cs.NIMar 5, 2026

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

Authors: Alireza Borhani, Vafa Andalibi, Bahar Asgari

Organizations: University of Maryland, College Park, MD, USA · Google, Manhattan, NY, USA

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

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.

Figures & tables

WorkDomainLightweightMulti-failureMulti-residentFail-stopOutlierSpikeStuck-atHigh-noiseDriftLocalizationHeterogeneousUnlabeledMethod
Mallick et al. [ 25 ]SH◐×\times×\times✓\checkmark✓\checkmark✓\checkmark✓\checkmark×\times×\times✓\checkmark✓\checkmark×\timesSEM (Freq. Itemsets + Spatiotemp. Rules)
ElHady et al. [ 12 ]SH●×\times×\times✓\checkmark×\times×\times×\times×\times×\times×\times×\times✓\checkmarkSEM (Assoc. Rule Mining)
Fu et al. [ 15 ]SH○×\times×\times×\times✓\checkmark×\times×\times×\times×\times×\times✓\checkmark×\timesSEM (Semantic Corr. + Shadow Exec.)
Nguyen et al. [ 27 ]SH●×\times×\times×\times✓\checkmark×\times×\times×\times×\times×\times×\times×\timesSEM (Spatial/Depend. Corr.)
Li et al. [ 23 ]SH●✓\checkmark×\times✓\checkmark✓\checkmark✓\checkmark✓\checkmark×\times×\times✓\checkmark✓\checkmark×\timesSEM (GNN + Attn.)
Xiao et al. [ 33 ]SH◐×\times×\times×\times×\times×\times✓\checkmark✓\checkmark×\times×\times✓\checkmark✓\checkmarkSEM (Transformer + Loss-Guided Mask)
TABLE I: Comparison of Prior Work on Sensor Failure Detection & Localization in Smart Homes and Related Domains.
Fig. 1: Tureis overview: An offline phase performs feature extraction and trains a BERT-style encoder via sensor-wise masked reconstruction. Then, a run-time execution phase applies the model to each window to derive per-sensor failure scores and iteratively mask tripped sensors for resilient operation.
Fig. 2: Coactivation gap between correlated and uncorrelated sensor pairs versus window length LL : The curve peaks at five minutes, and thus, L=5L=5 is selected for all modules.
Fig. 3: Five-interval window (i.e., sequence) produced by the context-aware feature extraction module: Rows are consecutive interval feature vectors ∈{0,1}D\in\{0,1\}^{D} obtained via early fusion across channels, B1,…,BmB_{1},\ldots,B_{m} denote binary sensors (2 bits per sensor) and N1,…,NnN_{1},\ldots,N_{n} denote numeric sensors (4 bits per sensor).
Fig. 4: Transformer-based Modeling: masked reconstruction in Tureis . In this illustration, the numeric channel N1N_{1} is masked across all LL intervals. However, in general, each training sequence masks a random subset of sensor channels by replacing their bit positions with a learnable [MASK] token.
Fig. 5: Run-time execution and streaming inference in Tureis : Reconstruction logits are converted to per-sensor residuals, EWMA-smoothed, and compared to calibrated per-sensor thresholds for failure localization. Flagged sensors are then masked in subsequent sequences to prevent interference and maintain uninterrupted streaming.
Fig. 6: Single-failure detection: precision, recall, and F1 score for Tureis , ThingsDND, DICE, and AT on five smart homes (the number of residents is shown in parentheses). F1 score (i.e., the harmonic mean of precision and recall) is shown with a bold outline to emphasize its role as the primary summary metric.
Fig. 7: Single-failure localization: precision, recall, and F1 score across the five smart homes (resident counts as in labels). F1 score is bolded as the primary summary metric.
Fig. 8: Single-failure localization time: Mean delay (minutes) from ground-truth failure start to the first correct localization for Tureis , ThingsDND, DICE, and AT across five homes.
Fig. 9: Multi-failure detection: precision, recall, and F1 score across the five smart homes (resident counts shown in labels). Up to five simultaneous failures are injected, and F1 score is bolded as the primary summary metric.
Fig. 10: Multi-failure localization: precision, recall, and F1 score across five smart homes (resident counts in labels). Up to five simultaneous failures are injected, and F1 score is bolded as the primary summary metric. Moreover, AT is not applicable to multi-failure localization and is shown as N/A.
Fig. 11: Multi-failure localization time: mean delay (minutes) from failure onset to the first correct localization. Up to five simultaneous failures are injected. N/A indicates that AT is not applicable to multi-failure localization.
Fig. 12: Per-fault-type results: percentage of injected failures that are detected and located for six fault types. Results are aggregated over all five smart homes.

Explore similar work

CardsList

  1. Lightweight Transformer Models for On-Device Fault Detection: A Benchmark Study on Resource-Constrained Deployment

    Jun 23, 2026Disha PatelEfficient Transformer InferenceAdaptive Inference

    Department of Computer Science California State University, Fullerton

  2. LastAct: Trajectory-Guided Latest-Activity Localization for Real-Time Smart-Home Activity Recognition

    May 29, 2026Zishuai Liu, Ruili Fang, Jin Lu +1Human Activity RecognitionInternet of Things

    School of Computing, University of Georgia, USA

  3. SIDE: Sensor Impersonation Detection at the Edge via Sequence Prediction

    Sep 5, 2026Nahom BirhanInternet of ThingsTime-Series Anomaly Detection

    Department of Electrical and Computer Engineering Old Dominion University Virginia, USA