A technique for video stabilization that maintains the subject steady while also eliminating hand shaking. Our network topology is especially made to stabilize both the background and the foreground simultaneously while giving the user the opportunity to adjust the stabilization emphasis. We additionally offer a real-time frame-warping stiff moving least squares grid approximation. To explicitly infer the stiff moving least squares warping, which implicitly balances between global rigidity and local flexibility, a linear convolutional network is utilised. Our method is fully automated and requires no user preparation or input. The use of video stabilization is crucial in both amateur and professional filming. As a result, there are several mechanical, optical, and computational solutions. Stabilization may be used to capture handheld photos with lengthy exposure durations in still image photography as well.
{"title":"Utilizing the Point Feature Matching for Video Stabilization","authors":"Nithin Kumar Brahamadevara, GAE Satish Kumar, Purna Goud Palusa, Dinesh Bandaru","doi":"10.1109/I2CT57861.2023.10126471","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126471","url":null,"abstract":"A technique for video stabilization that maintains the subject steady while also eliminating hand shaking. Our network topology is especially made to stabilize both the background and the foreground simultaneously while giving the user the opportunity to adjust the stabilization emphasis. We additionally offer a real-time frame-warping stiff moving least squares grid approximation. To explicitly infer the stiff moving least squares warping, which implicitly balances between global rigidity and local flexibility, a linear convolutional network is utilised. Our method is fully automated and requires no user preparation or input. The use of video stabilization is crucial in both amateur and professional filming. As a result, there are several mechanical, optical, and computational solutions. Stabilization may be used to capture handheld photos with lengthy exposure durations in still image photography as well.","PeriodicalId":150346,"journal":{"name":"2023 IEEE 8th International Conference for Convergence in Technology (I2CT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125648739","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 : 2023-04-07DOI: 10.1109/I2CT57861.2023.10126217
A. Chikaraddi, Suvarna G. Kanakaraddi, Pavan Kamat, S. V. Budani, Karuna C. Gull
A life care management system is a web-based application that generally manages the client details, hires the agent, and provides the portal so that he can add clients and study the policy details. This project aims to create a portal that allows personal information to be updated securely using a website to get updates about the agent and client and then follow up with the client to pay the premium. There are many possibilities of fraud customers or some customers who may not be eligible for that policy, where a machine learning algorithm will help to find whether the policy should be approved or not. So that the agent doesn’t go on to any complications of adding the customer and find any difficulty. To help the CLIA officer(admin) and agent, this work helps to record the data and handle the data Smoothly.
{"title":"Lifecare Management system using Machine Learning Techniques","authors":"A. Chikaraddi, Suvarna G. Kanakaraddi, Pavan Kamat, S. V. Budani, Karuna C. Gull","doi":"10.1109/I2CT57861.2023.10126217","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126217","url":null,"abstract":"A life care management system is a web-based application that generally manages the client details, hires the agent, and provides the portal so that he can add clients and study the policy details. This project aims to create a portal that allows personal information to be updated securely using a website to get updates about the agent and client and then follow up with the client to pay the premium. There are many possibilities of fraud customers or some customers who may not be eligible for that policy, where a machine learning algorithm will help to find whether the policy should be approved or not. So that the agent doesn’t go on to any complications of adding the customer and find any difficulty. To help the CLIA officer(admin) and agent, this work helps to record the data and handle the data Smoothly.","PeriodicalId":150346,"journal":{"name":"2023 IEEE 8th International Conference for Convergence in Technology (I2CT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132382743","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 : 2023-04-07DOI: 10.1109/I2CT57861.2023.10126119
V. Rao, M. Rani
With increase in memory dimensions and complexity, the VLSI manufacturing units are working on improving the features of memory dice for bigger capacities. Fault tolerant techniques are employed to take care of increased faults as the probability faults are increasing with increase in memory size. This is achieved by incorporating built-in redundancy analysis (BIRA) into the chip. For multiple memories of SoC, simple spare structure with local spares and columns is inadequate as optimum repair rate and area overhead are not obtained. So the proposed work global spares are incorporated in addition to local spares to enhance the yield and reduce hardware overhead. The proposed algorithm searches these various spares efficiently resulting in less hardware overhead with quick analysis.
{"title":"Efficient Built in Self Repair for Multiple RAMs","authors":"V. Rao, M. Rani","doi":"10.1109/I2CT57861.2023.10126119","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126119","url":null,"abstract":"With increase in memory dimensions and complexity, the VLSI manufacturing units are working on improving the features of memory dice for bigger capacities. Fault tolerant techniques are employed to take care of increased faults as the probability faults are increasing with increase in memory size. This is achieved by incorporating built-in redundancy analysis (BIRA) into the chip. For multiple memories of SoC, simple spare structure with local spares and columns is inadequate as optimum repair rate and area overhead are not obtained. So the proposed work global spares are incorporated in addition to local spares to enhance the yield and reduce hardware overhead. The proposed algorithm searches these various spares efficiently resulting in less hardware overhead with quick analysis.","PeriodicalId":150346,"journal":{"name":"2023 IEEE 8th International Conference for Convergence in Technology (I2CT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125204484","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 : 2023-04-07DOI: 10.1109/I2CT57861.2023.10126398
Lohith R, Manjula R. Bharamagoudra, T. S. S. Reddy, K. Sravani
Our daily life starts with providing nutrition to our human body. A huge amount of food is provided by the agricultural sector. But always there isn’t 100% yield because of some issues like plant diseases, irregular rainfall, Natural disasters, etc. A major issue is plant diseases which are troublesome for this industry. An accurate and quick detection model is required for identifying the disease. In this paper, we have tested many classification algorithms for performance analysis such as EffecientNet-B0, GoogleNet, Resnext50 32x4d, and MobileNet-V2 on a GPU system. Various parameters have been taken into consideration for evaluating different classification models such as training time, training accuracy, and total loss to predict the best model which uses the least GPU cores and the result claims that Resnext50 32x4d gives higher accuracy.
{"title":"Performance Analysis of Convolutional Neural Network for Plant Diseases Identification","authors":"Lohith R, Manjula R. Bharamagoudra, T. S. S. Reddy, K. Sravani","doi":"10.1109/I2CT57861.2023.10126398","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126398","url":null,"abstract":"Our daily life starts with providing nutrition to our human body. A huge amount of food is provided by the agricultural sector. But always there isn’t 100% yield because of some issues like plant diseases, irregular rainfall, Natural disasters, etc. A major issue is plant diseases which are troublesome for this industry. An accurate and quick detection model is required for identifying the disease. In this paper, we have tested many classification algorithms for performance analysis such as EffecientNet-B0, GoogleNet, Resnext50 32x4d, and MobileNet-V2 on a GPU system. Various parameters have been taken into consideration for evaluating different classification models such as training time, training accuracy, and total loss to predict the best model which uses the least GPU cores and the result claims that Resnext50 32x4d gives higher accuracy.","PeriodicalId":150346,"journal":{"name":"2023 IEEE 8th International Conference for Convergence in Technology (I2CT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131170046","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 : 2023-04-07DOI: 10.1109/I2CT57861.2023.10126481
A. Kaulage, Shraddha Shaha, Tanaya Naik, Khushi Nikumbh, Vedant Jagtap
This paper focuses on minimizing energy consumption by servers in data centers. Server’s energy consumption can be impacted by numerous factors, such as the number of connected devices, the workload being processed, and the energy efficiency of the components.High energy consumption can be serious because of several reasons as it can impact the reliability of servers because high temperatures generated by energy consumption can lead to hardware failure and other technical issues. Therefore, reducing energy consumption in servers is important for improving the cost-effectiveness, sustainability, scalability, and reliability of data center operations. A type of reinforcement learning called Deep Q-Learning (DQL) can be used to address issues with server energy consumption. The basic idea behind DQL is to train an artificial agent, such as a neural network, to make decisions about energy consumption in real time. The agent is trained by frequently performing actions in a setting and earning rewards depending on the amount of energy consumed by specific actions. Over time, the agent learns which actions are most likely to lead to energy savings, and it can then be deployed to make real-time decisions about energy consumption in a server. Experimental results of the proposed research show an average of 66% power saving in the server’s consumption of energy using Deep Q-Learning (DQL).
{"title":"AI Approach for Minimizing The Energy Consumption of Servers Using Deep-Q-Learning","authors":"A. Kaulage, Shraddha Shaha, Tanaya Naik, Khushi Nikumbh, Vedant Jagtap","doi":"10.1109/I2CT57861.2023.10126481","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126481","url":null,"abstract":"This paper focuses on minimizing energy consumption by servers in data centers. Server’s energy consumption can be impacted by numerous factors, such as the number of connected devices, the workload being processed, and the energy efficiency of the components.High energy consumption can be serious because of several reasons as it can impact the reliability of servers because high temperatures generated by energy consumption can lead to hardware failure and other technical issues. Therefore, reducing energy consumption in servers is important for improving the cost-effectiveness, sustainability, scalability, and reliability of data center operations. A type of reinforcement learning called Deep Q-Learning (DQL) can be used to address issues with server energy consumption. The basic idea behind DQL is to train an artificial agent, such as a neural network, to make decisions about energy consumption in real time. The agent is trained by frequently performing actions in a setting and earning rewards depending on the amount of energy consumed by specific actions. Over time, the agent learns which actions are most likely to lead to energy savings, and it can then be deployed to make real-time decisions about energy consumption in a server. Experimental results of the proposed research show an average of 66% power saving in the server’s consumption of energy using Deep Q-Learning (DQL).","PeriodicalId":150346,"journal":{"name":"2023 IEEE 8th International Conference for Convergence in Technology (I2CT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130947238","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}
To ensure power quality, the power system needs to be monitored and analyzed. Often, accidents happen as a result of poor power supply quality. So both the power department and the consumers of electricity seek to raise the quality of the power. Observe and analyses Power quality systems are commonly employed. Using a technique for frequency spectrum analysis based on the capture of time domain data, the research tracked fluctuations in the power quality index and examined their causes. Using LabVIEW, a monitoring and analysis system is created. This study first discussed the significance of monitoring power quality and analyzing its index before introducing the fundamental concept
{"title":"IoT based Multifunctional Power Analyzer","authors":"Bhagyashri Baviskar, Gargi Deshmukh, Dipak Shimpi, Amrita Tuteja","doi":"10.1109/I2CT57861.2023.10126265","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126265","url":null,"abstract":"To ensure power quality, the power system needs to be monitored and analyzed. Often, accidents happen as a result of poor power supply quality. So both the power department and the consumers of electricity seek to raise the quality of the power. Observe and analyses Power quality systems are commonly employed. Using a technique for frequency spectrum analysis based on the capture of time domain data, the research tracked fluctuations in the power quality index and examined their causes. Using LabVIEW, a monitoring and analysis system is created. This study first discussed the significance of monitoring power quality and analyzing its index before introducing the fundamental concept","PeriodicalId":150346,"journal":{"name":"2023 IEEE 8th International Conference for Convergence in Technology (I2CT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132153787","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 : 2023-04-07DOI: 10.1109/I2CT57861.2023.10126305
Uday Kulkarni, Shashank Agasimani, Pranavi P Kulkarni, Sagar P Kabadi, P. Aditya, Raunak Ujawane
A Rough Surface involves a lot of imperfections and is prone to friction as it offers resistance to moving objects on the surface. The roughness of a Surface is an indicator of the probable performance of every mechanical component since imperfections on the surface might further lead to the formation of nucleation sites for corrosion or ruptures. As rough surfaces have higher friction coefficients as compared to smooth surfaces, it becomes absolutely imperative to test surface roughness and take appropriate action before deployment in automobiles and other industries in order to maintain safety standards. Surface roughness is a calculation of the relative roughness of a surface profile based on a single numeric parameter, Average Roughness (RA). RA is the most commonly specified surface texture parameter measured using a Stylus based instrument wherein a small tip is dragged across any surface while its undulations are recorded which provides a general measure of surface texture in microns. This paper proposes a Machine Learning model developed to read the detected value from the RA Tester and store it in the database thereby reducing manual interference. This proposed model uses a pipeline of the YOLOv5 Algorithm and EasyOCR to detect the Region Of Interest (ROI) from the image and the RA values respectively. This paper produces a real-time solution with an Accuracy of 95.3% for an Automated Entry of the Roughness Average values read directly from the image into the database and has been implemented successfully in the Automobile Industry. This project was conceptualized and Implemented jointly by KLE Technological University and Dana Anand India Private Limited, Dharwad, India.
{"title":"Vision based Roughness Average Value Detection using YOLOv5 and EasyOCR","authors":"Uday Kulkarni, Shashank Agasimani, Pranavi P Kulkarni, Sagar P Kabadi, P. Aditya, Raunak Ujawane","doi":"10.1109/I2CT57861.2023.10126305","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126305","url":null,"abstract":"A Rough Surface involves a lot of imperfections and is prone to friction as it offers resistance to moving objects on the surface. The roughness of a Surface is an indicator of the probable performance of every mechanical component since imperfections on the surface might further lead to the formation of nucleation sites for corrosion or ruptures. As rough surfaces have higher friction coefficients as compared to smooth surfaces, it becomes absolutely imperative to test surface roughness and take appropriate action before deployment in automobiles and other industries in order to maintain safety standards. Surface roughness is a calculation of the relative roughness of a surface profile based on a single numeric parameter, Average Roughness (RA). RA is the most commonly specified surface texture parameter measured using a Stylus based instrument wherein a small tip is dragged across any surface while its undulations are recorded which provides a general measure of surface texture in microns. This paper proposes a Machine Learning model developed to read the detected value from the RA Tester and store it in the database thereby reducing manual interference. This proposed model uses a pipeline of the YOLOv5 Algorithm and EasyOCR to detect the Region Of Interest (ROI) from the image and the RA values respectively. This paper produces a real-time solution with an Accuracy of 95.3% for an Automated Entry of the Roughness Average values read directly from the image into the database and has been implemented successfully in the Automobile Industry. This project was conceptualized and Implemented jointly by KLE Technological University and Dana Anand India Private Limited, Dharwad, India.","PeriodicalId":150346,"journal":{"name":"2023 IEEE 8th International Conference for Convergence in Technology (I2CT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132687262","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 article discusses the exponential stabilization of node-dependent delayed multilayer neural networks (NDDMNNs) under impulsive control. To address different modeling requirements in complicated applications, node-based interlayer and intralayer parameters are presented to design the neural network model, indicating that The nodes constituting the network can have different structures. Meanwhile, the novel model considers the node-dependent time-varying delays, and this article develops the sparse matrix approach to translate the node-dependent delayed NDDMNNs model into an multiple delayed model, ensuring that the vector form of NDDMNNs can be constructed and studied by using existing technical approaches. Then, an analytical framework with super-Laplacian matrix and time-dependent Lyapunov function methods is proposed to derive exponential stabilization results. Finally, a numerical simulation example is given to verify the obtained results.
{"title":"Impulsive Stabilization of Unconstrained Multilayer Recurrent Neural Networks with Node-Based Time-varying Delays","authors":"Xiangxiang Wang, Yongbin Yu, Xiao Feng, Xinyi Han, Jingya Wang, Jingye Cai","doi":"10.1109/I2CT57861.2023.10126392","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126392","url":null,"abstract":"This article discusses the exponential stabilization of node-dependent delayed multilayer neural networks (NDDMNNs) under impulsive control. To address different modeling requirements in complicated applications, node-based interlayer and intralayer parameters are presented to design the neural network model, indicating that The nodes constituting the network can have different structures. Meanwhile, the novel model considers the node-dependent time-varying delays, and this article develops the sparse matrix approach to translate the node-dependent delayed NDDMNNs model into an multiple delayed model, ensuring that the vector form of NDDMNNs can be constructed and studied by using existing technical approaches. Then, an analytical framework with super-Laplacian matrix and time-dependent Lyapunov function methods is proposed to derive exponential stabilization results. Finally, a numerical simulation example is given to verify the obtained results.","PeriodicalId":150346,"journal":{"name":"2023 IEEE 8th International Conference for Convergence in Technology (I2CT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127641859","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 : 2023-04-07DOI: 10.1109/I2CT57861.2023.10126237
Pratik J. Mhatre, M. Joshi
In this paper, authors propose electrically small wearable tunable antenna that could conform to a smartwatch dial. This antenna has been designed with a clear target of fitting it into smartwatch. Proposed antenna has been tuned to human body parameters and resonates at 2.4 GHz band. For this, authors have utilized a human body model they have published previously. The final antenna design has been evolved from simple monopole and a shorting pin has been added to improve the return loss. Antenna PCB is fabricated using FR4 substrate of 1.6 mm height and radius of 17.5 mm. Return loss at 2.4 GHz is -24 dB and VSWR value 1.2 is observed. Authors can achieve gain of 0.5 dB. Simulated and measured results of antenna are found in agreement.
{"title":"\"Electrically Small Wearable Tunable Antenna that fits into Smartwatch Dial\"","authors":"Pratik J. Mhatre, M. Joshi","doi":"10.1109/I2CT57861.2023.10126237","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126237","url":null,"abstract":"In this paper, authors propose electrically small wearable tunable antenna that could conform to a smartwatch dial. This antenna has been designed with a clear target of fitting it into smartwatch. Proposed antenna has been tuned to human body parameters and resonates at 2.4 GHz band. For this, authors have utilized a human body model they have published previously. The final antenna design has been evolved from simple monopole and a shorting pin has been added to improve the return loss. Antenna PCB is fabricated using FR4 substrate of 1.6 mm height and radius of 17.5 mm. Return loss at 2.4 GHz is -24 dB and VSWR value 1.2 is observed. Authors can achieve gain of 0.5 dB. Simulated and measured results of antenna are found in agreement.","PeriodicalId":150346,"journal":{"name":"2023 IEEE 8th International Conference for Convergence in Technology (I2CT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131848576","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：