Advanced Wind Power Forecasting

Heart disease is one of the leading causes of mortality worldwide, emphasizing the need for early and accurate diagnosis. Traditional machine learning (ML) models such as Random Forest (RF) and Support Vector Machines (SVM) have been widely used for heart disease classification. However, these models often lack the ability to extract hierarchical patterns and long-range dependencies present in complex medical data. To address this limitation, we propose a hybrid deep learning framework that integrates XGBoost with Capsule Networks (XGBoost-CapsNet) and Convolutional Neural Networks (CNN) with Transformer Encoders (CNN-TE) to enhance classification performance.The study utilizes a structured dataset containing essential heart disease indicators. Feature selection is performed using XGBoost, which ranks attributes based on importance. The Capsule Network (CapsNet) is then used to preserve spatial relationships and hierarchical dependencies among features. Meanwhile, the CNN-TE model extracts spatial features through convolutional layers and captures long-range dependencies using a Transformer Encoder with multi-head self-attention mechanisms. The models are trained using optimized hyperparameters and evaluated against baseline ML models (Random Forest, SVM, and standalone CNN). Performance metrics such as accuracy, precision, recall, F1-score, and AUC-ROC are used for comparison.Experimental evaluations demonstrate that the proposed hybrid models significantly outperform traditional approaches. The XGBoost-CapsNet model achieves an accuracy of 98.2%, while CNN-TE reaches 97.4%, both surpassing standalone CNN (95.1%), Random Forest (94.2%), and SVM (91.8%). The AUC-ROC scores further validate the robustness of the models, with XGBoost-CapsNet scoring 0.99 and CNN-TE achieving 0.98. The use of feature selection with XGBoost improves interpretability and computational efficiency, while the hybrid deep learning models enable better feature extraction and classification accuracy.

Graph convolutional network – Long short term memory neural network- multi layer perceptron- Gaussian progress regression model: A new deep learning model for predicting ozone concertation

The risk of an impact between a large asteroid and the Earth has been deemed signicant enough to attract the attention of an increasing number of researchers and government ocials. Researchers have provided a large volume of information related to the location and mitigation of Earth-threatening asteroids. Congress directed NASA in 2005, via the George E. Brown, Jr. Near-Earth Object Survey Act, to provide an analysis of some of the alternatives proposed for both nding and mitigating threats. This paper focuses on a mitigation technique that was not included among the alternatives listed in the report, namely the use of a long tether and ballast mass to divert an asteroid. In a previous study, such a tether was modeled as massless and inelastic, and the results showed that a tetherballast system may be a viable method for diverting Earth-threatening asteroids from impacting the Earth. For this study, it was desired to gradually relax this assumption, so models were developed to include mass or elasticity or both. This increased model complexity comes with a price, computational time, which is also discussed. Several key issues are highlighted as the model complexity increases, such as the eect of a tether going slack on maximum tether tension.

Ship dynamic models serve as the foundation for designing ship controllers, trajectory planning, and obstacle avoidance. Support vector regression (SVR) is a commonly used nonparametric modelling method for ship dynamics. Achieving high accuracy SVR models requires a substantial amount of training samples. Additionally, as the number of training samples increases, the computational efficiency for solving the quadratic programming problem (QPP) of SVR decreases. Ship controllers demand dynamic models with both high accuracy and computational efficiency. Therefore, to enhance the prediction accuracy and computational efficiency of SVR, this paper proposes a nonparametric modelling method based on twin SVR (TSVR). TSVR replaces a large QPP with a set of smaller QPPs, significantly enhancing generalizability and computational efficiency. To further improve the predictive accuracy of TSVR, the puma optimizer algorithm is employed to determine the optimal hyperparameters. The performance of the proposed method is validated using a Mariner class vessel. Gaussian white noise is introduced into the modelling data to simulate measurement error. The TSVR model accurately predicts various zigzag and turning circle manoeuvring motions under disturbance conditions, demonstrating its robustness and generalizability. Compared to the SVR model, the TSVR model achieves lower root mean square error and computational time, confirming its superior predictive accuracy and computational efficiency.

Purpose– The purpose of this paper is to develop a consolidated framework for government e-procurement (e-GP) performance measurement based on the importance internal stakeholders attach to performance measures and metrics, providing in-depth understanding of their interest in e-GP performance.Design/methodology/approach– This study is divided into two main phases: internal stakeholder identification and consolidation of performance measures and metrics. The mixed-methods approach follows semi-structured expert interviews with questionnaires collected from 413 internal stakeholders.Findings– Five internal stakeholder groups were identified: management, auditors, financial officers, service users, and service support staff. Eight measures and 44 corresponding metrics were consolidated, and 21 significantly distinct performance metrics were identified from stakeholders’ perceptions. As expected, financial measures were most important to financial officers, while contract management was most important to service support staff.Practical implications– Although e-GP processes can vary by country, this study’s approach to developing an e-GP performance measurement framework is adaptable, offering beneficial guidelines for designing e-GP performance measurement systems.Originality/value– This paper goes beyond the existing literature by magnifying the internal stakeholder roles and perceptions of importance, as reflected in the consolidated e-GP performance measurement framework. The consolidation approach with theoretical references (new public management, transaction cost economics, and institutional theory) yielded comprehensive e-GP-specific performance measures and metrics, providing a rigorous approach to measuring e-GP performance.

With the advancement of sensor technologies such as LiDAR and depth cameras, the significance of three-dimensional point cloud data in autonomous driving and environment sensing continues to increase.Point cloud registration stands as a fundamental task in constructing high-precision environmental models, with particular significance in overlapping regions where the accuracy of feature extraction and matching directly impacts registration quality. Despite advancements in deep learning approaches, existing methods continue to demonstrate limitations in extracting comprehensive features within these overlapping areas. This study introduces an innovative point cloud registration framework that synergistically combines the K-nearest neighbor (KNN) algorithm with a channel attention mechanism (CAM) to significantly enhance feature extraction and matching capabilities in overlapping regions. Additionally, by designing an effectiveness scoring network, the proposed method improves registration accuracy and enhances system robustness in complex scenarios. Comprehensive evaluations on the ModelNet40 dataset reveal that our approach achieves markedly superior performance metrics, demonstrating significantly lower root mean square error (RMSE) and mean absolute error (MAE) compared to established methods including iterative closest point (ICP), Robust & Efficient Point Cloud Registration using PointNet (PointNetLK), Go-ICP, fast global registration (FGR), deep closest point (DCP), self-supervised learning for a partial-to-partial registration (PRNet), and Iterative Distance-Aware Similarity Matrix Convolution (IDAM). This performance advantage is consistently maintained across various challenging conditions, including unseen shapes, novel categories, and noisy environments. Furthermore, additional experiments on the Stanford dataset validate the applicability and robustness of the proposed method for high-precision 3D shape registration tasks.

Introduction: In order to assess how well conventional and hybrid pitch detection techniques perform in speech processing applications, a comparative analysis of the two types of methods is conducted. Method: A proposed hybrid approach, Proposed PEF+CEP, is examined alongside five traditional algorithms, namely Normalized Correlation Function (NCF), Pitch Estimation Filter (PEF), Log- Harmonic Summation (LHS), Summation of Residual Harmonics (SRH) and Cepstrum Pitch Determination (CEP). The effectiveness is evaluated using performance metrics like accuracy, specificity, sensitivity, and Gross Pitch Error (GPE). Results and Discussion: Our findings show that the accuracy and specificity of the traditional methods are impressive; the accuracy and sensitivity of the suggested hybrid method surpass their performance, with an astounding 98.8% accuracy and 99.2% sensitivity. Conclusion: Furthermore, the Proposed PEF+CEP method is a promising solution for accurate and dependable pitch detection in speech processing applications because it strikes a strong balance between computational efficiency and robustness. These results open up new avenues for research in the field of speech processing and demonstrate the potential of hybrid approaches.

Lung diseases are a global health concern that require accurate and efficient automated diagnostic systems, particularly in healthcare facilities with limited resources. This study evaluates the performance and computational efficiency of two lightweight convolutional neural network architectures, namely MobileNetV3-Small and EfficientNetV2-Small, on the multi-label classification task of low-resolution ChestMNIST chest X-ray images. Experiments were conducted across eight testing scenarios with and without light spatial data augmentation. The evaluation encompassed predictive performance using accuracy and Area Under the Curve (AUC-ROC) metrics, as well as computational efficiency based on the number of parameters, FLOPs, model size, training time, and inference time. Results indicated that although both models achieved high accuracy (0.93–0.95), MobileNetV3-Small consistently produced higher and more stable AUC-ROC values compared to EfficientNetV2-Small, while being significantly more computationally efficient. Moreover, the application of light spatial data augmentation on low-resolution datasets such as ChestMNIST did not provide consistent performance improvements and instead increased training costs, indicating the limited effectiveness of simple geometric variations when spatial information in the images is highly constrained. These findings provide insight that, in low-resolution medical image multi-label classification, the suitability of an efficient CNN architecture design has a greater impact on overall performance than increasing model complexity or applying light spatial augmentation.

Introduction As the core equipment in industrial production, rotating machinery bearings play a critical role. However, traditional feature extraction algorithms for vibration signals are susceptible to noise interference and inaccurate in extracting complex features. Meanwhile, traditional fault classification algorithms face challenges such as high dependence on feature quality and insufficient generalization ability. Methods For vibration signal feature extraction, an improved multi-scale divergence entropy method is proposed. It integrates multi-scale sample entropy and divergence entropy to enhance the discrimination of signal features. For fault classification, a regularized extreme learning machine (ELM) model is developed, where regularization constraints are introduced to avoid pathological matrices. Results When using the refined composite multi-scale divergence entropy for feature extraction, setting the scale to 20 minimized the entropy value and achieved the highest classification accuracy of 98.79%. For the regularized ELM model, adopting the Softplus function as the activation function and setting the neuron number to 17 led to the lowest loss rate and the highest average classification accuracy of 93.98% ± 0.94%. Additionally, the model exhibited a relatively short running time of only 400 ms. Discussion The results indicate that the improved multi-scale divergence entropy effectively enhances the robustness and accuracy of feature extraction under noise interference. The regularized ELM model improves both classification accuracy and computational efficiency compared to traditional algorithms. This proposed method not only advances the classification accuracy of rotating machinery faults but also provides new technical support for machine fault prevention work, demonstrating potential for practical industrial applications in fault diagnosis systems.

Owing to the loss of effective information and incomplete feature extraction caused by the convolution and pooling operations in a convolution subsampling network, the accuracy and speed of current speech processing architectures based on the conformer model are influenced because the shallow features of speech signals are not completely extracted. To solve these problems, in this study, we researched a method that used a capsule network to improve the accuracy of feature extraction in a conformer-based model, and then, we proposed a new end-to-end model architecture for speech recognition. First, to improve the accuracy of speech feature extraction, a capsule network with a dynamic routing mechanism was introduced into the conformer model; thus, the structural information in speech was preserved, and it was input to the conformer blocks via sequestered vectors; the learning ability of the conformed-based model was significantly enhanced using dynamic weight updating. Second, a residual network was added to the capsule blocks, thus, the mapping ability of our model was improved and the training difficulty was reduced. Furthermore, the bi-transformer model was adopted in the decoding network to promote the consistency of the hypotheses in different directions through bidirectional modeling. Finally, the effectiveness and robustness of the proposed model were verified against different types of recognition models by performing multiple sets of experiments. The experimental results demonstrated that our speech recognition model achieved a lower word error rate without a language model because of the higher accuracy of speech feature extraction and learning using our model architecture with a capsule network. Furthermore, our model architecture benefited from the advantage of the capsule network and the conformer encoder, and also has potential for other speech-related applications.

The discusser would like to thank the author for presenting an improved nonlinear Muskingum model with a variable exponent parameter and would like to draw attention to some points. The need to consider a variable exponent parameter for a nonlinear Muskingum model has been pointed out by the author. The variable exponent parameter accounts for the nonlinearity of flood wave and clearly produces better model performance than that with the constant exponent parameter. The author found that even a small number of inflow levels result in an improvement in model performance. As mentioned by the author, as the number of inflow levels increase, model performance improves, but the improvement was found to be small beyond five levels in different case studies. The variable exponent parameter proposed by the author accounts for the nonlinearity of flood wave in a disaggregate manner. When five inflow levels are used, the number of model parameters will be seven making it a highly overparameterized model. Additional parameters should not be added to a model unless the increased accuracy justifies the increase in model complexity. Also, model complexity can sometimes lead to an undesirable loss of predictive power. In a regression model, accuracy needs to be balanced against complexity, and slight improvements in accuracy do not compensate for the additional complexity. As it will be shown in this discussion, considering a suitable continuous functional form for exponent parameter of nonlinear Muskingum model results in a substantial improvement in model performance. The proposed general functional form has five parameters and thus will be comparable with the case of five inflow levels proposed by the author. The author and most of the previous researchers have used inaccurate explicit Euler’s method [Tung’s method (Tung 1985)] along with the manipulated discharge equation to get a better fit for observed data. This manipulation [using It−1 rather than It in Eq. (6) of the original paper] is not acceptable from a mathematical viewpoint. All explicit solution methods will produce similar results for small size of the time interval, Δt, but in practice for historical field data, the size of the time interval is fixed and may not be small enough, and thus a suitable solution method with sufficient accuracy should be used. As shown by Vatankhah (2010, 2014), fourth-order Runge-Kutta method is an accurate and suitable solution method among the explicit solution methods for solving the Muskingum model which will be used in this discussion.

Traffic flow prediction is an important function of intelligent transportation systems. Accurate prediction results facilitate traffic management to issue early congestion warnings so that drivers can avoid congested roads, thus directly reducing the average driving time of vehicles, which means less greenhouse gas emissions. However, traffic flow data has complex spatial and temporal correlations, which makes it challenging to predict traffic flow accurately. A Gated Recurrent Graph Convolutional Attention Network (GRGCAN) for traffic flow prediction is proposed to solve this problem. The model consists of three components with the same structure, each of which contains one temporal feature extractor and one spatial feature extractor. The temporal feature extractor first introduces a gated recurrent unit (GRU) and uses the hidden states of the GRU combined with an attention mechanism to adaptively assign weights to each time step. In the spatial feature extractor, a node attention mechanism is constructed to dynamically assigns weights to each sensor node, and it is fused with the graph convolution operation. In addition, a residual connection is introduced into the network to reduce the loss of features in the deep network. Experimental results of 1-h traffic flow prediction on two real-world datasets (PeMSD4 and PeMSD8) show that the mean absolute percentage error (MAPE) of the GRGCAN model is as low as 15.97% and 12.13%, and the prediction accuracy and computational efficiency are better than the baselines.

In today fast-paced society, psychological health issues such as anxiety, depression, and stress have become increasingly prevalent across diverse populations.This paper explores the prediction of anxiety, depression, and stress levels via machine learning algorithms. Five different machine learning algorithms were employed to predict the severity of anxiety, depression, and stress across the sampled population. These algorithms were chosen for their high accuracy, making them particularly well-suited for predicting psychological problems. However, applying these algorithms made it apparent that class imbalances existed in the confusion matrix, necessitating incorporating the F1 score measure. The F1 score proved crucial in identifying the most accurate model among the five applied algorithms, ultimately revealing that the random forest classifier was the most effective in predicting anxiety, depression, and stress levels. Moreover, the specificity parameter was examined, showing that the algorithms exhibited notable sensitivity to negative results. The authors emphasized the trade-off between accuracy and execution time, particularly in the hybrid approach. While the hybrid model combined the strengths of multiple algorithms to achieve higher prediction accuracy for anxiety, depression, and stress levels, it also resulted in longer execution times. This trade-off is a common challenge in machine learning, where increasing model complexity can lead to improved accuracy but at the cost of slower processing speeds. This study contributes to the growing body of research on machine learning in mental health prediction, offering valuable insights into the intricacies of class imbalances and the importance of performance metrics such as the f1 score and specificity. The findings underscore the potential of machine learning algorithms, particularly the random forest classifier, in enhancing our understanding and prediction of psychological health issues in diverse and dynamic populations.

Accurate State of Health (SOH) estimation is critical for ensuring the safe operation of lithium-ion batteries. However, current data-driven approaches face significant challenges: insufficient feature extraction and ambiguous physical meaning compromise prediction accuracy, while initialization sensitivity to noise undermines stability; the inherent nonlinearity and temporal complexity of battery degradation data further lead to slow convergence or susceptibility to local optima. To address these limitations, this study proposes an enhanced CNN-BIGRU model. The model replaces conventional random initialization with a Hiking Optimization Algorithm (HOA) to identify superior initial weights, significantly improving early training stability. Furthermore, it integrates an Attention mechanism to dynamically weight features, strengthening the capture of key degradation characteristics. Rigorous experimental validation, utilizing multi-dimensional features extracted from the NASA dataset, demonstrates the model’s superior convergence speed and prediction accuracy compared to the CNN-BIGRU-Attention benchmark. Compared with other methods, the HOA-CNN-BIRGU-Attention model proposed in this study has a higher prediction accuracy and better robustness under different conditions, and the RMSEs on the NASA dataset are all controlled within 0.01, with R2 kept above 0.91. The RMSEs on the University of Maryland dataset are all below 0.006, with R2 kept above 0.98. Compared with the CNN-BIGRU-ATTENTION baseline model without HOA optimization, the RMSE is reduced by at least 0.15% across different battery groups in the NASA dataset.

The use of MRI-guided radiation therapy (MRIgRT) has shown considerable advantages. However, the acquisition of electron density information still relies on Computed tomography (CT) images. In the context of medical image synthesis, achieving high global and local accuracy, as well as efficient synthetic CT (sCT) generation, remains a key challenge. This study aims to improve the accuracy of sCT image generation from MRI by introducing a novel deep learning model that leverages global context and local detail, with a minimal increase in model complexity. In this study, we propose a novel generative adversarial network based on Mamba block and Residual Constraint (RC) strategy, namely RC-MambaGAN, which achieves a significant improvement in accuracy with only a minimal increase in computation time required for sCT generation. Specifically, we integrate Mamba block into the generator to enhance the model's ability to capture long-range contextual information, while preserving the precision of local features and maintaining the global structure of the image. The RC strategy improves the alignment between sCT and real CT by minimizing residuals. The model was validated on multi-center datasets that included both tumor and pelvic-region data. Furthermore, the dosimetric accuracy of the generated sCT images was evaluated to assess their clinical applicability. RC-MambaGAN achieved high performance with mean absolute error (MAE) of 37.094±8.761 HU, peak signal-to-noise ratio (PSNR) of 28.424±1.145dB, structural similarity index measure (SSIM) of 0.947±0.004, and Mutual Information (MI) of 1.426±0.012. External validation demonstrated that RC-MambaGAN outperformed existing state-of-the-art methods in both image quality and quantitative accuracy, even for structures visible in MRI but not in CT images. The proposed RC-MambaGAN markedly improves the image quality and anatomical accuracy of sCT images derived from MRI, thereby advancing the feasibility of MRI-only radiotherapy workflows.