Pub Date : 2022-03-16DOI: 10.1109/ICEARS53579.2022.9752158
A. Sweatha, Naluguru Udaya Kumar, S. Bachu
Real world applications like robotic wheelchairs need the automatic detection of roads, potholes, and anomalies. Conventional image processing methods perform the improper recognition of anomalies and result in poor performance. Thus, this article mainly focuses on the implementation of Self-Supervised Label Generator (SSLG) based road anomaly detection system using vertical disparity maps. Initially, the disparity maps are used to identify the borders of the road and then anomalies are identified using filtered disparity maps. Further, the depth anomaly map is calculated using probabilistic approaches. Further, the implementations are performed on real world Red-Green-Blue-Depth (RGB-D) dataset. The simulation results show that the performance of proposed method results in superior performance as compared to the state-of-the-art approaches.
{"title":"Drivable Area and Road Anomaly Segmentation using SSLG with V-Disparity Maps","authors":"A. Sweatha, Naluguru Udaya Kumar, S. Bachu","doi":"10.1109/ICEARS53579.2022.9752158","DOIUrl":"https://doi.org/10.1109/ICEARS53579.2022.9752158","url":null,"abstract":"Real world applications like robotic wheelchairs need the automatic detection of roads, potholes, and anomalies. Conventional image processing methods perform the improper recognition of anomalies and result in poor performance. Thus, this article mainly focuses on the implementation of Self-Supervised Label Generator (SSLG) based road anomaly detection system using vertical disparity maps. Initially, the disparity maps are used to identify the borders of the road and then anomalies are identified using filtered disparity maps. Further, the depth anomaly map is calculated using probabilistic approaches. Further, the implementations are performed on real world Red-Green-Blue-Depth (RGB-D) dataset. The simulation results show that the performance of proposed method results in superior performance as compared to the state-of-the-art approaches.","PeriodicalId":252961,"journal":{"name":"2022 International Conference on Electronics and Renewable Systems (ICEARS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127171183","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 : 2022-03-16DOI: 10.1109/ICEARS53579.2022.9752290
Meghna Madhu, Anushka Xavier, N. Jayapandian
One of the deadly diseases in recent years is covid19 which is affecting the lives of peoples. Also leading to severe adverse problems and death. Prevention is done using early diagnosis and medication which in turn helps in early detection of the disease. The basic aim of the paper is to identify and further classify the patients using the chest x-rays. From scratch the Convolutional Neural Network is diagnosed producing a very high accurate and optimum results. In recent years, researchers found out that in the radiological images such as like x-rays, the traces of covid-19 can be found. In few areas, a good accuracy of the covid-19 detection cannot be achieved due to lack of the people who test so the artificial intelligence is combined with the radiological image. In machine learning the models used are deep learning by automatizing the actions and making it certain by swift, skillful and proficient outcome produced by the chest images provided by the patients. There are several layers like convolutional layer, max pooling layer etc. which are initiated and are used with aid of ReLU activation function. These images given as inputs are also classified accordingly. There is a sequence of neurons being given as input to the active dense layer and there is a result to the input by a sigmoidal function. There is a rise in efficiency because the models are trained and there is a decline of loss at the same time. If there is a model where fitting is done earlier to the overfitting and is restricted from implementing in the data augmentation. There is a better and efficient involvement of suggestions to models of deep learning. Further there is a classification of chest images for identifying and analyzing covid19. So, to check the Covid detection, the images are used as raw. In this paper a model is proposed to have good accuracy in the classification between Covid and normal and further it can be classified into three categories like Covid, pneumonia, normal. There is a 98.08% for the first one and 87.02% for the second one. By introducing 17 convolutional layers and using the Darknet model used for classifying you only look once (YOLO) for the live identification of the objects and multiple layers of filters are used. In the model there is an initial screening.
{"title":"Covid-19 Classification and Detection Model using Deep Learning","authors":"Meghna Madhu, Anushka Xavier, N. Jayapandian","doi":"10.1109/ICEARS53579.2022.9752290","DOIUrl":"https://doi.org/10.1109/ICEARS53579.2022.9752290","url":null,"abstract":"One of the deadly diseases in recent years is covid19 which is affecting the lives of peoples. Also leading to severe adverse problems and death. Prevention is done using early diagnosis and medication which in turn helps in early detection of the disease. The basic aim of the paper is to identify and further classify the patients using the chest x-rays. From scratch the Convolutional Neural Network is diagnosed producing a very high accurate and optimum results. In recent years, researchers found out that in the radiological images such as like x-rays, the traces of covid-19 can be found. In few areas, a good accuracy of the covid-19 detection cannot be achieved due to lack of the people who test so the artificial intelligence is combined with the radiological image. In machine learning the models used are deep learning by automatizing the actions and making it certain by swift, skillful and proficient outcome produced by the chest images provided by the patients. There are several layers like convolutional layer, max pooling layer etc. which are initiated and are used with aid of ReLU activation function. These images given as inputs are also classified accordingly. There is a sequence of neurons being given as input to the active dense layer and there is a result to the input by a sigmoidal function. There is a rise in efficiency because the models are trained and there is a decline of loss at the same time. If there is a model where fitting is done earlier to the overfitting and is restricted from implementing in the data augmentation. There is a better and efficient involvement of suggestions to models of deep learning. Further there is a classification of chest images for identifying and analyzing covid19. So, to check the Covid detection, the images are used as raw. In this paper a model is proposed to have good accuracy in the classification between Covid and normal and further it can be classified into three categories like Covid, pneumonia, normal. There is a 98.08% for the first one and 87.02% for the second one. By introducing 17 convolutional layers and using the Darknet model used for classifying you only look once (YOLO) for the live identification of the objects and multiple layers of filters are used. In the model there is an initial screening.","PeriodicalId":252961,"journal":{"name":"2022 International Conference on Electronics and Renewable Systems (ICEARS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126967219","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}
Renewable energy is quickly gaining importance as an alternative energy resource since fossil fuels are limited and their prices are very costly, sun being the biggest source of free energy. The main aim is to utilize the energy getting from the sun in the most efficient way. Also, farmers and other non-technical people in our country are unable to calculate the power consumed and amount of back-up that will be getting according to the load connected to the battery. Thus, the proposed system gives the solution for both the problems by making proper and efficient use of it to solve the crisis of reduction in fossil fuels, since solar is available in abundance. This is a smart system which aims to develop a dual axis solar tracker with an IoT (Internet of ThingS) monitoring system using a microcontroller. Solar panels must be aligned with the sun using a system that tracks the sun in order to optimum power output. Using panels that can revolve along an axis in relation to the location of the sun can increase conversion efficiency by at least 30-40%. Proposed system can be remotely operated using IoT .This report represents the design of a smart solar tracking system which is based on the MSP430 Microcontroller which provides movement of the solar panel in dual axis mode in direction where maximum sunlight is incident. The data which is collected from the system is stored in a cloud. So as it is observed, a two-axis solar tracking system generates more power. It is easier to maintain, no electricity required, no fuel cost and easy to install with long operating life.
{"title":"Smart Solar Tracker With Energy Monitoring","authors":"Shaista Khanam, Rohit Chavan, Shubham Bari, Komal Gupta, Shruti Kuvekar, Trupti Shah, Jayshree Mhatre","doi":"10.1109/ICEARS53579.2022.9752255","DOIUrl":"https://doi.org/10.1109/ICEARS53579.2022.9752255","url":null,"abstract":"Renewable energy is quickly gaining importance as an alternative energy resource since fossil fuels are limited and their prices are very costly, sun being the biggest source of free energy. The main aim is to utilize the energy getting from the sun in the most efficient way. Also, farmers and other non-technical people in our country are unable to calculate the power consumed and amount of back-up that will be getting according to the load connected to the battery. Thus, the proposed system gives the solution for both the problems by making proper and efficient use of it to solve the crisis of reduction in fossil fuels, since solar is available in abundance. This is a smart system which aims to develop a dual axis solar tracker with an IoT (Internet of ThingS) monitoring system using a microcontroller. Solar panels must be aligned with the sun using a system that tracks the sun in order to optimum power output. Using panels that can revolve along an axis in relation to the location of the sun can increase conversion efficiency by at least 30-40%. Proposed system can be remotely operated using IoT .This report represents the design of a smart solar tracking system which is based on the MSP430 Microcontroller which provides movement of the solar panel in dual axis mode in direction where maximum sunlight is incident. The data which is collected from the system is stored in a cloud. So as it is observed, a two-axis solar tracking system generates more power. It is easier to maintain, no electricity required, no fuel cost and easy to install with long operating life.","PeriodicalId":252961,"journal":{"name":"2022 International Conference on Electronics and Renewable Systems (ICEARS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130672201","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 : 2022-03-16DOI: 10.1109/ICEARS53579.2022.9752458
Chandini Nekkanti, Prabha K Venkata Ratna, Anupama Korabathina, Sathya Sai Guddanti, L. Vallabhaneni, P. Ramesh
In recent years, early identification of brain tumors has become a major topic of research. Early detection of a tumor for initial therapy enhances the likelihood of the victims life span. Computing Magnetic Resonance Imaging (MRI) for prior tumor identification has the dispute of high computing overhead due to the large volume of image input to the computing system. As a result, there was a significant delay and a drop in system efficiency. As a result, the demand for a more advanced detection system that can accurately segment and represent data for quicker and more precise computing has grown in the latest years. In recent literatures, new methodologies for brain tumor detection based on better learning and processing have been proposed. This study provides a brief overview of recent advances in the field of MRI computing for prompt identification and diagnosis of brain tumors, including representation, segmentation and the application of novel Image Processing and Artificial Intelligence (AI) approaches in analyzing. The present tendency in brain tumor detection computerization, as well as the benefits, limitations, and prospects of existing systems for computer aided diagnostics in detection of brain tumor, are discussed.
近年来，脑肿瘤的早期识别已成为一个重要的研究课题。早期发现肿瘤进行初始治疗可以提高患者寿命的可能性。计算磁共振成像(computational Magnetic Resonance Imaging, MRI)用于肿瘤的预先识别，由于需要向计算系统输入大量的图像，因此存在计算开销大的争议。结果，出现了明显的延迟和系统效率的下降。因此，近年来，对更先进的检测系统的需求不断增长，该系统可以准确地分割和表示数据，以实现更快、更精确的计算。在最近的文献中，提出了基于更好的学习和处理的脑肿瘤检测新方法。本研究简要概述了MRI计算在快速识别和诊断脑肿瘤方面的最新进展，包括表征、分割以及新型图像处理和人工智能(AI)方法在分析中的应用。本文讨论了目前脑肿瘤检测计算机化的发展趋势，以及现有计算机辅助诊断系统在脑肿瘤检测中的优势、局限性和前景。
{"title":"A Review of Technical Coherence between Brain Tumors and their Diagnostic Imaging Spectra","authors":"Chandini Nekkanti, Prabha K Venkata Ratna, Anupama Korabathina, Sathya Sai Guddanti, L. Vallabhaneni, P. Ramesh","doi":"10.1109/ICEARS53579.2022.9752458","DOIUrl":"https://doi.org/10.1109/ICEARS53579.2022.9752458","url":null,"abstract":"In recent years, early identification of brain tumors has become a major topic of research. Early detection of a tumor for initial therapy enhances the likelihood of the victims life span. Computing Magnetic Resonance Imaging (MRI) for prior tumor identification has the dispute of high computing overhead due to the large volume of image input to the computing system. As a result, there was a significant delay and a drop in system efficiency. As a result, the demand for a more advanced detection system that can accurately segment and represent data for quicker and more precise computing has grown in the latest years. In recent literatures, new methodologies for brain tumor detection based on better learning and processing have been proposed. This study provides a brief overview of recent advances in the field of MRI computing for prompt identification and diagnosis of brain tumors, including representation, segmentation and the application of novel Image Processing and Artificial Intelligence (AI) approaches in analyzing. The present tendency in brain tumor detection computerization, as well as the benefits, limitations, and prospects of existing systems for computer aided diagnostics in detection of brain tumor, are discussed.","PeriodicalId":252961,"journal":{"name":"2022 International Conference on Electronics and Renewable Systems (ICEARS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132397082","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 : 2022-03-16DOI: 10.1109/ICEARS53579.2022.9751731
Y. Vedavyas, S. Harsha, M. Subhash, S. Vasavi
Nowadays Drones are being widely used for surveillance and various other activities. The video stream produced by the drone can be disturbing or can contain noise data which might reduce the quality of the video stream. The video stream can be enhanced so that there is no disturbance in the video stream. The video enhancement can be done in real-time with the help of field programmable gate array (FPGA) which reduces the processing time with low energy consumption. Our project mainly focuses on enhancing the quality of the video stream using enhanced super-resolution generative adversarial networks (ESRGAN), contrast-limited Adaptive histogram equalization (CLAHE), Gamma Correction and Saturation Adjustment by integrating the image source in the drone with the FPGA.
{"title":"Quality Enhancement for Drone Based Video using FPGA","authors":"Y. Vedavyas, S. Harsha, M. Subhash, S. Vasavi","doi":"10.1109/ICEARS53579.2022.9751731","DOIUrl":"https://doi.org/10.1109/ICEARS53579.2022.9751731","url":null,"abstract":"Nowadays Drones are being widely used for surveillance and various other activities. The video stream produced by the drone can be disturbing or can contain noise data which might reduce the quality of the video stream. The video stream can be enhanced so that there is no disturbance in the video stream. The video enhancement can be done in real-time with the help of field programmable gate array (FPGA) which reduces the processing time with low energy consumption. Our project mainly focuses on enhancing the quality of the video stream using enhanced super-resolution generative adversarial networks (ESRGAN), contrast-limited Adaptive histogram equalization (CLAHE), Gamma Correction and Saturation Adjustment by integrating the image source in the drone with the FPGA.","PeriodicalId":252961,"journal":{"name":"2022 International Conference on Electronics and Renewable Systems (ICEARS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130996280","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 : 2022-03-16DOI: 10.1109/ICEARS53579.2022.9752220
S. Biruntha, B. S. Sowmiya, R. Subashri, M. Vasanth
Rainfall forecasting is extremely important in a variety of situations and contexts. By implementing good security precautions in advance, it is possible to significantly limit the consequences of unexpected and excessive rains. Accurate rainfall forecasts have become more difficult than ever before due to climatic changes. Data mining algorithms can forecast rainfall by identifying hidden patterns in meteorological variables from previous data. This study contributes by investigating the application of two data mining approaches for rainfall prediction in the city of Austin. k Nearest Neighbour (kNN) and Decision Trees are some of the techniques used. The dataset comes from a weather forecasting service and includes numerous atmospheric parameters. The pre-processing approach, which includes cleaning and normalising operations, is utilised for successful prediction. The performance of data mining algorithms are evaluated in terms of accuracy, recall, and f-measure with varied training/test data ratios. The future year's rainfall is estimated using the Decision Tree and kNN machine learning algorithms and compare the results obtained by each approach.
{"title":"Rainfall Prediction using kNN and Decision Tree","authors":"S. Biruntha, B. S. Sowmiya, R. Subashri, M. Vasanth","doi":"10.1109/ICEARS53579.2022.9752220","DOIUrl":"https://doi.org/10.1109/ICEARS53579.2022.9752220","url":null,"abstract":"Rainfall forecasting is extremely important in a variety of situations and contexts. By implementing good security precautions in advance, it is possible to significantly limit the consequences of unexpected and excessive rains. Accurate rainfall forecasts have become more difficult than ever before due to climatic changes. Data mining algorithms can forecast rainfall by identifying hidden patterns in meteorological variables from previous data. This study contributes by investigating the application of two data mining approaches for rainfall prediction in the city of Austin. k Nearest Neighbour (kNN) and Decision Trees are some of the techniques used. The dataset comes from a weather forecasting service and includes numerous atmospheric parameters. The pre-processing approach, which includes cleaning and normalising operations, is utilised for successful prediction. The performance of data mining algorithms are evaluated in terms of accuracy, recall, and f-measure with varied training/test data ratios. The future year's rainfall is estimated using the Decision Tree and kNN machine learning algorithms and compare the results obtained by each approach.","PeriodicalId":252961,"journal":{"name":"2022 International Conference on Electronics and Renewable Systems (ICEARS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127907394","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 : 2022-03-16DOI: 10.1109/ICEARS53579.2022.9751851
C. Sivakumar, D. Sathyanarayanan, P. Karthikeyan, S. Velliangiri
Recently, social media has arisen not only as a personal communication media, but also, as a media to communicate opinions about products and services or even political and general events among its users. Due to its widespread and popularity, there is a massive amount of user reviews or opinions produced and shared daily. Twitter is one of the most widely used social media micro blogging sites. In this paper, a deep learning-based approach is developed to detect the anomalies in social media using text mining. The emotional classification is considered as a part of the model that classifies emotional anomalies present in the text. Classification of such text is conducted via proper training and testing of the classifier.
{"title":"An Improvised Method for Anomaly Detection in social media using Deep Learning","authors":"C. Sivakumar, D. Sathyanarayanan, P. Karthikeyan, S. Velliangiri","doi":"10.1109/ICEARS53579.2022.9751851","DOIUrl":"https://doi.org/10.1109/ICEARS53579.2022.9751851","url":null,"abstract":"Recently, social media has arisen not only as a personal communication media, but also, as a media to communicate opinions about products and services or even political and general events among its users. Due to its widespread and popularity, there is a massive amount of user reviews or opinions produced and shared daily. Twitter is one of the most widely used social media micro blogging sites. In this paper, a deep learning-based approach is developed to detect the anomalies in social media using text mining. The emotional classification is considered as a part of the model that classifies emotional anomalies present in the text. Classification of such text is conducted via proper training and testing of the classifier.","PeriodicalId":252961,"journal":{"name":"2022 International Conference on Electronics and Renewable Systems (ICEARS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128760425","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 : 2022-03-16DOI: 10.1109/ICEARS53579.2022.9751856
Akhil Nigam, K. Sharma
There are various sustainable energy sources which play vital role in producing feasible electricity with less gas emissions and have received extensive attention of researchers across worldwide. Sunlight and wind are two commonly used renewable energy sources. There are two important factors such solar irradiance and wind speed which may change in an unconditional manner. This further produces challenges with the integration of power grid because sometimes electricity may not produce as per load requirement. Hence instead of using single energy source hybrid energy system has been introduced for the production of continuity of electricity. Hybrid energy system may consist of renewable and non-renewable energy sources. In this paper integration of hybrid power system with solar PV cell, wind turbine and hydro energy system has been described under environment of MATLAB/Simulink and done comparative analysis of hybrid energy model.
{"title":"Integration of Hybrid Energy Model with Solar PV, Hydro & Wind Turbine by Using MATLAB/Simulink","authors":"Akhil Nigam, K. Sharma","doi":"10.1109/ICEARS53579.2022.9751856","DOIUrl":"https://doi.org/10.1109/ICEARS53579.2022.9751856","url":null,"abstract":"There are various sustainable energy sources which play vital role in producing feasible electricity with less gas emissions and have received extensive attention of researchers across worldwide. Sunlight and wind are two commonly used renewable energy sources. There are two important factors such solar irradiance and wind speed which may change in an unconditional manner. This further produces challenges with the integration of power grid because sometimes electricity may not produce as per load requirement. Hence instead of using single energy source hybrid energy system has been introduced for the production of continuity of electricity. Hybrid energy system may consist of renewable and non-renewable energy sources. In this paper integration of hybrid power system with solar PV cell, wind turbine and hydro energy system has been described under environment of MATLAB/Simulink and done comparative analysis of hybrid energy model.","PeriodicalId":252961,"journal":{"name":"2022 International Conference on Electronics and Renewable Systems (ICEARS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126836465","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 : 2022-03-16DOI: 10.1109/ICEARS53579.2022.9751890
V. Pavani, M. N. Swetha, Y. Prasanthi, K. Kavya, M. Pavithra
Driver sleepiness has become a leading cause of traffic accidents and fatalities in recent years. The goal of this research is to find a way to identify driver fatigue and provide early warning so that people can be saved. Using image processing techniques, a camera captures video of the driver's face and measures the status of their eye and mouth opening ratios and delivers a warning if necessary. This is a real-time system. There are a variety of methods for determining whether a driver is drowsy, but this one is absolutely non-intrusive and has no effect on the driving in any way. The per-closure value of the eye is taken into account for the identification of drowsiness. Consequently, the driver is classified as sleepy if the closing of the eye exceeds a predetermined threshold. Offline testing of various machine learning algorithms has also been conducted. Support Vector Machine-based classification has a sensibility of 95.58 percent and a specificity of 100 percent.
{"title":"Drowsy Driver Monitoring Using Machine Learning and Visible Actions","authors":"V. Pavani, M. N. Swetha, Y. Prasanthi, K. Kavya, M. Pavithra","doi":"10.1109/ICEARS53579.2022.9751890","DOIUrl":"https://doi.org/10.1109/ICEARS53579.2022.9751890","url":null,"abstract":"Driver sleepiness has become a leading cause of traffic accidents and fatalities in recent years. The goal of this research is to find a way to identify driver fatigue and provide early warning so that people can be saved. Using image processing techniques, a camera captures video of the driver's face and measures the status of their eye and mouth opening ratios and delivers a warning if necessary. This is a real-time system. There are a variety of methods for determining whether a driver is drowsy, but this one is absolutely non-intrusive and has no effect on the driving in any way. The per-closure value of the eye is taken into account for the identification of drowsiness. Consequently, the driver is classified as sleepy if the closing of the eye exceeds a predetermined threshold. Offline testing of various machine learning algorithms has also been conducted. Support Vector Machine-based classification has a sensibility of 95.58 percent and a specificity of 100 percent.","PeriodicalId":252961,"journal":{"name":"2022 International Conference on Electronics and Renewable Systems (ICEARS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126899672","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 : 2022-03-16DOI: 10.1109/ICEARS53579.2022.9752426
D. K. Surya Teja, C. Rupa, Ch. Roop Kumar, K. Pavan
According to the Energy Information Administration (EIA), wastage of electricity in the world is more than 34%. To reduce and save energy consumption, we need to have smart and automated rooms. The smart room idea carries solace and comfort to our lives with the guide of IoT. Though there are many models of smart and automated rooms, there is a lack of security for most of them. Any person can able to operate the devices very easily without verifying their identity. One more major problem in the present situation is that electricity wastage that causes to raise the cost of the power unit. To overcome these problems, the proposed model uses a web camera for facial recognition (lbph algorithm), a smart lock for unlocking the door, and intelligent power management to reduce power consumption. This model offers the services such as security, automation, and electricity saving. The project’s end product can be predominantly focused at places where reduction of power consumption and security matters like colleges, universities, offices, etc.
{"title":"Secure Smart Room with Intelligent Power Management","authors":"D. K. Surya Teja, C. Rupa, Ch. Roop Kumar, K. Pavan","doi":"10.1109/ICEARS53579.2022.9752426","DOIUrl":"https://doi.org/10.1109/ICEARS53579.2022.9752426","url":null,"abstract":"According to the Energy Information Administration (EIA), wastage of electricity in the world is more than 34%. To reduce and save energy consumption, we need to have smart and automated rooms. The smart room idea carries solace and comfort to our lives with the guide of IoT. Though there are many models of smart and automated rooms, there is a lack of security for most of them. Any person can able to operate the devices very easily without verifying their identity. One more major problem in the present situation is that electricity wastage that causes to raise the cost of the power unit. To overcome these problems, the proposed model uses a web camera for facial recognition (lbph algorithm), a smart lock for unlocking the door, and intelligent power management to reduce power consumption. This model offers the services such as security, automation, and electricity saving. The project’s end product can be predominantly focused at places where reduction of power consumption and security matters like colleges, universities, offices, etc.","PeriodicalId":252961,"journal":{"name":"2022 International Conference on Electronics and Renewable Systems (ICEARS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126237230","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：