Search

Accurately predicting crop yield is essential for optimizing agricultural practices and ensuring food security. However, existing approaches often struggle to capture the complex interactions between various environmental factors and crop growth, leading to suboptimal predictions. Consequently, identifying the most important feature is vital when leveraging Support Vector Regressor (SVR) for crop yield prediction. In addition, the manual tuning of SVR hyperparameters may not always offer high accuracy. In this paper, we introduce a novel framework for predicting crop yields that address these challenges. Our framework integrates a new hybrid feature selection approach with an optimized SVR model to enhance prediction accuracy efficiently. The proposed framework comprises three phases: preprocessing, hybrid feature selection, and prediction phases. In preprocessing phase, data normalization is conducted, followed by an application of K-means clustering in conjunction with the correlation-based filter (CFS) to generate a reduced dataset. Subsequently, in the hybrid feature selection phase, a novel hybrid FMIG-RFE feature selection approach is proposed. Finally, the prediction phase introduces an improved variant of Crayfish Optimization Algorithm (COA), named ICOA, which is utilized to optimize the hyperparameters of SVR model thereby achieving superior prediction accuracy along with the novel hybrid feature selection approach. Several experiments are conducted to assess and evaluate the performance of the proposed framework. The results demonstrated the superior performance of the proposed framework over state-of-art approaches. Furthermore, experimental findings regarding the ICOA optimization algorithm affirm its efficacy in optimizing the hyperparameters of SVR model, thereby enhancing both prediction accuracy and computational efficiency, surpassing existing algorithms. [ABSTRACT FROM AUTHOR]

The Leaf Area Index (LAI) is a crucial structural parameter linked to the photosynthetic capacity and biomass of crops. While integrating machine learning algorithms with spectral variables has improved LAI estimation over large areas, excessive input parameters can lead to data redundancy and reduced generalizability across different crop species. To address these challenges, we propose a novel framework based on Bayesian-Optimized Random Forest Regression (Bayes-RFR) for enhanced LAI estimation. This framework employs a tree model-based feature selection method to identify critical features, reducing redundancy and improving model interpretability. A Gaussian process serves as a prior model to optimize the hyperparameters of the Random Forest Regression. The field experiments conducted over two years on maize and wheat involved collecting LAI, hyperspectral, multispectral, and RGB data. The results indicate that the tree model-based feature selection outperformed the traditional correlation analysis and Recursive Feature Elimination (RFE). The Bayes-RFR model demonstrated a superior validation accuracy compared to the standard Random Forest Regression and Pso-optimized models, with the R2 values increasing by 27% for the maize hyperspectral data, 12% for the maize multispectral data, and 47% for the wheat hyperspectral data. These findings suggest that the proposed Bayes-RFR framework significantly enhances the stability and predictive capability of LAI estimation across various crop types, offering valuable insights for precision agriculture and crop monitoring. [ABSTRACT FROM AUTHOR]

Forecasting sales trends is a valuable activity for companies of all types and sizes, as it enables more efficient decision making to avoid unnecessary expenses from excess inventory or, conversely, losses due to insufficient inventory to meet demand. In this paper, we designed a personalized cost function to reduce economic losses caused by the excessive acquisition of products or derived from their scarcity when needed. Moreover, we designed an LSTM network integrated with Glorot and Orthogonal initializers and dropout to forecast sales trends in a lumber mill in Tamaulipas, Mexico. To generalize and appropriately forecast the sales of the lumber mill products, we optimized the LSTM network's hyperparameters through a genetic algorithm, which was essential to explore the solution space. We evaluated our proposal in instances obtained from the historical sales of the five main products sold by the lumber mill. According to the results, we concluded that for our case study the proposed function cost and the hyperparameters optimization allowed the LSTM to forecast the direction and trend of the lumber mill's product sales despite the variability of the products. [ABSTRACT FROM AUTHOR]

Predicting survival outcomes in critical accidents has been a focal point in machine learning research. This study addresses several limitations of existing methods, including insufficient management of data imbalance, lack of emphasis on hyperparameter tuning, and proneness to overfitting. Many existing models struggle to generalize effectively on imbalanced datasets or depend on default hyperparameter settings, resulting in biased predictions. By integrating Principal Component Analysis (PCA), hyperparameter optimization, and resampling methods, as well as combining Edited Nearest Neighbors (ENN) with the Synthetic Minority Oversampling Technique (SMOTE), the model significantly improves predictive accuracy and model generalization. An ensemble model combining seven machine learning algorithms—Logistic Regression, Support Vector Machine, KNN, Random Forest, XGBoost, LightGBM, and CatBoost—was applied to predict survival outcomes. Stochastic Weighted Averaging (SWA) was applied to mitigate overfitting and enhance generalization. The accuracy increased from 91.97% to 94.89% after SWA was applied in this specific scenario. The combination of PCA-based dimensionality reduction, hyperparameter tuning, and resampling techniques (ENN + SMOTE) ensured the model handled data imbalance and optimized predictive accuracy. The final model demonstrated excellent performance, with Area Under the Curve (AUC) and Average Precision (AP) values both reaching 0.98, indicating high accuracy and precision. These improvements were validated using the Titanic dataset in a binary classification problem of predicting passenger survival. The results emphasize that ensemble learning, enhanced by SWA, offers a powerful framework for handling imbalanced and complex datasets, providing significant advancements in predictive modeling accuracy. This study provides insights into how machine learning techniques can be effectively combined to solve classification challenges in real-world scenarios. [ABSTRACT FROM AUTHOR]

This study investigates the use of automated machine learning to forecast the demand of electrical loads. A stochastic optimization algorithm minimizes the cost and risk of the traded asset across different markets using a generic framework for trading activities of load portfolios. Assuming an always overbought condition in the Day-Ahead as well as in the Futures Market, the excess energy returns without revenue to the market, and the results are compared with a standard contract in Greece, which stands as the lowest as far as the billing price is concerned. The analysis achieved a mean absolute percentage error (MAPE) of 12.89% as the best fitted model and without using any kind of pre-processing methods. [ABSTRACT FROM AUTHOR]

The objective of this research is to provide a comprehensive analysis of diamond price prediction by evaluating a wide array of 23 machine learning models (ML), including both regression and classification techniques. This study aims to fill a gap in existing literature by applying hyperparameter tuning optimization across various models to enhance prediction accuracy, estimated values and Time execution efficiency, setting a new benchmark in the field. This approach involved a systematic assessment of multiple ML models on their base and tuned performance concerning accuracy, execution time, and predictive value alignment (under, accurate, over). The study utilized advanced hyperparameter tuning techniques to optimize each model's performance, offering a comparative analysis that highlights the effectiveness of different models in predicting diamond prices. This research makes a distinct contribution through its extensive benchmarking of numerous ML models in the context of diamond price prediction, which is unprecedented in the literature. By applying hyperparameter tuning extensively to enhance model performance, its originality is derived from its comprehensive application of hyperparameter tuning to improve model performance by essentially tuning the model, this paper provides a novel contribution to the growing area of predictive analytics. By benchmarking an unprecedented amount of ML models for diamond price prediction and employing hyperparameter tuning, this paper moves the state of the art by noting the remarkable scope for accuracy improvements in tailored ML applications and demonstrates the extreme importance of model selection and optimization. The findings encompass that CatBoost Regressor, XGBoost Regressor still, kept high accuracy scores after tuning process and Random Forest Regressor accelerated much after tuning. Lastly, CatBoost Classifier, LightGBM Classifier existent achieving accuracies and efficiencies on the problem of diamond price classification tasks. Given its holistic nature, this study acknowledges the potential of overfitting in highly tuned models and their reliance on the specific dataset used for training. Future research might explore the generalisability of these techniques to other datasets and further investigate the trade-offs between model complexity and interpretability. The practical implications of this research are significant for stakeholders in the diamond industry such as retailers, appraisers, and investors. By identifying the most effective models for price prediction, we offer actionable insights that can improve decision-making processes, optimize inventory management, and enhance pricing policies. [ABSTRACT FROM AUTHOR]

In response to growing security concerns and the increasing demand for face recognition (FR) technology in various sectors, this research explores the application of deep learning techniques, specifically pre-trained Convolutional Neural Network (CNN) models, in the field of FR. The study harnesses the power of five pre-trained CNN models—DenseNet201, ResNet152V2, MobileNetV2, SeResNeXt, and Xception—for robust feature extraction, followed by SoftMax classification. A novel weighted average ensemble model, meticulously optimized through a grid search technique, is introduced to augment feature extraction and classification efficacy. Emphasizing the significance of robust data pre-processing, encompassing resizing, data augmentation, splitting, and normalization, the research endeavors to fortify the reliability of FR systems. Methodologically, the study systematically investigates hyperparameters across deep learning models, fine-tuning network depth, learning rate, activation functions, and optimization methods. Comprehensive evaluations unfold across diverse datasets to discern the effectiveness of the proposed models. Key contributions of this work encompass the utilization of pre-trained CNN models for feature extraction, extensive evaluation across multiple datasets, the introduction of a weighted average ensemble model, emphasis on robust data pre-processing, systematic hyperparameter tuning, and the utilization of comprehensive evaluation metrics. The results, meticulously analyzed, unveil the superior performance of the proposed method, consistently outshining alternative models across pivotal metrics, including Recall, Precision, F1 Score, Matthews Correlation Coefficient (MCC), and Accuracy. Notably, the proposed method attains an exceptional accuracy of 99.48% on the labeled faces in the wild (LFW) dataset, surpassing erstwhile state-of-the-art benchmarks. This research represents a significant stride in FR technology, furnishing a dependable and accurate solution fortified by empirical substantiation. The proposed method showcases the potential of pre-trained CNN models, ensemble learning, robust data pre-processing, and hyperparameter tuning in augmenting the accuracy and reliability of FR systems, with far-reaching implications for real-world applications. [ABSTRACT FROM AUTHOR]

The stochastic and intermittent nature of solar energy presents the power grid with the challenge of providing a stable, secure, and economical power supply, especially in the case of large-scale penetration. The prerequisite for addressing these challenges is accurate power output estimation from PV systems. In addition, accurate power estimation also ensures the correct sizing of PV systems for investors. In this study, the PV output prediction model has been developed based on ensemble algorithms using two years of real power and meteorological data from grid-connected PV systems. Grid search, random search, and Bayesian optimization were used to determine the optimal hyperparameters for ensemble algorithms. The originality of this study is that (i) the use of hyperparameter optimization for ensemble algorithms in predicting PV performance, (ii) the degradation rate of PV panels by ensemble algorithms using the first two years' data, and (iii) the performance comparison of ensemble algorithms using the hyperparameter optimization technique. The accuracy and precision of the prediction model are determined by the relative root mean square error (RMSE), mean absolute error (MAE), mean bias error (MBE), mean scaled error (MSE), coefficient of determination (R2), mean absolute percentage error (MAPE), and maximum absolute error (MaxAE). To the best of our knowledge, this is one of the first studies to address the optimization of all hyperparameters to find the best parameters for ensemble algorithms and PV panel degradation rates. The results show that the CatBoost algorithm has better performance than the other algorithms used. The performance metrics of the CatBoost algorithm were determined to be 0.9327 R2, 0.047 MSE, 0.0388 MAE, 0.0003 MBE, 0.069 RMSE, 18.7 MAPE, and 0.79 MaxAE. [ABSTRACT FROM AUTHOR]

Buildings are complex assets, characterized by environments and uses that change over time, variable occupancies, and long life cycles. They have high operational costs, mostly due to their energy requirements, and account for 30% to 40% of global greenhouse gas emissions. Consequently, substantial effort has been made to forecast their energy needs, with the scope of optimizing their economic and environmental impact. In this regard, the available literature focuses mainly on short-term modeling through the implementation of sets of physics-based equations (i.e., white-box), functional relationships between input and output variables (i.e., black-box), or a combination of both (i.e., grey-box). On the other hand, more research is required on long-term forecast models with the aim of reducing the energy needs. Within this context, this article presents an original automatic procedure for forecasting the energy needs of buildings in short- and long-term time horizons. This is accomplished by scaling an unknown facility from a similar facility that is already known and by executing a black-box approach based on machine learning algorithms. The proposed method is implemented in real case studies in Italy, predicting the energy needs (i.e., heating, cooling, and electricity) of Sant'Anna Hospital in Ferrara using the historical data of Ca' Foncello Hospital in Treviso. The results show an adjusted coefficient of determination above 0.7 and an average error below 10% for all the energy vectors, demonstrating a feasible forecast performance with a low training set-to-test set ratio. [ABSTRACT FROM AUTHOR]

Solar energy is emerging as an environmentally friendly and sustainable energy source. However, with the widespread use of solar panels, how to manage these panels after their end-of-life becomes an important problem. It is known that heavy metals in solar modules can harm the environment and if not managed properly, it can cause great difficulties in waste management. Therefore, regular inspection, maintenance and waste management of solar modules are of great importance. The main objective of the study is to develop a Convolutional Neural Network (CNN) model to detect and classify failures in solar panels. By utilizing a large-scale IR image dataset obtained from real solar fields, the proposed CNN model is designed to effectively detect and classify various faults in photovoltaic (PV) modules. The dataset consists of 20,000 IR images including 12 different situations that occur under different conditions such as partial shading, short circuit, dust accumulation. The study addresses the issues of low-resolution and low-contrast images, class imbalance, and difficulty in tuning model parameters. The impact of resolving these issues on model performance is examined, with a focus on the effects of image preprocessing techniques like histogram equalization, data augmentation, and oversampling, as well as hyperparameter optimization methods such as Hyperband, Optuna, Successive Halving, and Bayesian Optimization. The results of the study show that the proposed model can predict an anomaly module with an average accuracy of 92% and correctly classify 12 anomaly types with an average accuracy of 82%. [ABSTRACT FROM AUTHOR]

In the rapidly evolving landscape of the Internet of Things (IoT), cybersecurity remains a critical challenge due to the diverse and complex nature of network traffic and the increasing sophistication of cyber threats. This study investigates the application of the Artificial Bee Colony (ABC) algorithm for hyperparameter optimization (HPO) in machine learning classifiers, specifically focusing on Decision Trees, Support Vector Machines (SVM), and K-Nearest Neighbors (KNN) for IoT network traffic analysis and malware detection. Initially, the basic machine learning models demonstrated accuracies ranging from 69.68% to 99.07%, reflecting their limitations in fully adapting to the varied IoT environments. Through the employment of the ABC algorithm for HPO, significant improvements were achieved, with optimized classifiers reaching up to 100% accuracy, precision, recall, and F1-scores in both training and testing stages. These results highlight the profound impact of HPO in refining model decision boundaries, reducing overfitting, and enhancing generalization capabilities, thereby contributing to the development of more robust and adaptive security frameworks for IoT environments. This study further demonstrates the ABC algorithm's generalizability across different IoT networks and threats, positioning it as a valuable tool for advancing cybersecurity in increasingly complex IoT ecosystems. [ABSTRACT FROM AUTHOR]

This study addresses a major cybersecurity challenge by focusing on the detection of Distributed Denial of Service (DDoS) attacks. These attacks pose a major threat to online services by overwhelming targets with traffic from multiple sources. Traditional detection approaches often fail to adapt to changing attack patterns, necessitating advanced machine-learning techniques. This study proposes a fine-tuned Multi- Layer Perceptron (MLP) model to improve DDoS detection accuracy while reducing false positives. This study uses fine-tuning techniques, such as hyperparameter optimization and transfer learning, to build a robust and adaptive detection framework. After extensive experiments with multiple data splits and cross- validation, the fine-tuned MLP model exhibited strong performance metrics with an average accuracy of 98.5%, precision of 98.1%, recall of 97.8%, and F1 score of 97.9%. These findings demonstrate the model's ability to successfully distinguish between benign and malicious traffic, enhancing network security and resilience. By overcoming the limitations of existing detection methods, this study adds new insights to the field of cybersecurity, providing a more precise and efficient approach to DDoS detection. [ABSTRACT FROM AUTHOR]

This study introduces an optimized hybrid deep learning approach that leverages meteorological data to improve short-term wind energy forecasting in desert regions. Over a year, various machine learning and deep learning models have been tested across different wind speed categories, with multiple performance metrics used for evaluation. Hyperparameter optimization for the LSTM and Conv-Dual Attention Long Short-Term Memory (Conv-DA-LSTM) architectures was performed. A comparison of the techniques indicates that the deep learning methods consistently outperform the classical techniques, with Conv-DA-LSTM yielding the best overall performance with a clear margin. This method obtained the lowest error rates (RMSE: 71.866) and the highest level of accuracy (R2: 0.93). The optimization clearly works for higher wind speeds, achieving a remarkable improvement of 22.9%. When we look at the monthly performance, all the months presented at least some level of consistent enhancement (RRMSE reductions from 1.6 to 10.2%). These findings highlight the potential of advanced deep learning techniques in enhancing wind energy forecasting accuracy, particularly in challenging desert environments. The hybrid method developed in this study presents a promising direction for improving renewable energy management. This allows for more efficient resource allocation and improves wind resource predictability. [ABSTRACT FROM AUTHOR]

Accurately predicting carbon dioxide (CO2) emissions is crucial for environmental protection. Currently, there are two main issues with predicting CO2 emissions: (1) existing CO2 emission prediction models mainly rely on Long Short-Term Memory (LSTM) and Gate Recurrent Unit (GRU) models, which can only model unidirectional temporal features, resulting in insufficient accuracy: (2) existing research on CO2 emissions mainly focuses on designing predictive models, without paying attention to model optimization, resulting in models being unable to achieve their optimal performance. To address these issues, this paper proposes a framework for predicting CO2 emissions, called CGAOA-AttBiGRU. In this framework, Attentional-Bidirectional Gate Recurrent Unit (AttBiGRU) is a prediction model that uses BiGRU units to extract bidirectional temporal features from the data, and adopts an attention mechanism to adaptively weight the bidirectional temporal features, thereby improving prediction accuracy. CGAOA is an improved Arithmetic Optimization Algorithm (AOA) used to optimize the five key hyperparameters of the AttBiGRU. We first validated the optimization performance of the improved CGAOA algorithm on 24 benchmark functions. Then, CGAOA was used to optimize AttBiGRU and compared with 12 optimization algorithms. The results indicate that the AttBiGRU optimized by CGAOA has the best predictive performance. [ABSTRACT FROM AUTHOR]

With the increasing popularity of Android smartphones, malware targeting the Android platform is showing explosive growth. Currently, mainstream detection methods use static analysis methods to extract features of the software and apply machine learning algorithms for detection. However, static analysis methods can be less effective when faced with Android malware that employs sophisticated obfuscation techniques such as altering code structure. In order to effectively detect Android malware and improve the detection accuracy, this paper proposes a dynamic detection model for Android malware based on the combination of an Improved Zebra Optimization Algorithm (IZOA) and Light Gradient Boosting Machine (LightGBM) model, called IZOA-LightGBM. By introducing elite opposition-based learning and firefly perturbation strategies, IZOA enhances the convergence speed and search capability of the traditional zebra optimization algorithm. Then, the IZOA is employed to optimize the LightGBM model hyperparameters for the dynamic detection of Android malware multi-classification. The results from experiments indicate that the overall accuracy of the proposed IZOA-LightGBM model on the CICMalDroid-2020, CCCS-CIC-AndMal-2020, and CIC-AAGM-2017 datasets is 99.75%, 98.86%, and 97.95%, respectively, which are higher than the other comparative models. [ABSTRACT FROM AUTHOR]

Launch anomalies occur frequently during the early phase of a program, with many of the anomalies attributed to propulsion systems. Approaches for identifying and mitigating potential propulsion failures can aid development programs and accelerate the resolution of root cause investigations. In reusable systems, anomaly detection methods can be employed to detect latent system health issues that could become problematic as the system ages. Modern launch support relies on human judgement for redline limit generation and visual family data comparison for many operational aspects, which makes it challenging to identify failure modes and to diagnose an anomaly. Additionally, family data comparison is unavailable for the first few launches of a new vehicle. Automated tools to quickly identify system failures of new and reusable systems can bridge these gaps. Physics-based modeling and machine learning (PBMML) offers methods that can improve the reliability of new or reusable launch vehicles by identifying propulsion anomalies or issues before they jeopardize future space missions. PBMML can then be used to inform corrective actions. This paper describes an anomaly data generation module which automates the process of simulating anomalous scenarios in launch vehicle and fluid networks, while a long-term short-term memory network is used to provide real-time anomaly classification on a simplified stage test case. [ABSTRACT FROM AUTHOR]

Cardiovascular diseases, which significantly affect the heart and blood vessels, are one of the leading causes of death worldwide. Early diagnosis and treatment of these diseases, which cause approximately 19.1 million deaths, are essential. Many problems, such as coronary artery disease, blood vessel disease, irregular heartbeat, heart muscle disease, heart valve problems, and congenital heart defects, are included in this disease definition. Today, researchers in the field of cardiovascular disease are using approaches based on diagnosis-oriented machine learning. In this study, feature extraction is performed for the detection of cardiovascular disease, and classification processes are performed with a Support Vector Machine, Naive Bayes, Decision Tree, K-Nearest Neighbor, Bagging Classifier, Random Forest, Gradient Boosting, Logistic Regression, AdaBoost, Linear Discriminant Analysis and Artificial Neural Networks methods. A total of 918 observations from Cleveland, Hungarian Institute of Cardiology, University Hospitals of Switzerland, and Zurich, VA Medical Center were included in the study. Principal Component Analysis, a dimensionality reduction method, was used to reduce the number of features in the dataset. In the experimental findings, feature increase with artificial variables was also performed and used in the classifiers in addition to feature reduction. Support Vector Machines, Decision Trees, Grid Search Cross Validation, and existing various Bagging and Boosting techniques have been used to improve algorithm performance in disease classification. Gaussian Naïve Bayes was the highest-performing algorithm among the compared methods, with 91.0% accuracy on a weighted average basis as a result of a 3.0% improvement. [ABSTRACT FROM AUTHOR]

The prediction of total ionospheric electron content (TEC) is of great significance for space weather monitoring and wireless communication. Recently, deep learning models have become increasingly popular in TEC prediction. However, these deep learning models usually contain a large number of hyperparameters. Finding the optimal hyperparameters (also known as hyperparameter optimization) is currently a great challenge, directly affecting the predictive performance of the deep learning models. The Beluga Whale Optimization (BWO) algorithm is a swarm intelligence optimization algorithm that can be used to optimize hyperparameters of deep learning models. However, it is easy to fall into local minima. This paper analyzed the drawbacks of BWO and proposed an improved BWO algorithm, named FAMBWO (Firefly Assisted Multi-strategy Beluga Whale Optimization). Our proposed FAMBWO was compared with 11 state-of-the-art swarm intelligence optimization algorithms on 30 benchmark functions, and the results showed that our improved algorithm had faster convergence speed and better solutions on almost all benchmark functions. Then we proposed an automated machine learning framework FAMBWO-MA-BiLSTM for TEC prediction, where MA-BiLSTM is for TEC prediction and FAMBWO for hyperparameters optimization. We compared it with grid search, random search, Bayesian optimization algorithm and beluga whale optimization algorithm. Results showed that the MA-BiLSTM model optimized by FAMBWO is significantly better than the MA-BiLSTM model optimized by grid search, random search, Bayesian optimization algorithm, and BWO. [ABSTRACT FROM AUTHOR]

Kriging metamodeling (also called Gaussian Process regression) is a popular approach to predict the output of a function based on few observations. The Kriging method involves length-scale hyperparameters whose optimization is essential to obtain an accurate model and is typically performed using maximum likelihood estimation (MLE). However, for high-dimensional problems, the hyperparameter optimization is problematic and often fails to provide correct values. This is especially true for Kriging-based design optimization where the dimension is often quite high. In this article, we propose a method for building high-dimensional surrogate models which avoids the hyperparameter optimization by combining Kriging sub-models with randomly chosen length-scales. Contrarily to other approaches, it does not rely on dimension reduction techniques and it provides a closed-form expression for the model. We present a recipe to determine a suitable range for the sub-models length-scales. We also compare different approaches to compute the weights in the combination. We show for a high-dimensional test problem and a real-world application that our combination is more accurate than the classical Kriging approach using MLE. [ABSTRACT FROM AUTHOR]

This paper presents a new approach that automates the tuning process in topology optimization of parameters that are traditionally defined by the user. The new method draws inspiration from hyperparameter optimization in machine learning. A new design problem is formulated where the topology optimization hyperparameters are defined as design variables and the problem is solved by surrogate optimization. The new design problem is nested, such that a topology optimization problem is solved as an inner problem. To encourage the identification of high-performing solutions while limiting the computational resource requirements, the outer objective function is defined as the original objective combined with penalization for intermediate densities and deviations from the prescribed material consumption. The contribution is demonstrated on density-based topology optimization with various hyperparameters and objectives, including compliance minimization, compliant mechanism design, and buckling load factor maximization. Consistent performance is observed across all tested examples. For a simple two hyperparameter case, the new framework is shown to reduce amount of times a topology optimization algorithm is executed by 90% without notably sacrificing the objective compared to a rigorous manual grid search. [ABSTRACT FROM AUTHOR]

Diabetes is a prevalent global disease that significantly diminishes the quality of life and can even lead to fatalities due to its complications. Early detection and treatment of diabetes are crucial for mitigating and averting associated risks. This study aims to facilitate the prompt and straightforward diagnosis of individuals at risk of diabetes. To achieve this objective, a dataset for early stage diabetes risk prediction from the University of California Irvine (UCI) database, widely utilized in the literature, was employed. A hybrid deep learning model comprising genetic algorithm, stacked autoencoder, and Softmax classifier was developed for classification on this dataset. The performance of this model, wherein both the model architecture and all hyperparameters were specifically optimized for the given problem, was compared with commonly used methods in the literature. These methods include K-nearest neighbor, decision tree, support vector machine, and convolutional neural network, utilizing tenfold cross-validation. The results obtained with the proposed method surpassed those obtained with other methods, with higher accuracy rates than previous studies utilizing the same dataset. Furthermore, based on the study's findings, a web-based application was developed for early diabetes diagnosis. [ABSTRACT FROM AUTHOR]

With the goal of forecasting streamflow time series with sufficient lead time, we evaluate the efficiency and accuracy of data-based models ranging from relatively simple to complex. Based on this, we systematically explain the model construction and selection process according to lead time, type and amount of data, and optimization method. This analysis involved optimizing the inputs and hyperparameters of four unique data-driven models: Autoregressive Integrated Moving Average (ARIMA), Artificial Neural Network (ANN), Long Short-Term Memory (LSTM), and Transformer (TRANS), which were applied to the Soyang watershed, South Korea. The type and amount of model inputs are determined through a fine-tuning process that samples based on a correlation threshold, correlation to predictand, and autocorrelation to historical data and evaluates the simulated objective function. Hyperparameters are simultaneously optimized using three conventional optimization methods: Bayesian optimization (BO), particle swarm optimization (PSO), and gray wolf optimization (GWO). The experimental results provide insight into the role of input predictors, data preparations (e.g., wavelet transform), hyperparameter optimization, and model structures. From this, we can provide guidelines for model selection. Relatively simple models can be used when the dataset is small or there are few input variables, when only the near future is predicted, or when the selection of optimization methods is limited. However, a more complex model should be selected if the type and amount of data are sufficient, various optimization methods can be applied, or it is necessary to secure more lead time. More parameters, more complex model structures, and more training materials make this possible. [ABSTRACT FROM AUTHOR]

In the deep learning field, Long Short-Term Memory networks (LSTMs) are a type of recurrent neural network (RNN) that use gates to control and retain important information, enabling them to handle long-range dependencies and effectively forecast time series models. Despite their effectiveness, LSTMs can be further optimized for increased accuracy and efficiency. Optimizing these networks involves fine-tuning hyperparameters, which are external parameters determined manually. While this can be done through trial and error, it is more efficiently accomplished using hyperparameter optimization algorithms such as random search, Bayesian optimization, and Hyperband. This paper compares these three algorithms, finding that random search achieved low mean-squared error but raised concerns about reproducibility and consistency, Hyperband excelled in resource efficiency but struggled with optimal configuration, and the Bayesian algorithm offered consistency and a smooth learning process at a higher computational cost and required parameter adjustments. [ABSTRACT FROM AUTHOR]

Precision agriculture uses data gathered from various sources to improve agricultural yields and the effectiveness of crop management techniques like fertiliser application, irrigation management, and pesticide application. Reduced usage of agrochemicals is a key step towards more sustainable agriculture. Weed management robots which can perform tasks like selective sprinkling or mechanical weed elimination, contribute to this objective. A trustworthy crop/weed classification system that can accurately recognise and classify crops and weeds is required for these robots to function. In this paper, we explore various deep learning models for achieving reliable segmentation results in less training time. We classify every pixel of the images into different categories using semantic segmentation models. The models are based on an encoder-decoder architecture, where feature maps are extracted during encoding and spatial information is recovered during decoding. We examine the segmentation output on a beans dataset containing different weeds, which were collected under highly distinct environmental conditions, including cloudy, rainy, dawn, evening, full sun, and shadow. [ABSTRACT FROM AUTHOR]

The global foreign exchange (FX) market represents a critical and sizeable component of our financial system. It is a market where firms and investors engage in both speculative trading and hedging. Over the years, there has been a growing interest in FX modeling and prediction. Recently, machine learning (ML) and deep learning (DL) techniques have shown promising results in enhancing predictive accuracy. Motivated by the growing size of the FX market, as well as advancements in ML, we propose a novel forecasting framework, the MVO-BiGRU model, which integrates variational mode decomposition (VMD), data augmentation, Optuna-optimized hyperparameters, and bidirectional GRU algorithms for monthly FX rate forecasting. The data augmentation in the Prevention module significantly increases the variety of data combinations, effectively reducing overfitting issues, while the Optuna optimization ensures optimal model configuration for enhanced performance. Our study's contributions include the development of the MVO-BiGRU model, as well as the insights gained from its application in FX markets. Our findings demonstrate that the MVO-BiGRU model can successfully avoid overfitting and achieve the highest accuracy in out-of-sample forecasting, while outperforming benchmark models across multiple assessment criteria. These findings offer valuable insights for implementing ML and DL models on low-frequency time series data, where artificial data augmentation can be challenging. [ABSTRACT FROM AUTHOR]

This study explores the impact of hyperparameter optimization on machine learning models for predicting cardiovascular disease using data from an IoST (Internet of Sensing Things) device. Ten distinct machine learning approaches were implemented and systematically evaluated before and after hyperparameter tuning. Significant improvements were observed across various models, with SVM and Neural Networks consistently showing enhanced performance metrics such as F1-Score, recall, and precision. The study underscores the critical role of tailored hyperparameter tuning in optimizing these models, revealing diverse outcomes among algorithms. Decision Trees and Random Forests exhibited stable performance throughout the evaluation. While enhancing accuracy, hyperparameter optimization also led to increased execution time. Visual representations and comprehensive results support the findings, confirming the hypothesis that optimizing parameters can effectively enhance predictive capabilities in cardiovascular disease. This research contributes to advancing the understanding and application of machine learning in healthcare, particularly in improving predictive accuracy for cardiovascular disease management and intervention strategies. [ABSTRACT FROM AUTHOR]

Federated learning (FL) is an attractive paradigm for privacy-aware distributed machine learning, which enables clients to collaboratively learn a global model without sharing clients' data. Recently, many strategies have been proposed to improve the generality of the global model and thus improve FL effect. However, existing strategies either ignore the fairness among clients or sacrifice performance for fairness. They cannot ensure that the gap among clients is as small as possible without sacrificing federated performance. To address this issue, we propose ParetoFed, a new local information aggregation method dedicated to obtaining better federated performance with smaller gap among clients. Specifically, we propose to use multi-objective hyperparameter optimization (HPO) algorithm to gain global models that are both fair and effective. Then, we send Pareto Optimal global models to each client, allowing them to choose the most suitable one as the base to optimize their local model. ParetoFed not only make the global models more fair but also make the selection of local models more personalized, which can further improve the federated performance. Extensive experiments show that ParetoFed outperforms existing FL methods in terms of fairness, and even achieves better federated performance, which demonstrates the significance of our method. [ABSTRACT FROM AUTHOR]

Electricity expense management presents significant challenges, as this resource is susceptible to various influencing factors. In universities, the demand for this resource is rapidly growing with institutional expansion and has a significant environmental impact. In this study, the machine learning models long short-term memory (LSTM), random forest (RF), support vector regression (SVR), and extreme gradient boosting (XGBoost) were trained with historical consumption data from the Federal Institute of Paraná (IFPR) over the last seven years and climatic variables to forecast electricity consumption 12 months ahead. Datasets from two campuses were adopted. To improve model performance, feature selection was performed using Shapley additive explanations (SHAP), and hyperparameter optimization was carried out using genetic algorithm (GA) and particle swarm optimization (PSO). The results indicate that the proposed cooperative ensemble learning approach named Weaker Separator Booster (WSB) exhibited the best performance for datasets. Specifically, it achieved an sMAPE of 13.90% and MAE of 1990.87 kWh for the IFPR–Palmas Campus and an sMAPE of 18.72% and MAE of 465.02 kWh for the Coronel Vivida Campus. The SHAP analysis revealed distinct feature importance patterns across the two IFPR campuses. A commonality that emerged was the strong influence of lagged time-series values and a minimal influence of climatic variables. [ABSTRACT FROM AUTHOR]

Abstract This study examines the formidable and complex challenge of insider threats to organizational security, addressing risks such as ransomware incidents, data breaches, and extortion attempts. The research involves six experiments utilizing email, HTTP, and file content data. To combat insider threats, emerging Natural Language Processing techniques are employed in conjunction with powerful Machine Learning classifiers, specifically XGBoost and AdaBoost. The focus is on recognizing the sentiment and context of malicious actions, which are considered less prone to change compared to commonly tracked metrics like location and time of access. To enhance detection, a term frequency-inverse document frequency-based approach is introduced, providing a more robust, adaptable, and maintainable method. Moreover, the study acknowledges the significant impact of hyperparameter selection on classifier performance and employs various contemporary optimizers, including a modified version of the red fox optimization algorithm. The proposed approach undergoes testing in three simulated scenarios using a public dataset, showcasing commendable outcomes.

Climate change and increasing global temperatures have increased the frequency and intensity of forest fires, making fire risk evaluation increasingly important. This study aims to improve the accuracy of predicting forest fuel drought conditions (Drought Code) by using the XGBoost algorithm optimized with RandomizedSearchCV. The research methods include collecting data related to forest fires, preprocessing data to ensure quality and consistency, and using RandomizedSearchCV for XGBoost hyperparameter optimization. The results showed that the optimized XGBoost model resulted in a decrease in Mean Squared Error (MSE) and an increase in R-squared value compared to the default model. The optimized model achieved an MSE of 0.0210 and R2 of 0.9820 on the test data, indicating significantly improved prediction accuracy for forest fuel drought conditions. These findings emphasize the importance of hyperparameter optimization in improving the accuracy of predictive models for forest fire risk assessment.

Electricity expense management presents significant challenges, as this resource is susceptible to various influencing factors. In universities, the demand for this resource is rapidly growing with institutional expansion and has a significant environmental impact. In this study, the machine learning models long short-term memory (LSTM), random forest (RF), support vector regression (SVR), and extreme gradient boosting (XGBoost) were trained with historical consumption data from the Federal Institute of Paraná (IFPR) over the last seven years and climatic variables to forecast electricity consumption 12 months ahead. Datasets from two campuses were adopted. To improve model performance, feature selection was performed using Shapley additive explanations (SHAP), and hyperparameter optimization was carried out using genetic algorithm (GA) and particle swarm optimization (PSO). The results indicate that the proposed cooperative ensemble learning approach named Weaker Separator Booster (WSB) exhibited the best performance for datasets. Specifically, it achieved an sMAPE of 13.90% and MAE of 1990.87 kWh for the IFPR–Palmas Campus and an sMAPE of 18.72% and MAE of 465.02 kWh for the Coronel Vivida Campus. The SHAP analysis revealed distinct feature importance patterns across the two IFPR campuses. A commonality that emerged was the strong influence of lagged time-series values and a minimal influence of climatic variables.

The stochastic contextual bandit problem, recognized for its effectiveness in navigating the classic exploration-exploitation dilemma through ongoing player-environment interactions, has found broad applications across various industries. This utility largely stems from the algorithms’ ability to accurately forecast reward functions and maintain an optimal balance between exploration and exploitation, contingent upon the precise selection and calibration of hyperparameters. However, the inherently dynamic and real-time nature of bandit environments significantly complicates hyperparameter tuning, rendering traditional offline methods inadequate. While specialized methods have been developed to overcome these challenges, they often face three primary issues: difficulty in adaptively learning hyperparameters in ever-changing environments, inability to simultaneously optimize multiple hyperparameters for complex models, and inefficiencies in data utilization and knowledge transfer from analogous tasks. To tackle these hurdles, this paper introduces an innovative transfer learning-based approach designed to harness past task knowledge for accelerated optimization and dynamically optimize multiple hyperparameters, making it well-suited for fluctuating environments. The method employs a dual Gaussian meta-model strategy—one for transfer learning and the other for assessing hyperparameters’ performance within the current task —enabling it to leverage insights from previous tasks while quickly adapting to new environmental changes. Furthermore, the framework’s meta-model-centric architecture enables simultaneous optimization of multiple hyperparameters. Experimental evaluations demonstrate that this approach markedly outperforms competing methods in scenarios with perturbations and exhibits superior performance in 70% of stationary cases while matching performance in the remaining 30%. This superiority in performance, coupled with its computational efficiency on par with existing alternatives, positions it as a superior and practical solution for optimizing hyperparameters in contextual bandit settings.

Copyright of International Journal of Engineering Design & Technology (IJEDT) is the property of Burdur Mehmet Akif Ersoy University, Faculty of Architecture & Engineering and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Hopfield neural network stands out from artificial neural network models for solving optimization problems due to its unique ability to rapidly converge on global solutions without requiring complex supervised learning steps, although the performance of this network depends mainly on the tuning of its hyperparameters. This study aims to address the complexity of hyperparameter optimization in Hopfield neural networks by framing it as a sequential decision problem. Unlike traditional optimization techniques, which often struggle with the dynamic and iterative nature of hyperparameter tuning, the proposed approach uses reinforcement learning (RL) principles to adapt and optimize in real time. By using RL, we can dynamically adjust hyperparameters based on feedback from the network's performance, resulting in a more efficient and effective optimization process. The proposed approach significantly improves both the performance of the network and the execution time, thereby increasing the overall efficiency and effectiveness of the system. To demonstrate the effectiveness of the proposed approach, we applied it to the optimization of the tourist visit planning problem. The application of Hopfield neural networks, combined with reinforcement learning to optimize the hyperparameters of this network, has enabled the creation of a powerful model for optimizing tourist itineraries. This approach shows a clear improvement over traditional methods, maximizing the visitor experience and ensuring more efficient and enjoyable visits. [ABSTRACT FROM AUTHOR]

Cardiotocography (CTG) is used to assess the health of the fetus during birth or antenatally in the third trimester. It concurrently detects the maternal uterine contractions (UC) and fetal heart rate (FHR). Fetal distress, which may require therapeutic intervention, can be diagnosed using baseline FHR and its reaction to uterine contractions. Using CTG, a pragmatic machine learning strategy based on feature reduction and hyperparameter optimization was suggested in this study to classify the various fetal states (Normal, Suspect, Pathological). An application of this strategy can be a decision support tool to manage pregnancies. On a public dataset of 2126 CTG recordings, the model was assessed using various standard CTG dataset specific and relevant classifiers. The classifiers' accuracy was improved by the proposed method. The model accuracy was increased to 97.20% while using Random Forest (best classifier). Practically speaking, the model was able to correctly predict 100% of all pathological cases and 98.8% of all normal cases in the dataset. The proposed model was also implemented on another public CTG dataset having 552 CTG signals, resulting in a 97.34% accuracy. If integrated with telemedicine, this proposed model could also be used for long-distance "stay at home" fetal monitoring in high-risk pregnancies. [ABSTRACT FROM AUTHOR]

Boosting algorithms have been widely utilized in the development of landslide susceptibility mapping (LSM) studies. However, these algorithms possess distinct computational strategies and hyperparameters, making it challenging to propose an ideal LSM model. To investigate the impact of different boosting algorithms and hyperparameter optimization algorithms on LSM, this study constructed a geospatial database comprising 12 conditioning factors, such as elevation, stratum, and annual average rainfall. The XGBoost (XGB), LightGBM (LGBM), and CatBoost (CB) algorithms were employed to construct the LSM model. Furthermore, the Bayesian optimization (BO), particle swarm optimization (PSO), and Hyperband optimization (HO) algorithms were applied to optimizing the LSM model. The boosting algorithms exhibited varying performances, with CB demonstrating the highest precision, followed by LGBM, and XGB showing poorer precision. Additionally, the hyperparameter optimization algorithms displayed different performances, with HO outperforming PSO and BO showing poorer performance. The HO-CB model achieved the highest precision, boasting an accuracy of 0.764, an F1-score of 0.777, an area under the curve (AUC) value of 0.837 for the training set, and an AUC value of 0.863 for the test set. The model was interpreted using SHapley Additive exPlanations (SHAP), revealing that slope, curvature, topographic wetness index (TWI), degree of relief, and elevation significantly influenced landslides in the study area. This study offers a scientific reference for LSM and disaster prevention research. This study examines the utilization of various boosting algorithms and hyperparameter optimization algorithms in Wanzhou District. It proposes the HO-CB-SHAP framework as an effective approach to accurately forecast landslide disasters and interpret LSM models. However, limitations exist concerning the generalizability of the model and the data processing, which require further exploration in subsequent studies.

Hyperparameter optimization (HPO) has been well-developed and evolved into a well-established research topic over the decades. With the success and wide application of deep learning, HPO has garnered increased attention, particularly within the realm of machine learning model training and inference. The primary objective is to mitigate the challenges associated with manual hyperparameter tuning, which can be ad-hoc, reliant on human expertise, and consequently hinders reproducibility while inflating deployment costs. Recognizing the growing significance of HPO, this paper surveyed classical HPO methods, approaches for accelerating the optimization process, HPO in an online setting (dynamic algorithm configuration, DAC), and when there is more than one objective to optimize (multi-objective HPO). Acceleration strategies were categorized into multi-fidelity, bandit-based, and early stopping; DAC algorithms encompassed gradient-based, population-based, and reinforcement learning-based methods; multi-objective HPO can be approached via scalarization, metaheuristics, and model-based algorithms tailored for multi-objective situation. A tabulated overview of popular frameworks and tools for HPO was provided, catering to the interests of practitioners.

Abstract Sports image classification is a complex undertaking that necessitates the utilization of precise and robust techniques to differentiate between various sports activities. This study introduces a novel approach that combines the deep neural network (DNN) with a modified metaheuristic algorithm known as novel tuna swarm optimization (NTSO) for the purpose of sports image classification. The DNN is a potent technique capable of extracting high-level features from raw images, while the NTSO algorithm optimizes the hyperparameters of the DNN, including the number of layers, neurons, and activation functions. Through the application of NTSO to the DNN, a finely-tuned network is developed, exhibiting exceptional performance in sports image classification. Rigorous experiments have been conducted on an extensive dataset of sports images, and the obtained results have been compared against other state-of-the-art methods, including Attention-based graph convolution-guided third-order hourglass network (AGTH-Net), particle swarm optimization algorithm (PSO), YOLOv5 backbone and SPD-Conv, and Depth Learning (DL). According to a fivefold cross-validation technique, the DNN/NTSO model provided remarkable precision, recall, and F1-score results: 97.665 ± 0.352%, 95.400 ± 0.374%, and 0.8787 ± 0.0031, respectively. Detailed comparisons reveal the DNN/NTSO model's superiority toward various performance metrics, solidifying its standing as a top choice for sports image classification tasks. Based on the practical dataset, the DNN/NTSO model has been successfully evaluated in real-world scenarios, showcasing its resilience and flexibility in various sports categories. Its capacity to uphold precision in dynamic settings, where elements like lighting, backdrop, and motion blur are prominent, highlights its utility. The model's scalability and efficiency in analyzing images from live sports competitions additionally validate its suitability for integration into real-time sports analytics and media platforms. This research not only confirms the theoretical superiority of the DNN/NTSO model but also its pragmatic effectiveness in a wide array of demanding sports image classification assignments.

Accurate and reliable short-term runoff prediction plays a pivotal role in water resource management, agriculture, and flood control, enabling decision-makers to implement timely and effective measures to enhance water use efficiency and minimize losses. To further enhance the accuracy of runoff prediction, this study proposes a FA-LSTM model that integrates the Firefly algorithm (FA) with the long short-term memory neural network (LSTM). The research focuses on historical daily runoff data from the Dahuangjiangkou and Wuzhou Hydrology Stations in the Xijiang River Basin. The FA-LSTM model is compared with RNN, LSTM, GRU, SVM, and RF models. The FA-LSTM model was used to carry out the generalization experiment in Qianjiang, Wuxuan, and Guigang hydrology stations. Additionally, the study analyzes the performance of the FA-LSTM model across different forecasting horizons (1–5 days). Four quantitative evaluation metrics—mean absolute error (MAE), root mean square error (RMSE), coefficient of determination (R2), and Kling–Gupta efficiency coefficient (KGE)—are utilized in the evaluation process. The results indicate that: (1) Compared to RNN, LSTM, GRU, SVM, and RF models, the FA-LSTM model exhibits the best prediction performance, with daily runoff prediction determination coefficients (R2) reaching as high as 0.966 and 0.971 at the Dahuangjiangkou and Wuzhou Stations, respectively, and the KGE is as high as 0.965 and 0.960, respectively. (2) FA-LSTM model was used to conduct generalization tests at Qianjiang, Wuxuan and Guigang hydrology stations, and its R2 and KGE are 0.96 or above, indicating that the model has good adaptability in different hydrology stations and strong robustness. (3) As the prediction period extends, the R2 and KGE of the FA-LSTM model show a decreasing trend, but the whole model still showed feasible forecasting ability. The FA-LSTM model introduced in this study presents an effective new approach for daily runoff prediction. [ABSTRACT FROM AUTHOR]

The increasing volume of medical information available in digital format presents a significant challenge for researchers seeking to extract relevant information. Manually analyzing voluminous data is a time-consuming process that constrains researchers' productivity. In this context, innovative and intelligent computational approaches to information search, such as large language models (LLMs), offer a promising solution. LLMs understand natural language questions and respond accurately to complex queries, even in the specialized domain of medicine. This paper presents MédicoBERT, a medical language model in Spanish developed by adapting a general domain language model (BERT) to medical terminology and vocabulary related to diseases, treatments, symptoms, and medications. The model was pre-trained with 3 M medical texts containing 1.1 B words. Furthermore, with promising results, MédicoBERT was adapted and evaluated to answer medical questions in Spanish. The question-answering (QA) task was fine-tuned using a Spanish corpus of over 34,000 medical questions and answers. A search was then conducted to identify the optimal hyperparameter configuration using heuristic methods and nonlinear regression models. The evaluation of MédicoBERT was carried out using metrics such as perplexity to measure the adaptation of the language model to the medical vocabulary in Spanish, where it obtained a value of 4.28, and the average F1 metric for the task of answering medical questions, where it obtained a value of 62.35%. The objective of MédicoBERT is to provide support for research in the field of natural language processing (NLP) in Spanish, with a particular emphasis on applications within the medical domain. [ABSTRACT FROM AUTHOR]

The importance of power quality monitoring, detection, and classification on electrical systems increased recently in terms of economics, security, the efficiency depending on the spreading of the smart grid. The current monitoring systems are based on IEEE 1159 and similar standards under some stable conditions and assuming. But the detailed measurements of power quality disturbances should be evaluated robustly even in a noisy environment with a specific method for each power quality disturbance (PQD) for every window. Because this approach is very time-consuming and not feasible, most studies with different techniques promote primarily detection of the PQDs and then classifications of these. For this purpose, a study using hyperparameter optimization of machine learning algorithms (MLAs) is executed for the detection and classification (D&C) of PQDs. 21 class datasets consisting of single and multiple PQDs with different-level noise are prepared randomly. These datasets are trained and tested with a lot of MLAs in a workstation as the time-series signals with no preprocessing apart from the other methods. The results obtained from comparative MLAs show that the best MLA and the hyperparameters of that are kNN, RF, LightGBM, and XGBoost with an accuracy of 99.82%, 98.78%, 98.10%, and 94.77%, respectively. In as much as the optimized parameters and the related MLAs were obtained by investigating the time-series signal datasets with no preprocessing in the whole hyperparameter space, this approach brings the advantages of high accuracy. [ABSTRACT FROM AUTHOR]

Accurate prediction of air quality change is essential for air pollution control and human daily mobility. Due to the strong spatial and temporal correlation of air quality changes, existing air quality prediction methods often face the problem of low prediction accuracy due to insufficient extraction of spatio-temporal features. In this paper, we proposed a self-tuning spatio-temporal neural network (ST2NN) to enhance air quality prediction. ST2NN model consisted of four modules. First, ST2NN model constructed a temporal feature extraction module and a spatial feature extraction module based on gated recurrent unit (GRU) and graph convolutional neural network (GCN), respectively, and the two feature extraction modules adopted a parallel structure, which could effectively extract the spatio-temporal features in data. Additionally, ST2NN model constructed a feature fusion module based on gating mechanism to delineate the contribution of spatio-temporal features to the predicted values. Further, ST2NN model constructed a Hyperband hyperparameter optimization module based on Hyperband optimization algorithm to automatically adjust the network hyperparameters. The structure of ST2NN model endowed it with excellent spatio-temporal feature extraction and parameter adaptability. ST2NN model was evaluated and compared with existing models, including convolutional long short-term memory neural network (ConvLSTM), GRU, combined convolutional neural network and long short-term memory neural network (CNN-LSTM), and GCN-LSTM for air quality index (AQI) prediction using data from twelve monitoring stations in Beijing, China. Across all four evaluation indexes, ST2NN model outperformed the comparative models, improving prediction accuracy by 0.51%-10.18% (measured using R 2 ). From the experimental results, it can be seen that ST2NN model constructed from the perspective of spatio-temporal feature extraction has better prediction performance compared with the existing air quality prediction model, which provides a new method for air quality prediction and has certain application value. [ABSTRACT FROM AUTHOR]

Numerical methods for solving differential equations often rely on the expansion of the approximate solution using basis functions. The choice of an appropriate basis function plays a crucial role in enhancing the accuracy of the solution. In this study, our aim is to develop algorithms that can identify an optimal basis function for any given differential equation. To achieve this, we explore fractional rational Jacobi functions as a versatile basis, incorporating hyperparameters related to rational mappings, Jacobi polynomial parameters, and fractional components. Our research develops hyperparameter optimization algorithms, including parallel grid search, parallel random search, Bayesian optimization, and parallel genetic algorithms. To evaluate the impact of each hyperparameter on the accuracy of the solution, we analyze two benchmark problems on a semi‐infinite domain: Volterra's population model and Kidder's equation. We achieve improved convergence and accuracy by judiciously constraining the ranges of the hyperparameters through a combination of random search and genetic algorithms. Notably, our findings demonstrate that the genetic algorithm consistently outperforms other approaches, yielding superior hyperparameter values that significantly enhance the quality of the solution, surpassing state‐of‐the‐art results. [ABSTRACT FROM AUTHOR]

The expeditious and precise prediction of stress variations in nonlinear boom structures is paramount for ensuring the safe, dependable, and effective operation of pump trucks. Nonetheless, balancing prediction accuracy and efficiency by constructing a suitable machine-learning model remains a challenge in engineering practice. To this end, this paper introduces an interpretable fusion model named RS–XGBoost–RF (Random Search–Extreme Gradient Boosting Tree–Random Forest) and develops an intelligent algorithm for the stress prediction of the nonlinear boom structure of concrete pump trucks. Firstly, an information acquisition system is deployed to collect relevant data from the boom systems of ZLJ5440THBBF 56X-6RZ concrete pump trucks during its operational phase. Data pre-processing is conducted on the 2.4 million sets of acquired data. Then, a sample dataset of typical working conditions is obtained. Secondly, the RS algorithm, RF model, and XGBoost model are selected based on their complementary strengths to construct the fusion model. The model fusion condition is established with a focus on prediction efficiency. By leveraging the synergy between search and prediction mechanisms, the RS–XGBoost model is constructed for the prediction of the master hyperparameters of the RF model. This model uses the random search (RS) process to obtain the mapping between the loss function and the hyperparameters. This mapping relationship is then learned using the XGBoost model, and the hyperparameter value with the smallest loss value is predicted. Finally, the RS–XGBoost–RF model with optimized hyperparameters is employed to achieve rapid stress prediction at various detection points of the nonlinear boom structure. The findings demonstrate that, within the acceptable prediction efficiency for engineering practice, the fitting accuracy (R2) of the RS–XGBoost–RF model consistently exceeds 0.955 across all measurement points, with only a few exceptions. Concerning the stress magnitudes themselves, the mean absolute error (MAE) and root mean square error (RMSE) are maintained within the ranges of 2.22% to 3.91% and 4.79% to 7.85%, respectively. In comparison with RS–RF–RF, RS–RF–XGBoost, and RS–XGBoost–XGBoost, the proposed model exhibits the optimal prediction performance. The method delineated in this paper offers valuable insights for expeditious structural stress prediction in the realm of inherent safety within construction machinery. [ABSTRACT FROM AUTHOR]

This study investigates the influence of NaOH treatment on tribological behavior in hybrid fiber‐reinforced composites, specifically employing Banana fiber with Al2O3 filler in an epoxy matrix. Through design of experiments (DOE), disc speed, wear duration, and NaOH treatment are analyzed for specific wear rate (SWR) and coefficient of friction (COF). To advance the understanding of wear characteristics, the study leverages advanced machine learning, using Python‐powered artificial neural networks (ANN), is integrated with innovative ANN hyperparameter optimization. Optimized parameters (1050 rpm, 60 s, 5% treatment) significantly minimize SWR (12.38 × 10−5 mm3/Nm) and COF (0.2). Scanning electron microscopy (SEM) analysis reveals improved interfacial adhesion and identifies micro‐cracks as the primary wear mechanism. This work contributes to a profound understanding of wear in hybrid composites, offering a fine‐tuned predictive model for optimizing tribological behavior and advancing material science and engineering. Highlights: Reduced SWR, COF in composites via NaOH optimization.DOE: Explored disc speed, duration, NaOH impact.Advanced machine learning techniques enhanced wear prediction.Innovative: ANN hyperparameter optimization.Optimal Parameters: 1050 rpm, 60 s, 5% treatment. [ABSTRACT FROM AUTHOR]

Reinforcement learning is a promising paradigm for learning robot control, allowing complex control policies to be learned without requiring a dynamics model. However, even state of the art algorithms can be difficult to tune for optimum performance. We propose employing an ensemble of multiple reinforcement learning agents, each with a different set of hyperparameters, along with a mechanism for choosing the best performing set(s) on-line. In the literature, the ensemble technique is used to improve performance in general, but the current work specifically addresses decreasing the hyperparameter tuning effort. Furthermore, our approach targets on-line learning on a single robotic system, and does not require running multiple simulators in parallel. Although the idea is generic, the Deep Deterministic Policy Gradient was the model chosen, being a representative deep learning actor-critic method with good performance in continuous action settings but known high variance. We compare our online weighted q-ensemble approach to q-average ensemble strategies addressed in literature using alternate policy training, as well as online training, demonstrating the advantage of the new approach in eliminating hyperparameter tuning. The applicability to real-world systems was validated in common robotic benchmark environments: the bipedal robot half cheetah and the swimmer. Online weighted Q-Ensemble presented overall lower variance and superior results when compared with q-average ensembles using randomized parameterizations. [ABSTRACT FROM AUTHOR]

The short‐term load prediction is the critical operation in the peak demand administration and power generation scheduling of buildings that integrated the smart solar microgrid (SSM). Many research studies have proved that hybrid deep learning strategies achieve more accuracy and feasibility in practical applications than individual algorithms. Moreover, many buildings have integrated the SSM on the rooftop with the battery management system (BMS) to enhance energy efficiency management. However, the traditional methodologies only processed the weather parameters and power demand information for short‐term load prediction, ignoring the collected data from SSM and BMS by the advanced metering infrastructures (AMI), which probably improved prediction accuracy. In this research, many accumulated data of building and SSM are collected before methodology implementation. Considering the diversities of accumulated parameters from SSM and BMS, an adaptive convolution neural network long short‐term memory (CNN‐LSTM) is proposed for hourly electrical load prediction. The CNN could extract the critical large‐scale input feature, while the LSTM could achieve better accurate forecasts. The Pearson correlation matrix is calculated for the feature selection scheme from different data units. The hyperparameter tuning is utilized for obtaining the optimized hybrid CNN‐LSTM algorithm. The K‐fold cross‐validation is employed for deep learning algorithm verification, which includes LSTM, GRU, CNN, and Bi‐LSTM methodologies. The results prove that the hybrid CNN‐LSTM achieved outperformed improvements, which are 20.57%, 29.63%, 19.06% in MSE, MAE, MAPE, and 21.24%, 22.02%, 3.82% in validating MSE, MAE, MAPE, respectively. The hybrid CNN and LSTM combined with the feature selection scheme achieve superior predicting accuracies, proving the adaptability ability for integrating into the energy management system (EMS) of the building's SSM. [ABSTRACT FROM AUTHOR]

Air conditioning contributes a high percentage of energy consumption over the world. The efficient prediction of energy consumption can help to reduce energy consumption. Traditionally, multidimensional air conditioning energy consumption data could only be processed sequentially for each dimension, thus resulting in inefficient feature extraction. Furthermore, due to reasons such as implicit correlations between hyperparameters, automatic hyperparameter optimization (HPO) approaches can not be easily achieved. In this paper, we propose an auto-optimization parallel energy consumption prediction approach based on reinforcement learning. It can parallel process multidimensional time series data and achieve the automatic optimization of model hyperparameters, thus yielding an accurate prediction of air conditioning energy consumption. Extensive experiments on real air conditioning datasets from five factories have demonstrated that the proposed approach outperforms existing prediction solutions, with an increase in average accuracy by 11.48% and an average performance improvement of 32.48%. [ABSTRACT FROM AUTHOR]

This study introduces an innovative hyperparameter optimization approach for enhancing multilayer perceptrons (MLP) using the Jaya algorithm. Addressing the crucial role of hyperparameter tuning in MLP's performance, the Jaya algorithm, inspired by social behavior, emerges as a promising optimization technique without algorithm-specific parameters. Systematic application of Jaya dynamically adjusts hyperparameter values, leading to notable improvements in convergence speeds and model generalization. Quantitatively, the Jaya algorithm consistently achieves convergences at first iteration, faster convergence compared to conventional methods, resulting in 7% higher accuracy levels on several datasets. This research contributes to hyperparameter optimization, offering a practical and effective solution for optimizing MLP in diverse applications, with implications for improved computational efficiency and model performance. [ABSTRACT FROM AUTHOR]

For many machine learning models, a choice of hyperparameters is a crucial step towards achieving high performance. Prevalent meta-learning approaches focus on obtaining good hyperparameter configurations with a limited computational budget for a completely new task based on the results obtained from the prior tasks. This paper proposes a new formulation of the tuning problem, called consolidated learning, more suited to practical challenges faced by model developers, in which a large number of predictive models are created on similar datasets. In such settings, we are interested in the total optimization time rather than tuning for a single task. We show that a carefully selected static portfolio of hyperparameter configurations yields good results for anytime optimization, while maintaining the ease of use and implementation. Moreover, we point out how to construct such a portfolio for specific domains. The improvement in the optimization is possible due to the more efficient transfer of hyperparameter configurations between similar tasks. We demonstrate the effectiveness of this approach through an empirical study for the XGBoost algorithm and the newly created metaMIMIC benchmarks of predictive tasks extracted from the MIMIC-IV medical database. In the paper, we show that the potential of consolidated learning is considerably greater due to its compatibility with many machine learning application scenarios. [ABSTRACT FROM AUTHOR]