Search Results (2,379)

Accurate measurement of ocean wave parameters is paramount for offshore engineering design and marine environmental monitoring. Distributed pressure sensing technology provides a robust data foundation for analyzing the spatio-temporal characteristics of wave fields through synchronized observations at multiple stations. However, multi-sensor data exhibit high-dimensional spatio-temporal coupling, posing significant challenges for traditional single-point signal processing methods in capturing the topological associations between measurement sites. To address these limitations, this study develops a framework for spatio-temporal feature modeling and wave height reconstruction based on Graph Neural Networks (GNNs). The proposed framework integrates the spatial configuration of sensor arrays with graph-theoretic topological representations. By fusing geometric distances and signal correlations, an adaptive adjacency matrix is constructed to establish a dynamically adjustable graph structure. On the feature extraction level, a spatio-temporal fusion method combining multi-scale graph convolutions and gated temporal modeling is proposed. The experimental results obtained on the Blancs Sablons Bay multi-sensor dataset demonstrate that the proposed method significantly outperforms traditional approaches, achieving lower prediction errors and validating the effectiveness of graph-structured modeling in distributed wave sensing. Full article

Permanent magnet synchronous motors (PMSMs) have been widely used in new-energy vehicles and industrial servo systems. However, demagnetization faults (DMFs) can lead to severe issues, including torque ripple and magnetic field distortion. This paper proposes an intelligent diagnostic approach for DMFs based on stator tooth flux (STF). A mathematical model of STF is formulated, and the magnetic flux change is measured using multiple sets of anti-series-connected detection coils (DCs). By combining finite element simulation with signal processing technology, we establish a comprehensive diagnostic system covering fault feature extraction, fault location identification, and severity assessment is established. The proposed method employs wavelet transform (WT) to extract time-frequency features of voltage signals and combines it with a convolutional neural network (CNN) to form the WT-CNN intelligent diagnosis model. Based on the extracted voltage signal features, the method achieves intelligent identification and visual localization of DMFs. Simulation results show that the proposed method achieves an accuracy above 80% for fault location identification (defined as sample-level multi-label classification accuracy across 12 PMs) and above 85% for demagnetization severity estimation (defined as classification accuracy across 9 severity degrees from 10% to 90%). These results provide an effective technical foundation for motor condition monitoring and fault early warning in simulation environments. Full article

Iris biometric systems are recognized as secure alternatives to conventional authentication methods, yet challenges such as variable illumination, noise, and intricate iris textures persist. To address these issues, our study presents a novel hybrid iris recognition framework that integrates advanced deep learning with a pioneering application of Multivariate Ensemble Empirical Mode Decomposition (MEEMD) for feature extraction—a method not previously applied in this context. Our framework first employs MEEMD to extract statistical features that capture the iris’s nonlinear and nonstationary variations. We then combine global semantic information from two pretrained convolutional neural networks—VGG16 and ResNet-152—with local micro-texture details encoded by Local Binary Patterns (LBP) to form a comprehensive feature representation. An efficient pre-processing and segmentation stage precisely isolates the iris region, and the resulting features are refined through dimensionality reduction techniques to yield a robust, compact representation. These features are subsequently classified using multiple models, each rigorously tuned via hyperparameter optimization. Experimental validation on benchmark datasets—including IITD, CASIA, and UBIRIS.v2—shows that our model achieves recognition rates of up to 98% on IITD, 97% on CASIA, and 97.30% on UBIRIS.v2, surpassing existing approaches. This work not only enhances iris recognition performance but also establishes a novel method that bridges advanced deep learning with innovative feature extraction for high-security applications. Full article

In this paper we present a hybrid convolutional neural network–hidden Markov model framework for detecting solar flare events of intensity greater than or equal to M1.0 from very low frequency signals via their induced sudden ionospheric disturbances. The convolutional neural network processes fixed-length windows of raw very low frequency signals and their temporal derivatives to produce probabilistic flare estimates, which serve as emission probabilities for a two-state hidden Markov model. Viterbi decoding enforces temporal consistency, suppressing spurious fluctuations and yielding physically plausible event sequences. The approach is specifically designed to detect the onset-to-peak interval of flare events and, with further development, could operate in real time for early flare warning. The model was trained and evaluated on very low frequency data from the DHO38 transmitter in Germany to a receiver near Birr, Ireland. Sample-level evaluation achieved a balanced accuracy of 0.819 and a Matthews correlation coefficient of 0.529, while event-level detection reached a peak F1-score of 0.558 for moderate-to-strong flares of intensity greater than or equal to C6.0. These results demonstrate automated, physically consistent detection of solar flares based on sudden ionospheric disturbances, indicating the potential of the proposed approach, when combined across multiple receivers, to act as a low-cost complement to satellite-based monitoring. Full article

The Babylonian numeral system, developed more than four thousand years ago, is one of the earliest known positional number systems, employing a sexagesimal (base-60) structure and a limited set of wedge-shaped symbols. Despite their visual simplicity, Babylonian numerals exhibit substantial structural and positional complexity, particularly when multiple symbols are combined to represent larger numerical values. This complexity presents significant challenges for modern computational recognition, especially in handwritten and degraded archaeological contexts. Most existing research has focused on the recognition of isolated Babylonian numeral symbols, which does not adequately reflect real inscriptions where numerals typically appear as composite sequences. To address this limitation, this paper proposes a hybrid deep learning framework capable of identifying, interpreting, and computing the decimal values of multi-symbol handwritten Babylonian numerals. Building on prior work in single-symbol recognition, we construct a synthetic yet realistic dataset of composite numeral images by combining handwritten glyphs into sequences of two to four symbols while incorporating natural variations in spacing, alignment, and handwriting style. The proposed framework integrates a Convolutional Neural Network (CNN) for visual feature extraction with optional structural feature fusion, followed by a Support Vector Machine (SVM) classifier for reliable multi-class discrimination. A rule-based positional decoder is then applied to convert recognized symbol sequences into their corresponding decimal values using Babylonian base-60 logic. By combining visual recognition with positional numerical reasoning, the proposed system enables end-to-end interpretation of handwritten Babylonian numeral sequences. To the best of our knowledge, this work represents one of the first approaches to jointly classify, decode, and compute numerical values from multi-symbol handwritten Babylonian numerals, contributing to digital epigraphy, archaeological text analysis, and cultural heritage preservation. Full article

Accurate photovoltaic (PV) power forecasting is essential for the efficient operation of residential energy systems and microgrids, as reliable short-term predictions enable improved energy scheduling, demand management, and operational planning in distributed energy environments. In this study, one-hour-ahead forecasting of residential PV power generation is investigated using real-world data collected from multiple households within an Irish energy community. Several deep-learning architectures, including long short-term memory (LSTM), gated recurrent unit (GRU), convolutional neural networks (CNN), CNN–LSTM hybrid networks, and attention-based LSTM models, are evaluated and compared with a seasonal autoregressive integrated moving average (SARIMA) statistical model. A sliding-window approach is employed to transform the PV time series into a supervised learning problem. To ensure statistical robustness, deep-learning models are evaluated using a multi-run framework, and results are reported as mean ± standard deviation based on MAE, RMSE, MAPE, and R² metrics across multiple households. The results indicate that deep-learning models achieve consistently strong forecasting performance, with GRU frequently providing the most reliable predictions across several households. For instance, in House 5, GRU achieved an RMSE of 142.02 ± 1.87 W and an R² of 0.694 ± 0.008, while in Houses 11 and 13 it attained R² values of 0.837 ± 0.002 and 0.835 0.08, respectively. However, performance varied across households, reflecting the influence of data variability and generation patterns on model effectiveness. In comparison, the SARIMA model demonstrated competitive performance and, in certain cases, outperformed deep-learning models. For example, in House 4, it achieved the lowest RMSE of 90.68 W and the highest R² of 0.709. Overall, these findings highlight that while deep-learning models offer greater adaptability and stability, statistical models remain effective for more regular PV generation patterns. Consequently, the study emphasizes the importance of evaluating forecasting models under realistic household-level conditions and demonstrates that both deep-learning and statistical approaches can provide short-term PV forecasting. Full article

The widespread dissemination of fake news across different domains exerts a negative impact on social order. Current fake news detection models face two major challenges. First, the issue of domain shift constrains the generalization capability of models in cross-domain scenarios. Second, general neural networks struggle to extract features between distant words in text, resulting in poor quality of original features and adversely affecting the final detection outcomes. In response to the aforementioned issues, this paper proposes a multi-domain fake news detection framework based on multi-view hybrid attention enhancement. Firstly, superior original feature extraction is achieved through Recurrent Convolutional Neural Networks (RCNN) and Bidirectional Long Short-Term Memory (BiLSTM). Secondly, a hybrid attention mechanism is established between features and domains across multiple views—including news semantics, sentiment, and style—thereby forming domain-specific memory. This enables the model to achieve more precise classification of news within specific, subdivided domains. Finally, experiments conducted on the public dataset Weibo21 demonstrate that the proposed method attains F1 scores of 93.26% and 85.31% on Chinese and English datasets. Full article

Conventional multispectral photodetectors typically rely on multiple electrical terminals to discriminate different wavelengths, which inevitably increases structural complexity. Here, we break this paradigm by demonstrating a dual-color visible–infrared photodetector based on a simple two-terminal Au/MoS₂/Te heterostructure. The device operates through a bias-switching mechanism: reversing the voltage polarity selectively activates either the MoS₂/Au Schottky junction for visible-light detection (520 nm) or the Te/MoS₂ heterojunction for infrared detection (1550 nm). This bias-controlled wavelength selectivity is unambiguously verified by scanning photocurrent mapping. Beyond dual-color discrimination, an adaptive convolutional neural network is employed to decode the nonlinear current–voltage characteristics and enable precise spectral identification, achieving a reconstruction error of approximately 4.5%. Furthermore, high-fidelity dual-color imaging is demonstrated at room temperature. These results establish a hardware–algorithm co-design strategy based on a minimalist two-terminal architecture, providing a viable route toward compact and intelligent spectral-sensing systems. Full article

With increasing port automation and operational intensity, the gearboxes of gantry cranes widely used in bulk cargo terminals are prone to bearing and gear failures under prolonged heavy loads, intense vibrations, and complex operating conditions. Since fault samples often exhibit imbalanced distributions, this imposes two higher requirements on diagnostic methods—first, the ability to effectively address sample imbalance and, second, the capability to simultaneously identify multiple fault categories. To address these challenges, this paper proposes a joint diagnostic method integrating an improved Conditional Wasserstein Generative Adversarial Network with Gradient Penalty (CWGAN-GP) and Multi-Task Learning (MTL). First, the modified CWGAN-GP performs conditional augmentation for minority fault classes, evaluating synthetic sample authenticity and diversity through multiple metrics. Subsequently, a multi-channel diagnostic network is constructed, in which vibration signals are fed into two parallel sub-networks: time–frequency features are extracted from the Short-Time Fourier Transform (STFT)-based time–frequency representations via a residual-block Convolutional Neural Network (CNN), while temporal features are captured from the raw time-domain signal using a Bidirectional Long Short-Term Memory (Bi-LSTM) with an attention mechanism. An attention fusion layer then integrates these two feature types, enabling joint classification of bearings and gears within a multi-task learning framework. Experimental validation on public gearbox datasets and port gantry crane gearbox datasets demonstrates that this method achieves an average diagnostic accuracy exceeding 97%. The proposed method reduces the impact of class imbalance, thereby improving the accuracy and stability of multi-task fault identification. Full article

Every year, floods disrupt the lives of hundreds of millions of people worldwide. Their impacts are further intensified by climate change, rapid urbanization, and land-use changes, making it crucial to identify areas most susceptible to flooding. While machine learning (ML) models have proven effective in identifying flood susceptibility, their validity and the integration of human risk remain underexplored in geomorphologically complex and highly flood-prone regions. This study developed an ensemble ML framework for flood susceptibility mapping in the Kosi Megafan, located in Nepal and India. We compared its performance with established ML models and a one-dimensional convolutional neural network (1D-CNN), validated results using Dartmouth Flood Observatory (DFO) and Sentinel-1 SAR (Synthetic Aperture Radar) data, and assessed the population exposed to high-risk zones. A total of 13 (8 retained) flood conditioning factors (FCFs) were derived from remote sensing datasets, and a flood inventory was created to train multiple ML models, including Random Forest (RF), Extreme Gradient Boosting (XGBoost), Adaptive Boosting (AdaBoost), Support Vector Machine (SVM), 1D-CNN, and a Stacked Ensemble model. Among these, the stacked ensemble model achieved the highest performance (AUC = 0.76, accuracy = 0.70, precision = 0.69, recall = 0.72, F1-score = 0.70). The resulting susceptibility map identified high-risk zones mainly in the southern and southwestern Megafan, showing strong spatial agreement with the Sentinel-1-derived flood inventory and the DFO flood data (1992–2022). This study highlights the effectiveness of combining SAR-derived flood evidence with ensemble ML approaches for accurate and scalable flood susceptibility mapping in data-scarce, hazard-prone basins. Ultimately, the research supports efforts to build resilience and mitigate the long-term impact of flooding in the region. Full article

Food insecurity occurs due to the impact of climate change and intense global conditions. Thus, understanding crop farming plans and monitoring crop yields have become major tasks for decision makers. Previous work has applied remote sensing techniques and empirical methods to predict the yields and analyse the relationships between spectral indices and historical crop yield data. However, a limitation of these studies is that they do not extract the values of spectral indices by crop types when the testing area is regional with multiple farmlands and requires a crop classification process. This can cause inaccurate results when investigating the correlations between the yield and the spectral indices. This research develops a yield prediction framework with historical crop maps by means of unsupervised classification with zero ground truth using Sentinel-2 imagery to retrieve the values of spectral indices of winter barley. The extracted spectral indices and the meteorological and historical yield data in North Norfolk, UK, are implemented in 1D Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM) and CNN–LSTM for winter barley yield predictions. LSTM has outstanding performance overall and the best result approaches a Root Mean Square Error (RMSE) of 0.406 kg/hectare, a Mean Square Error (MSE) of 0.165 kg/hectare and a Mean Absolute Error (MAE) of 10.495 kg/hectare. The EVI in April, May and June is the most important feature in the LSTM model and shows strong positive correlation with the yield of winter barley. The developed framework with unsupervised crop classification and LSTM can be applied to multiple crop types and in different regions using opensource datasets, historical yields, spectral indices and meteorological data. Correlations between these datasets indicate that higher EVI and maximum and minimum temperature and sun hours at the germination and seedling growth stages increase the yields of winter barley, but excess Water Content (WC) in plants with a higher Normalised Difference Moisture Index (NDMI) from April to June leads to a decline in the yields of winter barley. Full article

Accurate prediction of the Remaining Useful Life (RUL) of lithium-ion batteries is essential for improving the reliability, safety, and maintenance planning of electric vehicles and energy storage systems. However, battery degradation is a complex and nonlinear process influenced by multiple operational conditions, making reliable RUL estimation a challenging task. Although numerous data-driven approaches have been proposed in the literature, many studies focus primarily on improving prediction accuracy using a single modeling technique, while limited attention has been given to systematic comparisons of different algorithms and the quantification of prediction uncertainty. This study proposes a comprehensive data-driven framework for lithium-ion battery RUL prediction by integrating both traditional machine learning and deep learning approaches. A Convolutional Neural Network (CNN) model is developed to capture nonlinear degradation patterns from battery cycling data. The dataset was divided using a battery-wise validation strategy to evaluate model generalization. In addition, conventional machine learning algorithms, including k-Nearest Neighbors (KNNs), Random Forest (RF), and Extreme Gradient Boosting (XGBoost), are implemented to perform a comparative analysis of different predictive models. Key degradation-related features derived from voltage, current, temperature, and cycle information are extracted through a structured preprocessing pipeline. Furthermore, prediction uncertainty is quantified by constructing confidence intervals around the estimated RUL values. The predictive performance of the models is evaluated using prognostic metrics such as Root Mean Square Error (RMSE), Relative Prediction Error (RPE), and Prognostic Horizon (PH). The performance of the models is evaluated using multiple prognostic metrics, including Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and the coefficient of determination (R²), to ensure a comprehensive assessment of prediction accuracy. The experimental results demonstrate that the proposed framework provides accurate RUL predictions. Among the evaluated models, the CNN achieved the best performance with a Mean Absolute Error (MAE) of 7.75 and a Root Mean Square Error (RMSE) of 10.80, outperforming traditional machine learning models such as Random Forest and XGBoost. The KNN model also showed competitive performance with an RMSE of 12.07 and an R² value of 0.64, indicating that similarity-based learning can effectively capture battery degradation patterns. Full article

This article introduces an intelligent framework using deep learning to recognize and classify different faults through the real-time detection of multiple faults in power distribution systems. A collection of data representing normal operating conditions, alongside various fault scenarios including line-to-ground (LG), line-to-line (LL), double line-to-ground (LLG), and three-phase line (LLL) faults, was created using three phase current signals obtained from the Real-Time Digital Simulator (RTDS) microgrid test system. To properly model the system dynamics, a feature extraction method that integrates phase currents, differential currents, summation currents and magnitude results was developed. The temporal features of the fault signals were identified by using a sliding window approach to fit the data. A one-dimensional convolutional neural network (CNN) was developed to identify different types of faults. This model performed well, obtaining nearly 96.15% accuracy while testing. In order to evaluate the feasibility of the approach, the trained model was loaded on Raspberry Pi 5, NodeMCU, ESP32 and existing sensing devices. The fault classification performed in real-time was time-sensitive. The proposed intelligent framework is applicable to low-scale operation for smart grid fault monitoring and protection and it is an economically viable solution. Full article

The reliability of high-frequency (HF) frequency selection technology relies on the prediction accuracy of the Maximum Usable Frequency of the ionospheric F2 layer (MUF-F2). To improve its short-term prediction performance, a novel hybrid deep learning prediction model is proposed, which achieves accurate modeling of the complex spatiotemporal variation patterns of MUF-F2 by integrating a feature enhancement mechanism, a dual-branch feature extraction structure, and a bidirectional temporal dependency capture network. The hybrid prediction model integrates the Channel Attention mechanism (CA), Dual-Branch Convolutional Neural Network (DCNN), and Bidirectional Long Short-Term Memory network (BiLSTM). The model is trained and validated using MUF-F2 data from 5 communication links over China during geomagnetically quiet periods and 4 during geomagnetic storm periods, with the difference in the number of links attributed to experimental constraints and the disruptive effects of geomagnetic storms. Its performance is evaluated via multiple metrics, and a comparative analysis is conducted with commonly used prediction models such as the Long Short-Term Memory (LSTM) network. Experimental results show that during geomagnetically quiet periods, the proposed model achieves lower prediction errors (Root Mean Square Error (RMSE) < 1.1 MHz, Mean Absolute Percentage Error (MAPE) < 3.8%) and a higher goodness of fit (coefficient of determination (R²) > 0.94), with the average error reduction across all links ranging 8 from 6.2% to 46.9% compared with the baseline model. Under geomagnetic storm disturbance conditions, the model still maintains robust prediction performance, with R² > 0.89 for all communication links, as well as RMSE < 0.6 MHz, Mean Absolute Error (MAE) < 0.4 MHz, and MAPE < 3.3%. The study demonstrates that the proposed CA-DCNN-BiLSTM model exhibits excellent prediction accuracy and anti-interference capability under different geomagnetic activity conditions, which can effectively improve the short-term prediction accuracy of MUF-F2 and provide more reliable technical support for HF communication frequency decision-making. Full article

Deep learning has emerged as an effective tool for automatic waste classification, supporting cleaner cities and more sustainable recycling systems. Because environmental protection is central to the United Nations Sustainable Development Goals (SDGs), improving the sorting and processing of everyday waste is a practical step toward this broader objective. In many real-world settings, however, waste is still sorted manually, which is slow, labor-intensive, and prone to human error. Although convolutional neural networks (CNNs) can automate this task with high accuracy, many state-of-the-art models remain too large and computationally demanding for low-cost edge devices intended for deployment in homes, schools, and small recycling facilities. In this work, we investigate lightweight waste-classification models suitable for TinyML deployment while preserving competitive accuracy. We first benchmark multiple CNN architectures to establish a strong baseline, then apply complementary compression strategies including quantization, pruning, singular value decomposition (SVD) low-rank approximation, and knowledge distillation. In addition, we evaluate an RL-guided multi-teacher selection benchmark that adaptively chooses one teacher per minibatch during distillation to improve student training stability, achieving up to 85% accuracy with only 0.496 M parameters (FP32 ≈ 1.89 MB; INT8 ≈ 0.47 MB). Across all experiments, the best accuracy–size trade-off is obtained by combining knowledge distillation with post-training quantization, reducing the model footprint from approximately 16 MB to 281 KB while maintaining 82% accuracy. The resulting model is feasible for deployment on mobile applications and resource-constrained embedded devices based on model size and TensorFlow Lite Micro compatibility. Full article