Search Results (156)

Institutional governance systems increasingly rely on stakeholder surveys in strategic decision-making. Yet survey participants can act as strategic agents who shape organizational outcomes in their favor. By transforming the information content of response distributions, such behavior can systematically distort institutional decisions made under uncertainty. This study proposes a dynamic framework that detects strategic data manipulation in institutional surveys using Shannon entropy and Kullback–Leibler divergence, and converts this detection into decision support. The framework operates in three stages. First, it constructs a robust reference entropy profile from historical data. Second, it processes incoming survey responses as a sequential stream and compares them against this profile. Third, it detects manipulation at both the population and individual levels through a multi-layered anomaly scoring system. The reference profile was built from anonymized real survey data spanning 2021–2025, comprising 1233 participants and 19,728 clean observations. The framework was validated through 600 Monte Carlo scenarios derived from this profile, covering four manipulation types and five intensity levels, and was benchmarked against the Z-score and Isolation Forest methods. The findings are threefold. Straight-lining detection identifies individual suppression and inflation manipulations with perfect accuracy. KL divergence monitoring flags coordinated coalition entries before data collection is complete. Hierarchical clustering recovers a coordinated suppression group that individual scoring fails to isolate, with 76.5% cluster purity and ~59% recall. Policy impact analysis further shows that manipulation distorts dimensions in opposite directions: the gap between raw and verified means is positive in the dimension targeted by coordinated suppression but clearly negative in the dimension targeted by coordinated inflation. This bidirectional distortion shows why dimension-selective detection is necessary, as a single uniform correction cannot resolve it. The study contributes to the literature in two areas, integrating decision-making under uncertainty with strategic agent models, and survey integrity research with information-theoretic metrics. Full article

Anomaly signals in the Attitude Determination and Control System (ADCS) of nanosatellites can significantly degrade mission performance, especially in the absence of robust Fault Detection, Isolation, and Recovery (FDIR) mechanisms. Thus, traditional threshold-based approaches, while portable and compact, may overlook subtle faults, whereby abnormal sensor signals or current spikes within the threshold may compromise the operation of the entire ADCS as a subsystem. Furthermore, the lack of interpretable detection methods further limits the development of reliable machine learning (ML) FDIR solutions. To address these limitations, this work presents a wavelet-based anomaly detection framework that introduces a two-stage hybrid architecture combining a lightweight Convolutional Neural Network (CNN) for anomaly detection with logistic regression for fault classification, both based on discrete wavelet transform (DWT) detail coefficients extracted from sensor and actuator data. The framework was validated using a statistics-based anomaly dataset for a 1U CubeSat ADCS simulated in MATLAB, in which anomalies are introduced at the component level with controlled variations in magnitude, frequency, and waveform, ensuring 99% statistical significance. Additionally, to demonstrate operational feasibility, constraints for onboard implementation were considered by executing the proposed framework in a Processor-in-the-Loop (PIL) environment. For benchmarking, lightweight detection and classification algorithms were compared, including Out-Of-Limit (OOL) and compact machine learning approaches. Finally, to identify the framework’s limitations and trace faulty events to physical phenomena, Gradient-weighted Class Activation Mapping (Grad-CAM), SHapley Additive exPlanations (SHAP), and impurity analysis were performed on the proposed algorithms as primary interpretability tools. Consequently, the results demonstrate accurate anomaly detection and identification to support both autonomous FDIR actions and ground operator decision-making. The proposed validation framework and dataset provide a reproducible basis for advancing anomaly detection onboard nanosatellites. Full article

Smart-home sensor networks enable unobtrusive monitoring of daily activity and are increasingly used to support independent living among older adults. However, many anomaly detection methods produce scalar anomaly scores or binary alerts without explaining how the detected behavior differs from a resident’s normal routine. This paper proposes a two-stage framework for interpretable routine-deviation assessment using smart-home motion and door-contact sensors. In Stage 1, raw sensor streams are aligned on a two-second master calendar, aggregated into hourly event counts, mapped into functional household activity zones, and converted into daily routine profiles. A Gated Recurrent Unit (GRU) routine prediction model is trained using a three-day lookback window to predict expected daily zone-level activity. Candidate routine-deviation days are automatically identified from daily prediction errors. In Stage 2, the recent monitoring period is plotted as 24-h radar profiles against the learned routine model, allowing a human expert to visually assess deviations in timing, location, and severity. The workflow was evaluated using 28 days of smart-home data collected from multiple independent residents. The proposed GRU framework achieved RMSE values ranging from 0.136 to 0.180 and MAE values ranging from 0.126 to 0.138 across the four participants, consistently outperforming the Previous-Day Baseline and generally providing lower prediction errors than the Seasonal Naïve Baseline. These findings demonstrate the effectiveness of participant-specific routine modeling for personalized routine-deviation detection in smart-home environments. The results indicate that deviation-sensitive target zones differed across the four participants, suggesting the importance of participant-specific routine modeling. The proposed approach successfully links automated candidate routine-deviation identification with radar-based visual analytics, providing a proof-of-concept, personalized, and interpretable decision support workflow for ambient assisted living research. Full article

Detecting localized morphological anomalies in three-dimensional point clouds is difficult because geometric deviations are entangled with rigid pose variation, residual registration error, sampling noise, and normal inter-subject variability. This challenge is particularly relevant in translational neuroimaging, where abnormal shape changes may be subtle and abnormal annotations are scarce. We propose an unsupervised framework that formulates 3D anomaly detection as a two-stage factorization problem, termed AdvFlow3D-AD. First, Fast Global Registration, followed by multi-scale Iterative Closest Point refinement, establishes a common geometric reference frame and reduces rigid-body nuisance variation. Second, an adversarially regularized normalizing flow models the residual distribution of aligned normal coordinates, enabling localized anomaly scores based on distance from the learned normal latent support. Percentile calibration on normal data then defines interpretable point-level and object-level operating points without requiring abnormal samples during training. We evaluate AdvFlow3D-AD on the Real3D-AD and Anomaly ShapeNet3D datasets, achieving a point-level area under the receiver operating characteristic curve (AUROC) of 0.747 on Real3D-AD and an object-level AUROC of 0.816 on Anomaly ShapeNet3D. We further present an exploratory neurodevelopmental brain-shape case study involving pediatric perinatal-asphyxia cases. The resulting anomaly maps showed qualitative spatial correspondence with anatomically plausible hippocampal and cerebellar regions under neuroradiological review. These results suggest that separating geometric nuisance variation from residual morphology can support interpretable anomaly localization when abnormal labels are limited. Full article

Routine inspections of transmission lines are essential for maintaining the reliability of the power grid. Airborne LiDAR technology provides detailed 3D corridor data for automated hazard detection, such as vegetation encroachment and structural anomalies. However, manually analyzing large point clouds is inefficient, and current segmentation methods struggle with scene complexity, scale variation, and the high cost of annotation. In this study, we present a label-efficient segmentation method built on MinkUNet, a sparse voxel convolutional network enhanced with self-attention modules in its encoder–decoder for better spatial reasoning over corridor objects (e.g., trees, buildings, towers). To further handle structural diversity and class imbalance, we adopt task-specific data augmentations and focal loss. A multi-stage pseudo-labeling strategy is then employed to enable effective cross-scene generalization with minimal labeled data. We validate our method on three real-world transmission line datasets. On the Foshan dataset, it achieves a mean Intersection over Union (mIoU) of 0.740 with an inference time of 1.31 s. Cross-scene tests at two other locations, Shumuyuan and Langwang Village, yield mIoUs of 0.762 and 0.757, respectively. These results confirm robust performance even with limited annotations. Overall, our findings demonstrate the practicality of our approach for routine power line inspections, enabling reliable hazard detection with minimal annotation effort. Full article

Accurate extraction of typical load curves (TLCs) is essential for electricity market trading, demand-side management, and optimal design of energy storage systems. However, conventional methods are highly sensitive to anomalous consumption days caused by equipment failures or maintenance, which can distort normal electricity consumption patterns. To address this issue, this paper proposes a two-stage unsupervised framework that integrates a deep sequence model with an anomaly detection algorithm for robust TLC extraction. First, a Transformer-based autoencoder is employed to learn complex temporal dependencies and intrinsic patterns from historical daily load data, extracting robust periodic features by reconstructing the input load sequences. Subsequently, the reconstruction error of each daily load curve is computed as an anomaly assessment metric. These reconstruction error features are then fed into an Isolation Forest algorithm to identify anomaly loads that significantly deviate from the learned normal patterns, without requiring predefined thresholds or labeled data. Validation using real-world commercial and industrial electricity consumption data demonstrates that the proposed method effectively filters out various anomalies (e.g., spikes, troughs, and shape distortions) that conventional methods fail to exclude. The extracted TLCs exhibit improved robustness and representativeness. Further case studies indicate that adopting purified TLCs to guide electricity procurement in market trading facilitates more scientific trading strategies and avoids increased electricity costs caused by distorted load patterns. In summary, the proposed Transformer-Isolation Forest hybrid framework provides an effective data-driven solution for robust TLC extraction. The resulting TLCs can be directly used to guide day-ahead market bidding, optimize power purchase contract decomposition, and assess user demand response potential. Full article

Accurate and robust detection of leaf diseases is a key enabler for precision agriculture and large-scale crop health monitoring. Despite the strong generalization of modern one-stage detectors (e.g., YOLOv8), two domain-specific challenges remain: (i) weak or blurry lesion boundaries hinder precise localization, and (ii) low color contrast between diseased and healthy tissues forces models to rely on subtle texture patterns rather than salient shapes. To tackle these challenges, we reframe the core agricultural disease detection task as the identification of “asymmetric morphological anomalies” and propose a domain-tailored enhancement framework. First, we introduce an Edge Enhancement Module (EEM) that explicitly strengthens boundary-aware representations. Inspired by the natural symmetry of healthy leaves, our EEM is specifically designed to capture symmetry-breaking boundary discontinuities and localized asymmetric edges caused by disease lesions. Our method enhances edge and texture cues that are indicative of disease lesions, which often exhibit local asymmetries and boundary discontinuities. The EEM includes a Differential Normalized Pooling Block (DNPB) that highlights edge responses through discrepancies between max pooling and average pooling, which also models cross-group edge correlations. Second, the Lightweight Texture-Sensitive Feature Enhancement (LTSFE) mechanism amplifies texture-discriminative channels under low-contrast conditions by leveraging complementary global statistics and efficient channel mixing, all with negligible computational overhead. We evaluated our method on a self-constructed dataset of 106,434 images with 225,640 annotations covering diverse crops. Experiments show that the proposed method achieves state-of-the-art accuracy (81.54% mAP@0.5:0.95) while maintaining real-time inference (142 FPS), consistently outperforming strong baselines. Ablations confirm the effectiveness and complementarity of EEM and LTSFE, demonstrating that domain-specific architectural design, inspired by biological symmetry, can substantially improve agricultural vision systems. Full article

Selective laser melting (SLM) equipment operates as a complex cyber–physical system, wherein strong implicit coupling among internal subsystems presents significant challenges for condition monitoring and fault diagnosis. Existing deep learning methods often suffer from feature submersion when processing multi-source heterogeneous data and lack the capability for system-level topological causal inference. To address these issues, we propose a multisystem coupling modeling and anomaly traceability method based on a decoupled graph attention network (ST-DBGAE). Independent local spatiotemporal feature alignment modules are constructed to map heterogeneous sensory data into a unified latent space. This eliminates dimensional discrepancies while strictly maintaining the feature independence of underlying hardware subsystems, such as optical and gas circuits. A dynamic graph attention mechanism with sparse priors is subsequently introduced to adaptively capture time-varying coupling weights triggered by implicit interactions (e.g., thermal fluids), bypassing the need for predefined rigid physical connections. Furthermore, a dual-branch two-stage decoupled optimization architecture is designed. By blocking the cross-interference of global backpropagation, this architecture outputs a continuous equipment health index (HI) based on reconstruction errors and employs a topological difference matrix inference mechanism to reversely anchor the root-cause nodes responsible for cross-system cascading degradation. Experimental results based on over 310,000 real operational monitoring records from industrial SLM equipment demonstrate that the proposed model achieves a comprehensive diagnostic Macro-F1 score of 96.5% across eight operating states. The single-class detection rates (ACCs) of specific underlying anomalies are significantly improved. This method not only enables high-precision equipment health warnings but also provides a physically interpretable microscopic fault propagation mapping for predictive maintenance. Full article

Fault detection is essential for the reliable operation of wind turbines. Traditional supervised methods for fault detection based on SCADA data face highly imbalanced datasets of normal and fault samples. This paper presents a two-stage detection method to address this limitation by integrating unsupervised anomaly detection or classification with supervised classification. In the first stage, the unsupervised classifier of OCSVM, together with two complementary anomaly scores, is used to flag deviations from normal operation or separate abnormal data samples from normal data samples. In the second stage, the supervised classifier of CNN is applied to the detected abnormal data samples to identify fault samples among only these samples, thus enhancing the discrimination capability between normal and abnormal conditions. Experiments on real-world SCADA data show that the introduced two-stage detection method noticeably improves fault detection compared to supervised methods, both in terms of accuracy and missed fault rates. Full article

Microsatellites operate in highly dynamic thermal environments due to severe physical constraints, making temperature telemetry a critical onboard health indicator. Conventional threshold-based monitoring fails to distinguish normal operational mode transitions from genuine faults, causing excessive false alarms. To address this, we propose a two-stage framework integrating unsupervised thermal mode discovery with mode-specific deep learning prediction. Raw temperature telemetry is downsampled and segmented into orbital cycles. Unsupervised clustering identifies two nominal thermal regimes and four canonical fault-type libraries (step, spike, drift, and noise), each corresponding to distinct in-orbit failure mechanisms. For each nominal mode, a Convolutional Neural Network–Long Short-Term Memory (CNN-LSTM) is trained on 7-day historical windows to forecast 3-day temperature evolution. Post-downlink, incoming cycle mode is inferred via nearest-neighbor DTW classification; anomalies are flagged when prediction residuals exceed mode-adaptive thresholds. Validation on Macau Science Satellite-1B (MSS-1B, COSPAR 2023-069-B, NORAD 56732) in-orbit telemetry from a 41° inclination low-Earth orbit—where solar illumination dominates external thermal loading and internal heat from the data-communication module and scientific payload constitutes the primary internal thermal source—shows the method reduces anomaly flags by 96.6% and improves prediction mean absolute error by 51.3% compared to a non-classified global baseline under nominal operating conditions, correctly detecting a known operational transient while suppressing spurious alarms. A synthetic fault injection experiment with four anomaly types and five baseline methods further confirms the framework’s detection capability, achieving an overall F1 score of 0.725 vs. 0.258 for the global baseline—a 2.8× improvement driven primarily by a 4× precision gain. Sensitivity analysis reveals that the two-stage advantage is most pronounced for low-magnitude and short-duration faults, where mode-specific context is essential. This work advances microsatellite autonomous health management by providing reliable anomaly detection with quantified fault detection performance. Full article

Semiconductor manufacturing demands exceptional precision, as even minor process deviations can result in significant yield degradation. The increasing deployment of sensors generates extensive time-series data. However, such data are often affected by temporal misalignments, nonlinear distortions, and inter-wafer variability, complicating direct comparison and automated anomaly detection. To address these challenges, this paper proposes a robust framework that employs a Dynamic Time Warping (DTW)-based two-stage alignment strategy with Sakoe–Chiba constraint followed by a bidirectional polyline distance measure to identify subtle anomalies. This approach effectively handles scarce anomaly labels and high variability in sensor data, enabling reliable process health monitoring. Experimental results on real semiconductor production data demonstrate that the framework enhances detection accuracy, contributing to early fault identification and reduced wafer scrap in manufacturing environments. Full article

The possibility of zero-day attacks on Internet of Things (IoT) networks is high, particularly in dynamic and heterogeneous IoT environments, including emerging battlefield scenarios (IoBT). Detecting these attacks requires adaptive and generalizable security mechanisms. Due to the unique and unknown signatures of these attacks, they go undetected using signature-based Intrusion Detection Systems (IDSs) on the one side. On the other side, current anomaly-based IDSs that employ traditional machine learning on statistical features struggle to adapt and generalize to unknown networks, which is the case in IoBT. Transformer-based deep learning models have shown the capability of learning complex sequential patterns. This ability can be leveraged to analyze packet payloads that encompass opcodes capable of executing malicious patterns within an IoT network. In this work, we propose a dual-stage Transformer IDS that operates on the raw payload of network packets to detect zero-day attacks. Due to the lack of IoBT datasets, we evaluate the algorithm on three comprehensive IoT traffic benchmarks—MQTT-IoT, IoT-23, and CIC-IoT-2022—which have a high number of IoT devices and various attacks. Importantly, model evaluation is performed in two cross-validation settings to address the key operational challenges associated with unseen scenarios and networks. The evaluation settings are split-at-scenario to evaluate the detection ability of zero-day attacks and split-at-dataset to evaluate the model’s generalizability to new environments. In the former, the average increase in the F1-score of the proposed algorithm over the baseline model is 44% in detecting four zero-day attacks presented in the MQTT-IoT dataset. In the latter, the average increase in the F1-score is 16% in detecting malicious attacks across the three datasets. These results show the benefit of advanced AI in securing the next generation of IoT systems in future Internet applications. Full article

Smart grids increasingly rely on digital communication, expanding the attack surface beyond the reach of conventional network intrusion-detection systems. Physics-based monitoring can detect anomalies that bypass traffic inspection, but most prior methods only provide binary detection and do not identify attackers or describe associated network behaviour. This paper presents a two-stage cyber–physical detection and attribution pipeline for the IEEE 14-bus smart grid. In Stage 1, a four-layer GATv2 model analyses sliding windows of PLC sensor data and operates as a binary anomaly detector (Benign vs. Attack), achieving $96.39\pm 1.26\%$ accuracy, macro-F1 $0.949\pm 0.019$, recall $0.992\pm 0.007$, and ROC-AUC $0.994\pm 0.005$ (mean ± std, 5 seeds, tuned configuration). GATv2 achieves the highest recall among all tested binary classifiers (Random Forest: $0.970$; SVM: $0.860$; KNN: $0.988$ at low AUC $0.759$), the primary metric in safety-critical intrusion detection where a missed attack is more dangerous than a false alarm. A Welch t-test across five independent seeds confirms that GATv2 and RF are statistically equivalent in accuracy ($t=-2.030$, $p=0.096$). A six-class ablation study reveals that Backdoor is physically near-invisible (F1 $=0.238$, lowest among all classes), motivating the network attribution stage. In Stage 2, triggered only after anomaly detection, a LightGBM model trained on 27 network-traffic features attributes the attack campaign, reaching $83.05\pm 0.00\%$ accuracy and macro-F1 $0.819\pm 0.002$ across all six cyber classes. A final enrichment stage correlates anomaly windows with network events to extract attacker IP and MAC information, suspicious ports, Modbus manipulation signals, and connection-rate anomalies, producing a structured forensic report. Ablations and visual analyses show that graph-based physical sensing and statistical network attribution are complementary. To the best of our knowledge, this is the first work to combine topology-aware GNN physical detection, multi-class cyber attribution, and automated forensic enrichment in a single pipeline evaluated on this dataset. Full article

The Internet of Medical Things (IoMT) has become integral to modern healthcare, yet its always-connected and resource-constrained nature enlarges the attack surface and complicates timely intrusion detection. This study presents a deployment-oriented, two-stage anomaly-detection pipeline. First, Principal Component Analysis (PCA) is employed to reduce the dimensionality of network traffic data, capturing the most significant variance. Subsequently, a One-Class Support Vector Machine (OC-SVM) is trained exclusively on these principal components of normal traffic. This approach prioritizes computational efficiency for resource-constrained IoMT devices while maintaining high model robustness. By modeling the principal components of normal behavior, our method achieves state-of-the-art performance across diverse attack families. We adopt a uniform protocol across four public IoMT corpora—BoT-IoT, CICIoMT2024, ECU-IoHT, and IoMT-TrafficData. The model’s hyperparameters, including the optimal number of principal components determined by explained variance, are tuned via randomized search. Despite using no attack labels during training, the proposed PCA-enhanced detector achieves state-of-the-art performance across diverse attack families: on BoT-IoT we obtain 99.92% F1-score (99.84% accuracy), on CICIoMT2024 we obtain 99.88% F1-score (99.77% accuracy), on ECU-IoHT 99.25% F1-score (98.58% accuracy), and on IoMT-TrafficData 99.19% F1-score (98.66% accuracy). The compact model size, enabled by PCA, makes the approach highly amenable to edge or gateway deployment in clinical networks, while the normal-only training paradigm improves robustness to zero-day threats. The results demonstrate that modeling the principal components of routine network behavior is a highly effective and efficient strategy for reliable, low-latency threat detection in realistic IoMT settings. Full article

In large-scale caged broiler houses, the combined effects of ventilation regulation, external meteorological disturbances, and changes in flock growth stages can easily cause the indoor thermal environment to deviate from the target settings, thereby increasing the difficulty of environmental control and production risks. Meanwhile, the broiler house environment exhibits pronounced spatial heterogeneity, while manual inspection is limited by low efficiency, high labor intensity, and delayed detection of anomalies. Therefore, this study proposes an inspection-robot-based method for predicting and providing early warnings for temperature deviation (TD) and temperature–humidity index (THI). In this method, TD is used to characterize the degree of deviation in environmental control, whereas THI is used to characterize the overall thermal environmental risk under the coupled effects of temperature and humidity. For the two prediction tasks, input variables were separately selected based on correlation analysis, and the same Wavelet–ECA–GRU model architecture was adopted for training to achieve short-term prediction over the next 30 min. The results show that the proposed model outperformed baseline models, including LSTM, TCN, and GRU. On the test set, the RMSE and R² for TD prediction were 0.2886 and 0.9238, respectively, while those for THI prediction were 0.4309 and 0.9287, respectively. Based on the TD classification results and THI risk thresholds, warning strategies for heat deviation, cold deviation, and humid-heat risk were established. The proposed method can identify potential thermal environmental anomalies in caged broiler houses in advance from the perspectives of environmental control deviation and comprehensive thermal environmental risk, thereby assisting farm managers in assessing whether timely adjustments to ventilation, heating, or cooling are needed. Full article