Search Results (2,256)

Accurate natural gas price forecasting is vital for risk management, trading strategies, and policy-making in energy markets. This study proposes and evaluates four hybrid deep learning architectures—CNN-LSTM-Attention, CNN-BiLSTM-Attention, TCN-LSTM-Attention, and TCN-BiLSTM-Attention—integrating convolutional feature extraction, sequential learning, and attention mechanisms. Using Henry Hub and NYMEX datasets, the models are trained on long historical periods and tested under multi-step horizons. The results show that all hybrid models significantly outperform the traditional moving average benchmark, achieving R² values above 95% for one-step-ahead forecasts and maintaining an accuracy of over 87% at longer horizons. CNN-BiLSTM-Attention performs best in short-term prediction due to its ability to capture bidirectional dependencies, while TCN-based models demonstrate greater robustness over extended horizons due to their effective modeling of long-range temporal structures. These findings confirm the advantages of deep learning hybrids in energy forecasting and emphasize the importance of horizon-sensitive evaluation. This study contributes methodological innovation and provides practical insights for market participants, with future directions including the integration of macroeconomic and climatic factors, exploration of advanced architectures such as Transformers, and probabilistic forecasting for uncertainty quantification. Full article

To address the challenge that MOSFET temperature in motor controllers is influenced by multiple factors, exhibits strong temporal dependence, and involves complex feature interactions, this study proposes a temperature prediction model that integrates Temporal Convolutional Networks (TCNs) and the Informer architecture in parallel, enhanced with a cross-attention mechanism. The model leverages TCNs to capture local temporal patterns, while the Informer extracts long-range dependencies, and cross-attention strengthens feature interactions across channels to improve predictive accuracy. A dataset was constructed based on measured MOSFET temperatures under various operating conditions, with input features including voltage, load current, switching frequency, and multiple ambient temperatures. Experimental evaluation shows that the proposed method achieves a mean absolute error of 0.2521 °C, a root mean square error of 0.3641 °C, and an R² of 0.9638 on the test set, outperforming benchmark models such as Times-Net, Informer, and LSTM. These results demonstrate the effectiveness of the proposed approach in reducing prediction errors and enhancing generalization, providing a reliable tool for real-time thermal monitoring of motor controllers. Full article

Recurrent erysipelas is a common and clinically significant condition that poses challenges for both patients and healthcare systems. Each episode may damage lymphatic vessels, leading to chronic lymphedema, which perpetuates the risk of further relapses. Recurrence rates remain high, ranging from 11% in outpatients during the first year to up to 46% of hospitalized patients within three years. The lower limbs are the most frequent site, although recurrences may also occur in other regions, such as the upper limb after mastectomy with lymph node dissection. This review summarizes current knowledge on risk factors, preventive measures, and chemoprophylaxis in recurrent erysipelas. Modifiable risk factors such as obesity, diabetes, venous insufficiency, tinea pedis, and poor hygiene play an important role, while non-modifiable factors include age, sex, and a history of prior episodes. Non-pharmacological strategies—weight reduction, glycemic control, smoking cessation, compression therapy, and meticulous skin care—form the cornerstone of prevention and may reduce the need for long-term antibiotics. Antibiotic prophylaxis, most commonly with oral penicillin V or intramuscular benzathine penicillin, has been shown to lower recurrence rates. However, efficacy may be reduced in patients with chronic edema or severe obesity. Macrolides serve as alternatives in penicillin-allergic patients, but concerns remain about resistance, adverse effects, and drug–drug interactions. In conclusion, recurrent erysipelas requires a multifaceted approach. While antibiotic prophylaxis is effective, its long-term success depends on simultaneous management of underlying conditions. Further studies are needed to define optimal regimens, treatment duration, and non-antibiotic alternatives. Full article

Accurate semantic segmentation of high-resolution remote sensing imagery is challenged by substantial intra-class variability, inter-class similarity, and the limitations of single-modality data. This paper proposes MMFNet, a novel multimodal fusion network that leverages the Mamba architecture to efficiently capture long-range dependencies for semantic segmentation tasks. MMFNet adopts a dual-encoder design, combining ResNet-18 for local detail extraction and VMamba for global contextual modelling, striking a balance between segmentation accuracy and computational efficiency. A Multimodal Feature Fusion Block (MFFB) is introduced to effectively integrate complementary information from optical imagery and digital surface models (DSMs), thereby enhancing multimodal feature interaction and improving segmentation accuracy. Furthermore, a frequency-aware upsampling module (FreqFusion) is incorporated in the decoder to enhance boundary delineation and recover fine spatial details. Extensive experiments on the ISPRS Vaihingen and Potsdam benchmarks demonstrate that MMFNet achieves mean IoU scores of 83.50% and 86.06%, outperforming eight state-of-the-art methods while maintaining relatively low computational complexity. These results highlight MMFNet’s potential for efficient and accurate multimodal semantic segmentation in remote sensing applications. Full article

Bitcoin transaction anomaly detection is essential for maintaining financial market stability. A significant challenge is capturing the dynamically evolving transaction patterns within transaction networks. Dynamic graph models are effective for characterizing the temporal evolution of transaction systems. However, current methods struggle to mine long-range temporal dependencies and address the class imbalance caused by the scarcity of abnormal samples. To address these issues, we propose a novel approach, the Bidirectional EvolveGCN with Class-Balanced Learning Network (Balanced-BiEGCN), for Bitcoin transaction anomaly detection. This model integrates two key components: (1) a bidirectional temporal feature fusion mechanism (Bi-EvolveGCN) that enhances the capture of long-range temporal dependencies and (2) a Sample Class Transformation (CSCT) classifier that generates difficult-to-distinguish abnormal samples to balance the positive and negative class distribution. The generation of these samples is guided by two loss functions: the adjacency distance adaptive loss function and the symmetric space adjustment loss function, which optimize the spatial distribution and confusion of abnormal samples. Experimental results on the Elliptic dataset demonstrate that Balanced-BiEGCN outperforms existing baseline methods in anomaly detection. Full article

Nitrous oxide (N₂O), a potent greenhouse gas, is an important environmental concern associated with biological nitrogen removal in wastewater treatment plants. Anaerobic ammonium oxidation (anammox), recognized as an advanced carbon-neutral nitrogen removal technology, requires a continuous supply of nitrite, which also serves as a key precursor for N₂O generation. However, the regulation of the carbon-to-nitrogen (C/N) ratio to minimize N₂O emission in mainstream anammox systems remains insufficiently understood. In this study, we evaluated the long-term nitrogen removal performance and N₂O emission potential of an oxygen-limited anammox biofilm reactor treating synthetic municipal wastewater with a typical C/N range of 4.0–6.0. Experimental results demonstrated that the highest nitrogen removal efficiency (95.3%), achieved through coupled anammox and denitrification, and the lowest N₂O emission factor (0.73%) occurred at a C/N ratio of 5.0. As the C/N ratio increased from 4.0 to 5.0, N₂O emissions decreased progressively, but rose slightly when the ratio was further increased to 6.0. High-throughput sequencing revealed that microbial community composition and the abundance of key functional taxa were significantly influenced by the C/N ratio. At a C/N ratio of 5.0, proliferation of anammox bacteria and the disappearance of Acinetobacter populations appeared to contribute to the significant reduction in N₂O emission. Furthermore, gene annotation analysis indicated higher abundances of anammox-associated genes (hzs, hdh) and N₂O reductase gene (nosZ) at this ratio compared with others. Overall, this study identifies a C/N-dependent strategy for mitigating N₂O emissions in mainstream anammox systems and provides new insights into advancing carbon-neutral wastewater treatment. Full article

Crack detection and analysis are essential for maintaining the stability and longevity of infrastructure; however, traditional manual inspections or simple image processing techniques are inefficient. To address this, automated crack segmentation using deep learning is being actively researched. This study proposes a hybrid model combining U-Net and a Vision Transformer to enhance the accuracy of crack segmentation. The proposed model is based on U-Net’s encoder–decoder architecture and integrates a Convolutional Neural Network (CNN), which is strong in local feature extraction, with a Vision Transformer, which excels at capturing global features and long-range dependencies, to effectively learn complex crack patterns. Experimental results on the CrackSeg9k dataset show that the proposed model achieves a mean Intersection over Union (mIoU) of 0.7184, demonstrating superior segmentation performance compared to other models like the conventional U-Net and Attention U-Net. This indicates that the proposed hybrid approach successfully leverages both local and global features, proving its effectiveness in segmenting complex and irregular crack patterns. Full article

The growing demand for reliable long-term traffic forecasting has become increasingly critical in the development of intelligent transportation systems (ITS). However, capturing both strong periodic patterns and long-range temporal dependencies presents a significant challenge, and existing approaches often fail to balance these factors effectively, resulting in unstable or suboptimal predictions. To address this issue, we propose MixModel , a novel hybrid framework that integrates TimesNet and Informer to leverage their complementary strengths. Specifically, the TimesNet branch extracts periodic variations through frequency-domain decomposition and multi-scale convolution, while the Informer branch employs ProbSparse attention to efficiently capture long-range dependencies across extended horizons. By unifying these capabilities, MixModel achieves enhanced forecasting accuracy, robustness, and stability compared with state-of-the-art baselines. Extensive experiments on real-world highway datasets demonstrate the effectiveness of our model, highlighting its potential for advancing large-scale urban traffic management and planning. To the best of our knowledge, MixModel is the first hybrid framework that explicitly bridges frequency-domain periodic modeling and efficient long-range dependency learning for long-term traffic forecasting, establishing a new benchmark for future research in Intelligent Transportation Systems. Full article

Spinal cord injury (SCI) often results in long-term locomotor impairments, and strategies to enhance functional recovery remain limited. While epidural electrical stimulation (EES) has shown clinical promise, our understanding of the mechanisms by which it improves function remains incomplete. Here, we use genetic tools in an animal model to perform neuromodulation and treadmill rehabilitation in a manner similar to EES, but with the benefit of the genetic tools and animal model allowing for targeted manipulation, precise quantification of the cells and circuits that were manipulated, and the gathering of extensive kinematic data. We used a viral construct that selectively transduces large diameter afferent fibers (LDAFs) with a designer receptor exclusively activated by a designer drug (hM3Dq DREADD; a chemogenetic construct) to increase the excitability of large fibers specifically, in the rat contusion SCI model. As changes in locomotion with afferent stimulation can be subtle, we carried out a detailed characterization of the kinematics of locomotor recovery over time. Adult Long-Evans rats received contusion injuries and direct intraganglionic injections containing AAV2-hSyn-hM3Dq-mCherry, a viral vector that has been shown to preferentially transduce LDAFs, or a control with tracer only (AAV2-hSyn-mCherry). These neurons then had their activity increased by application of the designer drug Clozapine-N-oxide (CNO), inducing tonic excitation during treadmill training in the recovery phase. Kinematic data were collected during treadmill locomotion across a range of speeds over nine weeks post-injury. Data were analyzed using a mixed effects model chosen from amongst several models using information criteria. That model included fixed effects for treatment (DREADDs vs. control injection), time (weeks post injury), and speed, with random intercepts for rat and time point nested within rat. Significant effects of treatment and treatment interactions were found in many parameters, with a sometimes complicated dependence on speed. Generally, DREADDs activation resulted in shorter stance duration, but less reduction in swing duration with speed, yielding lower duty factors. Interestingly, our finding of shorter stance durations with DREADDs activation mimics a past study in the hemi-section injury model, but other changes, including the variability of anterior superior iliac spine (ASIS) height, showed an opposite trend. These may reflect differences in injury severity and laterality (i.e., in the hemi-section injury the contralateral limb is expected to be largely functional). Furthermore, as with that study, withdrawal of DREADDs activation in week seven did not cause significant changes in kinematics, suggesting that activation may have dwindling effects at this later stage. This study highlights the utility of high-resolution kinematics for detecting subtle changes during recovery, and will enable the refinement of neuromechanical models that predict how locomotion changes with afferent neuromodulation, injury, and recovery, suggesting new directions for treatment of SCI. Full article

With the escalating global cyber threats, Distributed Denial of Service (DDoS) attacks have become one of the most disruptive and prevalent network attacks. Traditional DDoS detection systems face significant challenges due to the unpredictable nature, diverse protocols, and coupled behavioral patterns of attack traffic. To address this issue, this paper proposes a novel approach for DDoS attack detection by leveraging the Transformer architecture to model both temporal dependencies and behavioral patterns, significantly improving detection accuracy. We utilize the global attention mechanism of the Transformer to effectively capture long-range temporal correlations in network traffic, and the model’s ability to process multiple traffic features simultaneously enables it to identify nonlinear interactions. By reconstructing the CIC-DDoS2019 dataset, we strengthen the representation of attack behaviors, enabling the model to capture dynamic attack patterns and subtle traffic anomalies. This approach represents a key contribution by applying Transformer-based self-attention mechanisms to accurately model DDoS attack traffic, particularly in handling complex and dynamic attack patterns. Experimental results demonstrate that the proposed method achieves 99.9% accuracy, with 100% precision, recall, and F1 score, showcasing its potential for high-precision, low-false-alarm automated DDoS attack detection. This study provides a new solution for real-time DDoS detection and holds significant practical implications for cybersecurity systems. Full article

This paper presents a comprehensive study on automated defect detection in complex structures using phased array ultrasonic testing data, focusing on both traditional signal processing and advanced deep learning methods. As a non-AI baseline, the well-known signal-to-noise ratio algorithm was improved by introducing automatic depth gate calculation using derivative analysis and eliminated the need for manual parameter tuning. Even though this method demonstrates robust flaw indication, it faces difficulties for automatic defect detection in highly noisy data or in cases with large pore zones. Considering this, multiple DL architectures—including fully connected networks, convolutional neural networks, and a novel Convolutional Attention Temporal Transformer for Sequences—are developed and trained on diverse datasets comprising simulated CIVA data and real-world data files from welded and composite specimens. Experimental results show that while the FCN architecture is limited in its ability to model dependencies, the CNN achieves a strong performance with a test accuracy of 94.9%, effectively capturing local features from PAUT signals. The CATT-S model, which integrates a convolutional feature extractor with a self-attention mechanism, consistently outperforms the other baselines by effectively modeling both fine-grained signal morphology and long-range inter-beam dependencies. Achieving a remarkable accuracy of 99.4% and a strong F1-score of 0.905 on experimental data, this integrated approach demonstrates significant practical potential for improving the reliability and efficiency of NDT in complex, heterogeneous materials. Full article

In intensive broiler production, rapid environmental fluctuations can induce heat stress, adversely affecting flock welfare and productivity. Apparent temperature (AT), integrating temperature, humidity, and wind speed, provides a comprehensive thermal index, guiding predictive climate control. This study develops a multi-step AT forecasting model based on a hybrid SE-TCN–Transformer architecture enhanced with Kalman filtering. The temporal convolutional network with SE attention extracts short-term local trends, the Transformer captures long-range dependencies, and Kalman smoothing reduces prediction noise, collectively improving robustness and accuracy. The model was trained on multi-source time-series data from a commercial broiler house and evaluated for 5, 15, and 30 min horizons against LSTM, GRU, Autoformer, and Informer benchmarks. Results indicate that the proposed model achieves substantially lower prediction errors and higher determination coefficients. By combining multi-variable feature integration, local–global temporal modeling, and dynamic smoothing, the model offers a precise and reliable tool for intelligent ventilation control and heat stress management. These findings provide both scientific insight into multi-step thermal environment prediction and practical guidance for optimizing broiler welfare and production performance. Full article

This research introduces a hybrid framework that integrates stochastic modeling and machine learning for predicting postprandial glucose levels in individuals with Type 1 Diabetes (T1D). The primary aim is to enhance the accuracy of glucose predictions by merging a biophysical Glucose–Insulin–Meal (GIM) model with advanced machine learning techniques. This framework is tailored to utilize the Kaggle BRIST1D dataset, which comprises real-world data from continuous glucose monitoring (CGM), insulin administration, and meal intake records. The methodology employs the GIM model as a physiological prior to generate simulated glucose and insulin trajectories, which are then utilized as input features for the machine learning (ML) component. For this component, the study leverages the Light Gradient Boosting Machine (LightGBM) due to its efficiency and strong performance with tabular data, while Long Short-Term Memory (LSTM) networks are applied to capture temporal dependencies. Additionally, Bayesian regression is integrated to assess prediction uncertainty. A key advancement of this research is the transition from a deterministic GIM formulation to a stochastic differential equation (SDE) framework, which allows the model to represent the probabilistic range of physiological responses and improves uncertainty management when working with real-world data. The findings reveal that this hybrid methodology enhances both the precision and applicability of glucose predictions by integrating the physiological insights of Glucose Interaction Models (GIM) with the flexibility of data-driven machine learning techniques to accommodate real-world variability. This innovative framework facilitates the creation of robust, transparent, and personalized decision-support systems aimed at improving diabetes management. Full article

Accurate evaluation of subgrade behaviour under dynamic loading is essential for the long-term performance of transport infrastructure. While the Light Weight Deflectometer (LWD) is commonly used to assess subgrade stiffness, it provides only a single stiffness value and may not fully capture the time-dependent response of soil. This study presents an image-based vision system developed to monitor soil surface displacements during loading, enabling more detailed analysis of dynamic behaviour. The system incorporates high-speed cameras and MATLAB-based computer vision algorithms to track vertical movement of the plate during impact. Laboratory and field experiments were conducted to evaluate the system’s performance, with results compared directly to those from the LWD. A strong correlation was observed (R² = 0.9901), with differences between the two methods ranging from 0.8% to 13%, confirming the accuracy of the vision-based measurements despite the limited dataset. The findings highlight the system’s potential as a practical and cost-effective tool for enhancing subgrade assessment, particularly in applications requiring improved understanding of ground response under repeated or transient loading. Full article

Investigating atmospheric volatile organic compounds (VOCs) is critical for understanding their sources, chemical reactivity, and impacts on air quality, climate, and human health, especially in remote regions like the Tibetan Plateau where baseline data remains scarce. In this study, ambient VOCs species were simultaneously measured at four remote background sites on the Tibetan Plateau (Nyingchi, Namtso, Ngari, and Mount Everest) from 2012 to 2014 to investigate their concentration, composition, sources, and chemical reactivity. Weekly integrated samples were collected and analyzed using a Gas Chromatograph-Mass Spectrometer/Flame Ionization Detector (GC-MS/FID) system. The total VOC mixing ratios exhibited site-dependent variability, with the highest levels observed in Nyingchi, followed by Mount Everest, Ngari and Namtso. The VOC composition in those remote sites was dominated by alkanes (25.7–48.5%) and aromatics (11.4–34.7%), followed by halocarbons (19.1–28.1%) and alkenes (11.5–18.5%). A distinct seasonal trend was observed, with higher VOC concentrations in summer and lower levels in spring and autumn. Source analysis based on correlations between specific VOC species suggests that combustion emissions (e.g., biomass burning or residential heating) were a major contributor during winter and spring, while traffic-related emissions influenced summer VOC levels. In addition, long-range transport of pollutants from South Asia also significantly impacted VOC concentrations across the plateau. Furthermore, reactivity assessments indicated that alkenes were the dominant contributors to OH radical loss rates, whereas aromatics were the largest drivers of ozone formation potential (OFP). These findings highlight the complex interplay of local emissions and regional transport in shaping VOC chemistry in this high-altitude background environment, with implications for atmospheric oxidation capacity and secondary pollutant formation. Full article