Pub Date : 2024-03-13DOI: 10.32996/jcsts.2024.6.1.25
Mujiba Shaima, Norun Nabi, Md Nasir Uddin Rana, Ahmed Ali Linkon, Badruddowza, Md Shohail Uddin Sarker, Nishat Anjum, Hammed Esa
This study analyzes machine learning algorithms to predict the need for corticosteroid (CS) therapy in COVID-19 patients based on initial assessments. Using data from 1861 COVID-19 patients, parameters like blood tests and pulmonary function tests were examined. Decision Tree and XGBoost emerged as top performers, achieving accuracy rates of 80.68% and 83.44% respectively. Multilayer Perceptron and AdaBoost also showed competitive performance. These findings highlight the potential of AI in guiding CS therapy decisions, with Decision Tree and XGBoost standing out as effective tools for patient identification. This research offers valuable insights for personalized medicine in infectious disease management.
{"title":"Machine Learning Models for Predicting Corticosteroid Therapy Necessity in COVID-19 Patients: A Comparative Study","authors":"Mujiba Shaima, Norun Nabi, Md Nasir Uddin Rana, Ahmed Ali Linkon, Badruddowza, Md Shohail Uddin Sarker, Nishat Anjum, Hammed Esa","doi":"10.32996/jcsts.2024.6.1.25","DOIUrl":"https://doi.org/10.32996/jcsts.2024.6.1.25","url":null,"abstract":"This study analyzes machine learning algorithms to predict the need for corticosteroid (CS) therapy in COVID-19 patients based on initial assessments. Using data from 1861 COVID-19 patients, parameters like blood tests and pulmonary function tests were examined. Decision Tree and XGBoost emerged as top performers, achieving accuracy rates of 80.68% and 83.44% respectively. Multilayer Perceptron and AdaBoost also showed competitive performance. These findings highlight the potential of AI in guiding CS therapy decisions, with Decision Tree and XGBoost standing out as effective tools for patient identification. This research offers valuable insights for personalized medicine in infectious disease management.","PeriodicalId":509154,"journal":{"name":"Journal of Computer Science and Technology Studies","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140247259","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-13DOI: 10.32996/jcsts.2024.6.1.26
Ahmed Ali Linkon, Mujiba ✉, Md Shohail Uddin Sarker, Norun Nabi, Md Nasir Uddin Rana, Sandip Kumar Ghosh, Mohammad Anisur Rahman, Hammed Esa, Faiaz Rahat Chowdhury
This comprehensive review delves into the landscape and recent advancements of Generative Artificial Intelligence (AI) and Large Language Models (LLMs), shedding light on their transformative potential and applications across various sectors. Generative AI, exemplified by models like ChatGPT, DALL-E, and Midjourney, has rapidly evolved and is driven by breakthroughs in deep learning architectures and the availability of vast datasets. Concurrently, LLMs have revolutionized natural language processing tasks, utilizing vast text corpora to generate human-like text. The study explores recent developments, including the introduction of advanced models like GPT-4 and PaLM2 and the emergence of specialized LLMs like small LLMs (sLLMs), aimed at overcoming hardware limitations and cost constraints. Additionally, the expanding applications of generative AI, from healthcare to finance, underscore its transformative potential in addressing real-world challenges. Through a comprehensive analysis, this research contributes to the ongoing discourse on AI ethics, governance, and regulation, emphasizing the importance of responsible innovation for the benefit of humanity.
{"title":"Advancements and Applications of Generative Artificial Intelligence and Large Language Models on Business Management: A Comprehensive Review","authors":"Ahmed Ali Linkon, Mujiba ✉, Md Shohail Uddin Sarker, Norun Nabi, Md Nasir Uddin Rana, Sandip Kumar Ghosh, Mohammad Anisur Rahman, Hammed Esa, Faiaz Rahat Chowdhury","doi":"10.32996/jcsts.2024.6.1.26","DOIUrl":"https://doi.org/10.32996/jcsts.2024.6.1.26","url":null,"abstract":"This comprehensive review delves into the landscape and recent advancements of Generative Artificial Intelligence (AI) and Large Language Models (LLMs), shedding light on their transformative potential and applications across various sectors. Generative AI, exemplified by models like ChatGPT, DALL-E, and Midjourney, has rapidly evolved and is driven by breakthroughs in deep learning architectures and the availability of vast datasets. Concurrently, LLMs have revolutionized natural language processing tasks, utilizing vast text corpora to generate human-like text. The study explores recent developments, including the introduction of advanced models like GPT-4 and PaLM2 and the emergence of specialized LLMs like small LLMs (sLLMs), aimed at overcoming hardware limitations and cost constraints. Additionally, the expanding applications of generative AI, from healthcare to finance, underscore its transformative potential in addressing real-world challenges. Through a comprehensive analysis, this research contributes to the ongoing discourse on AI ethics, governance, and regulation, emphasizing the importance of responsible innovation for the benefit of humanity.","PeriodicalId":509154,"journal":{"name":"Journal of Computer Science and Technology Studies","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140247009","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-07DOI: 10.32996/jcsts.2024.6.1.24
Arjun Naik
As the landscape of web development continues to evolve rapidly, choosing the right front-end technology stack for application development has become a critical challenge for developers and organizations. This research paper explores the multifaceted dimensions of the front-end dilemma, aiming to provide a comprehensive guide for decision-makers in the selection process. The study delves into the diverse range of front-end frameworks, libraries, and tools available, analyzing their strengths, weaknesses, and suitability for different types of applications. Based on the research done in the paper, we can say that each option is strong with Angular and React leading the pack but the choice will depend upon the use case, time on hand, maintenance and level of understanding.
{"title":"The Front-End Dilemma: How to Choose the Perfect Technology for your Application.","authors":"Arjun Naik","doi":"10.32996/jcsts.2024.6.1.24","DOIUrl":"https://doi.org/10.32996/jcsts.2024.6.1.24","url":null,"abstract":"As the landscape of web development continues to evolve rapidly, choosing the right front-end technology stack for application development has become a critical challenge for developers and organizations. This research paper explores the multifaceted dimensions of the front-end dilemma, aiming to provide a comprehensive guide for decision-makers in the selection process. The study delves into the diverse range of front-end frameworks, libraries, and tools available, analyzing their strengths, weaknesses, and suitability for different types of applications. Based on the research done in the paper, we can say that each option is strong with Angular and React leading the pack but the choice will depend upon the use case, time on hand, maintenance and level of understanding.","PeriodicalId":509154,"journal":{"name":"Journal of Computer Science and Technology Studies","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140258486","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-02-23DOI: 10.32996/jcsts.2024.6.1.22
Mujiba Shaima, ✉. N. Nabi, Md Nasir Uddin Rana, Estak Ahmed, Mazharul Islam Tusher, Mousumi Hasan, Mukti, Quazi Saad-Ul-Mosaher
With its novel bidirectional communication method, Neuralink, the brain-reading gadget created by Elon Musk, is poised to transform human-machine relations. It represents a revolutionary combination of health science, neurology, and artificial intelligence. Neuralink is a potentially beneficial brain implant that consists of tiny electrodes placed behind the ear and a small chip. It can be used to treat neurological conditions and improve cognitive function. Important discussions are nevertheless sparked by ethical worries about abuse, privacy, and security. It is important to maintain a careful balance between the development of technology and moral issues, as seen by the imagined future in which people interact with computers through thinking processes. In order for Neuralink to be widely accepted and responsibly incorporated into the fabric of human cognition and connectivity, ongoing discussions about ethical standards, regulatory frameworks, and societal ramifications are important. Meanwhile, new advancements in Brain-Chip-Interfaces (BCHIs) bring the larger context into focus. By enhancing signal transmission between nerve cells and chips, these developments offer increased signal fidelity and improved spatiotemporal resolution. The potential revolutionary influence of these innovations on neuroscience and human-machine symbiosis raises important considerations about the ethical and societal consequences of these innovations.
{"title":"Elon Musk’s Neuralink Brain Chip: A Review on ‘Brain-Reading’ Device","authors":"Mujiba Shaima, ✉. N. Nabi, Md Nasir Uddin Rana, Estak Ahmed, Mazharul Islam Tusher, Mousumi Hasan, Mukti, Quazi Saad-Ul-Mosaher","doi":"10.32996/jcsts.2024.6.1.22","DOIUrl":"https://doi.org/10.32996/jcsts.2024.6.1.22","url":null,"abstract":"With its novel bidirectional communication method, Neuralink, the brain-reading gadget created by Elon Musk, is poised to transform human-machine relations. It represents a revolutionary combination of health science, neurology, and artificial intelligence. Neuralink is a potentially beneficial brain implant that consists of tiny electrodes placed behind the ear and a small chip. It can be used to treat neurological conditions and improve cognitive function. Important discussions are nevertheless sparked by ethical worries about abuse, privacy, and security. It is important to maintain a careful balance between the development of technology and moral issues, as seen by the imagined future in which people interact with computers through thinking processes. In order for Neuralink to be widely accepted and responsibly incorporated into the fabric of human cognition and connectivity, ongoing discussions about ethical standards, regulatory frameworks, and societal ramifications are important. Meanwhile, new advancements in Brain-Chip-Interfaces (BCHIs) bring the larger context into focus. By enhancing signal transmission between nerve cells and chips, these developments offer increased signal fidelity and improved spatiotemporal resolution. The potential revolutionary influence of these innovations on neuroscience and human-machine symbiosis raises important considerations about the ethical and societal consequences of these innovations.","PeriodicalId":509154,"journal":{"name":"Journal of Computer Science and Technology Studies","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140435885","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-02-20DOI: 10.32996/jcsts.2024.6.1.21
Sunil Sukumaran Nair
The paper sheds light on the rising scope of cloud computing and its impacts on businesses. Furthermore, the purpose of this article is to describe the harm caused by cloud computing despite its promised sustainable nature. The energy consumption during the operation of cloud systems is quite high. This article analyzes the factors that lead to huge energy consumption. E-waste is also a serious problem in the IT field because a large number of hardware resources are used, and once obsolete, they cause environmental pollution. There are various challenges, but taking some productive steps in the right direction can help solve the problem.
本文揭示了云计算范围的不断扩大及其对企业的影响。此外，本文的目的还在于描述云计算所造成的危害，尽管它承诺可持续发展。云计算系统运行过程中的能耗相当高。本文分析了导致巨大能源消耗的因素。电子垃圾也是 IT 领域的一个严重问题，因为大量的硬件资源被使用，一旦淘汰，就会造成环境污染。虽然面临着各种挑战，但朝着正确的方向采取一些富有成效的措施有助于解决问题。
{"title":"Challenges and Concerns Related to the Environmental Impact of Cloud Computing and the Carbon Footprint of Data Transmission","authors":"Sunil Sukumaran Nair","doi":"10.32996/jcsts.2024.6.1.21","DOIUrl":"https://doi.org/10.32996/jcsts.2024.6.1.21","url":null,"abstract":"The paper sheds light on the rising scope of cloud computing and its impacts on businesses. Furthermore, the purpose of this article is to describe the harm caused by cloud computing despite its promised sustainable nature. The energy consumption during the operation of cloud systems is quite high. This article analyzes the factors that lead to huge energy consumption. E-waste is also a serious problem in the IT field because a large number of hardware resources are used, and once obsolete, they cause environmental pollution. There are various challenges, but taking some productive steps in the right direction can help solve the problem.","PeriodicalId":509154,"journal":{"name":"Journal of Computer Science and Technology Studies","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140446516","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-28DOI: 10.32996/jcsts.2024.6.1.16
Rejon Kumar Ray, Ahmed Ali Linkon, Mohammad Shafiquzzaman Bhuiyan, Rasel Mahmud Jewel, Nishat Anjum, Bishnu Padh Ghosh, Md Tuhin Mia, Badruddowza, Md Shohail Uddin Sarker, Mujiba Shaima
Breast cancer stands as one of the most prevalent and perilous forms of cancer affecting both women and men. The detection and treatment of breast cancer benefit significantly from histopathological images, which carry crucial phenotypic information. To enhance accuracy in breast cancer detection, Deep Neural Networks (DNNs) are commonly utilized. Our research delves into the analysis of pre-trained deep transfer learning models, including ResNet50, ResNet101, VGG16, and VGG19, for identifying breast cancer using a dataset comprising 2453 histopathology images. The dataset categorizes images into two groups: those featuring invasive ductal carcinoma (IDC) and those without IDC. Through our analysis of transfer learning models, we observed that ResNet50 outperformed the other models, achieving impressive metrics such as accuracy rates of 92.2%, Area under Curve (AUC) rates of 91.0%, recall rates of 95.7%, and a minimal loss of 3.5%.
{"title":"Transforming Breast Cancer Identification: An In-Depth Examination of Advanced Machine Learning Models Applied to Histopathological Images","authors":"Rejon Kumar Ray, Ahmed Ali Linkon, Mohammad Shafiquzzaman Bhuiyan, Rasel Mahmud Jewel, Nishat Anjum, Bishnu Padh Ghosh, Md Tuhin Mia, Badruddowza, Md Shohail Uddin Sarker, Mujiba Shaima","doi":"10.32996/jcsts.2024.6.1.16","DOIUrl":"https://doi.org/10.32996/jcsts.2024.6.1.16","url":null,"abstract":"Breast cancer stands as one of the most prevalent and perilous forms of cancer affecting both women and men. The detection and treatment of breast cancer benefit significantly from histopathological images, which carry crucial phenotypic information. To enhance accuracy in breast cancer detection, Deep Neural Networks (DNNs) are commonly utilized. Our research delves into the analysis of pre-trained deep transfer learning models, including ResNet50, ResNet101, VGG16, and VGG19, for identifying breast cancer using a dataset comprising 2453 histopathology images. The dataset categorizes images into two groups: those featuring invasive ductal carcinoma (IDC) and those without IDC. Through our analysis of transfer learning models, we observed that ResNet50 outperformed the other models, achieving impressive metrics such as accuracy rates of 92.2%, Area under Curve (AUC) rates of 91.0%, recall rates of 95.7%, and a minimal loss of 3.5%.","PeriodicalId":509154,"journal":{"name":"Journal of Computer Science and Technology Studies","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140490794","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-28DOI: 10.32996/jcsts.2024.6.1.15
Md Rokibul Hasan
The electric grid entails a diverse range of components with pervasive heterogeneity. Conventional electricity models in the U.S.A. encounter challenges in terms of affirming the stability and security of the power system, particularly, when dealing with unexpected incidents. This study explored various electric grid models adopted in various nations and their shortcomings. To resolve these challenges, the research concentrated on consolidating machine learning algorithms as an optimization strategy for the electricity power grid. As such, this study proposed Ensemble Learning with a Feature Engineering Model which exemplified promising outputs, with the voting classifier performing well as compared to the rainforest classifier model. Particularly, the accuracy of the voting classifier was ascertained to be 94.57%, illustrating that approximately 94.17% of its predictions were correct as contrasted to the Random Forest. Besides, the precision of the voting classifier was ascertained to be 93.78%, implying that it correctly pinpointed positive data points 93.78% of the time. Remarkably, the Voting Classifier for the Ensemble Learning with Feature Engineering Model technique surpassed the performance of most other techniques, demonstrating an accuracy rate of 94.57%. These techniques provide protective and preventive measures to resolve the vulnerabilities and challenges faced by geographically distributed power systems.
{"title":"Revitalizing the Electric Grid: A Machine Learning Paradigm for Ensuring Stability in the U.S.A.","authors":"Md Rokibul Hasan","doi":"10.32996/jcsts.2024.6.1.15","DOIUrl":"https://doi.org/10.32996/jcsts.2024.6.1.15","url":null,"abstract":"The electric grid entails a diverse range of components with pervasive heterogeneity. Conventional electricity models in the U.S.A. encounter challenges in terms of affirming the stability and security of the power system, particularly, when dealing with unexpected incidents. This study explored various electric grid models adopted in various nations and their shortcomings. To resolve these challenges, the research concentrated on consolidating machine learning algorithms as an optimization strategy for the electricity power grid. As such, this study proposed Ensemble Learning with a Feature Engineering Model which exemplified promising outputs, with the voting classifier performing well as compared to the rainforest classifier model. Particularly, the accuracy of the voting classifier was ascertained to be 94.57%, illustrating that approximately 94.17% of its predictions were correct as contrasted to the Random Forest. Besides, the precision of the voting classifier was ascertained to be 93.78%, implying that it correctly pinpointed positive data points 93.78% of the time. Remarkably, the Voting Classifier for the Ensemble Learning with Feature Engineering Model technique surpassed the performance of most other techniques, demonstrating an accuracy rate of 94.57%. These techniques provide protective and preventive measures to resolve the vulnerabilities and challenges faced by geographically distributed power systems.","PeriodicalId":509154,"journal":{"name":"Journal of Computer Science and Technology Studies","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140491870","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-26DOI: 10.32996/jcsts.2024.6.1.14
Hao, Kun, Huang, Yongchao, Hou, Bang, Yu, Junli
The purpose of this study was to identify the variables that may influence how well students at particular Chinese computer schools are able to maintain their computer systems. It also looked into the types of technology-related leadership behaviors program administrators demonstrated how those behaviors affected and possibly even predicted the various ways that technology was used in schools. Based on the findings, it was determined that the factors that can affect the improvement of information technology students' skills in computer system maintenance were not significantly influenced by time management, test preparation, or reading in terms of sex, monthly family income, or academic performance.
{"title":"Factors Affecting Computer System Maintenance Skills Improvement of Information Technology Students","authors":"Hao, Kun, Huang, Yongchao, Hou, Bang, Yu, Junli","doi":"10.32996/jcsts.2024.6.1.14","DOIUrl":"https://doi.org/10.32996/jcsts.2024.6.1.14","url":null,"abstract":"The purpose of this study was to identify the variables that may influence how well students at particular Chinese computer schools are able to maintain their computer systems. It also looked into the types of technology-related leadership behaviors program administrators demonstrated how those behaviors affected and possibly even predicted the various ways that technology was used in schools. Based on the findings, it was determined that the factors that can affect the improvement of information technology students' skills in computer system maintenance were not significantly influenced by time management, test preparation, or reading in terms of sex, monthly family income, or academic performance.","PeriodicalId":509154,"journal":{"name":"Journal of Computer Science and Technology Studies","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140493629","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-03DOI: 10.32996/jcsts.2024.6.1.6
Ansarullah Hasas, Mohammad Shuaib Zarinkhail, Musawer Hakimi, Mohammad Mustafa Quchi
Digital security is an ever-escalating concern in today's interconnected world, necessitating advanced intrusion detection systems. This research focuses on fortifying digital security through the integration of Long Short-Term Memory (LSTM), K-Nearest Neighbors (KNN), and Random Forest for dynamic attack detection. Leveraging a robust dataset, the models were subjected to rigorous evaluation, considering metrics such as accuracy, precision, recall, F1-score, and AUC-ROC. The LSTM model exhibited exceptional proficiency in capturing intricate sequential dependencies within network traffic, attaining a commendable accuracy of 99.11%. KNN, with its non-parametric adaptability, demonstrated resilience with a high accuracy of 99.23%. However, the Random Forest model emerged as the standout performer, boasting an accuracy of 99.63% and showcasing exceptional precision, recall, and F1-score metrics. Comparative analyses unveiled nuanced differences, guiding the selection of models based on specific security requirements. The AUC-ROC comparison reinforced the discriminative power of the models, with Random Forest consistently excelling. While all models excelled in true positive predictions, detailed scrutiny of confusion matrices offered insights into areas for refinement. In conclusion, the integration of LSTM, KNN, and Random Forest presents a robust and adaptive approach to dynamic attack detection. This research contributes valuable insights to the evolving landscape of digital security, emphasizing the significance of leveraging advanced machine learning techniques in constructing resilient defenses against cyber adversaries. The findings underscore the need for adaptive security solutions as the cyber threat landscape continues to evolve, with implications for practitioners, researchers, and policymakers in the field of cybersecurity.
{"title":"Strengthening Digital Security: Dynamic Attack Detection with LSTM, KNN, and Random Forest","authors":"Ansarullah Hasas, Mohammad Shuaib Zarinkhail, Musawer Hakimi, Mohammad Mustafa Quchi","doi":"10.32996/jcsts.2024.6.1.6","DOIUrl":"https://doi.org/10.32996/jcsts.2024.6.1.6","url":null,"abstract":"Digital security is an ever-escalating concern in today's interconnected world, necessitating advanced intrusion detection systems. This research focuses on fortifying digital security through the integration of Long Short-Term Memory (LSTM), K-Nearest Neighbors (KNN), and Random Forest for dynamic attack detection. Leveraging a robust dataset, the models were subjected to rigorous evaluation, considering metrics such as accuracy, precision, recall, F1-score, and AUC-ROC. The LSTM model exhibited exceptional proficiency in capturing intricate sequential dependencies within network traffic, attaining a commendable accuracy of 99.11%. KNN, with its non-parametric adaptability, demonstrated resilience with a high accuracy of 99.23%. However, the Random Forest model emerged as the standout performer, boasting an accuracy of 99.63% and showcasing exceptional precision, recall, and F1-score metrics. Comparative analyses unveiled nuanced differences, guiding the selection of models based on specific security requirements. The AUC-ROC comparison reinforced the discriminative power of the models, with Random Forest consistently excelling. While all models excelled in true positive predictions, detailed scrutiny of confusion matrices offered insights into areas for refinement. In conclusion, the integration of LSTM, KNN, and Random Forest presents a robust and adaptive approach to dynamic attack detection. This research contributes valuable insights to the evolving landscape of digital security, emphasizing the significance of leveraging advanced machine learning techniques in constructing resilient defenses against cyber adversaries. The findings underscore the need for adaptive security solutions as the cyber threat landscape continues to evolve, with implications for practitioners, researchers, and policymakers in the field of cybersecurity.","PeriodicalId":509154,"journal":{"name":"Journal of Computer Science and Technology Studies","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139388238","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-02DOI: 10.32996/jcsts.2024.6.1.3
Md Abdur Rakib Rahat, MD Tanvir Islam, Duc M Cao, Maliha Tayaba, Bishnu Padh Ghosh, Eftekhar Hossain Ayon, Nur Nob, Aslima Akter, Mamunur Rahman, Mohammad Shafiquzzaman Bhuiyan
In medical care, side effect trial and error processes are utilized for the discovery of hidden reasons for ailments and the determination of conditions. In our exploration, we used a crossbreed strategy to refine our optimal model, improving the Pearson relationship for highlight choice purposes. The underlying stage included the choice of ideal models through a careful survey of the current writing. Hence, our proposed half-and-half model incorporated a blend of these models. The base classifiers utilized included XGBoost, Arbitrary Woods, Strategic Relapse, AdaBoost, and the Crossover model classifiers, while the Meta classifier was the Irregular Timberland classifier. The essential target of this examination was to evaluate the best AI grouping techniques and decide the best classifier concerning accuracy. This approach resolved the issue of overfitting and accomplished the most elevated level of exactness. The essential focal point of the assessment was precision, and we introduced a far-reaching examination of the significant writing in even configuration. To carry out our methodology, we used four top-performing AI models and fostered another model named "half and half," utilizing the UCI Persistent Kidney Disappointment dataset for prescient purposes. In our experiment, we found out that the AI model XGBoost classifier gains almost 94% accuracy, a random forest gains 93% accuracy, Logistic Regression about 90% accuracy, AdaBoost gains 91% accuracy, and our proposed new model named hybrid gains the highest 95% accuracy, and performance of Hybrid model is best on this equivalent dataset. Various noticeable AI models have been utilized to foresee the event of persistent kidney disappointment (CKF). These models incorporate Naïve Bayes, Random Forest, Decision Tree, Support Vector Machine, K-nearest neighbor, LDA (Linear Discriminant Analysis), GB (Gradient Boosting), and neural networks. In our examination, we explicitly used XGBoost, AdaBoost, Logistic Regression, Random Forest, and Hybrid models with the equivalent dataset of highlights to analyze their accuracy scores.
{"title":"Comparing Machine Learning Techniques for Detecting Chronic Kidney Disease in Early Stage","authors":"Md Abdur Rakib Rahat, MD Tanvir Islam, Duc M Cao, Maliha Tayaba, Bishnu Padh Ghosh, Eftekhar Hossain Ayon, Nur Nob, Aslima Akter, Mamunur Rahman, Mohammad Shafiquzzaman Bhuiyan","doi":"10.32996/jcsts.2024.6.1.3","DOIUrl":"https://doi.org/10.32996/jcsts.2024.6.1.3","url":null,"abstract":"In medical care, side effect trial and error processes are utilized for the discovery of hidden reasons for ailments and the determination of conditions. In our exploration, we used a crossbreed strategy to refine our optimal model, improving the Pearson relationship for highlight choice purposes. The underlying stage included the choice of ideal models through a careful survey of the current writing. Hence, our proposed half-and-half model incorporated a blend of these models. The base classifiers utilized included XGBoost, Arbitrary Woods, Strategic Relapse, AdaBoost, and the Crossover model classifiers, while the Meta classifier was the Irregular Timberland classifier. The essential target of this examination was to evaluate the best AI grouping techniques and decide the best classifier concerning accuracy. This approach resolved the issue of overfitting and accomplished the most elevated level of exactness. The essential focal point of the assessment was precision, and we introduced a far-reaching examination of the significant writing in even configuration. To carry out our methodology, we used four top-performing AI models and fostered another model named \"half and half,\" utilizing the UCI Persistent Kidney Disappointment dataset for prescient purposes. In our experiment, we found out that the AI model XGBoost classifier gains almost 94% accuracy, a random forest gains 93% accuracy, Logistic Regression about 90% accuracy, AdaBoost gains 91% accuracy, and our proposed new model named hybrid gains the highest 95% accuracy, and performance of Hybrid model is best on this equivalent dataset. Various noticeable AI models have been utilized to foresee the event of persistent kidney disappointment (CKF). These models incorporate Naïve Bayes, Random Forest, Decision Tree, Support Vector Machine, K-nearest neighbor, LDA (Linear Discriminant Analysis), GB (Gradient Boosting), and neural networks. In our examination, we explicitly used XGBoost, AdaBoost, Logistic Regression, Random Forest, and Hybrid models with the equivalent dataset of highlights to analyze their accuracy scores.","PeriodicalId":509154,"journal":{"name":"Journal of Computer Science and Technology Studies","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139391323","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：