Pub Date : 2023-07-06DOI: 10.1109/ICESC57686.2023.10193319
C. Genitha, S. Danny, A. S. H. Ajibah, S. Aravint, A. Angeline, Valentina Sweety, Engineering Chennai
This study presents a novel system that utilizes computer vision and machine learning approaches to address the problem of traffic congestion in urban areas. The proposed system leverages the advanced object detection algorithm, You Only Look Once (YOLO), to detect and track vehicles in live camera footage from traffic junctions. The system then calculates the traffic density in real-time by analyzing the number and speed of vehicles passing through the intersection. The proposed system utilizes an intelligent algorithm that optimizes traffic flow by switching traffic lights based on the calculated traffic density. This approach reduces congestion and minimizes delays, resulting in faster transit times and reduced fuel consumption and air pollution. To assess the performance of the proposed system, experiments are carried on real-world traffic data. The results demonstrate that the system can accurately detect and track vehicles with high precision and recall rates. The real-time traffic density calculations produced by the system were found to be highly reliable, and the traffic light switching algorithm led to a significant reduction in traffic congestion and improved traffic flow. The proposed system has several advantages over traditional traffic management systems, including lower implementation and maintenance costs, improved accuracy and efficiency, and the ability to adapt to changing traffic conditions in real-time.
本研究提出了一种利用计算机视觉和机器学习方法来解决城市交通拥堵问题的新系统。该系统利用先进的目标检测算法You Only Look Once (YOLO)，从交通路口的实时摄像头镜头中检测和跟踪车辆。然后，系统通过分析通过交叉路口的车辆数量和速度，实时计算交通密度。该系统利用一种智能算法，根据计算的交通密度，通过切换交通灯来优化交通流。这种方法减少了拥堵，最大限度地减少了延误，从而缩短了运输时间，减少了燃料消耗和空气污染。为了评估该系统的性能，在实际交通数据上进行了实验。结果表明，该系统能够准确地检测和跟踪车辆，具有较高的检测精度和召回率。系统产生的实时交通密度计算具有较高的可靠性，红绿灯切换算法显著减少了交通拥堵，改善了交通流量。与传统的交通管理系统相比，该系统具有几个优点，包括更低的实施和维护成本，更高的准确性和效率，以及实时适应不断变化的交通状况的能力。
{"title":"AI based Real-Time Traffic Signal Control System using Machine Learning","authors":"C. Genitha, S. Danny, A. S. H. Ajibah, S. Aravint, A. Angeline, Valentina Sweety, Engineering Chennai","doi":"10.1109/ICESC57686.2023.10193319","DOIUrl":"https://doi.org/10.1109/ICESC57686.2023.10193319","url":null,"abstract":"This study presents a novel system that utilizes computer vision and machine learning approaches to address the problem of traffic congestion in urban areas. The proposed system leverages the advanced object detection algorithm, You Only Look Once (YOLO), to detect and track vehicles in live camera footage from traffic junctions. The system then calculates the traffic density in real-time by analyzing the number and speed of vehicles passing through the intersection. The proposed system utilizes an intelligent algorithm that optimizes traffic flow by switching traffic lights based on the calculated traffic density. This approach reduces congestion and minimizes delays, resulting in faster transit times and reduced fuel consumption and air pollution. To assess the performance of the proposed system, experiments are carried on real-world traffic data. The results demonstrate that the system can accurately detect and track vehicles with high precision and recall rates. The real-time traffic density calculations produced by the system were found to be highly reliable, and the traffic light switching algorithm led to a significant reduction in traffic congestion and improved traffic flow. The proposed system has several advantages over traditional traffic management systems, including lower implementation and maintenance costs, improved accuracy and efficiency, and the ability to adapt to changing traffic conditions in real-time.","PeriodicalId":235381,"journal":{"name":"2023 4th International Conference on Electronics and Sustainable Communication Systems (ICESC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116789917","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 : 2023-07-06DOI: 10.1109/ICESC57686.2023.10193418
R. Rajkumar, N.Selvarani, B. Bright, S. Kaliappan, B. V. S. Thrinath, Amal Rebin
In order to developing the smart and reliable photovoltaic system, it is essential to use the DC-DC converter so that a huge fluctuation in voltage can be controlled. In this context, for enhancing the efficacy of the system, the Fuzzy logic circuit has been utilized in this research study. The FLC is used to control the converter’s output voltage, which is essential for the reliability and performance of the PV system. The FLC is adapted for use in Microsoft Excel, making this powerful tool both affordable and easily accessible. Simulations are used to assess the controller’s efficiency, revealing that the FLC is successful in minimizing overshoot, settling time, and steady-state error. The findings of this work might dramatically lower entry barriers for building and improving fuzzy logic controller’s, which has crucial implications for the creation of more efficient and dependable energy systems. Exploring the possibilities of this technology and improving the FLC for other closed-loop DC-DC converters might be the subject of future study.
{"title":"Photovoltaic System based on Closed Loop DC-DC Converter with Fuzzy Logic Controller","authors":"R. Rajkumar, N.Selvarani, B. Bright, S. Kaliappan, B. V. S. Thrinath, Amal Rebin","doi":"10.1109/ICESC57686.2023.10193418","DOIUrl":"https://doi.org/10.1109/ICESC57686.2023.10193418","url":null,"abstract":"In order to developing the smart and reliable photovoltaic system, it is essential to use the DC-DC converter so that a huge fluctuation in voltage can be controlled. In this context, for enhancing the efficacy of the system, the Fuzzy logic circuit has been utilized in this research study. The FLC is used to control the converter’s output voltage, which is essential for the reliability and performance of the PV system. The FLC is adapted for use in Microsoft Excel, making this powerful tool both affordable and easily accessible. Simulations are used to assess the controller’s efficiency, revealing that the FLC is successful in minimizing overshoot, settling time, and steady-state error. The findings of this work might dramatically lower entry barriers for building and improving fuzzy logic controller’s, which has crucial implications for the creation of more efficient and dependable energy systems. Exploring the possibilities of this technology and improving the FLC for other closed-loop DC-DC converters might be the subject of future study.","PeriodicalId":235381,"journal":{"name":"2023 4th International Conference on Electronics and Sustainable Communication Systems (ICESC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120851448","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 : 2023-07-06DOI: 10.1109/ICESC57686.2023.10193104
C. Ranganathan, Rajeshkumar Sampathrajan
Migration to the cloud is gaining popularity as a means for businesses to save expenses, improve scalability, and get access to cutting-edge technology; it is also an integral aspect of any successful digital transformation strategy. Cloud migration has many advantages, but it’s not always simple to complete the shift in the allotted amount of time. This is because moving all the data, apps, and hardware to the cloud is a very involved operation. It may be difficult to predict how long it will take to complete a cloud migration owing to the many variables that might emerge throughout the process. A better understanding of the cloud migration’s complexity is necessary for establishing a time estimate. Migration to the cloud may be simple or difficult, depending on the scale and complexity of the organization’s current infrastructure and the chosen cloud solutions. Timeliness may also be impacted by the accessibility of knowledgeable employees and the speed of the internet connection. Furthermore, the availability of critical resources, such as storage and processing power, to guarantee a smooth transfer to the cloud might impact the schedule for making the move.
{"title":"Cloud Migration Meets Targeted Deadlines","authors":"C. Ranganathan, Rajeshkumar Sampathrajan","doi":"10.1109/ICESC57686.2023.10193104","DOIUrl":"https://doi.org/10.1109/ICESC57686.2023.10193104","url":null,"abstract":"Migration to the cloud is gaining popularity as a means for businesses to save expenses, improve scalability, and get access to cutting-edge technology; it is also an integral aspect of any successful digital transformation strategy. Cloud migration has many advantages, but it’s not always simple to complete the shift in the allotted amount of time. This is because moving all the data, apps, and hardware to the cloud is a very involved operation. It may be difficult to predict how long it will take to complete a cloud migration owing to the many variables that might emerge throughout the process. A better understanding of the cloud migration’s complexity is necessary for establishing a time estimate. Migration to the cloud may be simple or difficult, depending on the scale and complexity of the organization’s current infrastructure and the chosen cloud solutions. Timeliness may also be impacted by the accessibility of knowledgeable employees and the speed of the internet connection. Furthermore, the availability of critical resources, such as storage and processing power, to guarantee a smooth transfer to the cloud might impact the schedule for making the move.","PeriodicalId":235381,"journal":{"name":"2023 4th International Conference on Electronics and Sustainable Communication Systems (ICESC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127277387","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 : 2023-07-06DOI: 10.1109/ICESC57686.2023.10193548
N. Nalini, G. Uganya, M. Sathesh, M. Sheela
The purpose of the research was to is to compare accuracy and specificity in the bone fracture detection using novel modified Prewitt Edge Detection (PED) with Laplacian Edge Detection (LED). Two groups are compared, novel modified Prewitt Edge Detection (PED) (N=10) and Laplacian edge detection (LED) (N=10) The overall sample size was calculated using the G Power software with an alpha of 0.05, enrollment ratio of 0.1, confidence interval of 5%, and power of 80%. Using the SPSS statistical package, an independent sample t-test was used to compare the accuracy and specificity rate. Novel modified Prewitt edge detection (PED) algorithm found to be statistically significant when compared with the Laplacian edge detection (LED) classifier which gives accuracy p= 0.026, and specificity p=0.001(p<0.05) of bone fracture X-ray image. The Laplacian edge detection approach seems to be outperformed by a new modified Prewitt edge detection algorithm.
{"title":"Detection of Bone Fracture using Prewitt Edge Algorithm and Comparing with Laplacian Algorithm to Increase Accuracy and Sensitivity.","authors":"N. Nalini, G. Uganya, M. Sathesh, M. Sheela","doi":"10.1109/ICESC57686.2023.10193548","DOIUrl":"https://doi.org/10.1109/ICESC57686.2023.10193548","url":null,"abstract":"The purpose of the research was to is to compare accuracy and specificity in the bone fracture detection using novel modified Prewitt Edge Detection (PED) with Laplacian Edge Detection (LED). Two groups are compared, novel modified Prewitt Edge Detection (PED) (N=10) and Laplacian edge detection (LED) (N=10) The overall sample size was calculated using the G Power software with an alpha of 0.05, enrollment ratio of 0.1, confidence interval of 5%, and power of 80%. Using the SPSS statistical package, an independent sample t-test was used to compare the accuracy and specificity rate. Novel modified Prewitt edge detection (PED) algorithm found to be statistically significant when compared with the Laplacian edge detection (LED) classifier which gives accuracy p= 0.026, and specificity p=0.001(p<0.05) of bone fracture X-ray image. The Laplacian edge detection approach seems to be outperformed by a new modified Prewitt edge detection algorithm.","PeriodicalId":235381,"journal":{"name":"2023 4th International Conference on Electronics and Sustainable Communication Systems (ICESC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127489248","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 : 2023-07-06DOI: 10.1109/ICESC57686.2023.10193038
Akshay Kumar, K. Stephen, A. Sabitha
Sensor fusion technology is a critical component of autonomous vehicles, enabling them to perceive and respond to their environment with greater accuracy and speed. This technology integrates data from multiple sensors, such as lidar, radar, cameras, and GPS, to create a comprehensive understanding of the vehicle’s surroundings. By combining and analyzing this data, sensor fusion technology can identify objects, predict their movements, and make decisions about the best course of action. In this way, it enables autonomous vehicles to operate safely and reliably in complex environments, such as urban streets or highways. Sensor fusion technology is a rapidly evolving field, and researchers are continually developing new algorithms and techniques to improve its accuracy and reliability.
{"title":"A Systematic Review on Sensor Fusion Technology in Autonomous Vehicles","authors":"Akshay Kumar, K. Stephen, A. Sabitha","doi":"10.1109/ICESC57686.2023.10193038","DOIUrl":"https://doi.org/10.1109/ICESC57686.2023.10193038","url":null,"abstract":"Sensor fusion technology is a critical component of autonomous vehicles, enabling them to perceive and respond to their environment with greater accuracy and speed. This technology integrates data from multiple sensors, such as lidar, radar, cameras, and GPS, to create a comprehensive understanding of the vehicle’s surroundings. By combining and analyzing this data, sensor fusion technology can identify objects, predict their movements, and make decisions about the best course of action. In this way, it enables autonomous vehicles to operate safely and reliably in complex environments, such as urban streets or highways. Sensor fusion technology is a rapidly evolving field, and researchers are continually developing new algorithms and techniques to improve its accuracy and reliability.","PeriodicalId":235381,"journal":{"name":"2023 4th International Conference on Electronics and Sustainable Communication Systems (ICESC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125152971","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 : 2023-07-06DOI: 10.1109/ICESC57686.2023.10193289
Nrusimhadri Sai Deepak, T. Hanitha, Kiranmai Tanniru, Lukka Raj Kiran, Dr. N.Raghavendra Sai, Dr. M. Jogendra Kumar
One of the most crucial global concerns is the issue of cybercrime, which leads to significant financial losses for nations and their citizens every day. The frequency of cyberattacks has steadily increased, emphasizing the need to identify the individuals behind these criminal activities and understand their strategies. Detecting and preventing cyberattacks pose significant challenges, but recent advancements have introduced security models and prediction tools based on artificial intelligence to tackle these issues. Although there is a wealth of literature on crime prediction strategies, they may need to be more effectively suited for awaiting cybercrime and cyber-attack techniques. One potential solution to address this problem involves utilizing real-world data to determine the occurrence of an attack and identify the responsible party. This information encompasses details about the offense, offender demographics, property damage, and attack vectors. Forensic teams can collect information from victims of cyber-attacks through application processes. This research study employs machine learning techniques to analyze cybercrime using two models and predict how the attributes can contribute to identifying the method of cyber-attack and the criminal. This study has compared eight different machine-learning techniques, and discovered that they yielded similar results in terms of accuracy. The Support Vector Machine (SVM) linear model achieved the highest accuracy rate among the various cyber-attack methods tested. In the first model, valuable insights on the types of attacks victims were likely to face. Logistic regression, with a high success rate, was the most effective strategy for identifying malicious actors. The second model focused on comparing offender and victim attributes to make predictions regarding identification. Our findings indicate that the likelihood of becoming a victim of cyberattacks decreases with higher levels of education and wealth. This proposed concept is eagerly estimated for implementation by cybercrime departments, as it will simplify the detection of cyber-attacks and enhance the efficiency of the battle against them.
{"title":"Analyze and Forecast the Cyber Attack Detection Process using Machine Learning Techniques","authors":"Nrusimhadri Sai Deepak, T. Hanitha, Kiranmai Tanniru, Lukka Raj Kiran, Dr. N.Raghavendra Sai, Dr. M. Jogendra Kumar","doi":"10.1109/ICESC57686.2023.10193289","DOIUrl":"https://doi.org/10.1109/ICESC57686.2023.10193289","url":null,"abstract":"One of the most crucial global concerns is the issue of cybercrime, which leads to significant financial losses for nations and their citizens every day. The frequency of cyberattacks has steadily increased, emphasizing the need to identify the individuals behind these criminal activities and understand their strategies. Detecting and preventing cyberattacks pose significant challenges, but recent advancements have introduced security models and prediction tools based on artificial intelligence to tackle these issues. Although there is a wealth of literature on crime prediction strategies, they may need to be more effectively suited for awaiting cybercrime and cyber-attack techniques. One potential solution to address this problem involves utilizing real-world data to determine the occurrence of an attack and identify the responsible party. This information encompasses details about the offense, offender demographics, property damage, and attack vectors. Forensic teams can collect information from victims of cyber-attacks through application processes. This research study employs machine learning techniques to analyze cybercrime using two models and predict how the attributes can contribute to identifying the method of cyber-attack and the criminal. This study has compared eight different machine-learning techniques, and discovered that they yielded similar results in terms of accuracy. The Support Vector Machine (SVM) linear model achieved the highest accuracy rate among the various cyber-attack methods tested. In the first model, valuable insights on the types of attacks victims were likely to face. Logistic regression, with a high success rate, was the most effective strategy for identifying malicious actors. The second model focused on comparing offender and victim attributes to make predictions regarding identification. Our findings indicate that the likelihood of becoming a victim of cyberattacks decreases with higher levels of education and wealth. This proposed concept is eagerly estimated for implementation by cybercrime departments, as it will simplify the detection of cyber-attacks and enhance the efficiency of the battle against them.","PeriodicalId":235381,"journal":{"name":"2023 4th International Conference on Electronics and Sustainable Communication Systems (ICESC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122093154","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 : 2023-07-06DOI: 10.1109/ICESC57686.2023.10193195
R.Maruthi, S. Nagarajan, Asst ProfessorSG, Rohini A Asst, Vanita Jaitly Asst ProfessorSG
The population has increased over the years, which has affected the food supply and demand. Population growth, climate change and natural resource challenges are inter-linked factors that have affected the conventional way of farming. These challenging factors led to the introduction of Smart farming and Internet of Things (IoT) and climate-smart agriculture (CSA). This study explores an automated remote monitoring system using IoT in Smart farming. Irrigation is one of the main factors that directly affect crop growth, and up to 70 percent of the freshwater globally goes to agriculture. The proposed system uses moisture sensors to monitor the soil moisture levels for automated condition-based irrigation. The proposed system can be implemented in small-scale and large-scale farming; it will help farmers save costs and reduce water waste on a global scale. It uses 95 percent less water than conventional irrigation methods.
{"title":"IoT based Automated Remote Monitoring System for Smart Farming","authors":"R.Maruthi, S. Nagarajan, Asst ProfessorSG, Rohini A Asst, Vanita Jaitly Asst ProfessorSG","doi":"10.1109/ICESC57686.2023.10193195","DOIUrl":"https://doi.org/10.1109/ICESC57686.2023.10193195","url":null,"abstract":"The population has increased over the years, which has affected the food supply and demand. Population growth, climate change and natural resource challenges are inter-linked factors that have affected the conventional way of farming. These challenging factors led to the introduction of Smart farming and Internet of Things (IoT) and climate-smart agriculture (CSA). This study explores an automated remote monitoring system using IoT in Smart farming. Irrigation is one of the main factors that directly affect crop growth, and up to 70 percent of the freshwater globally goes to agriculture. The proposed system uses moisture sensors to monitor the soil moisture levels for automated condition-based irrigation. The proposed system can be implemented in small-scale and large-scale farming; it will help farmers save costs and reduce water waste on a global scale. It uses 95 percent less water than conventional irrigation methods.","PeriodicalId":235381,"journal":{"name":"2023 4th International Conference on Electronics and Sustainable Communication Systems (ICESC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128252833","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 : 2023-07-06DOI: 10.1109/ICESC57686.2023.10193428
Suresh Kumar Balam, Rituraj Jain, J. S. Alaric, B. Pattanaik, Terefe Bayisa Ayele
The smart grid has grown to be a major study topic due to the rising need for Renewable Energy Sources (RES) and the requirement to efficiently control energy usage. A smart grid is intelligent and energy-efficient could be developed by integrating cloud-based IoT technology with RES. In order to increase energy efficiency, reduce energy losses, and assure reliable power distribution, this work presented a unique technique for the incorporation of RES utilizing IoT and multilevel converters. The suggested method makes use of IoT devices’ capacity to gather, process, and analyze data in order to improve grid control and track the effectiveness of renewable energy installations. To ensure the grid operates steadily and effectively, a multilevel converter is utilized to optimize power distribution, voltage management, and power quality (PQ). The efficacy and viability of the suggested strategy are demonstrated by the results of its validation utilizing a model for simulation in MATLAB/Simulink.
{"title":"Renewable Energy Integration of IoT Systems for Smart Grid Applications","authors":"Suresh Kumar Balam, Rituraj Jain, J. S. Alaric, B. Pattanaik, Terefe Bayisa Ayele","doi":"10.1109/ICESC57686.2023.10193428","DOIUrl":"https://doi.org/10.1109/ICESC57686.2023.10193428","url":null,"abstract":"The smart grid has grown to be a major study topic due to the rising need for Renewable Energy Sources (RES) and the requirement to efficiently control energy usage. A smart grid is intelligent and energy-efficient could be developed by integrating cloud-based IoT technology with RES. In order to increase energy efficiency, reduce energy losses, and assure reliable power distribution, this work presented a unique technique for the incorporation of RES utilizing IoT and multilevel converters. The suggested method makes use of IoT devices’ capacity to gather, process, and analyze data in order to improve grid control and track the effectiveness of renewable energy installations. To ensure the grid operates steadily and effectively, a multilevel converter is utilized to optimize power distribution, voltage management, and power quality (PQ). The efficacy and viability of the suggested strategy are demonstrated by the results of its validation utilizing a model for simulation in MATLAB/Simulink.","PeriodicalId":235381,"journal":{"name":"2023 4th International Conference on Electronics and Sustainable Communication Systems (ICESC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124666561","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 : 2023-07-06DOI: 10.1109/ICESC57686.2023.10193150
Esha Kadam, Aryan Gupta, Srushti Jagtap, Ishu Dubey, G. Tawde
Many individuals apply for bank loans. But the banks have limited assets, so it can grant credit to a limited number of customers. The credit gained by the customers can be a growing asset for a bank due to the earnings from interests or a liability if the customer is unable to pay the loan. A huge amount of capital that is disbursed may turn into bad debt just because the bank was not well informed about the repayment capabilities of its customer. Determining beforehand that which customer can repay the loan will be a safer option for the bank. The process of predicting whether a loan should be approved or not, can be done by bank officials by inspecting various parameters of a customer. Doing so will require manpower and capital as human employees would perform the job of prediction. To tackle this situation, there is a need for automation. Previous research in this area has shown that there are numerous strategies for reducing the number of loan defaults. However, accurate prediction is critical for profit maximisation. The proposed loan approval prediction system is a web application based on machine learning, designed to provide instant loan approval predictions to users. The application uses logistic regression to predict the probability of loan approval and also computes a credit score which is referred as CIBIL score. Overall, the loan approval prediction system is a powerful tool for individuals and financial institutions looking to quickly assess loan applications and make informed decisions. It leverages the power of machine learning to provide accurate and reliable predictions, and also provides an easy and a convenient way for users to access this functionality.
{"title":"Loan Approval Prediction System using Logistic Regression and CIBIL Score","authors":"Esha Kadam, Aryan Gupta, Srushti Jagtap, Ishu Dubey, G. Tawde","doi":"10.1109/ICESC57686.2023.10193150","DOIUrl":"https://doi.org/10.1109/ICESC57686.2023.10193150","url":null,"abstract":"Many individuals apply for bank loans. But the banks have limited assets, so it can grant credit to a limited number of customers. The credit gained by the customers can be a growing asset for a bank due to the earnings from interests or a liability if the customer is unable to pay the loan. A huge amount of capital that is disbursed may turn into bad debt just because the bank was not well informed about the repayment capabilities of its customer. Determining beforehand that which customer can repay the loan will be a safer option for the bank. The process of predicting whether a loan should be approved or not, can be done by bank officials by inspecting various parameters of a customer. Doing so will require manpower and capital as human employees would perform the job of prediction. To tackle this situation, there is a need for automation. Previous research in this area has shown that there are numerous strategies for reducing the number of loan defaults. However, accurate prediction is critical for profit maximisation. The proposed loan approval prediction system is a web application based on machine learning, designed to provide instant loan approval predictions to users. The application uses logistic regression to predict the probability of loan approval and also computes a credit score which is referred as CIBIL score. Overall, the loan approval prediction system is a powerful tool for individuals and financial institutions looking to quickly assess loan applications and make informed decisions. It leverages the power of machine learning to provide accurate and reliable predictions, and also provides an easy and a convenient way for users to access this functionality.","PeriodicalId":235381,"journal":{"name":"2023 4th International Conference on Electronics and Sustainable Communication Systems (ICESC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124693909","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 : 2023-07-06DOI: 10.1109/ICESC57686.2023.10193483
L. Jenitha Mary, V. Vijayashanthi, M. Parameswari, E. Venitha, T. A. Mohanaprakash, S. D. Hariharan
When left untreated, diabetes, a chronic ailment that affects a vast number of people overall, might result in major unanticipated problems. The risk of complications can be completely reduced and considerable improvements can be achieved with early detection of diabetes. Recently, the use of wearable technology has emerged as a potential tool for diagnosing and checking illnesses. Smartwatches with bioactive sensors are perfect for diabetes screening because they can provide continuous, painless monitoring of bodily vitals. This paper suggests a methodology for building a hybrid AI model to detect the existence of diabetes using patient data. The system combines body vitals calculated using a smartwatch equipped with a bioactive sensor to provide accurate and continuous information on the wearer’s health state. The hybrid model combines both deep learning and traditional AI computations to achieve a high level of accuracy while diagnosing diabetes. The framework collects data on many bodily parameters, including skin conductance, circulatory strain, and pulse — all of which are known to be strongly associated with diabetes. The acquired data is pre-processed before being utilized to create the hybrid model. The standard AI calculation is used to classify the information into diabetes or non-diabetic categories, while the profound learning calculation is used to eliminate important level highlights from the raw data. The hybrid approach combines the advantages of both deep learning and traditional AI to improve the accuracy of diabetes localization.
{"title":"Real-time Non-invasive Blood Glucose Monitoring using Advanced Machine Learning Techniques","authors":"L. Jenitha Mary, V. Vijayashanthi, M. Parameswari, E. Venitha, T. A. Mohanaprakash, S. D. Hariharan","doi":"10.1109/ICESC57686.2023.10193483","DOIUrl":"https://doi.org/10.1109/ICESC57686.2023.10193483","url":null,"abstract":"When left untreated, diabetes, a chronic ailment that affects a vast number of people overall, might result in major unanticipated problems. The risk of complications can be completely reduced and considerable improvements can be achieved with early detection of diabetes. Recently, the use of wearable technology has emerged as a potential tool for diagnosing and checking illnesses. Smartwatches with bioactive sensors are perfect for diabetes screening because they can provide continuous, painless monitoring of bodily vitals. This paper suggests a methodology for building a hybrid AI model to detect the existence of diabetes using patient data. The system combines body vitals calculated using a smartwatch equipped with a bioactive sensor to provide accurate and continuous information on the wearer’s health state. The hybrid model combines both deep learning and traditional AI computations to achieve a high level of accuracy while diagnosing diabetes. The framework collects data on many bodily parameters, including skin conductance, circulatory strain, and pulse — all of which are known to be strongly associated with diabetes. The acquired data is pre-processed before being utilized to create the hybrid model. The standard AI calculation is used to classify the information into diabetes or non-diabetic categories, while the profound learning calculation is used to eliminate important level highlights from the raw data. The hybrid approach combines the advantages of both deep learning and traditional AI to improve the accuracy of diabetes localization.","PeriodicalId":235381,"journal":{"name":"2023 4th International Conference on Electronics and Sustainable Communication Systems (ICESC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129742683","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：