There are countless applications of non-linear systems that incorporate delay and algebraic equations. Despite current improvements in control theory, stochastic actuator defects still pose challenges when it comes to these systems. Furthermore, when it is not possible to measure the states of the system, and when uncertainties affect the system under investigation, the problem becomes even more complex. This paper is concerned with fault-tolerant observer-based controller synthesis for non-linear delayed singular systems with uncertainties and stochastic actuator failures. On the basis of interval valued models, a new Lyapunov-Krasovskii functional is built to develop a less conservative criterion to ensure that the closed-loop system is admissible in the mean-square sense. In addition, as these matrices are coupled with multiple variables, finding the parametric matrices of the observer and controller in terms of the obtained condition is more complex and challenging. The proposed method employs the matrix inequality decoupling technique to resolve this issue. Eventually, simulations are carried out to demonstrate the applicability of the proposed method.
{"title":"Observer-based feedback control of interval-valued fuzzy singular system with time-varying delay and stochastic faults","authors":"H. Jerbi, M. Kchaou, Obaid S. Alshammari, Rabeh Abassi, D. Popescu","doi":"10.15837/ijccc.2022.6.4957","DOIUrl":"https://doi.org/10.15837/ijccc.2022.6.4957","url":null,"abstract":"There are countless applications of non-linear systems that incorporate delay and algebraic equations. Despite current improvements in control theory, stochastic actuator defects still pose challenges when it comes to these systems. Furthermore, when it is not possible to measure the states of the system, and when uncertainties affect the system under investigation, the problem becomes even more complex. This paper is concerned with fault-tolerant observer-based controller synthesis for non-linear delayed singular systems with uncertainties and stochastic actuator failures. On the basis of interval valued models, a new Lyapunov-Krasovskii functional is built to develop a less conservative criterion to ensure that the closed-loop system is admissible in the mean-square sense. In addition, as these matrices are coupled with multiple variables, finding the parametric matrices of the observer and controller in terms of the obtained condition is more complex and challenging. The proposed method employs the matrix inequality decoupling technique to resolve this issue. Eventually, simulations are carried out to demonstrate the applicability of the proposed method.","PeriodicalId":179619,"journal":{"name":"Int. J. Comput. Commun. Control","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132979981","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}
Digital technology has drastically transformed businesses’ activities, operations, and processes. Today, digital efficiencies have inspired companies to take initiatives to leverage the firm’s environmental performance. The study’s primary purpose was to examine how a digital transformation strategy affects environmental performance under the mediating role of innovation capabilities and moderating role of digital organizational culture. The data was obtained from manufacturing industry employees in Pakistan. The results reveal that digital transformation strategy (DTS) positively and significantly affects innovation capabilities and environmental performance. The link between digital transformation and environmental performance is mediated by innovation capabilities, while digital organizational culture moderates the relationship between innovation capabilities and environmental performance.
{"title":"Digital Transformation Strategy and Environmental Performance: A Case Study","authors":"M. Sarfraz, Zhixiao Ye, Florin Dragan, L. Ivașcu, A. Artene","doi":"10.15837/ijccc.2022.6.5029","DOIUrl":"https://doi.org/10.15837/ijccc.2022.6.5029","url":null,"abstract":"Digital technology has drastically transformed businesses’ activities, operations, and processes. Today, digital efficiencies have inspired companies to take initiatives to leverage the firm’s environmental performance. The study’s primary purpose was to examine how a digital transformation strategy affects environmental performance under the mediating role of innovation capabilities and moderating role of digital organizational culture. The data was obtained from manufacturing industry employees in Pakistan. The results reveal that digital transformation strategy (DTS) positively and significantly affects innovation capabilities and environmental performance. The link between digital transformation and environmental performance is mediated by innovation capabilities, while digital organizational culture moderates the relationship between innovation capabilities and environmental performance.","PeriodicalId":179619,"journal":{"name":"Int. J. Comput. Commun. Control","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115859170","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}
Stock research is an important field of Finance and time series research. Stock data research is also a typical financial time series problem. In the research of financial time series, there are many methods, such as model building, data mining, heuristic algorithm, machine learning, deep learning, and so on. VAR, ARIMA and other methods are widely used in practice. ARIMA and its combination methods have good processing effect on small data sets, but there are over fitting problems, which are difficult to process large data sets and data with different time granularity. At present, this paper takes the decision table transformation method of financial time series data as the research object, and puts forward the trend division method of financial time series based on different time granularity through the trend division of financial time series. On this basis, it puts forward the trend extreme point extraction method, and constructs the stock time series decision table according to the extreme point information and combined with the stock technical indicators, The decision table is verified by support vector machine based on the decision table. The research shows that the trend division method under different time granularity can transform the extreme point information into a decision table, which will not produce over fitting problem in practical application. It is an effective time series processing method, and provides a new research method for the future time series research with different granularity.
{"title":"A financial time series data mining method with different time granularity based on trend Division","authors":"Haining Yang, Xuedong Gao, L. Han, Wei Cui","doi":"10.15837/ijccc.2022.6.4952","DOIUrl":"https://doi.org/10.15837/ijccc.2022.6.4952","url":null,"abstract":"Stock research is an important field of Finance and time series research. Stock data research is also a typical financial time series problem. In the research of financial time series, there are many methods, such as model building, data mining, heuristic algorithm, machine learning, deep learning, and so on. VAR, ARIMA and other methods are widely used in practice. ARIMA and its combination methods have good processing effect on small data sets, but there are over fitting problems, which are difficult to process large data sets and data with different time granularity. At present, this paper takes the decision table transformation method of financial time series data as the research object, and puts forward the trend division method of financial time series based on different time granularity through the trend division of financial time series. On this basis, it puts forward the trend extreme point extraction method, and constructs the stock time series decision table according to the extreme point information and combined with the stock technical indicators, The decision table is verified by support vector machine based on the decision table. The research shows that the trend division method under different time granularity can transform the extreme point information into a decision table, which will not produce over fitting problem in practical application. It is an effective time series processing method, and provides a new research method for the future time series research with different granularity.","PeriodicalId":179619,"journal":{"name":"Int. J. Comput. Commun. Control","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129974523","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}
Solid-state data storage is becoming a widely accepted technology and is looking for new ways to provide cost-effective solutions across various information systems. Solid-state drives (SSDs), existing in different types and models, have several sustainable features: storage, dimensions, volume, etc. Due to the wide range of attributes, designing a robust method can easily select from the purchaser/retailer/wholesaler point of view. This work offers a joint multi-criteria decision-making (MCDM) to rank SSD alternatives, and a newly developed approach, namely Measurement Alternatives and Ranking according to the Compromise Solution (MARCOS) technique, is utilised, and a comparative investigation has also been achieved with other MCDM methods. Data of separate SSDs have been collected from the Indian market with twenty-six different models of eleven brands. The Bonferroni operator (BFO) allocates and compiles the objective weights using the Entropy weights technique (EWT), the Criteria Importance through Inter criteria Correlation (CRITIC) and the Method based on the Removal Effects of Criteria (MEREC). The sensitivity analysis using objective weights considering 18 scenarios was performed, and analysis with the Standard deviation shows that the joint MCDM possesses high accuracy and robustness. The results achieved have been tested with Spearman’s rank and Wojciech-Salabun (WS) coefficient, and the first rank goes to SSD-7. The presented results benefit the manufacturers to understand the market requirement better and for the consumer to make a wise decision while purchasing SSD. It also offers future scope for applying the proposed methodology in similar areas, social sciences and engineering, to make complex decisions.
{"title":"A New Joint Strategy for Multi-Criteria Decision-Making: A Case Study for Prioritizing Solid-State Drive","authors":"Raman Kumar, Pankaj Goel, E. Zavadskas, Željko Stević, V. Vujovic","doi":"10.15837/ijccc.2022.6.5010","DOIUrl":"https://doi.org/10.15837/ijccc.2022.6.5010","url":null,"abstract":"Solid-state data storage is becoming a widely accepted technology and is looking for new ways to provide cost-effective solutions across various information systems. Solid-state drives (SSDs), existing in different types and models, have several sustainable features: storage, dimensions, volume, etc. Due to the wide range of attributes, designing a robust method can easily select from the purchaser/retailer/wholesaler point of view. This work offers a joint multi-criteria decision-making (MCDM) to rank SSD alternatives, and a newly developed approach, namely Measurement Alternatives and Ranking according to the Compromise Solution (MARCOS) technique, is utilised, and a comparative investigation has also been achieved with other MCDM methods. Data of separate SSDs have been collected from the Indian market with twenty-six different models of eleven brands. The Bonferroni operator (BFO) allocates and compiles the objective weights using the Entropy weights technique (EWT), the Criteria Importance through Inter criteria Correlation (CRITIC) and the Method based on the Removal Effects of Criteria (MEREC). The sensitivity analysis using objective weights considering 18 scenarios was performed, and analysis with the Standard deviation shows that the joint MCDM possesses high accuracy and robustness. The results achieved have been tested with Spearman’s rank and Wojciech-Salabun (WS) coefficient, and the first rank goes to SSD-7. The presented results benefit the manufacturers to understand the market requirement better and for the consumer to make a wise decision while purchasing SSD. It also offers future scope for applying the proposed methodology in similar areas, social sciences and engineering, to make complex decisions.","PeriodicalId":179619,"journal":{"name":"Int. J. Comput. Commun. Control","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121857960","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}
Fog computing is a viewpoint that expands on the Cloud stage concept by placing processing assets at the organization’s edges. It might be described as a cloud-like platform with comparable data, computation, storage, and applications. They are unique in that they are decentralized in nature. Data protection and route analysis of time-sensitive data are made easier using fog computing. This minimizes the volume and distance of data sent to the cloud, lowering the risk of security and privacy breaches in IoT applications. When it comes to security and privacy, fog computing confronts several issues. The constraints of fog computing resources are the root of these difficulties. The fog system, in fact, may raise new security and privacy concerns. To address these challenges, cryptography is used in conjunction with key management techniques to provide safe data transfer. A Minimal Resource Viterbi based Bi-level Secured Key Generation (MRV-BSKG) technique for a secured fog-based system is proposed to compromise the security level and computational complexity. The BSKG technique, which combines Lagrange’s Key Generation (LKG) and the Location-Based Key (LBK) generation approaches, can safeguard secrecy and integrity. In comparison to the previous techniques, the new MRV, BSKG, delivers security with improved outcomes.
{"title":"Bi-Level Minimal Resource Protected Key Generation Framework For Fog Computing Applications","authors":"A. P, Bharathi.R","doi":"10.15837/ijccc.2022.6.4363","DOIUrl":"https://doi.org/10.15837/ijccc.2022.6.4363","url":null,"abstract":"Fog computing is a viewpoint that expands on the Cloud stage concept by placing processing assets at the organization’s edges. It might be described as a cloud-like platform with comparable data, computation, storage, and applications. They are unique in that they are decentralized in nature. Data protection and route analysis of time-sensitive data are made easier using fog computing. This minimizes the volume and distance of data sent to the cloud, lowering the risk of security and privacy breaches in IoT applications. When it comes to security and privacy, fog computing confronts several issues. The constraints of fog computing resources are the root of these difficulties. The fog system, in fact, may raise new security and privacy concerns. To address these challenges, cryptography is used in conjunction with key management techniques to provide safe data transfer. A Minimal Resource Viterbi based Bi-level Secured Key Generation (MRV-BSKG) technique for a secured fog-based system is proposed to compromise the security level and computational complexity. The BSKG technique, which combines Lagrange’s Key Generation (LKG) and the Location-Based Key (LBK) generation approaches, can safeguard secrecy and integrity. In comparison to the previous techniques, the new MRV, BSKG, delivers security with improved outcomes.","PeriodicalId":179619,"journal":{"name":"Int. J. Comput. Commun. Control","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131648801","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 collaborative (or sharing) economy continues to shape the tourism industry, challenging both the traditional areas of supply, but especially the trust and digital skills of users, the acceptance of platforms and new inter-personal and community relationships. In the present paper a crosssectional quantitative research was conducted with non-random convenience sampling in order to determine the impact of the collaborative Airbnb platform among Romanian tourists, how wellknown it is and what elements motivate tourists to choose this platform. We also want to analyse the extent to which the benefits and innovations brought by this new phenomenon are in line with the needs and expectations of tourists and whether they are interested in this phenomenon, the extent to which tourists have chosen the Airbnb platform to stay in Romania or abroad.
{"title":"Digitalisation and the sharing economy. A survey-based research on Airbnb in Romania","authors":"A. Badulescu, D. Badulescu, R. Simuț, Elena Herte, Afrodita Borma, Ionut Pandelica","doi":"10.15837/ijccc.2022.6.5004","DOIUrl":"https://doi.org/10.15837/ijccc.2022.6.5004","url":null,"abstract":"The collaborative (or sharing) economy continues to shape the tourism industry, challenging both the traditional areas of supply, but especially the trust and digital skills of users, the acceptance of platforms and new inter-personal and community relationships. In the present paper a crosssectional quantitative research was conducted with non-random convenience sampling in order to determine the impact of the collaborative Airbnb platform among Romanian tourists, how wellknown it is and what elements motivate tourists to choose this platform. We also want to analyse the extent to which the benefits and innovations brought by this new phenomenon are in line with the needs and expectations of tourists and whether they are interested in this phenomenon, the extent to which tourists have chosen the Airbnb platform to stay in Romania or abroad.","PeriodicalId":179619,"journal":{"name":"Int. J. Comput. Commun. Control","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114591021","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 term "smart agriculture" refers to a management concept that is centered on industrial agriculture. It makes use of cutting-edge technologies such as big data, cloud, and the Internet of Things to monitor, automate, and evaluate agricultural operations. Smart agriculture is a management concept. Software and sensors are used in smart agriculture, also known as precision agriculture. Smart agriculture is managed by the software. This pa-per proposes the development of low-cost environment parameters and electrical quantities monitoring device. According to the findings, such Internet of Things devices are suited for digitizing the relevant data in order to ac-quire information that may help farmers make optimal changes.
{"title":"Smart Agriculture: IoT-based Greenhouse Monitoring System","authors":"A. Simo, S. Dzitac, G. Badea, D. Meianu","doi":"10.15837/ijccc.2022.6.5039","DOIUrl":"https://doi.org/10.15837/ijccc.2022.6.5039","url":null,"abstract":"The term \"smart agriculture\" refers to a management concept that is centered on industrial agriculture. It makes use of cutting-edge technologies such as big data, cloud, and the Internet of Things to monitor, automate, and evaluate agricultural operations. Smart agriculture is a management concept. Software and sensors are used in smart agriculture, also known as precision agriculture. Smart agriculture is managed by the software. This pa-per proposes the development of low-cost environment parameters and electrical quantities monitoring device. According to the findings, such Internet of Things devices are suited for digitizing the relevant data in order to ac-quire information that may help farmers make optimal changes.","PeriodicalId":179619,"journal":{"name":"Int. J. Comput. Commun. Control","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126398041","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}
Selecting reasonable suppliers can effectively improve the efficiency of enterprise supply chain management. Among them, expert evaluation is an important part of supplier selection problem, but the uncertainty, fuzziness and incompleteness of expert opinions make supplier selection problem difficult to solve. In order to systematically and effectively solve the uncertainty, ambiguity and incompleteness in supplier selection problem, this paper presents a new supplier selection method based on D numbers and transformation function. First, fuzzy preference relation is generated based on the decision matrix of pairwise comparisons given by experts. D numbers which can effectively deal with uncertain information extend fuzzy preference relation (D matrix). Second, the D matrix is converted into a crisp matrix form based on the integration representation of D numbers according to different situations whether or not the information in D matrix is complete. Third, the crisp matrix is converted into judgement matrix by using the transformation functions. Finally, analytic hierarchy process (AHP) method is applied based on the judgment matrix to give a priority weights for decision making. Three numerical examples and application of the supplier selection are used to show the feasibility and effectiveness of the proposed method.
{"title":"Supplier Selection Model Based on D Numbers and Transformation Function","authors":"Leihui Xiong, Xiaoyan Su, Hong Qian","doi":"10.15837/ijccc.2022.5.4468","DOIUrl":"https://doi.org/10.15837/ijccc.2022.5.4468","url":null,"abstract":"Selecting reasonable suppliers can effectively improve the efficiency of enterprise supply chain management. Among them, expert evaluation is an important part of supplier selection problem, but the uncertainty, fuzziness and incompleteness of expert opinions make supplier selection problem difficult to solve. In order to systematically and effectively solve the uncertainty, ambiguity and incompleteness in supplier selection problem, this paper presents a new supplier selection method based on D numbers and transformation function. First, fuzzy preference relation is generated based on the decision matrix of pairwise comparisons given by experts. D numbers which can effectively deal with uncertain information extend fuzzy preference relation (D matrix). Second, the D matrix is converted into a crisp matrix form based on the integration representation of D numbers according to different situations whether or not the information in D matrix is complete. Third, the crisp matrix is converted into judgement matrix by using the transformation functions. Finally, analytic hierarchy process (AHP) method is applied based on the judgment matrix to give a priority weights for decision making. Three numerical examples and application of the supplier selection are used to show the feasibility and effectiveness of the proposed method.","PeriodicalId":179619,"journal":{"name":"Int. J. Comput. Commun. Control","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124712861","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}
Today, satellite imagery is being utilized to help repair and restore societal issues caused by habitats for a variety of scientific studies. Water resource search, environmental protection simulations, meteorological analysis, and soil class analysis may all benefit from the satellite images. The categorization algorithms were used generally and the most appropriate strategies are also be used for analyzing the Satellite image. There are several normal classification mechanisms, such as optimum likelihood, parallel piping or minimum distance classification that have presented in some other existing technologies. But the traditional classification algorithm has some disadvantages. Convolutional neural network (CNN) classification based on CA was implemented in this article. Using the gray level Satellite image as the target and CNN image classification by the CA’s selfiteration mechanism and eventually explores the efficacy and viability of the proposed method in long-term satellite remote sensing image water body classification. Our findings indicate that the proposed method not only has rapid convergence speed, reliability but can also efficiently classify satellite remote sensing images with long-term sequence and reasonable applicability. The proposed technique acquires an accuracy of 91% which is maximum than conventional methods.
{"title":"Efficient Classification of Satellite Image with Hybrid Approach Using CNN-CA","authors":"S. Poonkuntran, V. Abinaya, Manthira Moorthi Subbiah, M. Oza","doi":"10.15837/ijccc.2022.5.4485","DOIUrl":"https://doi.org/10.15837/ijccc.2022.5.4485","url":null,"abstract":"Today, satellite imagery is being utilized to help repair and restore societal issues caused by habitats for a variety of scientific studies. Water resource search, environmental protection simulations, meteorological analysis, and soil class analysis may all benefit from the satellite images. The categorization algorithms were used generally and the most appropriate strategies are also be used for analyzing the Satellite image. There are several normal classification mechanisms, such as optimum likelihood, parallel piping or minimum distance classification that have presented in some other existing technologies. But the traditional classification algorithm has some disadvantages. Convolutional neural network (CNN) classification based on CA was implemented in this article. Using the gray level Satellite image as the target and CNN image classification by the CA’s selfiteration mechanism and eventually explores the efficacy and viability of the proposed method in long-term satellite remote sensing image water body classification. Our findings indicate that the proposed method not only has rapid convergence speed, reliability but can also efficiently classify satellite remote sensing images with long-term sequence and reasonable applicability. The proposed technique acquires an accuracy of 91% which is maximum than conventional methods.","PeriodicalId":179619,"journal":{"name":"Int. J. Comput. Commun. Control","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132936768","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}
Image classification is usually done using deep learning algorithms. Deep learning architectures are set deterministically. The aim of this paper is to propose an evolutionary computation paradigm that optimises a deep learning neural network’s architecture. A set of chromosomes are randomly generated, after which selection, recombination, and mutation are applied. At each generation the fittest chromosomes are kept. The best chromosome from the last generation determines the deep learning architecture. We have tested our method on a second trimester fetal morphology database. The proposed model is statistically compared with DenseNet201 and ResNet50, proving its competitiveness.
{"title":"Evolutionary Computation Paradigm to Determine Deep Neural Networks Architectures","authors":"R. Ivanescu, Smaranda Belciug, Andrei Nascu, M. Serbanescu, D. Iliescu","doi":"10.15837/ijccc.2022.5.4886","DOIUrl":"https://doi.org/10.15837/ijccc.2022.5.4886","url":null,"abstract":"\u0000\u0000\u0000Image classification is usually done using deep learning algorithms. Deep learning architectures are set deterministically. The aim of this paper is to propose an evolutionary computation paradigm that optimises a deep learning neural network’s architecture. A set of chromosomes are randomly generated, after which selection, recombination, and mutation are applied. At each generation the fittest chromosomes are kept. The best chromosome from the last generation determines the deep learning architecture. We have tested our method on a second trimester fetal morphology database. The proposed model is statistically compared with DenseNet201 and ResNet50, proving its competitiveness.\u0000\u0000\u0000","PeriodicalId":179619,"journal":{"name":"Int. J. Comput. Commun. Control","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130860677","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：