Pub Date : 2023-04-07DOI: 10.1109/I2CT57861.2023.10126309
Taj Sapra, Shubhama, S. Meena
The world has seen an exponential rise in machine learning and artificial intelligence since the 1990s. We apply machine learning models to solve various real life problems like regression and classification. However, class imbalance is a very common issue faced for classification problems in machine learning. In this study, we propose new greedy resampling techniques to solve the problem of class imbalance. We shall also compare the results of these techniques with the Synthetic Minority Over-sampling Technique (SMOTE).
{"title":"A Novel approach to Handle Imbalanced Dataset in Machine Learning","authors":"Taj Sapra, Shubhama, S. Meena","doi":"10.1109/I2CT57861.2023.10126309","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126309","url":null,"abstract":"The world has seen an exponential rise in machine learning and artificial intelligence since the 1990s. We apply machine learning models to solve various real life problems like regression and classification. However, class imbalance is a very common issue faced for classification problems in machine learning. In this study, we propose new greedy resampling techniques to solve the problem of class imbalance. We shall also compare the results of these techniques with the Synthetic Minority Over-sampling Technique (SMOTE).","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":"121832114","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/I2CT57861.2023.10126428
Hridya V Ramesh, Rahul Krishnan Pathinarupothi
Globally the rate of heart disease has increased drastically due to unhealthy eating habits and reduced physical activities. It has become one of the significant causes of death worldwide. As per the reports of the world health organization(WHO), 31% of all deaths worldwide are caused by cardiovascular diseases. This demands the development of a system capable of early detection of cardiovascular diseases at an affordable cost. With this as the objective, multiple machine learning algorithms have been selected to evaluate their performance in the early detection of cardiovascular diseases. This work utilizes available data sets of an individual’s vital parameters, demographic data, and exercise parameters for predicting cardiovascular diseases. An extensive evaluation is performed to identify the best-suited supervised machine learning classifier that could predict cardiovascular diseases using the available datasets. This research work details the nine different classification algorithms utilized for this analysis. For each algorithm, the F1-score, precision, recall, accuracy, and Area Under the Receiver Operating Characteristics (AUROC) values for each model have been determined and compared with the rest of the algorithms. The results show that random forest and gradient boosting models outperform others and demonstrate an F1-Score of 0.88 and an AUROC value of 0.92, respectively. This showcases that doctors could utilize this technique for the early identification of cardiovascular diseases. This will provide the opportunity to offer adequate medical treatments early, thus saving lives.
在全球范围内，由于不健康的饮食习惯和体育活动的减少，心脏病的发病率急剧上升。它已成为世界范围内死亡的主要原因之一。根据世界卫生组织(WHO)的报告，全世界31%的死亡是由心血管疾病引起的。这就要求开发一种能够以负担得起的成本及早发现心血管疾病的系统。以此为目标，我们选择了多种机器学习算法来评估它们在心血管疾病早期检测中的表现。这项工作利用个人重要参数、人口统计数据和运动参数的可用数据集来预测心血管疾病。进行了广泛的评估，以确定最适合的监督机器学习分类器，该分类器可以使用可用的数据集预测心血管疾病。这项研究工作详细介绍了用于此分析的九种不同的分类算法。对于每种算法，确定了每种模型的f1评分、精度、召回率、准确度和接收者操作特征下面积(Area Under the Receiver Operating Characteristics, AUROC)值，并与其他算法进行了比较。结果表明，随机森林模型和梯度增强模型的F1-Score为0.88,AUROC值为0.92，优于其他模型。这表明医生可以利用这项技术来早期识别心血管疾病。这将提供机会及早提供适当的医疗，从而挽救生命。
{"title":"Performance Analysis of Machine Learning Algorithms to Predict Cardiovascular Disease","authors":"Hridya V Ramesh, Rahul Krishnan Pathinarupothi","doi":"10.1109/I2CT57861.2023.10126428","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126428","url":null,"abstract":"Globally the rate of heart disease has increased drastically due to unhealthy eating habits and reduced physical activities. It has become one of the significant causes of death worldwide. As per the reports of the world health organization(WHO), 31% of all deaths worldwide are caused by cardiovascular diseases. This demands the development of a system capable of early detection of cardiovascular diseases at an affordable cost. With this as the objective, multiple machine learning algorithms have been selected to evaluate their performance in the early detection of cardiovascular diseases. This work utilizes available data sets of an individual’s vital parameters, demographic data, and exercise parameters for predicting cardiovascular diseases. An extensive evaluation is performed to identify the best-suited supervised machine learning classifier that could predict cardiovascular diseases using the available datasets. This research work details the nine different classification algorithms utilized for this analysis. For each algorithm, the F1-score, precision, recall, accuracy, and Area Under the Receiver Operating Characteristics (AUROC) values for each model have been determined and compared with the rest of the algorithms. The results show that random forest and gradient boosting models outperform others and demonstrate an F1-Score of 0.88 and an AUROC value of 0.92, respectively. This showcases that doctors could utilize this technique for the early identification of cardiovascular diseases. This will provide the opportunity to offer adequate medical treatments early, thus saving lives.","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":"116332368","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/I2CT57861.2023.10126373
Priyanka Priyadarsinee, Sumit Swain, Satyabhama Dash, M. Tripathy
This paper, initially investigates a fractional-order bandpass filter using resistors and inductors. Where, it has been found out that, by incorporation of fractional-order devices in place of classical components, the centre-frequency and bandwidth of the filter can be increased to a very high extend, i.e., to microwave range. Now, in this study, a resistorless bandpass filter has been designed and the orders of the two fractional-inductors L1 & L2 and two fractional-capacitors C1& C2 are varied from 0.3 to 1.0 one at a time. It has been found that the exponents of the elements L1 and C2 play a vital role in improving the fractional bandpass filter’s bandwidth, as well as it increases the frequency range of the filter to 1010Hz to 1025Hz ranges that are probable frequency ranges that can be used for 5G applications.
{"title":"Performance Analysis of Fractional-Order Microwave Bandpass Filter for 5G Applications","authors":"Priyanka Priyadarsinee, Sumit Swain, Satyabhama Dash, M. Tripathy","doi":"10.1109/I2CT57861.2023.10126373","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126373","url":null,"abstract":"This paper, initially investigates a fractional-order bandpass filter using resistors and inductors. Where, it has been found out that, by incorporation of fractional-order devices in place of classical components, the centre-frequency and bandwidth of the filter can be increased to a very high extend, i.e., to microwave range. Now, in this study, a resistorless bandpass filter has been designed and the orders of the two fractional-inductors L1 & L2 and two fractional-capacitors C1& C2 are varied from 0.3 to 1.0 one at a time. It has been found that the exponents of the elements L1 and C2 play a vital role in improving the fractional bandpass filter’s bandwidth, as well as it increases the frequency range of the filter to 1010Hz to 1025Hz ranges that are probable frequency ranges that can be used for 5G applications.","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":"127135335","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/I2CT57861.2023.10126393
Atul B. Kathole, Ajim Shikalgar, Nitish Supe, Tejasha Patil
India is anticipated to overtake China as the third-largest vehicle market in the near future. Vehicle theft, according to data, has increased yearly. But the proportion of cases that the police really resolve is still quite small. It is challenging for police to locate stolen vehicles since they are sometimes carried to locations distant from the scene of the theft. Therefore, a need for an automated system to assist in tracking such cars arises. These issues are what our project tries to fix. The police will receive a tonne of information from this system that they may utilise to solve theft cases. Using the YOLO V3 algorithm and Canny Edge Detection, the identification system will automatically recognize automobile license plate numbers. After a license plate is identified, the following actions are taken: 1. to photograph the license plate. 2. to recognize and divide characters. 3. The time and date are then recorded in a database together with the identifying license plate for further use. 4. In the event that a stolen vehicle is discovered, a thorough report detailing the location and the time the vehicle first appeared is prepared, and police are notified that a match has been made. The method may be applied to increase security and accuracy.
{"title":"License Plate Recognition for Detecting Stolen Vehicle Using Deep Learning","authors":"Atul B. Kathole, Ajim Shikalgar, Nitish Supe, Tejasha Patil","doi":"10.1109/I2CT57861.2023.10126393","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126393","url":null,"abstract":"India is anticipated to overtake China as the third-largest vehicle market in the near future. Vehicle theft, according to data, has increased yearly. But the proportion of cases that the police really resolve is still quite small. It is challenging for police to locate stolen vehicles since they are sometimes carried to locations distant from the scene of the theft. Therefore, a need for an automated system to assist in tracking such cars arises. These issues are what our project tries to fix. The police will receive a tonne of information from this system that they may utilise to solve theft cases. Using the YOLO V3 algorithm and Canny Edge Detection, the identification system will automatically recognize automobile license plate numbers. After a license plate is identified, the following actions are taken: 1. to photograph the license plate. 2. to recognize and divide characters. 3. The time and date are then recorded in a database together with the identifying license plate for further use. 4. In the event that a stolen vehicle is discovered, a thorough report detailing the location and the time the vehicle first appeared is prepared, and police are notified that a match has been made. The method may be applied to increase security and 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":"125123463","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/I2CT57861.2023.10126179
N. VinaySeshu, A.G.K. SriHarsha, D. Shivareddy, K. Swaraja, N. Sreekanth, C. Sujatha
The primary causes of the detrimental effects on crops and plant life are majorly plant disease and leaf disease. For the agricultural unit, this is the main risk. Food scarcity is causing agony for millions of people. Farmers' ability to make a living is severely impacted by crop damage caused by damaged leaves. Crops are not receiving a good diagnosis, which has an impact on plant growth, due to ignorance about the type of illness and pesticide usage. Food security is seriously threatened by crop diseases. It might be difficult to diagnose a disease at an early stage in many places of the world. Early recognition and diagnosis of the disease is the solution to improve the overall health of the crop and thus reduce the scarcity of the food. To help farmers, a smart agricultural framework is designed by using CNN. In this paper a 10- DCNN is implemented for the identification and diagnosis of tomato leaf disease. The proposed framework attained 95.4% of training accuracy and 93.01% of testing accuracy.
{"title":"Recognition of Tomato Leaf Disease Using 10-Layered DCNN","authors":"N. VinaySeshu, A.G.K. SriHarsha, D. Shivareddy, K. Swaraja, N. Sreekanth, C. Sujatha","doi":"10.1109/I2CT57861.2023.10126179","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126179","url":null,"abstract":"The primary causes of the detrimental effects on crops and plant life are majorly plant disease and leaf disease. For the agricultural unit, this is the main risk. Food scarcity is causing agony for millions of people. Farmers' ability to make a living is severely impacted by crop damage caused by damaged leaves. Crops are not receiving a good diagnosis, which has an impact on plant growth, due to ignorance about the type of illness and pesticide usage. Food security is seriously threatened by crop diseases. It might be difficult to diagnose a disease at an early stage in many places of the world. Early recognition and diagnosis of the disease is the solution to improve the overall health of the crop and thus reduce the scarcity of the food. To help farmers, a smart agricultural framework is designed by using CNN. In this paper a 10- DCNN is implemented for the identification and diagnosis of tomato leaf disease. The proposed framework attained 95.4% of training accuracy and 93.01% of testing 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":"125291270","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/I2CT57861.2023.10126250
A. Deo, S. Shinde, Tejas Borde, Suraj Dhamak, Shreyas Dungarwal
This review paper focuses on different methods that are already in use for Grayscale Image Colorization. Image Colorization can be done using various methods. In today’s world, Convolutional Neural Networks(CNNs), Autoencoders, Generative Adversarial Networks, etc are the modern techniques that are used for Image Colorization. This paper gives a comparative study of the above methodologies/architectures. Along with this, a review of different Loss functions is categorized into three categories viz. Error-based, GAN-based, Distribution-based Loss functions are described in detail. We also discuss different methods for the evaluation of an image colorizer. Finally we summarize the results of different methodologies.
{"title":"A Comprehensive Review of Image Colorization Methods","authors":"A. Deo, S. Shinde, Tejas Borde, Suraj Dhamak, Shreyas Dungarwal","doi":"10.1109/I2CT57861.2023.10126250","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126250","url":null,"abstract":"This review paper focuses on different methods that are already in use for Grayscale Image Colorization. Image Colorization can be done using various methods. In today’s world, Convolutional Neural Networks(CNNs), Autoencoders, Generative Adversarial Networks, etc are the modern techniques that are used for Image Colorization. This paper gives a comparative study of the above methodologies/architectures. Along with this, a review of different Loss functions is categorized into three categories viz. Error-based, GAN-based, Distribution-based Loss functions are described in detail. We also discuss different methods for the evaluation of an image colorizer. Finally we summarize the results of different methodologies.","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":"126860848","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/I2CT57861.2023.10126225
Dipali Padwad, H. Naidu
Renewable green energy generation with the study of biomass growth potential of plants using artificial light without any damage to environment is being experimented and the fuzzy logic is being implemented to compare with the actual experimental results. Plants are available abundantly in nature across the globe and become more useful by knowing the electric generation potential inside it which acts as an alternative energy source to curtail the CO2 emission as well as environmental temperature to prevent global warming. In this paper, Plant Microbial Fuel Technology (PMFC) is used on Marigold, Rose plant, Nerium Oleander, Coriander, Mustard, Tomato and Mint plants for generation of green electricity using copper and iron electrodes including study of biomass growth potential. The results are satisfactory since it concludes that hidden potential of generation of electricity and the biomass growth potential enhanced due to wavelength variations of artificial light. The voltage obtained in the plants is enhanced by introducing Boost converter model which is simulated in the MATLAB software and gave satisfactory results.
{"title":"Comparative Study with Fuzzy Logic System for Renewable Green Energy Generation","authors":"Dipali Padwad, H. Naidu","doi":"10.1109/I2CT57861.2023.10126225","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126225","url":null,"abstract":"Renewable green energy generation with the study of biomass growth potential of plants using artificial light without any damage to environment is being experimented and the fuzzy logic is being implemented to compare with the actual experimental results. Plants are available abundantly in nature across the globe and become more useful by knowing the electric generation potential inside it which acts as an alternative energy source to curtail the CO2 emission as well as environmental temperature to prevent global warming. In this paper, Plant Microbial Fuel Technology (PMFC) is used on Marigold, Rose plant, Nerium Oleander, Coriander, Mustard, Tomato and Mint plants for generation of green electricity using copper and iron electrodes including study of biomass growth potential. The results are satisfactory since it concludes that hidden potential of generation of electricity and the biomass growth potential enhanced due to wavelength variations of artificial light. The voltage obtained in the plants is enhanced by introducing Boost converter model which is simulated in the MATLAB software and gave satisfactory 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":"126864911","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/I2CT57861.2023.10126240
Sarvesh Ransubhe, Mohammad Abdul Mughni, Chinmay R. Shiralkar, Bhakti Ratnaparkhi
Different Traffic control systems have played a crucial part in traffic management around the globe, especially in densely populated major cities, but they are still not as efficient as they could be. Perhaps some changes can be made to better deal with the traffic in this ever-changing traffic density environment. Traffic congestion has consistently been a rage issue in numerous urban cities. The traditional way was to give each lane a specific predefined time with the green light and had to stop for the rest of the time. Even the lanes with no traffic got the same amount of time as the lane with huge traffic jams. These were promoting traffic congestion rather than solving the issue. Thus, the need for a better system has emerged for changing the current traffic handling setup to be smarter enough to meet this ever-changing demand. In this paper, the idea of traffic lights controlled by live video feed is explored with an enhanced traffic flow system to optimally benefit from the computer vision technology used.
{"title":"Smart Traffic Light Switching and Traffic Density Calculation Model using Computer Vision","authors":"Sarvesh Ransubhe, Mohammad Abdul Mughni, Chinmay R. Shiralkar, Bhakti Ratnaparkhi","doi":"10.1109/I2CT57861.2023.10126240","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126240","url":null,"abstract":"Different Traffic control systems have played a crucial part in traffic management around the globe, especially in densely populated major cities, but they are still not as efficient as they could be. Perhaps some changes can be made to better deal with the traffic in this ever-changing traffic density environment. Traffic congestion has consistently been a rage issue in numerous urban cities. The traditional way was to give each lane a specific predefined time with the green light and had to stop for the rest of the time. Even the lanes with no traffic got the same amount of time as the lane with huge traffic jams. These were promoting traffic congestion rather than solving the issue. Thus, the need for a better system has emerged for changing the current traffic handling setup to be smarter enough to meet this ever-changing demand. In this paper, the idea of traffic lights controlled by live video feed is explored with an enhanced traffic flow system to optimally benefit from the computer vision technology used.","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":"126110862","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}
In the recent years, recognition of human actions and the interactions of human body bones provide crucial data. It has been applied in many fields from video intelligence to computer vision. The idea behind working of these have a common approach of using deep learning methods that include Convolutional Networks. The Graph convolution networks (GCN) is extensively used in recognition of skeleton action-based data. We point out that current GCN-based methods generally rely on specified graphical patterns (i.e., a hand-crafted structure of the joints in the skeleton), which hinders their potential to gather intricate connections between joints. Thus a better advanced model can be proposed out of the GCN-based model. This paper aims in delivering a novel model of Spatial Temporal Graph Convolutional Networks (ST-GCN) are interactive skeletons that learn from the spatial and temporal variability of input data(ST-GCN) [1]. We here use a large dataset –Kinetics to perform the analysis and predict the output for given skeletal data.
{"title":"Convolutional Networks for Skeleton-Based Gesture Recognition Using Spatial Temporal Graphs","authors":"Soumya Jituri, Sankalp Balannavar, Shri Nagahari Savanur, Guruprasad Ghaligi, A. Shanbhag, Uday Kulkarni","doi":"10.1109/I2CT57861.2023.10126371","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126371","url":null,"abstract":"In the recent years, recognition of human actions and the interactions of human body bones provide crucial data. It has been applied in many fields from video intelligence to computer vision. The idea behind working of these have a common approach of using deep learning methods that include Convolutional Networks. The Graph convolution networks (GCN) is extensively used in recognition of skeleton action-based data. We point out that current GCN-based methods generally rely on specified graphical patterns (i.e., a hand-crafted structure of the joints in the skeleton), which hinders their potential to gather intricate connections between joints. Thus a better advanced model can be proposed out of the GCN-based model. This paper aims in delivering a novel model of Spatial Temporal Graph Convolutional Networks (ST-GCN) are interactive skeletons that learn from the spatial and temporal variability of input data(ST-GCN) [1]. We here use a large dataset –Kinetics to perform the analysis and predict the output for given skeletal data.","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":"127827519","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/I2CT57861.2023.10126180
Rachuri Sai Manasa, Jatoth Madhu, MD Sufiyanuddin, Patil Mounica
In today’s scenario traffic congestion is a serious issue to look after which has became a hectic issue to solve. There are some major consequences due to this traffic congestion like pollution, wastage of time due to the unnecessary stoppage at the signals due to the conventional time based signaling system and even it results in the loss of human life if the emergency vehicle like Ambulance got stuck in the traffic. So, to resolve these issues we have implemented a device which clears the traffic based on density as wells as when the ambulance arrives at the signal. This paper mainly focus on two important aspects 1. Clearing the traffic based on the density by using of IR sensors and Arduino UNO helps in collecting, processing and analyzing the information which monitors the signal accordingly 2. Controlling of traffic for ambulance by using IOT. Blynkapp is an IOT platforms used for the monitoring of the ambulance when it arrives near the traffic signals.
{"title":"Smart Traffic Signal Management System","authors":"Rachuri Sai Manasa, Jatoth Madhu, MD Sufiyanuddin, Patil Mounica","doi":"10.1109/I2CT57861.2023.10126180","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126180","url":null,"abstract":"In today’s scenario traffic congestion is a serious issue to look after which has became a hectic issue to solve. There are some major consequences due to this traffic congestion like pollution, wastage of time due to the unnecessary stoppage at the signals due to the conventional time based signaling system and even it results in the loss of human life if the emergency vehicle like Ambulance got stuck in the traffic. So, to resolve these issues we have implemented a device which clears the traffic based on density as wells as when the ambulance arrives at the signal. This paper mainly focus on two important aspects 1. Clearing the traffic based on the density by using of IR sensors and Arduino UNO helps in collecting, processing and analyzing the information which monitors the signal accordingly 2. Controlling of traffic for ambulance by using IOT. Blynkapp is an IOT platforms used for the monitoring of the ambulance when it arrives near the traffic signals.","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":"127589803","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：