Pub Date : 2022-12-01DOI: 10.1109/ICECA55336.2022.10009087
Harshavardhan Vibhandik, Sudhanshu Kale, Samiksha Shende, M. Goudar
Healthcare sectors such as hospitals, nursing homes, medical offices, and hospice homes encountered several obstacles due to the outbreak of Covid-19. Wearing a mask, social distancing and sanitization are some of the most effective methods that have been proven to be essential to minimize the virus spread. Lately, medical executives have been appointed to monitor the virus spread and encourage the individuals to follow cautious instructions that have been provided to them. To solve the aforementioned challenges, this research study proposes an autonomous medical assistance robot. The proposed autonomous robot is completely service-based, which helps to monitor whether or not people are wearing a mask while entering any health care facility and sanitizes the people after sending a warning to wear a mask by using the image processing and computer vision technique. The robot not only monitors but also promotes social distancing by giving precautionary warnings to the people in healthcare facilities. The robot can assist the health care officials carrying the necessities of the patent while following them for maintaining a touchless environment. With thorough simulative testing and experiments, results have been finally validated.
{"title":"Medical Assistance Robot with capabilities of Mask Detection with Automatic Sanitization and Social Distancing Detection/ Awareness","authors":"Harshavardhan Vibhandik, Sudhanshu Kale, Samiksha Shende, M. Goudar","doi":"10.1109/ICECA55336.2022.10009087","DOIUrl":"https://doi.org/10.1109/ICECA55336.2022.10009087","url":null,"abstract":"Healthcare sectors such as hospitals, nursing homes, medical offices, and hospice homes encountered several obstacles due to the outbreak of Covid-19. Wearing a mask, social distancing and sanitization are some of the most effective methods that have been proven to be essential to minimize the virus spread. Lately, medical executives have been appointed to monitor the virus spread and encourage the individuals to follow cautious instructions that have been provided to them. To solve the aforementioned challenges, this research study proposes an autonomous medical assistance robot. The proposed autonomous robot is completely service-based, which helps to monitor whether or not people are wearing a mask while entering any health care facility and sanitizes the people after sending a warning to wear a mask by using the image processing and computer vision technique. The robot not only monitors but also promotes social distancing by giving precautionary warnings to the people in healthcare facilities. The robot can assist the health care officials carrying the necessities of the patent while following them for maintaining a touchless environment. With thorough simulative testing and experiments, results have been finally validated.","PeriodicalId":356949,"journal":{"name":"2022 6th International Conference on Electronics, Communication and Aerospace Technology","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124943639","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 : 2022-12-01DOI: 10.1109/ICECA55336.2022.10009148
N. S, Manu S Rao, Sagar B M, P. T, Cauvery N K
Deep learning is a branch of Artificial Intelligence (AI) where neural networks are trained to learn patterns from large amounts of data. The primary issue raised by the growth in data volume and diversity of neural networks is selecting hardware accelerators that are effective and appropriate for the specified dataset and selected neural network. This paper studies the performance of CPU and GPU based on the input data size, size of data batches and type of neural network chosen. Four datasets were chosen for benchmark testing, these included a csv data file, a textual dataset and two image datasets. Suitable neural networks were chosen for given data sets. Tests were performed on Intel i5 9th gen CPU and NVIDIA GeForce GTX 1650 GPU. The results show that performance of CPU and GPU doesn't depend on the data format, but rather depends on the type of architecture of the neural network. Neural networks which support parallelization, provide performance boost in GPU s compared to CPUs. When ANN architecture was used, CPUs performed 1.2 times better than GPUs in terms of execution time. With deeper CNN models GPUs performed 8.8 times and with RNNs 4.90 times faster than CPU s. Linear relation between dataset size and training time was observed and GPUs outdid CPUs when batch size was increased irrespective of NN architecture.
{"title":"Performance of CPUs and GPUs on Deep Learning Models For Heterogeneous Datasets","authors":"N. S, Manu S Rao, Sagar B M, P. T, Cauvery N K","doi":"10.1109/ICECA55336.2022.10009148","DOIUrl":"https://doi.org/10.1109/ICECA55336.2022.10009148","url":null,"abstract":"Deep learning is a branch of Artificial Intelligence (AI) where neural networks are trained to learn patterns from large amounts of data. The primary issue raised by the growth in data volume and diversity of neural networks is selecting hardware accelerators that are effective and appropriate for the specified dataset and selected neural network. This paper studies the performance of CPU and GPU based on the input data size, size of data batches and type of neural network chosen. Four datasets were chosen for benchmark testing, these included a csv data file, a textual dataset and two image datasets. Suitable neural networks were chosen for given data sets. Tests were performed on Intel i5 9th gen CPU and NVIDIA GeForce GTX 1650 GPU. The results show that performance of CPU and GPU doesn't depend on the data format, but rather depends on the type of architecture of the neural network. Neural networks which support parallelization, provide performance boost in GPU s compared to CPUs. When ANN architecture was used, CPUs performed 1.2 times better than GPUs in terms of execution time. With deeper CNN models GPUs performed 8.8 times and with RNNs 4.90 times faster than CPU s. Linear relation between dataset size and training time was observed and GPUs outdid CPUs when batch size was increased irrespective of NN architecture.","PeriodicalId":356949,"journal":{"name":"2022 6th International Conference on Electronics, Communication and Aerospace Technology","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127992453","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 : 2022-12-01DOI: 10.1109/ICECA55336.2022.10009188
Pallavi, Vishal Bharti
Digital forensics is the study of discovering evidence pertaining to digital crimes & attacks. To monitor and investigate cloud-based crimes, Cloud Forensics (CF) operates as a subfield of Digital Forensics. Cloud computing is a rapidly evolving, worldwide network of interconnected servers. Therefore, Cloud Forensics belongs to Network Forensics, which is a subset of Digital Forensics. There is yet to be an overt forensic revolution in the cloud service, which includes cloud businesses, cloud service providers, & cloud service customers. They cannot guarantee the security of their system or quality of their services that aid in criminal & cybercrime investigations without this crucial forensic capacity. This research study analyzes the forensics procedure, the difficulties of CF, and the tools available to help the investigation. In the context of Blockchain Technology (BT), the approaches to solutions and future possibilities of CF have been outlined. These investigations will pave the path for future scholars to have a deeper grasp of the difficulties and develop innovative solutions.
{"title":"A Comprehensive Review of Cloud Forensics and Blockchain Based Solutions","authors":"Pallavi, Vishal Bharti","doi":"10.1109/ICECA55336.2022.10009188","DOIUrl":"https://doi.org/10.1109/ICECA55336.2022.10009188","url":null,"abstract":"Digital forensics is the study of discovering evidence pertaining to digital crimes & attacks. To monitor and investigate cloud-based crimes, Cloud Forensics (CF) operates as a subfield of Digital Forensics. Cloud computing is a rapidly evolving, worldwide network of interconnected servers. Therefore, Cloud Forensics belongs to Network Forensics, which is a subset of Digital Forensics. There is yet to be an overt forensic revolution in the cloud service, which includes cloud businesses, cloud service providers, & cloud service customers. They cannot guarantee the security of their system or quality of their services that aid in criminal & cybercrime investigations without this crucial forensic capacity. This research study analyzes the forensics procedure, the difficulties of CF, and the tools available to help the investigation. In the context of Blockchain Technology (BT), the approaches to solutions and future possibilities of CF have been outlined. These investigations will pave the path for future scholars to have a deeper grasp of the difficulties and develop innovative solutions.","PeriodicalId":356949,"journal":{"name":"2022 6th International Conference on Electronics, Communication and Aerospace Technology","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126067193","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 : 2022-12-01DOI: 10.1109/ICECA55336.2022.10009346
R. Shah, Vrunda Shah, Anuja R. Nair, Tarjni Vyas, Shivani Desai, S. Degadwala
Accurate software work estimates is essential to the planning, management, and execution of a successful project on schedule and within budget. The necessity for accurate software work estimates is something that will never go away since both overestimation and underestimate provide substantial barriers to the development of additional software (SEE). Research and practise are aimed at finding the machine learning estimating technique that is most successful for a given set of criteria and data. This is the goal of the research and practise. Most academics working in a particular subject are not aware of the findings of previous studies that investigated different approaches to effort estimate in machine learning. The primary purpose of this investigation is to aid researchers working in the field of software development by assisting them in determining which method of machine learning produces the most promising effort estimate accuracy prediction.
{"title":"Software Effort Estimation using Machine Learning Algorithms","authors":"R. Shah, Vrunda Shah, Anuja R. Nair, Tarjni Vyas, Shivani Desai, S. Degadwala","doi":"10.1109/ICECA55336.2022.10009346","DOIUrl":"https://doi.org/10.1109/ICECA55336.2022.10009346","url":null,"abstract":"Accurate software work estimates is essential to the planning, management, and execution of a successful project on schedule and within budget. The necessity for accurate software work estimates is something that will never go away since both overestimation and underestimate provide substantial barriers to the development of additional software (SEE). Research and practise are aimed at finding the machine learning estimating technique that is most successful for a given set of criteria and data. This is the goal of the research and practise. Most academics working in a particular subject are not aware of the findings of previous studies that investigated different approaches to effort estimate in machine learning. The primary purpose of this investigation is to aid researchers working in the field of software development by assisting them in determining which method of machine learning produces the most promising effort estimate accuracy prediction.","PeriodicalId":356949,"journal":{"name":"2022 6th International Conference on Electronics, Communication and Aerospace Technology","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125844205","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 : 2022-12-01DOI: 10.1109/ICECA55336.2022.10009050
M. G. Kumar, R. Maheswari, M. Bakrutheen, B. Vigneshwaran
In the present decade, biodegradability is the most preferable and viable alternative solution for all kind of applications, which is also true for high voltage applications. In recent upgrades, researchers can suggest using natural oils for environmental concerns. This paper deals with the idea of blending petroleum based mineral oil (PBMO) and comestible corn oil (CCO) for high voltage liquid insulation. Conventional insulating oil has a high breakdown voltage, low viscosity and pour point, and a high flash and fire point. The main goal of the work is to navigate the blend oil ratio concentration to enhance the performance and improve the dielectric properties of insulating oil. As per standards, in order to verify the suitability of the fundamental oil test, it is taken and analyzed in all proportions. When compared to conventional oil, a blend oil ratio has exhibits the desired performance. Furthermore, the result of the fuzzy logic approach (FLA) is determined to improve the compactness of the research.
{"title":"Fuzzy Logic Based Efficient Blending of Mineral and Vegetable Oil as Alternate Liquid Insulation","authors":"M. G. Kumar, R. Maheswari, M. Bakrutheen, B. Vigneshwaran","doi":"10.1109/ICECA55336.2022.10009050","DOIUrl":"https://doi.org/10.1109/ICECA55336.2022.10009050","url":null,"abstract":"In the present decade, biodegradability is the most preferable and viable alternative solution for all kind of applications, which is also true for high voltage applications. In recent upgrades, researchers can suggest using natural oils for environmental concerns. This paper deals with the idea of blending petroleum based mineral oil (PBMO) and comestible corn oil (CCO) for high voltage liquid insulation. Conventional insulating oil has a high breakdown voltage, low viscosity and pour point, and a high flash and fire point. The main goal of the work is to navigate the blend oil ratio concentration to enhance the performance and improve the dielectric properties of insulating oil. As per standards, in order to verify the suitability of the fundamental oil test, it is taken and analyzed in all proportions. When compared to conventional oil, a blend oil ratio has exhibits the desired performance. Furthermore, the result of the fuzzy logic approach (FLA) is determined to improve the compactness of the research.","PeriodicalId":356949,"journal":{"name":"2022 6th International Conference on Electronics, Communication and Aerospace Technology","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122009833","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 : 2022-12-01DOI: 10.1109/ICECA55336.2022.10009062
Khammampati R Sreejyothi, Balakrishnakothapalli, KALAGOTLA CHENCHIREDDY, Shabbier Ahmed Sydu, V. Kumar, W. Sultana
This paper presents a bi-directional battery charger circuit. The implemented circuit is controlled by a PI controller. The DC to DC converters are plays a key role in solar power plants and battery charging stations. It is possible to charge and discharge batteries using this bi-directional DC to DC converter. The converter functions as a boost converter when it is discharging and as a buck converter when it is charging. The bi-directional converter is managed by the closed-loop PI controller. These paper simulation results are verified in MATLAB/Simulink software during battery charging and discharging mode. The simulation results during charging and discharging mode reached reference values.
{"title":"Bidirectional Battery Charger Circuit using Buck/Boost Converter","authors":"Khammampati R Sreejyothi, Balakrishnakothapalli, KALAGOTLA CHENCHIREDDY, Shabbier Ahmed Sydu, V. Kumar, W. Sultana","doi":"10.1109/ICECA55336.2022.10009062","DOIUrl":"https://doi.org/10.1109/ICECA55336.2022.10009062","url":null,"abstract":"This paper presents a bi-directional battery charger circuit. The implemented circuit is controlled by a PI controller. The DC to DC converters are plays a key role in solar power plants and battery charging stations. It is possible to charge and discharge batteries using this bi-directional DC to DC converter. The converter functions as a boost converter when it is discharging and as a buck converter when it is charging. The bi-directional converter is managed by the closed-loop PI controller. These paper simulation results are verified in MATLAB/Simulink software during battery charging and discharging mode. The simulation results during charging and discharging mode reached reference values.","PeriodicalId":356949,"journal":{"name":"2022 6th International Conference on Electronics, Communication and Aerospace Technology","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122841584","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 : 2022-12-01DOI: 10.1109/ICECA55336.2022.10009488
Parthiban Aravamudhan, T. Kanimozhi
Today, every IT business uses Cloud Computing since it's scalable and versatile. Its open and distributed nature makes security and privacy a big problem due to intruders. The Internet of Things (IoT) will impact many aspects of our lives due to its rapid development in household appliances, wearable technology, and intelligent sensors. IoT devices are connected, widespread, and low-powered. By 2020, there will be 50 billion Internet of Things (IoT) devices in use worldwide. There have been more IoT-based cyberattacks as a result of the growth of IoT devices, which now easily outweigh desktop PCs. To solve this challenge, new approaches must be developed for spotting assaults from hacked IoT devices. In this regard, machine learning and deep learning should be used as a detective control against IoT attacks. In addition to an introduction of intrusion detection methods, this paper analyses the technologies, protocols, and architecture of IoT networks and reviews the dangers of hacked IoT devices. This study examines methods for recognizing IoT cyberattacks using deep learning and machine learning. Various optimizer algorithms are discussed to improve the quality, efficiency and accuracy of the model.
{"title":"A Comprehensive Survey of Intrusion Detection Systems using Advanced Technologies","authors":"Parthiban Aravamudhan, T. Kanimozhi","doi":"10.1109/ICECA55336.2022.10009488","DOIUrl":"https://doi.org/10.1109/ICECA55336.2022.10009488","url":null,"abstract":"Today, every IT business uses Cloud Computing since it's scalable and versatile. Its open and distributed nature makes security and privacy a big problem due to intruders. The Internet of Things (IoT) will impact many aspects of our lives due to its rapid development in household appliances, wearable technology, and intelligent sensors. IoT devices are connected, widespread, and low-powered. By 2020, there will be 50 billion Internet of Things (IoT) devices in use worldwide. There have been more IoT-based cyberattacks as a result of the growth of IoT devices, which now easily outweigh desktop PCs. To solve this challenge, new approaches must be developed for spotting assaults from hacked IoT devices. In this regard, machine learning and deep learning should be used as a detective control against IoT attacks. In addition to an introduction of intrusion detection methods, this paper analyses the technologies, protocols, and architecture of IoT networks and reviews the dangers of hacked IoT devices. This study examines methods for recognizing IoT cyberattacks using deep learning and machine learning. Various optimizer algorithms are discussed to improve the quality, efficiency and accuracy of the model.","PeriodicalId":356949,"journal":{"name":"2022 6th International Conference on Electronics, Communication and Aerospace Technology","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125999522","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 : 2022-12-01DOI: 10.1109/ICECA55336.2022.10009360
A. Bhavana, K. Shalini Reddy, Madhu, D. Praveen Kumar
Deaf and dumb persons who are physically impaired use sign language to communicate. The main obstacles that have prevented much ASL study have been incorporated characteristics and local dialect variance in this work sets. To communicate with them, sign language should be learned. Peer groups are typically where learning happens. There aren't many study resources accessible for learning signs. The process of learning sign language is therefore a very challenging undertaking. Finger spelling is the first stage of sign learning, and it is also used when the signer is unfamiliar of the equivalent sign or when there isn't one. The majority of the currently available sign language learning systems rely on expensive external sensors. By gathering a dataset and using various feature extraction approaches to extract relevant data, this research discipline has been further advanced. The data is then entered into various supervised learning algorithms. The reason why the proposed results differ from existing research work is that in the developed fourfold cross validation, the validation set corresponds to the images of a person, which are different from the people present in the training set. Currently, the fourfold cross validated results are provided for various techniques.
{"title":"Deep Neural Network based Sign Language Detection","authors":"A. Bhavana, K. Shalini Reddy, Madhu, D. Praveen Kumar","doi":"10.1109/ICECA55336.2022.10009360","DOIUrl":"https://doi.org/10.1109/ICECA55336.2022.10009360","url":null,"abstract":"Deaf and dumb persons who are physically impaired use sign language to communicate. The main obstacles that have prevented much ASL study have been incorporated characteristics and local dialect variance in this work sets. To communicate with them, sign language should be learned. Peer groups are typically where learning happens. There aren't many study resources accessible for learning signs. The process of learning sign language is therefore a very challenging undertaking. Finger spelling is the first stage of sign learning, and it is also used when the signer is unfamiliar of the equivalent sign or when there isn't one. The majority of the currently available sign language learning systems rely on expensive external sensors. By gathering a dataset and using various feature extraction approaches to extract relevant data, this research discipline has been further advanced. The data is then entered into various supervised learning algorithms. The reason why the proposed results differ from existing research work is that in the developed fourfold cross validation, the validation set corresponds to the images of a person, which are different from the people present in the training set. Currently, the fourfold cross validated results are provided for various techniques.","PeriodicalId":356949,"journal":{"name":"2022 6th International Conference on Electronics, Communication and Aerospace Technology","volume":"111 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129276576","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 : 2022-12-01DOI: 10.1109/ICECA55336.2022.10009394
Saravanan Alagarsamy, S. A. Reddy, V. V. Reddy, Varun S. Reddy, Y.V. Praneeth Reddy
Physically challenged people are feeling quite difficult to operate a mouse. The suggested method employs eye moments to direct the mouse pointer as a remedy for those who are physically unable to do so. The computer vision technique is useful for controlling the mouse on a computer using eye movements. It is an alternate way that enables a person to operate their computer using their eyes alone for those who are unable to use a mouse. For those with physical disabilities, eye moment might be seen as a crucial real-time input modality for human-computer communication. The suggested method explains how to utilize a webcam and Python to implement both eye moment and moment of cursor according to eye location, which may be used to control the cursor on the screen. Eye tracking is a sensor technology that can track what someone is looking at in real time while also detecting their presence. Eye motions are converted by the technology into a data stream that includes details like pupil position, gaze vectors for each eye, and gaze point.
{"title":"Control the Movement of Mouse Using Computer Vision technique","authors":"Saravanan Alagarsamy, S. A. Reddy, V. V. Reddy, Varun S. Reddy, Y.V. Praneeth Reddy","doi":"10.1109/ICECA55336.2022.10009394","DOIUrl":"https://doi.org/10.1109/ICECA55336.2022.10009394","url":null,"abstract":"Physically challenged people are feeling quite difficult to operate a mouse. The suggested method employs eye moments to direct the mouse pointer as a remedy for those who are physically unable to do so. The computer vision technique is useful for controlling the mouse on a computer using eye movements. It is an alternate way that enables a person to operate their computer using their eyes alone for those who are unable to use a mouse. For those with physical disabilities, eye moment might be seen as a crucial real-time input modality for human-computer communication. The suggested method explains how to utilize a webcam and Python to implement both eye moment and moment of cursor according to eye location, which may be used to control the cursor on the screen. Eye tracking is a sensor technology that can track what someone is looking at in real time while also detecting their presence. Eye motions are converted by the technology into a data stream that includes details like pupil position, gaze vectors for each eye, and gaze point.","PeriodicalId":356949,"journal":{"name":"2022 6th International Conference on Electronics, Communication and Aerospace Technology","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127530758","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 : 2022-12-01DOI: 10.1109/ICECA55336.2022.10009412
P. Srihari, J. Harikiran
Thermal image is formed by capturing of radiation emitted by object to its surroundings and the difference in radiation of object and its surroundings. The advantages of Thermal images over Normal RGB images is the ability to visible at night time irrespective of illumination conditions and weather conditions like rain, fog, mist, and dust. Thermal images can form images in typical situations like smoke, dust, and high intensity, where the normal RGB camera fails to capture image. Human Activity Recognition in Thermal Images is still a challenging task due to less availability of Thermal Human Activity Datasets. This research work has proposed a human activity recognition system using Siamese Networks of Gait Skeleton Thermal Images. The proposed approach can train a new human activity by extracting Gait Skeleton from existing RGB videos and can be compared to a gait skeleton extracted from a Thermal video in case of utilizing very less thermal videos for human activity recognition. Thermal videos are extracted from IITR- IAR dataset and the performance is analyzed with CNN+LSTM, LRCN, Inflated 3D CNN, Siamese using accuracy and the proposed model has achieved a better accuracy when compared to CNN+LSTM, LRCN, Inflated 3D CNN.
热图像是通过捕获物体对周围环境的辐射以及物体与周围环境的辐射差而形成的。与普通RGB图像相比，热图像的优点是能够在夜间看到，而不受照明条件和雨、雾、雾和灰尘等天气条件的影响。热成像可以在烟雾、灰尘和高强度等典型情况下形成图像，而普通RGB相机无法捕获图像。由于热人体活动数据集的可用性较低，热图像中的人体活动识别仍然是一项具有挑战性的任务。本研究提出了一种基于步态骨骼热图像连体网络的人体活动识别系统。该方法可以通过从现有的RGB视频中提取步态骨架来训练新的人体活动，并且可以在使用很少的热视频进行人体活动识别的情况下与从热视频中提取的步态骨架进行比较。从IITR- IAR数据集中提取热视频，并使用CNN+LSTM、LRCN、Inflated 3D CNN、Siamese进行准确率分析，与CNN+LSTM、LRCN、Inflated 3D CNN相比，本文提出的模型取得了更好的准确率。
{"title":"Skeleton Based Human Activity Prediction in Gait Thermal images using Siamese Networks","authors":"P. Srihari, J. Harikiran","doi":"10.1109/ICECA55336.2022.10009412","DOIUrl":"https://doi.org/10.1109/ICECA55336.2022.10009412","url":null,"abstract":"Thermal image is formed by capturing of radiation emitted by object to its surroundings and the difference in radiation of object and its surroundings. The advantages of Thermal images over Normal RGB images is the ability to visible at night time irrespective of illumination conditions and weather conditions like rain, fog, mist, and dust. Thermal images can form images in typical situations like smoke, dust, and high intensity, where the normal RGB camera fails to capture image. Human Activity Recognition in Thermal Images is still a challenging task due to less availability of Thermal Human Activity Datasets. This research work has proposed a human activity recognition system using Siamese Networks of Gait Skeleton Thermal Images. The proposed approach can train a new human activity by extracting Gait Skeleton from existing RGB videos and can be compared to a gait skeleton extracted from a Thermal video in case of utilizing very less thermal videos for human activity recognition. Thermal videos are extracted from IITR- IAR dataset and the performance is analyzed with CNN+LSTM, LRCN, Inflated 3D CNN, Siamese using accuracy and the proposed model has achieved a better accuracy when compared to CNN+LSTM, LRCN, Inflated 3D CNN.","PeriodicalId":356949,"journal":{"name":"2022 6th International Conference on Electronics, Communication and Aerospace Technology","volume":"202 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127582971","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：