In today’s digital era, businesses are actively generating an astonishing 2.5 quintillion bytes of data every single day. For those of you wondering how much that is—well, there are 18 zeroes at a quintillion! With people using social media platforms, digital communication channels, and various contactless services, it is no surprise that big data continues to grow at a colossal rate. But how can we harness the potential of all this information in the future? And what’s machine learning have to do with it? First of all we have To better understand the future of machine learning, one must be able to differentiate between these 3 concepts deep learning (DL), artificial intelligence (AI) and machine learning (ML) interchangeably. machine learning (ML)
{"title":"Machine Learning and their Importance","authors":"Priyanka R. Gondaliya","doi":"10.55041/ijsrem36768","DOIUrl":"https://doi.org/10.55041/ijsrem36768","url":null,"abstract":"In today’s digital era, businesses are actively generating an astonishing 2.5 quintillion bytes of data every single day. For those of you wondering how much that is—well, there are 18 zeroes at a quintillion! With people using social media platforms, digital communication channels, and various contactless services, it is no surprise that big data continues to grow at a colossal rate. But how can we harness the potential of all this information in the future? And what’s machine learning have to do with it? First of all we have To better understand the future of machine learning, one must be able to differentiate between these 3 concepts deep learning (DL), artificial intelligence (AI) and machine learning (ML) interchangeably. machine learning (ML)","PeriodicalId":504501,"journal":{"name":"INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT","volume":"114 23","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141802117","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}
This research proposes Narrative Canvas, a novel framework for Stable Diffusion-based story-inspired picture synthesis. Our method uses deep learning models to produce visually appealing and logical drawings from narrative inputs. Through the integration of cutting-edge text-to-image synthesis algorithms, Narrative Canvas ensures that images faithfully convey the story's central themes and maintain character consistency. The suggested technique trains and fine-tunes the model using the COYO-300M data set, allowing it to handle a variety of storytelling aspects with effectiveness. The outcomes of our experiments show that our system can generate high-quality visuals that complement the storyline and improve the storytelling experience. This work creates new opportunities for automated content generation, especially in interactive media, digital art, and children's literature. Key Words: Story-inspired image synthesis, Stable Diffusion, deep learning, text-to-image synthesis, narrative consistency, COYO-300M data set, automated content creation
{"title":"Narrative Canvas: Story-Inspired Image Synthesis","authors":"Harshitha G N, Ms. Jeevitha M","doi":"10.55041/ijsrem36822","DOIUrl":"https://doi.org/10.55041/ijsrem36822","url":null,"abstract":"This research proposes Narrative Canvas, a novel framework for Stable Diffusion-based story-inspired picture synthesis. Our method uses deep learning models to produce visually appealing and logical drawings from narrative inputs. Through the integration of cutting-edge text-to-image synthesis algorithms, Narrative Canvas ensures that images faithfully convey the story's central themes and maintain character consistency. The suggested technique trains and fine-tunes the model using the COYO-300M data set, allowing it to handle a variety of storytelling aspects with effectiveness. The outcomes of our experiments show that our system can generate high-quality visuals that complement the storyline and improve the storytelling experience. This work creates new opportunities for automated content generation, especially in interactive media, digital art, and children's literature. Key Words: Story-inspired image synthesis, Stable Diffusion, deep learning, text-to-image synthesis, narrative consistency, COYO-300M data set, automated content creation","PeriodicalId":504501,"journal":{"name":"INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT","volume":"6 11","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141801225","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}
As our world becomes more and more dependent on cyberspace in all fields, the number of cyber threats, their frequency and complexity have risen with an alarming rate. There are many forms of illegal activities committed over the internet, and together they form cyber-threats; from malware to phishing attacks, APT (advanced persistent threats), ransomware etc. Traditional security sits interaction of these threats is still limited compared to evolving nature, and hardly mitigates zero day attacks. As a result, Machine learning (ML) has become an essential indeed much-needed technology to empower Cyber threat detection and response. This paper investigates the increase in cyber threats as well as how cybersecurity techniques are perpetually enforced, while analysing methodology used by hackers. Here, we investigate a few of the bleeding-edge ML techniques being applied to detect and fight cyber threats from deep learning models like Convolutional Neural Networks (CNNs), Recurrent Neural Network, ensemble learning methods such as Random Forest and Support Vector Machine (SVM). This comprehensive overview highlights the effectiveness of these ML techniques in identifying and mitigating cyber threats, emphasizing the need for continuous innovation to stay ahead of increasingly sophisticated cybercriminal activities. KEYWORDS: Cyber Threat; Cybercrime; Machine Learning Application; Malware; Phishing; Ransomware; Spam;
随着我们的世界在各个领域越来越依赖网络空间,网络威胁的数量、频率和复杂性也以惊人的速度上升。通过互联网实施的非法活动形式多样,它们共同构成了网络威胁;从恶意软件到网络钓鱼攻击、APT(高级持续性威胁)、勒索软件等。与不断发展的性质相比,传统的安全解决方案对这些威胁的交互仍然有限,很难缓解零日攻击。因此,机器学习(ML)已成为增强网络威胁检测和响应能力的一项必不可少且亟需的技术。本文在分析黑客使用的方法的同时,还调查了网络威胁的增加情况以及网络安全技术是如何被不断执行的。在这里,我们研究了一些用于检测和应对网络威胁的前沿 ML 技术,包括卷积神经网络(CNN)、循环神经网络等深度学习模型,以及随机森林和支持向量机(SVM)等集合学习方法。本综述重点介绍了这些 ML 技术在识别和减轻网络威胁方面的有效性,强调了不断创新以应对日益复杂的网络犯罪活动的必要性。关键词: 网络威胁;网络犯罪;机器学习应用;恶意软件;网络钓鱼;勒索软件;垃圾邮件;
{"title":"Cyber Threat Detection Using Machine Learning","authors":"Prakriti Prakriti","doi":"10.55041/ijsrem36799","DOIUrl":"https://doi.org/10.55041/ijsrem36799","url":null,"abstract":"As our world becomes more and more dependent on cyberspace in all fields, the number of cyber threats, their frequency and complexity have risen with an alarming rate. There are many forms of illegal activities committed over the internet, and together they form cyber-threats; from malware to phishing attacks, APT (advanced persistent threats), ransomware etc. Traditional security sits interaction of these threats is still limited compared to evolving nature, and hardly mitigates zero day attacks. As a result, Machine learning (ML) has become an essential indeed much-needed technology to empower Cyber threat detection and response. This paper investigates the increase in cyber threats as well as how cybersecurity techniques are perpetually enforced, while analysing methodology used by hackers. Here, we investigate a few of the bleeding-edge ML techniques being applied to detect and fight cyber threats from deep learning models like Convolutional Neural Networks (CNNs), Recurrent Neural Network, ensemble learning methods such as Random Forest and Support Vector Machine (SVM). This comprehensive overview highlights the effectiveness of these ML techniques in identifying and mitigating cyber threats, emphasizing the need for continuous innovation to stay ahead of increasingly sophisticated cybercriminal activities. KEYWORDS: Cyber Threat; Cybercrime; Machine Learning Application; Malware; Phishing; Ransomware; Spam;","PeriodicalId":504501,"journal":{"name":"INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT","volume":"21 9","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141801663","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The goal of this task, "Pancreatic Cancer Prediction Using Random Forest Classifier," is to create a reliable predictive model for categorizing pancreatic diseases. It focuses on three main categories: control cases (no pancreatic disease), benign hepatobiliary diseases (like chronic pancreatitis), and pancreatic ductal adenocarcinoma (pancreatic cancer). The model is trained on biomarker data, such as plasma_CA19_9, creatinine, LYVE1, REG1B, TFF1, and REG1A, by utilizing the capabilities of machine learning, specifically a Random Forest classifier. The goal is to use patient biomarker profiles to accurately distinguish between various illnesses. The purpose of this tool is to help medical practitioners manage pancreatic disorders early on, allocate treatments appropriately, and improve patient outcomes. Keyword: Pancreatic Cancer, Random Forest Classifier, Disease Classification, Machine Learning.
{"title":"Pancreatic Cancer Prediction Using Random Forest Classifier","authors":"D. M, D. Bg","doi":"10.55041/ijsrem36818","DOIUrl":"https://doi.org/10.55041/ijsrem36818","url":null,"abstract":"The goal of this task, \"Pancreatic Cancer Prediction Using Random Forest Classifier,\" is to create a reliable predictive model for categorizing pancreatic diseases. It focuses on three main categories: control cases (no pancreatic disease), benign hepatobiliary diseases (like chronic pancreatitis), and pancreatic ductal adenocarcinoma (pancreatic cancer). The model is trained on biomarker data, such as plasma_CA19_9, creatinine, LYVE1, REG1B, TFF1, and REG1A, by utilizing the capabilities of machine learning, specifically a Random Forest classifier. The goal is to use patient biomarker profiles to accurately distinguish between various illnesses. The purpose of this tool is to help medical practitioners manage pancreatic disorders early on, allocate treatments appropriately, and improve patient outcomes. Keyword: Pancreatic Cancer, Random Forest Classifier, Disease Classification, Machine Learning.","PeriodicalId":504501,"journal":{"name":"INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT","volume":"59 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141799038","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}
Accurately predicting stock market prices is vital in today’s economy, leading researchers to explore novel approaches for forecasting. Recent studies have shown that historical stock data, search engine queries, and social mood from platforms like Twitter and news websites can predict future stock prices. Previous research often lacked comprehensive data, especially concerning social mood. This study presents an effective method to integrate multiple information sources to address this gap and enhance prediction accuracy. We utilized Long Short-Term Memory (LSTM) and Recurrent Neural Network (RNN) models to analyse individual data sources. To further improve prediction accuracy, we employed an ensemble method combining Weighted Average and Differential Evolution techniques. The results yielded precise forecasts for one-day, seven-day, 15-day, and 30- day intervals, providing valuable insights for investors and helping companies gauge their future market performance. Keywords-- Stock market prediction; Sentiment Analysis; Neural Networks; Long-short Term Memory Neural Networks, DJIA, Ensemble Method, Weighted Average
{"title":"Stock Market Predictions Using Machine Learning Techniques","authors":"Nagapoojitha D N","doi":"10.55041/ijsrem36812","DOIUrl":"https://doi.org/10.55041/ijsrem36812","url":null,"abstract":"Accurately predicting stock market prices is vital in today’s economy, leading researchers to explore novel approaches for forecasting. Recent studies have shown that historical stock data, search engine queries, and social mood from platforms like Twitter and news websites can predict future stock prices. Previous research often lacked comprehensive data, especially concerning social mood. This study presents an effective method to integrate multiple information sources to address this gap and enhance prediction accuracy. We utilized Long Short-Term Memory (LSTM) and Recurrent Neural Network (RNN) models to analyse individual data sources. To further improve prediction accuracy, we employed an ensemble method combining Weighted Average and Differential Evolution techniques. The results yielded precise forecasts for one-day, seven-day, 15-day, and 30- day intervals, providing valuable insights for investors and helping companies gauge their future market performance. Keywords-- Stock market prediction; Sentiment Analysis; Neural Networks; Long-short Term Memory Neural Networks, DJIA, Ensemble Method, Weighted Average","PeriodicalId":504501,"journal":{"name":"INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT","volume":"51 8","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141799905","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract—With faster and more dependable connectivity, 5G technology has completely changed the wireless network sector and set the stage for the ”Internet of Things” (IoT). We anticipate the advent of ”smart cities” with 5G, where traffic signals, energy grids, and emergency services are connected to minimize inefficiencies. Much more substantial breakthroughs in wireless technology are anticipated with the release of the next generation. Although the exact nature of 6G remains unclear, researchers are actively investigating novel technologies that may provide even faster data transfer rates, reduced latency, and increased connection. According to some analysts, 6G may make it possible for technologies like the Internet of Nano-Things (IoNT) and augmented and virtual reality to become widely used. The possibilities are infinite once 6G is deployed. The possibility of quantum communication, which would provide unmatched speed and security, is being investigated by certain researchers. Some are in the process of creating novel wireless technologies that may allow nanoscale device communication. Even though these technologies are still in their infancy, they have the power to completely change how we engage with one another and the world at large. The possibilities for wireless networks seem limitless when we consider their future. The next wave of wireless technology, 5G and beyond, has the power to completely alter industry, communication, and society as a whole. We may anticipate fresh and interesting developments in the years to come thanks to continued research and development.
{"title":"From 5G Technology to Infinity whats next in Wireless Network","authors":"Preethi L C, Pooja Pooja, Mrs. Roopa H M","doi":"10.55041/ijsrem36801","DOIUrl":"https://doi.org/10.55041/ijsrem36801","url":null,"abstract":"Abstract—With faster and more dependable connectivity, 5G technology has completely changed the wireless network sector and set the stage for the ”Internet of Things” (IoT). We anticipate the advent of ”smart cities” with 5G, where traffic signals, energy grids, and emergency services are connected to minimize inefficiencies. Much more substantial breakthroughs in wireless technology are anticipated with the release of the next generation. Although the exact nature of 6G remains unclear, researchers are actively investigating novel technologies that may provide even faster data transfer rates, reduced latency, and increased connection. According to some analysts, 6G may make it possible for technologies like the Internet of Nano-Things (IoNT) and augmented and virtual reality to become widely used. The possibilities are infinite once 6G is deployed. The possibility of quantum communication, which would provide unmatched speed and security, is being investigated by certain researchers. Some are in the process of creating novel wireless technologies that may allow nanoscale device communication. Even though these technologies are still in their infancy, they have the power to completely change how we engage with one another and the world at large. The possibilities for wireless networks seem limitless when we consider their future. The next wave of wireless technology, 5G and beyond, has the power to completely alter industry, communication, and society as a whole. We may anticipate fresh and interesting developments in the years to come thanks to continued research and development.","PeriodicalId":504501,"journal":{"name":"INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT","volume":"28 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141800557","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}
Artificial intelligence (AI) has significantly impacted various industries, including disaster recovery (DR) planning for IT Applications, virtualization, and Databases. With the growth of servers, Data, and advancements in AI, real-time analytics and time-sensitive applications are now feasible. In disaster recovery, AI can automate processes, initiate DR plans swiftly during untimely downtimes in the IT industry whether it is enterprises, BFSI, manufacturing, or health care IT applications, and provide critical insights. This paper discusses use cases for AI in the DR workflow: pre- disaster, implementation, and aftermath. The benefits and challenges of AI adoption in disaster management are also highlighted.
人工智能(AI)对各行各业产生了重大影响,包括 IT 应用程序、虚拟化和数据库的灾难恢复(DR)规划。随着服务器、数据的增长和人工智能的进步,实时分析和时间敏感型应用现在变得可行。在灾难恢复方面,人工智能可以实现流程自动化,在 IT 行业(无论是企业、BFSI、制造业还是医疗保健 IT 应用程序)出现意外宕机时迅速启动灾难恢复计划,并提供重要见解。本文讨论了灾难恢复工作流程中的人工智能用例:灾难前、实施和灾难后。本文还强调了在灾难管理中采用人工智能的好处和挑战。
{"title":"AI use in Automated Disaster Recovery for IT Applications in Multi Cloud","authors":"Rishiraj Nandedkar","doi":"10.55041/ijsrem36816","DOIUrl":"https://doi.org/10.55041/ijsrem36816","url":null,"abstract":"Artificial intelligence (AI) has significantly impacted various industries, including disaster recovery (DR) planning for IT Applications, virtualization, and Databases. With the growth of servers, Data, and advancements in AI, real-time analytics and time-sensitive applications are now feasible. In disaster recovery, AI can automate processes, initiate DR plans swiftly during untimely downtimes in the IT industry whether it is enterprises, BFSI, manufacturing, or health care IT applications, and provide critical insights. This paper discusses use cases for AI in the DR workflow: pre- disaster, implementation, and aftermath. The benefits and challenges of AI adoption in disaster management are also highlighted.","PeriodicalId":504501,"journal":{"name":"INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT","volume":"46 12","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141798991","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract—The goal of abstract design is to create visually ar- resting and thought-provoking user interfaces without necessarily depending on realistic representations. It entails utilizing bold colors, unusual shapes, and imaginative typography to create a singular and engrossing user experience. Art, architecture, and even surrealism are all frequently included into abstract design to create a surreal ambiance that emotionally connects with people. Abstract design has the power to arouse emotions, ignite the imagination, and even subvert consumers’ preconceptions by defying conventional design standards. Abstract components are useful in web design because they can be utilized to make websites stand out from the competition with dynamic backgrounds, inter- active animations, and creative navigation.Abstract components in web design can give a website a sophisticated, creative touch. In abstract design, non-representational shapes, forms, and colors are used to create a distinct visual language that does not always replicate scenes or items from the real world. This method can produce visually arresting and thought-provoking user interfaces that emotionally connect with users. Innovative navigation sys- tems, dynamic backgrounds, and interactive animations may all be made with abstract design to make a website stand out from the competition. Web designers can defy conventional design rules and produce a genuinely immersive user experience that makes an impression by introducing abstract components.
{"title":"Web Design Encompasses UI,UX and Responsive Development","authors":"K. Bhoomika, Dr Rajani Narayan","doi":"10.55041/ijsrem36809","DOIUrl":"https://doi.org/10.55041/ijsrem36809","url":null,"abstract":"Abstract—The goal of abstract design is to create visually ar- resting and thought-provoking user interfaces without necessarily depending on realistic representations. It entails utilizing bold colors, unusual shapes, and imaginative typography to create a singular and engrossing user experience. Art, architecture, and even surrealism are all frequently included into abstract design to create a surreal ambiance that emotionally connects with people. Abstract design has the power to arouse emotions, ignite the imagination, and even subvert consumers’ preconceptions by defying conventional design standards. Abstract components are useful in web design because they can be utilized to make websites stand out from the competition with dynamic backgrounds, inter- active animations, and creative navigation.Abstract components in web design can give a website a sophisticated, creative touch. In abstract design, non-representational shapes, forms, and colors are used to create a distinct visual language that does not always replicate scenes or items from the real world. This method can produce visually arresting and thought-provoking user interfaces that emotionally connect with users. Innovative navigation sys- tems, dynamic backgrounds, and interactive animations may all be made with abstract design to make a website stand out from the competition. Web designers can defy conventional design rules and produce a genuinely immersive user experience that makes an impression by introducing abstract components.","PeriodicalId":504501,"journal":{"name":"INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT","volume":"19 8","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141799271","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}
Ms. Nikita Kotangale, Dr.Shrikant Sonekar, D. S. S. Sawwashere, Prof. Mirza Moiz Baig
Now a days intrusion detection systems are essential for defending computer networking toward hostile activity. With the increasing complexity and diversity of modern cyber threats, traditional single-classifier-based IDS approaches often struggle to achieve optimal detection performance. To address this challenge, this study proposes an Intrusion Detection System using Ensemble Machine Learning. The methodology combines the strengths of multiple machine learning algorithms in an ensemble framework to enhance the accuracy, robustness, and efficiency of intrusion detection. The system incorporates steps such as data preprocessing, feature selection, ensemble model construction, and model performance. Techniques like data balancing, attribute encoding, and feature selection based on correlation are applied to optimize the IDS performance. The ensemble model benefits from the collective intelligence and diverse decision-making of multiple classifiers, improving the system's ability to accurately identify and respond to network intrusions. Through comprehensive result analysis, the study validates the effectiveness of the proposed IDS in terms of evaluation metrics, feature importance, robustness, and real- world impact. The proposed IDS using Ensemble Machine Learning offers a promising approach to tackle the dynamic and evolving nature of cyber threats, enhancing the security and resilience of computer networks. Keywords - Intrusion Detection System, Ensemble Machine Learning, Data Balancing, Feature Selection, Cyber Security.
{"title":"Intrusion Detection using Ensemble Machine Learning","authors":"Ms. Nikita Kotangale, Dr.Shrikant Sonekar, D. S. S. Sawwashere, Prof. Mirza Moiz Baig","doi":"10.55041/ijsrem36806","DOIUrl":"https://doi.org/10.55041/ijsrem36806","url":null,"abstract":"Now a days intrusion detection systems are essential for defending computer networking toward hostile activity. With the increasing complexity and diversity of modern cyber threats, traditional single-classifier-based IDS approaches often struggle to achieve optimal detection performance. To address this challenge, this study proposes an Intrusion Detection System using Ensemble Machine Learning. The methodology combines the strengths of multiple machine learning algorithms in an ensemble framework to enhance the accuracy, robustness, and efficiency of intrusion detection. The system incorporates steps such as data preprocessing, feature selection, ensemble model construction, and model performance. Techniques like data balancing, attribute encoding, and feature selection based on correlation are applied to optimize the IDS performance. The ensemble model benefits from the collective intelligence and diverse decision-making of multiple classifiers, improving the system's ability to accurately identify and respond to network intrusions. Through comprehensive result analysis, the study validates the effectiveness of the proposed IDS in terms of evaluation metrics, feature importance, robustness, and real- world impact. The proposed IDS using Ensemble Machine Learning offers a promising approach to tackle the dynamic and evolving nature of cyber threats, enhancing the security and resilience of computer networks. Keywords - Intrusion Detection System, Ensemble Machine Learning, Data Balancing, Feature Selection, Cyber Security.","PeriodicalId":504501,"journal":{"name":"INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT","volume":"8 6","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141801040","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}
Payal Singh, Dr. R.R.L Birali, Akhand Pratap Singh
Asset management is a systematic process focused on maintaining, upgrading, and operating assets effectively. Numerous agencies have adopted asset management principles as a strategic tool to define goals and prioritize resources for decision-making. In the realm of road asset management, key components include bridges, traffic signs, pavement markings, and culverts. This project aims to develop a comprehensive Traffic Sign Asset Management System tailored for the Indian context. The core of this system involves a visual nighttime inspection method to assess the retro-reflectivity of traffic signs. Regular nighttime surveys will be conducted using vehicle high beam lights to evaluate the visibility of each sign. Signs failing to meet visibility standards will be identified, and maintenance or replacement actions will be recommended accordingly. The study highlights the importance of integrating asset management programs into decision-making processes. It includes a detailed cost analysis of each traffic sign, covering both manufacturing and maintenance costs. The project also involves recording the latitude and longitude of each sign, creating a detailed map using ArcGIS to plot the exact positions of all traffic signs. Key findings of the study emphasize the need for formal asset management programs to improve traffic sign visibility and maintenance. This research provides a foundational framework for establishing a traffic sign asset management system in India, ensuring that traffic signs are adequately maintained and managed for optimal road safety. Keywords: Asset Management, Traffic Signs, Management Methods, ArcGIS, Cost Analysis, Retro-reflectivity
{"title":"Improving Traffic Sign Management: Creating An Indian Specific-Asset Management System","authors":"Payal Singh, Dr. R.R.L Birali, Akhand Pratap Singh","doi":"10.55041/ijsrem36837","DOIUrl":"https://doi.org/10.55041/ijsrem36837","url":null,"abstract":"Asset management is a systematic process focused on maintaining, upgrading, and operating assets effectively. Numerous agencies have adopted asset management principles as a strategic tool to define goals and prioritize resources for decision-making. In the realm of road asset management, key components include bridges, traffic signs, pavement markings, and culverts. This project aims to develop a comprehensive Traffic Sign Asset Management System tailored for the Indian context. The core of this system involves a visual nighttime inspection method to assess the retro-reflectivity of traffic signs. Regular nighttime surveys will be conducted using vehicle high beam lights to evaluate the visibility of each sign. Signs failing to meet visibility standards will be identified, and maintenance or replacement actions will be recommended accordingly. The study highlights the importance of integrating asset management programs into decision-making processes. It includes a detailed cost analysis of each traffic sign, covering both manufacturing and maintenance costs. The project also involves recording the latitude and longitude of each sign, creating a detailed map using ArcGIS to plot the exact positions of all traffic signs. Key findings of the study emphasize the need for formal asset management programs to improve traffic sign visibility and maintenance. This research provides a foundational framework for establishing a traffic sign asset management system in India, ensuring that traffic signs are adequately maintained and managed for optimal road safety. Keywords: Asset Management, Traffic Signs, Management Methods, ArcGIS, Cost Analysis, Retro-reflectivity","PeriodicalId":504501,"journal":{"name":"INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT","volume":"28 7","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141801795","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}