short-window masked reconstruction—based on a BERT-style Transformer—to generate reconstruction residuals, combined with an iterative isolation mechanism to accurately pinpoint multiple fault sources. Requiring neither labeled data nor human intervention, Tureis employs bit-level feature encoding and a compact architecture suitable for edge deployment. Experiments on five real-world multi-occupant datasets demonstrate that Tureis improves F1 scores by up to 25.0% and 35.4% for single- and multi-fault localization, respectively, while maintaining a model size under 1 MB, processing one minute of sensor data in just a few milliseconds on a Raspberry Pi 5 with peak memory usage of approximately 0.5 GB.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Unsupervised & Self-Supervised Learning
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Search and Retrieval-Augmented AI: Personalized, context-aware and across-device search
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

Smart-home IoT systems rely on heterogeneous sensor networks whose correctness shapes application behavior and the physical environment. However, these low-cost, resource-constrained sensors are highly prone to failure under real-world stressors. Prior methods often assume single-failure, single-resident settings, offer only failure detection rather than sensor-level localization, cover limited fault types and sensor modalities, require labels and human intervention, or impose overheads hindering edge deployment. To overcome these limitations, we propose Tureis, a self-supervised, context-aware method for failure detection and faulty-sensor localization in smart homes, designed for multi-failure, multi-resident edge settings. Tureis encodes heterogeneous binary and numeric sensor streams into compact bit-level features. It then trains a lightweight BERT-style Transformer with sensor-wise masked reconstruction over short-horizon windows, capturing spatial and short-term temporal correlations without mixing unrelated events. This self-supervised objective removes the need for labels or curated semantics. Then, at run-time, Tureis converts reconstruction residuals into sensor-level failure evidence and uses an iterative isolate-and-continue loop that masks flagged sensors, allowing other failures to surface and enabling resilient, fine-grained localization. Across five datasets with up to nine residents, Tureis improves single-failure localization F1 by +7.6%, +21.0%, and +25.0% over three strong baselines. In multi-failure scenarios with up to five faulty sensors, it further boosts localization F1 by +17.6% and +35.4% over two baselines, while the third does not extend to this setting. These gains come with minute-scale localization and an edge-friendly footprint, as a sub-megabyte model that processes each minute of data in a few milliseconds with ~0.5 GB peak memory on a Raspberry Pi 5.

Problem

• IoT resilience
• sensor failure localization
• smart homes
• multi-failure scenarios
• edge deployment

Innovation

• Transformer
• self-supervised learning
• fault localization
• edge computing
• smart home IoT