Pub Date : 2023-07-19DOI: 10.1109/ICECAA58104.2023.10212404
Milanjit Kaur, K. Joshi, Bhawna Goyal, Ayush Dogra
To perform the sentiment analysis as a basis for defining and extracting subjective information from sources or easily relating to the identification phase of the polarity of the text, the concept of Natural Processing is used. Participatory approach is required to perform this analysis. It was also called opinion mining as it extracts a user's view or perspective. There are many attributes which pose a problem with knowledge. It is an arbitrary for choosing assets giving a wider range of values. In the current paper, various algorithms of classification are used and it is concluded that the best algorithm is random forest. The issue is that decision trees, especially if the tree is particularly deep, are vulnerable to being over fit. To minimize the bias and error of variance, classification along with random forest classification is used. Through practicing on different data sets, random forests minimize variance. In the proposed study, boosted methodology along with Random forest, instead of using only random forest is implemented due to which optimization of the Ant colony search alongside with the proposed classification to hit the classification for sentiment analysis of various reviews of films for research precision.
{"title":"An Approach to Perform Sentiment Analysis using Data Mining Algorithms","authors":"Milanjit Kaur, K. Joshi, Bhawna Goyal, Ayush Dogra","doi":"10.1109/ICECAA58104.2023.10212404","DOIUrl":"https://doi.org/10.1109/ICECAA58104.2023.10212404","url":null,"abstract":"To perform the sentiment analysis as a basis for defining and extracting subjective information from sources or easily relating to the identification phase of the polarity of the text, the concept of Natural Processing is used. Participatory approach is required to perform this analysis. It was also called opinion mining as it extracts a user's view or perspective. There are many attributes which pose a problem with knowledge. It is an arbitrary for choosing assets giving a wider range of values. In the current paper, various algorithms of classification are used and it is concluded that the best algorithm is random forest. The issue is that decision trees, especially if the tree is particularly deep, are vulnerable to being over fit. To minimize the bias and error of variance, classification along with random forest classification is used. Through practicing on different data sets, random forests minimize variance. In the proposed study, boosted methodology along with Random forest, instead of using only random forest is implemented due to which optimization of the Ant colony search alongside with the proposed classification to hit the classification for sentiment analysis of various reviews of films for research precision.","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":"131969506","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/ICECAA58104.2023.10212176
S. Velusamy, Pallikonda Rajasekaran Murugan, Kottaimalai Ramaraj, Arunprasath Thiyagarajan, V. Govindaraj, Vidyavathi Kamalakkannan
A non-stationary signal called an electrocardiogram (ECG) is used to assess the rhythm and tempo of a person's heartbeat. Feature extraction is the primary phase in ECG classification, since it is responsible for identifying a group of pertinent characteristics that can achieve the greatest accuracy. After everything is said and done, this study provides a comprehensive overview of the methods currently used for detecting ECG waveforms. This study compares and contrast the current methods for ECG classification and ECG waveform detection and highlight their respective strength and weakness. The major goal of this study is to offer an automated ECG wave identification and classification method. From the outcomes, it can be decided as the accuracy is need to be enhanced/improved. The X-wave of ECG could be recognized using Min Max threshold analysis method. Then it is subjected to classification by means of Convolutional Neural Network (CNN). It is anticipated that this evaluation will prove to be an efficient tool for researchers, scientific engineers, and others engaged in this field to identify pertinent sources.
{"title":"Exploring the Feasibilities of Applying Min-Max Threshold Analysis with Machine Learning Techniques for Categorization of X-Wave in ECG Signal","authors":"S. Velusamy, Pallikonda Rajasekaran Murugan, Kottaimalai Ramaraj, Arunprasath Thiyagarajan, V. Govindaraj, Vidyavathi Kamalakkannan","doi":"10.1109/ICECAA58104.2023.10212176","DOIUrl":"https://doi.org/10.1109/ICECAA58104.2023.10212176","url":null,"abstract":"A non-stationary signal called an electrocardiogram (ECG) is used to assess the rhythm and tempo of a person's heartbeat. Feature extraction is the primary phase in ECG classification, since it is responsible for identifying a group of pertinent characteristics that can achieve the greatest accuracy. After everything is said and done, this study provides a comprehensive overview of the methods currently used for detecting ECG waveforms. This study compares and contrast the current methods for ECG classification and ECG waveform detection and highlight their respective strength and weakness. The major goal of this study is to offer an automated ECG wave identification and classification method. From the outcomes, it can be decided as the accuracy is need to be enhanced/improved. The X-wave of ECG could be recognized using Min Max threshold analysis method. Then it is subjected to classification by means of Convolutional Neural Network (CNN). It is anticipated that this evaluation will prove to be an efficient tool for researchers, scientific engineers, and others engaged in this field to identify pertinent sources.","PeriodicalId":114624,"journal":{"name":"2023 2nd International Conference on Edge Computing and Applications (ICECAA)","volume":"56 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":"130042538","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/ICECAA58104.2023.10212284
Rahul S Jagzap, Kunal N Adhav, Mahesh R Raktate, Shivnath S Gadekar, P. Thokal, D. Pardeshi
The quality of electricity is a critical factor in manufacturing and other applications, as it directly impacts the efficiency and reliability of electrical systems. Maintaining a certain power quality standard is essential for various applications to ensure smooth operation and minimize technical issues, which in turn reduces energy costs. One important parameter that determines power quality is the mains power factor, which indicates the efficiency of the power system. Reduced efficiency results when the power factor drops due to an increase in the demand for reactive power. In order to remedy this, when the power factor drops below the desired value, ideally 0.92, capacitance of the needed value needs to be introduced to the system. Capacitors are a helpful addition in lowering losses and enhancing power factor. In order to enhance power quality, this article suggests a computationally managed infrastructure for Automated Power Factor Correction (APFC). The paper describes the design and simulation of an APFC system utilising an Arduino UNO microcontroller. The Arduino's microprocessor controls capacitor banks switching to adjust for reactive power while reducing the power factor almost to unity, which enhances the quality of the electricity. A power factor transducer is used by the system to determine the power factor. Additionally, the modelling outputs show up in the paper. Demonstrating the effectiveness of the proposed system in improving power quality by maintaining a high power factor.
{"title":"Automatic Power Factor Improvement Using Microcontroller","authors":"Rahul S Jagzap, Kunal N Adhav, Mahesh R Raktate, Shivnath S Gadekar, P. Thokal, D. Pardeshi","doi":"10.1109/ICECAA58104.2023.10212284","DOIUrl":"https://doi.org/10.1109/ICECAA58104.2023.10212284","url":null,"abstract":"The quality of electricity is a critical factor in manufacturing and other applications, as it directly impacts the efficiency and reliability of electrical systems. Maintaining a certain power quality standard is essential for various applications to ensure smooth operation and minimize technical issues, which in turn reduces energy costs. One important parameter that determines power quality is the mains power factor, which indicates the efficiency of the power system. Reduced efficiency results when the power factor drops due to an increase in the demand for reactive power. In order to remedy this, when the power factor drops below the desired value, ideally 0.92, capacitance of the needed value needs to be introduced to the system. Capacitors are a helpful addition in lowering losses and enhancing power factor. In order to enhance power quality, this article suggests a computationally managed infrastructure for Automated Power Factor Correction (APFC). The paper describes the design and simulation of an APFC system utilising an Arduino UNO microcontroller. The Arduino's microprocessor controls capacitor banks switching to adjust for reactive power while reducing the power factor almost to unity, which enhances the quality of the electricity. A power factor transducer is used by the system to determine the power factor. Additionally, the modelling outputs show up in the paper. Demonstrating the effectiveness of the proposed system in improving power quality by maintaining a high power factor.","PeriodicalId":114624,"journal":{"name":"2023 2nd International Conference on Edge Computing and Applications (ICECAA)","volume":"11 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":"130179102","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/ICECAA58104.2023.10212377
Jamunadevi C, Subith R, D. S, Pandikumar S
This research study intends to reduce the features and predict whether the patients are satisfied with the service provided by the hospitals. The proposed system classifies top five features and give more accuracy using the machine learning algorithm. The existing system has a limitation that it requires an optimization solver and increases the computing work if the number of variables become large. The proposed system considers 17 attributes in the dataset and five features are selected to evaluate the system to increase the efficiency. Since the correlation of several dataset features is nearly equal, they are eliminated. Chi-square test is one of the most efficient feature selection method to reduce the unwanted data or unwanted features from the dataset before training and testing the model for attaining better accuracy and reducing the complexity of the model. The taken dataset is imbalanced, it affects the accuracy, so SMOTE technique is used to balance the dataset. The acquired dataset is cleared of any potential irregular data and pre-processed with several methods followed by feature selection and model building. The SVM, Random Forest, XGBOOST and Ensembling of Random Forest and XGBoost are the classifiers that were employed. When using a machine learning approach for both training and testing, Random Forest ultimately has higher accuracy compared to other algorithms. This method has the amazing capacity to increase categorization and forecasting precision.
{"title":"Analysis of Patient Satisfaction through Interpretable Machine Learning Algorithms","authors":"Jamunadevi C, Subith R, D. S, Pandikumar S","doi":"10.1109/ICECAA58104.2023.10212377","DOIUrl":"https://doi.org/10.1109/ICECAA58104.2023.10212377","url":null,"abstract":"This research study intends to reduce the features and predict whether the patients are satisfied with the service provided by the hospitals. The proposed system classifies top five features and give more accuracy using the machine learning algorithm. The existing system has a limitation that it requires an optimization solver and increases the computing work if the number of variables become large. The proposed system considers 17 attributes in the dataset and five features are selected to evaluate the system to increase the efficiency. Since the correlation of several dataset features is nearly equal, they are eliminated. Chi-square test is one of the most efficient feature selection method to reduce the unwanted data or unwanted features from the dataset before training and testing the model for attaining better accuracy and reducing the complexity of the model. The taken dataset is imbalanced, it affects the accuracy, so SMOTE technique is used to balance the dataset. The acquired dataset is cleared of any potential irregular data and pre-processed with several methods followed by feature selection and model building. The SVM, Random Forest, XGBOOST and Ensembling of Random Forest and XGBoost are the classifiers that were employed. When using a machine learning approach for both training and testing, Random Forest ultimately has higher accuracy compared to other algorithms. This method has the amazing capacity to increase categorization and forecasting precision.","PeriodicalId":114624,"journal":{"name":"2023 2nd International Conference on Edge Computing and Applications (ICECAA)","volume":"7 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":"130959735","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/ICECAA58104.2023.10212222
V. M. Reddy, T. Vaishnavi, K. Kumar
Speech-to-Text (STT) and Text-to-Speech (TTS) recognition technologies have witnessed significant advancements in recent years, transforming various industries and applications. STT allows for the conversion of spoken language into written text, while TTS enables the generation of natural-sounding speech from written text. In this research paper, we provide a comprehensive review of the latest advancements in STT and TTS recognition technologies, including their underlying methodologies, applications, challenges, and future directions. We begin by discussing the key components of STT and TTS systems, including Automatic Speech Recognition (ASR) and speech synthesis techniques. This research study highlights the evolution of these technologies, from traditional approaches to data-driven deep learning methods, such as Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and transformer based models. Further, this research study analyses various applications of STT and TTS recognition technologies in different domains, including healthcare, customer service, accessibility, and language translation and discusses about the benefits of STT and TTS in improving communication, accessibility, and user experience, and address the challenges and limitations of these technologies, such as accuracy in noisy environments, handling diverse accents and languages, context awareness, and ethical considerations. Moreover, this study highlights the ongoing research efforts to address these challenges and improve the performance and robustness of STT and TTS systems. Finally, we outline the future directions and potential research opportunities in STT and TTS, including advancements in deep learning techniques, multimodal integration, domain adaptation, and personalized speech synthesis and also emphasizes the importance of interdisciplinary research collaborations, data collection, and benchmarking efforts to further drive the development and deployment of STT and TTS recognition technologies in real-world applications.
{"title":"Speech-to-Text and Text-to-Speech Recognition Using Deep Learning","authors":"V. M. Reddy, T. Vaishnavi, K. Kumar","doi":"10.1109/ICECAA58104.2023.10212222","DOIUrl":"https://doi.org/10.1109/ICECAA58104.2023.10212222","url":null,"abstract":"Speech-to-Text (STT) and Text-to-Speech (TTS) recognition technologies have witnessed significant advancements in recent years, transforming various industries and applications. STT allows for the conversion of spoken language into written text, while TTS enables the generation of natural-sounding speech from written text. In this research paper, we provide a comprehensive review of the latest advancements in STT and TTS recognition technologies, including their underlying methodologies, applications, challenges, and future directions. We begin by discussing the key components of STT and TTS systems, including Automatic Speech Recognition (ASR) and speech synthesis techniques. This research study highlights the evolution of these technologies, from traditional approaches to data-driven deep learning methods, such as Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and transformer based models. Further, this research study analyses various applications of STT and TTS recognition technologies in different domains, including healthcare, customer service, accessibility, and language translation and discusses about the benefits of STT and TTS in improving communication, accessibility, and user experience, and address the challenges and limitations of these technologies, such as accuracy in noisy environments, handling diverse accents and languages, context awareness, and ethical considerations. Moreover, this study highlights the ongoing research efforts to address these challenges and improve the performance and robustness of STT and TTS systems. Finally, we outline the future directions and potential research opportunities in STT and TTS, including advancements in deep learning techniques, multimodal integration, domain adaptation, and personalized speech synthesis and also emphasizes the importance of interdisciplinary research collaborations, data collection, and benchmarking efforts to further drive the development and deployment of STT and TTS recognition technologies in real-world applications.","PeriodicalId":114624,"journal":{"name":"2023 2nd International Conference on Edge Computing and Applications (ICECAA)","volume":"39 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":"131278796","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/ICECAA58104.2023.10212230
Varun Nair, Ancy Jenifer. J, Rithick S, Joshua Premkumar C
The demand for energy-efficient and sustainable air conditioning systems has increased in recent years. In response, a new air conditioner regulating system has been developed by utilizing smart sensors and machine learning algorithms to optimize energy efficiency and user comfort. The proposed system is designed to switch ON the air conditioner when there is a decrease in temperature and switch ON the fan when there is an increase in bad humidity, reducing energy consumption and providing users with personalized comfort. If both temperature and humidity is not upto threshold, the system enters power saving mode to further reduce the energy consumption. Additionally, the system includes a LED notification system to alert users when temperature increases, allowing for timely adjustments to maintain user comfort and reduce energy waste. The system also includes real-time data analysis and machine learning algorithms, allowing it to learn user preferences and adjust settings accordingly. The system has been tested in a residential setting and has shown a significant reduction in energy consumption compared to traditional air conditioning systems. The air conditioner regulating system has the potential to revolution by providing a sustainable and energy-efficient solution that improves user comfort and reduces environmental impact.
{"title":"Efficient Energy Management Using Sensors and Smart Grid","authors":"Varun Nair, Ancy Jenifer. J, Rithick S, Joshua Premkumar C","doi":"10.1109/ICECAA58104.2023.10212230","DOIUrl":"https://doi.org/10.1109/ICECAA58104.2023.10212230","url":null,"abstract":"The demand for energy-efficient and sustainable air conditioning systems has increased in recent years. In response, a new air conditioner regulating system has been developed by utilizing smart sensors and machine learning algorithms to optimize energy efficiency and user comfort. The proposed system is designed to switch ON the air conditioner when there is a decrease in temperature and switch ON the fan when there is an increase in bad humidity, reducing energy consumption and providing users with personalized comfort. If both temperature and humidity is not upto threshold, the system enters power saving mode to further reduce the energy consumption. Additionally, the system includes a LED notification system to alert users when temperature increases, allowing for timely adjustments to maintain user comfort and reduce energy waste. The system also includes real-time data analysis and machine learning algorithms, allowing it to learn user preferences and adjust settings accordingly. The system has been tested in a residential setting and has shown a significant reduction in energy consumption compared to traditional air conditioning systems. The air conditioner regulating system has the potential to revolution by providing a sustainable and energy-efficient solution that improves user comfort and reduces environmental impact.","PeriodicalId":114624,"journal":{"name":"2023 2nd International Conference on Edge Computing and Applications (ICECAA)","volume":"168 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":"127238818","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/ICECAA58104.2023.10212170
Tannmay Gupta
The world has seen a significant transformation over the last ten years due to the steady advancement of innovation, which has also reduced processing power in many facets of everyday life. Understanding physical intelligence in all of its manifestations was one of computer science's major goals. Conventional teaching approaches that rely on lectures or include passive learning styles for the student are ineffective. Technology in higher education encourages interactive education, where the student's motivation increases and becomes the primary performer in his education. Artificial intelligence, a rapidly developing field of intelligence, can analyze vast amounts of data effectively and quickly, significantly enhancing the educational field. As a result, a smart education management framework employing artificial intelligence has been suggested. The framework is established inside a Hadoop-controlled storage group, which serves as the environment's server cluster. The associated facilities for education administration, learning platforms, and virtual teaching have been established in the framework. As a dataset, students were utilized. Analysis of Variance (ANOVA) is used to assess the use of AI in education. The test outcomes were assessed using several criteria and contrasted using different technologies. The test results demonstrate that AI has a beneficial effect on educational and instructional systems.
{"title":"Research on the Application of Artificial Intelligence in the Education and Teaching System","authors":"Tannmay Gupta","doi":"10.1109/ICECAA58104.2023.10212170","DOIUrl":"https://doi.org/10.1109/ICECAA58104.2023.10212170","url":null,"abstract":"The world has seen a significant transformation over the last ten years due to the steady advancement of innovation, which has also reduced processing power in many facets of everyday life. Understanding physical intelligence in all of its manifestations was one of computer science's major goals. Conventional teaching approaches that rely on lectures or include passive learning styles for the student are ineffective. Technology in higher education encourages interactive education, where the student's motivation increases and becomes the primary performer in his education. Artificial intelligence, a rapidly developing field of intelligence, can analyze vast amounts of data effectively and quickly, significantly enhancing the educational field. As a result, a smart education management framework employing artificial intelligence has been suggested. The framework is established inside a Hadoop-controlled storage group, which serves as the environment's server cluster. The associated facilities for education administration, learning platforms, and virtual teaching have been established in the framework. As a dataset, students were utilized. Analysis of Variance (ANOVA) is used to assess the use of AI in education. The test outcomes were assessed using several criteria and contrasted using different technologies. The test results demonstrate that AI has a beneficial effect on educational and instructional systems.","PeriodicalId":114624,"journal":{"name":"2023 2nd International Conference on Edge Computing and Applications (ICECAA)","volume":"87 1","pages":"1168-1173"},"PeriodicalIF":0.0,"publicationDate":"2023-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139357644","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}
Manufacturing systems nowadays are becoming more complex, dynamic and interconnected. Manufacturing operations confront challenges from highly nonlinear and stochastic activities due to the numerous uncertainties and interdependencies that exist. Recent developments in artificial intelligence (AI), particularly machine learning (ML) have established considerable technological capabilities to transform the manufacturing industry with advanced analytics tools for processing enormous amounts of manufacturing production data. This study summarizes the incisive concept of machine learning and its importance in the manufacturing industry. The research further covers a systematic review of several ML systems that have been enacted in the manufacturing industry and production procedure. In addition, the study also discusses some of the major challenges encountered while implementing machine learning in the manufacturing industry and highlighted some of the significant tasks achieved by machine learning technologies.
如今，制造系统正变得越来越复杂、动态和相互关联。由于存在众多不确定性和相互依存性，制造业务面临着高度非线性和随机活动的挑战。人工智能（AI），尤其是机器学习（ML）的最新发展，为利用先进的分析工具处理海量制造业生产数据提供了可观的技术能力，从而改变了制造业。本研究总结了机器学习的精辟概念及其在制造业中的重要性。研究还系统回顾了在制造业和生产流程中应用的多个 ML 系统。此外，本研究还讨论了在制造业中实施机器学习时遇到的一些主要挑战，并强调了机器学习技术所实现的一些重要任务。
{"title":"Implementation of Artificial Intelligence and Machine Learning in Manufacturing","authors":"J. Chohan, Raman Kumar, Sandeep Kumar, Bhawna Goyal, Ayush Dogra, Vinay Kukreja","doi":"10.1109/ICECAA58104.2023.10212238","DOIUrl":"https://doi.org/10.1109/ICECAA58104.2023.10212238","url":null,"abstract":"Manufacturing systems nowadays are becoming more complex, dynamic and interconnected. Manufacturing operations confront challenges from highly nonlinear and stochastic activities due to the numerous uncertainties and interdependencies that exist. Recent developments in artificial intelligence (AI), particularly machine learning (ML) have established considerable technological capabilities to transform the manufacturing industry with advanced analytics tools for processing enormous amounts of manufacturing production data. This study summarizes the incisive concept of machine learning and its importance in the manufacturing industry. The research further covers a systematic review of several ML systems that have been enacted in the manufacturing industry and production procedure. In addition, the study also discusses some of the major challenges encountered while implementing machine learning in the manufacturing industry and highlighted some of the significant tasks achieved by machine learning technologies.","PeriodicalId":114624,"journal":{"name":"2023 2nd International Conference on Edge Computing and Applications (ICECAA)","volume":"15 1","pages":"497-503"},"PeriodicalIF":0.0,"publicationDate":"2023-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139357785","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/ICECAA58104.2023.10212350
R. Niranjana, T. Hemadarshana, S. Ilakkya, R. Jaiveena, A. Ravi
LPG is widely used for cooking in many countries due to its accessibility, affordability, and popularity as a source of fuel. When using it, common issues include gas cylinders running out of fuel at prime cooking times, forgetting how much gasoline is actually in the tank, and failing to predict the LPG cylinder's useful life after installation. Leakage can explode if it is not discovered Therefore, a system to ceaselessly monitor this is needed. This study focuses on automatic valve closure when a leak is detected and automatic LPG cycle booking when the level drops below a threshold. The gas sensor, Arduino, and solenoid valve are used to automatically close the valve. The gas sensor detects a gas leak and sends the information to the Arduino, which processes it and activates the solenoid valve. The quantity of LPG using a load sensor to measure (SEN-10245). The sensor's output is linked to an Arduino R3. IFTTT is used to transmit information to users via SMS (short message service), and it also handles automatic booking by sending a message to a gas agency. When LPG leaks, the user is notified with an IOT buzzer and by receiving a message on their mobile device. Additionally, a notification is sent when the level is dangerously low (below 20%). So, by doing this, early and late reservations can be avoided. Consequently, we may avoid unforeseen LPG gas burst accidents in the home by detecting the leak.
{"title":"An Intelligent Gas Monitoring System with Solenoid Valve and Weight Cell using MQTT","authors":"R. Niranjana, T. Hemadarshana, S. Ilakkya, R. Jaiveena, A. Ravi","doi":"10.1109/ICECAA58104.2023.10212350","DOIUrl":"https://doi.org/10.1109/ICECAA58104.2023.10212350","url":null,"abstract":"LPG is widely used for cooking in many countries due to its accessibility, affordability, and popularity as a source of fuel. When using it, common issues include gas cylinders running out of fuel at prime cooking times, forgetting how much gasoline is actually in the tank, and failing to predict the LPG cylinder's useful life after installation. Leakage can explode if it is not discovered Therefore, a system to ceaselessly monitor this is needed. This study focuses on automatic valve closure when a leak is detected and automatic LPG cycle booking when the level drops below a threshold. The gas sensor, Arduino, and solenoid valve are used to automatically close the valve. The gas sensor detects a gas leak and sends the information to the Arduino, which processes it and activates the solenoid valve. The quantity of LPG using a load sensor to measure (SEN-10245). The sensor's output is linked to an Arduino R3. IFTTT is used to transmit information to users via SMS (short message service), and it also handles automatic booking by sending a message to a gas agency. When LPG leaks, the user is notified with an IOT buzzer and by receiving a message on their mobile device. Additionally, a notification is sent when the level is dangerously low (below 20%). So, by doing this, early and late reservations can be avoided. Consequently, we may avoid unforeseen LPG gas burst accidents in the home by detecting the leak.","PeriodicalId":114624,"journal":{"name":"2023 2nd International Conference on Edge Computing and Applications (ICECAA)","volume":"363 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":"115900431","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/ICECAA58104.2023.10212376
Tushar Chawla, D. Kumar, V. Kukreja
In India, gateways have been an integral part of architecture and have served as entrances to many historical buildings. These gateways are known for their unique design, intricate carvings, and beautiful ornamentation. The gateways of heritage buildings in India are not only significant architectural features but also have historical, cultural, and religious significance. At present time detecting gateways in heritage buildings is a difficult task for tourism agencies. To address the gateway recognition through real-time captured images, a novel-based heritage gateway recognition system is proposed through an enhanced ET-YOLOV5 object detector. The ET-YOLOV5 model uses the Resnet-50 as a feature extraction and spatial pyramid pooling model. The ETYOLOV5 model has been trained, tested, and validated on preprocessed 3000 heritage buildings image datasets. During the comparison, the ET-YOLOV5 increases the 9% mAP rate as compared to YOLOV5 and YOLOV4 for gateways recognition in heritage buildings of India.
{"title":"An Enhanced YOLOV5 Model for Gateways Recognition in Heritage Buildings","authors":"Tushar Chawla, D. Kumar, V. Kukreja","doi":"10.1109/ICECAA58104.2023.10212376","DOIUrl":"https://doi.org/10.1109/ICECAA58104.2023.10212376","url":null,"abstract":"In India, gateways have been an integral part of architecture and have served as entrances to many historical buildings. These gateways are known for their unique design, intricate carvings, and beautiful ornamentation. The gateways of heritage buildings in India are not only significant architectural features but also have historical, cultural, and religious significance. At present time detecting gateways in heritage buildings is a difficult task for tourism agencies. To address the gateway recognition through real-time captured images, a novel-based heritage gateway recognition system is proposed through an enhanced ET-YOLOV5 object detector. The ET-YOLOV5 model uses the Resnet-50 as a feature extraction and spatial pyramid pooling model. The ETYOLOV5 model has been trained, tested, and validated on preprocessed 3000 heritage buildings image datasets. During the comparison, the ET-YOLOV5 increases the 9% mAP rate as compared to YOLOV5 and YOLOV4 for gateways recognition in heritage buildings of India.","PeriodicalId":114624,"journal":{"name":"2023 2nd International Conference on Edge Computing and Applications (ICECAA)","volume":"20 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":"124578369","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：