In recent years, many experimental articles have been conducted to study ultra-high-performance concrete (UHPC). Thus, the relationship between its blend composition and the mechanical properties of UHPC is highly non...
详细信息
In recent years, many experimental articles have been conducted to study ultra-high-performance concrete (UHPC). Thus, the relationship between its blend composition and the mechanical properties of UHPC is highly non-linear and challenging to utilize conventional statistical approaches. A robust and sophisticated method is needed to rationalize the variety of relevant experimental datasets, provide insight into aspects of non-linear materials science, and make estimative tools of desirable accuracy. Machine learning (ML) is a potent strategy that can reveal underlying patterns in complex datasets. This study aims to employ state-of-the-art ML methods for predicting the UHPC compressive strength (CS) by operating 165 previously published samples with 8 input characteristics via support vector regression (SVR). In addition, a novel approach has been used based on meta-heuristic algorithms to enhance accuracy, including Dynamic arithmetic optimization algorithm (DAOA), arithmetic optimization algorithm (AOA), and Black Widow optimization (BWO). Furthermore, the models evaluated the prediction input dataset by some criteria indicators. The results indicated that the represented models obtained suitable estimative efficiency and can be reliable on ML methods in saving time and energy. In general, in comparing hybrid models, SVDA has a more acceptable performance than other hybrid models.
The Internet of Things (IoT) and its applications are currently the most popular research areas. The properties of IoT are easily adapted to real-life applications but they disclose threats. In computer security, the ...
详细信息
The Internet of Things (IoT) and its applications are currently the most popular research areas. The properties of IoT are easily adapted to real-life applications but they disclose threats. In computer security, the Intrusion Detection System (IDS) plays an essential role in identifying and repealing malicious deeds in computer networks. The main purpose of this work is motivated by IoT security enhancement for IDS development using ensemble learning and proposing suitable methods for classifier performance. Initially, the preprocessing strategy is used for data cleaning, encoding and normalization, which are conducted in the RPL-NIDDS17 dataset. After that, the Synthetic Minority Oversampling Technique (SMOTE) is used to balance the dataset. Secondly, the Convolution Neural Network (CNN) has been used to extract the features from the dataset. From the extracted features, the optimal features are selected by the proposed arithmetic optimization algorithm (AOA). Finally, it is applied to the proposed weighted majority voting classifier. The AOA with the Butterfly optimizationalgorithm (BOA) is utilized to integrate the predictions of different classifiers to select the most vote class. This enhances the chances of perceived RF, kNN, SVM kernel, Bi-LSTM and GRU classifiers. The proposed method experiment is conducted in the MATLAB platform with the RPL-NIDDS17 dataset. The proposed scheme shows better performances in terms of accuracy, error, sensitivity, specificity, FPR, F1_score, Kappa and MCC, which are compared with the existing methods and algorithms.
作者:
Amsaveni, D.Malleswaran, M.Anna Univ
Ranippettai Engn Coll Dept ECE Wlaljapet 632513 Tamil Nadu India Anna Univ
Univ Coll Engn Kancheepuram Dept ECE Kancheepuram 631552 Tamil Nadu India
Lung cancer is a disease caused by a spontaneous proliferation of cells in the lung tissue. It is very important to detect cancer cells in the lungs that release oxygen to the human body and carbon dioxide in the body...
详细信息
Lung cancer is a disease caused by a spontaneous proliferation of cells in the lung tissue. It is very important to detect cancer cells in the lungs that release oxygen to the human body and carbon dioxide in the body as a result of vital functions. Hence, in this paper, Novel Hybrid Deep Learning Model (HDLM) and Fuzzy C Means Clustering Method (FCM) are developed for Pulmonary Nodule Detection in CT Images. The HDLM is a combination of a Deep Neural Network (DNN) and an arithmetic optimization algorithm (AOA). In the HDLM, the weight parameters are selected with the help of the AOA algorithm. The proposed methodology is working based on four phases: pre-processing phase, candidate nodule detection phase, feature extraction phase, and classification phase. In the pre-processing phase, the median filter is utilized to remove unwanted features from the input image. In the candidate module detection phase, FCM is utilized for reducing computational complexity and speeding up nodule detection. In the feature extraction phase, intensity-based features are utilized such as first-order statistics and second-order statistics. The first-order statistics are considered various features such as mean, variance, entropy, energy, and skewness. The second-order statistics are considered as gray level co-occurrence matrix (GLCM) features. At last, the HDLM is utilized in the classification phase which is used to reduce the false-positive result and improve the overall sensitivity of the system. The proposed methodology is evaluated by performance metrics and compared with conventional methods.
In recent years, Machine Learning (ML) techniques have been used by several researchers to classify diseases using gene expression data. Disease categorization using heterogeneous gene expression data is often used fo...
详细信息
In recent years, Machine Learning (ML) techniques have been used by several researchers to classify diseases using gene expression data. Disease categorization using heterogeneous gene expression data is often used for defining critical problems such as cancer analysis. A variety of evaluated factors known as genes are used to characterize the gene expression data gathered from DNA microarrays. Accurate classification of genetic data is essential to provide accurate treatments to sick people. A large number of genes can be viewed simultaneously from the collected data. However, processing this data has some limitations due to noises, redundant data, frequent errors, increased complexity, smaller samples with high dimensionality, difficult interpretation, etc. A model must be able to distinguish the features in such heterogeneous data with high accuracy to make accurate predictions. So this paper presents an innovative model to overcome these issues. The proposed model includes an effective multiple indefinite kernel learning based model for analyze the gene expression microarray data, then an optimized kernel principal component analysis (OKPCA) to select best features , hybrid flow-directed arithmetic support vector machine (SVM)-based multiple infinite kernel learning (FDASVM-MIKL) model for classification. Flow direction and arithmetic optimization algorithms are combined with SVM to increase classification accuracy. The proposed technique has an accuracy of 99.95%, 99.63%, 99.60%, 99.51% , 99.79% using the datasets including colon, Isolet, ALLAML, Lung_cancer, and Snp2 graph.
Precise short-term wind power forecasting plays a crucial role in ensuring the effective and secure functioning of wind power installations. To improve the accuracy of short-term wind power forecasts, in this paper, a...
详细信息
ISBN:
(纸本)9798350377477;9798350377460
Precise short-term wind power forecasting plays a crucial role in ensuring the effective and secure functioning of wind power installations. To improve the accuracy of short-term wind power forecasts, in this paper, a hybrid short-term wind power forecasting model STL-AOA-Transformer based on seasonal and trend decomposition using Loess (STL), arithmetic optimization algorithm (AOA) and transformer is proposed. AOA is used to optimize the parameters of transformer. STL is employed for the purpose of breaking down the initial data into modal components characterized by reduced volatility, in order to effectively capture the data features. These modal components are then fed into the AOA-Transformer for the prediction of short-term wind power and the subsequent derivation of the ultimate forecasted value. The efficacy of the model was assessed through testing and validation using authentic data spanning four seasons and four stations, and compared to three other models. The results show that the model fits the data well and has high prediction accuracy, which has important practical value.
The present study suggests a new damage index using natural frequency and modal strain energy called NFMSEBI for two-stage structural damage localization and quantification. The goal is to improve the performance of c...
详细信息
The accurate prediction of dam deformation is essential for ensuring safe and efficient dam operation and risk management. However, the nonlinear relationships between deformation and time-varying environmental factor...
详细信息
The accurate prediction of dam deformation is essential for ensuring safe and efficient dam operation and risk management. However, the nonlinear relationships between deformation and time-varying environmental factors pose significant challenges, often limiting the accuracy of conventional and deep learning models. To address these issues, this study aimed to improve the predictive accuracy and interpretability in dam deformation modeling by proposing a novel LSTM seq2seq model that integrates a chaos-based arithmetic optimization algorithm (AOA) and an attention mechanism. The AOA optimizes the model's learnable parameters by utilizing the distribution patterns of four mathematical operators, further enhanced by logistic and cubic mappings, to avoid local optima. The attention mechanism, placed between the encoder and decoder networks, dynamically quantifies the impact of influencing factors on deformation, enabling the model to focus on the most relevant information. This approach was applied to an earth-rock dam, achieving superior predictive performance with RMSE, MAE, and MAPE values of 0.695 mm, 0.301 mm, and 0.156%, respectively, outperforming conventional machine learning and deep learning models. The attention weights provide insights into the contributions of each factor, enhancing interpretability. This model holds potential for real-time deformation monitoring and predictive maintenance, contributing to the safety and resilience of dam infrastructure.
To overcome the shortcomings of the algorithmoptimizationalgorithm (AOA), such as its slow convergence speed and poor global search ability, an improved AOA based on RungeKutta and golden sine strategy (RGAOA) is pr...
详细信息
To overcome the shortcomings of the algorithmoptimizationalgorithm (AOA), such as its slow convergence speed and poor global search ability, an improved AOA based on RungeKutta and golden sine strategy (RGAOA) is proposed. In this algorithm, the improved r1 based on the sine factor is proposed and compared with the math optimizer accelerated (MOA) values for each iteration. In this way the weighting of the exploration phase and the exploitation phase of the optimization process is reconstructed. Then, the gold sine strategy is used to guide individuals to approach the optimal solutions. After obtaining the current optimal solution, the quality of the current optimal solution is further enhanced by the Enhanced Solution Quality (ESQ) of the RungeKutta optimizer (RUN). Then, twenty benchmark test functions, the CEC2017, CEC2019 test functions (2017 and 2019 IEEE Congress on Evolutionary Computation test functions) and the practical engineering application problems were selected to test the overall performance of the improved algorithm, and the results were compared with other algorithms and other improved versions. The experimental results show an 89.19% improvement in convergence speed, a 90.07% improvement in convergence accuracy and a 67.99% improvement in stability compared to AOA.
Today, image segmentation methods are widely used for various applications, including object detection. Multilevel Thresholding Image Segmentation (MTIS) methods are among the efficient methods for image seg-mentation...
详细信息
Today, image segmentation methods are widely used for various applications, including object detection. Multilevel Thresholding Image Segmentation (MTIS) methods are among the efficient methods for image seg-mentation. In MTIS methods, it is very important to find the thresholds that gives the best performance for the MTIS and better separate and detect the objects on the image from the image background. Meta-Heuristic (MH) algorithms are among the strategies that can achieve good results in obtaining optimal thresholds to solve this problem. In this paper, we use the combination of arithmetic optimization algorithm (AOA) and Harris Hawks Optimizer (HHO) to improve AOA in exploitation phase, and achieve an optimal threshold vector for MTIS. Therefore, our new hybrid AOA-HHO algorithm solves the MTIS problem with better quality than both AOA and HHO algorithms and some other MH algorithms, and can obtain better thresholds that increase the performance of the MTIS system than AOA and HHO. AOA is powerful in the exploration, and HHO in exploitation phase is powerful. Therefore, AOA-HHO uses the features of both algorithms to search the entire search space locally and globally to find the best find the solution, the high power of the AOA exploration phase, and the high power of the HHO exploitation phase. Also, we use a mathematical equation as the fitness function, that is obtained by using image features. A series of experiments were performed using seven different threshold levels on the test images. Experiments show that AOA-HHO method is better than the compared algorithms and even HHO and AOA in terms of image segmentation accuracy, fitness function value, Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM), and execution time.
Solar Photovoltaic (PV) system is one of the most significant forms of renewable energy resources, and it requires accuracy to assess, design, and extraction of its parameters. Several methods have been extensively ap...
详细信息
Solar Photovoltaic (PV) system is one of the most significant forms of renewable energy resources, and it requires accuracy to assess, design, and extraction of its parameters. Several methods have been extensively applied to mimic the nonlinearity and multi-model behavior of the PV system. However, there is no method to date that can guarantee the extracted parameter of the PV model is the most accurate one. Therefore, this paper presents a unique approach known as Hybridized arithmetic Operation algorithm based on Efficient Newton Raphson (HAOA(ENR)) to experimentally extract the parameters of the single-diode and double-diode PV models at the variability of the climatic changes. Firstly, the objective function is efficiently designed to roughly predict the initial root values of the PV equation. Secondly, the Levy flight and Brownian strategies are integrated in the four operators of AOA to thoroughly analyze the feature space of this problem. Additionally, the four operators of the AOA is divided into two phases to equilibrium between the exploration and exploitation tendencies. Furthermore, the chaotic map and robust mutation techniques are systematically employed in the beginning and halves of generations to ensure the algorithm can reach globally at few numbers iterations. Finally, a nonlinearly adjustable damping parameter of the Levenberg-Marquardt technique is linked with the NR method to replicate the fluctuation behaviours of the PV models. The experimental findings revealed that the proposed HAOA(ENR) outperformed all other methods found in the literature, with average RMSE values close to zero values for both PV models.
暂无评论