Pub Date : 2022-12-01DOI: 10.1109/ICECA55336.2022.10009578
Kanala Srinivas Praanesh, Likhith Seedarala, Pavan Chandra Vishal Chaganti, Lekshmi, S. S.
The electric power consumption is historically high and perpetual. The overdependence on non-renewable energy sources is rapidly depleting naturally available non-renewable resources. The future is safeguarded if the shift to renewable energy sources for power consumption happens efficiently and rapidly. Renewable source in layman terms is energy source with very high reusability and one which replenishes over time. The future is in sustainable and economically feasible, renewable energy source. The shift to renewable energy source is uncomplicated to ponder upon but very hard to implement in large scale. High upfront payments, lack of advanced storage capabilities and terrestrial limitations are some of the reasons which stop mass renewable energy production. Many smart people and scientists came up with alternative electrical sources like solar power generation, wind turbine energy production which are renewable and have high reusability. One of the renewable power generations the paper suggest is piezoelectric power generation using piezoelectric transducers. A piezoelectric transducer transforms mechanical energy to electrical energy. Piezo transducer can use human locomotive energy to transform mechanical energy to electrical energy. Densely populated and developing country like India with high pedestrian population can utilize this mode of power generation to great benefits. Piezo transducers can be placed in areas with high population density, so that the power generation is more. The energy generated can either be stored in batteries or can be directly used to run the load. In this paper, a module consisting of piezoelectric transducers, full wave rectifier and SEPIC Converter has been proposed. The module has been simulated in MATLAB/Simulink and its results has been discussed. A hardware prototype has also been discussed.
{"title":"Power Generation Using Piezoelectric Transducers","authors":"Kanala Srinivas Praanesh, Likhith Seedarala, Pavan Chandra Vishal Chaganti, Lekshmi, S. S.","doi":"10.1109/ICECA55336.2022.10009578","DOIUrl":"https://doi.org/10.1109/ICECA55336.2022.10009578","url":null,"abstract":"The electric power consumption is historically high and perpetual. The overdependence on non-renewable energy sources is rapidly depleting naturally available non-renewable resources. The future is safeguarded if the shift to renewable energy sources for power consumption happens efficiently and rapidly. Renewable source in layman terms is energy source with very high reusability and one which replenishes over time. The future is in sustainable and economically feasible, renewable energy source. The shift to renewable energy source is uncomplicated to ponder upon but very hard to implement in large scale. High upfront payments, lack of advanced storage capabilities and terrestrial limitations are some of the reasons which stop mass renewable energy production. Many smart people and scientists came up with alternative electrical sources like solar power generation, wind turbine energy production which are renewable and have high reusability. One of the renewable power generations the paper suggest is piezoelectric power generation using piezoelectric transducers. A piezoelectric transducer transforms mechanical energy to electrical energy. Piezo transducer can use human locomotive energy to transform mechanical energy to electrical energy. Densely populated and developing country like India with high pedestrian population can utilize this mode of power generation to great benefits. Piezo transducers can be placed in areas with high population density, so that the power generation is more. The energy generated can either be stored in batteries or can be directly used to run the load. In this paper, a module consisting of piezoelectric transducers, full wave rectifier and SEPIC Converter has been proposed. The module has been simulated in MATLAB/Simulink and its results has been discussed. A hardware prototype has also been discussed.","PeriodicalId":356949,"journal":{"name":"2022 6th International Conference on Electronics, Communication and Aerospace Technology","volume":"51 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":"124339395","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/ICECA55336.2022.10009551
Anurag Choudhary, P. Verma, Piyush Rai
Small, medium, and big organizations get several advantages from cloud computing, but it also presents obstacles. Whether a firm is in the financial, technology, or engineering sector, a cloud component might be beneficial. Though there are numerous obstacles associated with cloud computing, experts think that the benefits outweigh the drawbacks. The issues will be addressed when more research in the field of cloud computing is conducted. Cloud services are provided by a number of significant companies, including Amazon Web Services, Microsoft Azure, and Google Cloud Platform, among others. Among them, AWS (Amazon Web Services) is one of the fine cloud service providers that comprises several features, including the AWS EC2 (Elastic Compute Cloud) which is one of the widely used by many organizations. Amazon's Elastic Compute Cloud Web service delivers highly adjustable processing capacity throughout the cloud, allowing developers to construct applications with incredible scalability. Using EC2 (Elastic Compute Cloud) by using the proposed deployment method can be more effort saver for any IT development and deployment team for any organization. There should be an easy deployment method that auto-configures EC2 Instance. The aim of this research paper is to showcase the current deployment and service models provided by Amazon Web Services EC2 and present the proposed solution in order to the existing scenario. Furthermore, its advantages are also present so that it becomes easier to select the most appropriate one for deployment and research development.
小型、中型和大型组织从云计算中获得了一些优势，但它也存在障碍。无论一家公司是在金融、技术还是工程领域，云组件都可能是有益的。尽管与云计算相关的障碍有很多，但专家认为其利大于弊。这些问题将在云计算领域进行更多的研究后得到解决。云服务由许多重要的公司提供，包括亚马逊网络服务、微软Azure和谷歌云平台等。其中，AWS(亚马逊网络服务)是优秀的云服务提供商之一，它包含几个功能，包括AWS EC2(弹性计算云)，它是许多组织广泛使用的云服务之一。Amazon的弹性计算云Web服务在整个云中提供高度可调的处理能力，允许开发人员构建具有令人难以置信的可伸缩性的应用程序。通过使用建议的部署方法使用EC2(弹性计算云)可以为任何组织的任何IT开发和部署团队节省更多的工作。应该有一个简单的部署方法来自动配置EC2实例。这篇研究论文的目的是展示Amazon Web Services EC2提供的当前部署和服务模型，并针对现有场景提出建议的解决方案。此外，它的优点也存在，因此更容易选择最合适的部署和研究开发。
{"title":"The Proposed Pre-Configured Deployment Model for Amazon EC2 Cloud Services","authors":"Anurag Choudhary, P. Verma, Piyush Rai","doi":"10.1109/ICECA55336.2022.10009551","DOIUrl":"https://doi.org/10.1109/ICECA55336.2022.10009551","url":null,"abstract":"Small, medium, and big organizations get several advantages from cloud computing, but it also presents obstacles. Whether a firm is in the financial, technology, or engineering sector, a cloud component might be beneficial. Though there are numerous obstacles associated with cloud computing, experts think that the benefits outweigh the drawbacks. The issues will be addressed when more research in the field of cloud computing is conducted. Cloud services are provided by a number of significant companies, including Amazon Web Services, Microsoft Azure, and Google Cloud Platform, among others. Among them, AWS (Amazon Web Services) is one of the fine cloud service providers that comprises several features, including the AWS EC2 (Elastic Compute Cloud) which is one of the widely used by many organizations. Amazon's Elastic Compute Cloud Web service delivers highly adjustable processing capacity throughout the cloud, allowing developers to construct applications with incredible scalability. Using EC2 (Elastic Compute Cloud) by using the proposed deployment method can be more effort saver for any IT development and deployment team for any organization. There should be an easy deployment method that auto-configures EC2 Instance. The aim of this research paper is to showcase the current deployment and service models provided by Amazon Web Services EC2 and present the proposed solution in order to the existing scenario. Furthermore, its advantages are also present so that it becomes easier to select the most appropriate one for deployment and research development.","PeriodicalId":356949,"journal":{"name":"2022 6th International Conference on Electronics, Communication and Aerospace Technology","volume":"178 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":"114339030","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/ICECA55336.2022.10009478
Anly Antony M, R. Satheeshkumar
The quality estimation of fruits and vegetables plays a vital role in the field of agriculture. This paper reviews the latest improvements in estimating the quality of fruits and vegetables as well as grading them using machine learning techniques. As fruits and vegetables have high nutritional value, their sales are on high demand. The prime importance is given to the supply of toxin-free, premium quality products to the end-users. Quality of a fruits and vegetables highly affected by detecting the defects on them. Keeping the spoiled foods along with good food may contaminate the whole collection. Features of interest are needed for proper identification of food product. After extracting and refining features of interest, the images can be trained to error free categorization. This paper presents an elaborated description of various feature extraction and machine learning techniques to identify and grade different kinds of fruits and vegetables. This research study has reviewed many articles to sort out the problems in estimating the quality and classifying them according to the need. The results of this review show that incorporating image processing and computer vision techniques with machine learning techniques surpasses the traditional methods.
{"title":"A Comprehensive Review on Quality Prediction of Fruits and Vegetables using Feature Extraction and Machine Learning Techniques","authors":"Anly Antony M, R. Satheeshkumar","doi":"10.1109/ICECA55336.2022.10009478","DOIUrl":"https://doi.org/10.1109/ICECA55336.2022.10009478","url":null,"abstract":"The quality estimation of fruits and vegetables plays a vital role in the field of agriculture. This paper reviews the latest improvements in estimating the quality of fruits and vegetables as well as grading them using machine learning techniques. As fruits and vegetables have high nutritional value, their sales are on high demand. The prime importance is given to the supply of toxin-free, premium quality products to the end-users. Quality of a fruits and vegetables highly affected by detecting the defects on them. Keeping the spoiled foods along with good food may contaminate the whole collection. Features of interest are needed for proper identification of food product. After extracting and refining features of interest, the images can be trained to error free categorization. This paper presents an elaborated description of various feature extraction and machine learning techniques to identify and grade different kinds of fruits and vegetables. This research study has reviewed many articles to sort out the problems in estimating the quality and classifying them according to the need. The results of this review show that incorporating image processing and computer vision techniques with machine learning techniques surpasses the traditional methods.","PeriodicalId":356949,"journal":{"name":"2022 6th International Conference on Electronics, Communication and Aerospace Technology","volume":"8 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":"114522598","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/ICECA55336.2022.10009170
Akanksha Budholiya, A. Manwar
Both the world and technology are changing. Autonomous vehicles are already common on several nations' roadways thanks to advancements in electronics. We're getting closer to a time when everyone will drive safer, greener vehicles. A dedicated vehicular ad hoc network named VANET was developed for this reason. Routing protocols are among the most crucial components for network dependability. The most well-known VANET routing protocols are examined in this work. These three are DS R (Dynamic Source Routing), DSDV (Destination Sequence Distance Vector) and AODV (Ad hoc on Demand Distance Vector). In vehicular ad hoc networks, as well as in autonomous and connected vehicles, there are numerous cutting-edge techniques for intrusion detection. An intrusion detection system's primary task is to find and report attacks (IDS). IDS is improved with deep learning to make it smarter and more precise. On the other side, it suggests additional difficulties. This research compares the effectiveness and efficiency of the proposed IDS -based deep learning systems.
世界和技术都在变化。由于电子技术的进步，自动驾驶汽车在几个国家的道路上已经很普遍了。我们离每个人驾驶更安全、更环保的汽车的时代越来越近了。为此，开发了专用车辆自组织网络VANET。路由协议是网络可靠性最关键的组件之一。在这项工作中，研究了最著名的VANET路由协议。这三个是DS R(动态源路由)，DSDV(目的地序列距离向量)和AODV (Ad hoc on Demand距离向量)。在车辆自组织网络以及自动驾驶和联网车辆中，存在许多用于入侵检测的尖端技术。入侵检测系统的主要任务是发现和报告攻击(IDS)。IDS通过深度学习进行改进，使其更智能、更精确。另一方面，这意味着更多的困难。本研究比较了所提出的基于IDS的深度学习系统的有效性和效率。
{"title":"Machine Learning based Analysis of VANET Communication Protocols in Wireless Sensor Networks","authors":"Akanksha Budholiya, A. Manwar","doi":"10.1109/ICECA55336.2022.10009170","DOIUrl":"https://doi.org/10.1109/ICECA55336.2022.10009170","url":null,"abstract":"Both the world and technology are changing. Autonomous vehicles are already common on several nations' roadways thanks to advancements in electronics. We're getting closer to a time when everyone will drive safer, greener vehicles. A dedicated vehicular ad hoc network named VANET was developed for this reason. Routing protocols are among the most crucial components for network dependability. The most well-known VANET routing protocols are examined in this work. These three are DS R (Dynamic Source Routing), DSDV (Destination Sequence Distance Vector) and AODV (Ad hoc on Demand Distance Vector). In vehicular ad hoc networks, as well as in autonomous and connected vehicles, there are numerous cutting-edge techniques for intrusion detection. An intrusion detection system's primary task is to find and report attacks (IDS). IDS is improved with deep learning to make it smarter and more precise. On the other side, it suggests additional difficulties. This research compares the effectiveness and efficiency of the proposed IDS -based deep learning systems.","PeriodicalId":356949,"journal":{"name":"2022 6th International Conference on Electronics, Communication and Aerospace Technology","volume":"73 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":"114714705","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/ICECA55336.2022.10009165
Janmejay Pant, R. Sharma, Amit Juyal, Devendra Singh, Himanshu Pant, Puspha Pant
In the modern world, weather forecasting is an essential application. The forecasts can help us reduce weather- related losses. The need for a massive data and highly computationally intensive parameterization procedure can be eliminated or reduced by the use of machine learning and deep learning algorithms for forecasting. This research work intends to forecast the temperature of three cities (Dehradun, Mukteshwar and Pantnagar) of Uttarakhand using emerging time series model AR/MA (Auto Regressive Integrated Moving Average). The results of this study prove that using the auto ARIMA produces very less MAPE (Mean Absolute Percentage Error) score for all testing data of all three regions. Our used model produces 8.45%,9.65% and 5.64% mean absolute percentage error in temperature data for Dehradun, Mukteshwar and Pantnagar respectively. Hence this paper explains briefly how different parameters can be used to formulate the AR/MA model to predict temperature. MAPE (Mean Absolute Percentage Error) indicates that auto AR/MA model yields excellent results.
{"title":"A Machine-Learning Approach to Time Series Forecasting of Temperature","authors":"Janmejay Pant, R. Sharma, Amit Juyal, Devendra Singh, Himanshu Pant, Puspha Pant","doi":"10.1109/ICECA55336.2022.10009165","DOIUrl":"https://doi.org/10.1109/ICECA55336.2022.10009165","url":null,"abstract":"In the modern world, weather forecasting is an essential application. The forecasts can help us reduce weather- related losses. The need for a massive data and highly computationally intensive parameterization procedure can be eliminated or reduced by the use of machine learning and deep learning algorithms for forecasting. This research work intends to forecast the temperature of three cities (Dehradun, Mukteshwar and Pantnagar) of Uttarakhand using emerging time series model AR/MA (Auto Regressive Integrated Moving Average). The results of this study prove that using the auto ARIMA produces very less MAPE (Mean Absolute Percentage Error) score for all testing data of all three regions. Our used model produces 8.45%,9.65% and 5.64% mean absolute percentage error in temperature data for Dehradun, Mukteshwar and Pantnagar respectively. Hence this paper explains briefly how different parameters can be used to formulate the AR/MA model to predict temperature. MAPE (Mean Absolute Percentage Error) indicates that auto AR/MA model yields excellent results.","PeriodicalId":356949,"journal":{"name":"2022 6th International Conference on Electronics, Communication and Aerospace Technology","volume":"3 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":"114900104","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/ICECA55336.2022.10009335
B. Selvin Sanjay, S. Singh, S. Bansod, Prashant Pal
The main objective of this research is to detect the fault in the power system and rectify it before it affects the entire system. Artificial Intelligence circumstancing Artificial Neural Network (ANN) methods and its topologies are used to detect the fault. In this method, the system specifically analyses the data obtained from the transmission and consumer ends of the power system. The intelligence -based detection is undertaken by the power system which has a capacity of rapid fault detection, and this prediction can be obtained in ANN algorithm. ANN is the core part of this research which stimulates the detection of fault before it's occurrence. A simulated medium length transmission line has been tested by the detector and the results demonstrate the capability of the detector which is visualized in the MATLAB.
{"title":"Artificial Intelligence based Power Fault Detection and Power Restoration","authors":"B. Selvin Sanjay, S. Singh, S. Bansod, Prashant Pal","doi":"10.1109/ICECA55336.2022.10009335","DOIUrl":"https://doi.org/10.1109/ICECA55336.2022.10009335","url":null,"abstract":"The main objective of this research is to detect the fault in the power system and rectify it before it affects the entire system. Artificial Intelligence circumstancing Artificial Neural Network (ANN) methods and its topologies are used to detect the fault. In this method, the system specifically analyses the data obtained from the transmission and consumer ends of the power system. The intelligence -based detection is undertaken by the power system which has a capacity of rapid fault detection, and this prediction can be obtained in ANN algorithm. ANN is the core part of this research which stimulates the detection of fault before it's occurrence. A simulated medium length transmission line has been tested by the detector and the results demonstrate the capability of the detector which is visualized in the MATLAB.","PeriodicalId":356949,"journal":{"name":"2022 6th International Conference on Electronics, Communication and Aerospace Technology","volume":"63 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":"116931486","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/ICECA55336.2022.10009469
K. Mouthami, S. Anandamurugan, S. Ayyasamy
In the last decade, large numbers of comment texts have been generated on social media and websites. In the era of sentiment analysis, mining the role of emotional tendency in comments through deep learning technology is helpful for the timely classification of sentiment text as positive, negative, and neutral. Sentiment analysis is a task that predicts people's opinions on product reviews based on text data, and it's both a valuable and challenging task. This research study has utilized a novel deep learning based predictive framework, which is applied in analyzing the product reviews along with user opinion information. Firstly, the training set generates character vectors as input layers by using Bidirectional Encoder Representation of Transformers (BERT) and FLAIR embedding models, which are used to convert the product review into low-dimensional representation; and then uses this vector as input to a novel hybrid Bidirectional Long-Short-term memory model (Bi-LS TM) and Bidirectional Gated recurrent unit model (Bi-GRU), which are combined into a single architecture to predict the feature. Finally, the processed context information is classified using the softmax classifier. The resultant review shows the significant accuracy of our model.
{"title":"BERT-BiLSTM-BiGRU-CRF: Ensemble Multi Models Learning for Product Review Sentiment Analysis","authors":"K. Mouthami, S. Anandamurugan, S. Ayyasamy","doi":"10.1109/ICECA55336.2022.10009469","DOIUrl":"https://doi.org/10.1109/ICECA55336.2022.10009469","url":null,"abstract":"In the last decade, large numbers of comment texts have been generated on social media and websites. In the era of sentiment analysis, mining the role of emotional tendency in comments through deep learning technology is helpful for the timely classification of sentiment text as positive, negative, and neutral. Sentiment analysis is a task that predicts people's opinions on product reviews based on text data, and it's both a valuable and challenging task. This research study has utilized a novel deep learning based predictive framework, which is applied in analyzing the product reviews along with user opinion information. Firstly, the training set generates character vectors as input layers by using Bidirectional Encoder Representation of Transformers (BERT) and FLAIR embedding models, which are used to convert the product review into low-dimensional representation; and then uses this vector as input to a novel hybrid Bidirectional Long-Short-term memory model (Bi-LS TM) and Bidirectional Gated recurrent unit model (Bi-GRU), which are combined into a single architecture to predict the feature. Finally, the processed context information is classified using the softmax classifier. The resultant review shows the significant accuracy of our model.","PeriodicalId":356949,"journal":{"name":"2022 6th International Conference on Electronics, Communication and Aerospace Technology","volume":"67 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":"116979290","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/ICECA55336.2022.10009145
Kayal Padmanandam, Alekhya Yadav, Aishwarya, Harshitha N
Mathematical symbol recognition is a topic of attention that convert physical documents into digital format. Despite the existing techniques to recognize handwritten characters and symbols, recognition accuracy is unstable. The main objective of this work is to build an intelligent system to recognize handwritten characters or symbols written in different styles with improved and stable accuracy. The proposed system can read handwritten mathematical characters or symbols as input and recognize them with corresponding characters or symbol names. The proposed implementation uses various machine learning and deep learning algorithms like Logistic Regression, Convolutional Neural networks, and Dense net. The dataset used for this research is 46 MB, which contains images of numerical values from 0 to 9, mathematical symbols, and alphabets that are available in the Kaggle open-source platform. Each data category has around 500 plus handwritten images. The implementation uses various machine learning and deep learning algorithms like Logistic Regression, Convolutional Neural networks, and Dense net to address the symbol recognition challenges. The comparative study is implemented with these algorithms and the Dense net has presented exceptional results during the training and testing phase with an accuracy of 99% and 94.2% respectively. This improved accuracy is due to the utilization of Densenet over other CNN architectures, as the DenseNet concatenates the output of the predecessor layer with the successor layer and it weakens the vanishing gradient problem. Also, the Dynamic feature propagation helps in the regulated flow of information in the dense network architecture.
{"title":"Handwritten Mathematical Symbol Recognition using Neural Network Architectures","authors":"Kayal Padmanandam, Alekhya Yadav, Aishwarya, Harshitha N","doi":"10.1109/ICECA55336.2022.10009145","DOIUrl":"https://doi.org/10.1109/ICECA55336.2022.10009145","url":null,"abstract":"Mathematical symbol recognition is a topic of attention that convert physical documents into digital format. Despite the existing techniques to recognize handwritten characters and symbols, recognition accuracy is unstable. The main objective of this work is to build an intelligent system to recognize handwritten characters or symbols written in different styles with improved and stable accuracy. The proposed system can read handwritten mathematical characters or symbols as input and recognize them with corresponding characters or symbol names. The proposed implementation uses various machine learning and deep learning algorithms like Logistic Regression, Convolutional Neural networks, and Dense net. The dataset used for this research is 46 MB, which contains images of numerical values from 0 to 9, mathematical symbols, and alphabets that are available in the Kaggle open-source platform. Each data category has around 500 plus handwritten images. The implementation uses various machine learning and deep learning algorithms like Logistic Regression, Convolutional Neural networks, and Dense net to address the symbol recognition challenges. The comparative study is implemented with these algorithms and the Dense net has presented exceptional results during the training and testing phase with an accuracy of 99% and 94.2% respectively. This improved accuracy is due to the utilization of Densenet over other CNN architectures, as the DenseNet concatenates the output of the predecessor layer with the successor layer and it weakens the vanishing gradient problem. Also, the Dynamic feature propagation helps in the regulated flow of information in the dense network architecture.","PeriodicalId":356949,"journal":{"name":"2022 6th International Conference on Electronics, Communication and Aerospace Technology","volume":"95 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":"116316502","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/ICECA55336.2022.10009126
Vuyyuru Sai Venkata Murali Krishna, Tammana Sai Rama Vamsi, S. Kavitha
The advancement of cyber technology has a tremendous boost over the years which results in a threat to security as one outcome. So, the domain of forensics plays a crucial role in detecting and preventing various cyber threats. As a motto of minimizing hardware storage and computation, industries are moving towards the cloud platform which provides maximum services such as storage, computation, etc. at low cost and also based on the requirement. Therefore, this ideology has attracted several organizations and individuals in moving toward cloud platforms. Hence as an instinct, the threat of the CIA triad has also arrived on the cloud. In every software application, the database plays a major role, as a result, it has become a resource for attackers to gain information which resulted in various attacks on the database. Therefore, database monitoring has become an important role. To monitor or investigate the attack the logs of the database are used. Hence storing the logs is also a challenge since the logs shouldn't lose their integrity. This research work proposes a novel architecture with maximum throughput and a strong storing mechanism to automatically store the logs following a user-defined timeline analysis by using Athena, Lambda, and EventBridge along with strong security features such as encryption, versioning, etc. that guide the monitoring process and forensic analysis.
{"title":"Automation of Forensic Analysis for AWS Aurora using EventBridge and Athena","authors":"Vuyyuru Sai Venkata Murali Krishna, Tammana Sai Rama Vamsi, S. Kavitha","doi":"10.1109/ICECA55336.2022.10009126","DOIUrl":"https://doi.org/10.1109/ICECA55336.2022.10009126","url":null,"abstract":"The advancement of cyber technology has a tremendous boost over the years which results in a threat to security as one outcome. So, the domain of forensics plays a crucial role in detecting and preventing various cyber threats. As a motto of minimizing hardware storage and computation, industries are moving towards the cloud platform which provides maximum services such as storage, computation, etc. at low cost and also based on the requirement. Therefore, this ideology has attracted several organizations and individuals in moving toward cloud platforms. Hence as an instinct, the threat of the CIA triad has also arrived on the cloud. In every software application, the database plays a major role, as a result, it has become a resource for attackers to gain information which resulted in various attacks on the database. Therefore, database monitoring has become an important role. To monitor or investigate the attack the logs of the database are used. Hence storing the logs is also a challenge since the logs shouldn't lose their integrity. This research work proposes a novel architecture with maximum throughput and a strong storing mechanism to automatically store the logs following a user-defined timeline analysis by using Athena, Lambda, and EventBridge along with strong security features such as encryption, versioning, etc. that guide the monitoring process and forensic analysis.","PeriodicalId":356949,"journal":{"name":"2022 6th International Conference on Electronics, Communication and Aerospace Technology","volume":"1 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":"116387945","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/ICECA55336.2022.10009383
M. Meghana, Muppuru Bhargavaram, Vamsi Sannareddy
Recently, COVID-19 is spreading rapidly and fast detection of COVID-19 can save millions of lives. Further, the COVID-19 can be detected easily from chest x ray (CXR) images using artificial intelligence methods. However, the performance of these application and methods are reduced due to noises presented in the CXR images, which degrading the performance of overall systems. Therefore, this article is focused on implementation of an innovative method for quickly processing CXR images of low quality, which enhances the contrast using fuzzy logic. This method makes use of tuned fuzzy intensification operators and is intended to speed up the processing time. Therefore, this work is focused on implementation of CXR image-based disease classification network (CIDC-Net) for identification of COVID-19 and pneumonia related 21 diseases. The CIDC-Net utilizes the deep learning convolutional neural network (CNN) model for training and testing. Finally, the simulations revealed that the proposed CIDC-Net resulted in superior performance as compared to existing models.
{"title":"CIDC-Net: Chest-X Ray Image based Disease Classification Network using Deep Learning","authors":"M. Meghana, Muppuru Bhargavaram, Vamsi Sannareddy","doi":"10.1109/ICECA55336.2022.10009383","DOIUrl":"https://doi.org/10.1109/ICECA55336.2022.10009383","url":null,"abstract":"Recently, COVID-19 is spreading rapidly and fast detection of COVID-19 can save millions of lives. Further, the COVID-19 can be detected easily from chest x ray (CXR) images using artificial intelligence methods. However, the performance of these application and methods are reduced due to noises presented in the CXR images, which degrading the performance of overall systems. Therefore, this article is focused on implementation of an innovative method for quickly processing CXR images of low quality, which enhances the contrast using fuzzy logic. This method makes use of tuned fuzzy intensification operators and is intended to speed up the processing time. Therefore, this work is focused on implementation of CXR image-based disease classification network (CIDC-Net) for identification of COVID-19 and pneumonia related 21 diseases. The CIDC-Net utilizes the deep learning convolutional neural network (CNN) model for training and testing. Finally, the simulations revealed that the proposed CIDC-Net resulted in superior performance as compared to existing models.","PeriodicalId":356949,"journal":{"name":"2022 6th International Conference on Electronics, Communication and Aerospace Technology","volume":"82 2 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":"129376996","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：