Journal of Computing Theories and Applications最新文献_第2页

Generating Harmonious Colors through the Combination of n-Grams and K-means 通过 n-Grams 和 K-means 组合生成和谐色彩

Journal of Computing Theories and Applications Pub Date : 2023-12-04 DOI: 10.33633/jcta.v1i2.9470

Shreeniwas Sharma, Jyoti Tandukar, Rabindra Bista

引用次数: 0

Solving the Green Economic Load Dispatch by Applying the Novel Meta-heuristic Algorithm 应用新型元启发式算法解决绿色经济负荷调度问题

Journal of Computing Theories and Applications Pub Date : 2023-11-23 DOI: 10.33633/jcta.v1i2.9389

Nguyen Anh Tang, Nguyen Minh Duc Cuong

{"title":"Solving the Green Economic Load Dispatch by Applying the Novel Meta-heuristic Algorithm","authors":"Nguyen Anh Tang, Nguyen Minh Duc Cuong","doi":"10.33633/jcta.v1i2.9389","DOIUrl":"https://doi.org/10.33633/jcta.v1i2.9389","url":null,"abstract":"This study focuses on solving the green economic load dispatch problem by considering the presence of green energy sources, including wind energy and solar power plants. The main objective function of the whole study is to minimize the total fuel cost (TFC) of all the thermal generating sources (TGSs) in the system. Moreover, the multiple selection of all TGSs is also evaluated. Fire hawk optimization (FHO) and the Zebra optimization algorithm (ZOA) are applied to solve the problem of achieving the best TFC value and satisfying all the constraints involved. The results indicated that ZOA can achieve a better optimal solution compared to FHO. Particularly, the results obtained by ZOA are completely superior to FHO in all comparison criteria at two load demand levels, such as Best TFC value (Best.Cost), Average TFC value (Aver.Cost), and Maximum TFC value (Max.Cost). On top of that, ZOA is the only algorithm of two applied ones providing the fast convergence capability to the optimal value of the main objective functions in two cases of load demand levels. Therefore, ZOA is an efficient search method to deal with such GELD problems.","PeriodicalId":397752,"journal":{"name":"Journal of Computing Theories and Applications","volume":"7 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139245451","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Butterflies Recognition using Enhanced Transfer Learning and Data Augmentation 利用增强迁移学习和数据增强技术识别蝴蝶

Journal of Computing Theories and Applications Pub Date : 2023-11-18 DOI: 10.33633/jcta.v1i2.9443

Harish Trio Adityawan, Omar Farroq, Stefanus Santosa, Hussain Md Mehedul Islam, M. K. Sarker, De Rosal Ignatius Moses Setiadi

{"title":"Butterflies Recognition using Enhanced Transfer Learning and Data Augmentation","authors":"Harish Trio Adityawan, Omar Farroq, Stefanus Santosa, Hussain Md Mehedul Islam, M. K. Sarker, De Rosal Ignatius Moses Setiadi","doi":"10.33633/jcta.v1i2.9443","DOIUrl":"https://doi.org/10.33633/jcta.v1i2.9443","url":null,"abstract":"Butterflies’ recognition serves a crucial role as an environmental indicator and a key factor in plant pollination. The automation of this recognition process, facilitated by Convolutional Neural Networks (CNNs), can expedite this task. Several pre-trained CNN models, such as VGG, ResNet, and Inception, have been widely used for this purpose. However, the scope of previous research has been somewhat constrained, focusing only on a maximum of 15 classes. This study proposes to modify the CNN InceptionV3 model and combine it with three data augmentations to recognize up to 100 butterfly species. To curb overfitting, this study employs a series of data augmentation techniques. In parallel, we refine the InceptionV3 model by reducing the number of layers and integrating four new layers. The test results demonstrate that our proposed model achieves an impressive accuracy of 99.43% for 15 classes with only 10 epochs, exceeding prior models by approximately 5%. When extended to 100 classes, the model maintains a high accuracy rate of 98.49% with 50 epochs. The proposed model surpasses the performance of standard pre-trained models, including VGG16, ResNet50, and InceptionV3, illustrating its potential for broader application.","PeriodicalId":397752,"journal":{"name":"Journal of Computing Theories and Applications","volume":"136 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139262194","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Electricity Generation Cost Optimization Based on Lagrange Function and Local Search 基于拉格朗日函数和局部搜索的发电成本优化

Journal of Computing Theories and Applications Pub Date : 2023-11-17 DOI: 10.33633/jcta.v1i2.9354

Thanh Van Nguyen

{"title":"Electricity Generation Cost Optimization Based on Lagrange Function and Local Search","authors":"Thanh Van Nguyen","doi":"10.33633/jcta.v1i2.9354","DOIUrl":"https://doi.org/10.33633/jcta.v1i2.9354","url":null,"abstract":"This paper proposes a method based on the Lagrange optimization function and local search technique for minimizing the total cost of two power systems. The first system comprises ten multiple fuel thermal units (MFTUs) while the second system combines the first system with renewable energies, solar and wind power. The proposed method has advantages over its conventional method without a local search technique, called the conventional Lagrange function-based method (CLM), such as having the same parameters and exploiting other search spaces after getting convergence. The proposed method is more effective than CLM for the first system with the last case of load demand. In addition, the proposed method has better costs than previous algorithms, such as the Hierarchical numerical method (HNUM), Hopfield neural network, Adaptive Hopfield neural networks (AHNN) and modified Lagrange neural network (MLANN). Especially, the proposed method can find smaller costs than them, up to $6.78, corresponding to 1.4% for Case 1, and up to $2.43, corresponding to 0.4% for Case 4. Only the proposed method is tested on the second test system. The simulation results indicate that the method is very efficient for the problem with solar and wind energies and multiple fuel thermal units.","PeriodicalId":397752,"journal":{"name":"Journal of Computing Theories and Applications","volume":"155 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139265038","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

High-Performance Convolutional Neural Network Model to Identify COVID-19 in Medical Images 基于高性能卷积神经网络模型识别医学图像中的COVID-19

Journal of Computing Theories and Applications Pub Date : 2023-08-30 DOI: 10.33633/jcta.v1i1.8936

Macellino Setyaji Sunarjo, Hongbin Gan, D. Setiadi

{"title":"High-Performance Convolutional Neural Network Model to Identify COVID-19 in Medical Images","authors":"Macellino Setyaji Sunarjo, Hongbin Gan, D. Setiadi","doi":"10.33633/jcta.v1i1.8936","DOIUrl":"https://doi.org/10.33633/jcta.v1i1.8936","url":null,"abstract":"Convolutional neural network (CNN) is a deep learning (DL) model that has significantly contributed to medical systems because it is very useful in digital image processing. However, CNN has several limitations, such as being prone to overfitting, not being properly trained if there is data duplication, and can cause unwanted results if there is an imbalance in the amount of data in each class. Data augmentation techniques are used to overcome overfitting, eliminate data duplication, and random under sampling methods to balance the amount of data in each class, to overcome these problems. In addition, if the CNN model is not designed properly, the computation is less efficient. Research has proved that data augmentation can prevent or overcome overfitting, eliminating duplicate data can make the model more stable, and balancing the amount of data makes the model unbiased and easy to learn new data as evidenced through model evaluation and testing. The results also show that the custom convolutional neural network model is the best model compared to ResNet50 and VGG19 in terms of accuracy, precision, recall, F1-score, loss performance, and computation time efficiency","PeriodicalId":397752,"journal":{"name":"Journal of Computing Theories and Applications","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121830176","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Web Phishing Classification using Combined Machine Learning Methods 结合机器学习方法的网络钓鱼分类

Journal of Computing Theories and Applications Pub Date : 2023-08-30 DOI: 10.33633/jcta.v1i1.8898

Bambang Mahardhika Poerbo Waseso, Noor Ageng Setiyanto

引用次数: 1

Plant Diseases Classification based Leaves Image using Convolutional Neural Network 基于叶片图像的卷积神经网络植物病害分类

Journal of Computing Theories and Applications Pub Date : 2023-08-30 DOI: 10.33633/jcta.v1i1.8877

Satrio Bagus Imanulloh, Ahmad Rofiqul Muslikh, D. Setiadi

引用次数: 2