Pub Date : 2024-05-21DOI: 10.47392/irjaeh.2024.0184
Arun Sebastian, Dr Asaletha Raghavan
One of the increasingly common unexpected outcomes of the extensive usage of electronic devices and systems is electromagnetic interference (EMI). The need for efficient fillers and shielding materials to manage electromagnetic interference (EMI) and associated issues is rising. Adding more filler typically means greater production costs, poor dispersion, and unintended agglomeration, which makes polymer composites harder to work with and mechanically weak. Therefore, it is highly desired to design a strong composite with conductive filler content that nonetheless performs well as an EMI shield. Therefore, using a graphene substrate and dispersion of conducting polymers such as polyacetylene and MWCNT fillers, a hybrid polymer composite based on polyetherimide is proposed in this research. Next, the enhancement of EMI shielding efficiency is examined. The design of the graphene substrate was completed with a coating based on nano filler, and the blending methods of the polymer matrix and the reinforcing filler materials are explored. ANSYS-HFSS software is then used to assess the shield's efficacy among others, and the results demonstrated improved performance. Therefore, by putting the suggested design into practice, high-performance EMI shielding materials can be created by combining various shield fillers. As a result, the composites' mechanical, electrical, and EMI shielding qualities will all improve.
{"title":"Advanced Polymer Composite with Graphene Content for Emi Shielding","authors":"Arun Sebastian, Dr Asaletha Raghavan","doi":"10.47392/irjaeh.2024.0184","DOIUrl":"https://doi.org/10.47392/irjaeh.2024.0184","url":null,"abstract":"One of the increasingly common unexpected outcomes of the extensive usage of electronic devices and systems is electromagnetic interference (EMI). The need for efficient fillers and shielding materials to manage electromagnetic interference (EMI) and associated issues is rising. Adding more filler typically means greater production costs, poor dispersion, and unintended agglomeration, which makes polymer composites harder to work with and mechanically weak. Therefore, it is highly desired to design a strong composite with conductive filler content that nonetheless performs well as an EMI shield. Therefore, using a graphene substrate and dispersion of conducting polymers such as polyacetylene and MWCNT fillers, a hybrid polymer composite based on polyetherimide is proposed in this research. Next, the enhancement of EMI shielding efficiency is examined. The design of the graphene substrate was completed with a coating based on nano filler, and the blending methods of the polymer matrix and the reinforcing filler materials are explored. ANSYS-HFSS software is then used to assess the shield's efficacy among others, and the results demonstrated improved performance. Therefore, by putting the suggested design into practice, high-performance EMI shielding materials can be created by combining various shield fillers. As a result, the composites' mechanical, electrical, and EMI shielding qualities will all improve.","PeriodicalId":517766,"journal":{"name":"International Research Journal on Advanced Engineering Hub (IRJAEH)","volume":"34 15","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141118250","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 : 2024-05-21DOI: 10.47392/irjaeh.2024.0171
M. Vinitha, Dr.B. Nagarajanaik, Mallikarjuna Nandi, C. Naga, Sri Charan, K. Priyanka
Fashion recommendation systems have become increasingly essential in the e-commerce industry, providing personalized outfit suggestions to users, enhancing their shopping experience, and boosting sales. This paper presents a novel approach to fashion recommendation by combining machine learning and deep learning techniques. We leverage a comprehensive dataset of user preferences and fashion items to create a robust recommendation system. Our approach first employs collaborative filtering and matrix factorization methods to establish user-item interactions. Subsequently, deep learning models, such as neural collaborative filtering and recurrent neural networks, are utilized to capture intricate patterns within the fashion data. This combination enables the system to offer personalized fashion recommendations based on the user's historical choices, style, and real-time Behaviour. The evaluation of our system demonstrates its effectiveness in enhancing user engagement and satisfaction while increasing the platform's revenue. The proposed fashion recommendation system showcases the potential of integrating machine learning and deep learning for optimizing personalized fashion suggestions in the ever- evolving fashion e-commerce landscape. This research contributes to the broader field of recommendation systems and their applications in the fashion industry.
{"title":"Fashion Recommendation System","authors":"M. Vinitha, Dr.B. Nagarajanaik, Mallikarjuna Nandi, C. Naga, Sri Charan, K. Priyanka","doi":"10.47392/irjaeh.2024.0171","DOIUrl":"https://doi.org/10.47392/irjaeh.2024.0171","url":null,"abstract":"Fashion recommendation systems have become increasingly essential in the e-commerce industry, providing personalized outfit suggestions to users, enhancing their shopping experience, and boosting sales. This paper presents a novel approach to fashion recommendation by combining machine learning and deep learning techniques. We leverage a comprehensive dataset of user preferences and fashion items to create a robust recommendation system. Our approach first employs collaborative filtering and matrix factorization methods to establish user-item interactions. Subsequently, deep learning models, such as neural collaborative filtering and recurrent neural networks, are utilized to capture intricate patterns within the fashion data. This combination enables the system to offer personalized fashion recommendations based on the user's historical choices, style, and real-time Behaviour. The evaluation of our system demonstrates its effectiveness in enhancing user engagement and satisfaction while increasing the platform's revenue. The proposed fashion recommendation system showcases the potential of integrating machine learning and deep learning for optimizing personalized fashion suggestions in the ever- evolving fashion e-commerce landscape. This research contributes to the broader field of recommendation systems and their applications in the fashion industry.","PeriodicalId":517766,"journal":{"name":"International Research Journal on Advanced Engineering Hub (IRJAEH)","volume":"130 31","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141115174","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}
Motorcycle accidents and head injuries are critical concerns globally, especially where helmet non-compliance is prevalent. To address this, a multi-domain smart safety helmet is proposed for rider safety and accident prevention through advanced sensor technology. This smart helmet integrates sensors like an MQ-3 alcohol sensor and helmet detection sensors to ensure safety conditions before the motorcycle engine starts. If alcohol levels exceed a threshold, the ignition system disables, preventing intoxicated riding. Helmet detection promotes helmet use, reducing head injury risk. The scalable sensor infrastructure enables multi-domain applications beyond motorcycles. This helmet can integrate into industries like coal mining and firefighting. In coal mining, it monitors environmental conditions and worker vital signs. In firefighting, it detects hazardous gases and monitors firefighter status. During motorcycle operation, the helmet continuously monitors critical parameters—speed, tilt, and environment—providing immediate feedback on unsafe behaviours. In accidents, the helmet's accelerometer detects impacts, activating GPS to pinpoint the location and GSM to alert emergency contacts. This smart helmet aims to enhance motorcycle safety, prevent accidents, and expedite emergency responses. It represents progress towards reducing motorcycle-related injuries and fatalities, with adaptable features for broader safety applications across industries and domains.
{"title":"Multi-Domain Smart Safety Helmet","authors":"Kavitha S, Tammineni Loksai, Vanna Balaji Naidu, Shiva kumar, Venkatesha B","doi":"10.47392/irjaeh.2024.0181","DOIUrl":"https://doi.org/10.47392/irjaeh.2024.0181","url":null,"abstract":"Motorcycle accidents and head injuries are critical concerns globally, especially where helmet non-compliance is prevalent. To address this, a multi-domain smart safety helmet is proposed for rider safety and accident prevention through advanced sensor technology. This smart helmet integrates sensors like an MQ-3 alcohol sensor and helmet detection sensors to ensure safety conditions before the motorcycle engine starts. If alcohol levels exceed a threshold, the ignition system disables, preventing intoxicated riding. Helmet detection promotes helmet use, reducing head injury risk. The scalable sensor infrastructure enables multi-domain applications beyond motorcycles. This helmet can integrate into industries like coal mining and firefighting. In coal mining, it monitors environmental conditions and worker vital signs. In firefighting, it detects hazardous gases and monitors firefighter status. During motorcycle operation, the helmet continuously monitors critical parameters—speed, tilt, and environment—providing immediate feedback on unsafe behaviours. In accidents, the helmet's accelerometer detects impacts, activating GPS to pinpoint the location and GSM to alert emergency contacts. This smart helmet aims to enhance motorcycle safety, prevent accidents, and expedite emergency responses. It represents progress towards reducing motorcycle-related injuries and fatalities, with adaptable features for broader safety applications across industries and domains.","PeriodicalId":517766,"journal":{"name":"International Research Journal on Advanced Engineering Hub (IRJAEH)","volume":"119 43","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141115409","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}
Traditionally, the agricultural supply chains have dealt with a lot of flaws that affect the whole sector. The agricultural industry is undergoing a transformative shift with advanced technologies, particularly Machine Learning. This review depicts the bridging of the gap in the development of agricultural supply chains. ML and AI are found to be powerful tools for making informed decisions regarding challenges like post-harvest losses, price volatility, logistical difficulties, etc. In many review papers, the stated challenges are not addressed completely. The same can be addressed by handling and analyzing the data carefully and properly using ML algorithms to make the system more efficient than the present scenario. We believe these gaps can be bridged with techniques like demand forecasting, optimal resource utilization, supply chain visibility, etc.
传统上，农业供应链存在许多影响整个行业的缺陷。随着先进技术尤其是机器学习技术的发展，农业产业正在经历一场变革。本综述描述了农业供应链发展中的差距。我们发现，ML 和 AI 是针对收获后损失、价格波动、物流困难等挑战做出明智决策的有力工具。在许多综述论文中，所述挑战并未得到彻底解决。通过仔细处理和分析数据，并适当使用 ML 算法，使系统比目前的情况更有效，同样可以解决这些问题。我们相信，这些差距可以通过需求预测、资源优化利用、供应链可视性等技术来弥补。
{"title":"Data-Driven Transformation of Agri-Supply Chain (Ascs): Comprehensive Review","authors":"Piyush Nimbokar, Sanika Yawale, Samiksha Kasulkar, Shreya Patil, Seema Wankhade","doi":"10.47392/irjaeh.2024.0176","DOIUrl":"https://doi.org/10.47392/irjaeh.2024.0176","url":null,"abstract":"Traditionally, the agricultural supply chains have dealt with a lot of flaws that affect the whole sector. The agricultural industry is undergoing a transformative shift with advanced technologies, particularly Machine Learning. This review depicts the bridging of the gap in the development of agricultural supply chains. ML and AI are found to be powerful tools for making informed decisions regarding challenges like post-harvest losses, price volatility, logistical difficulties, etc. In many review papers, the stated challenges are not addressed completely. The same can be addressed by handling and analyzing the data carefully and properly using ML algorithms to make the system more efficient than the present scenario. We believe these gaps can be bridged with techniques like demand forecasting, optimal resource utilization, supply chain visibility, etc.","PeriodicalId":517766,"journal":{"name":"International Research Journal on Advanced Engineering Hub (IRJAEH)","volume":"68 11","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141113937","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 : 2024-05-21DOI: 10.47392/irjaeh.2024.0175
Bhavya Doshi, Anuradha C. Phadke
This work explores the use of Python Turtle graphics as a tool for designing art with programming concepts in creative ways. Turtle graphics is an easy and entertaining approach for learners to visualize and play with code in an artistic manner. The paper explains “Mandala Art Creator”; a Python program to generate a random or customized Mandala Art using the Turtle graphics module and its implementation in the textile industry. In Mandala Art Creator the user is prompted to provide their name and choose between two options: random configuration and personalized configuration. The computer’s algorithm determines colors and angles for the Mandala Art on its own in random mode. The user can customize the Mandala Art experience in custom mode by specifying colors and rotation degrees.
{"title":"Mandala Art Creator: Art with Python Turtle Graphics","authors":"Bhavya Doshi, Anuradha C. Phadke","doi":"10.47392/irjaeh.2024.0175","DOIUrl":"https://doi.org/10.47392/irjaeh.2024.0175","url":null,"abstract":"This work explores the use of Python Turtle graphics as a tool for designing art with programming concepts in creative ways. Turtle graphics is an easy and entertaining approach for learners to visualize and play with code in an artistic manner. The paper explains “Mandala Art Creator”; a Python program to generate a random or customized Mandala Art using the Turtle graphics module and its implementation in the textile industry. In Mandala Art Creator the user is prompted to provide their name and choose between two options: random configuration and personalized configuration. The computer’s algorithm determines colors and angles for the Mandala Art on its own in random mode. The user can customize the Mandala Art experience in custom mode by specifying colors and rotation degrees.","PeriodicalId":517766,"journal":{"name":"International Research Journal on Advanced Engineering Hub (IRJAEH)","volume":"74 20","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141116644","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 study aims to develop an intelligent agricultural yield recommendation framework leveraging the capabilities of AI algorithms. The proposed framework takes yield efficiency and optimal growing seasons as crucial factors in generating appropriate crop recommendations. We have put forth four widely used models, namely Linear Regression (LR) and Multi-Layer Perceptron (MLP), which were trained and evaluated on a comprehensive dataset comprising historical agricultural data encompassing various features such as climatic factors, soil properties, and geographical variables. Furthermore, the data was segmented based on seasonal patterns to provide crop suggestions tailored to specific time periods. The performance of these models was assessed using standard metrics, and an ensemble approach was considered to enhance the system's robustness. Ultimately, the developed framework offers farmers and agricultural professionals a valuable tool for making informed decisions, optimizing crop selection, and enhancing overall agricultural productivity.
{"title":"Crop Recommendation System Using Machine Learning Algorithm","authors":"Ms. Suguna, Prakalya Murali, Pradhusha Ayyasamy, Obuli Obuli","doi":"10.47392/irjaeh.2024.0170","DOIUrl":"https://doi.org/10.47392/irjaeh.2024.0170","url":null,"abstract":"This study aims to develop an intelligent agricultural yield recommendation framework leveraging the capabilities of AI algorithms. The proposed framework takes yield efficiency and optimal growing seasons as crucial factors in generating appropriate crop recommendations. We have put forth four widely used models, namely Linear Regression (LR) and Multi-Layer Perceptron (MLP), which were trained and evaluated on a comprehensive dataset comprising historical agricultural data encompassing various features such as climatic factors, soil properties, and geographical variables. Furthermore, the data was segmented based on seasonal patterns to provide crop suggestions tailored to specific time periods. The performance of these models was assessed using standard metrics, and an ensemble approach was considered to enhance the system's robustness. Ultimately, the developed framework offers farmers and agricultural professionals a valuable tool for making informed decisions, optimizing crop selection, and enhancing overall agricultural productivity.","PeriodicalId":517766,"journal":{"name":"International Research Journal on Advanced Engineering Hub (IRJAEH)","volume":"103 34","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141124916","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 : 2024-05-17DOI: 10.47392/irjaeh.2024.0168
Mr. Pramod S. Aswale, Mrs. Nishigandha Vyawahare, Abhijeet Patange, Prathamesh Hargude, Ganesh Gadkari, Sandesh Patil
Crowdfunding and other forms of digitalized philanthropy have created new channels of communication between donors and fundraisers. Nevertheless, new issues about privacy and security have arisen due to these advancements. Donors may lose trust in conventional techniques due to a lack of transparency on the allocation of their funds, increasing the risk of potential misuse or exploitation. This study suggests a new use of blockchain technology as a viable solution for difficulties in the crowdfunding and charity sectors. By leveraging the inherent immutability, security, and openness of blockchain technology, all transactions and fund allocations are documented on a public ledger accessible to all stakeholders. As a result, our system will operate smoothly. This solution offers real-time donation tracking from the moment of contribution to final expenditure and automates payment distribution using smart contracts. This is done to ensure that contributions are used appropriately. The initiative includes a feedback mechanism for recipients to report on the impact of contributions, setting it apart from other similar schemes. This terminates the relationship between the donors and the beneficiaries. The prototype showcases how blockchain technology may enhance trust and transparency, namely in the realms of crowdfunding and charitable donations. Blockchain-based solutions have the ability to greatly improve the efficiency of fund distribution and the transparency of financial transactions, based on user input and trial results. This can motivate more people to participate in acts of generosity and charity initiatives.
{"title":"Transparent Charity Application and Crowdfunding Using Blockchain","authors":"Mr. Pramod S. Aswale, Mrs. Nishigandha Vyawahare, Abhijeet Patange, Prathamesh Hargude, Ganesh Gadkari, Sandesh Patil","doi":"10.47392/irjaeh.2024.0168","DOIUrl":"https://doi.org/10.47392/irjaeh.2024.0168","url":null,"abstract":"Crowdfunding and other forms of digitalized philanthropy have created new channels of communication between donors and fundraisers. Nevertheless, new issues about privacy and security have arisen due to these advancements. Donors may lose trust in conventional techniques due to a lack of transparency on the allocation of their funds, increasing the risk of potential misuse or exploitation. This study suggests a new use of blockchain technology as a viable solution for difficulties in the crowdfunding and charity sectors. By leveraging the inherent immutability, security, and openness of blockchain technology, all transactions and fund allocations are documented on a public ledger accessible to all stakeholders. As a result, our system will operate smoothly. This solution offers real-time donation tracking from the moment of contribution to final expenditure and automates payment distribution using smart contracts. This is done to ensure that contributions are used appropriately. The initiative includes a feedback mechanism for recipients to report on the impact of contributions, setting it apart from other similar schemes. This terminates the relationship between the donors and the beneficiaries. The prototype showcases how blockchain technology may enhance trust and transparency, namely in the realms of crowdfunding and charitable donations. Blockchain-based solutions have the ability to greatly improve the efficiency of fund distribution and the transparency of financial transactions, based on user input and trial results. This can motivate more people to participate in acts of generosity and charity initiatives.","PeriodicalId":517766,"journal":{"name":"International Research Journal on Advanced Engineering Hub (IRJAEH)","volume":"25 6","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140965190","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 : 2024-05-17DOI: 10.47392/irjaeh.2024.0167
By-Prakhar Pandey, Arpit, Umashankar Sharma
Distributed object storage systems have emerged as pivotal infrastructures for managing the escalating volumes of unstructured data. This research comprehensively explores the architecture, challenges, advancements, and applications of distributed object storage. The architectural analysis delineates core components, such as metadata servers and storage nodes, emphasizing their role in facilitating scalability and fault tolerance. Challenges encompassing data consistency, security, and performance bottlenecks underscore the need for continual innovation. Advancements, ranging from erasure coding to the integration of machine learning and blockchain, propel the field forward, enhancing resilience and expanding applications. Use cases illustrate the adaptability of distributed object storage across industries, while future directions suggest potential areas for exploration. In conclusion, distributed object storage epitomizes a foundational technology in modern data management, with the research delineating its current significance and future potential.
{"title":"Comprehensive Analysis of Distributed Object Storage Systems","authors":"By-Prakhar Pandey, Arpit, Umashankar Sharma","doi":"10.47392/irjaeh.2024.0167","DOIUrl":"https://doi.org/10.47392/irjaeh.2024.0167","url":null,"abstract":"Distributed object storage systems have emerged as pivotal infrastructures for managing the escalating volumes of unstructured data. This research comprehensively explores the architecture, challenges, advancements, and applications of distributed object storage. The architectural analysis delineates core components, such as metadata servers and storage nodes, emphasizing their role in facilitating scalability and fault tolerance. Challenges encompassing data consistency, security, and performance bottlenecks underscore the need for continual innovation. Advancements, ranging from erasure coding to the integration of machine learning and blockchain, propel the field forward, enhancing resilience and expanding applications. Use cases illustrate the adaptability of distributed object storage across industries, while future directions suggest potential areas for exploration. In conclusion, distributed object storage epitomizes a foundational technology in modern data management, with the research delineating its current significance and future potential.","PeriodicalId":517766,"journal":{"name":"International Research Journal on Advanced Engineering Hub (IRJAEH)","volume":"19 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140965300","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 : 2024-05-17DOI: 10.47392/irjaeh.2024.0169
Mrs. Sapana Bhushan Raghuwanshi, Dr. Nilesh Ashok Suryawanshi
The PCE Risk Calculator, developed by the ACC/AHA, is frequently utilized in the United States for the purpose of averting the onset of Atherosclerotic cardiovascular disease (ASCVD) via first-line defense strategies. However, this calculator may not accurately estimate risk for certain populations, potentially leading to either under- or over-estimation of risk. We have created calculator for ASCVD risk specific to a population by leveraging advanced Machine Learning (ML) techniques and Electronic Medical Record (EMR) data. Our study involved comparing predictive accuracy of our calculator with PCE calculator. Between January 1, 2009, and April 30, 2020, data was gathered from 101,110 distinct EMRs of patients who were actively receiving treatment. Patient datasets underwent machine learning techniques containing Longitudinal (LT) and Cross-Sectional (CS) features, or solely CS features, derived from laboratory values and vital statistics. The models' effectiveness was assessed using fresh price metric (Screened Cases Percentage @Sensitivity level). In terms of prediction accuracy, every ML model that was tested performed better than the PCE risk calculator. Area Under Curve (AUC) score of 0.902 was obtained by Random Forest (RF) ML technique when CS and LT characteristics were combined (RF-LTC). Our machine learning model only needed to screen 43% of patients in order to identify 90% of positive ASCVD cases, in contrast to the PCE risk calculator, which required screening 69% of patients. Prediction models created using ML techniques reduce the amount number of tests necessary to forecast ASCVD and increase the accuracy of ASCVD prediction when compared to using PCE calculator alone. The combination of LT and CS features in these ML models leads to a significant enhancement in comparing the ASCVD prediction to utilizing CS features exclusively.
{"title":"Improving Cardiovascular Disease Forecasting with Machine Learning and Electronic Medical Record Data Characteristics Within a Local Healthcare Network","authors":"Mrs. Sapana Bhushan Raghuwanshi, Dr. Nilesh Ashok Suryawanshi","doi":"10.47392/irjaeh.2024.0169","DOIUrl":"https://doi.org/10.47392/irjaeh.2024.0169","url":null,"abstract":"The PCE Risk Calculator, developed by the ACC/AHA, is frequently utilized in the United States for the purpose of averting the onset of Atherosclerotic cardiovascular disease (ASCVD) via first-line defense strategies. However, this calculator may not accurately estimate risk for certain populations, potentially leading to either under- or over-estimation of risk. We have created calculator for ASCVD risk specific to a population by leveraging advanced Machine Learning (ML) techniques and Electronic Medical Record (EMR) data. Our study involved comparing predictive accuracy of our calculator with PCE calculator. Between January 1, 2009, and April 30, 2020, data was gathered from 101,110 distinct EMRs of patients who were actively receiving treatment. Patient datasets underwent machine learning techniques containing Longitudinal (LT) and Cross-Sectional (CS) features, or solely CS features, derived from laboratory values and vital statistics. The models' effectiveness was assessed using fresh price metric (Screened Cases Percentage @Sensitivity level). In terms of prediction accuracy, every ML model that was tested performed better than the PCE risk calculator. Area Under Curve (AUC) score of 0.902 was obtained by Random Forest (RF) ML technique when CS and LT characteristics were combined (RF-LTC). Our machine learning model only needed to screen 43% of patients in order to identify 90% of positive ASCVD cases, in contrast to the PCE risk calculator, which required screening 69% of patients. Prediction models created using ML techniques reduce the amount number of tests necessary to forecast ASCVD and increase the accuracy of ASCVD prediction when compared to using PCE calculator alone. The combination of LT and CS features in these ML models leads to a significant enhancement in comparing the ASCVD prediction to utilizing CS features exclusively.","PeriodicalId":517766,"journal":{"name":"International Research Journal on Advanced Engineering Hub (IRJAEH)","volume":"3 10","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140963358","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 : 2024-05-17DOI: 10.47392/irjaeh.2024.0165
Pooja sri G, Nuha Fathima N, Abinaya B
An innovative approach is presented in this study to enhance the performance of Ant Colony Optimization (ACO), a type of Bio-Inspired Algorithm (BIA), by integrating machine learning (ML) techniques for fault prediction. The goal is to address the challenges of high end-to-end delay and susceptibility to faults in traditional ACO implementations by leveraging ML methods. Through the application of ML techniques to optimize ACO efficiency and anticipate faults using the Random Forest model, significant reductions in end-to-end delay and improvements in system survivability are achieved. Additionally, the utilization of Least Absolute Shrinkage and Selection Operator (LASSO) feature selection streamlines the optimization process and enhances overall performance. Experimental results demonstrate the superiority of the proposed ML-enhanced ACO approach, indicating its potential for real-world applications in optimization problems.
本研究提出了一种创新方法，通过整合用于故障预测的机器学习（ML）技术来提高蚁群优化（ACO）（一种生物启发算法（BIA））的性能。其目标是利用 ML 方法解决传统 ACO 实现中端到端延迟高和易发故障的难题。通过应用 ML 技术优化 ACO 效率，并使用随机森林模型预测故障，可显著降低端到端延迟，提高系统生存能力。此外，利用最小绝对收缩和选择操作符（LASSO）特征选择简化了优化过程并提高了整体性能。实验结果证明了所提出的 ML 增强 ACO 方法的优越性，显示了其在优化问题的实际应用中的潜力。
{"title":"Efficient Fault Tolerance Methodology in Fanet Using Aco and Ml Techniques","authors":"Pooja sri G, Nuha Fathima N, Abinaya B","doi":"10.47392/irjaeh.2024.0165","DOIUrl":"https://doi.org/10.47392/irjaeh.2024.0165","url":null,"abstract":"An innovative approach is presented in this study to enhance the performance of Ant Colony Optimization (ACO), a type of Bio-Inspired Algorithm (BIA), by integrating machine learning (ML) techniques for fault prediction. The goal is to address the challenges of high end-to-end delay and susceptibility to faults in traditional ACO implementations by leveraging ML methods. Through the application of ML techniques to optimize ACO efficiency and anticipate faults using the Random Forest model, significant reductions in end-to-end delay and improvements in system survivability are achieved. Additionally, the utilization of Least Absolute Shrinkage and Selection Operator (LASSO) feature selection streamlines the optimization process and enhances overall performance. Experimental results demonstrate the superiority of the proposed ML-enhanced ACO approach, indicating its potential for real-world applications in optimization problems.","PeriodicalId":517766,"journal":{"name":"International Research Journal on Advanced Engineering Hub (IRJAEH)","volume":"112 44","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141126516","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：