{"_links":{"self":{"href":"https:\/\/peerj.com\/articles\/index.json?journal=cs"},"next":{"href":"https:\/\/peerj.com\/articles\/index.json?journal=cs&page=2"},"alternate":{"atom":{"type":"application\/atom+xml","href":"https:\/\/peerj.com\/articles\/index.atom"},"rss1":{"type":"application\/rdf+xml","href":"https:\/\/peerj.com\/articles\/index.rss1"},"rss2":{"type":"application\/rss+xml","href":"https:\/\/peerj.com\/articles\/index.rss2"},"rss3":{"type":"text\/plain","href":"https:\/\/peerj.com\/articles\/index.rss3"},"html":{"type":"text\/html","href":"https:\/\/peerj.com\/articles\/index.html"}}},"_items":[{"title":"Visual resource extraction and artistic communication model design based on improved CycleGAN algorithm","date":"2024-03-18","doi":"10.7717\/peerj-cs.1889","language":"en","pdf_url":"https:\/\/peerj.com\/articles\/cs-1889.pdf","fulltext_html_url":"https:\/\/peerj.com\/articles\/cs-1889","volume":"10","firstpage":"e1889","author":["Anyu Yang","Muhammad Kashif Hanif"],"author_institution":["International School of Arts, Dalian University of Foreign Languages, Dalian, Liaoning, China","Department of Computer Science, Government College University, Faisalabad, Pakistan"],"author_email":"y13941124025@163.com","authors":"Yang, Anyu; Kashif Hanif, Muhammad","author_institutions":"International School of Arts, Dalian University of Foreign Languages, Dalian, Liaoning, China; Department of Computer Science, Government College University, Faisalabad, Pakistan","keywords":["GAN","CycleGAN","Attention mechanism","Image style migration","Visual resource and artistic communication"],"journal_title":"PeerJ Computer Science","journal_abbrev":"PeerJ Comput. Sci.","publisher":"PeerJ Inc.","issn":"2376-5992","description":"Through the application of computer vision and deep learning methodologies, real-time style transfer of images becomes achievable. This process involves the fusion of diverse artistic elements into a single image, resulting in the creation of innovative pieces of art. This article centers its focus on image style transfer within the realm of art education and introduces an ATT-CycleGAN model enriched with an attention mechanism to enhance the quality and precision of style conversion. The framework enhances the generators within CycleGAN. At first, images undergo encoder downsampling before entering the intermediate transformation model. In this intermediate transformation model, feature maps are acquired through four encoding residual blocks, which are subsequently input into an attention module. Channel attention is incorporated through multi-weight optimization achieved via global max-pooling and global average-pooling techniques. During the model\u2019s training process, transfer learning techniques are employed to improve model parameter initialization, enhancing training efficiency. Experimental results demonstrate the superior performance of the proposed model in image style transfer across various categories. In comparison to the traditional CycleGAN model, it exhibits a notable increase in structural similarity index measure (SSIM) and peak signal-to-noise ratio (PSNR) metrics. Specifically, on the Places365 and selfi2anime datasets, compared with the traditional CycleGAN model, SSIM is increased by 3.19% and 1.31% respectively, and PSNR is increased by 10.16% and 5.02% respectively. These findings provide valuable algorithmic support and crucial references for future research in the fields of art education, image segmentation, and style transfer.","description-html":"\n
Through the application of computer vision and deep learning methodologies, real-time style transfer of images becomes achievable. This process involves the fusion of diverse artistic elements into a single image, resulting in the creation of innovative pieces of art. This article centers its focus on image style transfer within the realm of art education and introduces an ATT-CycleGAN model enriched with an attention mechanism to enhance the quality and precision of style conversion. The framework enhances the generators within CycleGAN. At first, images undergo encoder downsampling before entering the intermediate transformation model. In this intermediate transformation model, feature maps are acquired through four encoding residual blocks, which are subsequently input into an attention module. Channel attention is incorporated through multi-weight optimization achieved via<\/i> global max-pooling and global average-pooling techniques. During the model\u2019s training process, transfer learning techniques are employed to improve model parameter initialization, enhancing training efficiency. Experimental results demonstrate the superior performance of the proposed model in image style transfer across various categories. In comparison to the traditional CycleGAN model, it exhibits a notable increase in structural similarity index measure (SSIM) and peak signal-to-noise ratio (PSNR) metrics. Specifically, on the Places365 and selfi2anime datasets, compared with the traditional CycleGAN model, SSIM is increased by 3.19% and 1.31% respectively, and PSNR is increased by 10.16% and 5.02% respectively. These findings provide valuable algorithmic support and crucial references for future research in the fields of art education, image segmentation, and style transfer.<\/p>\n ","title-html":"Visual resource extraction and artistic communication model design based on improved CycleGAN algorithm","subjects":["Algorithms and Analysis of Algorithms","Artificial Intelligence","Data Mining and Machine Learning","Neural Networks"],"identifiers":{"peerj":"cs-1889","pubmed":null,"pmc":null},"@context":"http:\/\/static.peerj.com\/context\/citation\/context.json","@type":"http:\/\/schema.org\/ScholarlyArticle","@id":"https:\/\/peerj.com\/articles\/cs-1889","_links":{"self":{"href":"https:\/\/peerj.com\/articles\/cs-1889.json"},"alternate":{"html":{"type":"text\/html","href":"https:\/\/peerj.com\/articles\/cs-1889.html"},"xml":{"type":"application\/xml","href":"https:\/\/peerj.com\/articles\/cs-1889.xml"},"pdf":{"type":"application\/pdf","href":"https:\/\/peerj.com\/articles\/cs-1889.pdf"},"rdf":{"type":"application\/rdf+xml","href":"https:\/\/peerj.com\/articles\/cs-1889.rdf"},"ris":{"type":"application\/x-research-info-systems","href":"https:\/\/peerj.com\/articles\/cs-1889.ris"},"bib":{"type":"application\/x-bibtex","href":"https:\/\/peerj.com\/articles\/cs-1889.bib"},"citeproc":{"type":"application\/vnd.citationstyles.csl+json","href":"https:\/\/peerj.com\/articles\/cs-1889.citeproc"},"bibjson":{"type":"application\/bibjson+json","href":"https:\/\/peerj.com\/articles\/cs-1889.bibjson"},"unixref":{"type":"application\/unixref+xml","href":"https:\/\/peerj.com\/articles\/cs-1889.unixref"}}}},{"title":"Performance discrepancy mitigation in heart disease prediction for multisensory inter-datasets","date":"2024-03-18","doi":"10.7717\/peerj-cs.1917","language":"en","pdf_url":"https:\/\/peerj.com\/articles\/cs-1917.pdf","fulltext_html_url":"https:\/\/peerj.com\/articles\/cs-1917","volume":"10","firstpage":"e1917","author":["Mahmudul Hasan","Md Abdus Sahid","Md Palash Uddin","Md Abu Marjan","Seifedine Kadry","Jungeun Kim"],"author_institution":["Department of Computer Science and Engineering, Hajee Mohammad Danesh Science and Technology University, Dinajpur, Bangladesh","School of Information Technology, Deakin University, Geelong, VIC, Australia","Department of Computer Science and Engineering, Hajee Mohammad Danesh Science and Technology University, Dinajpur, Bangladesh","Department of Computer Science and Engineering, Hajee Mohammad Danesh Science and Technology University, Dinajpur, Bangladesh","School of Information Technology, Deakin University, Geelong, VIC, Australia","Department of Computer Science and Engineering, Hajee Mohammad Danesh Science and Technology University, Dinajpur, Bangladesh","Department of Electrical and Computer Engineering, Lebanese American University, Byblos, Lebanon","Department of Applied Data Science, Noroff University College, Kristiansand, Norway","Artificial Intelligence Research Center (AIRC), Ajman University, Ajman, Norway","MEU Research Unit, Middle East University, Amman, Jordan","Department of Software, Kongju National University, Cheonan, Republic of South Korea"],"author_email":["palash_cse@hstu.ac.bd","jekim@kongju.ac.kr"],"authors":"Hasan, Mahmudul; Sahid, Md Abdus; Uddin, Md Palash; Marjan, Md Abu; Kadry, Seifedine; Kim, Jungeun","author_institutions":"Department of Computer Science and Engineering, Hajee Mohammad Danesh Science and Technology University, Dinajpur, Bangladesh; School of Information Technology, Deakin University, Geelong, VIC, Australia; Department of Electrical and Computer Engineering, Lebanese American University, Byblos, Lebanon; Department of Applied Data Science, Noroff University College, Kristiansand, Norway; Artificial Intelligence Research Center (AIRC), Ajman University, Ajman, Norway; MEU Research Unit, Middle East University, Amman, Jordan; Department of Software, Kongju National University, Cheonan, Republic of South Korea","keywords":["Inter-dataset","Performance discrepancy","Dimensionality reduction","Heart disease prediction","Machine learning"],"journal_title":"PeerJ Computer Science","journal_abbrev":"PeerJ Comput. Sci.","publisher":"PeerJ Inc.","issn":"2376-5992","description":"Heart disease is one of the primary causes of morbidity and death worldwide. Millions of people have had heart attacks every year, and only early-stage predictions can help to reduce the number. Researchers are working on designing and developing early-stage prediction systems using different advanced technologies, and machine learning (ML) is one of them. Almost all existing ML-based works consider the same dataset (intra-dataset) for the training and validation of their method. In particular, they do not consider inter-dataset performance checks, where different datasets are used in the training and testing phases. In inter-dataset setup, existing ML models show a poor performance named the inter-dataset discrepancy problem. This work focuses on mitigating the inter-dataset discrepancy problem by considering five available heart disease datasets and their combined form. All potential training and testing mode combinations are systematically executed to assess discrepancies before and after applying the proposed methods. Imbalance data handling using SMOTE-Tomek, feature selection using random forest (RF), and feature extraction using principle component analysis (PCA) with a long preprocessing pipeline are used to mitigate the inter-dataset discrepancy problem. The preprocessing pipeline builds on missing value handling using RF regression, log transformation, outlier removal, normalization, and data balancing that convert the datasets to more ML-centric. Support vector machine, K-nearest neighbors, decision tree, RF, eXtreme Gradient Boosting, Gaussian naive Bayes, logistic regression, and multilayer perceptron are used as classifiers. Experimental results show that feature selection and classification using RF produce better results than other combination strategies in both single- and inter-dataset setups. In certain configurations of individual datasets, RF demonstrates 100% accuracy and 96% accuracy during the feature selection phase in an inter-dataset setup, exhibiting commendable precision, recall, F1 score, specificity, and AUC score. The results indicate that an effective preprocessing technique has the potential to improve the performance of the ML model without necessitating the development of intricate prediction models. Addressing inter-dataset discrepancies introduces a novel research avenue, enabling the amalgamation of identical features from various datasets to construct a comprehensive global dataset within a specific domain.","description-html":"\n
Heart disease is one of the primary causes of morbidity and death worldwide. Millions of people have had heart attacks every year, and only early-stage predictions can help to reduce the number. Researchers are working on designing and developing early-stage prediction systems using different advanced technologies, and machine learning (ML) is one of them. Almost all existing ML-based works consider the same dataset (intra-dataset) for the training and validation of their method. In particular, they do not consider inter-dataset performance checks, where different datasets are used in the training and testing phases. In inter-dataset setup, existing ML models show a poor performance named the inter-dataset discrepancy problem. This work focuses on mitigating the inter-dataset discrepancy problem by considering five available heart disease datasets and their combined form. All potential training and testing mode combinations are systematically executed to assess discrepancies before and after applying the proposed methods. Imbalance data handling using SMOTE-Tomek, feature selection using random forest (RF), and feature extraction using principle component analysis (PCA) with a long preprocessing pipeline are used to mitigate the inter-dataset discrepancy problem. The preprocessing pipeline builds on missing value handling using RF regression, log transformation, outlier removal, normalization, and data balancing that convert the datasets to more ML-centric. Support vector machine, K-nearest neighbors, decision tree, RF, eXtreme Gradient Boosting, Gaussian naive Bayes, logistic regression, and multilayer perceptron are used as classifiers. Experimental results show that feature selection and classification using RF produce better results than other combination strategies in both single- and inter-dataset setups. In certain configurations of individual datasets, RF demonstrates 100% accuracy and 96% accuracy during the feature selection phase in an inter-dataset setup, exhibiting commendable precision, recall, F1 score, specificity, and AUC score. The results indicate that an effective preprocessing technique has the potential to improve the performance of the ML model without necessitating the development of intricate prediction models. Addressing inter-dataset discrepancies introduces a novel research avenue, enabling the amalgamation of identical features from various datasets to construct a comprehensive global dataset within a specific domain.<\/p>\n","title-html":"Performance discrepancy mitigation in heart disease prediction for multisensory inter-datasets","subjects":["Bioinformatics","Computer Vision","Data Mining and Machine Learning"],"identifiers":{"peerj":"cs-1917","pubmed":null,"pmc":null},"@context":"http:\/\/static.peerj.com\/context\/citation\/context.json","@type":"http:\/\/schema.org\/ScholarlyArticle","@id":"https:\/\/peerj.com\/articles\/cs-1917","_links":{"self":{"href":"https:\/\/peerj.com\/articles\/cs-1917.json"},"alternate":{"html":{"type":"text\/html","href":"https:\/\/peerj.com\/articles\/cs-1917.html"},"xml":{"type":"application\/xml","href":"https:\/\/peerj.com\/articles\/cs-1917.xml"},"pdf":{"type":"application\/pdf","href":"https:\/\/peerj.com\/articles\/cs-1917.pdf"},"rdf":{"type":"application\/rdf+xml","href":"https:\/\/peerj.com\/articles\/cs-1917.rdf"},"ris":{"type":"application\/x-research-info-systems","href":"https:\/\/peerj.com\/articles\/cs-1917.ris"},"bib":{"type":"application\/x-bibtex","href":"https:\/\/peerj.com\/articles\/cs-1917.bib"},"citeproc":{"type":"application\/vnd.citationstyles.csl+json","href":"https:\/\/peerj.com\/articles\/cs-1917.citeproc"},"bibjson":{"type":"application\/bibjson+json","href":"https:\/\/peerj.com\/articles\/cs-1917.bibjson"},"unixref":{"type":"application\/unixref+xml","href":"https:\/\/peerj.com\/articles\/cs-1917.unixref"}}}},{"title":"The reconstruction of equivalent underlying model based on direct causality for multivariate time series","date":"2024-03-18","doi":"10.7717\/peerj-cs.1922","language":"en","pdf_url":"https:\/\/peerj.com\/articles\/cs-1922.pdf","fulltext_html_url":"https:\/\/peerj.com\/articles\/cs-1922","volume":"10","firstpage":"e1922","author":["Liyang Xu","Dezheng Wang"],"author_institution":["Liangjiang International College, Chongqing University of Technology, Chongqing, China","Big Data and Artificial Intelligence College, Chongqing Institute of Engineering, Chongqing, China","School of Automation, Southeast University, Nanjing, China"],"author_email":"wangdezheng@seu.edu.cn","authors":"Xu, Liyang; Wang, Dezheng","author_institutions":"Liangjiang International College, Chongqing University of Technology, Chongqing, China; Big Data and Artificial Intelligence College, Chongqing Institute of Engineering, Chongqing, China; School of Automation, Southeast University, Nanjing, China","keywords":["Reconstruction","Direct causality","Multivariate time series","Equivalent expression"],"journal_title":"PeerJ Computer Science","journal_abbrev":"PeerJ Comput. Sci.","publisher":"PeerJ Inc.","issn":"2376-5992","description":"This article presents a novel approach for reconstructing an equivalent underlying model and deriving a precise equivalent expression through the use of direct causality topology. Central to this methodology is the transfer entropy method, which is instrumental in revealing the causality topology. The polynomial fitting method is then applied to determine the coefficients and intrinsic order of the causality structure, leveraging the foundational elements extracted from the direct causality topology. Notably, this approach efficiently discovers the core topology from the data, reducing redundancy without requiring prior domain-specific knowledge. Furthermore, it yields a precise equivalent model expression, offering a robust foundation for further analysis and exploration in various fields. Additionally, the proposed model for reconstructing an equivalent underlying framework demonstrates strong forecasting capabilities in multivariate time series scenarios.","description-html":"\n
This article presents a novel approach for reconstructing an equivalent underlying model and deriving a precise equivalent expression through the use of direct causality topology. Central to this methodology is the transfer entropy method, which is instrumental in revealing the causality topology. The polynomial fitting method is then applied to determine the coefficients and intrinsic order of the causality structure, leveraging the foundational elements extracted from the direct causality topology. Notably, this approach efficiently discovers the core topology from the data, reducing redundancy without requiring prior domain-specific knowledge. Furthermore, it yields a precise equivalent model expression, offering a robust foundation for further analysis and exploration in various fields. Additionally, the proposed model for reconstructing an equivalent underlying framework demonstrates strong forecasting capabilities in multivariate time series scenarios.<\/p>\n ","title-html":"The reconstruction of equivalent underlying model based on direct causality for multivariate time series","subjects":["Algorithms and Analysis of Algorithms","Data Mining and Machine Learning","Data Science"],"identifiers":{"peerj":"cs-1922","pubmed":null,"pmc":null},"@context":"http:\/\/static.peerj.com\/context\/citation\/context.json","@type":"http:\/\/schema.org\/ScholarlyArticle","@id":"https:\/\/peerj.com\/articles\/cs-1922","_links":{"self":{"href":"https:\/\/peerj.com\/articles\/cs-1922.json"},"alternate":{"html":{"type":"text\/html","href":"https:\/\/peerj.com\/articles\/cs-1922.html"},"xml":{"type":"application\/xml","href":"https:\/\/peerj.com\/articles\/cs-1922.xml"},"pdf":{"type":"application\/pdf","href":"https:\/\/peerj.com\/articles\/cs-1922.pdf"},"rdf":{"type":"application\/rdf+xml","href":"https:\/\/peerj.com\/articles\/cs-1922.rdf"},"ris":{"type":"application\/x-research-info-systems","href":"https:\/\/peerj.com\/articles\/cs-1922.ris"},"bib":{"type":"application\/x-bibtex","href":"https:\/\/peerj.com\/articles\/cs-1922.bib"},"citeproc":{"type":"application\/vnd.citationstyles.csl+json","href":"https:\/\/peerj.com\/articles\/cs-1922.citeproc"},"bibjson":{"type":"application\/bibjson+json","href":"https:\/\/peerj.com\/articles\/cs-1922.bibjson"},"unixref":{"type":"application\/unixref+xml","href":"https:\/\/peerj.com\/articles\/cs-1922.unixref"}}}},{"title":"Sensor-based systems for the measurement of Functional Reach Test results: a systematic review","date":"2024-03-15","doi":"10.7717\/peerj-cs.1823","language":"en","pdf_url":"https:\/\/peerj.com\/articles\/cs-1823.pdf","fulltext_html_url":"https:\/\/peerj.com\/articles\/cs-1823","volume":"10","firstpage":"e1823","author":["Lu\u00eds Francisco","Jo\u00e3o Duarte","Ant\u00f3nio Nunes Godinho","Eftim Zdravevski","Carlos Albuquerque","Ivan Miguel Pires","Paulo Jorge Coelho"],"author_institution":["School of Technology and Management, Polytechnic University of Leiria, Leiria, Portugal","School of Technology and Management, Polytechnic University of Leiria, Leiria, Portugal","Coimbra Institute of Engineering, Polytechnic of Coimbra, Coimbra, Portugal","Faculty of Computer Science and Engineering, University of Sts. Cyril and Methodius, Skopje, North Macedonia","Child Studies Research Center (CIEC), University of Minho, Braga, Portugal","Higher School of Health, Polytechnic Institute of Viseu, Viseu, Portugal","Nursing School of Coimbra (ESEnfC), Health Sciences Research Unit: Nursing (UICISA: E), Coimbra, Portugal","Instituto de Telecomunica\u00e7\u00f5es, Escola Superior de Tecnologia e Gest\u00e3o de \u00c1gueda, Universidade de Aveiro, \u00c1gueda, Portugal","School of Technology and Management, Polytechnic University of Leiria, Leiria, Portugal","Institute for Systems Engineering and Computers at Coimbra (INESC Coimbra), Coimbra, Portugal"],"author_email":"paulo.coelho@ipleiria.pt","authors":"Francisco, Lu\u00eds; Duarte, Jo\u00e3o; Godinho, Ant\u00f3nio Nunes; Zdravevski, Eftim; Albuquerque, Carlos; Pires, Ivan Miguel; Coelho, Paulo Jorge","author_institutions":"School of Technology and Management, Polytechnic University of Leiria, Leiria, Portugal; Coimbra Institute of Engineering, Polytechnic of Coimbra, Coimbra, Portugal; Faculty of Computer Science and Engineering, University of Sts. Cyril and Methodius, Skopje, North Macedonia; Child Studies Research Center (CIEC), University of Minho, Braga, Portugal; Higher School of Health, Polytechnic Institute of Viseu, Viseu, Portugal; Nursing School of Coimbra (ESEnfC), Health Sciences Research Unit: Nursing (UICISA: E), Coimbra, Portugal; Instituto de Telecomunica\u00e7\u00f5es, Escola Superior de Tecnologia e Gest\u00e3o de \u00c1gueda, Universidade de Aveiro, \u00c1gueda, Portugal; Institute for Systems Engineering and Computers at Coimbra (INESC Coimbra), Coimbra, Portugal","keywords":["Functional Reach Test","Sensors","Technological devices","Physical diseases","Systematic Review","Ambient Assisted Living"],"journal_title":"PeerJ Computer Science","journal_abbrev":"PeerJ Comput. Sci.","publisher":"PeerJ Inc.","issn":"2376-5992","description":"The measurement of Functional Reach Test (FRT) is a widely used assessment tool in various fields, including physical therapy, rehabilitation, and geriatrics. This test evaluates a person\u2019s balance, mobility, and functional ability to reach forward while maintaining stability. Recently, there has been a growing interest in utilizing sensor-based systems to objectively and accurately measure FRT results. This systematic review was performed in various scientific databases or publishers, including PubMed Central, IEEE Explore, Elsevier, Springer, the Multidisciplinary Digital Publishing Institute (MDPI), and the Association for Computing Machinery (ACM), and considered studies published between January 2017 and October 2022, related to methods for the automation of the measurement of the Functional Reach Test variables and results with sensors. Camera-based devices and motion-based sensors are used for Functional Reach Tests, with statistical models extracting meaningful information. Sensor-based systems offer several advantages over traditional manual measurement techniques, as they can provide objective and precise measurements of the reach distance, quantify postural sway, and capture additional parameters related to the movement.","description-html":"\n
The measurement of Functional Reach Test (FRT) is a widely used assessment tool in various fields, including physical therapy, rehabilitation, and geriatrics. This test evaluates a person\u2019s balance, mobility, and functional ability to reach forward while maintaining stability. Recently, there has been a growing interest in utilizing sensor-based systems to objectively and accurately measure FRT results. This systematic review was performed in various scientific databases or publishers, including PubMed Central, IEEE Explore, Elsevier, Springer, the Multidisciplinary Digital Publishing Institute (MDPI), and the Association for Computing Machinery (ACM), and considered studies published between January 2017 and October 2022, related to methods for the automation of the measurement of the Functional Reach Test variables and results with sensors. Camera-based devices and motion-based sensors are used for Functional Reach Tests, with statistical models extracting meaningful information. Sensor-based systems offer several advantages over traditional manual measurement techniques, as they can provide objective and precise measurements of the reach distance, quantify postural sway, and capture additional parameters related to the movement.<\/p>\n ","title-html":"Sensor-based systems for the measurement of Functional Reach Test results: a systematic review","subjects":["Bioinformatics","Mobile and Ubiquitous Computing"],"identifiers":{"peerj":"cs-1823","pubmed":null,"pmc":null},"@context":"http:\/\/static.peerj.com\/context\/citation\/context.json","@type":"http:\/\/schema.org\/ScholarlyArticle","@id":"https:\/\/peerj.com\/articles\/cs-1823","_links":{"self":{"href":"https:\/\/peerj.com\/articles\/cs-1823.json"},"alternate":{"html":{"type":"text\/html","href":"https:\/\/peerj.com\/articles\/cs-1823.html"},"xml":{"type":"application\/xml","href":"https:\/\/peerj.com\/articles\/cs-1823.xml"},"pdf":{"type":"application\/pdf","href":"https:\/\/peerj.com\/articles\/cs-1823.pdf"},"rdf":{"type":"application\/rdf+xml","href":"https:\/\/peerj.com\/articles\/cs-1823.rdf"},"ris":{"type":"application\/x-research-info-systems","href":"https:\/\/peerj.com\/articles\/cs-1823.ris"},"bib":{"type":"application\/x-bibtex","href":"https:\/\/peerj.com\/articles\/cs-1823.bib"},"citeproc":{"type":"application\/vnd.citationstyles.csl+json","href":"https:\/\/peerj.com\/articles\/cs-1823.citeproc"},"bibjson":{"type":"application\/bibjson+json","href":"https:\/\/peerj.com\/articles\/cs-1823.bibjson"},"unixref":{"type":"application\/unixref+xml","href":"https:\/\/peerj.com\/articles\/cs-1823.unixref"}}}},{"title":"Blockchain based general data protection regulation compliant data breach detection system","date":"2024-03-15","doi":"10.7717\/peerj-cs.1882","language":"en","pdf_url":"https:\/\/peerj.com\/articles\/cs-1882.pdf","fulltext_html_url":"https:\/\/peerj.com\/articles\/cs-1882","volume":"10","firstpage":"e1882","author":["Kainat Ansar","Mansoor Ahmed","Saif Ur Rehman Malik","Markus Helfert","Jungsuk Kim"],"author_institution":["Department of Computer Science, COMSATS University Islamabad, Islamabad, Pakistan","ADAPT Centre, Innovation Value Institute, Maynooth University, Maynooth, Ireland","Information Security Institute, Cybernetica AS, Tallinn, Estonia","ADAPT Centre, Innovation Value Institute, Maynooth University, Maynooth, Ireland","Cellico Company R&D Lab, Seungnam-si, Gyeonggi-do, Republic of South Korea","Department of Biomedical Engineering, Gachon University, Incheon, Republic of South Korea"],"author_email":"jungsuk@gachon.ac.kr","authors":"Ansar, Kainat; Ahmed, Mansoor; Malik, Saif Ur Rehman; Helfert, Markus; Kim, Jungsuk","author_institutions":"Department of Computer Science, COMSATS University Islamabad, Islamabad, Pakistan; ADAPT Centre, Innovation Value Institute, Maynooth University, Maynooth, Ireland; Information Security Institute, Cybernetica AS, Tallinn, Estonia; Cellico Company R&D Lab, Seungnam-si, Gyeonggi-do, Republic of South Korea; Department of Biomedical Engineering, Gachon University, Incheon, Republic of South Korea","keywords":["Data breach detection","General data protection regulation compliance","Blockchain","Smart contract"],"journal_title":"PeerJ Computer Science","journal_abbrev":"PeerJ Comput. Sci.","publisher":"PeerJ Inc.","issn":"2376-5992","description":"Context Data breaches caused by insiders are on the rise, both in terms of frequency and financial impact on organizations. Insider threat originates from within the targeted organization and users with authorized access to an organization\u2019s network, applications, or databases commit insider attacks. Motivation Insider attacks are difficult to detect because an attacker with administrator capabilities can change logs and login records to destroy the evidence of the attack. Moreover, when such a harmful insider attack goes undetected for months, it can do a lot of damage. Such data breaches may significantly impact the affected data owner\u2019s life. Developing a system for rapidly detecting data breaches is still critical and challenging. General Data Protection Regulation (GDPR) has defined the procedures and policies to mitigate the problems of data protection. Therefore, under the GDPR implementation, the data controller must notify the data protection authority when a data breach has occurred. Problem Statement Existing data breach detection mechanisms rely on a reliable third party. Because of the presence of a third party, such systems are not trustworthy, transparent, secure, immutable, and GDPR-compliant. Contributions To overcome these issues, this study proposed a GDPR-compliant data breach detection system by leveraging the benefits of blockchain technology. Smart contracts are written in Solidity and deployed on a local Ethereum test network to implement the solution. The proposed system can generate alert notifications against every data breach. Results We tested and deployed our proposed system, and the findings indicate that it can accomplish the insider threat mitigation objective. Furthermore, the GDPR compliance analysis of our system was also evaluated to make sure that it complies with the GDPR principles (such as right to be forgotten, access control, conditions for consent, and breach notifications). The conducted analysis has confirmed that the proposed system offers capabilities to comply with the GDPR from an application standpoint.","description-html":"\n Data breaches caused by insiders are on the rise, both in terms of frequency and financial impact on organizations. Insider threat originates from within the targeted organization and users with authorized access to an organization\u2019s network, applications, or databases commit insider attacks.<\/p>\n <\/section>\n Insider attacks are difficult to detect because an attacker with administrator capabilities can change logs and login records to destroy the evidence of the attack. Moreover, when such a harmful insider attack goes undetected for months, it can do a lot of damage. Such data breaches may significantly impact the affected data owner\u2019s life. Developing a system for rapidly detecting data breaches is still critical and challenging. General Data Protection Regulation (GDPR) has defined the procedures and policies to mitigate the problems of data protection. Therefore, under the GDPR implementation, the data controller must notify the data protection authority when a data breach has occurred.<\/p>\n <\/section>\n Existing data breach detection mechanisms rely on a reliable third party. Because of the presence of a third party, such systems are not trustworthy, transparent, secure, immutable, and GDPR-compliant.<\/p>\n <\/section>\n To overcome these issues, this study proposed a GDPR-compliant data breach detection system by leveraging the benefits of blockchain technology. Smart contracts are written in Solidity and deployed on a local Ethereum test network to implement the solution. The proposed system can generate alert notifications against every data breach.<\/p>\n <\/section>\n We tested and deployed our proposed system, and the findings indicate that it can accomplish the insider threat mitigation objective. Furthermore, the GDPR compliance analysis of our system was also evaluated to make sure that it complies with the GDPR principles (such as right to be forgotten, access control, conditions for consent, and breach notifications). The conducted analysis has confirmed that the proposed system offers capabilities to comply with the GDPR from an application standpoint.<\/p>\n <\/section>\n ","title-html":"Blockchain based general data protection regulation compliant data breach detection system","subjects":["Security and Privacy","Blockchain"],"identifiers":{"peerj":"cs-1882","pubmed":null,"pmc":null},"@context":"http:\/\/static.peerj.com\/context\/citation\/context.json","@type":"http:\/\/schema.org\/ScholarlyArticle","@id":"https:\/\/peerj.com\/articles\/cs-1882","_links":{"self":{"href":"https:\/\/peerj.com\/articles\/cs-1882.json"},"alternate":{"html":{"type":"text\/html","href":"https:\/\/peerj.com\/articles\/cs-1882.html"},"xml":{"type":"application\/xml","href":"https:\/\/peerj.com\/articles\/cs-1882.xml"},"pdf":{"type":"application\/pdf","href":"https:\/\/peerj.com\/articles\/cs-1882.pdf"},"rdf":{"type":"application\/rdf+xml","href":"https:\/\/peerj.com\/articles\/cs-1882.rdf"},"ris":{"type":"application\/x-research-info-systems","href":"https:\/\/peerj.com\/articles\/cs-1882.ris"},"bib":{"type":"application\/x-bibtex","href":"https:\/\/peerj.com\/articles\/cs-1882.bib"},"citeproc":{"type":"application\/vnd.citationstyles.csl+json","href":"https:\/\/peerj.com\/articles\/cs-1882.citeproc"},"bibjson":{"type":"application\/bibjson+json","href":"https:\/\/peerj.com\/articles\/cs-1882.bibjson"},"unixref":{"type":"application\/unixref+xml","href":"https:\/\/peerj.com\/articles\/cs-1882.unixref"}}}},{"title":"Architecting an enterprise financial management model: leveraging multi-head attention mechanism-transformer for user information transformation","date":"2024-03-15","doi":"10.7717\/peerj-cs.1928","language":"en","pdf_url":"https:\/\/peerj.com\/articles\/cs-1928.pdf","fulltext_html_url":"https:\/\/peerj.com\/articles\/cs-1928","volume":"10","firstpage":"e1928","author":["Wan Yu","Habib Hamam"],"author_institution":["Huanghe Science and Technology University, Zhengzhou, Henan, China","Faculty of Engineering, Uni de Moncton, Moncton, Canada","International Institute of Technology and Management (IITG), Avenue des Grandes Ecoles, Libreville, Gabon","Bridges for Academic Excellence, Tunis, Centre Ville, Tunisia","Department of Electrical and Electronic Engineering Science, School of Electrical Engineering, University of Johannesburg, Johannesburg, South Africa"],"author_email":"amanda19881109@163.com","authors":"Yu, Wan; Hamam, Habib","author_institutions":"Huanghe Science and Technology University, Zhengzhou, Henan, China; Faculty of Engineering, Uni de Moncton, Moncton, Canada; International Institute of Technology and Management (IITG), Avenue des Grandes Ecoles, Libreville, Gabon; Bridges for Academic Excellence, Tunis, Centre Ville, Tunisia; Department of Electrical and Electronic Engineering Science, School of Electrical Engineering, University of Johannesburg, Johannesburg, South Africa","keywords":["Financial management","Transformer","Reinforcement learning","GAN"],"journal_title":"PeerJ Computer Science","journal_abbrev":"PeerJ Comput. Sci.","publisher":"PeerJ Inc.","issn":"2376-5992","description":"Financial management assumes a pivotal role as a fundamental information system contributing to enterprise development. Nonetheless, prevalent methodologies frequently encounter challenges in proficiently overseeing diverse information streams inherent to financial management. This study introduces an innovative paradigm for enterprise financial management centered on the transformation of user information signals. In its initial phases, the methodology augments the Transformer network and self-attention mechanism to extract features pertaining to both users and financial data, fostering a more cohesive integration of financial and user information. Subsequently, a reinforcement learning-based alignment method is implemented to reconcile disparities between financial and user information, thereby enhancing semantic alignment. Ultimately, a signal conversion technique employing generative adversarial networks is deployed to harness user information, elevating financial management efficacy and, consequently, optimizing overall financial operations. The empirical validation of this approach, achieving an impressive mAP score of 81.9%, not only outperforms existing methodologies but also underscores the tangible impact and enhanced execution prowess that this paradigm brings to financial management systems. As such, this work not only contributes to the state of the art but also holds promise for revolutionizing the landscape of enterprise financial management.","description-html":"\n Financial management assumes a pivotal role as a fundamental information system contributing to enterprise development. Nonetheless, prevalent methodologies frequently encounter challenges in proficiently overseeing diverse information streams inherent to financial management. This study introduces an innovative paradigm for enterprise financial management centered on the transformation of user information signals. In its initial phases, the methodology augments the Transformer network and self-attention mechanism to extract features pertaining to both users and financial data, fostering a more cohesive integration of financial and user information. Subsequently, a reinforcement learning-based alignment method is implemented to reconcile disparities between financial and user information, thereby enhancing semantic alignment. Ultimately, a signal conversion technique employing generative adversarial networks is deployed to harness user information, elevating financial management efficacy and, consequently, optimizing overall financial operations. The empirical validation of this approach, achieving an impressive mAP score of 81.9%, not only outperforms existing methodologies but also underscores the tangible impact and enhanced execution prowess that this paradigm brings to financial management systems. As such, this work not only contributes to the state of the art but also holds promise for revolutionizing the landscape of enterprise financial management.<\/p>\n ","title-html":"Architecting an enterprise financial management model: leveraging multi-head attention mechanism-transformer for user information transformation","subjects":["Algorithms and Analysis of Algorithms","Artificial Intelligence","Data Mining and Machine Learning","Scientific Computing and Simulation"],"identifiers":{"peerj":"cs-1928","pubmed":null,"pmc":null},"@context":"http:\/\/static.peerj.com\/context\/citation\/context.json","@type":"http:\/\/schema.org\/ScholarlyArticle","@id":"https:\/\/peerj.com\/articles\/cs-1928","_links":{"self":{"href":"https:\/\/peerj.com\/articles\/cs-1928.json"},"alternate":{"html":{"type":"text\/html","href":"https:\/\/peerj.com\/articles\/cs-1928.html"},"xml":{"type":"application\/xml","href":"https:\/\/peerj.com\/articles\/cs-1928.xml"},"pdf":{"type":"application\/pdf","href":"https:\/\/peerj.com\/articles\/cs-1928.pdf"},"rdf":{"type":"application\/rdf+xml","href":"https:\/\/peerj.com\/articles\/cs-1928.rdf"},"ris":{"type":"application\/x-research-info-systems","href":"https:\/\/peerj.com\/articles\/cs-1928.ris"},"bib":{"type":"application\/x-bibtex","href":"https:\/\/peerj.com\/articles\/cs-1928.bib"},"citeproc":{"type":"application\/vnd.citationstyles.csl+json","href":"https:\/\/peerj.com\/articles\/cs-1928.citeproc"},"bibjson":{"type":"application\/bibjson+json","href":"https:\/\/peerj.com\/articles\/cs-1928.bibjson"},"unixref":{"type":"application\/unixref+xml","href":"https:\/\/peerj.com\/articles\/cs-1928.unixref"}}}},{"title":"Data aggregation algorithm for wireless sensor networks with different initial energy of nodes","date":"2024-03-15","doi":"10.7717\/peerj-cs.1932","language":"en","pdf_url":"https:\/\/peerj.com\/articles\/cs-1932.pdf","fulltext_html_url":"https:\/\/peerj.com\/articles\/cs-1932","volume":"10","firstpage":"e1932","author":["Zhenpeng Liu","Jialiang Zhang","Yi Liu","Fan Feng","Yifan Liu"],"author_institution":["School of Cyber Security and Computer, Hebei University, Baoding, Hebei, China","Information Technology Center, Hebei University, Baoding, Hebei, China","School of Cyber Security and Computer, Hebei University, Baoding, Hebei, China","Information Technology Center, Hebei University, Baoding, Hebei, China","Information Technology Center, Hebei University, Baoding, Hebei, China","School of Cyber Security and Computer, Hebei University, Baoding, Hebei, China"],"author_email":"lyf@hbu.edu.cn","authors":"Liu, Zhenpeng; Zhang, Jialiang; Liu, Yi; Feng, Fan; Liu, Yifan","author_institutions":"School of Cyber Security and Computer, Hebei University, Baoding, Hebei, China; Information Technology Center, Hebei University, Baoding, Hebei, China","keywords":["Data aggregation","Different initial energy","Privacy-preserving","Slice-and-mix technology","Wireless sensor networks","Node death rate","Tree topology","Communication overhead","Energy consumption","Dynamically reconfigure"],"journal_title":"PeerJ Computer Science","journal_abbrev":"PeerJ Comput. Sci.","publisher":"PeerJ Inc.","issn":"2376-5992","description":"Data aggregation plays a critical role in sensor networks for efficient data collection. However, the assumption of uniform initial energy levels among sensors in existing algorithms is unrealistic in practical production applications. This discrepancy in initial energy levels significantly impacts data aggregation in sensor networks. To address this issue, we propose Data Aggregation with Different Initial Energy (DADIE), a novel algorithm that aims to enhance energy-saving, privacy-preserving efficiency, and reduce node death rates in sensor networks with varying initial energy nodes. DADIE considers the transmission distance between nodes and their initial energy levels when forming the network topology, while also limiting the number of child nodes. Furthermore, DADIE reconstructs the aggregation tree before each round of data transmission. This allows nodes closer to the receiving end with higher initial energy to undertake more data aggregation and transmission tasks while limiting energy consumption. As a result, DADIE effectively reduces the node death rate and improves the efficiency of data transmission throughout the network. To enhance network security, DADIE establishes secure transmission channels between transmission nodes prior to data transmission, and it employs slice-and-mix technology within the network. Our experimental simulations demonstrate that the proposed DADIE algorithm effectively resolves the data aggregation challenges in sensor networks with varying initial energy nodes. It achieves 5\u201320% lower communication overhead and energy consumption, 10\u201320% higher security, and 10\u201330% lower node mortality than existing algorithms.","description-html":"\n Data aggregation plays a critical role in sensor networks for efficient data collection. However, the assumption of uniform initial energy levels among sensors in existing algorithms is unrealistic in practical production applications. This discrepancy in initial energy levels significantly impacts data aggregation in sensor networks. To address this issue, we propose Data Aggregation with Different Initial Energy (DADIE), a novel algorithm that aims to enhance energy-saving, privacy-preserving efficiency, and reduce node death rates in sensor networks with varying initial energy nodes. DADIE considers the transmission distance between nodes and their initial energy levels when forming the network topology, while also limiting the number of child nodes. Furthermore, DADIE reconstructs the aggregation tree before each round of data transmission. This allows nodes closer to the receiving end with higher initial energy to undertake more data aggregation and transmission tasks while limiting energy consumption. As a result, DADIE effectively reduces the node death rate and improves the efficiency of data transmission throughout the network. To enhance network security, DADIE establishes secure transmission channels between transmission nodes prior to data transmission, and it employs slice-and-mix technology within the network. Our experimental simulations demonstrate that the proposed DADIE algorithm effectively resolves the data aggregation challenges in sensor networks with varying initial energy nodes. It achieves 5\u201320% lower communication overhead and energy consumption, 10\u201320% higher security, and 10\u201330% lower node mortality than existing algorithms.<\/p>\n","title-html":"Data aggregation algorithm for wireless sensor networks with different initial energy of nodes","subjects":["Algorithms and Analysis of Algorithms","Computer Networks and Communications","Databases","Security and Privacy"],"identifiers":{"peerj":"cs-1932","pubmed":null,"pmc":null},"@context":"http:\/\/static.peerj.com\/context\/citation\/context.json","@type":"http:\/\/schema.org\/ScholarlyArticle","@id":"https:\/\/peerj.com\/articles\/cs-1932","_links":{"self":{"href":"https:\/\/peerj.com\/articles\/cs-1932.json"},"alternate":{"html":{"type":"text\/html","href":"https:\/\/peerj.com\/articles\/cs-1932.html"},"xml":{"type":"application\/xml","href":"https:\/\/peerj.com\/articles\/cs-1932.xml"},"pdf":{"type":"application\/pdf","href":"https:\/\/peerj.com\/articles\/cs-1932.pdf"},"rdf":{"type":"application\/rdf+xml","href":"https:\/\/peerj.com\/articles\/cs-1932.rdf"},"ris":{"type":"application\/x-research-info-systems","href":"https:\/\/peerj.com\/articles\/cs-1932.ris"},"bib":{"type":"application\/x-bibtex","href":"https:\/\/peerj.com\/articles\/cs-1932.bib"},"citeproc":{"type":"application\/vnd.citationstyles.csl+json","href":"https:\/\/peerj.com\/articles\/cs-1932.citeproc"},"bibjson":{"type":"application\/bibjson+json","href":"https:\/\/peerj.com\/articles\/cs-1932.bibjson"},"unixref":{"type":"application\/unixref+xml","href":"https:\/\/peerj.com\/articles\/cs-1932.unixref"}}}},{"title":"An improved differential evolution algorithm for multi-modal multi-objective optimization","date":"2024-03-14","doi":"10.7717\/peerj-cs.1839","language":"en","pdf_url":"https:\/\/peerj.com\/articles\/cs-1839.pdf","fulltext_html_url":"https:\/\/peerj.com\/articles\/cs-1839","volume":"10","firstpage":"e1839","author":["Dan Qu","Hualin Xiao","Huafei Chen","Hongyi Li"],"author_institution":["College of Mathematics Education, China West Normal University, Nanchong, China","College of Mathematics and Statistics, Sichuan University of Science & Engineering, Zigong, China","College of Mathematics Education, China West Normal University, Nanchong, China","College of Mathematics and Statistics, Sichuan University of Science & Engineering, Zigong, China","College of Mathematics and Statistics, Sichuan University of Science & Engineering, Zigong, China"],"author_email":"hualin_xiao688@163.com","authors":"Qu, Dan; Xiao, Hualin; Chen, Huafei; Li, Hongyi","author_institutions":"College of Mathematics Education, China West Normal University, Nanchong, China; College of Mathematics and Statistics, Sichuan University of Science & Engineering, Zigong, China","keywords":["Multi-modal multi-objective optimization","Differential Evolution Algorithm","Affinity propagation"],"journal_title":"PeerJ Computer Science","journal_abbrev":"PeerJ Comput. Sci.","publisher":"PeerJ Inc.","issn":"2376-5992","description":"Multi-modal multi-objective problems (MMOPs) have gained much attention during the last decade. These problems have two or more global or local Pareto optimal sets (PSs), some of which map to the same Pareto front (PF). This article presents a new affinity propagation clustering (APC) method based on the Multi-modal multi-objective differential evolution (MMODE) algorithm, called MMODE_AP, for the suit of CEC\u20192020 benchmark functions. First, two adaptive mutation strategies are adopted to balance exploration and exploitation and improve the diversity in the evolution process. Then, the affinity propagation clustering method is adopted to define the crowding degree in decision space (DS) and objective space (OS). Meanwhile, the non-dominated sorting scheme incorporates a particular crowding distance to truncate the population during the environmental selection process, which can obtain well-distributed solutions in both DS and OS. Moreover, the local PF membership of the solution is defined, and a predefined parameter is introduced to maintain of the local PSs and solutions around the global PS. Finally, the proposed algorithm is implemented on the suit of CEC\u20192020 benchmark functions for comparison with some MMODE algorithms. According to the experimental study results, the proposed MMODE_AP algorithm has about 20 better performance results on benchmark functions compared to its competitors in terms of reciprocal of Pareto sets proximity (rPSP), inverted generational distances (IGD) in the decision (IGDX) and objective (IGDF). The proposed algorithm can efficiently achieve the two goals, i.e., the convergence to the true local and global Pareto fronts along with better distributed Pareto solutions on the Pareto fronts.","description-html":"\n Multi-modal multi-objective problems (MMOPs) have gained much attention during the last decade. These problems have two or more global or local Pareto optimal sets (PSs), some of which map to the same Pareto front (PF). This article presents a new affinity propagation clustering (APC) method based on the Multi-modal multi-objective differential evolution (MMODE) algorithm, called MMODE_AP, for the suit of CEC\u20192020 benchmark functions. First, two adaptive mutation strategies are adopted to balance exploration and exploitation and improve the diversity in the evolution process. Then, the affinity propagation clustering method is adopted to define the crowding degree in decision space (DS) and objective space (OS). Meanwhile, the non-dominated sorting scheme incorporates a particular crowding distance to truncate the population during the environmental selection process, which can obtain well-distributed solutions in both DS and OS. Moreover, the local PF membership of the solution is defined, and a predefined parameter is introduced to maintain of the local PSs and solutions around the global PS. Finally, the proposed algorithm is implemented on the suit of CEC\u20192020 benchmark functions for comparison with some MMODE algorithms. According to the experimental study results, the proposed MMODE_AP algorithm has about 20 better performance results on benchmark functions compared to its competitors in terms of reciprocal of Pareto sets proximity (rPSP), inverted generational distances (IGD) in the decision (IGDX) and objective (IGDF). The proposed algorithm can efficiently achieve the two goals, i.e., the convergence to the true local and global Pareto fronts along with better distributed Pareto solutions on the Pareto fronts.<\/p>\n ","title-html":"An improved differential evolution algorithm for multi-modal multi-objective optimization","subjects":["Artificial Intelligence","Optimization Theory and Computation"],"identifiers":{"peerj":"cs-1839","pubmed":null,"pmc":null},"@context":"http:\/\/static.peerj.com\/context\/citation\/context.json","@type":"http:\/\/schema.org\/ScholarlyArticle","@id":"https:\/\/peerj.com\/articles\/cs-1839","_links":{"self":{"href":"https:\/\/peerj.com\/articles\/cs-1839.json"},"alternate":{"html":{"type":"text\/html","href":"https:\/\/peerj.com\/articles\/cs-1839.html"},"xml":{"type":"application\/xml","href":"https:\/\/peerj.com\/articles\/cs-1839.xml"},"pdf":{"type":"application\/pdf","href":"https:\/\/peerj.com\/articles\/cs-1839.pdf"},"rdf":{"type":"application\/rdf+xml","href":"https:\/\/peerj.com\/articles\/cs-1839.rdf"},"ris":{"type":"application\/x-research-info-systems","href":"https:\/\/peerj.com\/articles\/cs-1839.ris"},"bib":{"type":"application\/x-bibtex","href":"https:\/\/peerj.com\/articles\/cs-1839.bib"},"citeproc":{"type":"application\/vnd.citationstyles.csl+json","href":"https:\/\/peerj.com\/articles\/cs-1839.citeproc"},"bibjson":{"type":"application\/bibjson+json","href":"https:\/\/peerj.com\/articles\/cs-1839.bibjson"},"unixref":{"type":"application\/unixref+xml","href":"https:\/\/peerj.com\/articles\/cs-1839.unixref"}}}},{"title":"Enhancing brain tumor diagnosis: an optimized CNN hyperparameter model for improved accuracy and reliability","date":"2024-03-14","doi":"10.7717\/peerj-cs.1878","language":"en","pdf_url":"https:\/\/peerj.com\/articles\/cs-1878.pdf","fulltext_html_url":"https:\/\/peerj.com\/articles\/cs-1878","volume":"10","firstpage":"e1878","author":["Abdullah A. Asiri","Ahmad Shaf","Tariq Ali","Muhammad Aamir","Muhammad Irfan","Saeed Alqahtani"],"author_institution":["Radiological Sciences Department, College of Applied Medical Sciences, Najran University, Najran, Najran, Saudi Arabia","Department of Computer Science, COMSATS University Islamabad, Sahiwal, Punjan, Pakistan","Department of Computer Science, COMSATS University Islamabad, Sahiwal, Punjan, Pakistan","Department of Computer Science, COMSATS University Islamabad, Sahiwal, Punjan, Pakistan","Electrical Engineering Department, College of Engineering, Najran University, Najran, Najran, Saudi Arabia","Radiological Sciences Department, College of Applied Medical Sciences, Najran University, Najran, Najran, Saudi Arabia"],"author_email":"ahmadshaf@cuisahiwal.edu.pk","authors":"Asiri, Abdullah A.; Shaf, Ahmad; Ali, Tariq; Aamir, Muhammad; Irfan, Muhammad; Alqahtani, Saeed","author_institutions":"Radiological Sciences Department, College of Applied Medical Sciences, Najran University, Najran, Najran, Saudi Arabia; Department of Computer Science, COMSATS University Islamabad, Sahiwal, Punjan, Pakistan; Electrical Engineering Department, College of Engineering, Najran University, Najran, Najran, Saudi Arabia","keywords":["Hyperparameter tuning","Brain tumor diagnosis","Feature extraction","Spatial resolution","Model complexity","Decision-making processes","Optimization techniques"],"journal_title":"PeerJ Computer Science","journal_abbrev":"PeerJ Comput. Sci.","publisher":"PeerJ Inc.","issn":"2376-5992","description":"Hyperparameter tuning plays a pivotal role in the accuracy and reliability of convolutional neural network (CNN) models used in brain tumor diagnosis. These hyperparameters exert control over various aspects of the neural network, encompassing feature extraction, spatial resolution, non-linear mapping, convergence speed, and model complexity. We propose a meticulously refined CNN hyperparameter model designed to optimize critical parameters, including filter number and size, stride padding, pooling techniques, activation functions, learning rate, batch size, and the number of layers. Our approach leverages two publicly available brain tumor MRI datasets for research purposes. The first dataset comprises a total of 7,023 human brain images, categorized into four classes: glioma, meningioma, no tumor, and pituitary. The second dataset contains 253 images classified as \u201cyes\u201d and \u201cno.\u201d Our approach delivers exceptional results, demonstrating an average 94.25% precision, recall, and F1-score with 96% accuracy for dataset 1, while an average 87.5% precision, recall, and F1-score, with accuracy of 88% for dataset 2. To affirm the robustness of our findings, we perform a comprehensive comparison with existing techniques, revealing that our method consistently outperforms these approaches. By systematically fine-tuning these critical hyperparameters, our model not only enhances its performance but also bolsters its generalization capabilities. This optimized CNN model provides medical experts with a more precise and efficient tool for supporting their decision-making processes in brain tumor diagnosis.","description-html":"\n Hyperparameter tuning plays a pivotal role in the accuracy and reliability of convolutional neural network (CNN) models used in brain tumor diagnosis. These hyperparameters exert control over various aspects of the neural network, encompassing feature extraction, spatial resolution, non-linear mapping, convergence speed, and model complexity. We propose a meticulously refined CNN hyperparameter model designed to optimize critical parameters, including filter number and size, stride padding, pooling techniques, activation functions, learning rate, batch size, and the number of layers. Our approach leverages two publicly available brain tumor MRI datasets for research purposes. The first dataset comprises a total of 7,023 human brain images, categorized into four classes: glioma, meningioma, no tumor, and pituitary. The second dataset contains 253 images classified as \u201cyes\u201d and \u201cno.\u201d Our approach delivers exceptional results, demonstrating an average 94.25% precision, recall, and F1-score with 96% accuracy for dataset 1, while an average 87.5% precision, recall, and F1-score, with accuracy of 88% for dataset 2. To affirm the robustness of our findings, we perform a comprehensive comparison with existing techniques, revealing that our method consistently outperforms these approaches. By systematically fine-tuning these critical hyperparameters, our model not only enhances its performance but also bolsters its generalization capabilities. This optimized CNN model provides medical experts with a more precise and efficient tool for supporting their decision-making processes in brain tumor diagnosis.<\/p>\n","title-html":"Enhancing brain tumor diagnosis: an optimized CNN hyperparameter model for improved accuracy and reliability","subjects":["Computer Vision","Neural Networks"],"identifiers":{"peerj":"cs-1878","pubmed":null,"pmc":null},"@context":"http:\/\/static.peerj.com\/context\/citation\/context.json","@type":"http:\/\/schema.org\/ScholarlyArticle","@id":"https:\/\/peerj.com\/articles\/cs-1878","_links":{"self":{"href":"https:\/\/peerj.com\/articles\/cs-1878.json"},"alternate":{"html":{"type":"text\/html","href":"https:\/\/peerj.com\/articles\/cs-1878.html"},"xml":{"type":"application\/xml","href":"https:\/\/peerj.com\/articles\/cs-1878.xml"},"pdf":{"type":"application\/pdf","href":"https:\/\/peerj.com\/articles\/cs-1878.pdf"},"rdf":{"type":"application\/rdf+xml","href":"https:\/\/peerj.com\/articles\/cs-1878.rdf"},"ris":{"type":"application\/x-research-info-systems","href":"https:\/\/peerj.com\/articles\/cs-1878.ris"},"bib":{"type":"application\/x-bibtex","href":"https:\/\/peerj.com\/articles\/cs-1878.bib"},"citeproc":{"type":"application\/vnd.citationstyles.csl+json","href":"https:\/\/peerj.com\/articles\/cs-1878.citeproc"},"bibjson":{"type":"application\/bibjson+json","href":"https:\/\/peerj.com\/articles\/cs-1878.bibjson"},"unixref":{"type":"application\/unixref+xml","href":"https:\/\/peerj.com\/articles\/cs-1878.unixref"}}}},{"title":"AutoSCAN: automatic detection of DBSCAN parameters and efficient clustering of data in overlapping density regions","date":"2024-03-14","doi":"10.7717\/peerj-cs.1921","language":"en","pdf_url":"https:\/\/peerj.com\/articles\/cs-1921.pdf","fulltext_html_url":"https:\/\/peerj.com\/articles\/cs-1921","volume":"10","firstpage":"e1921","author":["Adil Abdu Bushra","Dongyeon Kim","Yejin Kan","Gangman Yi"],"author_institution":["Department of Multimedia Engineering, Dongguk University, Seoul, South Korea","Department of Artificial Intelligence, Dongguk University, Seoul, South Korea","Department of Multimedia Engineering, Dongguk University, Seoul, South Korea","Department of Multimedia Engineering, Dongguk University, Seoul, South Korea","Department of Artificial Intelligence, Dongguk University, Seoul, South Korea","Division of AI Software Convergence, Dongguk University, Seoul, South Korea"],"author_email":"gangman@dongguk.edu","authors":"Bushra, Adil Abdu; Kim, Dongyeon; Kan, Yejin; Yi, Gangman","author_institutions":"Department of Multimedia Engineering, Dongguk University, Seoul, South Korea; Department of Artificial Intelligence, Dongguk University, Seoul, South Korea; Division of AI Software Convergence, Dongguk University, Seoul, South Korea","keywords":["DBSCAN","Density-based clustering","Unsupervised clustering","K-nearest neighbors"],"journal_title":"PeerJ Computer Science","journal_abbrev":"PeerJ Comput. Sci.","publisher":"PeerJ Inc.","issn":"2376-5992","description":"The density-based clustering method is considered a robust approach in unsupervised clustering technique due to its ability to identify outliers, form clusters of irregular shapes and automatically determine the number of clusters. These unique properties helped its pioneering algorithm, the Density-based Spatial Clustering on Applications with Noise (DBSCAN), become applicable in datasets where various number of clusters of different shapes and sizes could be detected without much interference from the user. However, the original algorithm exhibits limitations, especially towards its sensitivity on its user input parameters minPts and \u025b. Additionally, the algorithm assigned inconsistent cluster labels to data objects found in overlapping density regions of separate clusters, hence lowering its accuracy. To alleviate these specific problems and increase the clustering accuracy, we propose two methods that use the statistical data from a given dataset\u2019s k-nearest neighbor density distribution in order to determine the optimal \u025b values. Our approach removes the burden on the users, and automatically detects the clusters of a given dataset. Furthermore, a method to identify the accurate border objects of separate clusters is proposed and implemented to solve the unpredictability of the original algorithm. Finally, in our experiments, we show that our efficient re-implementation of the original algorithm to automatically cluster datasets and improve the clustering quality of adjoining cluster members provides increase in clustering accuracy and faster running times when compared to earlier approaches.","description-html":"\n The density-based clustering method is considered a robust approach in unsupervised clustering technique due to its ability to identify outliers, form clusters of irregular shapes and automatically determine the number of clusters. These unique properties helped its pioneering algorithm, the Density-based Spatial Clustering on Applications with Noise (DBSCAN), become applicable in datasets where various number of clusters of different shapes and sizes could be detected without much interference from the user. However, the original algorithm exhibits limitations, especially towards its sensitivity on its user input parameters minPts and \u025b<\/i>. Additionally, the algorithm assigned inconsistent cluster labels to data objects found in overlapping density regions of separate clusters, hence lowering its accuracy. To alleviate these specific problems and increase the clustering accuracy, we propose two methods that use the statistical data from a given dataset\u2019s k-nearest neighbor density distribution in order to determine the optimal \u025b<\/i> values. Our approach removes the burden on the users, and automatically detects the clusters of a given dataset. Furthermore, a method to identify the accurate border objects of separate clusters is proposed and implemented to solve the unpredictability of the original algorithm. Finally, in our experiments, we show that our efficient re-implementation of the original algorithm to automatically cluster datasets and improve the clustering quality of adjoining cluster members provides increase in clustering accuracy and faster running times when compared to earlier approaches.<\/p>\n ","title-html":"AutoSCAN: automatic detection of DBSCAN parameters and efficient clustering of data in overlapping density regions","subjects":["Data Mining and Machine Learning","Data Science"],"identifiers":{"peerj":"cs-1921","pubmed":null,"pmc":null},"@context":"http:\/\/static.peerj.com\/context\/citation\/context.json","@type":"http:\/\/schema.org\/ScholarlyArticle","@id":"https:\/\/peerj.com\/articles\/cs-1921","_links":{"self":{"href":"https:\/\/peerj.com\/articles\/cs-1921.json"},"alternate":{"html":{"type":"text\/html","href":"https:\/\/peerj.com\/articles\/cs-1921.html"},"xml":{"type":"application\/xml","href":"https:\/\/peerj.com\/articles\/cs-1921.xml"},"pdf":{"type":"application\/pdf","href":"https:\/\/peerj.com\/articles\/cs-1921.pdf"},"rdf":{"type":"application\/rdf+xml","href":"https:\/\/peerj.com\/articles\/cs-1921.rdf"},"ris":{"type":"application\/x-research-info-systems","href":"https:\/\/peerj.com\/articles\/cs-1921.ris"},"bib":{"type":"application\/x-bibtex","href":"https:\/\/peerj.com\/articles\/cs-1921.bib"},"citeproc":{"type":"application\/vnd.citationstyles.csl+json","href":"https:\/\/peerj.com\/articles\/cs-1921.citeproc"},"bibjson":{"type":"application\/bibjson+json","href":"https:\/\/peerj.com\/articles\/cs-1921.bibjson"},"unixref":{"type":"application\/unixref+xml","href":"https:\/\/peerj.com\/articles\/cs-1921.unixref"}}}}]}Context<\/h2>\n
Motivation<\/h2>\n
Problem Statement<\/h2>\n
Contributions<\/h2>\n
Results<\/h2>\n