Search Results (1,835)

This paper introduces an optimized deep neural network (DNN) framework for an efficient gas detection system applicable across various settings. The proposed optimized DNN model addresses key issues in conventional machine learning (ML), including slow computation times, convergence issues, and poor adaptability to new data, which can result in increased prediction errors and reduced reliability. The proposed framework methodology comprises four phases: data collection, pre-processing, offline DNN training optimization, and online model testing and deployment. The training datasets are collected from seven classes of liquid beverages and environmental air samples using integrated gas sensor devices and an edge intelligence environment. The proposed DNN algorithm is trained on high-performance computing systems by fine-tuning multiple hyperparameter optimization techniques, resulting in an optimized DNN. This well-trained DNN model is validated using unseen new testing datasets in high-performance computing systems. Experimental results demonstrate that the optimized DNN can accurately recognize different beverages, achieving an impressive detection accuracy rate of 98.29%. The findings indicate that the proposed system significantly enhances gas identification capabilities and effectively addresses the slow computation and performance issues associated with traditional ML methods. This work highlights the potential of optimized DNNs to provide reliable and efficient contactless detection solutions across various industries, enhancing real-time gas detection applications. Full article

This paper addresses the challenge of degradation prediction in proton-exchange membrane fuel cells (PEMFCs). Traditional methods often struggle to balance accuracy and complexity, particularly under dynamic operational conditions. To overcome these limitations, this study proposes a data-driven approach based on the gated recurrent unit (GRU) neural network, optimized by the grey wolf optimizer (GWO). The integration of the GWO automates the hyperparameter tuning process, enhancing the predictive performance of the GRU network. The proposed GWO-GRU method was validated utilizing actual PEMFC data under dynamic load conditions. The results demonstrate that the GWO-GRU method achieves superior accuracy compared to other standard methods. The method offers a practical solution for online PEMFC degradation prediction, providing stable and accurate forecasting for PEMFC systems in dynamic environments. Full article

Since the beginning of the 21st century, the development of computer networks has been advancing rapidly, and the world has gradually entered a new era of digital connectivity. While enjoying the convenience brought by digitization, people are also facing increasingly serious threats from network security (NS) issues. Due to the significant shortcomings in accuracy and efficiency of traditional Long Short-Term Memory (LSTM) neural networks (NN), different scholars have conducted research on computer NS situation prediction methods to address the aforementioned issues of traditional LSTM based NS situation prediction algorithms. Although these algorithms can improve the accuracy of NS situation prediction to a certain extent, there are still some limitations, such as low computational efficiency, low accuracy, and high model complexity. To address these issues, new methods and techniques have been proposed, such as using NN and machine learning techniques to improve the accuracy and efficiency of prediction models. This article referred to the Bidirectional Gated Recurrent Unit (BiGRU) improved by Gated Recurrent Unit (GRU), and introduced a multi model NS situation prediction algorithm with attention mechanism. In addition, the improved Particle Swarm Optimization (PSO) algorithm can be utilized to optimize hyperparameters and improve the training efficiency of the GRU NN. The experimental results on the UNSW-NB15 dataset show that the algorithm had an average absolute error of 0.0843 in terms of NS prediction accuracy. The RMSE was 0.0932, which was lower than traditional prediction algorithms LSTM and GRU, and significantly improved prediction accuracy. Full article

Accurate load forecasting is crucial to the stable operation of integrated energy systems (IES), which plays a significant role in advancing sustainable development. Addressing the challenge of insufficient prediction accuracy caused by the inherent uncertainty and volatility of load data, this study proposes a multi-energy load forecasting method for IES using an improved VMD-TCN-BiLSTM model. The proposed model consists of optimizing the Variational Mode Decomposition (VMD) parameters through a mathematical model based on minimizing the average permutation entropy (PE). Moreover, load sequences are decomposed into different Intrinsic Mode Functions (IMFs) using VMD, with the optimal number of models determined by the average PE to reduce the non-stationarity of the original sequences. Considering the coupling relationship among electrical, thermal, and cooling loads, the input features of the forecasting model are constructed by combining the IMF set of multi-energy loads with meteorological data and related load information. As a result, a hybrid neural network structure, integrating a Temporal Convolutional Network (TCN) with a Bidirectional Long Short-Term Memory (BiLSTM) network for load prediction is developed. The Sand Cat Swarm Optimization (SCSO) algorithm is employed to obtain the optimal hyper-parameters of the TCN-BiLSTM model. A case analysis is performed using the Arizona State University Tempe campus dataset. The findings demonstrate that the proposed method can outperform six other existing models in terms of Mean Absolute Percentage Error (MAPE) and Coefficient of Determination (R²), verifying its effectiveness and superiority in load forecasting. Full article

In developing countries, vehicle emissions are a major source of atmospheric pollution, worsened by aging vehicle fleets and less stringent emissions regulations. This results in elevated levels of particulate matter, contributing to the degradation of urban air quality and increasing concerns over the broader effects of atmospheric emissions on human health. This study proposes a Hybrid Explainable Boosting Machine (EBM) framework, optimized using the Covariance Matrix Adaptation Evolution Strategy (CMA-ES), to predict vehicle-related PM_2.5 concentrations and analyze contributing factors. Air quality data were collected from Open-Seneca sensors installed along the Nairobi Expressway, alongside meteorological and traffic data. The CMA-ES-tuned EBM model achieved a Mean Absolute Error (MAE) of 2.033 and an R² of 0.843, outperforming other models. A key strength of the EBM is its interpretability, revealing that the location was the most critical factor influencing PM_2.5 concentrations, followed by humidity and temperature. Elevated PM_2.5 levels were observed near the Westlands roundabout, and medium to high humidity correlated with higher PM_2.5 levels. Furthermore, the interaction between humidity and traffic volume played a significant role in determining PM_2.5 concentrations. By combining CMA-ES for hyperparameter optimization and EBM for prediction and interpretation, this study provides both high predictive accuracy and valuable insights into the environmental drivers of urban air pollution, providing practical guidance for air quality management. Full article

Vessel traffic flow forecasting in port waterways is critical to improving safety and efficiency of port navigation. Aiming at the stage characteristics of vessel traffic in port waterways in time sequence, which leads to complexity of data in the prediction process and difficulty in adjusting the model parameters, a convolutional neural network (CNN) based on the optimization of the pelican algorithm (POA) and the combination of bi-directional gated recurrent units (BiGRUs) is proposed as a prediction model, and the POA algorithm is used to search for optimized hyper-parameters, and then the iterative optimization of the optimal parameter combinations is input into the best combination of iteratively found parameters, which is input into the CNN-BiGRU model structure for training and prediction. The results indicate that the POA algorithm has better global search capability and faster convergence than other optimization algorithms in the experiment. Meanwhile, the BiGRU model is introduced and compared with the CNN-BiGRU model prediction; the POA-CNN-BiGRU combined model has higher prediction accuracy and stability; the prediction effect is significantly improved; and it can provide more accurate prediction information and cycle characteristics, which can serve as a reference for the planning of ships’ routes in and out of ports and optimizing the management of ships’ organizations. Full article

Accurately forecasting power consumption is crucial important for efficient energy management. Machine learning (ML) models are often employed for this purpose. However, tuning their hyperparameters is a complex and time-consuming task. The article presents a novel multi-objective (MO) hybrid evolutionary-based approach, GA-SHADE-MO, for tuning ML models aimed at solving the complex problem of forecasting power consumption. The proposed algorithm simultaneously optimizes both hyperparameters and feature sets across six different ML models, ensuring enhanced accuracy and efficiency. The study focuses on predicting household power consumption at hourly and daily levels. The hybrid MO evolutionary algorithm integrates elements of genetic algorithms and self-adapted differential evolution. By incorporating MO optimization, GA-SHADE-MO balances the trade-offs between model complexity (the number of used features) and prediction accuracy, ensuring robust performance across various forecasting scenarios. Experimental numerical results show the superiority of the proposed method compared to traditional tuning techniques, and random search, showcasing significant improvements in predictive accuracy and computational efficiency. The findings suggest that the proposed GA-SHADE-MO approach offers a powerful tool for optimizing ML models in the context of energy consumption forecasting, with potential applications in other domains requiring precise predictive modeling. The study contributes to the advancement of ML optimization techniques, providing a framework that can be adapted and extended for various predictive analytics tasks. Full article

The rapid evolution of deep learning has led to significant achievements in computer vision, primarily driven by complex convolutional neural networks (CNNs). However, the increasing depth and parameter count of these networks often result in overfitting and elevated computational demands. Knowledge distillation (KD) has emerged as a promising technique to address these issues by transferring knowledge from a large, well-trained teacher model to a more compact student model. This paper introduces a novel knowledge distillation method that simplifies the distillation process and narrows the performance gap between teacher and student models without relying on intricate knowledge representations. Our approach leverages a unique teacher network architecture designed to enhance the efficiency and effectiveness of knowledge transfer. Additionally, we introduce a streamlined teacher network architecture that transfers knowledge effectively through a simplified distillation process, enabling the student model to achieve high accuracy with reduced computational demands. Comprehensive experiments conducted on the CIFAR-10 dataset demonstrate that our proposed model achieves superior performance compared to traditional KD methods and established architectures such as ResNet and VGG networks. The proposed method not only maintains high accuracy but also significantly reduces training and validation losses. Key findings highlight the optimal hyperparameter settings (temperature T = 15.0 and smoothing factor α = 0.7), which yield the highest validation accuracy and lowest loss values. This research contributes to the theoretical and practical advancements in knowledge distillation, providing a robust framework for future applications and research in neural network compression and optimization. The simplicity and efficiency of our approach pave the way for more accessible and scalable solutions in deep learning model deployment. Full article

As an important part of traditional Chinese architecture, Fuzhou’s ancient houses have unique cultural and historical value. However, over time, environmental factors such as efflorescence and plant growth have caused surface damage to their gray brick walls, leading to a decline in the quality of the buildings’ structure and even posing a threat to the buildings’ safety. Traditional damage detection methods mainly rely on manual labor, which is inefficient and consumes a lot of human resources. In addition, traditional non-destructive detection methods, such as infrared imaging and laser scanning, often face difficulty in accurately identifying specific types of damage, such as efflorescence and plant growth, on the surface of gray bricks and are easily hampered by diverse surface features. This study uses the YOLOv8 machine learning model for the automated detection of two common types of damage to the gray brick walls of Fuzhou’s ancient houses: efflorescence and plant growth. We establish an efficient gray brick surface damage detection model through dataset collection and annotation, experimental parameter optimization, model evaluation, and analysis. The research results reveal the following. (1) Reasonable hyperparameter settings and model-assisted annotation significantly improve the detection accuracy and stability. (2) The model’s average precision (AP) is improved from 0.30 to 0.90, demonstrating good robustness in detecting complex backgrounds and high-resolution real-life images. The F1 value of the model’s gray brick detection efficiency is improved (classification model performance index) from 0.22 to 0.77. (3) The model’s ability to recognize the damage details of gray bricks under high-resolution conditions is significantly enhanced, demonstrating its ability to cope with complex environments. (4) The simplified data enhancement strategy effectively reduces the feature extraction interference and enhances the model’s adaptability in different environments. Full article

There has been extensive research on the partial differential equations governing the theory of gas flow in coal mines. However, the traditional Proper Orthogonal Decomposition–Radial Basis Function (POD-RBF) reduced-order algorithm requires significant computational resources and is inefficient when calculating high-dimensional data for coal mine gas pressure fields. To achieve the rapid computation of gas extraction pressure fields, this paper proposes a model reduction method based on deep neural networks (DNNs) and convolutional autoencoders (CAEs). The CAE is used to compress and reconstruct full-order numerical solutions for coal mine gas extraction, while the DNN is employed to establish the nonlinear mapping between the physical parameters of gas extraction and the latent space parameters of the reduced-order model. The DNN-CAE model is applied to the reduced-order modeling of gas extraction flow–solid coupling mathematical models in coal mines. A full-order model pressure field numerical dataset for gas extraction was constructed, and optimal hyperparameters for the pressure field reconstruction model and latent space parameter prediction model were determined through hyperparameter testing. The performance of the DNN-CAE model order reduction algorithm was compared to the POD-RBF model order reduction algorithm. The results indicate that the DNN-CAE method has certain advantages over the traditional POD-RBF method in terms of pressure field reconstruction accuracy, overall structure retention, extremum capture, and computational efficiency. Full article

To enhance lychee quality assessment and address inconsistencies in post-harvest pest detection, this study presents a multi-source fusion approach combining hyperspectral imaging, X-ray imaging, and visible/near-infrared (Vis/NIR) spectroscopy. Traditional single-sensor methods are limited in detecting pest damage, particularly in lychees with complex skins, as they often fail to capture both external and internal fruit characteristics. By integrating multiple sensors, our approach overcomes these limitations, offering a more accurate and robust detection system. Significant differences were observed between pest-free and infested lychees. Pest-free lychees exhibited higher hardness, soluble sugars (11% higher in flesh, 7% higher in peel), vitamin C (50% higher in flesh, 2% higher in peel), polyphenols, anthocyanins, and ORAC values (26%, 9%, and 14% higher, respectively). The Vis/NIR data processed with SG+SNV+CARS yielded a partial least squares regression (PLSR) model with an R² of 0.82, an RMSE of 0.18, and accuracy of 89.22%. The hyperspectral model, using SG+MSC+SPA, achieved an R² of 0.69, an RMSE of 0.23, and 81.74% accuracy, while the X-ray method with support vector regression (SVR) reached an R² of 0.69, an RMSE of 0.22, and 76.25% accuracy. Through feature-level fusion, Recursive Feature Elimination with Cross-Validation (RFECV), and dimensionality reduction using PCA, we optimized hyperparameters and developed a Random Forest model. This model achieved 92.39% accuracy in pest detection, outperforming the individual methods by 3.17%, 10.25%, and 16.14%, respectively. The multi-source fusion approach also improved the overall accuracy by 4.79%, highlighting the critical role of sensor fusion in enhancing pest detection and supporting the development of automated non-destructive systems for lychee stem borer detection. Full article

It is often difficult for a structural safety design method based on deterministic analysis to fully and reasonably reflect the randomness of mechanical parameters, while the traditional reliability analysis method has a large calculation cost and low accuracy. In this paper, based on the seepage–stress coupling numerical model, the random variables affecting the reliability of the collaborative bearing of surrounding rock and lining structures are successfully identified. Then, the improved sparrow search algorithm (ISSA) is used to optimize the hyper-parameters of the Kriging surrogate model, in order to improve the computational efficiency and accuracy of the reliability analysis model. Finally, the ISSA-Kriging-MCS model is used to quantitatively evaluate the reliability of the surrounding rock-reinforced concrete lining structure under multiple failure modes, and the sensitivity of each random variable is discussed in depth. The results show that the high-pressure tunnel structure has high safety and reliability. The reliability indexes of each failure mode decrease with the increase in the coefficient of variation (COV) of random variables. In addition, the same random variable also exhibits varying degrees of influence in different failure modes. Full article

Emotion classification is a challenge in affective computing, with applications ranging from human–computer interaction to mental health monitoring. In this study, the classification of emotional states using electroencephalography (EEG) data were investigated. Specifically, the efficacy of the combination of various feature selection methods and hyperparameter tuning of machine learning algorithms for accurate and robust emotion recognition was studied. The following feature selection methods were explored: filter (SelectKBest with analysis of variance (ANOVA) F-test), embedded (least absolute shrinkage and selection operator (LASSO) tuned using Bayesian optimization (BO)), and wrapper (genetic algorithm (GA)) methods. We also executed hyperparameter tuning of machine learning algorithms using BO. The performance of each method was assessed. Two different EEG datasets, EEG Emotion and DEAP Dataset, containing 2548 and 160 features, respectively, were evaluated using random forest (RF), logistic regression, XGBoost, and support vector machine (SVM). For both datasets, the experimented three feature selection methods consistently improved the accuracy of the models. For EEG Emotion dataset, RF with LASSO achieved the best result among all the experimented methods increasing the accuracy from 98.78% to 99.39%. In the DEAP dataset experiment, XGBoost with GA showed the best result, increasing the accuracy by 1.59% and 2.84% for valence and arousal. We also show that these results are superior to those by the previous other methods in the literature. Full article

Reliable prediction of building-level energy demand is crucial for the building managers to optimize and regulate energy consumption. Conventional prediction models omit the uncertainties associated with demand over time; hence, they are mostly inaccurate and unreliable. In this study, a Bayesian neural network (BNN)-based probabilistic prediction model is proposed to tackle this challenge. By quantifying the uncertainty, BNNs provide probabilistic predictions that capture the variations in the energy demand. The proposed model is trained and evaluated on a subset of the building operations dataset of Lawrence Berkeley National Laboratory (LBNL), Berkeley, California, which includes diverse attributes related to climate and key building-performance indicators. We have performed thorough hyperparameter tuning and used fixed-horizon validation to evaluate trained models on various test data to assess generalization ability. To validate the results, quantile random forest (QRF) was used as a benchmark. This study compared BNN with LSTM, showing that BNN outperformed LSTM in uncertainty quantification. Full article

Small datasets are frequent in some scientific fields. Such datasets are usually created due to the difficulty or cost of producing laboratory and experimental data. On the other hand, researchers are interested in using machine learning methods to analyze this scale of data. For this reason, in some cases, low-performance, overfitting models are developed for small-scale data. As a result, it appears necessary to develop methods for dealing with this type of data. In this research, we provide a new and innovative framework for regression problems with a small sample size. The base of our proposed method is the K-nearest neighbors (KNN) algorithm. For feature selection, instance selection, and hyperparameter tuning, we use the bat optimization algorithm (BA). Generative Adversarial Networks (GANs) are employed to generate synthetic data, effectively addressing the challenges associated with data sparsity. Concurrently, Deep Neural Networks (DNNs), as a deep learning approach, are utilized for feature extraction from both synthetic and real datasets. This hybrid framework integrates KNN, DNN, and GAN as foundational components and is optimized in multiple aspects (features, instances, and hyperparameters) using BA. The outcomes exhibit an enhancement of up to 5% in the coefficient of determination ($R^2$ score) using the proposed method compared to the standard KNN method optimized through grid search. Full article