Software development effort estimation is regarded as a crucial activity for managing project cost, time, and quality, as well as for the software development life cycle. As a result, proper estimating is crucial to the success of projects and to lower risks. Software effort estimation has drawn much research interest recently and has become a problem for the software industry. When results are inaccurate, an effort may be over- or under-estimated, which can disastrously affect project resources. In the sector, machine learning methods are becoming more and more prominent. Therefore, in this paper, we propose a Modified Jaya algorithm to improve the effectiveness of the estimated model; Modified JOA selects the ideal subset of components from an extensive feature collection. Then, the ensemble machine learning-based Enhanced Extreme gradient boosting algorithm and Ensemble Learning machine approach are employed to estimate the software effort. On the PROMISE SDEE repository, the proposed methodologies are empirically assessed. In this approach, applying machine learning techniques to the effort estimation process increases the likelihood that the time and cost estimates will be accurate. The proposed approach yields a greater performance. The key benefit of this approach is that it lowers the computational cost. This approach can also inspire the development of a tool that could reliably, effectively, and accurately estimate the effort required to complete different software projects.
{"title":"Software Effort Estimation Based on Ensemble Extreme Gradient Boosting Algorithm and Modified Jaya Optimization Algorithm","authors":"Beesetti Kiran Kumar, Saurabh Bilgaiyan, Bhabani Shankar Prasad Mishra","doi":"10.1142/s1469026823500323","DOIUrl":"https://doi.org/10.1142/s1469026823500323","url":null,"abstract":"Software development effort estimation is regarded as a crucial activity for managing project cost, time, and quality, as well as for the software development life cycle. As a result, proper estimating is crucial to the success of projects and to lower risks. Software effort estimation has drawn much research interest recently and has become a problem for the software industry. When results are inaccurate, an effort may be over- or under-estimated, which can disastrously affect project resources. In the sector, machine learning methods are becoming more and more prominent. Therefore, in this paper, we propose a Modified Jaya algorithm to improve the effectiveness of the estimated model; Modified JOA selects the ideal subset of components from an extensive feature collection. Then, the ensemble machine learning-based Enhanced Extreme gradient boosting algorithm and Ensemble Learning machine approach are employed to estimate the software effort. On the PROMISE SDEE repository, the proposed methodologies are empirically assessed. In this approach, applying machine learning techniques to the effort estimation process increases the likelihood that the time and cost estimates will be accurate. The proposed approach yields a greater performance. The key benefit of this approach is that it lowers the computational cost. This approach can also inspire the development of a tool that could reliably, effectively, and accurately estimate the effort required to complete different software projects.","PeriodicalId":45994,"journal":{"name":"International Journal of Computational Intelligence and Applications","volume":"14 1","pages":""},"PeriodicalIF":1.8,"publicationDate":"2023-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139245154","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}
Pub Date : 2023-11-11DOI: 10.1142/s146902682350030x
Xiao Yu, Cong Chen, Qi Gong, Weihan Li, Lina Lu
Soybean leaf disease labeling data are not easy to obtain, and soybean leaf disease model training often needs a lot of data. Due to the limitations of fixed rules such as rotation and clipping, traditional data enhancement cannot generate images with diversity and variability. In view of the above problems, this study proposed a data enhancement method based on generative adversarial network to expand the original soybean leaf disease dataset. This method was based on cyclic confrontation network, and its discriminator uses dense connection strategy to realize feature reuse, so as to reduce the amount of calculation. In the training process, improved transfer learning is used to automatically fine tune the pre-training model. The accuracy of the optimized method in 9 kinds of soybean leaf disease image recognition is 95.84%, which is 0.98% higher than the traditional fine-tuning method. The experimental results show that this method based on generating confrontation network has significant ability in generating soybean leaf disease image, and can expand the existing dataset. In addition, this method also provides an effective data enhancement solution for the expansion of other crop disease image datasets.
{"title":"Soybean Leaf Diseases Recognition Based on Generative Adversarial Network and Transfer Learning","authors":"Xiao Yu, Cong Chen, Qi Gong, Weihan Li, Lina Lu","doi":"10.1142/s146902682350030x","DOIUrl":"https://doi.org/10.1142/s146902682350030x","url":null,"abstract":"Soybean leaf disease labeling data are not easy to obtain, and soybean leaf disease model training often needs a lot of data. Due to the limitations of fixed rules such as rotation and clipping, traditional data enhancement cannot generate images with diversity and variability. In view of the above problems, this study proposed a data enhancement method based on generative adversarial network to expand the original soybean leaf disease dataset. This method was based on cyclic confrontation network, and its discriminator uses dense connection strategy to realize feature reuse, so as to reduce the amount of calculation. In the training process, improved transfer learning is used to automatically fine tune the pre-training model. The accuracy of the optimized method in 9 kinds of soybean leaf disease image recognition is 95.84%, which is 0.98% higher than the traditional fine-tuning method. The experimental results show that this method based on generating confrontation network has significant ability in generating soybean leaf disease image, and can expand the existing dataset. In addition, this method also provides an effective data enhancement solution for the expansion of other crop disease image datasets.","PeriodicalId":45994,"journal":{"name":"International Journal of Computational Intelligence and Applications","volume":"19 14","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135087195","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}
Pub Date : 2023-11-10DOI: 10.1142/s1469026823500293
Yi Chen, Jingsong Sun, Ziyue Xu, Genglong Zhang, Naibin Qi, Yuchen Song
With the rapid advancement of internet technology, various industries have accumulated vast amounts of data, including on user behavior and personal preferences. Traditional museums can leverage this user data to uncover individual preferences and offer personalized services to their visitors. However, the exponential growth of information has also led to the problem of information overload, making it challenging for users to find relevant information within the vast data landscape. Consequently, the utilization rate of available information decreases. By harnessing the power of cloud computing, big data analytics, and recommendation systems, museums can enhance visitors’ touring experiences by helping them discover collections aligned with their interests and connecting with like-minded individuals. To address this objective, the research focuses on optimizing the initial clustering centers of the fuzzy clustering algorithm and parallelizing the optimized algorithm using MapReduce, resulting in the development of a novel MapReduce-based k-prototype fuzzy c-means (MRKPFCM) algorithm. Subsequently, the MRKPFCM algorithm is combined with the classical collaborative filtering algorithm to create a hybrid and parallelized collaborative filtering recommendation algorithm, incorporating elements such as MRKPFCM, audience, and collection. This hybrid algorithm is further supplemented by a content-based recommendation approach to generate comprehensive and refined recommendation results. Experimental findings demonstrate that the predictive scoring errors, as measured by RMSE and MAE, exhibited a downward trend when the number of nearest neighbors for target users fell within the range of 10–20. For instance, the studied algorithm’s MAE value decreased from 0.7512 to 0.7179, surpassing the corresponding figures for the two comparison algorithms. Moreover, with an increase in the number of nearest neighbors within the same range, all three algorithms experienced improved accuracy in prediction results. In particular, the accuracy rate rose from 17.84% to 18.82%, outperforming the two comparison algorithms. In summary, the enhanced hybrid recommendation algorithm achieved through this study displays superior recommendation accuracy and holds significant practical value.
{"title":"A Study of Digital Museum Collection Recommendation Algorithm Based on Improved Fuzzy Clustering Algorithm","authors":"Yi Chen, Jingsong Sun, Ziyue Xu, Genglong Zhang, Naibin Qi, Yuchen Song","doi":"10.1142/s1469026823500293","DOIUrl":"https://doi.org/10.1142/s1469026823500293","url":null,"abstract":"With the rapid advancement of internet technology, various industries have accumulated vast amounts of data, including on user behavior and personal preferences. Traditional museums can leverage this user data to uncover individual preferences and offer personalized services to their visitors. However, the exponential growth of information has also led to the problem of information overload, making it challenging for users to find relevant information within the vast data landscape. Consequently, the utilization rate of available information decreases. By harnessing the power of cloud computing, big data analytics, and recommendation systems, museums can enhance visitors’ touring experiences by helping them discover collections aligned with their interests and connecting with like-minded individuals. To address this objective, the research focuses on optimizing the initial clustering centers of the fuzzy clustering algorithm and parallelizing the optimized algorithm using MapReduce, resulting in the development of a novel MapReduce-based k-prototype fuzzy c-means (MRKPFCM) algorithm. Subsequently, the MRKPFCM algorithm is combined with the classical collaborative filtering algorithm to create a hybrid and parallelized collaborative filtering recommendation algorithm, incorporating elements such as MRKPFCM, audience, and collection. This hybrid algorithm is further supplemented by a content-based recommendation approach to generate comprehensive and refined recommendation results. Experimental findings demonstrate that the predictive scoring errors, as measured by RMSE and MAE, exhibited a downward trend when the number of nearest neighbors for target users fell within the range of 10–20. For instance, the studied algorithm’s MAE value decreased from 0.7512 to 0.7179, surpassing the corresponding figures for the two comparison algorithms. Moreover, with an increase in the number of nearest neighbors within the same range, all three algorithms experienced improved accuracy in prediction results. In particular, the accuracy rate rose from 17.84% to 18.82%, outperforming the two comparison algorithms. In summary, the enhanced hybrid recommendation algorithm achieved through this study displays superior recommendation accuracy and holds significant practical value.","PeriodicalId":45994,"journal":{"name":"International Journal of Computational Intelligence and Applications","volume":" 69","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135191783","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}
Pub Date : 2023-11-03DOI: 10.1142/s1469026823500311
Jianhua Wang, Haozhan Wang
Orchid is a type of plant that grows on land. It is highly valued for its beauty and is cherished by many because of its graceful flower shape, delicate fragrance, vibrant colors, and noble symbolism. Although there are various types of orchids, some of them look similar in appearance and color, making it challenging for people to distinguish them quickly and accurately. The existing methods for classifying orchid species face issues with accuracy due to the similarities between different species and the differences within the same species. This affects their practical use. To address these challenges, this paper introduces an efficient method for classifying orchid species using transfer learning. The main achievement of this study is the successful utilization of transfer learning to achieve accurate orchid species classification. This approach reduces the need for large datasets, minimizes overfitting, cuts down on training time and costs, and enhances classification accuracy. Specifically, the proposed approach involves four phases. First, we gathered a collection of 12 orchid image sets, totaling 12,227 images, through a combination of network sources and field photography. Next, we analyzed the distinctive features present in the collected orchid image sets. We identified certain connections between the acquired orchid datasets and other datasets. Finally, we employed transfer learning technology to create an efficient classification function for orchid species based on these relationships. As a result, our proposed method effectively addresses the challenges highlighted. Experimental results demonstrate that our classification algorithm, which utilizes transfer learning, achieves a classification accuracy rate of 96.16% compared to not using the transfer learning method. This substantial improvement in accuracy greatly enhances the efficiency of orchid classification.
{"title":"Efficiency in Orchid Species Classification: A Transfer Learning-Based Approach","authors":"Jianhua Wang, Haozhan Wang","doi":"10.1142/s1469026823500311","DOIUrl":"https://doi.org/10.1142/s1469026823500311","url":null,"abstract":"Orchid is a type of plant that grows on land. It is highly valued for its beauty and is cherished by many because of its graceful flower shape, delicate fragrance, vibrant colors, and noble symbolism. Although there are various types of orchids, some of them look similar in appearance and color, making it challenging for people to distinguish them quickly and accurately. The existing methods for classifying orchid species face issues with accuracy due to the similarities between different species and the differences within the same species. This affects their practical use. To address these challenges, this paper introduces an efficient method for classifying orchid species using transfer learning. The main achievement of this study is the successful utilization of transfer learning to achieve accurate orchid species classification. This approach reduces the need for large datasets, minimizes overfitting, cuts down on training time and costs, and enhances classification accuracy. Specifically, the proposed approach involves four phases. First, we gathered a collection of 12 orchid image sets, totaling 12,227 images, through a combination of network sources and field photography. Next, we analyzed the distinctive features present in the collected orchid image sets. We identified certain connections between the acquired orchid datasets and other datasets. Finally, we employed transfer learning technology to create an efficient classification function for orchid species based on these relationships. As a result, our proposed method effectively addresses the challenges highlighted. Experimental results demonstrate that our classification algorithm, which utilizes transfer learning, achieves a classification accuracy rate of 96.16% compared to not using the transfer learning method. This substantial improvement in accuracy greatly enhances the efficiency of orchid classification.","PeriodicalId":45994,"journal":{"name":"International Journal of Computational Intelligence and Applications","volume":"7 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135875255","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}
Pub Date : 2023-10-26DOI: 10.1142/s1469026823420014
Liu Yajuan, Xu Wenbin
Private equity investment funds targeted increase in NEEQ has become a new strategy for PE investment. However, the currently adopted Logit regression and one-factor ANOVA models are not suitable for analyzing nonlinear investment activities, and the investment appraisal does not work well. In this paper, all NEEQ companies that implemented private placement in 2017 are used as the study sample. This paper also empirically analyzes the current situation of domestic private equity investment funds based on BP and Hopfield neural network models, then the results of the two models are compared. It is concluded that the accuracy of the BP neural network model can be more than 90%. So, the BP neural network can be used as the optimal model of private equity investment funds investment strategy in NEEQ.
{"title":"Research on the Investment Strategy of Private Equity Investment Fund Targeted Increase in NEEQ — An Empirical Analysis Based on BP and Hopfield Neural Network Model","authors":"Liu Yajuan, Xu Wenbin","doi":"10.1142/s1469026823420014","DOIUrl":"https://doi.org/10.1142/s1469026823420014","url":null,"abstract":"Private equity investment funds targeted increase in NEEQ has become a new strategy for PE investment. However, the currently adopted Logit regression and one-factor ANOVA models are not suitable for analyzing nonlinear investment activities, and the investment appraisal does not work well. In this paper, all NEEQ companies that implemented private placement in 2017 are used as the study sample. This paper also empirically analyzes the current situation of domestic private equity investment funds based on BP and Hopfield neural network models, then the results of the two models are compared. It is concluded that the accuracy of the BP neural network model can be more than 90%. So, the BP neural network can be used as the optimal model of private equity investment funds investment strategy in NEEQ.","PeriodicalId":45994,"journal":{"name":"International Journal of Computational Intelligence and Applications","volume":"19 04","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134907508","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}
The microservice architecture breaks through the traditional cluster architecture mode based on virtual machines and uses containers as carriers to interact through lightweight communication mechanisms to reduce system coupling and provide more flexible system service support. With the expansion of the system scale, a large number of system logs with complex structures and chaotic relationships are generated. How to accurately analyze the system logs and make efficient fault prediction is particularly important for building a safe and reliable system. By studying neural network technology, this paper proposes an Attention-Based Bidirectional Long Short-Term Memory Network (Bi-LSTM). Combined with the dual channel convolutional neural network model (DCNN), it uses the attention mechanism to explore the differences between dimensional features, realizes multi-dimensional feature fusion, and establishes a BiLSTM-DCNN deep learning model that integrates the attention mechanism. From the perspective of social network analysis, a data preprocessing method is proposed to process fault redundant data and improve the accuracy of fault prediction under Microservices. Compare BiLSTM-DCNN with the mainstream system log analysis machine learning models SVM, CNN and Bi-LSTM, and explore the advantages of BiLSTM-DCNN in processing microservice system log text. The model is applied to simulation data and HDFS data set for experimental comparison, which proves the good generalization ability and universality of BiLSTM-DCNN.
{"title":"Research on Fault Detection for Microservices Based on Log Information and Social Network Mechanism Using BiLSTM-DCNN Model","authors":"Shuai-Peng Guan, Zi-Hao Chen, Pei-Xuan Wu, Man-Yuan Guo","doi":"10.1142/s1469026823420026","DOIUrl":"https://doi.org/10.1142/s1469026823420026","url":null,"abstract":"The microservice architecture breaks through the traditional cluster architecture mode based on virtual machines and uses containers as carriers to interact through lightweight communication mechanisms to reduce system coupling and provide more flexible system service support. With the expansion of the system scale, a large number of system logs with complex structures and chaotic relationships are generated. How to accurately analyze the system logs and make efficient fault prediction is particularly important for building a safe and reliable system. By studying neural network technology, this paper proposes an Attention-Based Bidirectional Long Short-Term Memory Network (Bi-LSTM). Combined with the dual channel convolutional neural network model (DCNN), it uses the attention mechanism to explore the differences between dimensional features, realizes multi-dimensional feature fusion, and establishes a BiLSTM-DCNN deep learning model that integrates the attention mechanism. From the perspective of social network analysis, a data preprocessing method is proposed to process fault redundant data and improve the accuracy of fault prediction under Microservices. Compare BiLSTM-DCNN with the mainstream system log analysis machine learning models SVM, CNN and Bi-LSTM, and explore the advantages of BiLSTM-DCNN in processing microservice system log text. The model is applied to simulation data and HDFS data set for experimental comparison, which proves the good generalization ability and universality of BiLSTM-DCNN.","PeriodicalId":45994,"journal":{"name":"International Journal of Computational Intelligence and Applications","volume":"34 12","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134906971","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}
Pub Date : 2023-09-26DOI: 10.1142/s146902682350027x
Ouiem Bchir, Mohamed Maher Ben Ismail
The effectiveness of machine learning approaches depends on the quality of the data representation. In fact, some representations may mislead such learning approaches upon concealing relevant explanatory variables. Although feature engineering, that utilizes domain knowledge and/or expert supervision, yields typical data representation techniques, generic unsupervised feature learning represents an even more objective alternative to determine relevant attributes and generate optimal feature spaces. In this paper, we propose a new fuzzy unsupervised feature learning approach (FUL) that automatically derives new features by revealing the intrinsic structure of the data. In fact, FUL exploits the clusters and the associated fuzzy memberships generated by a fuzzy C-means algorithm, and devises new basis functions and their corresponding representation. The experiments results showed that FUL overtakes relevant state of the art approaches. It yielded the highest F1-measure with an improvement of 8%, 11%, 3%, and 4% on Parkinson, Epilepsy, Gait, and breast cancer datasets, respectively.
{"title":"A Novel Fuzzy Unsupervised Feature Learning Approach","authors":"Ouiem Bchir, Mohamed Maher Ben Ismail","doi":"10.1142/s146902682350027x","DOIUrl":"https://doi.org/10.1142/s146902682350027x","url":null,"abstract":"The effectiveness of machine learning approaches depends on the quality of the data representation. In fact, some representations may mislead such learning approaches upon concealing relevant explanatory variables. Although feature engineering, that utilizes domain knowledge and/or expert supervision, yields typical data representation techniques, generic unsupervised feature learning represents an even more objective alternative to determine relevant attributes and generate optimal feature spaces. In this paper, we propose a new fuzzy unsupervised feature learning approach (FUL) that automatically derives new features by revealing the intrinsic structure of the data. In fact, FUL exploits the clusters and the associated fuzzy memberships generated by a fuzzy C-means algorithm, and devises new basis functions and their corresponding representation. The experiments results showed that FUL overtakes relevant state of the art approaches. It yielded the highest F1-measure with an improvement of 8%, 11%, 3%, and 4% on Parkinson, Epilepsy, Gait, and breast cancer datasets, respectively.","PeriodicalId":45994,"journal":{"name":"International Journal of Computational Intelligence and Applications","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134959984","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}
Pub Date : 2023-08-22DOI: 10.1142/s1469026823500268
Lathika P, D. S. Singh
In recent years, rainfall prediction has received major attention in research areas because of its demanding applications in pollution control management and flood control management. Despite having numerous learning-based approaches to calculate future rainfall trends, it remains inefficient to predict rainfall occurrences by learning linear and nonlinear data patterns of historical weather information (i.e., exact prediction value is complicated to be predicted). These complications are addressed with the evolution of stochastic models which have a greater ability to minimize prediction bias and represent long-term weather variability. Therefore, this paper proposes a novel modified stochastic fuzzy Aquila (MSFA) algorithm to make precise predictions regarding future trends by evaluating rainfall time series data. The proposed MSFA algorithm is applied in rainfall prediction applications in evaluating the effectiveness of the proposed stochastic model. Here, 10 features of the open weather dataset collected from Tamil Nadu are provided as input for the proposed rainfall prediction design. The data inconsistencies such as undesirable format and missing values are structured using preprocessing procedures, namely data arrangement, null value removal, and data partitioning. The preprocessed data are fed into the proposed MSFA algorithm which learns the data features more precisely and predicts the probable occurrence of rainfall. To evaluate the performances of the proposed MSFA algorithm, the metrics such as mean absolute error (MAE), coefficient of determination, root mean squared logarithmic error (RMSLE), and root mean square error (RMSE) are analyzed. The experimental results illustrate that the proposed MSFA algorithm achieves superior performance in terms of all metrics.
{"title":"A Modified Stochastic Model for Rainfall Prediction Using Fuzzy Aquila Optimization","authors":"Lathika P, D. S. Singh","doi":"10.1142/s1469026823500268","DOIUrl":"https://doi.org/10.1142/s1469026823500268","url":null,"abstract":"In recent years, rainfall prediction has received major attention in research areas because of its demanding applications in pollution control management and flood control management. Despite having numerous learning-based approaches to calculate future rainfall trends, it remains inefficient to predict rainfall occurrences by learning linear and nonlinear data patterns of historical weather information (i.e., exact prediction value is complicated to be predicted). These complications are addressed with the evolution of stochastic models which have a greater ability to minimize prediction bias and represent long-term weather variability. Therefore, this paper proposes a novel modified stochastic fuzzy Aquila (MSFA) algorithm to make precise predictions regarding future trends by evaluating rainfall time series data. The proposed MSFA algorithm is applied in rainfall prediction applications in evaluating the effectiveness of the proposed stochastic model. Here, 10 features of the open weather dataset collected from Tamil Nadu are provided as input for the proposed rainfall prediction design. The data inconsistencies such as undesirable format and missing values are structured using preprocessing procedures, namely data arrangement, null value removal, and data partitioning. The preprocessed data are fed into the proposed MSFA algorithm which learns the data features more precisely and predicts the probable occurrence of rainfall. To evaluate the performances of the proposed MSFA algorithm, the metrics such as mean absolute error (MAE), coefficient of determination, root mean squared logarithmic error (RMSLE), and root mean square error (RMSE) are analyzed. The experimental results illustrate that the proposed MSFA algorithm achieves superior performance in terms of all metrics.","PeriodicalId":45994,"journal":{"name":"International Journal of Computational Intelligence and Applications","volume":" ","pages":""},"PeriodicalIF":1.8,"publicationDate":"2023-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45877038","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}
Pub Date : 2023-08-22DOI: 10.1142/s1469026823500256
Ruiming Wen, Jian Wang, Yuanlun Xie, Wenhong Tian
In recent years, the rapid development of mobile devices and embedded system raises a demand for intelligent models to address increasingly complicated problems. However, the complexity of the structure and extensive parameters press significantly on efficiency, storage space, and energy consumption. Additionally, the explosive growth of tasks with enormous model structures and parameters makes it impossible to compress models manually. Thus, a standardized and effective model compression solution achieving lightweight neural networks is established as an urgent demand by the industry. Accordingly, Dynamic Channel Ranking Strategy (DCRS) method is proposed to compress deep convolutional neural networks. DCRS selects channels with high contribution of each prunable layer according to compression ratio searched by reinforcement learning agent. Compared with current model compression methods, DCRS efficaciously applies various channel ranking strategies on prunable layers. Experiments indicate with a 50% compression ratio, compressed MobileNet achieved 70.62% top1 and 88.2% top5 accuracy on ImageNet, and compressed ResNet achieved 92.03% accuracy on CIFAR-10. DCRS reduces more FLOPS in these neural networks. The compressed model achieves the best Top-1 and Top-5 accuracy on ResNet50, the best Top-1 accuracy on MobilNetV1.
{"title":"A CNN Compression Method via Dynamic Channel Ranking Strategy","authors":"Ruiming Wen, Jian Wang, Yuanlun Xie, Wenhong Tian","doi":"10.1142/s1469026823500256","DOIUrl":"https://doi.org/10.1142/s1469026823500256","url":null,"abstract":"In recent years, the rapid development of mobile devices and embedded system raises a demand for intelligent models to address increasingly complicated problems. However, the complexity of the structure and extensive parameters press significantly on efficiency, storage space, and energy consumption. Additionally, the explosive growth of tasks with enormous model structures and parameters makes it impossible to compress models manually. Thus, a standardized and effective model compression solution achieving lightweight neural networks is established as an urgent demand by the industry. Accordingly, Dynamic Channel Ranking Strategy (DCRS) method is proposed to compress deep convolutional neural networks. DCRS selects channels with high contribution of each prunable layer according to compression ratio searched by reinforcement learning agent. Compared with current model compression methods, DCRS efficaciously applies various channel ranking strategies on prunable layers. Experiments indicate with a 50% compression ratio, compressed MobileNet achieved 70.62% top1 and 88.2% top5 accuracy on ImageNet, and compressed ResNet achieved 92.03% accuracy on CIFAR-10. DCRS reduces more FLOPS in these neural networks. The compressed model achieves the best Top-1 and Top-5 accuracy on ResNet50, the best Top-1 accuracy on MobilNetV1.","PeriodicalId":45994,"journal":{"name":"International Journal of Computational Intelligence and Applications","volume":" ","pages":""},"PeriodicalIF":1.8,"publicationDate":"2023-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44590082","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}
Pub Date : 2023-08-08DOI: 10.1142/s1469026823500232
Qiang Wu
As the popularity of wireless networks deepens, the diversity of device types and hardware environments makes network data take on heterogeneous forms while the threat of malicious attacks from outside can prevent ordinary methods from mining information from abnormal data. In view of this, the research will be devoted to the feature processing of the anomalous data itself, and the convolutional operation of the anomalous information by the convolutional neural network (CNN). This is to extract the internal information. In the first step of the cascaded CNNs, the dimensions of the anomaly data will be processed, the anomaly data will be sorted under the concept of relevance grouping, and then the sorted results will be added to the convolution and pooling. The performance test uses three datasets with different feature capacities as the attack sources, and the results show a 13.22% improvement in information mining performance compared to the standard CNN. The extended CNN step will perform feature identification for homologous or similar network threats, with feature expansion within the convolutional layer first, and then pooling to reduce the computational cost. The test results show that when the maximum value domain of linear expansion is 2, the model has the best feature recognition performance, fluctuating around 85%; The model comparison test results show that the accuracy of the extended CNN is higher than that of the standard CNN, and the model stability is better than that of the back propagation (BP) neural network. This indicates that the cascaded CNN dual module can mine for the data itself, thus ignoring the risk unknowns, and this connected CNN has some practical significance. The proposed cascaded CNN module applies advanced neural network technology to identify internal and external risk data. The research content has important reference value for the security management of IoT systems.
{"title":"Anomaly Detection Algorithm for Heterogeneous Wireless Networks Based on Cascaded Convolutional Neural Networks","authors":"Qiang Wu","doi":"10.1142/s1469026823500232","DOIUrl":"https://doi.org/10.1142/s1469026823500232","url":null,"abstract":"As the popularity of wireless networks deepens, the diversity of device types and hardware environments makes network data take on heterogeneous forms while the threat of malicious attacks from outside can prevent ordinary methods from mining information from abnormal data. In view of this, the research will be devoted to the feature processing of the anomalous data itself, and the convolutional operation of the anomalous information by the convolutional neural network (CNN). This is to extract the internal information. In the first step of the cascaded CNNs, the dimensions of the anomaly data will be processed, the anomaly data will be sorted under the concept of relevance grouping, and then the sorted results will be added to the convolution and pooling. The performance test uses three datasets with different feature capacities as the attack sources, and the results show a 13.22% improvement in information mining performance compared to the standard CNN. The extended CNN step will perform feature identification for homologous or similar network threats, with feature expansion within the convolutional layer first, and then pooling to reduce the computational cost. The test results show that when the maximum value domain of linear expansion is 2, the model has the best feature recognition performance, fluctuating around 85%; The model comparison test results show that the accuracy of the extended CNN is higher than that of the standard CNN, and the model stability is better than that of the back propagation (BP) neural network. This indicates that the cascaded CNN dual module can mine for the data itself, thus ignoring the risk unknowns, and this connected CNN has some practical significance. The proposed cascaded CNN module applies advanced neural network technology to identify internal and external risk data. The research content has important reference value for the security management of IoT systems.","PeriodicalId":45994,"journal":{"name":"International Journal of Computational Intelligence and Applications","volume":" ","pages":""},"PeriodicalIF":1.8,"publicationDate":"2023-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44148488","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：