Search Results (7,673)

This paper focuses on the ship control system and studies the problem of unknown control directions. Considering that the traditional Nussbaum gain method has to consider the complex situation where the gain converges to both positive and negative infinity when proving the stability of a system, a unilateral Nussbaum function is defined in this paper. By constructing this function, the design and proof process of the adaptive Nussbaum gain method are simplified. Taking the ship course–keeping control system as the research object, a course angle tracking controller is designed by combining neural network, robust adaptive, and sliding mode control techniques. A dual-input RBF single-output neural network is used to approximate the uncertain part of the system, and the robust adaptive control is adopted to deal with the unknown disturbance. The simulation results at the end of the article show that when the direction suddenly switches, the overshoot of the system reaches 40%, and the adjustment time is approximately 3 s. However, the system can still adapt to the change of the control direction and maintain stability, indicating that the method proposed in this paper is reasonable and effective. And the proposed method can effectively cope with the problems of the unknown control direction and its jump, keeping the system stable, which has great theoretical and engineering application value. Full article

Nano-modified concrete has attracted wide attention due to its improved mechanical properties. Among them, compressive strength is the most critical indicator. However, testing nano-concrete is costly and complex because it requires control over many factors, such as nanoparticle content and dispersion. Machine learning offers a data-driven way to predict compressive strength more efficiently. It reduces trial-and-error efforts and supports mix design optimization. Currently, machine learning is more adept at handling complicated datasets than experimental and traditional statistical models. In this article, the development of machine learning research in predicting the strength of concrete enhanced by nanoparticles is reviewed. First, we systematically outline a three-phase ML framework encompassing data curation, model development, and validation protocols; next, popular algorithms and their uses in predicting the strength of nano-modified concrete are evaluated, such as Artificial Neural Networks, K-Nearest Neighbor, Random Forest, etc. Ultimately, the article offers a forward-looking perspective on how future machine learning advancements can foster and accelerate the development of nano-modified concrete. Full article

White blood cell (WBC) classification plays a crucial role in hematopathology and clinical diagnostics. However, traditional methods are constrained by limited receptive fields and insufficient utilization of contextual information, which hinders classification performance. To address these limitations, this paper proposes an enhanced WBC classification algorithm, CCE-YOLOv7, which is built upon the YOLOv7 framework. The proposed method introduces four key innovations to enhance detection accuracy and model efficiency: (1) A novel Conv2Former (Convolutional Transformer) backbone was designed to combine the local pattern extraction capability of convolutional neural networks (CNNs) with the global contextual reasoning of transformers, thereby improving the expressiveness of feature representation. (2) The CARAFE (Content-Aware ReAssembly of Features) upsampling operator was adopted to replace conventional interpolation methods, thereby enhancing the spatial resolution and semantic richness of feature maps. (3) An Efficient Multi-scale Attention (EMA) module was introduced to refine multi-scale feature fusion, enabling the model to better focus on spatially relevant features critical for WBC classification. (4) Soft-NMS (Soft Non-Maximum Suppression) was used instead of traditional NMS to better preserve true positives in densely packed or overlapping cell scenarios, thereby reducing false positives and false negatives. Experimental validation was conducted on a WBC image dataset acquired using the Fourier ptychographic microscopy (FPM) system. The proposed CCE-YOLOv7 achieved a detection accuracy of 89.3%, showing a 7.8% improvement over the baseline YOLOv7. Furthermore, CCE-YOLOv7 reduced the number of parameters by 2 million and lowered computational complexity by 5.7 GFLOPs, offering an efficient and lightweight model suitable for real-time clinical applications. To further evaluate model effectiveness, comparative experiments were conducted with YOLOv8 and YOLOv11. CCE-YOLOv7 achieved a 4.1% higher detection accuracy than YOLOv8 while reducing computational cost by 2.4 GFLOPs. Compared with the more advanced YOLOv11, CCE-YOLOv7 maintained competitive accuracy (only 0.6% lower) while using significantly fewer parameters and 4.3 GFLOPs less in computation, highlighting its superior trade-off between accuracy and efficiency. These results demonstrate that CCE-YOLOv7 provides a robust, accurate, and computationally efficient solution for automated WBC classification, with significant clinical applicability. Full article

Air traffic control (ATC) communication is susceptible to speech noise interference, which undermines the quality of civil aviation speech. To resolve this problem, we propose a speech enhancement model, termed DeCGAN, based on the DeConformer generative adversarial network. The model’s generator, the DeConformer module, combining a time frequency channel attention (TFC-SA) module and a deformable convolution-based feedforward neural network (DeConv-FFN), effectively captures both long-range dependencies and local features of speech signals. For this study, the outputs from two branches—the mask decoder and the complex decoder—were amalgamated to produce an enhanced speech signal. An evaluation metric discriminator was then utilized to derive speech quality evaluation scores, and adversarial training was implemented to generate higher-quality speech. Subsequently, experiments were performed to compare DeCGAN with other speech enhancement models on the ATC dataset. The experimental results demonstrate that the proposed model is highly competitive compared to existing models. Specifically, the DeCGAN model achieved a perceptual evaluation of speech quality (PESQ) score of 3.31 and short-time objective intelligibility (STOI) value of 0.96. Full article

Graph neural networks (GNNs) have demonstrated significant potential in the field of computer vision in recent years, particularly in handling non-Euclidean data and capturing complex spatial and semantic relationships. This paper provides a comprehensive review of the latest research on GNNs in computer vision, with a focus on their applications in image processing, video analysis, and multimodal data fusion. First, we briefly introduce common GNN models, such as graph convolutional networks (GCN) and graph attention networks (GAT), and analyze their advantages in image and video data processing. Subsequently, this paper delves into the applications of GNNs in tasks such as object detection, image segmentation, and video action recognition, particularly in capturing inter-region dependencies and spatiotemporal dynamics. Finally, the paper discusses the applications of GNNs in multimodal data fusion tasks such as image–text matching and cross-modal retrieval, and highlights the main challenges faced by GNNs in computer vision, including computational complexity, dynamic graph modeling, heterogeneous graph processing, and interpretability issues. This paper provides a comprehensive understanding of the applications of GNNs in computer vision for both academia and industry and envisions future research directions. Full article

Machine learning models often face challenges in bridge inspections, especially in handling complex surface features and overlapping defects that make accurate classification difficult. These challenges are common for image-based monitoring, which has become increasingly popular for inspecting and assessing the structural condition of reinforced concrete bridges with automated possibilities. Despite advances in defect detection using convolutional neural networks (CNNs), although challenges such as overlapping defects, complex surface textures, and data imbalance remain difficult, full fine-tuning of deep learning models helps them better adapt to these conditions by updating all the layers for domain-specific learning. The aim of this study is to demonstrate how effective the fine-tuning of several deep learning architectures for bridge damage classification allows for robust performance and the best utilization value of the methods. Six CNN architectures, ResNet-18, ResNet-50, ResNet-101, ResNeXt-50, ResNeXt-101 and EfficientNet-B3, were fine-tuned using the CODEBRIM dataset. Their performance was evaluated using Precision, Recall, F1 Score, Balanced Accuracy and AUC-ROC metrics to ensure a robust evaluation framework. This indicates that the EfficientNet-B3 and ResNeXt-101 models outperformed the other models and achieved the highest classification accuracy in all the error categories. EfficientNet-B3 showed the best-balanced Precision (0.935) and perfect Recall (1.000) in background classification, indicating its ability to distinguish defect-free areas from structural damage. These results highlight the potential of these models to improve automated bridge inspection systems and thus increase accuracy and efficiency in real-world applications, as well as provide guidance for the selection of methods based on whether accuracy or overall consistency is more important for a specific application. Full article

Electric power load forecasting is essential for the efficient operation and strategic planning of utilities. Decisions regarding the electric market, power generation, load management, and infrastructure development all rely on accurate load predictions. This work presents a novel methodology for day-ahead load forecasting. The approach employs a long short-term memory neural network (LSTM NN) trained on representative load and meteorological data from the region. Before training, the load dataset is grouped by its statistical seasonality through K-means clustering analysis. Clustering load demand, along with similar-day data management, enables more focused training of the LSTM network on uniform data subsets, enhancing the model’s ability to capture temporal patterns and reducing the complexity associated with high variability in demand data. A case study using hourly load demand time-series data provided by the Centro Nacional de Control de Energía (CENACE) is analyzed, and the mean absolute percentage error (MAPE) is calculated, showing lower MAPE than traditional methods. This hybrid approach demonstrates the potential of integrating clustering techniques with neural networks and representative meteorological data from the region to achieve more reliable and accurate regional day-ahead load forecasting. Full article

Existing intelligent fault diagnosis methods have been widely developed and proven to be effective in monitoring the operating status of key mechanical components. However, centrifugal fans, as important equipment in energy and manufacturing industries, have been used for a long time in complex and harsh environments such as boiler plants and gas turbines. Therefore, the vibration signals they generate show complex and diverse characteristics, which brings great challenges to the monitoring of centrifugal fan operation status. To solve this problem, this paper proposes a centrifugal fan blade fault diagnosis method based on a modulational depthwise convolution (DWconv)–one-dimensional convolution neural network (MDC-1DCNN). Specifically, firstly, a convolutional modulation module (CMM) with strong local perception and global modeling capability is designed by drawing on the Transformer self-attention mechanism and global context modeling idea. Second, multiple DWconv layers of different sizes are introduced to capture high-frequency shocks and low-frequency fluctuation information of different frequencies and durations in the signal. Next, a DWconv layer of size 11 is embedded in the multilayer perceptron to enhance spatial information representation while saving computational resources. Finally, to verify the effectiveness of the method, this paper simulates and analyzes the actual working state of centrifugal fan blades, constructs a simulation dataset, and builds a centrifugal fan experimental bench to obtain a real dataset. The experimental results show that the MDC-1DCNN framework significantly outperforms the existing methods in both simulation and experimental bench datasets, fully proving its versatility and effectiveness in centrifugal fan blade fault diagnosis. Full article

To solve the problem of insufficient accuracy in tool wear process modeling and Remaining Useful Life (RUL) estimation, this study proposes a two-stage prediction method. Firstly, a linear prediction benchmark model is constructed: Support Vector Regression (SVR) is used to preliminarily model the tool wear process, obtaining initial prediction results and their error distribution. Building on this foundation, an Autoencoder (AE) is introduced to establish a nonlinear mapping relationship for the errors, achieving effective compensation of the SVR prediction results and establishing the SVR–AE prediction model. To further enhance model performance, the Ant Colony Optimization (ACO) algorithm is utilized to optimize three key parameters: the number of training epochs, batch size, and hidden layer dimensions, ultimately establishing the ACO–SVR–AE optimization model. Experimental validation demonstrates that on the PHM2010 dataset, compared to the Support Vector Regression (SVR) and Autoencoder (AE) models, the proposed method achieves average reductions of 26.1% in Mean Squared Error (MSE) and 14.5% in Mean Absolute Error (MAE). Compared to traditional random forest and neural network models, the MSE and MAE show average reductions of 32.3% and 25.3%. By combining linear modeling with nonlinear error compensation, this method provides an integrated optimization approach to prediction tasks in complex industrial scenarios. Full article

Despite their unprecedented success, artificial neural networks suffer extreme opacity and weakness in learning general knowledge from limited experience. Some argue that the key to overcoming those limitations in artificial neural networks is efficiently combining continuity with compositionality principles. While it is unknown how the brain encodes and decodes information in a way that enables both rapid responses and complex processing, there is evidence that the neocortex employs sparse distributed representations for this task. This is an active area of research. This work deals with one of the challenges in this field related to encoding and decoding nested compositional structures, which are essential for representing complex real-world concepts. One of the algorithms in this field is called context-dependent thinning (CDT). A distinguishing feature of CDT relative to other methods is that the CDT-encoded vector remains similar to each component input and combinations of similar inputs. In this work, we propose a novel encoding method termed CPSE, based on CDT ideas. In addition, we propose a novel decoding method termed CPSD, based on triadic memory. The proposed algorithms extend CDT by allowing both encoding and decoding of information, including the composition order. In addition, the proposed algorithms allow to optimize the amount of compute and memory needed to achieve the desired encoding/decoding performance. Full article

Heat exchangers play a crucial role in transferring heat between two mediums, directly impacting energy efficiency, product quality, and operational safety in industrial systems. This study presents a novel approach for fouling resistance estimation using two artificial intelligence models, the cascaded forward network (CFN) and the recurrent neural network (RN), with a minimal set of six input parameters. The proposed models utilize temperature and flow sensor data from heat exchangers to predict fouling resistance. The training process is optimized using the Levenberg–Marquardt (LM) algorithm, ensuring rapid convergence and high accuracy. Model performance is assessed based on mean squared error (MSE), regression values (R), and statistical error analysis. The results demonstrate that both models achieve high accuracy in predicting fouling resistance, with the CFN model outperforming the RN model. The CFN model achieves an MSE of 1.54 × 10⁻⁸, significantly lower than the RN model (MSE = 3.05 × 10⁻⁸), resulting in a 49.5% improvement in accuracy. Additionally, statistical analysis, including error histograms and correlation analysis, further confirms the robustness of the proposed models. Compared to traditional methods, the proposed AI-based models reduce computational complexity while maintaining superior accuracy. This study highlights the potential of AI in predictive maintenance and industrial optimization, paving the way for future enhancements in intelligent fouling estimation systems. Full article

This study compares the effectiveness of three methods—Fréchet Distance, Dynamic Time Warping (DTW), and Convolutional Neural Networks (CNNs)—in detecting similarities and pattern recognition in time series. It proposes a Pattern-Driven Case Generator (PDCG) framework to automate the creation of labeled time series data for training CNN models, addressing the challenge of manual dataset curation. By injecting controlled noise and interpolating diverse shapes (e.g., W/M/nAn/vVv), a PDCG synthesizes realistic training data that enhances model robustness. Experimental results demonstrate that the CNN model, trained with 10,000 PDCG-generated cases, achieves 86–98% accuracy in pattern recognition, outperforming traditional methods (Fréchet and DTW) for complex, misaligned, and variable-length sequences. The PDCG-enhanced CNN’s scalability and adaptability improve with larger datasets, validating the PDCG’s efficacy in bridging simulation and real-world applications. Full article

This systematic review investigates the integration of artificial intelligence (AI) in cost estimation within project management, focusing on its impact on accuracy and efficiency compared to traditional methods. This study synthesizes findings from 39 high-quality articles published between 2016 and 2024, evaluating various machine learning (ML), deep learning (DL), regression, and hybrid models in sectors such as construction, healthcare, manufacturing, and real estate. The results show that AI-powered approaches, particularly artificial neural networks (ANNs)—which constitute 26.33% of the studies—, enhance predictive accuracy and adaptability to complex, dynamic project environments. Key AI techniques, including support vector machines (SVMs) (7.90% of studies), decision trees, and gradient-boosting models, offer substantial improvements in cost prediction and resource optimization. ML models, including ANNs and deep learning models, represent approximately 70% of the reviewed studies, demonstrating a clear trend toward the adoption of advanced AI techniques. On average, deep learning models perform with 85–90% accuracy in cost estimation, making them highly effective for handling complex, nonlinear relationships and large datasets. Machine learning models achieve an average accuracy of 75–80%, providing strong performance, particularly in industries like road construction and healthcare. Regression models typically deliver 70–80% accuracy, being more suitable for simpler cost estimations where the relationships between variables are linear. Hybrid models combine the strengths of different algorithms, achieving 80–90% accuracy on average, and are particularly effective in complex, multi-faceted projects. Overall, deep learning and hybrid models offer the highest accuracy in cost estimation, while machine learning and regression models still provide reliable results for specific applications. Full article

A solid oxide fuel cell (SOFC) is an electrochemical energy conversion device that provides higher thermoelectric efficiency than traditional cogeneration systems. Current research in this field highlights a variety of mathematical models. These models are based on complex physicochemical and electrochemical reactions, enabling accurate simulation and optimal control of fuel cells. However, these models require substantial computational resources, leading to high processing times. White box and gray box models are unable to achieve real-time optimization of control parameters. A potential solution involves using data-driven machine learning (ML) black-box models. This study examines three ML models: artificial neural network (ANN), random forest (RF), and extreme gradient boosting (XGB). The training dataset consisted of experimental results from SOFC laboratory experiments, comprising 32,843 records with 47 control parameters. The study evaluated the effectiveness of input matrix dimensionality reduction using the following feature importance evaluation methods: mean decrease in impurity (MDI), permutation importance (PI), principal component analysis (PCA), and Shapley additive explanations (SHAP). The application of ML models revealed a complex nonlinear relationship between the SOFC output voltage and the control parameters of the system. The default XGB model achieved the optimal balance between accuracy (MSE = 0.9940) and training speed (τ = 0.173 s/it), with performance capabilities that enable real-time enhancement of SOFC thermoelectric characteristics during system operation. Full article

With the intensification of global climate change, the frequent occurrence of typhoon disaster events has become a great challenge to the sustainable development of cities around the world; thus, it is of great significance to carry out the assessment of typhoon-directed economic losses. Typhoon disaster loss assessment faces key challenges, including complex regional environments, scarce historical data, difficulties in multi-source heterogeneous data fusion, and challenges in quantifying assessment uncertainties. Meanwhile, existing studies often overlook the complex relationship between the spatial expansion of urban and rural construction (SEURC) and typhoon disaster losses, particularly their differential manifestations across different regions and disaster intensities. To address these issues, this study proposes CLPFT (Comprehensive Uncertainty Assessment Framework for Typhoon), an innovative assessment framework integrating prototype learning and uncertainty quantification through a UProtoMLP neural network. Results demonstrate three key findings: (1) By introducing prototype learning, a meta-learning approach, to guide model updates, we achieved precise assessments with small training samples, attaining an MAE of 1.02, representing 58.5–76.1% error reduction compared to conventional machine learning algorithms. This reveals that implicitly classifying typhoon disaster loss types through prototype learning can significantly improve assessment accuracy in data-scarce scenarios. (2) By designing a dual-path uncertainty quantification mechanism, we realized high-reliability risk assessment, with 95.45% of actual loss values falling within predicted confidence intervals (theoretical expectation: 95%). This demonstrates that the dual-path uncertainty quantification mechanism can provide statistically credible risk boundaries for disaster prevention decisions, significantly enhancing the practical utility of assessment results. (3) Further investigation through controlling dynamic assessment factors revealed significant regional heterogeneity in the relationship between SEURC and directed economic losses. Furthermore, the study found that when typhoon intensity reaches a critical value, the relationship shifts from negative to positive correlation. This indicates that typhoon disaster loss assessment should consider the interaction between urban resilience and typhoon intensity, providing important implications for disaster prevention and mitigation decisions. This paper provides a more comprehensive and accurate assessment method for evaluating typhoon disaster-directed economic losses and offers a scientific reference for determining the influencing factors of typhoon-directed economic loss assessments. Full article