Pub Date : 2023-07-19DOI: 10.1109/ICECAA58104.2023.10212373
P. Nagaraj, T. Rajkumar, S. Rakesh, A.Kavya Siva Durga, M. Jyothi, Ch. Guru Sai Nithin
Every area of the global economy has seen great advancements thanks to artificial intelligence, and agronomy is no exception. Modern agricultural farming faces great challenges in the cultivation of healthy crops. The “Internet of Things” is a system made up of actuators, sensors, or both that either directly or indirectly connect devices to the Internet. The development of the Internet of Things (IoT) can be used in smart farming to improve the standard of agriculture. The foundation of the Indian economy, agriculture, contributes to the country's overall economic growth. Yet, because of the usage of antiquated farming technology and the fact that individuals from rural areas now go to urban areas for more lucrative businesses rather than concentrating on agriculture, the obtained productivity is quite low compared to global standards. This artificial intelligence assists in increasing crop productivity and identifies or keeps track of crop illnesses. based on artificial intelligence to identify crop or leaf diseases, a robot or equipment has been created. It distinguishes or categorizes the plant as either disease-affected or unaffected. Image segmentation is a technique used to isolate the specific disease's affected area. This system's classification of diseased leaves offers farmers a better course of action. Faster feature collection, feature extraction, and illness classification methods based on R-CNN identify the disease afflicted.
{"title":"AI-based Leaf Disease Identification Robot using IoT Approach","authors":"P. Nagaraj, T. Rajkumar, S. Rakesh, A.Kavya Siva Durga, M. Jyothi, Ch. Guru Sai Nithin","doi":"10.1109/ICECAA58104.2023.10212373","DOIUrl":"https://doi.org/10.1109/ICECAA58104.2023.10212373","url":null,"abstract":"Every area of the global economy has seen great advancements thanks to artificial intelligence, and agronomy is no exception. Modern agricultural farming faces great challenges in the cultivation of healthy crops. The “Internet of Things” is a system made up of actuators, sensors, or both that either directly or indirectly connect devices to the Internet. The development of the Internet of Things (IoT) can be used in smart farming to improve the standard of agriculture. The foundation of the Indian economy, agriculture, contributes to the country's overall economic growth. Yet, because of the usage of antiquated farming technology and the fact that individuals from rural areas now go to urban areas for more lucrative businesses rather than concentrating on agriculture, the obtained productivity is quite low compared to global standards. This artificial intelligence assists in increasing crop productivity and identifies or keeps track of crop illnesses. based on artificial intelligence to identify crop or leaf diseases, a robot or equipment has been created. It distinguishes or categorizes the plant as either disease-affected or unaffected. Image segmentation is a technique used to isolate the specific disease's affected area. This system's classification of diseased leaves offers farmers a better course of action. Faster feature collection, feature extraction, and illness classification methods based on R-CNN identify the disease afflicted.","PeriodicalId":114624,"journal":{"name":"2023 2nd International Conference on Edge Computing and Applications (ICECAA)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122344373","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-07-19DOI: 10.1109/ICECAA58104.2023.10212368
M. Minu, K. Reddy, DouleNithishkumar, AmbadasRithvikBhargav
Due to the exponential increase in IoT device production, the IoT (Internet of Things) business has experienced rapid expansion on the market, which gives attackers a larger attack surface from which to launch potentially more devastating assaults. There has been a rise in cyber-attacks. When intruders perform cyber-attacks utilizing unique and inventive ways, many of these attacks have effectively fulfilled the maliciousintentions. Conventional machine learning approaches seem ineffective in the context of unanticipated network technology and various penetration strategies. The introduction of new vulnerabilities is a result of cyber-physical applications leveraging Internet of Things (IoT) devices. Because of the cross-domain, cross-layer, and multidisciplinary nature of the emerging security and dependability concerns, a comprehensive solution is required.
{"title":"A Hybrid Deep IoT Network-Driven Anomaly Detection using Multi-Scale Deep Representation Learning","authors":"M. Minu, K. Reddy, DouleNithishkumar, AmbadasRithvikBhargav","doi":"10.1109/ICECAA58104.2023.10212368","DOIUrl":"https://doi.org/10.1109/ICECAA58104.2023.10212368","url":null,"abstract":"Due to the exponential increase in IoT device production, the IoT (Internet of Things) business has experienced rapid expansion on the market, which gives attackers a larger attack surface from which to launch potentially more devastating assaults. There has been a rise in cyber-attacks. When intruders perform cyber-attacks utilizing unique and inventive ways, many of these attacks have effectively fulfilled the maliciousintentions. Conventional machine learning approaches seem ineffective in the context of unanticipated network technology and various penetration strategies. The introduction of new vulnerabilities is a result of cyber-physical applications leveraging Internet of Things (IoT) devices. Because of the cross-domain, cross-layer, and multidisciplinary nature of the emerging security and dependability concerns, a comprehensive solution is required.","PeriodicalId":114624,"journal":{"name":"2023 2nd International Conference on Edge Computing and Applications (ICECAA)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122548664","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-07-19DOI: 10.1109/ICECAA58104.2023.10212120
P. G, Devi R
Malicious websites are purposefully designed to deceive internet users to steal sensitive personal information, infect the victim's system with malware, cause financial losses, and damage the victim's reputation. Finding these pages or links is hard for internet users. Such websites are discovered using detection tools. The majority of detection techniques use blacklisting or whitelisting strategies to find and prevent malicious websites. However, compiling such a sizable list of website links is a time-consuming job that is challenging to update regularly. Therefore, the researchers employ machine learning-based methods to identify these fraudulent connections. These methods are based on the features taken from URLs or web pages. Additionally, features such as DNS details, webpage reputation, and visual similarity data are used. However, these features are few and do not fully utilize the URLs or website contents. This work focuses on merging URL lexical features and content-based features for malicious webpage detection in order to fully exploit the dataset's potential. Natural language processing methods like Hashing, Count, and Term Frequency - Inverse Document Frequency (TF-IDF) vectorizers are employed to extract features from the content of Web pages. The suggested approach's efficiency is evaluated by using the most well-known machine learning methods. The outcome shows that the Count vectorizer with Random Forest achieves a higher accuracy of 91.17% with 500 features.
{"title":"Malicious Webpage Detection Based on Feature Fusion Using Natural Language Processing and Machine Learning","authors":"P. G, Devi R","doi":"10.1109/ICECAA58104.2023.10212120","DOIUrl":"https://doi.org/10.1109/ICECAA58104.2023.10212120","url":null,"abstract":"Malicious websites are purposefully designed to deceive internet users to steal sensitive personal information, infect the victim's system with malware, cause financial losses, and damage the victim's reputation. Finding these pages or links is hard for internet users. Such websites are discovered using detection tools. The majority of detection techniques use blacklisting or whitelisting strategies to find and prevent malicious websites. However, compiling such a sizable list of website links is a time-consuming job that is challenging to update regularly. Therefore, the researchers employ machine learning-based methods to identify these fraudulent connections. These methods are based on the features taken from URLs or web pages. Additionally, features such as DNS details, webpage reputation, and visual similarity data are used. However, these features are few and do not fully utilize the URLs or website contents. This work focuses on merging URL lexical features and content-based features for malicious webpage detection in order to fully exploit the dataset's potential. Natural language processing methods like Hashing, Count, and Term Frequency - Inverse Document Frequency (TF-IDF) vectorizers are employed to extract features from the content of Web pages. The suggested approach's efficiency is evaluated by using the most well-known machine learning methods. The outcome shows that the Count vectorizer with Random Forest achieves a higher accuracy of 91.17% with 500 features.","PeriodicalId":114624,"journal":{"name":"2023 2nd International Conference on Edge Computing and Applications (ICECAA)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122948963","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-07-19DOI: 10.1109/ICECAA58104.2023.10212184
A. Philip, Amal Jacob, Tejus K, A. S, Aakash Ashok, Divya Kb
Traffic volume counting survey helps to get an analysis of number and class of vehicles passing through a particular road segment over a period. The work proposes design and development of a standalone edge device to obtain count of vehicles on road based on category like car, bus, truck, two wheeler and auto rickshaws. The YOLO v8 model along with Deep Sort algorithm is deployed over Jetson nano proposed as an edge device. An interactive dashboard is designed to obtain the count and class of each vehicle by specifying a time. The deep learning models are trained using custom real-world datasets and further optimized to be deployed on Jetson nano. Thus, Jetson nano serves as an edge IoT device for vehicle counting. The analysis of the proposed model indicates promising results.
{"title":"Smart Standalone Edge IoT Device for Traffic Volume Counting in Smart Cities","authors":"A. Philip, Amal Jacob, Tejus K, A. S, Aakash Ashok, Divya Kb","doi":"10.1109/ICECAA58104.2023.10212184","DOIUrl":"https://doi.org/10.1109/ICECAA58104.2023.10212184","url":null,"abstract":"Traffic volume counting survey helps to get an analysis of number and class of vehicles passing through a particular road segment over a period. The work proposes design and development of a standalone edge device to obtain count of vehicles on road based on category like car, bus, truck, two wheeler and auto rickshaws. The YOLO v8 model along with Deep Sort algorithm is deployed over Jetson nano proposed as an edge device. An interactive dashboard is designed to obtain the count and class of each vehicle by specifying a time. The deep learning models are trained using custom real-world datasets and further optimized to be deployed on Jetson nano. Thus, Jetson nano serves as an edge IoT device for vehicle counting. The analysis of the proposed model indicates promising results.","PeriodicalId":114624,"journal":{"name":"2023 2nd International Conference on Edge Computing and Applications (ICECAA)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124192172","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-07-19DOI: 10.1109/ICECAA58104.2023.10212398
Dr. E.Elakiya, Dr. S. Deepa Nivethika, Dr. R. Kanagaraj, Dr.R.Sujithra, Tejus Paturu, Student
The popularity of online shopping has grown worldwide, making it an integral part of many people's lives. As customers are free to express their emotions online, online sales have become a significant source of revenue. This enables obtaining honest feedback for various products, helping to understand not only what is popular but also the overall consensus. To make sense of the large amounts of product feedback and gauge the public's response, it is important to understand the widely held sentiments. Machine learning models provide a solution to extract feedback from text. Random Forest classifier produces the highest accuracy of 88 percentage.
{"title":"Text Feedback Classification using Machine Learning Techniques","authors":"Dr. E.Elakiya, Dr. S. Deepa Nivethika, Dr. R. Kanagaraj, Dr.R.Sujithra, Tejus Paturu, Student","doi":"10.1109/ICECAA58104.2023.10212398","DOIUrl":"https://doi.org/10.1109/ICECAA58104.2023.10212398","url":null,"abstract":"The popularity of online shopping has grown worldwide, making it an integral part of many people's lives. As customers are free to express their emotions online, online sales have become a significant source of revenue. This enables obtaining honest feedback for various products, helping to understand not only what is popular but also the overall consensus. To make sense of the large amounts of product feedback and gauge the public's response, it is important to understand the widely held sentiments. Machine learning models provide a solution to extract feedback from text. Random Forest classifier produces the highest accuracy of 88 percentage.","PeriodicalId":114624,"journal":{"name":"2023 2nd International Conference on Edge Computing and Applications (ICECAA)","volume":"93 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127982828","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}
Public health and the environment are in danger from the poor handling of biomedical waste produced by medical institutions and biomedical research institutes. The necessity for a system to detect and categorize biomedical waste products is brought on by the fact that the current human sorting procedure is not only ineffective but also risky for waste handlers and garbage collectors. In the existing system, the identified problem highlights the inefficiency and risks associated with manual sorting. In order to improve safety, effectiveness, and environmental sustainability in biomedical waste management practises, this study suggests a deep learning-based system that makes use of convolutional neural networks (CNNs) to reliably recognize and categorize items that are part of biomedical waste. The proposed approach might eventually achieve a 90% accuracy rate, which could result in cost savings and a decrease in the dangers related with manual sorting.
{"title":"Review on Deep Learning Based Biomedical Waste Detection and Classification","authors":"Srushti Bobe, Priyanka Adhav, Omkar Bhalerao, Sandeep Chaware","doi":"10.1109/ICECAA58104.2023.10212343","DOIUrl":"https://doi.org/10.1109/ICECAA58104.2023.10212343","url":null,"abstract":"Public health and the environment are in danger from the poor handling of biomedical waste produced by medical institutions and biomedical research institutes. The necessity for a system to detect and categorize biomedical waste products is brought on by the fact that the current human sorting procedure is not only ineffective but also risky for waste handlers and garbage collectors. In the existing system, the identified problem highlights the inefficiency and risks associated with manual sorting. In order to improve safety, effectiveness, and environmental sustainability in biomedical waste management practises, this study suggests a deep learning-based system that makes use of convolutional neural networks (CNNs) to reliably recognize and categorize items that are part of biomedical waste. The proposed approach might eventually achieve a 90% accuracy rate, which could result in cost savings and a decrease in the dangers related with manual sorting.","PeriodicalId":114624,"journal":{"name":"2023 2nd International Conference on Edge Computing and Applications (ICECAA)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129326102","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-07-19DOI: 10.1109/ICECAA58104.2023.10212236
M. A. Gandhi, K. Priya, Piyush Charan, Ritu Sharma, G. Rao, D. Suganthi
Electric Vehicles (EVs) are now essential since electrifying transportation has shown to be a game-changer in raising the sustainable and eco-friendly platform in global industry. Integrating Electric Vehicle Charging System (EVCS) as a new entity into the power distribution system is one of the most important and challenging concerns. The development of an EVCS network infrastructure is a key step toward the broad adoption of EVs. In order to make informed judgments about transmission, distribution, energy allocation, and charging station placement, the control center or central aggregator must have an accurate forecast of occupancy, consumption, and energy or charging demand. Data analytics and other methods have made it possible to regularly get information from the EVCS for the purposes of archiving and processing all of the data collected. This proposed approach to presents a solution to the aforementioned problems with energy demand forecasting for EVCS networks. Three steps make up the proposed method: preprocessing, feature selection, and model performance evaluation. Preprocessing data via normalization, feature selection by K-Means, and ultimately model evaluation via K-means. The proposed model has superior results to the LSTM, GRU, and BIGRU - AM models.
{"title":"Smart Electric Vehicle (EVs) Charging Network Management Using Bidirectional GRU - AM Approaches","authors":"M. A. Gandhi, K. Priya, Piyush Charan, Ritu Sharma, G. Rao, D. Suganthi","doi":"10.1109/ICECAA58104.2023.10212236","DOIUrl":"https://doi.org/10.1109/ICECAA58104.2023.10212236","url":null,"abstract":"Electric Vehicles (EVs) are now essential since electrifying transportation has shown to be a game-changer in raising the sustainable and eco-friendly platform in global industry. Integrating Electric Vehicle Charging System (EVCS) as a new entity into the power distribution system is one of the most important and challenging concerns. The development of an EVCS network infrastructure is a key step toward the broad adoption of EVs. In order to make informed judgments about transmission, distribution, energy allocation, and charging station placement, the control center or central aggregator must have an accurate forecast of occupancy, consumption, and energy or charging demand. Data analytics and other methods have made it possible to regularly get information from the EVCS for the purposes of archiving and processing all of the data collected. This proposed approach to presents a solution to the aforementioned problems with energy demand forecasting for EVCS networks. Three steps make up the proposed method: preprocessing, feature selection, and model performance evaluation. Preprocessing data via normalization, feature selection by K-Means, and ultimately model evaluation via K-means. The proposed model has superior results to the LSTM, GRU, and BIGRU - AM models.","PeriodicalId":114624,"journal":{"name":"2023 2nd International Conference on Edge Computing and Applications (ICECAA)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128730095","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-07-19DOI: 10.1109/ICECAA58104.2023.10212205
Wei Cai
With the continuous improvement of the current level of information technology, the malicious software produced by attackers is also becoming more complex. It's difficult for computer users to protect themselves against malicious software attacks. Malicious software can steal the user's privacy, damage the user's computer system, and often cause serious consequences and huge economic losses to the user or the organization. Hence, this research study presents a novel deep learning-based malware detection scheme considering packers and encryption. The proposed model has 2 aspects of innovations: (1) Generation steps of the packer malware is analyzed. Packing involves adding code to the program to be protected, and original program is compressed and encrypted during the packing process. By understanding this step, the analysis of the software will be efficient. (2) The deep learning based detection model is designed. Through the experiment compared with the latest methods, the performance is proven to be efficient.
{"title":"A Novel Deep Learning-Based Malware Detection Scheme Considering Packers and Encryption","authors":"Wei Cai","doi":"10.1109/ICECAA58104.2023.10212205","DOIUrl":"https://doi.org/10.1109/ICECAA58104.2023.10212205","url":null,"abstract":"With the continuous improvement of the current level of information technology, the malicious software produced by attackers is also becoming more complex. It's difficult for computer users to protect themselves against malicious software attacks. Malicious software can steal the user's privacy, damage the user's computer system, and often cause serious consequences and huge economic losses to the user or the organization. Hence, this research study presents a novel deep learning-based malware detection scheme considering packers and encryption. The proposed model has 2 aspects of innovations: (1) Generation steps of the packer malware is analyzed. Packing involves adding code to the program to be protected, and original program is compressed and encrypted during the packing process. By understanding this step, the analysis of the software will be efficient. (2) The deep learning based detection model is designed. Through the experiment compared with the latest methods, the performance is proven to be efficient.","PeriodicalId":114624,"journal":{"name":"2023 2nd International Conference on Edge Computing and Applications (ICECAA)","volume":"124 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115986711","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-07-19DOI: 10.1109/ICECAA58104.2023.10212099
Vamsi sai Krishna Katta, HarshaVardhan Kapalavai, Sourav Mondal
In recent years, deep learning models have gained popularity for producing realistic Images. Recent advancements in computer vision, particularly in deep generative models like GANs, have shown promise in synthesizing realistic images automatically. GANs use a competitive process involving two networks: a generative network and a discriminative network. The discriminative network determines whether an image is real or fake whereas the generative network generates artificial images. The generative network gains the ability to create more convincing images as training goes on in order to deceive the discriminative network. This research study intends to develop novel, high-resolution images of human faces by combining DCGAN (Deep Convolutional Generative Adversarial Network) with ESRGAN (Enhanced Super-Resolution Generative Adversarial Networks). DCGAN is a type of GAN that uses convolutional neural networks in both the generator and discriminator. The generator network learns to produce images from random noise, while the discriminator network learns to differentiate between real and fake images. Further, this study has used the CelebFaces Attributes Dataset (CelebA) to train the proposed DCGAN model, and the Structural Similarity Index (SSIM) to quantitatively evaluate the quality of the generated images. Additionally, ESRGAN is employed to improve the quality of the generated images. The obtained results reveal that combining DCGAN with ESRGAN produces high-quality human faces with clear details and improved resolution.
{"title":"Generating New Human Faces and Improving the Quality of Images Using Generative Adversarial Networks(GAN)","authors":"Vamsi sai Krishna Katta, HarshaVardhan Kapalavai, Sourav Mondal","doi":"10.1109/ICECAA58104.2023.10212099","DOIUrl":"https://doi.org/10.1109/ICECAA58104.2023.10212099","url":null,"abstract":"In recent years, deep learning models have gained popularity for producing realistic Images. Recent advancements in computer vision, particularly in deep generative models like GANs, have shown promise in synthesizing realistic images automatically. GANs use a competitive process involving two networks: a generative network and a discriminative network. The discriminative network determines whether an image is real or fake whereas the generative network generates artificial images. The generative network gains the ability to create more convincing images as training goes on in order to deceive the discriminative network. This research study intends to develop novel, high-resolution images of human faces by combining DCGAN (Deep Convolutional Generative Adversarial Network) with ESRGAN (Enhanced Super-Resolution Generative Adversarial Networks). DCGAN is a type of GAN that uses convolutional neural networks in both the generator and discriminator. The generator network learns to produce images from random noise, while the discriminator network learns to differentiate between real and fake images. Further, this study has used the CelebFaces Attributes Dataset (CelebA) to train the proposed DCGAN model, and the Structural Similarity Index (SSIM) to quantitatively evaluate the quality of the generated images. Additionally, ESRGAN is employed to improve the quality of the generated images. The obtained results reveal that combining DCGAN with ESRGAN produces high-quality human faces with clear details and improved resolution.","PeriodicalId":114624,"journal":{"name":"2023 2nd International Conference on Edge Computing and Applications (ICECAA)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116423770","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-07-19DOI: 10.1109/ICECAA58104.2023.10212395
S. Kalarani, V. Sharmila, Suma. S, Jayakumari Ag, K. Sudha
Computational humanity is enormously voluminous and complex. One of the computing industry's fastest-growing approaches is cloud computing. It is a cutting-edge method for providing IT service over the World Wide Web. Through the Internet, this concept offers computing resources to users in a pool. Resource scheduling and allocation for various aggregate web services is a crucial and challenging problem in cloud computing. This research looks at resource allocation using scalable computing. Infrastructure as a Service (IaaS), or the service of renting out computer resources through the Internet, is offered to users by cloud computing. The client can select from a variety of computing resources depending on their needs. This approach uses the IaaS model to allocate resources for real-time tasks. Real-Time jobs must be finished ahead of schedules. Elasticity or scalable computing refers to the ability to scale up the resource in this situation in accordance with the demands. The resources are scalable and open to a vast user base. In order to finish real-time work ahead of schedules, the user can choose any number of Virtual Machines (VMs) based on speed and rate. The client leases the virtual machines. Hence the fee is set just for the duration of the rental. Additionally, a method is devised to assign VMs to programs with real-time tasks. The allocation is presented as a problem of restricted optimization.
{"title":"Scalable Computing in Resource Allocation","authors":"S. Kalarani, V. Sharmila, Suma. S, Jayakumari Ag, K. Sudha","doi":"10.1109/ICECAA58104.2023.10212395","DOIUrl":"https://doi.org/10.1109/ICECAA58104.2023.10212395","url":null,"abstract":"Computational humanity is enormously voluminous and complex. One of the computing industry's fastest-growing approaches is cloud computing. It is a cutting-edge method for providing IT service over the World Wide Web. Through the Internet, this concept offers computing resources to users in a pool. Resource scheduling and allocation for various aggregate web services is a crucial and challenging problem in cloud computing. This research looks at resource allocation using scalable computing. Infrastructure as a Service (IaaS), or the service of renting out computer resources through the Internet, is offered to users by cloud computing. The client can select from a variety of computing resources depending on their needs. This approach uses the IaaS model to allocate resources for real-time tasks. Real-Time jobs must be finished ahead of schedules. Elasticity or scalable computing refers to the ability to scale up the resource in this situation in accordance with the demands. The resources are scalable and open to a vast user base. In order to finish real-time work ahead of schedules, the user can choose any number of Virtual Machines (VMs) based on speed and rate. The client leases the virtual machines. Hence the fee is set just for the duration of the rental. Additionally, a method is devised to assign VMs to programs with real-time tasks. The allocation is presented as a problem of restricted optimization.","PeriodicalId":114624,"journal":{"name":"2023 2nd International Conference on Edge Computing and Applications (ICECAA)","volume":"112 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117258303","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：