Pub Date : 2023-07-19DOI: 10.1109/ICECAA58104.2023.10212242
Jayakshata Pr, Kambam Shreya, S. Hariharan, V. Kukreja, H. Reddy, Andraju Bhanu Prasad
Moving from the era of using passwords, passcodes for digital security, research in the field of Artificial Intelligence has enabled new ways of security, wherein the most commonly used method is Facial recognition. A smart home recognition system must be capable of identifying facial features, motion sensing and detection of unusual movement, record the footages, alert user in emergency situation and remote access to door lock. These features come with a number of abundant and unavoidable drawbacks and risks like hacking into the system and high cost. This paper aims to conduct a complete survey of the current issues and functioning of recognition systems for home security based on related works published by several authors on the same. The result of the work is targeted at proposing a detailed and holistic view of current stage methods, features and issues of the system and discuss the future scope in this field of study.
{"title":"Research Dimension on Home Recognition for Improved Security System","authors":"Jayakshata Pr, Kambam Shreya, S. Hariharan, V. Kukreja, H. Reddy, Andraju Bhanu Prasad","doi":"10.1109/ICECAA58104.2023.10212242","DOIUrl":"https://doi.org/10.1109/ICECAA58104.2023.10212242","url":null,"abstract":"Moving from the era of using passwords, passcodes for digital security, research in the field of Artificial Intelligence has enabled new ways of security, wherein the most commonly used method is Facial recognition. A smart home recognition system must be capable of identifying facial features, motion sensing and detection of unusual movement, record the footages, alert user in emergency situation and remote access to door lock. These features come with a number of abundant and unavoidable drawbacks and risks like hacking into the system and high cost. This paper aims to conduct a complete survey of the current issues and functioning of recognition systems for home security based on related works published by several authors on the same. The result of the work is targeted at proposing a detailed and holistic view of current stage methods, features and issues of the system and discuss the future scope in this field of study.","PeriodicalId":114624,"journal":{"name":"2023 2nd International Conference on Edge Computing and Applications (ICECAA)","volume":"NS34 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":"116551720","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/ICECAA58104.2023.10212251
M. Praveena, A. Babiyola, S. Aghalya, A. Sasikar
This research work describes a Wireless Sensor Network (WSN) for monitoring different conditions of a greenhouse. Plant development requires careful temperature and humidity management in greenhouses. Manual monitoring is time-consuming and error-prone. The proposed WSN solves these issues. Each sensor node in the greenhouse has a microprocessor, wireless connection module, and temperature and humidity sensors. Nodes deliberately positioned to gather data from different areas provide a complete greenhouse perspective. A central base station aggregates and visualizes data from sensor nodes through wireless communication. Sensor nodes use strong communication protocols and data aggregation methods for accurate, real-time monitoring. Zigbee or Bluetooth low-power wireless communication protocols are used to send data to the base station to save energy and prolong network lifespan. The base station stores, processes, and analyzes data. Data is shown and analyzed using a simple interface. A web-based or mobile app allows remote greenhouse monitoring and control. Users get real-time warnings of important temperature or humidity variations to take immediate action. WSN greenhouse monitoring outperforms manual approaches. It monitors greenhouse temperature and humidity in real-time, allowing precise control and changes for ideal growing conditions. Wireless connections provide node placement freedom and lower installation costs. The WSN for greenhouse monitoring is a dependable and effective agricultural solution. It boosts productivity, lowers personnel costs, and allows real-time data-driven decision-making. This research advances precision agriculture and shows WSNs can improve greenhouse management and crop production.
{"title":"Wireless Sensor Network Based Greenhouse Monitoring Using Cloud Integration with Data Analytics","authors":"M. Praveena, A. Babiyola, S. Aghalya, A. Sasikar","doi":"10.1109/ICECAA58104.2023.10212251","DOIUrl":"https://doi.org/10.1109/ICECAA58104.2023.10212251","url":null,"abstract":"This research work describes a Wireless Sensor Network (WSN) for monitoring different conditions of a greenhouse. Plant development requires careful temperature and humidity management in greenhouses. Manual monitoring is time-consuming and error-prone. The proposed WSN solves these issues. Each sensor node in the greenhouse has a microprocessor, wireless connection module, and temperature and humidity sensors. Nodes deliberately positioned to gather data from different areas provide a complete greenhouse perspective. A central base station aggregates and visualizes data from sensor nodes through wireless communication. Sensor nodes use strong communication protocols and data aggregation methods for accurate, real-time monitoring. Zigbee or Bluetooth low-power wireless communication protocols are used to send data to the base station to save energy and prolong network lifespan. The base station stores, processes, and analyzes data. Data is shown and analyzed using a simple interface. A web-based or mobile app allows remote greenhouse monitoring and control. Users get real-time warnings of important temperature or humidity variations to take immediate action. WSN greenhouse monitoring outperforms manual approaches. It monitors greenhouse temperature and humidity in real-time, allowing precise control and changes for ideal growing conditions. Wireless connections provide node placement freedom and lower installation costs. The WSN for greenhouse monitoring is a dependable and effective agricultural solution. It boosts productivity, lowers personnel costs, and allows real-time data-driven decision-making. This research advances precision agriculture and shows WSNs can improve greenhouse management and crop production.","PeriodicalId":114624,"journal":{"name":"2023 2nd International Conference on Edge Computing and Applications (ICECAA)","volume":"24 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":"122823644","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/ICECAA58104.2023.10212354
E. Mythili, S. Vanithamani, Rajesh Kanna P, Rajeshkumar G, K. Gayathri, R. Harsha
Automatic License Plate Recognition (ALPR) System detects License Plate (LP) of a vehicle. The computer vision zone considers ALPR system as a resolved issue. However, the majority of current ALPR research is based on LP from specific countries and employs country-specific data. Therefore, the proposed methodology deals with the LP which will work on the regions in & around India. The algorithm applied in the proposed methodology is Convolution Neural Network (CNN). The proposed methodology comprises three major steps: Firstly, License plate detection which uses Single Shot Detector (SSD) which divides the image into grid cells, with each grid cell being in charge of detecting objects in that area. Secondly, Unified character recognition which uses easyOCR (Optical Character Recognition) has the ability to deal with multi scale and small objects. Finally, Multi-regional layout detection extracts the correct order of the license plate. The dataset is collected from which is “Indian License Plate Dataset”. Experiment results outperform the existing mechanisms in terms of time conception accuracy of LP recognition, end to end recognition and average execution time.
{"title":"AMLPDS: An Automatic Multi-Regional License Plate Detection System based on EasyOCR and CNN Algorithm","authors":"E. Mythili, S. Vanithamani, Rajesh Kanna P, Rajeshkumar G, K. Gayathri, R. Harsha","doi":"10.1109/ICECAA58104.2023.10212354","DOIUrl":"https://doi.org/10.1109/ICECAA58104.2023.10212354","url":null,"abstract":"Automatic License Plate Recognition (ALPR) System detects License Plate (LP) of a vehicle. The computer vision zone considers ALPR system as a resolved issue. However, the majority of current ALPR research is based on LP from specific countries and employs country-specific data. Therefore, the proposed methodology deals with the LP which will work on the regions in & around India. The algorithm applied in the proposed methodology is Convolution Neural Network (CNN). The proposed methodology comprises three major steps: Firstly, License plate detection which uses Single Shot Detector (SSD) which divides the image into grid cells, with each grid cell being in charge of detecting objects in that area. Secondly, Unified character recognition which uses easyOCR (Optical Character Recognition) has the ability to deal with multi scale and small objects. Finally, Multi-regional layout detection extracts the correct order of the license plate. The dataset is collected from which is “Indian License Plate Dataset”. Experiment results outperform the existing mechanisms in terms of time conception accuracy of LP recognition, end to end recognition and average execution time.","PeriodicalId":114624,"journal":{"name":"2023 2nd International Conference on Edge Computing and Applications (ICECAA)","volume":"27 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":"131195874","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/ICECAA58104.2023.10212178
Prabhakar Marry, Shriya Atluri, B. Anmol, K. S. Reddy, V. S. K. Reddy
The World Wide Web, particularly Twitter, and online social networks have expanded the network connecting people, allowing for the rapid dissemination of information to large numbers of people. There are several instances of this kind of online collaborative contagion, one of which is the development of self-destructive ideas in social media sites like Twitter, which has caused alarm. In this investigation, the implications and findings of several machine classifiers that were applied to the point order of tweets and terms connected to suicide are discussed. The classifier can distinguish between more stressful information, such as suicidal creativity, other suicide-related topics, in-depth suicide-related facts, loyalty, campaign, and support. A simple classifier utilizing emotional, lexical, psychological, and structural characteristics from Twitter is used to link and identify allusions to suicide. This procedure makes use of clustering, bracketing, association rules, NLP (natural language processing), and numerous machine-learning techniques. This research study explores the restrictions or difficulties in this field and serve as a guide for future research.
{"title":"Suicidal Ideation Detection: Application of Machine Learning Techniques on Twitter Data","authors":"Prabhakar Marry, Shriya Atluri, B. Anmol, K. S. Reddy, V. S. K. Reddy","doi":"10.1109/ICECAA58104.2023.10212178","DOIUrl":"https://doi.org/10.1109/ICECAA58104.2023.10212178","url":null,"abstract":"The World Wide Web, particularly Twitter, and online social networks have expanded the network connecting people, allowing for the rapid dissemination of information to large numbers of people. There are several instances of this kind of online collaborative contagion, one of which is the development of self-destructive ideas in social media sites like Twitter, which has caused alarm. In this investigation, the implications and findings of several machine classifiers that were applied to the point order of tweets and terms connected to suicide are discussed. The classifier can distinguish between more stressful information, such as suicidal creativity, other suicide-related topics, in-depth suicide-related facts, loyalty, campaign, and support. A simple classifier utilizing emotional, lexical, psychological, and structural characteristics from Twitter is used to link and identify allusions to suicide. This procedure makes use of clustering, bracketing, association rules, NLP (natural language processing), and numerous machine-learning techniques. This research study explores the restrictions or difficulties in this field and serve as a guide for future research.","PeriodicalId":114624,"journal":{"name":"2023 2nd International Conference on Edge Computing and Applications (ICECAA)","volume":"19 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":"116528515","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/ICECAA58104.2023.10212260
N. Saranya, L. M, N. Kanthimathi, V. Gnanprakash, L. Pavithra
Cancer is becoming the major reason of mortality. Automatic detection of lung cancer leads to early diagnosis and appropriate treatment. This work describes the development of an automated system that detects lung cancer using machine learning. The created system can capture medical images through computerized tomography. The model proposed here is developed using DCT for trait selection and SVM, KNN, Random Forest, Naive Bayes, linear regression and logistic regression classifiers for classification. The proposed system accepts medical images and efficiently detects cancer cells from CT images. Superpixel segmentation is utilized for the purpose of extracting the region of interest from the CT images and Gabor filter is applied for denoising the images. In the cancer detection system, the effectiveness of each of the above-mentioned classifiers was compared based on the parameters such as accuracy, precision, F1 score, MCC and error rate.
{"title":"Comparative Analysis of Machine Learning Algorithms for the Effective Detection of Lung Cancer","authors":"N. Saranya, L. M, N. Kanthimathi, V. Gnanprakash, L. Pavithra","doi":"10.1109/ICECAA58104.2023.10212260","DOIUrl":"https://doi.org/10.1109/ICECAA58104.2023.10212260","url":null,"abstract":"Cancer is becoming the major reason of mortality. Automatic detection of lung cancer leads to early diagnosis and appropriate treatment. This work describes the development of an automated system that detects lung cancer using machine learning. The created system can capture medical images through computerized tomography. The model proposed here is developed using DCT for trait selection and SVM, KNN, Random Forest, Naive Bayes, linear regression and logistic regression classifiers for classification. The proposed system accepts medical images and efficiently detects cancer cells from CT images. Superpixel segmentation is utilized for the purpose of extracting the region of interest from the CT images and Gabor filter is applied for denoising the images. In the cancer detection system, the effectiveness of each of the above-mentioned classifiers was compared based on the parameters such as accuracy, precision, F1 score, MCC and error rate.","PeriodicalId":114624,"journal":{"name":"2023 2nd International Conference on Edge Computing and Applications (ICECAA)","volume":"21 1","pages":"1008-1013"},"PeriodicalIF":0.0,"publicationDate":"2023-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139357659","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/ICECAA58104.2023.10212255
Girish S Bairagi, Tejas D Ahire, Siddesh N Suryvanshi, Rupesh B Phatangre, D. Pardeshi, Prof. Deepak Porwal
The requirement to satisfy energy demand in the most affordable and environmentally appropriate way possible remains as a significant challenge. This research study is focused on creating a reasonably small Vertical Axis Wind Turbine (VAWT), affordable alternative for renewable energy. When there is enough wind to rotate it, the windmill creates energy due to the attraction between its rotating and stationary coils. The wind turbine may be used to recharge a 12V battery in a variety of ways. This approach has the benefit of not requiring the use of fossil fuels, of functioning well in bad weather conditions without the need for constant monitoring, and of automatically charging the batteries without generating any undesired side effects. The work presented in this book is an example of what may be accomplished by combining renewable resources, such as wind, with effective energy utilization.
{"title":"Inverter Based Wind Energy Generation","authors":"Girish S Bairagi, Tejas D Ahire, Siddesh N Suryvanshi, Rupesh B Phatangre, D. Pardeshi, Prof. Deepak Porwal","doi":"10.1109/ICECAA58104.2023.10212255","DOIUrl":"https://doi.org/10.1109/ICECAA58104.2023.10212255","url":null,"abstract":"The requirement to satisfy energy demand in the most affordable and environmentally appropriate way possible remains as a significant challenge. This research study is focused on creating a reasonably small Vertical Axis Wind Turbine (VAWT), affordable alternative for renewable energy. When there is enough wind to rotate it, the windmill creates energy due to the attraction between its rotating and stationary coils. The wind turbine may be used to recharge a 12V battery in a variety of ways. This approach has the benefit of not requiring the use of fossil fuels, of functioning well in bad weather conditions without the need for constant monitoring, and of automatically charging the batteries without generating any undesired side effects. The work presented in this book is an example of what may be accomplished by combining renewable resources, such as wind, with effective energy utilization.","PeriodicalId":114624,"journal":{"name":"2023 2nd International Conference on Edge Computing and Applications (ICECAA)","volume":"48 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":"133682266","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/ICECAA58104.2023.10212397
Palak Vadhadiya, Nitin Jayavarapu, Lasya Mudigonda, Sai Sravani Parnem
Modern highways cannot exist unless traffic safety is prioritized. As a result, while determining speed restrictions for a certain route, the condition of the road and its tendency for accidents are considered. Speed monitoring cameras are strategically positioned along the route to detect motorists who exceed the speed limit. The traditional speed radar gun has been replaced with speed monitoring cameras. The main purpose of this research work is to create a speed-detecting camera by using image processing to process the videos using Haar Cascade in Python.
{"title":"Speed Detection using Haar-Cascade Classifier and Pixel per Meter","authors":"Palak Vadhadiya, Nitin Jayavarapu, Lasya Mudigonda, Sai Sravani Parnem","doi":"10.1109/ICECAA58104.2023.10212397","DOIUrl":"https://doi.org/10.1109/ICECAA58104.2023.10212397","url":null,"abstract":"Modern highways cannot exist unless traffic safety is prioritized. As a result, while determining speed restrictions for a certain route, the condition of the road and its tendency for accidents are considered. Speed monitoring cameras are strategically positioned along the route to detect motorists who exceed the speed limit. The traditional speed radar gun has been replaced with speed monitoring cameras. The main purpose of this research work is to create a speed-detecting camera by using image processing to process the videos using Haar Cascade in Python.","PeriodicalId":114624,"journal":{"name":"2023 2nd International Conference on Edge Computing and Applications (ICECAA)","volume":"27 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":"133784050","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/ICECAA58104.2023.10212283
Shally Vats, Pratham Jain, Devesh Baranwal
High demand for cloud computing resources has given rise to the enormous size of cloud data centers. Consequently, the energy demand for cloud resources has increased. This is high time to put a check on energy consumption to make cloud computing more profitable for the cloud service provider and to defend the environment from carbon footprint. In this paper, a method has been proposed to allocate the resources to the coming tasks in an energy efficient manner. The proposed method of host selection for VM consolidation is successful in the reduction of energy consumption and maintaining the SLA violations low.
{"title":"A New Dynamic Threshold Based Energy Saver Resource Allocation method for Cloud Infrastructure","authors":"Shally Vats, Pratham Jain, Devesh Baranwal","doi":"10.1109/ICECAA58104.2023.10212283","DOIUrl":"https://doi.org/10.1109/ICECAA58104.2023.10212283","url":null,"abstract":"High demand for cloud computing resources has given rise to the enormous size of cloud data centers. Consequently, the energy demand for cloud resources has increased. This is high time to put a check on energy consumption to make cloud computing more profitable for the cloud service provider and to defend the environment from carbon footprint. In this paper, a method has been proposed to allocate the resources to the coming tasks in an energy efficient manner. The proposed method of host selection for VM consolidation is successful in the reduction of energy consumption and maintaining the SLA violations low.","PeriodicalId":114624,"journal":{"name":"2023 2nd International Conference on Edge Computing and Applications (ICECAA)","volume":"69 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":"114323244","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/ICECAA58104.2023.10212135
M. Arumugam, Snegaa S R, C. Jayanthi
Sentimental analysis is a crucial step in natural language processing that aids in figuring out whether a text has a positive, negative, or neutral sentiment. In this experiment, we analyzed the sentiments expressed in tweets that included text, emojis, and emoticons. To categorize the tweets into different sentiments, we utilized four different algorithms: Multinomial Naive Bayes (MNB),Random Forest, Support Vector Machine (SVM) and Decision Tree. In order to increase the model's accuracy, we also combined the predictions from the four algorithms using the Voting Classifier, an ensemble learning technique. To preprocess the data, we used various techniques, such as removing stop words, stemming, and converting emojis and emoticons to their corresponding text representations. The performance of each algorithm was then trained on the preprocessed data using various assessment measures, including accuracy, precision, F1-score and recall. The SVM method fared better than the other algorithms, obtaining an accuracy of 96.27%, according to the data. Furthermore, we applied ensemble learning techniques, such as bagging to improve the performance of all the four algorithms. We also used the Voting Classifier to combine the predictions of the bagging models to further improve the accuracy of the model. The results revealed that the accuracy was increased to 97.21% by combining the bagging and voting classifiers. Overall, the project demonstrates the effectiveness of various algorithms and ensemble learning methods in performing sentimental analysis on tweets containing text, emojis, and emoticons.
{"title":"Machine Learning for Sentiment Analysis Utilizing Social Media","authors":"M. Arumugam, Snegaa S R, C. Jayanthi","doi":"10.1109/ICECAA58104.2023.10212135","DOIUrl":"https://doi.org/10.1109/ICECAA58104.2023.10212135","url":null,"abstract":"Sentimental analysis is a crucial step in natural language processing that aids in figuring out whether a text has a positive, negative, or neutral sentiment. In this experiment, we analyzed the sentiments expressed in tweets that included text, emojis, and emoticons. To categorize the tweets into different sentiments, we utilized four different algorithms: Multinomial Naive Bayes (MNB),Random Forest, Support Vector Machine (SVM) and Decision Tree. In order to increase the model's accuracy, we also combined the predictions from the four algorithms using the Voting Classifier, an ensemble learning technique. To preprocess the data, we used various techniques, such as removing stop words, stemming, and converting emojis and emoticons to their corresponding text representations. The performance of each algorithm was then trained on the preprocessed data using various assessment measures, including accuracy, precision, F1-score and recall. The SVM method fared better than the other algorithms, obtaining an accuracy of 96.27%, according to the data. Furthermore, we applied ensemble learning techniques, such as bagging to improve the performance of all the four algorithms. We also used the Voting Classifier to combine the predictions of the bagging models to further improve the accuracy of the model. The results revealed that the accuracy was increased to 97.21% by combining the bagging and voting classifiers. Overall, the project demonstrates the effectiveness of various algorithms and ensemble learning methods in performing sentimental analysis on tweets containing text, emojis, and emoticons.","PeriodicalId":114624,"journal":{"name":"2023 2nd International Conference on Edge Computing and Applications (ICECAA)","volume":"74 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":"114543993","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/ICECAA58104.2023.10212180
Siddharth Chhetri, M. Joshi, C. Mahamuni, Repana Naga Sangeetha, Tushar Roy
The paper provides a comprehensive overview of speech enhancement techniques and their applications. It discusses challenges in non-stationary noise, reverberation, and overlapping speech. Approaches like comb filtering, LPC-based filtering, and adaptive filtering, HMM filtering, Wiener filtering, ML estimation, Bayesian estimation, MMSE estimation, and transform domain methods, AI-based approaches are explored. The effectiveness and challenges of each approach are discussed. Applications in telecommunications, voice-controlled systems, hearing aids, speech recognition, and audio restoration are highlighted. The paper presents outcomes and advancements in speech enhancement. Valuable insights are provided for researchers, engineers, and practitioners in the field. The findings aid in selecting suitable techniques for improved speech quality and intelligibility.
{"title":"Speech Enhancement: A Survey of Approaches and Applications","authors":"Siddharth Chhetri, M. Joshi, C. Mahamuni, Repana Naga Sangeetha, Tushar Roy","doi":"10.1109/ICECAA58104.2023.10212180","DOIUrl":"https://doi.org/10.1109/ICECAA58104.2023.10212180","url":null,"abstract":"The paper provides a comprehensive overview of speech enhancement techniques and their applications. It discusses challenges in non-stationary noise, reverberation, and overlapping speech. Approaches like comb filtering, LPC-based filtering, and adaptive filtering, HMM filtering, Wiener filtering, ML estimation, Bayesian estimation, MMSE estimation, and transform domain methods, AI-based approaches are explored. The effectiveness and challenges of each approach are discussed. Applications in telecommunications, voice-controlled systems, hearing aids, speech recognition, and audio restoration are highlighted. The paper presents outcomes and advancements in speech enhancement. Valuable insights are provided for researchers, engineers, and practitioners in the field. The findings aid in selecting suitable techniques for improved speech quality and intelligibility.","PeriodicalId":114624,"journal":{"name":"2023 2nd International Conference on Edge Computing and Applications (ICECAA)","volume":"45 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":"117087983","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：