Search Results (3,162)

The effectiveness of machine learning and deep learning methods for network anomaly detection depends strongly on the quality and representativeness of the datasets used for training and evaluation. Despite recent advances, many publicly available benchmarks rely on synthetic traffic, outdated attack scenarios, or limited representation of encrypted communications. This work presents a network traffic dataset derived from operational firewall logs collected in a heterogeneous institutional environment dominated by HTTPS/TLS traffic. A structured data-centric pipeline was implemented, including preprocessing, behavioral feature engineering, unsupervised pseudo-labeling through the EFMS–KMeans algorithm, class balancing using SMOTE, and the generation of model-oriented sequential representations for deep learning analysis. The resulting dataset contains large-scale flow-level records describing volumetric, behavioral, and temporal traffic characteristics while preserving privacy through anonymization procedures. Technical validation was conducted using statistical analysis, entropy-based measurements, clustering quality metrics, and dimensionality reduction techniques, confirming data consistency, structural diversity, and class separability. The dataset is publicly available through the Mendeley Data repository together with metadata and documentation supporting anomaly detection research, encrypted traffic analysis, and the evaluation of machine learning and deep learning approaches in realistic cybersecurity environments. Full article

Background/Objectives: Branchio-oto syndrome (BOS) is an autosomal dominant disorder primarily associated with pathogenic variants in EYA1, mainly characterized by branchial anomalies, auricular abnormalities, and hearing loss. However, the co-occurrence of inner ear malformations in BOS remains understudied, especially severe malformations. This study aimed to investigate the clinical and genetic characteristics of patients with EYA1-associated BOS, with emphasis on cochlear nerve deficiency (CND). Methods: From January 2020 to April 2026, patients diagnosed with EYA1-associated BOS at an otology outpatient clinic in a tertiary hospital were included. Clinical manifestations, audiological assessments, imaging and genetic findings were analyzed. Results: Thirteen patients (six females and seven males) from eight unrelated families aged 0.3–58.3 years were enrolled. Branchial cleft fistulas and preauricular pits were each observed in 76.9% (10/13) of patients. The mean pure-tone average was 74.3 ± 20.7 dB HL. Eight EYA1 variants (four truncating, two large deletions, and two splicing) were identified. Among these, five were novel (c.320_329del, c.518del, c.1307dupT, c.1475+1G>A, and exon 12–18 deletion). CND was detected in 38.5% (5/13) of patients and 26.9% (7/26) of ears. Patients with CND carried either truncating variants (n = 3) or large deletions (n = 2) of EYA1. No CND was observed in patients with splicing variants. Conclusions: This study identifies five novel EYA1 pathogenic variants and suggests that CND may be a relatively common radiologic feature in EYA1-associated BOS, particularly among patients with truncating variants or large deletions, although larger studies are needed to confirm this association. Full article

Vector magnetic anomaly detection on ocean buoys is challenged by attitude changes, non-stationary backgrounds, and weak targets that adaptive filters may absorb. We propose an online target-protected framework combining attitude compensation, constant-false-alarm-rate normalized innovation squared (CFAR-NIS) threshold adaptation, target-dwell gating, whitening based on a target-free calibration covariance, and weighted multiscale generalized likelihood ratio test-cumulative sum (GLRT-CUSUM) fusion. The target-protection mechanism constrains covariance adaptation and the effective Kalman gain during suspected target intervals, while dual-threshold confirmation suppresses isolated background spikes. We evaluated the method using publicly available buoy attitude and triaxial magnetometer background data with injected ship magnetic signatures under semi-physical conditions. At SNR ≈ 2.7, 200 paired Monte Carlo trials yielded a detection probability of 0.965, a background false-alarm rate of 0.045, and an average delay of 208.3 samples. Compared with standard and adaptive Kalman filtering, orthogonal-basis-function (OBF), minimum-entropy, and spectral-residual CUSUM baselines, the proposed method significantly improved detection probability and shortened delay. Its false-alarm rate was comparable to OBF and SR-CUSUM but higher than those of standard KF, adaptive KF, and minimum-entropy detection. Validation with real operational sea-trial data remains necessary. Full article

For large-scale photovoltaic plant inspection, UAV-based infrared–visible real-time detection can combine thermal abnormality information with appearance and structural cues. This is useful for improving inspection and maintenance efficiency. However, in real UAV inspection, differences in sensor resolution, field of view, and flight attitude can cause weak misalignment between the two modalities. Since complex image registration is difficult to perform before real-time inference, this misalignment can affect cross-modal feature fusion and defect localization. To address this problem, this paper proposes Frequency-Aware Fusion YOLO (FAF-YOLO) for dual-modal photovoltaic defect detection. We also build a real-scene infrared–visible dual-modal photovoltaic defect dataset, named DM-PV, which covers six defect categories related to thermal anomalies and external environmental interference. FAF-YOLO is based on a dual-branch YOLO detection framework. The C3k2-DPRG module is used to enhance defect boundaries, local details, and neighborhood context. The Frequency-aware Selective Fusion (FSF) module models low-frequency structural information and high-frequency detail responses separately, which reduces edge ghosting and background mis-fusion caused by weak misalignment. A Multi-Scale Differentiated Decoupled Head is then used to handle scale-specific prediction and improve small-defect localization and regional-anomaly discrimination. Experimental results show that FAF-YOLO achieves 92.5% Precision, 86.7% Recall, 91.7% ${\mathrm{mAP}}_{50}$, and 61.4% ${\mathrm{mAP}}_{50:95}$ on the DM-PV dataset. It outperforms several mainstream dual-modal detection methods and has lower parameters and computational complexity. Further tests for real-time inspection show that the proposed method keeps more stable performance under weak misalignment perturbations. It also reaches an inference speed of 33 FPS on the Jetson Orin Nano edge platform, which verifies its effectiveness and deployability for UAV-based real-time photovoltaic inspection. Full article

This paper addresses the urgent scientific and applied problem of automatic tracking of highly maneuverable Unmanned Aerial Vehicles (UAVs) using systems based on platforms with limited computing power (Edge Computing). The paper analyzes the shortcomings of classical correlation trackers and detectors based on deep neural networks when tracking targets with non-linear trajectories. A hybrid tracking method is proposed, combining the speed of a Kernelized Correlation Filter (KCF) and the accuracy of a neural network detector (YOLO11s). A key feature of the method is the developed algorithm for adaptive Kalman Filter correction, which utilizes a dynamic, scale-invariant Prediction Error metric as a trigger for motion anomaly detection. This allows the system to distinguish between measurement noise and sharp target maneuvers, executing an adaptive state reset using finite differences only at critical moments. Experimental validation on edge hardware (Raspberry Pi 5) using highly dynamic video sequences from the UAV123 and VisDrone datasets demonstrated that the proposed approach maintains an average processing speed of 18.89 FPS. By limiting deep neural network invocations to merely 2.71% of total frames, the algorithm successfully curtails thermal throttling while achieving a global Mean Root Square Error (RMSE) of 259.10 pixels across highly erratic trajectories. The method ensures high tracking reliability without a critical increase in computational load, making it highly suitable for use in autonomous embedded systems. Full article

Weakly supervised video anomaly detection (WS-VAD) localizes anomalous events in untrimmed videos using only video-level annotations. While CLIP-based methods have advanced this task through vision–language alignment, widely adopted approaches construct text prototypes from short category-name prompts of at most five words, leaving the CLIP text encoder not fully exploited. We propose SETAS-VAD, which addresses this gap through a Category Semantic Alignment (CSA) loss function: for each anomaly category, a large language model generates multi-sentence descriptions covering complementary semantic aspects, encoded once offline into frozen prototype vectors. An InfoNCE contrastive objective pulls attention-weighted anomaly features toward ground-truth category prototypes at zero additional inference overhead (prototype generation and encoding are performed once offline as a preprocessing step, not at test time). Under fully reproducible conditions on UCF-Crime and XD-Violence, SETAS-VAD achieves state-of-the-art temporal localization (30.45% mAP on XD-Violence, 12.16% on UCF-Crime), with per-threshold gains increasing at stricter IoU values, indicating improved boundary precision rather than coarse detection sensitivity. Full article

Concealed fires within the insulation layers of buildings, such as cold storage facilities and cinemas, present a serious fire hazard because heat generated by electrical faults can accumulate behind protective panels before ignition and then spread rapidly once combustion begins. Conventional fire detection methods have limited capability to identify these hidden thermal abnormalities at the pre-ignition stage. To address this problem, this paper proposes a deep learning method, called the Multi-Scale Cross-Modal Fusion Network (MSCMFNet), that uses multispectral images to identify abnormal heat sources beneath insulation layers before visible combustion occurs. A standardized experimental platform was developed to accurately simulate subsurface heat sources within the pre-ignition temperature range of insulation materials. Instead of relying on fixed temperature thresholds, the proposed method learns the characteristic spectral patterns produced by hidden heating. It extracts information from different spectral bands, combines these complementary features, and verifies the persistence of detected heat sources over time to reduce false alarms caused by non-fire disturbances. Experimental results demonstrate that the proposed method can effectively detect concealed thermal anomalies before ignition, providing reliable early warning and offering a promising approach to improving fire safety in buildings that make extensive use of insulation materials. Full article

This study evaluates groundwater quality in the Bismil Plain (Diyarbakır, Southeast Türkiye) using a total of 208 samples collected from 26 wells during eight seasonal sampling periods conducted between 2022 and 2024. In each sample, pH, electrical conductivity (EC), and the major ions Ca²⁺, Mg²⁺, Na⁺, K⁺, Cl⁻, SO₄²⁻, HCO₃⁻ and NO₃⁻ were analyzed, and a WHO-based Water Quality Index (WQI) was calculated for every observation. The study combines classical hydrochemical interpretation methods, including descriptive statistics, hierarchical correlation analysis, variance inflation factor, and Piper and Gibbs diagrams, with an explainable machine learning framework integrating SHAP-based feature selection into Random Forest, XGBoost, support vector regression, and stacking ensemble models. In addition, spatial residuals were evaluated using Moran’s I and ordinary kriging, anomalies were identified using Isolation Forest and Local Outlier Factor algorithms, and predictive uncertainty was quantified through bootstrap resampling. WQI values ranged from 79.37 to 125.48 (mean: 99.67), with all samples classified only within the “Good” (49.5%) and “Poor” (50.5%) quality categories, indicating that the aquifer is close to a critical water-quality threshold. Spatially, the highest (poorest-quality) WQI values form a coherent zone in the south-western and central parts of the plain, whereas the central-eastern wells return the lowest values; the same pattern is reproduced by all four models. XGBoost and the stacking ensemble models showed comparable predictive performance (R² = 0.911 and 0.910; RMSE = 3.29 and 3.27, respectively), while SHAP analysis identified EC as the dominant controlling factor, followed by NO₃⁻, SO₄²⁻, Ca²⁺, Mg²⁺ and Cl⁻ (mean |SHAP| = 6.86, 1.57, 1.10, 1.09, 0.85 and 0.72 WQI units, respectively). Moran’s I computed on the residual fields was −0.067 (p = 0.275) for XGBoost and −0.068 (p = 0.273) for the stacking ensemble, so ordinary kriging of these residuals produced an essentially null correction, whereas the SVR residuals remained spatially autocorrelated (I = 0.242; p = 0.001) and were meaningfully corrected by the geostatistical step. The originality of the study lies in integrating explainable machine learning, geostatistical residual analysis, anomaly detection, and bootstrap-based uncertainty assessment within a unified framework for a multi-season groundwater dataset, while also evaluating the effectiveness of spatial correction using a Moran’s I-based approach. Full article

Consistency monitoring is essential for safe battery energy storage system operation, yet practical data often exhibit asynchronous sampling. This study proposes a tick-driven multi-scale consistency analysis and unsupervised detection method for energy storage batteries. Actual cell-voltage update instants are used as analysis ticks, while high-frequency string-level variables are aggregated over adjacent tick intervals to describe operating conditions. Voltage-dispersion features are then used for anomaly scoring and cell-level localization. The method was evaluated using two-day station data and a controlled 20 Ah 16-series module experiment. In the station dataset, 190 effective ticks were extracted, and a transient consistency deterioration at 24,023 s showed a voltage range of 0.049 V and a standard deviation of 0.0057 V. In the controlled experiment, 185 ticks were obtained from 166,797 voltage samples after 900 s batch resampling, reducing cell-level evaluation instances by over 99%; cell #13 was identified as the dominant high-response cell. The method provides an interpretable framework for consistency monitoring and abnormal-cell localization under asynchronous sampling. Full article

Epilepsy is a challenging brain disease that requires significant clinical findings. (1) Background: The aim of this study is to improve the success rate of epilepsy detection using a newly developed method by optimizing the high-dimensional dataset obtained from brain MRI images. Standard machine learning models fall short of achieving the desired success in high-dimensional datasets. To achieve this, we aimed to develop an optimized hybrid model by combining the local classification power of the k-Nearest Neighbor classifier and the anomaly detection success of the negative selection algorithm. (2) Methods: Cortical and subcortical brain regions were analyzed to examine volumetric differences. A dataset was created by identifying regions statistically significant for epilepsy. This dataset was then optimized using the Scatter Search Snake Optimization algorithm. The performances of six different machine learning models trained on this optimized dataset were compared. (3) Results: The standard and popular models, SVM (82.70%), kNN (78.70%), RF (69.30%), MLP (73.30%), and NSA (95.89%), demonstrated a detection success rate. In contrast, the proposed hybrid model, kNN-NSA (98.65%), demonstrated a detection success rate. (4) Conclusions: The optimized hybrid kNN-NSA approach, which considers local density in such high-dimensional datasets and tolerates outliers within the self-data, appears to outperform traditional methods. Furthermore, this study has demonstrated that volumetric differences in regions not previously reported in the literature, such as WM-hypointensities, ventral DC, and choroid plexus, may be effective in the decision-making process for diagnosing epilepsy, as they are also found to be significant. Full article

Background: Artificial intelligence (AI), which spans machine learning (ML), deep learning (DL), computer vision, and natural language processing (NLP), is now used across obstetric care, including ultrasound interpretation (biometry, anomaly detection), fetal monitoring (cardiotocography), maternal risk stratification (preeclampsia, preterm birth, hemorrhage), labor and delivery decision support, genomic screening, and telehealth. Methods: We conducted a narrative (non-systematic) review of the literature published between 2016 and 2026, distinguishing the level of evidence supporting each application. Results: Reported performance is frequently high for image-based tasks such as fetal biometry and anomaly detection (accuracy and AUC often exceeding 0.85), whereas intrapartum CTG analysis remains modest (AUROC ~0.60–0.70, overlapping the inter-observer variability of clinicians). Most published evidence is retrospective and internally validated; comparatively few tools have undergone external or prospective validation, and only a small number have received regulatory clearance. Limitations: The evidence base is heterogeneous, external validation and calibration are often absent, and we did not perform a formal risk-of-bias appraisal. Conclusions: AI has real potential to improve prenatal diagnosis and individualized care, but claims that it is ready for the clinic are often premature. Prospective and external validation, calibration and clinical-utility assessment, transparent reporting, attention to bias and equity, and sustained clinician oversight are prerequisites for safe adoption. Full article

We address here anomaly detection in the context of smart homes and the industrial internet of things (IIoT) by proposing a statistical framework based on Weibull mixture models (WMM) with context specific outlier handling. We model the normal traffic according to IoT device traffic characteristics. The outliers are modeled by uniform distributions for smart homes and Weibull distributions for the IIoT, reflecting their distinct attack profiles. We validated the proposed framework on both real and synthetic datasets for the specific context of the IIoT. WMM outperforms benchmark methods representing the common outlier detection approaches, achieving consistent robust ROC-AUC of 0.98 and Precison-AUC of 0.97. For its deployment in smart home and IIoT contexts, the framework provides adaptable architectural design to improve its efficiency implementation and management. Full article

Flight data-driven modeling has become an important approach for trajectory prediction, anomaly detection, and risk assessment in unmanned aerial vehicles and other aerial systems. Such data are usually high-dimensional, nonlinear, multirate, and non-stationary, especially during maneuvering flight, environmental disturbance, and mission-phase transitions. Traditional physics-based methods and shallow machine learning models often have limited adaptability in these conditions, while Long Short-Term Memory (LSTM) networks and their variants have shown strong potential for learning temporal dependencies from complex flight sequences. This paper reviews the development and application of LSTM-family models for flight data analysis, with attention to both methodological performance and resource-aware deployment. The reviewed models include basic LSTM, BiLSTM, CNN-LSTM, ConvLSTM, LSTM autoencoder, attention-enhanced LSTM, graph-based LSTM, and uncertainty-aware LSTM. Their applications are discussed in three main areas: flight trajectory prediction, anomaly detection, and risk assessment. Beyond prediction accuracy, this review also examines robustness to distribution shift, physical consistency, interpretability of anomalies, uncertainty estimation, and onboard implementation. A four-layer and ten-dimensional evaluation framework is presented across data characteristics, model performance, physical-mechanism consistency, and system-engineering constraints. The evidence shows that model size, runtime memory, computational cost, inference latency, energy consumption, and target hardware are often insufficiently reported, while direct quantitative onboard validation remains scarce. This gap highlights the need for standardized deployment reporting. Full article

To enhance the accuracy and real-time performance of anomaly detection for stay cables in cable-stayed bridges, especially those in water-rich environments, this paper proposes a stay cable anomaly identification method based on multi-point displacement measurements of the main girder. First, combined with finite element modeling, two anomaly identification indicators—“fitted displacement” and “effective displacement” of the main girder—are constructed, and their correlations with the location and severity of cable damage are clarified. Second, a gray level–displacement mapping model based on the Eulerian perspective is established, enabling non-contact, high-precision displacement measurement suitable for remote and distributed monitoring conditions. Subsequently, using a scaled cable-stayed bridge model in the laboratory, the feasibility and effectiveness of the method are verified through multi-condition experiments. Finally, the whale optimization algorithm (WOA)-optimized random forest model, enhancing the accuracy and stability of cable anomaly classification and identification. The results demonstrate that the proposed method offers significant advantages in accuracy, real-time performance, and intelligent recognition. It shows great potential for application in the health monitoring and safety management of water-related cable-stayed bridges, providing a new approach and technical support for intelligent safety diagnosis and reinforcement. Full article

Field vibration monitoring of EMU traction motor bearings is commonly constrained by weak or relative labels, fluctuations in operating conditions, and limited abnormal samples. Under these conditions, learning a normal boundary from a single bearing position may be unstable, and isolated score spikes may lead to unreliable alarms. To address these issues, this study proposes a multi-axle reference and temporal-consistency-enhanced Deep SVDD framework, termed MA-TC-Deep SVDD, for field anomaly detection of EMU traction motor bearings. Unlike closed-set fault diagnosis that requires known fault labels, the proposed framework focuses on identifying deviations from the stable operating regime. First, a compact 10-dimensional time-frequency representation is constructed from valid vibration segments. Second, stable samples from the target bearing position and screened stable samples from other monitored positions on the same EMU are organized as a multi-axle reference set for one-class normal-boundary learning. Third, feature recalibration, temporal-consistency regularization, reference-score standardization, causal smoothing, and consecutive-alarm judgment are incorporated to improve robustness against field disturbances. The anomaly-prior-guided health-state interpretation module is retained only as post hoc evidence for describing severity evolution and does not feed back into the anomaly detection threshold. Field data collected from an in-service EMU over D1–D5 are used for validation. The results show that bearing position 1 has low anomaly scores on D1–D2, exhibits transitional deviation on D3, and shows persistent state deviation on D4–D5, while the other monitored positions remain comparatively stable. Under the current weak-label evaluation protocol, MA-TC-Deep SVDD achieves higher average anomaly detection performance than the compared baseline methods, with AUC = 0.909, AP = 0.872, Precision = 0.887, Recall = 0.802, F1 = 0.843, and FAR = 0.047. These results indicate that the proposed framework can provide field anomaly-warning and severity-oriented interpretation under weak-label monitoring conditions. However, it should not be interpreted as a replacement for disassembly-confirmed fault-type diagnosis or remaining useful life prediction. Full article