Search Results (1,305)

Accurate and stable wind power prediction is essential for effective wind farm capacity management and grid dispatching. Wind power generation is influenced not only by historical data, but also by turbine conditions and external environmental factors, such as weather. Although deep learning has made significant progress in the field of wind power forecasting, it often fails to account for two key characteristics of the data: dynamic variability and heterogeneity. Specifically, the influence of external variables on wind power changes over time, and due to the diverse nature of the information carried by different variables, simple weighted fusion approaches are insufficient to fully integrate heterogeneous data. To address these challenges, this paper introduces a dynamic heterogeneous graph attention recurrent network (DHGAR), which incorporates dynamic graphs, heterogeneous graph attention mechanisms, and gated recurrent units. Dynamic graphs capture real-time associations between wind power and external variables, while heterogeneous graph attention allows for more effective aggregation of diverse information. These two components are integrated into the gated recurrent units, replacing traditional fully connected layers to better capture temporal dependencies in the wind power time series. Experimental results on three real-world datasets demonstrate the superior performance and practical applicability of the proposed model. Full article

To address the challenges of feature extraction and low classification accuracy in fault diagnosis of variable-speed rolling bearings, this paper proposes an intelligent fault diagnosis method based on bandwidth division variational mode decomposition (BDVMD), fractional domain time-shift multiscale fractional Boltzmann-Shannon interaction entropy (FRTSMFrBSIE), and parameter-optimized gated recurrent unit with multi-head self-attention (GRU-MHSA). First, the BDVMD is introduced to decompose and reconstruct signals, obtaining high-quality reconstructed fault signals. Next, the FRTSMFrBSIE is proposed to calculate the entropy of the reconstructed signals and generate a fault feature dataset. Subsequently, the improved dung beetle optimization (IDBO) algorithm is applied to optimize the parameters of the GRU-MHSA model, adaptively determining its optimal configuration. Finally, the fault feature dataset is input into the optimized model for fault classification, achieving a classification accuracy of 98.75%. Experiments conducted on the Ottawa bearing dataset validate the proposed method, and the results demonstrate its effectiveness and superiority in feature extraction and fault classification. Full article

In this paper, we present a low-cost, low-power millimeter-wave (mmWave) skeletal joint localization system. High-quality point cloud data are generated using the self-developed BHYY_MMW6044 59–64 GHz mmWave radar device. A sliding window mechanism is introduced to extend the single-frame point cloud into multi-frame time-series data, enabling the full utilization of temporal information. This is combined with convolutional neural networks (CNNs) for spatial feature extraction and a bidirectional gated recurrent unit (BiGRU) for temporal modeling. The proposed spatio-temporal information fusion framework for multi-frame point cloud data fully exploits spatio-temporal features, effectively alleviates the sparsity issue of radar point clouds, and significantly enhances the accuracy and robustness of pose estimation. Experimental results demonstrate that the proposed system accurately detects 25 skeletal joints, particularly improving the positioning accuracy of fine joints, such as the wrist, thumb, and fingertip, highlighting its potential for widespread application in human–computer interaction, intelligent monitoring, and motion analysis. Full article

Accurate deformation prediction is crucial for ensuring the safety and longevity of bridges. However, the complex fluctuations of deformation pose a challenge to achieving this goal. To improve the prediction accuracy, a bridge deformation prediction method based on a bidirectional gated recurrent unit (BiGRU) neural network and error correction is proposed. Firstly, the BiGRU model is employed to predict deformation data, which aims to enhance the modeling capability of the GRU network for time-series data through its bidirectional structure. Then, to extract the valuable information concealed in the error, a transformer model is introduced to rectify the error sequence. Finally, the preliminary and error prediction results are integrated to yield high-precision deformation prediction results. Two deformation datasets collected from an actual bridge health monitoring system are utilized as examples to verify the effectiveness of the proposed method. The results show that the proposed method outperforms the comparison model in terms of prediction accuracy, robustness, and generalization ability, with the predicted deformation results being closer to the actual results. Notably, the error-corrected model exhibits significantly improved evaluation metrics compared to the single model. The research findings herein offer a scientific foundation for bridges’ early safety warning and health monitoring. Additionally, they hold significant relevance for developing time-series prediction models based on deep learning. Full article

Motor impairment is a critical health issue that restricts disabled people from living their lives normally and with comfort. Detecting motor imagery (MI) in electroencephalography (EEG) signals can make their lives easier. There has been a lot of work on detecting two or four different MI movements, which include bilateral, contralateral, and unilateral upper limb movements. However, there is little research on the challenging problem of detecting more than four motor imagery tasks and unilateral lower limb movements. As a solution to this problem, a spectral-spatio-temporal multiscale network (SSTMNet) has been introduced to detect six imagery tasks. It first performs a spectral analysis of an EEG trial and attends to the salient brain waves (rhythms) using an attention mechanism. Then, the temporal dependency across the entire EEG trial is worked out using a temporal dependency block, resulting in spectral-spatio-temporal features, which are passed to a multiscale block to learn multiscale spectral-–spatio-temporal features. Finally, these features are deeply analyzed by a sequential block to extract high-level features, which are used to detect an MI task. In addition, to deal with the small dataset problem for each MI task, the researchers introduce a data augmentation technique based on Fourier transform, which generates new EEG trials from EEG signals belonging to the same class in the frequency domain, with the idea that the coefficients of the same frequencies must be fused, ensuring label-preserving trials. SSTMNet is thoroughly evaluated on a public-domain benchmark dataset; it achieves an accuracy of 77.52% and an F1-score of 56.19%. t-SNE plots, confusion matrices, and ROC curves are presented, which show the effectiveness of SSTMNet. Furthermore, when it is trained on augmented data generated by the proposed data augmentation method, it results in a better performance, which validates the effectiveness of the proposed technique. The results indicate that its performance is comparable with the state-of-the-art methods. An analysis of the features learned by the model reveals that the block architectural design aids the model in distinguishing between multi-imagery tasks. Full article

This paper presents an improved speech enhancement algorithm based on microphone arrays to improve speech enhancement performance in complex settings. The algorithm’s model consists of two key components: the feature extraction module and the speech enhancement module. The feature extraction module processes the speech amplitude spectral features derived from STFT (short-time Fourier transform). It employs parallel GRU-CNN (Gated Recurrent Units and CNN Convolutional Neural Network) structures to capture unique channel information, and skip connections are utilized to enhance the model’s convergence speed. The speech enhancement module focuses on obtaining cross-channel spatial information. By introducing an attention mechanism and applying a global hybrid pooling strategy, it reduces feature loss. This strategy dynamically assigns weights to each channel, emphasizing features that are most beneficial for speech signal restoration. Experimental results on the CHIME3 dataset show that the proposed model effectively suppresses diverse types of noise and outperforms other algorithms in improving speech quality and comprehension. Full article

With the widespread deployment of photovoltaic (PV) power stations, timely identification and rectification of module defects are crucial for extending service life and preserving efficiency. PV arrays, subjected to severe outside circumstances, are prone to defects exacerbated by dust accumulation, potentially leading to complex compound faults. The resemblance between individual and compound faults sometimes leads to misclassification. To address this challenge, this paper presents a novel hybrid deep learning model, ResGRU, which integrates a residual network (ResNet) with bidirectional gated recurrent units (BiGRU) to improve fault diagnostic accuracy. Additionally, a Squeeze-and-Excitation (SE) module is incorporated to enhance relevant features while suppressing irrelevant ones, hence improving performance. To further optimize inter-class separability and intra-class compactness, a center loss function is employed as an auxiliary loss to enhance the model’s discriminative capacity. This proposed method facilitates the automated extraction of fault features from I-V curves and accurate diagnosis of individual faults, partial shading scenarios, and compound faults under varying levels of dust accumulation, hence aiding in the formulation of efficient cleaning schedules. Experimental findings indicate that the suggested model achieves 99.94% accuracy on pristine data and 98.21% accuracy on noisy data, markedly surpassing established techniques such as artificial neural networks (ANN), ResNet, random forests (RF), multi-scale SE-ResNet, and other ResNet-based approaches. Thus, the model offers a reliable solution for accurate PV array fault diagnosis. Full article

This research aims to demonstrate a machine learning (ML) algorithm-based indoor air quality (IAQ) monitoring and forecasting system for a public sector building use case. Such a system has the potential to automate existing heating/ventilation systems, therefore reducing energy consumption. One of Riga Technical University’s campus buildings, equipped with around 128 IAQ sensors, is used as a test bed to create a digital shadow including a comparison of five ML-based data prediction tools. We compare the IAQ data prediction loss using Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) error metrics based on real sensor data. Gated Recurrent Unit (GRU) and Kolmogorov–Arnold Networks (KAN) prove to be the most accurate models regarding the prediction error. Also, GRU proved to be the most efficient model regarding the required computation time. Full article

In response to the typical fault issues encountered during the operation of marine diesel engines, a fault diagnosis method based on a convolutional neural network (CNN), a temporal convolutional network (TCN), and the attention mechanism (ATTENTION) is proposed, referred to as CNN-TCN–ATTENTION. This method successfully addresses the issue of insufficient feature extraction in previous fault diagnosis algorithms. The CNN is employed to capture the local features of diesel engine faults; the TCN is employed to explore the correlations and temporal dependencies in sequential data, further obtaining global features; and the attention mechanism is introduced to assign different weights to the features, ultimately achieving intelligent fault diagnosis for marine diesel engines. The results of the experiments demonstrate that the CNN-TCN–ATTENTION-based model achieves an accuracy of 100%, showing superior performance compared to the individual CNN, TCN, and CNN-TCN methods. Compared with commonly used algorithms such as Transformer, long short-term memory (LSTM), Gated Recurrent Unit (GRU), and Deep Belief Network (DBN), the proposed method demonstrates significantly higher accuracy. Furthermore, the model maintains an accuracy of over 90% in noise environments such as random noise, Gaussian noise, and salt-and-pepper noise, demonstrating strong diagnostic performance, generalization capability, and noise robustness. This provides a theoretical basis for its practical application in the fault diagnosis of marine diesel engines. Full article

Accurate financial time series forecasting is critical for effective decision making in areas such as risk management, portfolio optimization, and trading. Given the complexity and volatility of financial markets, traditional forecasting methods often fail to capture the underlying dynamics. Recent advances in artificial neural network (ANN) forecasting research indicate that ANNs present a valuable alternative to traditional linear methods, such as autoregressive integrated moving average (ARIMA). However, time series are typically influenced by a combination of factors which require to consider both linear and non-linear characteristics. This paper proposes a new hybrid model that integrates ARIMA and ANN models such as long short-term memory and gated recurrent unit neural network to leverage the distinct strengths of both linear and non-linear modeling. Moreover, the goodness of the proposed model is evaluated through a comparative analysis of the ARIMA, ANN and Zhang hybrid model, using three financial datasets (i.e., Unicredit SpA stock price, EUR/USD exchange rate and Bitcoin closing price). Various absolute and relative error metrics, computed to evaluate the performance of models, can support the use of the proposed approach. The Diebold–Mariano (DM) test is also implemented to asses the significance of the obtained differences of the hybrid model with respect to the other competing models. Full article

The proliferation of wearable sensors and mobile devices has fueled advancements in human activity recognition (HAR), with growing importance placed on both accuracy and privacy preservation. In this paper, the author proposes a federated learning framework for HAR, leveraging a hybrid Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) model to enhance feature extraction and classification in decentralized environments. Utilizing three public datasets—UCI-HAR, HARTH, and HAR7+—which contain diverse sensor data collected from free-living activities, the proposed system is designed to address the inherent privacy risks associated with centralized data processing by deploying Federated Averaging for local model training. To optimize recognition accuracy, the author introduces a dual-feature extraction mechanism, combining convolutional blocks for capturing local patterns and a hybrid LSTM-GRU structure to detect complex temporal dependencies. Furthermore, the author integrates an attention mechanism to focus on significant global relationships within the data. The proposed system is evaluated on the three public datasets—UCI-HAR, HARTH, and HAR7+—achieving superior performance compared to recent works in terms of F1-score and recognition accuracy. The results demonstrate that the proposed approach not only provides high classification accuracy but also ensures privacy preservation, making it a scalable and reliable solution for real-world HAR applications in decentralized and privacy-conscious environments. This work showcases the potential of federated learning in transforming human activity recognition, combining advanced feature extraction methodologies and privacy-respecting frameworks to deliver robust, real-time activity classification. Full article

The brain acts as the body’s central command, overseeing diverse functions including thought, memory, speech, movement, and the regulation of various organs. When healthy, the brain functions seamlessly and automatically; however, disruptions can lead to serious conditions such as Alzheimer’s Disease, Brain Cancer, Stroke, and Epilepsy. Epilepsy, a neurological disorder marked by recurrent seizures, results from irregular electrical activity in the brain. These seizures, which can strain both patients and neurologists, are characterized by symptoms like the loss of awareness, unusual behavior, and confusion. This study presents an efficient EEG-based epileptic seizure detection framework utilizing a hybrid Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU) models approach to support automated and accurate diagnosis. Handling imbalanced EEG data, which can otherwise bias model outcomes and reduce predictive accuracy, is a key focus. Experimental results indicate that the proposed framework generally outperforms other Deep Learning and Machine Learning techniques with the highest accuracy at 99.13%. Likewise, an Explainable Artificial Intelligence (XAI) called SHAP (SHapley Additive exPlanations) is utilized to analyze the results and to improve the interpretability of the models from medical decision-making. This framework aligns with the objectives of the Medical Internet of Things (MIoT), advancing smart medical applications and services for effective epileptic seizure detection. Full article

Remote sensing cross-modal text-image retrieval constitutes a pivotal component of multi-modal retrieval in remote sensing, central to which is the process of learning integrated visual and textual representations. Prior research predominantly emphasized the overarching characteristics of remote sensing images, or employed attention mechanisms for meticulous alignment. However, these investigations, to some degree, overlooked the intricacies inherent in the textual descriptions accompanying remote sensing images. In this paper, we introduce a novel cross-modal retrieval model, specifically tailored for remote sensing image-text, leveraging attention correction and filtering mechanisms. The proposed model is architected around four primary components: an image feature extraction module, a text feature extraction module, an attention correction module, and an attention filtering module. Within the image feature extraction module, the Visual Graph Neural Network (VIG) serves as the principal encoder, augmented by a multi-tiered node feature fusion mechanism. This ensures a comprehensive understanding of remote sensing images. For text feature extraction, both the Bidirectional Gated Recurrent Unit (BGRU) and the Graph Attention Network (GAT) are employed as encoders, furnishing the model with an enriched understanding of the associated text. The attention correction segment minimizes potential misalignments in image-text pairings, specifically by modulating attention weightings in cases where there’s a unique correlation between visual area attributes and textual descriptors. Concurrently, the attention filtering segment diminishes the influence of extraneous visual sectors and terms in the image-text matching process, thereby enhancing the precision of cross-modal retrieval. Extensive experimentation carried out on both the RSICD and RSITMD datasets, yielded commendable results, attesting to the superior efficacy of the proposed methodology in the domain of remote sensing cross-modal text-image retrieval. Full article

For the past few decades, brain tumors have had a substantial influence on human life, and pose severe health risks if not treated and diagnosed in the early stages. Brain tumor problems are highly diverse and vary extensively in terms of size, type, and location. This brain tumor diversity makes it challenging to progress an accurate and reliable diagnostic tool. In order to effectively segment and classify the tumor region, still several developments are required to make an accurate diagnosis. Thus, the purpose of this research is to accurately segment and classify brain tumor Magnetic Resonance Images (MRI) to enhance diagnosis. Primarily, the images are collected from BraTS 2019, 2020, and 2021 datasets, which are pre-processed using min–max normalization to eliminate noise. Then, the pre-processed images are given into the segmentation stage, where a Variational Spatial Attention with Graph Convolutional Neural Network (VSA-GCNN) is applied to handle the variations in tumor shape, size, and location. Then, the segmented outputs are processed into feature extraction, where an AlexNet model is used to reduce the dimensionality. Finally, in the classification stage, a Bidirectional Gated Recurrent Unit (Bi-GRU) is employed to classify the brain tumor regions as gliomas and meningiomas. From the results, it is evident that the proposed VSA-GCNN-BiGRU shows superior results on the BraTS 2019 dataset in terms of accuracy (99.98%), sensitivity (99.92%), and specificity (99.91%) when compared with existing models. By considering the BraTS 2020 dataset, the proposed VSA-GCNN-BiGRU shows superior results in terms of Dice similarity coefficient (0.4), sensitivity (97.7%), accuracy (98.2%), and specificity (97.4%). While evaluating with the BraTS 2021 dataset, the proposed VSA-GCNN-BiGRU achieved specificity of 97.6%, Dice similarity of 98.6%, sensitivity of 99.4%, and accuracy of 99.8%. From the overall observation, the proposed VSA-GCNN-BiGRU supports accurate brain tumor segmentation and classification, which provides clinical significance in MRI when compared to existing models. Full article

Electricity price forecasting is of significant practical importance, and improving prediction accuracy has become a key area of focus. Although substantial progress has been made in electricity price forecasting research, the unique characteristics of the electricity market make prices highly sensitive to even minor market changes. This results in prices exhibiting long-term trends while also experiencing sharp fluctuations due to sudden events, often leading to extreme values. Furthermore, most current models are “black-box” models, lacking transparency and interpretability. These unique features make electricity price forecasting particularly complex and challenging. This paper introduces a forecasting framework that incorporates the Seasonal Trend decomposition using Loess (STL), Gated Recurrent Unit (GRU), Light Gradient Boosting Machine (LightGBM), and Shapley Additive Explanations (SHAPs) and applies it to forecasting in the electricity markets of the United States and Australia. The proposed forecasting framework significantly improves prediction accuracy compared to nine other baseline models, especially in terms of RMSE and R² metrics, while also providing clear insights into the factors influencing the forecasts. On the U.S. dataset, the RMSE of this framework is 12.7% lower than that of the second-best model, while, on the Australian dataset, the RMSE of the SLGSEF is 2.58% lower than that of the second-best model. Full article