Abstract With the rapid development of social informatization, the Internet has become an important channel for global information dissemination. The wireless network space and the real space are intertwined and have a significant impact on the political, economic, and cultural aspects of international society. For example, it can effectively solve the problem of information exchange between cities, regions, and countries. Wireless network crime and wireless network space security issues involve the development of information technology in various countries and, more importantly, involve all aspects of national security. In the age of science and technology, the current situation of cybercrime can be expressed by data as follows: the online crime rate is high. According to relevant statistics, nearly 5 million Internet users are involved in various cases every year due to the use of the Internet. This article starts with the digital forensics of wireless network crime and wireless network security management systems and discusses the composition, characteristics, existing problems, and future development directions of the current wireless network security management system. By comparing the wireless network security laws of China and the United States, using the latent Dirichlet allocation (LDA)-Gibbs model and the k-means algorithm to analyze the data, this article provides guidance for future research on wireless network space governance. The combination of digital forensics analysis based on cybercrime and space governance can improve the level of public security work. At present, the world has made some progress in cyberspace, but it still faces severe challenges. In the face of new situations and new measures, it is necessary to strengthen legislation, improve relevant systems, and strengthen supervision capacity. At the same time, it is necessary to establish perfect technical means and safeguards to ensure that this goal can be achieved.
{"title":"Digital forensics analysis based on cybercrime and the study of the rule of law in space governance","authors":"Cheng Chen, Bin Dong","doi":"10.1515/comp-2022-0266","DOIUrl":"https://doi.org/10.1515/comp-2022-0266","url":null,"abstract":"Abstract With the rapid development of social informatization, the Internet has become an important channel for global information dissemination. The wireless network space and the real space are intertwined and have a significant impact on the political, economic, and cultural aspects of international society. For example, it can effectively solve the problem of information exchange between cities, regions, and countries. Wireless network crime and wireless network space security issues involve the development of information technology in various countries and, more importantly, involve all aspects of national security. In the age of science and technology, the current situation of cybercrime can be expressed by data as follows: the online crime rate is high. According to relevant statistics, nearly 5 million Internet users are involved in various cases every year due to the use of the Internet. This article starts with the digital forensics of wireless network crime and wireless network security management systems and discusses the composition, characteristics, existing problems, and future development directions of the current wireless network security management system. By comparing the wireless network security laws of China and the United States, using the latent Dirichlet allocation (LDA)-Gibbs model and the k-means algorithm to analyze the data, this article provides guidance for future research on wireless network space governance. The combination of digital forensics analysis based on cybercrime and space governance can improve the level of public security work. At present, the world has made some progress in cyberspace, but it still faces severe challenges. In the face of new situations and new measures, it is necessary to strengthen legislation, improve relevant systems, and strengthen supervision capacity. At the same time, it is necessary to establish perfect technical means and safeguards to ensure that this goal can be achieved.","PeriodicalId":43014,"journal":{"name":"Open Computer Science","volume":null,"pages":null},"PeriodicalIF":1.5,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44947025","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}
Abstract Blockchain technology is a widely used emerging technology. It can integrate cloud computing technology and big data to form a distributed cloud computing system, providing efficient services for local enterprises and governments. In addition, local cloud computing is also widely used, and there are many big data in these applications. Blockchain and local cloud computing technology offers safe and reliable information exchange for data exchange and provides a practical method for analyzing big data. This article aims to study how to analyze and research the application analysis method of big data based on blockchain technology and improve the classical apriori algorithm (CAA). This article compares and analyzes the performance of CAA and improved apriori algorithm (IAA) in big data applications. When the number of key words in the query are 20 and 100, the result search time of the CAA are 1.08 and 9.24 s, respectively, and the IAA are 0.76 and 7.58 s, respectively. The result search cost of the CAA is 12.43 and 91.55 kB, respectively, and the IAA is 5.05 and 63.72 kB, respectively. It is not difficult to see that applying the IAA to the blockchain-based government data-sharing scheme had relatively excellent performance and was worth further promotion and application.
{"title":"Blockchain localization cloud computing big data application evaluation method","authors":"Lin Xu","doi":"10.1515/comp-2023-0281","DOIUrl":"https://doi.org/10.1515/comp-2023-0281","url":null,"abstract":"Abstract Blockchain technology is a widely used emerging technology. It can integrate cloud computing technology and big data to form a distributed cloud computing system, providing efficient services for local enterprises and governments. In addition, local cloud computing is also widely used, and there are many big data in these applications. Blockchain and local cloud computing technology offers safe and reliable information exchange for data exchange and provides a practical method for analyzing big data. This article aims to study how to analyze and research the application analysis method of big data based on blockchain technology and improve the classical apriori algorithm (CAA). This article compares and analyzes the performance of CAA and improved apriori algorithm (IAA) in big data applications. When the number of key words in the query are 20 and 100, the result search time of the CAA are 1.08 and 9.24 s, respectively, and the IAA are 0.76 and 7.58 s, respectively. The result search cost of the CAA is 12.43 and 91.55 kB, respectively, and the IAA is 5.05 and 63.72 kB, respectively. It is not difficult to see that applying the IAA to the blockchain-based government data-sharing scheme had relatively excellent performance and was worth further promotion and application.","PeriodicalId":43014,"journal":{"name":"Open Computer Science","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135952845","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}
Abstract In the year 2019, during the month of December, the first case of SARS-CoV-2 was reported in China. As per reports, the virus started spreading from a wet market in the Wuhan City. The person infected with the virus is diagnosed with cough and fever, and in some rare occasions, the person suffers from breathing inabilities. The highly contagious nature of this corona virus disease (COVID-19) caused the rapid outbreak of the disease around the world. India contracted the disease from China and reported its first case on January 30, 2020, in Kerala. Despite several counter measures taken by Government, India like other countries could not restrict the outbreak of the epidemic. However, it is believed that the strict policies adopted by the Indian Government have slowed the rate of the epidemic to a certain extent. This article proposes an adaptive SEIR disease model and a sequence-to-sequence (Seq2Seq) learning model to predict the future trend of COVID-19 outbreak in India and analyze the performance of these models. Optimization of hyper parameters using RMSProp is done to obtain an efficient model with lower convergence time. This article focuses on evaluating the performance of deep learning networks and epidemiological models in predicting a pandemic outbreak.
{"title":"Predicting and monitoring COVID-19 epidemic trends in India using sequence-to-sequence model and an adaptive SEIR model","authors":"K. D. Gupta, R. Dwivedi, D. Sharma","doi":"10.1515/comp-2020-0221","DOIUrl":"https://doi.org/10.1515/comp-2020-0221","url":null,"abstract":"Abstract In the year 2019, during the month of December, the first case of SARS-CoV-2 was reported in China. As per reports, the virus started spreading from a wet market in the Wuhan City. The person infected with the virus is diagnosed with cough and fever, and in some rare occasions, the person suffers from breathing inabilities. The highly contagious nature of this corona virus disease (COVID-19) caused the rapid outbreak of the disease around the world. India contracted the disease from China and reported its first case on January 30, 2020, in Kerala. Despite several counter measures taken by Government, India like other countries could not restrict the outbreak of the epidemic. However, it is believed that the strict policies adopted by the Indian Government have slowed the rate of the epidemic to a certain extent. This article proposes an adaptive SEIR disease model and a sequence-to-sequence (Seq2Seq) learning model to predict the future trend of COVID-19 outbreak in India and analyze the performance of these models. Optimization of hyper parameters using RMSProp is done to obtain an efficient model with lower convergence time. This article focuses on evaluating the performance of deep learning networks and epidemiological models in predicting a pandemic outbreak.","PeriodicalId":43014,"journal":{"name":"Open Computer Science","volume":null,"pages":null},"PeriodicalIF":1.5,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43410520","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}
Rao Nadeem, R. Latif, Khalid Hussain, N. Jhanjhi, M. Humayun
Abstract GSD is a Global software development environment where data are distributed to more than two sites. These sites may be located on national or continental borders. Every year it expands its development volume, which has become a trend for the software development business. Because of increasing demand, it has become a common type of business. The value of offshore software development has increased immensely. According to the recent predictions, one-quarter of US software-related business shifts offshore, including integration and management-related services. GSD helps explore resources from other countries, increasing knowledge and enhancing operational efficiency. Therefore, globalization has changed the development nature of software. Different organizations face several challenges, such as coordination and requirement ambiguity, during the change management process in GSD. Traceability accommodates these changes in forward and backward direction. However, it gives rise to several challenges like less client involvement because of its distributed nature and challenging to manage the requirement ambiguity due to increased cost. Therefore, the Flexible Framework for Requirement Management (FFRM) must handle the abovementioned issues.
{"title":"A flexible framework for requirement management (FFRM) from software architecture toward distributed agile framework","authors":"Rao Nadeem, R. Latif, Khalid Hussain, N. Jhanjhi, M. Humayun","doi":"10.1515/comp-2022-0239","DOIUrl":"https://doi.org/10.1515/comp-2022-0239","url":null,"abstract":"Abstract GSD is a Global software development environment where data are distributed to more than two sites. These sites may be located on national or continental borders. Every year it expands its development volume, which has become a trend for the software development business. Because of increasing demand, it has become a common type of business. The value of offshore software development has increased immensely. According to the recent predictions, one-quarter of US software-related business shifts offshore, including integration and management-related services. GSD helps explore resources from other countries, increasing knowledge and enhancing operational efficiency. Therefore, globalization has changed the development nature of software. Different organizations face several challenges, such as coordination and requirement ambiguity, during the change management process in GSD. Traceability accommodates these changes in forward and backward direction. However, it gives rise to several challenges like less client involvement because of its distributed nature and challenging to manage the requirement ambiguity due to increased cost. Therefore, the Flexible Framework for Requirement Management (FFRM) must handle the abovementioned issues.","PeriodicalId":43014,"journal":{"name":"Open Computer Science","volume":null,"pages":null},"PeriodicalIF":1.5,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46897474","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}
Abstract Making a rapid unpredictable decision from N N choices of unequal value is a common control task. When the cost of predictability can be modelled as a penalty hidden under a single option by an intelligent adversary, then an optimal strategy can be found efficiently in O ( N log N ) Oleft(Nlog N) steps using an approach described by Sakaguchi for a zero-sum hide-search game. In this work, we extend this to two games with multiple parallel predictions, either coordinated or drawn independently from the optimal distribution, both of which can be solved with the same scaling. An open-source code is provided online at https://github.com/pec27/rams.
{"title":"Two hide-search games with rapid strategies for multiple parallel searches","authors":"P. Creasey","doi":"10.1515/comp-2022-0243","DOIUrl":"https://doi.org/10.1515/comp-2022-0243","url":null,"abstract":"Abstract Making a rapid unpredictable decision from N N choices of unequal value is a common control task. When the cost of predictability can be modelled as a penalty hidden under a single option by an intelligent adversary, then an optimal strategy can be found efficiently in O ( N log N ) Oleft(Nlog N) steps using an approach described by Sakaguchi for a zero-sum hide-search game. In this work, we extend this to two games with multiple parallel predictions, either coordinated or drawn independently from the optimal distribution, both of which can be solved with the same scaling. An open-source code is provided online at https://github.com/pec27/rams.","PeriodicalId":43014,"journal":{"name":"Open Computer Science","volume":null,"pages":null},"PeriodicalIF":1.5,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43648659","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}
Abstract In view of the current development trend of the smart medical industry in the context of the internet of things, this study conducts an evolutionary game analysis on information technology providers, medical institutions, digital medical equipment providers, and medical regulatory agencies in the smart medical industry. This study also analyzes the stable state of the future development of the smart medical industry and performs simulation calculations through MATLAB software. The research results show that the overall development trend of the smart medical industry structure in the future is consistent with the development trend of each industry structure. Under the strategic background of the supervision of medical regulatory agencies, information technology providers and digital medical equipment providers, respectively, provide the smart medical industry with the latest information technology and digital medical equipment to ensure the technical support of the smart medical industry. The smart medical industry provides corresponding medical talents and medical equipment to ensure the demand for talents and equipment of the smart medical industry, so that the structure of the smart medical industry can continuously improve the level of smart medical technology in the future development and ultimately promote the overall development of the smart medical industry.
{"title":"Research on the structure of smart medical industry based on the background of the internet of things","authors":"Luhong Zhang, Kai Zhou, Weibin Zhao, Huiyan Zhou","doi":"10.1515/comp-2022-0247","DOIUrl":"https://doi.org/10.1515/comp-2022-0247","url":null,"abstract":"Abstract In view of the current development trend of the smart medical industry in the context of the internet of things, this study conducts an evolutionary game analysis on information technology providers, medical institutions, digital medical equipment providers, and medical regulatory agencies in the smart medical industry. This study also analyzes the stable state of the future development of the smart medical industry and performs simulation calculations through MATLAB software. The research results show that the overall development trend of the smart medical industry structure in the future is consistent with the development trend of each industry structure. Under the strategic background of the supervision of medical regulatory agencies, information technology providers and digital medical equipment providers, respectively, provide the smart medical industry with the latest information technology and digital medical equipment to ensure the technical support of the smart medical industry. The smart medical industry provides corresponding medical talents and medical equipment to ensure the demand for talents and equipment of the smart medical industry, so that the structure of the smart medical industry can continuously improve the level of smart medical technology in the future development and ultimately promote the overall development of the smart medical industry.","PeriodicalId":43014,"journal":{"name":"Open Computer Science","volume":null,"pages":null},"PeriodicalIF":1.5,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45569149","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}
Abstract The rapid development of mobile communication technology not only brings convenience and fun to our life, but also brings a series of problems such as privacy disclosure. Therefore, it is very necessary to study the privacy protection method based on location service to strengthen the security of location privacy. The purpose of this work is to improve the security of location privacy and prevent the disclosure of user privacy by studying the characteristics of location services and privacy protection methods. This article first describes the characteristics of the important location privacy protection law, and then studies the structural characteristics and operation process of the location privacy protection law. This work evaluates the advantages and disadvantages of different methods, and finally compares the performance of several privacy protection algorithms through experimental analysis. Through the research of hiding space method, two-level cache method based on user grid, differential privacy protection method and experimental analysis of the algorithm, an effective privacy protection algorithm can be obtained. It can better protect the location privacy of users. For example, dual-active in the hidden space algorithm has the best privacy protection performance. Compared with other algorithms, the success rate of generating hidden space is increased by more than 10%, and the time of generating hidden space is shortened by about a quarter. The algorithm It has certain practical value and significance for use in the privacy protection of users.
{"title":"Privacy protection methods of location services in big data","authors":"Wenfeng Liu, Juanjuan Wu, Zhong Xi","doi":"10.1515/comp-2022-0250","DOIUrl":"https://doi.org/10.1515/comp-2022-0250","url":null,"abstract":"Abstract The rapid development of mobile communication technology not only brings convenience and fun to our life, but also brings a series of problems such as privacy disclosure. Therefore, it is very necessary to study the privacy protection method based on location service to strengthen the security of location privacy. The purpose of this work is to improve the security of location privacy and prevent the disclosure of user privacy by studying the characteristics of location services and privacy protection methods. This article first describes the characteristics of the important location privacy protection law, and then studies the structural characteristics and operation process of the location privacy protection law. This work evaluates the advantages and disadvantages of different methods, and finally compares the performance of several privacy protection algorithms through experimental analysis. Through the research of hiding space method, two-level cache method based on user grid, differential privacy protection method and experimental analysis of the algorithm, an effective privacy protection algorithm can be obtained. It can better protect the location privacy of users. For example, dual-active in the hidden space algorithm has the best privacy protection performance. Compared with other algorithms, the success rate of generating hidden space is increased by more than 10%, and the time of generating hidden space is shortened by about a quarter. The algorithm It has certain practical value and significance for use in the privacy protection of users.","PeriodicalId":43014,"journal":{"name":"Open Computer Science","volume":null,"pages":null},"PeriodicalIF":1.5,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48821902","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}
Saman Shojae Chaeikar, A. Ahmadi, Sasan Karamizadeh, Nakisa Shoja Chaeikar
Abstract For a secure data transmission in symmetric cryptography, data are encrypted and decrypted using an identical key. The process of creating, distributing, storing, deploying, and finally revoking the symmetric keys is called key management. Many key management schemes are devised that each one is suitable for a specific range of applications. However, these schemes have some common drawbacks like the hardness of key generation and distribution, key storage, attacks, and traffic load. In this article, a key management framework is proposed, which is attack resistant and transforms the current customary key management workflow to enhance security and reduce weaknesses. The main features of the proposed framework are eliminating key storage, smart attack resistant feature, reducing multiple-times key distribution to just one-time interpreter distribution, and having short key intervals – minutely, hourly, and daily. Moreover, the key revocation process happens automatically and with no revocation call.
{"title":"SIKM – a smart cryptographic key management framework","authors":"Saman Shojae Chaeikar, A. Ahmadi, Sasan Karamizadeh, Nakisa Shoja Chaeikar","doi":"10.1515/comp-2020-0167","DOIUrl":"https://doi.org/10.1515/comp-2020-0167","url":null,"abstract":"Abstract For a secure data transmission in symmetric cryptography, data are encrypted and decrypted using an identical key. The process of creating, distributing, storing, deploying, and finally revoking the symmetric keys is called key management. Many key management schemes are devised that each one is suitable for a specific range of applications. However, these schemes have some common drawbacks like the hardness of key generation and distribution, key storage, attacks, and traffic load. In this article, a key management framework is proposed, which is attack resistant and transforms the current customary key management workflow to enhance security and reduce weaknesses. The main features of the proposed framework are eliminating key storage, smart attack resistant feature, reducing multiple-times key distribution to just one-time interpreter distribution, and having short key intervals – minutely, hourly, and daily. Moreover, the key revocation process happens automatically and with no revocation call.","PeriodicalId":43014,"journal":{"name":"Open Computer Science","volume":null,"pages":null},"PeriodicalIF":1.5,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43788922","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}
A. Al-Gindy, Aya AlChikh Omar, Omar Mashal, Y. Shaker, E. Alhogaraty, S. Moussa
Abstract With the advent of high-speed broadband Internet access, the need to protect digital videos is highly recommended. The main objective of this study is to propose an adaptive algorithm for watermarked digital videos in the frequency domain based on discrete cosine transform (DCT). The watermark signature image is embedded into the whole frame of the video. The green channel of the RGB frame is selected for the embedding process using the DCT algorithm as it shows the recommended quality of the watermarked frames. The experiment results indicate that the proposed algorithm shows robustness and high quality of the watermarked videos by testing various strength values ∆ for different videos. It offers resistance against different types of attacks.
{"title":"A new watermarking scheme for digital videos using DCT","authors":"A. Al-Gindy, Aya AlChikh Omar, Omar Mashal, Y. Shaker, E. Alhogaraty, S. Moussa","doi":"10.1515/comp-2022-0238","DOIUrl":"https://doi.org/10.1515/comp-2022-0238","url":null,"abstract":"Abstract With the advent of high-speed broadband Internet access, the need to protect digital videos is highly recommended. The main objective of this study is to propose an adaptive algorithm for watermarked digital videos in the frequency domain based on discrete cosine transform (DCT). The watermark signature image is embedded into the whole frame of the video. The green channel of the RGB frame is selected for the embedding process using the DCT algorithm as it shows the recommended quality of the watermarked frames. The experiment results indicate that the proposed algorithm shows robustness and high quality of the watermarked videos by testing various strength values ∆ for different videos. It offers resistance against different types of attacks.","PeriodicalId":43014,"journal":{"name":"Open Computer Science","volume":null,"pages":null},"PeriodicalIF":1.5,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48068680","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}
Abstract Millions of people across the world are suffering from diabetic retinopathy. This disease majorly affects the retina of the eye, and if not identified priorly causes permanent blindness. Hence, detecting diabetic retinopathy at an early stage is very important to safeguard people from blindness. Several machine learning (ML) algorithms are implemented on the dataset of diabetic retinopathy available in the UCI ML repository to detect the symptoms of diabetic retinopathy. But, most of those algorithms are implemented individually. Hence, this article proposes an effective integrated ML approach that uses the support vector machine (SVM), principal component analysis (PCA), and moth-flame optimization techniques. Initially, the ML algorithms decision tree (DT), SVM, random forest (RF), and Naïve Bayes (NB) are applied to the diabetic retinopathy dataset. Among these, the SVM algorithm is outperformed with an average of 76.96% performance. Later, all the aforementioned ML algorithms are implemented by integrating the PCA technique to reduce the dimensions of the dataset. After integrating PCA, it is noticed that the performance of the algorithms NB, RF, and SVM is reduced dramatically; on the contrary, the performance of DT is increased. To improve the performance of ML algorithms, the moth-flame optimization technique is integrated with SVM and PCA. This proposed approach is outperformed with an average of 85.61% performance among all the other considered ML algorithms, and the classification of class labels is achieved correctly.
{"title":"An effective integrated machine learning approach for detecting diabetic retinopathy","authors":"Penikalapati Pragathi, Agastyaraju Nagaraja Rao","doi":"10.1515/comp-2020-0222","DOIUrl":"https://doi.org/10.1515/comp-2020-0222","url":null,"abstract":"Abstract Millions of people across the world are suffering from diabetic retinopathy. This disease majorly affects the retina of the eye, and if not identified priorly causes permanent blindness. Hence, detecting diabetic retinopathy at an early stage is very important to safeguard people from blindness. Several machine learning (ML) algorithms are implemented on the dataset of diabetic retinopathy available in the UCI ML repository to detect the symptoms of diabetic retinopathy. But, most of those algorithms are implemented individually. Hence, this article proposes an effective integrated ML approach that uses the support vector machine (SVM), principal component analysis (PCA), and moth-flame optimization techniques. Initially, the ML algorithms decision tree (DT), SVM, random forest (RF), and Naïve Bayes (NB) are applied to the diabetic retinopathy dataset. Among these, the SVM algorithm is outperformed with an average of 76.96% performance. Later, all the aforementioned ML algorithms are implemented by integrating the PCA technique to reduce the dimensions of the dataset. After integrating PCA, it is noticed that the performance of the algorithms NB, RF, and SVM is reduced dramatically; on the contrary, the performance of DT is increased. To improve the performance of ML algorithms, the moth-flame optimization technique is integrated with SVM and PCA. This proposed approach is outperformed with an average of 85.61% performance among all the other considered ML algorithms, and the classification of class labels is achieved correctly.","PeriodicalId":43014,"journal":{"name":"Open Computer Science","volume":null,"pages":null},"PeriodicalIF":1.5,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43846044","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：