A major contributing factor in car accidents is driver distraction. This research suggests a distraction detecting system for drivers that detects various forms of distractions by watching the driver with a camera in an effort to decrease traffic accidents and enhance transportation safety. To develop practical driving situations and to test the algorithms for distracted detection, an assisted driving testbed is being constructed. Pictures of the drivers in both their regular and distracted driving postures were taken for the authors’ dataset. The VGG-16, AlexNet, GoogleNet, and residual network are four deep convolutional neural networks that are developed and assessed on a platform with integrated graphics processing units. A voice warning system is developed to notify the driver when they are not paying attention to the road. As VGG-16 is a huge network, it takes more time to train its parameters. On the other hand, ‘texting left’ was misclassified with ‘safe driving’ in some scenarios when the steering wheel blocked the left hand. According to experimental findings, the proposed strategy works better than the baseline approach, which only uses 256 neurons in the fully linked layers. GoogleNet uses inception module, used for running multiple operations (pooling, convolution) with multiple filter sizes in parallel so that it is not necessary to face any trade-off. It takes less time to train its parameters.
{"title":"Distracted Driver Detection using Inception V1","authors":"Ms. Prathipati, Silpa Chaitanya, Bhagya, Rafiya Kowsar Sk, Joshna Rani","doi":"10.1109/ICESC57686.2023.10193551","DOIUrl":"https://doi.org/10.1109/ICESC57686.2023.10193551","url":null,"abstract":"A major contributing factor in car accidents is driver distraction. This research suggests a distraction detecting system for drivers that detects various forms of distractions by watching the driver with a camera in an effort to decrease traffic accidents and enhance transportation safety. To develop practical driving situations and to test the algorithms for distracted detection, an assisted driving testbed is being constructed. Pictures of the drivers in both their regular and distracted driving postures were taken for the authors’ dataset. The VGG-16, AlexNet, GoogleNet, and residual network are four deep convolutional neural networks that are developed and assessed on a platform with integrated graphics processing units. A voice warning system is developed to notify the driver when they are not paying attention to the road. As VGG-16 is a huge network, it takes more time to train its parameters. On the other hand, ‘texting left’ was misclassified with ‘safe driving’ in some scenarios when the steering wheel blocked the left hand. According to experimental findings, the proposed strategy works better than the baseline approach, which only uses 256 neurons in the fully linked layers. GoogleNet uses inception module, used for running multiple operations (pooling, convolution) with multiple filter sizes in parallel so that it is not necessary to face any trade-off. It takes less time to train its parameters.","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":"130375833","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/ICESC57686.2023.10193207
A. Siva, K. Jayashree, S. Pavithra, R. Preethi, A. Swetha, U. Ramani
Remote Monitoring of Energy Meter using Cloud storage is a project on enabling the measured energy which is consumed to be accessed by Android app in Mobile or in webpage through Data Excel Sheet. This is achieved by using Server Mediator (ESP8266), which stores the data in cloud storage. This study used Google cloud storage. Further, the current sensor and voltage transformer are used to calculate load current and supply voltage. These two parameters are given as input to Arduino to calculate the power consumed and also it will calculate the amount to be paid. These calculations are done by source code in C language that is programmed in Arduino. These calculated data will be send to LCD (Liquid Crystal Display) to get displayed and also stored in cloud. This avoids the direct reading of energy meters and also the consumer can know current energy consumed wherever they are in the world. And also they can Turn On/Off by Android app itself when unwanted power flow happens when no one is there at Home. Through this the consumer can save energy which leads to energy management.
{"title":"Remote Monitoring of Energy Meter using Cloud Storage","authors":"A. Siva, K. Jayashree, S. Pavithra, R. Preethi, A. Swetha, U. Ramani","doi":"10.1109/ICESC57686.2023.10193207","DOIUrl":"https://doi.org/10.1109/ICESC57686.2023.10193207","url":null,"abstract":"Remote Monitoring of Energy Meter using Cloud storage is a project on enabling the measured energy which is consumed to be accessed by Android app in Mobile or in webpage through Data Excel Sheet. This is achieved by using Server Mediator (ESP8266), which stores the data in cloud storage. This study used Google cloud storage. Further, the current sensor and voltage transformer are used to calculate load current and supply voltage. These two parameters are given as input to Arduino to calculate the power consumed and also it will calculate the amount to be paid. These calculations are done by source code in C language that is programmed in Arduino. These calculated data will be send to LCD (Liquid Crystal Display) to get displayed and also stored in cloud. This avoids the direct reading of energy meters and also the consumer can know current energy consumed wherever they are in the world. And also they can Turn On/Off by Android app itself when unwanted power flow happens when no one is there at Home. Through this the consumer can save energy which leads to energy management.","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":"115237601","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/ICESC57686.2023.10193053
Venkata Subba Reddy Bakka, Sai Sri Nidhin Tankala, Aarthi Bodumallu Gardannagari, Chandana Reddy Bakka, N. Sangeetha
Public bus transportation is the the most commonly used transportation system in any nation. More over, there is no reliable monitoring system in the existence. Users are facing many problems like long wait for the bus, ticket collection, seat availability etc. To avoid these kind of complications our research proposes an effective solution though the concept of RFID based smart public transit system The primary goal of this work is to provide an easy transportation facility by reducing the difficulties faced by the users, drivers and concerned officials. RFID based Smart Transportation Systems (STS) is the most efficient way to relieve traffic congestion, reduce accidents, and improve the transportation system as a whole on cloud. Here, Advanced technologies such as electronics, communication, computer, control and sensing are applied to various transportation systems to improve traffic conditions such as safety, efficiency and maintenance through real time information.
{"title":"RFID based Smart Public Transit System","authors":"Venkata Subba Reddy Bakka, Sai Sri Nidhin Tankala, Aarthi Bodumallu Gardannagari, Chandana Reddy Bakka, N. Sangeetha","doi":"10.1109/ICESC57686.2023.10193053","DOIUrl":"https://doi.org/10.1109/ICESC57686.2023.10193053","url":null,"abstract":"Public bus transportation is the the most commonly used transportation system in any nation. More over, there is no reliable monitoring system in the existence. Users are facing many problems like long wait for the bus, ticket collection, seat availability etc. To avoid these kind of complications our research proposes an effective solution though the concept of RFID based smart public transit system The primary goal of this work is to provide an easy transportation facility by reducing the difficulties faced by the users, drivers and concerned officials. RFID based Smart Transportation Systems (STS) is the most efficient way to relieve traffic congestion, reduce accidents, and improve the transportation system as a whole on cloud. Here, Advanced technologies such as electronics, communication, computer, control and sensing are applied to various transportation systems to improve traffic conditions such as safety, efficiency and maintenance through real time information.","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":"115974547","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/ICESC57686.2023.10193180
K. Bhaskar, T. Kumanan, S. Sree Southry., Vetrimani Elangovan
Wireless Sensor Network (WSN) is distinguished by size, dynamism, and decentralization. These complicated properties give rise to various problems, one of which is the impact of wireless communications on the efficiency of networks and the protocols used for routing. The prediction methods of link reliability can boost the efficiency of the routing algorithms used in WSNs while preventing weak connections. This approach introduces a Deep neural network algorithm to improve link reliability (DILR) in WSN. A Deep neural network (DNN) algorithm is used to evaluate the input parameters like node Received Signal Strength, available bandwidth, delay, and packet received rate parameters for calculating the link reliability output. The available bandwidth parameter recognizes the efficient data transmitting path. The experimental outcomes illustrate that the DILR mechanism improves the link reliability among nodes and reduces routing overhead compared to the conventional mechanism.
无线传感器网络(WSN)的特点是规模、动态性和分散性。这些复杂的特性引起了各种各样的问题,其中之一就是无线通信对网络效率和用于路由的协议的影响。链路可靠性预测方法可以在防止弱连接的同时提高无线传感器网络路由算法的效率。该方法引入了一种深度神经网络算法来提高无线传感器网络的链路可靠性。采用深度神经网络(Deep neural network, DNN)算法对节点接收信号强度(Received Signal Strength)、可用带宽(available bandwidth)、时延(delay)、接收包速率(packet Received rate)等输入参数进行评估,计算链路可靠性输出。可用带宽参数用于识别有效的数据传输路径。实验结果表明,与传统机制相比,DILR机制提高了节点间链路的可靠性,降低了路由开销。
{"title":"Deep Neural Network Algorithm to Improve Link Reliability in Wireless Sensor Networks","authors":"K. Bhaskar, T. Kumanan, S. Sree Southry., Vetrimani Elangovan","doi":"10.1109/ICESC57686.2023.10193180","DOIUrl":"https://doi.org/10.1109/ICESC57686.2023.10193180","url":null,"abstract":"Wireless Sensor Network (WSN) is distinguished by size, dynamism, and decentralization. These complicated properties give rise to various problems, one of which is the impact of wireless communications on the efficiency of networks and the protocols used for routing. The prediction methods of link reliability can boost the efficiency of the routing algorithms used in WSNs while preventing weak connections. This approach introduces a Deep neural network algorithm to improve link reliability (DILR) in WSN. A Deep neural network (DNN) algorithm is used to evaluate the input parameters like node Received Signal Strength, available bandwidth, delay, and packet received rate parameters for calculating the link reliability output. The available bandwidth parameter recognizes the efficient data transmitting path. The experimental outcomes illustrate that the DILR mechanism improves the link reliability among nodes and reduces routing overhead compared to the conventional mechanism.","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":"115544183","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/ICESC57686.2023.10193557
Remya Ravikumar, Pralay Sankar Maitra, Alka Singh, Nagesh K Subbana
Shoreline change is a constantly evolving phenomenon that threatens people and their livelihoods around the globe. India observes this phenomenon strongly at different locations being a tropical peninsular country with 6635kms of coastline. This study analyzes the effect of shoreline along the entire coast of Kerala state in India. Net changes in coastline positions are statistically calculated and observed using Linear Regression Rate (LRR) and validated using Artificial Neural Network. The study also employes a random forest regression to predict the ground water level changes with respect to shoreline change rate in the region. The shoreline change rate shows most of the region are undergoing erosion, only few accretions or land formation are observed which is formed artificially due to harbor building. The highest erosion rate in terms of LRR is 7m/year and highest accretion is 28m/year.
{"title":"Shore Line Change Detection using ANN and Ground Water Variability Along Kerala Coast Using Random Forest Regression","authors":"Remya Ravikumar, Pralay Sankar Maitra, Alka Singh, Nagesh K Subbana","doi":"10.1109/ICESC57686.2023.10193557","DOIUrl":"https://doi.org/10.1109/ICESC57686.2023.10193557","url":null,"abstract":"Shoreline change is a constantly evolving phenomenon that threatens people and their livelihoods around the globe. India observes this phenomenon strongly at different locations being a tropical peninsular country with 6635kms of coastline. This study analyzes the effect of shoreline along the entire coast of Kerala state in India. Net changes in coastline positions are statistically calculated and observed using Linear Regression Rate (LRR) and validated using Artificial Neural Network. The study also employes a random forest regression to predict the ground water level changes with respect to shoreline change rate in the region. The shoreline change rate shows most of the region are undergoing erosion, only few accretions or land formation are observed which is formed artificially due to harbor building. The highest erosion rate in terms of LRR is 7m/year and highest accretion is 28m/year.","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":"114120477","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/ICESC57686.2023.10193389
Dr.M.Jagadeeswari, P.Naveen Karthi, S.Lokith, S. Ram, V.A.Nitish Kumar
In the digital era, organizations, especially financial institutions, place an increasing emphasis on data security and privacy. To maintain data confidentiality, availability, and integrity, financial auditing organizations need secure file sharing and audit trail tracking technologies. Financial auditing firms demand a cloud-based audit trail monitoring platform as well as a secure file exchange platform with high encryption standards. Users may submit and download data using a secure online interface. An administrative dashboard simplifies user registration and deactivation. The audit trail function allows the administrator to know who requested a file, when they requested it, and when the file was downloaded. This audit trail monitoring technology raises compliance responsibilities. The platform uses Advanced Encryption Standard (AES) encryption to secure data. The platform encrypts submitted files using a random key. The file owner gets a download request, which he or she may accept or deny. If the request is granted, the owner sends the user the AES key required to decode and download the file. On the platform, Amazon Web Services and Relational Database Service (RDS) hold massive files (RDS). The Amazon database is protected by login and DoS alarms. Login notifications for Amazon root and IAM users notify the administrator of the browser, IP address, date, and number of attempted logins. The administrator receives DoS attack notifications and database traffic statistics from a variety of sources. Administrators may use alerts to prevent security breaches. The solution facilitates secure and timely communication between financial auditing firms. Data is protected by AES encryption and Amazon S3 storage, while audit trail monitoring and alerts prevent data breaches.
在数字时代,组织,特别是金融机构,越来越重视数据安全和隐私。为了维护数据的机密性、可用性和完整性,财务审计组织需要安全的文件共享和审计跟踪跟踪技术。金融审计公司需要基于云的审计跟踪监控平台,以及具有高加密标准的安全文件交换平台。用户可以使用安全的在线界面提交和下载数据。管理指示板简化了用户注册和停用。审计跟踪功能允许管理员知道谁请求了文件,何时请求,以及文件何时被下载。这种审计跟踪监视技术提高了遵从性责任。该平台采用高级加密标准AES (Advanced Encryption Standard)加密来保护数据。该平台使用随机密钥加密提交的文件。文件所有者收到下载请求,他或她可以接受或拒绝。如果请求被批准,所有者向用户发送解码和下载文件所需的AES密钥。在该平台上,Amazon Web Services和关系数据库服务(RDS)保存大量文件(RDS)。Amazon数据库有登录和DoS告警保护。Amazon root和IAM用户的登录通知通知管理员浏览器、IP地址、登录日期和尝试登录次数。管理员可以从不同的来源接收DoS攻击通知和数据库流量统计信息。管理员可以使用警报来防止安全漏洞。该解决方案促进了财务审计事务所之间安全、及时的沟通。数据由AES加密和Amazon S3存储保护,而审计跟踪监控和警报可防止数据泄露。
{"title":"A Secure File Sharing and Audit Trail Tracking Platform with Advanced Encryption Standard for Cloud-Based Environments","authors":"Dr.M.Jagadeeswari, P.Naveen Karthi, S.Lokith, S. Ram, V.A.Nitish Kumar","doi":"10.1109/ICESC57686.2023.10193389","DOIUrl":"https://doi.org/10.1109/ICESC57686.2023.10193389","url":null,"abstract":"In the digital era, organizations, especially financial institutions, place an increasing emphasis on data security and privacy. To maintain data confidentiality, availability, and integrity, financial auditing organizations need secure file sharing and audit trail tracking technologies. Financial auditing firms demand a cloud-based audit trail monitoring platform as well as a secure file exchange platform with high encryption standards. Users may submit and download data using a secure online interface. An administrative dashboard simplifies user registration and deactivation. The audit trail function allows the administrator to know who requested a file, when they requested it, and when the file was downloaded. This audit trail monitoring technology raises compliance responsibilities. The platform uses Advanced Encryption Standard (AES) encryption to secure data. The platform encrypts submitted files using a random key. The file owner gets a download request, which he or she may accept or deny. If the request is granted, the owner sends the user the AES key required to decode and download the file. On the platform, Amazon Web Services and Relational Database Service (RDS) hold massive files (RDS). The Amazon database is protected by login and DoS alarms. Login notifications for Amazon root and IAM users notify the administrator of the browser, IP address, date, and number of attempted logins. The administrator receives DoS attack notifications and database traffic statistics from a variety of sources. Administrators may use alerts to prevent security breaches. The solution facilitates secure and timely communication between financial auditing firms. Data is protected by AES encryption and Amazon S3 storage, while audit trail monitoring and alerts prevent data breaches.","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":"116178999","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/ICESC57686.2023.10193064
G. Jenulin Makros, J. Ancy Jenifer., B. V. Adithya, R. Rohan Samuel, M. Giribalan
Parking spots for people with disabilities help to create an environment that is accessible to everyone. Abusing these parking spots by parking when you don’t have a disability or when you don’t have a valid accessible parking permit prevents persons with disabilities from accessing resources, which is both unlawful and immoral. Through the use of a mobile application, this project allows authorized users to secure a parking place. To determine if the reserved vehicle has parked or not, this system employs RFID readers that can help recognizing the disabled vehicle. Each handicapped parking area has an IR sensor to detect the presence of a car. To warn non-disabled drivers who try to park in places reserved for the disabled, this system also uses an alarm system. The goal of this research is to make clear how various of the smart parking approaches under investigation may be utilized to administer parking for handicapped individuals and improved by validating disability parking authorization.
{"title":"Disabled Smart Parking Management using RFID Technology","authors":"G. Jenulin Makros, J. Ancy Jenifer., B. V. Adithya, R. Rohan Samuel, M. Giribalan","doi":"10.1109/ICESC57686.2023.10193064","DOIUrl":"https://doi.org/10.1109/ICESC57686.2023.10193064","url":null,"abstract":"Parking spots for people with disabilities help to create an environment that is accessible to everyone. Abusing these parking spots by parking when you don’t have a disability or when you don’t have a valid accessible parking permit prevents persons with disabilities from accessing resources, which is both unlawful and immoral. Through the use of a mobile application, this project allows authorized users to secure a parking place. To determine if the reserved vehicle has parked or not, this system employs RFID readers that can help recognizing the disabled vehicle. Each handicapped parking area has an IR sensor to detect the presence of a car. To warn non-disabled drivers who try to park in places reserved for the disabled, this system also uses an alarm system. The goal of this research is to make clear how various of the smart parking approaches under investigation may be utilized to administer parking for handicapped individuals and improved by validating disability parking authorization.","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":"116272752","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/ICESC57686.2023.10193473
D. Banerjee, V. Kukreja, Satvik Vats, Vishal Jain, Bhawna Goyal
This research utilizes a novel Convolutional Neural Network (CNN) and Support Vector Machine (SVM) based model to predict the sunflower diseases. For training the proposed model, three convolutional layers, three max-pooling layers, and two fully connected layers were used, with the second fully connected layer includes SVM. The proposed model is trained with a dataset of different diseases that affect sunflowers. The results of the proposed research study have resulted in a F1 score of 83.45 and a total accuracy of 83.59%. For classifying each disease, accuracy value has been obtained in the range of 80.65% to 85.37%. According to the meta-analysis of the layer parameters, the second fully connected layer highly influences the model’s accuracy. The results indicate that combining CNN and SVM could be an efficient strategy for predicting diseases in sunflowers and would also assist the process of disease management and crop yield.
{"title":"AI-Driven Sunflower Disease Multiclassification: Merging Convolutional Neural Networks and Support Vector Machines","authors":"D. Banerjee, V. Kukreja, Satvik Vats, Vishal Jain, Bhawna Goyal","doi":"10.1109/ICESC57686.2023.10193473","DOIUrl":"https://doi.org/10.1109/ICESC57686.2023.10193473","url":null,"abstract":"This research utilizes a novel Convolutional Neural Network (CNN) and Support Vector Machine (SVM) based model to predict the sunflower diseases. For training the proposed model, three convolutional layers, three max-pooling layers, and two fully connected layers were used, with the second fully connected layer includes SVM. The proposed model is trained with a dataset of different diseases that affect sunflowers. The results of the proposed research study have resulted in a F1 score of 83.45 and a total accuracy of 83.59%. For classifying each disease, accuracy value has been obtained in the range of 80.65% to 85.37%. According to the meta-analysis of the layer parameters, the second fully connected layer highly influences the model’s accuracy. The results indicate that combining CNN and SVM could be an efficient strategy for predicting diseases in sunflowers and would also assist the process of disease management and crop yield.","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":"123476966","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/ICESC57686.2023.10193369
Yasha Goel, A. N. Swaminathen, Rishika Yadav, B. Kanthamma, Ravi Kant, Amit Chauhan
The House Price Prediction is often employed to forecast housing market shifts. Individual house prices cannot be predicted using HPI alone due to the substantial correlation between housing price and other characteristics like location, area, and population. While several articles have used conventional machine learning methods to predict housing prices, these methods tend to focus on the market as a whole rather than on the performance of individual models. In addition, good data pretreatment methods are intended to be established to boost the precision of machine learning algorithms. The data is normalized and put to use. Features are selected using the correlation coefficient, and LSSVM is employed for model training. The proposed approach outperforms other models such as CNN and SVM.
{"title":"An Innovative Method for Housing Price Prediction using Least Square - SVM","authors":"Yasha Goel, A. N. Swaminathen, Rishika Yadav, B. Kanthamma, Ravi Kant, Amit Chauhan","doi":"10.1109/ICESC57686.2023.10193369","DOIUrl":"https://doi.org/10.1109/ICESC57686.2023.10193369","url":null,"abstract":"The House Price Prediction is often employed to forecast housing market shifts. Individual house prices cannot be predicted using HPI alone due to the substantial correlation between housing price and other characteristics like location, area, and population. While several articles have used conventional machine learning methods to predict housing prices, these methods tend to focus on the market as a whole rather than on the performance of individual models. In addition, good data pretreatment methods are intended to be established to boost the precision of machine learning algorithms. The data is normalized and put to use. Features are selected using the correlation coefficient, and LSSVM is employed for model training. The proposed approach outperforms other models such as CNN and SVM.","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":"124509642","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/ICESC57686.2023.10193514
Dipanshu Kumar Mishra, Deepak Kumar
Facial recognition is the technique used to identify the face of a person which is already detected and shows the results whether it is known or an unknown face. Face recognition is followed by the process of face detection. Both the processes are difficult tasks at their level. There are several methods or techniques to develop the system of face recognition, viz., Eigenface and Fisherface. The challenge for this system is that face images are with different backgrounds, different lighting, different facial expressions and occlusions. This system starts when an image is processed to train it. It is continued on the test image, the face is being identified, then the trained faces are compared and ultimately categorized it using classifiers of OpenCV. This study discusses the comparative study of different algorithms and come up with the most effective and convenient technique for the mentioned system.
{"title":"Face Recognition System using Artificial Intelligence: Comparison of Classifiers","authors":"Dipanshu Kumar Mishra, Deepak Kumar","doi":"10.1109/ICESC57686.2023.10193514","DOIUrl":"https://doi.org/10.1109/ICESC57686.2023.10193514","url":null,"abstract":"Facial recognition is the technique used to identify the face of a person which is already detected and shows the results whether it is known or an unknown face. Face recognition is followed by the process of face detection. Both the processes are difficult tasks at their level. There are several methods or techniques to develop the system of face recognition, viz., Eigenface and Fisherface. The challenge for this system is that face images are with different backgrounds, different lighting, different facial expressions and occlusions. This system starts when an image is processed to train it. It is continued on the test image, the face is being identified, then the trained faces are compared and ultimately categorized it using classifiers of OpenCV. This study discusses the comparative study of different algorithms and come up with the most effective and convenient technique for the mentioned system.","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":"122968950","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}