Pub Date : 2023-05-26DOI: 10.1109/INCET57972.2023.10170736
Akhtar I. Nadaf, S. Pardeshi
The use of machine learning technologies for the identification of sign language has gained popularity recently. This arises from the recognition of sign language as a valuable means of communication specifically designed for individuals who are mute or hearing-impaired. In order to build an optimised model based on sEMG, accelerometer, gyro, and magnetometer data, this research article compares decision tree classifiers, notably J48, Random tree, REPTree, and Random forest. This data is collected through the Myo arm band worn on both forearms of the user. The experiment is designed using the open-source Waikato Environment for Knowledge Analysis (WEKA) framework. To evaluate the effectiveness of the four algorithms, three attribute selection techniques information gain-based, correlation-based, and learner-based feature selection were used. The trial results showed that, among the investigated algorithms, the Random Forest method had the highest accuracy, measuring 97.9472%.
最近，机器学习技术在识别手语方面的应用越来越受欢迎。这是因为人们认识到手语是专门为哑巴或听障人士设计的一种宝贵的交流手段。为了构建基于表面肌电信号、加速度计、陀螺仪和磁力计数据的优化模型，本文比较了决策树分类器，特别是J48、Random tree、REPTree和Random forest。这些数据是通过佩戴在用户前臂上的Myo臂带收集的。实验是使用开源的Waikato Environment for Knowledge Analysis (WEKA)框架设计的。为了评估四种算法的有效性，使用了基于信息增益、基于相关性和基于学习者的特征选择三种属性选择技术。试验结果表明，在所研究的算法中，随机森林方法的准确率最高，为97.9472%。
{"title":"Classifying Sign Language Gestures using Decision Trees: A Comparison of sEMG and IMU Sensor Data","authors":"Akhtar I. Nadaf, S. Pardeshi","doi":"10.1109/INCET57972.2023.10170736","DOIUrl":"https://doi.org/10.1109/INCET57972.2023.10170736","url":null,"abstract":"The use of machine learning technologies for the identification of sign language has gained popularity recently. This arises from the recognition of sign language as a valuable means of communication specifically designed for individuals who are mute or hearing-impaired. In order to build an optimised model based on sEMG, accelerometer, gyro, and magnetometer data, this research article compares decision tree classifiers, notably J48, Random tree, REPTree, and Random forest. This data is collected through the Myo arm band worn on both forearms of the user. The experiment is designed using the open-source Waikato Environment for Knowledge Analysis (WEKA) framework. To evaluate the effectiveness of the four algorithms, three attribute selection techniques information gain-based, correlation-based, and learner-based feature selection were used. The trial results showed that, among the investigated algorithms, the Random Forest method had the highest accuracy, measuring 97.9472%.","PeriodicalId":403008,"journal":{"name":"2023 4th International Conference for Emerging Technology (INCET)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114612228","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 : 2023-05-26DOI: 10.1109/INCET57972.2023.10170149
Swati Laxmi Sahu, Renta Chintala Bhargavi
Potato, among the most vegetables is commercially significant and well-known vegetable which is known for its high nutritional content and delicious flavor. India is one of the world’s leading producers of potato. Unfortunately, plant diseases in potato have been one of the causes of decreased production. So, it is necessary to detect them. Collecting images of plants diseases is a big challenge as it is a very time-consuming process. Often, we do not have sufficient data to train our deep learning models, so data augmentation techniques are used for increasing the dataset which lead to poor generalization. This study focuses on detecting whether the plant is healthy or diseased. In this proposed method, limited dataset is used for potato plant disease classification without using any data augmentation techniques. Popular pre-trained models — VGG16, InceptionResNetV2, ResNet50V2 are used for feature extraction and traditional machine learning algorithms — XGBoost, Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Random Forest are used as classifiers. From the study, it is observed that the combination of VGG16 model as a feature extractor and SVM as a classifier achieved the highest accuracy of 93% compared to rest of the combination of models and algorithms. The method proposed in this study can be used for potato plant disease detection with limited dataset.
马铃薯是我国最具商业价值的蔬菜之一，以其营养价值高、风味鲜美而闻名于世。印度是世界主要的马铃薯生产国之一。不幸的是，马铃薯的植物病害已成为产量下降的原因之一。因此，有必要对它们进行检测。植物病害图像的采集是一项巨大的挑战，因为这是一个非常耗时的过程。通常，我们没有足够的数据来训练我们的深度学习模型，因此使用数据增强技术来增加数据集，从而导致较差的泛化。这项研究的重点是检测植物是健康还是患病。该方法采用有限数据集进行马铃薯病害分类，不使用任何数据增强技术。流行的预训练模型- VGG16, InceptionResNetV2, ResNet50V2用于特征提取，传统的机器学习算法- XGBoost，支持向量机(SVM)， k -最近邻(KNN)，随机森林被用作分类器。从研究中可以看出，VGG16模型作为特征提取器，SVM作为分类器的组合，与其他模型与算法的组合相比，准确率最高，达到93%。该方法可用于有限数据集的马铃薯病害检测。
{"title":"Prediction of Diseases in Potato Plant using Pre-trained and Traditional Machine Learning Models","authors":"Swati Laxmi Sahu, Renta Chintala Bhargavi","doi":"10.1109/INCET57972.2023.10170149","DOIUrl":"https://doi.org/10.1109/INCET57972.2023.10170149","url":null,"abstract":"Potato, among the most vegetables is commercially significant and well-known vegetable which is known for its high nutritional content and delicious flavor. India is one of the world’s leading producers of potato. Unfortunately, plant diseases in potato have been one of the causes of decreased production. So, it is necessary to detect them. Collecting images of plants diseases is a big challenge as it is a very time-consuming process. Often, we do not have sufficient data to train our deep learning models, so data augmentation techniques are used for increasing the dataset which lead to poor generalization. This study focuses on detecting whether the plant is healthy or diseased. In this proposed method, limited dataset is used for potato plant disease classification without using any data augmentation techniques. Popular pre-trained models — VGG16, InceptionResNetV2, ResNet50V2 are used for feature extraction and traditional machine learning algorithms — XGBoost, Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Random Forest are used as classifiers. From the study, it is observed that the combination of VGG16 model as a feature extractor and SVM as a classifier achieved the highest accuracy of 93% compared to rest of the combination of models and algorithms. The method proposed in this study can be used for potato plant disease detection with limited dataset.","PeriodicalId":403008,"journal":{"name":"2023 4th International Conference for Emerging Technology (INCET)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123757433","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}
This paper proposes the comparison between three text summarization models - BERT, BART and T5. All the three models focus on summarizing a single research paper for generating a summary which is automatic and relevant. After the analysis and implementation of the three pretrained models, it is noticed that T5 is the best suited for our problem statement. Many researchers, professionals as well as students need to be up-to-date about the new scientific documents for the project they are working on or to gain something new out of it. They frequently feel that the abstract is not informative enough in order to establish significance. The final system aims at resolving the mentioned problem.
{"title":"Synopsis Creation for Research Paper using Text Summarization Models","authors":"Sanskruti Badhe, Mubashshira Hasan, Vidhi Rughwani, Reeta Koshy","doi":"10.1109/INCET57972.2023.10170144","DOIUrl":"https://doi.org/10.1109/INCET57972.2023.10170144","url":null,"abstract":"This paper proposes the comparison between three text summarization models - BERT, BART and T5. All the three models focus on summarizing a single research paper for generating a summary which is automatic and relevant. After the analysis and implementation of the three pretrained models, it is noticed that T5 is the best suited for our problem statement. Many researchers, professionals as well as students need to be up-to-date about the new scientific documents for the project they are working on or to gain something new out of it. They frequently feel that the abstract is not informative enough in order to establish significance. The final system aims at resolving the mentioned problem.","PeriodicalId":403008,"journal":{"name":"2023 4th International Conference for Emerging Technology (INCET)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124201691","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 : 2023-05-26DOI: 10.1109/INCET57972.2023.10169957
Pengyu Cheng
The work path optimization of AUV manipulator based on PSO GA algorithm is a method to find the best work path of AUV manipulator. It is an extension of the original PSO GA algorithm, and uses the concept of pseudo Gaussian distribution to find a better solution under multiple local optimizations. The working path optimization of the underwater robot manipulator is to make the control of the underwater robot manipulator move along the working path with the minimum energy consumption. It is realized by using some mathematical techniques and algorithms. The main idea behind this technology is to find out the best point of the mobile underwater robot manipulator to minimize its total energy consumption. This technology is used for many purposes, such as motion planning, path planning and control design.. The main idea behind this algorithm is that if there are multiple local optima, the global optimal can be found by minimizing the total cost function of all local optima. This can be achieved by using Lagrange multiplication (LMM). In addition, this technology requires less computing power. In the actual working environment and experimental environment, the magnetic field interference may have an impact on the attitude parameters of AUV, which leads to the unsatisfactory control effect of AUV motion. In order to accurately measure the attitude of AUV system, this paper proposes an anti-jamming and fault-tolerant processing algorithm for MEMS inertial navigation system. This algorithm first estimates the signal residual, then dynamically adjusts the confidence level of local filter through the residual value, and finally fuses sensor signals with different working principles through the confidence level, which can significantly improve the stability and reliability of attitude feedback signals.
{"title":"Working Path Optimization of AUV Manipulator Based on PSO-GA Algorithm","authors":"Pengyu Cheng","doi":"10.1109/INCET57972.2023.10169957","DOIUrl":"https://doi.org/10.1109/INCET57972.2023.10169957","url":null,"abstract":"The work path optimization of AUV manipulator based on PSO GA algorithm is a method to find the best work path of AUV manipulator. It is an extension of the original PSO GA algorithm, and uses the concept of pseudo Gaussian distribution to find a better solution under multiple local optimizations. The working path optimization of the underwater robot manipulator is to make the control of the underwater robot manipulator move along the working path with the minimum energy consumption. It is realized by using some mathematical techniques and algorithms. The main idea behind this technology is to find out the best point of the mobile underwater robot manipulator to minimize its total energy consumption. This technology is used for many purposes, such as motion planning, path planning and control design.. The main idea behind this algorithm is that if there are multiple local optima, the global optimal can be found by minimizing the total cost function of all local optima. This can be achieved by using Lagrange multiplication (LMM). In addition, this technology requires less computing power. In the actual working environment and experimental environment, the magnetic field interference may have an impact on the attitude parameters of AUV, which leads to the unsatisfactory control effect of AUV motion. In order to accurately measure the attitude of AUV system, this paper proposes an anti-jamming and fault-tolerant processing algorithm for MEMS inertial navigation system. This algorithm first estimates the signal residual, then dynamically adjusts the confidence level of local filter through the residual value, and finally fuses sensor signals with different working principles through the confidence level, which can significantly improve the stability and reliability of attitude feedback signals.","PeriodicalId":403008,"journal":{"name":"2023 4th International Conference for Emerging Technology (INCET)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122299950","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 : 2023-05-26DOI: 10.1109/INCET57972.2023.10170179
Satyabrata Sahoo, S. Swain, Ritesh Dash
Electricity price volatility directly affects the deregulated electricity market where each market player is trying to sell their power with minimum cost. Hence effective price forecasting plays an important role for stability of electricity market and effective management of the interconnected power system network. The uncertainty in load demand and the distributed energy resources also directly affects the electricity price and the operational cost. The serious consequences of price dynamics can be avoided by designing more effective and accurate price forecasting models. This study compares three different intelligent techniques for unit price forecasting using machine learning. The three different artificial intelligent techniques are Support vector machine (SVM), Random forest and decision trees. As per the results obtained from the three models, all three models are effective for electricity price forecasting, but SVM model gives better performance than other two in terms of root mean square error.
{"title":"A Comparision Study of Machine Learning Methods for Unit Price Estimation in Smartgrid","authors":"Satyabrata Sahoo, S. Swain, Ritesh Dash","doi":"10.1109/INCET57972.2023.10170179","DOIUrl":"https://doi.org/10.1109/INCET57972.2023.10170179","url":null,"abstract":"Electricity price volatility directly affects the deregulated electricity market where each market player is trying to sell their power with minimum cost. Hence effective price forecasting plays an important role for stability of electricity market and effective management of the interconnected power system network. The uncertainty in load demand and the distributed energy resources also directly affects the electricity price and the operational cost. The serious consequences of price dynamics can be avoided by designing more effective and accurate price forecasting models. This study compares three different intelligent techniques for unit price forecasting using machine learning. The three different artificial intelligent techniques are Support vector machine (SVM), Random forest and decision trees. As per the results obtained from the three models, all three models are effective for electricity price forecasting, but SVM model gives better performance than other two in terms of root mean square error.","PeriodicalId":403008,"journal":{"name":"2023 4th International Conference for Emerging Technology (INCET)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128406596","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 : 2023-05-26DOI: 10.1109/INCET57972.2023.10170390
R. Krishnamoorthy, K. Kaliyamurthie
New opportunities for effective patient data management have emerged as a result of introduction of electronic health records (EHRs). By utilizing ML to mine digital patient record datasets, for instance, preventative rather than reactive medical practice is feasible. EHR is vulnerable to both insider and external threats due to sensitive nature of data, but security applications typically face the network's outer perimeter. Using deep learning methods, this study aims to enhance cloud data storage and malicious data detection. Blockchain trust based authentication is used to improve security-based cloud data storage in this study. After that, fuzzy rule Bayesian discriminant analysis is used to find malicious data. Utilizing results of malware analysis as well as detection and ML methods to evaluate difference in correlation symmetry, it was demonstrated that it was possible to detect harmful traffic on computer systems, thereby increasing network security. Data transmission rate, random accuracy, computation cost, communication overhead, mean average precision, and specificity are all examined in the experimental analysis for various electronic medical record datasets.
{"title":"Blockchain Trust based Authentication Protocol with Malicious Data Analysis Using Deep Learning Architectures: Electronic Medical Record Application","authors":"R. Krishnamoorthy, K. Kaliyamurthie","doi":"10.1109/INCET57972.2023.10170390","DOIUrl":"https://doi.org/10.1109/INCET57972.2023.10170390","url":null,"abstract":"New opportunities for effective patient data management have emerged as a result of introduction of electronic health records (EHRs). By utilizing ML to mine digital patient record datasets, for instance, preventative rather than reactive medical practice is feasible. EHR is vulnerable to both insider and external threats due to sensitive nature of data, but security applications typically face the network's outer perimeter. Using deep learning methods, this study aims to enhance cloud data storage and malicious data detection. Blockchain trust based authentication is used to improve security-based cloud data storage in this study. After that, fuzzy rule Bayesian discriminant analysis is used to find malicious data. Utilizing results of malware analysis as well as detection and ML methods to evaluate difference in correlation symmetry, it was demonstrated that it was possible to detect harmful traffic on computer systems, thereby increasing network security. Data transmission rate, random accuracy, computation cost, communication overhead, mean average precision, and specificity are all examined in the experimental analysis for various electronic medical record datasets.","PeriodicalId":403008,"journal":{"name":"2023 4th International Conference for Emerging Technology (INCET)","volume":"836 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128984943","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 : 2023-05-26DOI: 10.1109/INCET57972.2023.10170274
Rajesh Kumar C, Aroul Canessane R
Cloud computing has emerged as a technology behemoth with applications in a wide range of fields. When data is being migrated from offline data centres and stored in multiple cloud environments part of the control is always with the Cloud Service Providers(CSPs) leads to security concerns. The data stored in the cloud may sometimes be compromised even though the CSPs may take precautions to avoid such situations. In this paper, we discuss securely storing the data using the data dispersion technique by breaking the data into multiple segments and combining it with encryption along with replication. The division of data and storing it in the cloud helps in protecting the complete data even if an attacker tries to access the data it will not be easy for him to make sense of the retrieved data because the data is already being encrypted and combined with dispersion and replication adds to the complexity of retrieval. Security is achieved as the dispersed data is spread across multiple locations which makes it difficult for an attacker to get all the segments. In most scenarios be able it depends on traditional encryption techniques alone to protect the data. Here, We propose focusing more on how data is stored in the cloud to relieve the system of costly computational methodologies. In this strategy, the trade-off between security and the data retrieval time must also be considered.
{"title":"Securing Data storage in Cloud after Migration using Immutable Data Dispersion","authors":"Rajesh Kumar C, Aroul Canessane R","doi":"10.1109/INCET57972.2023.10170274","DOIUrl":"https://doi.org/10.1109/INCET57972.2023.10170274","url":null,"abstract":"Cloud computing has emerged as a technology behemoth with applications in a wide range of fields. When data is being migrated from offline data centres and stored in multiple cloud environments part of the control is always with the Cloud Service Providers(CSPs) leads to security concerns. The data stored in the cloud may sometimes be compromised even though the CSPs may take precautions to avoid such situations. In this paper, we discuss securely storing the data using the data dispersion technique by breaking the data into multiple segments and combining it with encryption along with replication. The division of data and storing it in the cloud helps in protecting the complete data even if an attacker tries to access the data it will not be easy for him to make sense of the retrieved data because the data is already being encrypted and combined with dispersion and replication adds to the complexity of retrieval. Security is achieved as the dispersed data is spread across multiple locations which makes it difficult for an attacker to get all the segments. In most scenarios be able it depends on traditional encryption techniques alone to protect the data. Here, We propose focusing more on how data is stored in the cloud to relieve the system of costly computational methodologies. In this strategy, the trade-off between security and the data retrieval time must also be considered.","PeriodicalId":403008,"journal":{"name":"2023 4th International Conference for Emerging Technology (INCET)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129262617","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 : 2023-05-26DOI: 10.1109/INCET57972.2023.10170301
Xikang Du
The energy-saving marine garbage collection algorithm and system based on machine vision is a system that provides real-time information of marine garbage collection. The system can be used to measure the amount of garbage in water, calculate the percentage of garbage collected by automatic mechanism, and predict its return rate. It also contributes to making all ocean related actions more efficient and effective. It is based on machine vision technology. The algorithm can identify marine debris and other objects in the water, including ships, buoys and fishing nets. The system will help reduce marine litter by up to 90 per cent. The main goal of the algorithm is to reduce the amount of garbage dumped into the ocean. This will also help to save energy by reducing the amount of energy used to treat such wastes.
{"title":"Energy saving Ocean Garbage Collection Return Algorithm and System Based on Machine Vision","authors":"Xikang Du","doi":"10.1109/INCET57972.2023.10170301","DOIUrl":"https://doi.org/10.1109/INCET57972.2023.10170301","url":null,"abstract":"The energy-saving marine garbage collection algorithm and system based on machine vision is a system that provides real-time information of marine garbage collection. The system can be used to measure the amount of garbage in water, calculate the percentage of garbage collected by automatic mechanism, and predict its return rate. It also contributes to making all ocean related actions more efficient and effective. It is based on machine vision technology. The algorithm can identify marine debris and other objects in the water, including ships, buoys and fishing nets. The system will help reduce marine litter by up to 90 per cent. The main goal of the algorithm is to reduce the amount of garbage dumped into the ocean. This will also help to save energy by reducing the amount of energy used to treat such wastes.","PeriodicalId":403008,"journal":{"name":"2023 4th International Conference for Emerging Technology (INCET)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129884263","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 : 2023-05-26DOI: 10.1109/INCET57972.2023.10169997
Mohammed Tahmid Hossain, Afra Hossain, Sabrina Masum Meem, Md Fahad Monir, Md Saef Ullah Miah, Talha Bin Sarwar
Over the past few decades, air pollution has emerged as a significant environmental hazard, causing premature deaths in Southeast Asia. The proliferation of industrialization and deforestation has resulted in an alarming increase in pollution levels. However, the COVID-19 pandemic has significantly reduced the amount of volatile organic compounds and toxic gases in the air due to the decrease in human activity caused by lockdowns and restrictions. This study aims to investigate the air quality in various geographical areas of Bangladesh, comparing the air quality index (AQI) during different lockdown periods to equivalent eight-year time spans in 10 of the country’s busiest cities. This study demonstrates a strong correlation between the rapid and widespread dispersion of COVID-19 and air pollution reduction in Bangladesh. In addition, we evaluated the performance of Support Vector Regression (SVR) in AQI forecasting using the time series dataset. The results can help improve machine learning and deep learning models for accurate AQI forecasting. This study contributes to developing effective policies and strategies for reducing air pollution in Bangladesh and other countries facing similar challenges.
{"title":"Impact of COVID-19 Lockdowns on Air Quality in Bangladesh: Analysis and AQI Forecasting with Support Vector Regression","authors":"Mohammed Tahmid Hossain, Afra Hossain, Sabrina Masum Meem, Md Fahad Monir, Md Saef Ullah Miah, Talha Bin Sarwar","doi":"10.1109/INCET57972.2023.10169997","DOIUrl":"https://doi.org/10.1109/INCET57972.2023.10169997","url":null,"abstract":"Over the past few decades, air pollution has emerged as a significant environmental hazard, causing premature deaths in Southeast Asia. The proliferation of industrialization and deforestation has resulted in an alarming increase in pollution levels. However, the COVID-19 pandemic has significantly reduced the amount of volatile organic compounds and toxic gases in the air due to the decrease in human activity caused by lockdowns and restrictions. This study aims to investigate the air quality in various geographical areas of Bangladesh, comparing the air quality index (AQI) during different lockdown periods to equivalent eight-year time spans in 10 of the country’s busiest cities. This study demonstrates a strong correlation between the rapid and widespread dispersion of COVID-19 and air pollution reduction in Bangladesh. In addition, we evaluated the performance of Support Vector Regression (SVR) in AQI forecasting using the time series dataset. The results can help improve machine learning and deep learning models for accurate AQI forecasting. This study contributes to developing effective policies and strategies for reducing air pollution in Bangladesh and other countries facing similar challenges.","PeriodicalId":403008,"journal":{"name":"2023 4th International Conference for Emerging Technology (INCET)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130489197","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 : 2023-05-26DOI: 10.1109/INCET57972.2023.10170151
Snehal R. Rathi, Samkit Oswal, Ayushi Ahuja
Academic Emotion Detection is fundamentally a system for detecting emotions. The system's main goal was to identify feelings expressed while attending online lectures during the COVID-19 epidemic. The topic Academic Emotion Detection using Machine Learning focuses on utilizing machine learning and deep learning to identify human face emotions in light of the shift to online learning.Our research has a limited scope, it focuses on four academic emotions: confusion, boredom, engagement, and frustration. A person may experience a wide range of other emotions as well. Here, we have used CNN and Deep LSTM for the prediction of said four emotions and it has been observed it increases the accuracy of prediction and effectiveness. We even incorporated a portion of a questionnaire into our research to compare our results with genuine human experiences.Concurrent Neural Network (CNN), Long-Short Term Memory (LSTM), and Recurrent Neural Network (RNN) are three different algorithms from the deep learning area that we have used in this study to examine how they operate and identify similarities and differences.
{"title":"A Coherent Way of Detecting Learner’s Academic Emotions via Live Camera Using CNN and Deep LSTM","authors":"Snehal R. Rathi, Samkit Oswal, Ayushi Ahuja","doi":"10.1109/INCET57972.2023.10170151","DOIUrl":"https://doi.org/10.1109/INCET57972.2023.10170151","url":null,"abstract":"Academic Emotion Detection is fundamentally a system for detecting emotions. The system's main goal was to identify feelings expressed while attending online lectures during the COVID-19 epidemic. The topic Academic Emotion Detection using Machine Learning focuses on utilizing machine learning and deep learning to identify human face emotions in light of the shift to online learning.Our research has a limited scope, it focuses on four academic emotions: confusion, boredom, engagement, and frustration. A person may experience a wide range of other emotions as well. Here, we have used CNN and Deep LSTM for the prediction of said four emotions and it has been observed it increases the accuracy of prediction and effectiveness. We even incorporated a portion of a questionnaire into our research to compare our results with genuine human experiences.Concurrent Neural Network (CNN), Long-Short Term Memory (LSTM), and Recurrent Neural Network (RNN) are three different algorithms from the deep learning area that we have used in this study to examine how they operate and identify similarities and differences.","PeriodicalId":403008,"journal":{"name":"2023 4th International Conference for Emerging Technology (INCET)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131078372","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：