Search Results (41)

Background and Aims: The glucose metabolism pattern of the liver is closely related to liver diseases. In recent years, alcoholic hepatitis, viral hepatitis, fatty liver and other diseases have become important liver diseases that impact people’s lives. IL-33 (interleukin-33), as a member of the IL-1 cytokine family, and “alarmin” play a multi-dimensional regulatory role in various physiological and pathological processes of the liver. Methods: This study, by integrating transcriptomic data analysis and in vitro and in vivo experiments, expounds on new insights into the regulation of hepatocyte fate by IL-33 through metabolic reprogramming and reveals the potential, new role of IL-33 as a regulatory factor of metabolism. Conclusions: Our research further confirmed that IL-33, in addition to serving as an alarm hormone, is also a key checkpoint for liver metabolism, capable of promoting oxidative phosphorylation in hepatocytes and antagonizing acute liver injury induced by CCl₄. Full article

Rapid global urbanization is increasing the need for accurate, large-scale traffic monitoring to support sustainable transportation and city governance. Satellite video remote sensing offers a unique way to continuously observe urban road networks over large areas. It provides high-resolution spatio-temporal data that is essential for traffic flow analysis, infrastructure assessment, and dynamic urban planning. Moving vehicle detection in satellite video sequences is a basic task that turns raw imagery into useful traffic-state information, supporting these applications. Despite the advantages of satellite video data, detecting moving vehicles in practice remains a tough problem. Objects are extremely small and lack clear appearance details, while low local contrast makes them hard to separate from complex backgrounds. Satellite platform motion also introduces background misalignment and intensity fluctuations, resulting in missed detections and false alarms that hurt monitoring reliability. Furthermore, current methods do not fully exploit temporal motion cues or transform-domain priors, creating a performance bottleneck that restricts their practical use. To solve these problems, this paper proposes a Channel-Attentive Spatio-Temporal-Frequency Alignment (CASTFA) framework to effectively use and combine multi-dimensional features for moving vehicle detection in satellite videos, with the goal of providing high-quality traffic monitoring data to help smart city planning. Specifically, a State Space-Guided Temporal Compression (SSGTC) module first collects information along the time dimension with linear computational complexity, greatly reducing overhead while keeping motion cues that are critical for traffic-state estimation. The compressed temporal features are then processed with a multi-scale Haar wavelet transform to get hierarchical time-frequency representations that capture subtle motion dynamics across different frequency bands. At the same time, a pre-trained backbone network extracts multi-scale spatial features. To allow these different domains to work together, a Cross-Domain Feature Alignment (CDFA) mechanism aligns and combines spatial and time-frequency features through channel-attentive operations. Experimental results on the publicly available satellite video moving vehicle detection dataset show that the proposed CASTFA method consistently outperforms existing approaches, with better precision, recall, and F1-scores across diverse urban scenarios. These results show that CASTFA can provide reliable moving vehicle detection performance under difficult real-world conditions, supporting accurate traffic-flow monitoring and providing valuable geospatial intelligence for smart urban planning, transportation management, and sustainable city development. Full article

With the large-scale integration of offshore wind farms (OWFs), harmonic issues caused by the interaction between high-frequency switching of converters and complex network impedances pose severe challenges to power quality. Traditional harmonic monitoring heavily relies on post-event fixed-threshold alarm mechanisms, which struggle to achieve early warning during the low-distortion sub-health operation stage and lack the capability for multi-dimensional tracing of harmonic degradation sources. To address these limitations, this paper proposes a deep warning network for grid harmonics combining multi-step regression and multi-dimensional tracing within a unified multi-task learning (MTL) architecture. First, a deep shared feature encoder, integrating a bi-directional long short-term memory (Bi-LSTM) network with a multi-head self-attention (MHSA) mechanism, is utilized to extract high-order temporal coupling features between meteorological evolution and multi-node electrical states. Subsequently, the main task branch executes a k-step-ahead multivariate time-series regression to accurately predict the evolution trend of total harmonic distortion (THD) at both the point of common coupling (PCC) and the turbine terminal. Simultaneously, the auxiliary task branch performs multi-label micro-state classification based on relative degradation thresholds, achieving fine-grained multi-dimensional tracing covering spatial nodes, electrical attributes, and their joint micro-states. Experimental results on real-world OWF operational data demonstrate that through the joint optimization of regression and tracing tasks, the proposed MultiDimKStepMTL model significantly improves time-series prediction accuracy, achieving a $10.3\%$ relative improvement over single-task baselines, while substantially reducing computational overhead. This research successfully advances grid harmonic monitoring from passive response to proactive micro-state early warning, providing a solid, highly interpretable data-driven foundation for active filter control of offshore wind clusters. Full article

Faults in aero-engine rotating components account for more than 60% of total failures, and their early features are easily masked by noise under complex conditions. Traditional single-sensor diagnosis suffers from low feature utilization, poor interpretability, and weak cross-condition generalization. This paper proposes a multi-source fault diagnosis method for aero-engines based on an explainable boosted tree, integrating spatiotemporal attention (STA) and adaptive feature selection (AFS). We collect multi-domain data from four standard core sensors widely used in existing engine health management systems and extract multi-dimensional features to build a heterogeneous feature set. Adaptive feature selection is implemented using mutual information and a variance inflation factor. A spatiotemporal attention mechanism is introduced to weight and fuse features effectively. The fused features are used to train an XGBoost classifier, and SHAP values are adopted to quantify feature contributions and improve model interpretability. Uncertainty sources and sensitivity boundaries are quantitatively analyzed to support engineering acceptance. The method achieves high sensitivity to early weak faults and stable uncertainty under complex operating conditions. Tests on a fault simulation test rig show that the proposed method achieves 99.2% diagnosis accuracy and 97.5% cross-condition generalization accuracy, outperforming conventional models. It can identify early weak fault signatures, clarify key fault indicators, and provide a quantitative basis for fault tracing and maintenance decision-making. The method employs a standard sensor suite without additional hardware costs, features lightweight computation and low inference overhead, and delivers clear economic benefits by reducing false alarms, avoiding unplanned downtime, and optimizing maintenance resources. It offers a reliable, cost-effective solution for aero-engine fault diagnosis under complex operating conditions. Full article

With the advancement of intelligent manufacturing strategies, Cyber–Physical Production Systems (CPPSs) generate massive amounts of multidimensional, dynamic, and non-stationary data, posing significant challenges to real-time Process Monitoring. Existing anomaly detection methods often suffer from insufficient feature robustness when dealing with complex spatio-temporal dynamics, high computational complexity, and difficulties in effectively capturing incipient faults within deep topological structures. To address these issues, this paper proposes a Spatio-Temporal Variational Graph Statistical Attention Autoencoder (ST-VGSAE). First, the framework performs end-to-end multi-scale temporal decomposition via an Adaptive Lifting Wavelet Module, which enhances feature robustness while effectively suppressing noise. Furthermore, a spatio-temporal Token statistical self-attention mechanism with linear complexity is incorporated. By modulating local features via global statistics, it significantly reduces computational costs while enhancing anomaly discriminability. Experiments on the Tennessee Eastman (TE) process dataset demonstrate that the proposed model significantly outperforms state-of-the-art methods in key metrics such as the Fault Detection Rate and the False Alarm Rate, exhibiting superior noise robustness and real-time performance. Full article

Enterprises in industries such as coking and metallurgy possess extensive industrial equipment requiring real-time monitoring and timely fault detection. Transmitting all monitoring data to servers or cloud platforms for processing presents challenges, including substantial data volumes, high latency, and significant bandwidth consumption, thereby compromising the monitoring system’s real-time performance and stability. This paper proposes a cloud–edge collaborative approach for edge feature extraction in equipment monitoring. A three-tier collaborative architecture is established: “edge pre-processing-cloud optimization-edge iteration”. At the edge, lightweight time-domain and frequency-domain feature extraction modules are employed based on equipment structure and failure mechanisms to rapidly pre-process and extract features from monitoring data (e.g., equipment vibration), substantially reducing uploaded data volume. The cloud node constructs a diagnostic feature library through threshold self-learning and data-driven model training, then disseminates optimized feature extraction parameters to the edge node via this threshold learning mechanism. The edge node dynamically iterates its feature extraction capabilities based on updated parameters, enhancing the capture accuracy of critical fault features under complex operating conditions. Verification and demonstration applications were conducted using an enterprise’s online equipment monitoring system as the experimental scenario. The results indicate that the proposed method reduces data transmission volume by 98.21% and required bandwidth by 98.25% compared to pure cloud-based solutions, while effectively enhancing the monitoring system’s real-time performance. This approach significantly improves equipment monitoring responsiveness, reduces demands on network bandwidth and data transmission, and provides an effective technical solution for equipment health management within industrial IoT environments. Full article

Traffic accidents remain a major public safety concern, particularly in regions where rapid motorization and limited infrastructure increase crash risk. This study proposes a machine learning-based framework to classify traffic accident severity and identify high-risk road segments using multidimensional crash data from Şırnak Province, Turkey. The dataset, obtained from the General Directorate of Security (EGM), contains 29 variables describing traffic, geometric, and operational roadway characteristics for crashes reported between 2018 and 2023. Due to the severe imbalance between injury and fatal crashes, the Synthetic Minority Oversampling Technique (SMOTE) was applied to enhance model sensitivity to the minority class. Five classifiers—Logistic Regression (LR), Support Vector Machines (SVM), Multilayer Perceptron (MLP), Random Forest (RF), and Extreme Gradient Boosting (XGBoost)—were trained and evaluated using accuracy, F1-score, ROC-AUC, and alarm metrics. Results from the original dataset showed that several models struggled to detect fatal crashes, while LR demonstrated moderate sensitivity. After SMOTE, performance improved across all models. XGBoost achieved the highest F1-score (0.61) with the lowest False Alarm rate (0.01), followed by RF and MLP, whereas SVM and LR yielded comparatively lower accuracy. Computation time analysis indicated that LR and SVM had the fastest runtimes, while MLP and XGBoost required longer training times. Overall, findings highlight the effectiveness of ensemble models—particularly XGBoost—in capturing critical crash patterns and supporting risk-based decision-making. Future work should incorporate time-series analysis and GIS-based spatial modeling to further enhance predictive capability and inform geographically targeted safety interventions. Full article

The safe and reliable operation of energy storage stations critically depends on their thermal management systems, specifically the health states or working conditions of involved sensors, such as temperature, humidity, and pressure sensor. Impacted by several environmental factors, some indiscernible defects including signal drift, elevated noise, and response lag may affect the exact surveillance of batteries, leading to potential combustion or even explosion, which requires fault risk early-warning to support timely maintenance. These multi-sensor environmental factor data typically exhibit mixed characteristics, component coupling, and high uncertainty, thus impacting diagnostic accuracy and robustness. With this motivation, this study proposes a pattern-guided framework for vulnerability diagnosis using Component Importance Measure. A pattern-guided strategy is first designed to perform rule induction and fuzzy processing on discrete and continuous sensor data, respectively, to extract underlying vulnerability-related components. Subsequently, a component Importance Measure, which assesses the impact of individual risks on the whole reliability, is established to achieve unified integration and mapping of previous heterogeneous information, therefore providing multidimensional vulnerability representations. An empirical case study demonstrates the fault detection rate, false alarm control, and diagnostic stability of the proposed framework. Full article

The alarming realism of Deepfake presents a significant challenge to digital authenticity, yet its inherent difficulty in synchronizing the emotional cues between facial expressions and speech offers a critical opportunity for detection. However, most existing approaches rely on general-purpose backbones for unimodal feature extraction, resulting in an inadequate representation of fine-grained dynamic emotional expressions. Although a limited number of studies have explored cross-modal emotional consistency of deepfake detection, they typically employ shallow fusion techniques which limit latent expressiveness. To address this, we propose ACE-Net, a novel framework that identifies forgeries via multimodal emotional inconsistency. For the speech modality, we design a bidirectional cross-attention mechanism to fuse acoustic features from a lightweight CNN-based model with textual features, yielding a representation highly sensitive to fine-grained emotional dynamics. For the visual modality, a MobileNetV3-based perception head is proposed to adaptively select keyframes, yielding a representation focused on the most emotionally salient moments. For multimodal emotional consistency discrimination, we develop a multi-dimensional fusion strategy to deeply integrate high-level emotional features from different modalities within a unified latent space. For unimodal emotion recognition, both the audio and visual branches outperform baseline models on the CREMA-D dataset. Building on this, the complete ACE-Net model achieves a state-of-the-art AUC of 0.921 on the challenging DFDC benchmark. Full article

Currently, thermal power units undertake the task of peak and frequency regulation, and their internal equipment is in a non-conventional environment, which could very easily fail and thus lead to unplanned shutdown of the unit. To realize the condition monitoring and early warning of the key equipment inside coal power units, this study proposes a deep learning-based equipment condition anomaly detection model, which combines the deep autoencoder (DAE), Transformer, and Gaussian mixture model (GMM) to establish an anomaly detection model. DAE and the Transformer encoder extract static and time-series features from multi-dimensional operation data, and GMM learns the feature distribution of normal data to realize anomaly detection. Based on the data verification of boiler superheater equipment and turbine bearings in real power plants, the model is more capable of detecting equipment anomalies in advance than the traditional method and is more stable with fewer false alarms. When applied to the superheater equipment, the proposed model triggered early warnings approximately 90 h in advance compared to the actual failure time, with a lower false negative rate, reducing the missed detection rate by 70% compared to the Transformer-GMM (TGMM) model, which verifies the validity of the model and its early warning capability. Full article

As low-voltage distribution networks incorporate increasingly diverse loads, series arc faults exhibit weak characteristics that are easily masked by load currents, leading to high misjudgment rates in traditional detection methods. This paper proposes a series arc fault detection method based on an improved Light Gradient Boosting Machine (LightGBM) model. First, a test platform containing 12 household loads was built to collect arc data from both individual and composite loads. Composite loads refer to composite load conditions where multiple devices are running simultaneously and arcing occurs on some loads. To address the challenge of feature extraction, Variational Mode Decomposition (VMD) is employed to isolate the fundamental frequency component. To enhance high-frequency arc characteristics, singular value decomposition (SVD) is then applied. A multidimensional statistical feature set—comprising peak-to-peak value, kurtosis, and other indicators—is constructed. Finally, the LightGBM algorithm is used to identify arc faults based on these features. To overcome the LightGBM model’s limited ability to focus on hard-to-classify samples, a dynamic weighted hybrid loss function is developed. Experiments demonstrate that the proposed method achieves 98.9% accuracy across 223,615 sample groups. When deployed on STM32H723VGT6 hardware, the average fault alarm time is 83.8 ms, meeting requirements. Full article

Lubricating oil degradation directly impacts friction coefficient, wear rate, and lubrication regime transitions, making precise health quantification essential for predictive tribological maintenance. However, conventional evaluation methods fail to capture subtle tribological changes preceding lubrication failure, often oversimplifying complex multi-parameter relationships critical to friction and wear performance. To address this challenge, this study proposes Seasonal–Trend decomposition using Loess, a Factor Attention Network, a Temporal Convolutional Network, and an Informer with Long Short-Term Memory Variational Autoencoder (SFTI-LVAE) framework for continuous tribological health assessment of diesel engine lubricants. The approach integrates Seasonal–Trend decomposition using Loess (STL) for trend–seasonal separation, a Factor Attention Network (FAN) for multidimensional feature fusion, and a Temporal Convolutional Network (TCN)-enhanced Informer for capturing long-term tribological dependencies. By combining Long Short-Term Memory (LSTM) temporal modeling with Variational Autoencoder (VAE) reconstruction, the method quantifies lubricant health through reconstruction error, establishing a direct correlation between data deviation and tribological performance degradation. Additionally, permutation importance-based feature evaluation and parameter contribution quantification techniques enable deep mechanistic analysis and fault source tracing of lubricant health degradation. Experimental validation using multi-sensor monitoring data demonstrates that SFTI-LVAE achieves a 96.67% fault detection accuracy with zero false alarms, providing early warning 6.47 h before lubrication failure. Unlike traditional anomaly detection methods that only classify conditions as abnormal or normal, the proposed continuous health index reveals gradual tribological degradation processes, capturing subtle viscosity–temperature relationships and wear particle evolution indicating early lubrication regime transitions. The health index correlates strongly with tribological performance indicators, enabling a transition from reactive maintenance to predictive tribological management, providing an innovative solution for equipment health evaluation in the digital tribology era. Full article

In the context of intelligent coal mine safety monitoring, an integrated prediction and early-warning method named MTGNN-Bayesian-IF-DBSCAN (Multi-Task Graph Neural Network–Bayesian Optimization–Isolation Forest–Density-Based Spatial Clustering of Applications with Noise) is proposed to address the challenges of gas concentration prediction and anomaly detection in coal mining faces. The MTGNN (Multi-Task Graph Neural Network) is first employed to model the spatiotemporal coupling characteristics of gas concentration and wind speed data. By constructing a graph structure based on sensor spatial dependencies and utilizing temporal convolutional layers to capture long short-term time-series features, the high-precision dynamic prediction of gas concentrations is achieved via the MTGNN. Experimental results indicate that the MTGNN outperforms comparative algorithms, such as CrossGNN and FourierGNN, in prediction accuracy, with the mean absolute error (MAE) being as low as 0.00237 and the root mean square error (RMSE) maintained below 0.0203 across different sensor locations (T0, T1, T2). For anomaly detection, a Bayesian optimization framework is introduced to adaptively optimize the fusion weights of IF (Isolation Forest) and DBSCAN (Density-Based Spatial Clustering of Applications with Noise). Through defining the objective function as the F1 score and employing Gaussian process surrogate models, the optimal weight combination (w_if = 0.43, w_dbscan = 0.52) is determined, achieving an F1 score of 1.0. By integrating original concentration data and residual features, gas anomalies are effectively identified by the proposed method, with the detection rate reaching a range of 93–96% and the false alarm rate controlled below 5%. Multidimensional analysis diagrams (e.g., residual distribution, 45° diagonal error plot, and boxplots) further validate the model’s robustness in different spatial locations, particularly in capturing abrupt changes and low-concentration anomalies. This study provides a new technical pathway for intelligent gas warning in coal mines, integrating spatiotemporal modeling, multi-algorithm fusion, and statistical optimization. The proposed framework not only enhances the accuracy and reliability of gas prediction and anomaly detection but also demonstrates potential for generalization to other industrial sensor networks. Full article

To address the high false alarm rate of intrusion detection systems based on distributed acoustic sensing (DAS) for power cables in complex underground environments, an innovative GRT-Transformer multimodal deep learning model is proposed. The core of this model lies in its distinctive three-branch parallel collaborative architecture: two branches employ Gramian Angular Summation Field (GASF) and Recursive Pattern (RP) algorithms to convert one-dimensional intrusion waveforms into two-dimensional images, thereby capturing rich spatial patterns and dynamic characteristics and the third branch utilizes a Gated Recurrent Unit (GRU) algorithm to directly focus on the temporal evolution features of the waveform; additionally, a Transformer component is integrated to capture the overall trend and global dependencies of the signals. Ultimately, the terminal employs a Bidirectional Long Short-Term Memory (BiLSTM) network to perform a deep fusion of the multidimensional features extracted from the three branches, enabling a comprehensive understanding of the bidirectional temporal dependencies within the data. Experimental validation demonstrates that the GRT-Transformer achieves an average recognition accuracy of 97.3% across three typical intrusion events—illegal tapping, mechanical operations, and vehicle passage—significantly reducing false alarms, surpassing traditional methods, and exhibiting strong practical potential in complex real-world scenarios. Full article

Poisoning and suffocation accidents occurred frequently in the pre-treatment pool workshops of biogas plants, so this paper provided a multi-dimensional risk analysis model: Bow-Tie-Qualitative Comparative Analysis (QCA)-Bayesian Neural Network-Consequence Simulation. First, the reasons for biogas poisoning and suffocation accidents were clarified through Bow-Tie. Then, the QCA method explored the accident cause combination paths in management. Next, the frequency distribution of biogas poisoning and suffocation accidents in the pre-treatment pool workshop was predicted to be 0.61–0.66 using the Bayesian neural network model, and the uncertainty of the forecast outcome was given. Finally, the ANSYS Fluent 16.0 simulation of biogas diffusion in three different ventilation types and a grid-independent solution of the simulation were conducted. The simulation results showed the distribution of methane, carbon dioxide and hydrogen sulfide gases and the hazards of the three gases to workers were analyzed. In addition, according to the results, this paper discussed the importance and necessity of ventilation in pre-treatment pool workshops and specified the hazard factors in biogas poisoning and suffocation accidents in the pre-treatment pool workshops. Some suggestions on gas alarms were also proposed. Full article