Pub Date : 2023-04-26DOI: 10.1109/ICICT57646.2023.10134026
S. Benedict, Rubiya Subair, Tanya Gupta, Vedanta S.P.
The step to the success of startups is through overcoming competitors by adopting software innovations that improve businesses. Serverless computing model, recently, has intrigued a sizable number of startup professionals belonging to various sectors, including financial or IoT-enabled application developers. One of the main flaws is its heavy dependency on cloud providers, which can still result in hefty pricing to startups and stalling functions in applications. This article proposes a penaltyenabled serverless architecture for startups. The architecture can boost the economy of startups and can analyze the serverlessoriented cost-saving options in applications. The penalty-oriented approach could enable cloud architects, developers, and startups, to rethink the utilization of serverless functions; to gleam of with future innovations.
{"title":"Penalty-Enabled Serverless Architecture for Cloud-based Startup Solutions","authors":"S. Benedict, Rubiya Subair, Tanya Gupta, Vedanta S.P.","doi":"10.1109/ICICT57646.2023.10134026","DOIUrl":"https://doi.org/10.1109/ICICT57646.2023.10134026","url":null,"abstract":"The step to the success of startups is through overcoming competitors by adopting software innovations that improve businesses. Serverless computing model, recently, has intrigued a sizable number of startup professionals belonging to various sectors, including financial or IoT-enabled application developers. One of the main flaws is its heavy dependency on cloud providers, which can still result in hefty pricing to startups and stalling functions in applications. This article proposes a penaltyenabled serverless architecture for startups. The architecture can boost the economy of startups and can analyze the serverlessoriented cost-saving options in applications. The penalty-oriented approach could enable cloud architects, developers, and startups, to rethink the utilization of serverless functions; to gleam of with future innovations.","PeriodicalId":126489,"journal":{"name":"2023 International Conference on Inventive Computation Technologies (ICICT)","volume":"302 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132897524","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}
The objective of this study is to create efficient machine learning (ML) models for the Heart Disease Prediction System (HDPS). This study shows how classification techniques for machine learning can forecast heart illness. To forecast and alert patients about potential cardiac abnormalities, machine learning (ML) models including Logistic Regression (LR), Decision Tree Classifiers (DTC), Random Forest Classifiers (RFC), Support Vector Classifiers (SVC), and voting classifiers are employed. Few challenges were encountered while developing the models, such as underfitting the model without balancing the data with decision tree classifier. The voting ensemble technique overcame the challenges and allowed for a generalized model on balanced data with high accuracy. The purpose of this investigation is to see whether the technique for properly forecasting heart disease is based on health factors. A voting classifier is made up of LR and RFC. Among all models, this voting classifier had the highest accuracy of 98.36%.
{"title":"Prediction of Heart Disease Based on Machine Learning Algorithms","authors":"Nirmala Koshiga, Premkumar Borugadda, Snehit Shaprapawad","doi":"10.1109/ICICT57646.2023.10134422","DOIUrl":"https://doi.org/10.1109/ICICT57646.2023.10134422","url":null,"abstract":"The objective of this study is to create efficient machine learning (ML) models for the Heart Disease Prediction System (HDPS). This study shows how classification techniques for machine learning can forecast heart illness. To forecast and alert patients about potential cardiac abnormalities, machine learning (ML) models including Logistic Regression (LR), Decision Tree Classifiers (DTC), Random Forest Classifiers (RFC), Support Vector Classifiers (SVC), and voting classifiers are employed. Few challenges were encountered while developing the models, such as underfitting the model without balancing the data with decision tree classifier. The voting ensemble technique overcame the challenges and allowed for a generalized model on balanced data with high accuracy. The purpose of this investigation is to see whether the technique for properly forecasting heart disease is based on health factors. A voting classifier is made up of LR and RFC. Among all models, this voting classifier had the highest accuracy of 98.36%.","PeriodicalId":126489,"journal":{"name":"2023 International Conference on Inventive Computation Technologies (ICICT)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132155575","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 : 2023-04-26DOI: 10.1109/ICICT57646.2023.10134149
Milagros Ortega, Jericho Quintanilla, Edward Ryan Ong, Raymond Marius Ramos, Carla Joy Trinidad
Customer retention is critical in the car insurance industry, marked by a 22% annual churn rate. Existing customer relationship management platforms primarily cater to e-commerce or online stores, neglecting the unique requirements of the insurance industry. Most insurers acknowledge their companies' need for a customer retention strategy. Despite losing approximately 16% of their customer base annually, insurance companies often prioritize acquisition over retention, even though acquiring a new client is 7–9 times costlier than retaining an existing one. This study focuses on developing a web-based system to optimize customer retention strategies for car insurance companies using data analysis techniques, such as cohort and churn analysis. Cohort Analysis segments customers based on insurance dates, enabling policy subscription renewal behavior tracking. Churn Analysis utilizes a predictive model to estimate customer attrition likelihood, enabling proactive issue resolution and improvement of satisfaction. A random forest model trained on a car insurance dataset achieved an 87.69% accuracy. Data visualizations generated from analyses and customer feedback reports facilitated extracting valuable data-driven insights to inform and refine retention strategies. The system's quality was assessed using ISO/IEC 25010, with an overall mean category rating of 4.58 and a Strongly Agreed rating, meeting established quality requirements and evaluation standards. This study underscores the significance of utilizing specialized data analysis techniques to optimize customer retention in the car insurance industry. By investing in tailored retention strategies, businesses can enhance customer experience, increase loyalty, and reduce churn, contributing to improved financial performance and long-term success.
{"title":"Asfalis: A Web-based System for Customer Retention Strategies Optimization of a Car Insurance Company Using Cohort and Churn Analysis","authors":"Milagros Ortega, Jericho Quintanilla, Edward Ryan Ong, Raymond Marius Ramos, Carla Joy Trinidad","doi":"10.1109/ICICT57646.2023.10134149","DOIUrl":"https://doi.org/10.1109/ICICT57646.2023.10134149","url":null,"abstract":"Customer retention is critical in the car insurance industry, marked by a 22% annual churn rate. Existing customer relationship management platforms primarily cater to e-commerce or online stores, neglecting the unique requirements of the insurance industry. Most insurers acknowledge their companies' need for a customer retention strategy. Despite losing approximately 16% of their customer base annually, insurance companies often prioritize acquisition over retention, even though acquiring a new client is 7–9 times costlier than retaining an existing one. This study focuses on developing a web-based system to optimize customer retention strategies for car insurance companies using data analysis techniques, such as cohort and churn analysis. Cohort Analysis segments customers based on insurance dates, enabling policy subscription renewal behavior tracking. Churn Analysis utilizes a predictive model to estimate customer attrition likelihood, enabling proactive issue resolution and improvement of satisfaction. A random forest model trained on a car insurance dataset achieved an 87.69% accuracy. Data visualizations generated from analyses and customer feedback reports facilitated extracting valuable data-driven insights to inform and refine retention strategies. The system's quality was assessed using ISO/IEC 25010, with an overall mean category rating of 4.58 and a Strongly Agreed rating, meeting established quality requirements and evaluation standards. This study underscores the significance of utilizing specialized data analysis techniques to optimize customer retention in the car insurance industry. By investing in tailored retention strategies, businesses can enhance customer experience, increase loyalty, and reduce churn, contributing to improved financial performance and long-term success.","PeriodicalId":126489,"journal":{"name":"2023 International Conference on Inventive Computation Technologies (ICICT)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130431044","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 : 2023-04-26DOI: 10.1109/ICICT57646.2023.10134419
Madala Guru Brahmam, R. Vijay Anand
With sophisticated technologies in wireless communication and cloud environments, virtual machine data centers and their applications are exponentially increasing. Energy consumption and impact on environmental factors play a significant role in the design and implementation of cloud platforms. Virtualization is a mode of operation in a cloud to simplify and reduce the workload of data centers through optimized resource utilization and energy bandwidth utilization. Cloud technologies facilitate the virtualization model by migrating content from physical data centers to virtual data centers with a trivial suspension of services. Multiple virtual machines can be hosted on a physical machine space, reducing the actual energy consumption of physical devices. The process is termed to be server consolidation for conserving the energy demand. Server consolidation can be achieved through renowned techniques, accommodating various parameters and conditions. The purpose of consolidations is to eliminate the dependency on hardware underlying the overall architecture. The available migration techniques are categorized into manner, distance, and granularity aspects for a better understanding. Non-Live migration techniques are listed briefly for comparison against a detailed perspective of live migration techniques. User mobility is a significant parameter for fog computing in VM migrations during cloud architecture deployment. Algorithmic approaches are listed in detail, predominantly used in server consolidation. The open challenges and other considerable issues are expressed in this survey article.
{"title":"An Investigation of Consolidating Virtual Servers and Data Centers based on Energy Consumptions using various Algorithms","authors":"Madala Guru Brahmam, R. Vijay Anand","doi":"10.1109/ICICT57646.2023.10134419","DOIUrl":"https://doi.org/10.1109/ICICT57646.2023.10134419","url":null,"abstract":"With sophisticated technologies in wireless communication and cloud environments, virtual machine data centers and their applications are exponentially increasing. Energy consumption and impact on environmental factors play a significant role in the design and implementation of cloud platforms. Virtualization is a mode of operation in a cloud to simplify and reduce the workload of data centers through optimized resource utilization and energy bandwidth utilization. Cloud technologies facilitate the virtualization model by migrating content from physical data centers to virtual data centers with a trivial suspension of services. Multiple virtual machines can be hosted on a physical machine space, reducing the actual energy consumption of physical devices. The process is termed to be server consolidation for conserving the energy demand. Server consolidation can be achieved through renowned techniques, accommodating various parameters and conditions. The purpose of consolidations is to eliminate the dependency on hardware underlying the overall architecture. The available migration techniques are categorized into manner, distance, and granularity aspects for a better understanding. Non-Live migration techniques are listed briefly for comparison against a detailed perspective of live migration techniques. User mobility is a significant parameter for fog computing in VM migrations during cloud architecture deployment. Algorithmic approaches are listed in detail, predominantly used in server consolidation. The open challenges and other considerable issues are expressed in this survey article.","PeriodicalId":126489,"journal":{"name":"2023 International Conference on Inventive Computation Technologies (ICICT)","volume":"97 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128828021","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 : 2023-04-26DOI: 10.1109/ICICT57646.2023.10134271
Priyanka Padhiyar, Kajal Parmar, Naina Parmar, S. Degadwala
Today's situation is risky because safety and monitoring must come first. It is defined as the action that is unusual in nature that deviates from the norm in a specific context. Exams are frequently monitored by invigilators manually or by video surveillance in exam halls all around the globe. Monitoring a test facility involves a lot of the personal and time. When using interdisciplinary approaches, the manual process of exam rooms is likely to be inaccurate. When created, an “Abnormal Behavior Detection Technique” would not only help identify hazardous actions, but also help reduce them. This study will cover a broad variety of strategies for outlier identification and classification, as well as their pros and downsides. The entire future of the any new unusual species uncovered in the exam auditorium would be purposeful after the experiment.
{"title":"Visual Distance Fraudulent Detection in Exam Hall using YOLO Detector","authors":"Priyanka Padhiyar, Kajal Parmar, Naina Parmar, S. Degadwala","doi":"10.1109/ICICT57646.2023.10134271","DOIUrl":"https://doi.org/10.1109/ICICT57646.2023.10134271","url":null,"abstract":"Today's situation is risky because safety and monitoring must come first. It is defined as the action that is unusual in nature that deviates from the norm in a specific context. Exams are frequently monitored by invigilators manually or by video surveillance in exam halls all around the globe. Monitoring a test facility involves a lot of the personal and time. When using interdisciplinary approaches, the manual process of exam rooms is likely to be inaccurate. When created, an “Abnormal Behavior Detection Technique” would not only help identify hazardous actions, but also help reduce them. This study will cover a broad variety of strategies for outlier identification and classification, as well as their pros and downsides. The entire future of the any new unusual species uncovered in the exam auditorium would be purposeful after the experiment.","PeriodicalId":126489,"journal":{"name":"2023 International Conference on Inventive Computation Technologies (ICICT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128869110","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}
Sleep quality refers to how well a person sleeps during the night. There are many factors that can affect sleep quality, including stress, anxiety, diet, exercise, and environmental factors such as noise and light levels. Good sleep quality is essential for overall quality of life. Poor sleep quality can have a number of detrimental impacts on one's physical as well as mental health. To improve sleep quality, it is important to establish a consistent sleep routine. There are many existing works on sleep quality prediction from wearable device data. Few of those analyzed sleep quality using the same algorithms used in this study. Several machine learning algorithms, however, have been proposed to reach great accuracy. Overfitting and insufficient data availability are common problems for these models. This research aims to increase the accuracy and performance of models for predicting sleep quality using wearable device data. To overcome these challenges, the objective of proposed work is to develop a sleep quality prediction system using a combination of feature selection techniques and machine learning models. The methodology is divided into three parts: data preprocessing, model building, and model evaluation. Three types of models were proposed in this study: single models, hybrid models, and an ensemble model for training and validation. The data acquired from a wearable IoT device was preprocessed by eliminating outliers and normalizing the data. The models were trained and evaluated based on accuracy, precision, recall, and F1-Score. The results show that the ensemble model was superior to all other models in terms of accuracy and F1-Score of 0.9897 and 0.9745 respectively. The hybrid models had lower performance metrics compared to the ensemble model, but still performed better than the individual models. This research provides insights into the potential of using wearable devices for sleep quality prediction and demonstrates the effectiveness of combining different models for improved accuracy and performance.
{"title":"A Hybrid and Ensemble Deep Learning Approach for Prediction and Analysis of Sleep Quality using Wearable IoT Device Data for Improved Accuracy","authors":"T. Jebaseeli, Chikkam Saranya, Shalem Preetham Gandu, Chikkam Swapna, Telagalapudi Sanjana Benjamin, Sharon Ekula","doi":"10.1109/ICICT57646.2023.10134451","DOIUrl":"https://doi.org/10.1109/ICICT57646.2023.10134451","url":null,"abstract":"Sleep quality refers to how well a person sleeps during the night. There are many factors that can affect sleep quality, including stress, anxiety, diet, exercise, and environmental factors such as noise and light levels. Good sleep quality is essential for overall quality of life. Poor sleep quality can have a number of detrimental impacts on one's physical as well as mental health. To improve sleep quality, it is important to establish a consistent sleep routine. There are many existing works on sleep quality prediction from wearable device data. Few of those analyzed sleep quality using the same algorithms used in this study. Several machine learning algorithms, however, have been proposed to reach great accuracy. Overfitting and insufficient data availability are common problems for these models. This research aims to increase the accuracy and performance of models for predicting sleep quality using wearable device data. To overcome these challenges, the objective of proposed work is to develop a sleep quality prediction system using a combination of feature selection techniques and machine learning models. The methodology is divided into three parts: data preprocessing, model building, and model evaluation. Three types of models were proposed in this study: single models, hybrid models, and an ensemble model for training and validation. The data acquired from a wearable IoT device was preprocessed by eliminating outliers and normalizing the data. The models were trained and evaluated based on accuracy, precision, recall, and F1-Score. The results show that the ensemble model was superior to all other models in terms of accuracy and F1-Score of 0.9897 and 0.9745 respectively. The hybrid models had lower performance metrics compared to the ensemble model, but still performed better than the individual models. This research provides insights into the potential of using wearable devices for sleep quality prediction and demonstrates the effectiveness of combining different models for improved accuracy and performance.","PeriodicalId":126489,"journal":{"name":"2023 International Conference on Inventive Computation Technologies (ICICT)","volume":"158 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123264382","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 : 2023-04-26DOI: 10.1109/ICICT57646.2023.10134062
V. Aishwarya, R. D. Babu, S. S. Adithya, Ainsely Jebaraj, Vignesh G R, Mahesh Veezhinathan
India is a diverse country filled with a rich culture and heritage. Bharatanatyam is one of the traditional classical dance forms of India. To achieve expertise in the art form proper maintenance of different postures for a long time is very important, which imposes immense physical demands on the body during training and performance. About 90% of the dancers experience recurrent pain prevalently in the lower extremities. In the proposed work, a survey was conducted among 30 dancers to get insights about dance-related pain and injuries. A computer vision model was built and used to detect and analyze the most significant posture in Bharatanatyam namely the Aramandi. Posture analysis on the pose was performed by sketching the nodal points. The x, y, and z coordinate values of the nodal points were extracted, and the angle formed between the joints of the knee and ankle was also determined. This extracted data was used to identify deviation from the proper form, thereby determining the proper posture. Also, an attempt has been devised to overcome the problem of key point estimation by using the Media Pipe pose algorithm. The results of the work confirmed that the extracted features were useful in providing accurate classification between the proper and improper Aramandi posture.
{"title":"Identification of Improper Posture in Female Bharatanatyam Dancers - A Computational Approach","authors":"V. Aishwarya, R. D. Babu, S. S. Adithya, Ainsely Jebaraj, Vignesh G R, Mahesh Veezhinathan","doi":"10.1109/ICICT57646.2023.10134062","DOIUrl":"https://doi.org/10.1109/ICICT57646.2023.10134062","url":null,"abstract":"India is a diverse country filled with a rich culture and heritage. Bharatanatyam is one of the traditional classical dance forms of India. To achieve expertise in the art form proper maintenance of different postures for a long time is very important, which imposes immense physical demands on the body during training and performance. About 90% of the dancers experience recurrent pain prevalently in the lower extremities. In the proposed work, a survey was conducted among 30 dancers to get insights about dance-related pain and injuries. A computer vision model was built and used to detect and analyze the most significant posture in Bharatanatyam namely the Aramandi. Posture analysis on the pose was performed by sketching the nodal points. The x, y, and z coordinate values of the nodal points were extracted, and the angle formed between the joints of the knee and ankle was also determined. This extracted data was used to identify deviation from the proper form, thereby determining the proper posture. Also, an attempt has been devised to overcome the problem of key point estimation by using the Media Pipe pose algorithm. The results of the work confirmed that the extracted features were useful in providing accurate classification between the proper and improper Aramandi posture.","PeriodicalId":126489,"journal":{"name":"2023 International Conference on Inventive Computation Technologies (ICICT)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121447445","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 : 2023-04-26DOI: 10.1109/ICICT57646.2023.10134493
K. Vinutha, Manoj Kumar Niranjan, J. Makhijani, B. Natarajan, V. Nirmala, T. R. Vijaya Lakshmi
Facial recognition is in use for the past decade there are many applications that needs facial expression to learn the human behaviour and emotions for certain activities. Facial recognition is in a development phase where many service providers use this feature to find the expression of the people on using their BlogSpot or website or reading any news article. This recognition of facial expression is highly possible with the help of machine learning technology. This research study has developed a facial expression recognizing algorithm using Python programming language with the help of Keras software package. This algorithm is purely based on machine learning approach that enables the programmer to process the facial image and convert it into data that is helpful in prediction of facial expression using the fuzzy logic technique. The fuzzy logic technique is a prediction method that helps programmer to predict the intermediate data by providing the initial and ending conditions. For enabling the facial recognition to process any system or a mobile device the algorithm needs permission to access the camera, once the onto the access is permitted the algorithm retrieves the image from the Vision sensor and with the help of image processing technology of the machine learning algorithm the program the program converts the data from the vision sensor into required facial expression and emotional content.
{"title":"A Machine Learning based Facial Expression and Emotion Recognition for Human Computer Interaction through Fuzzy Logic System","authors":"K. Vinutha, Manoj Kumar Niranjan, J. Makhijani, B. Natarajan, V. Nirmala, T. R. Vijaya Lakshmi","doi":"10.1109/ICICT57646.2023.10134493","DOIUrl":"https://doi.org/10.1109/ICICT57646.2023.10134493","url":null,"abstract":"Facial recognition is in use for the past decade there are many applications that needs facial expression to learn the human behaviour and emotions for certain activities. Facial recognition is in a development phase where many service providers use this feature to find the expression of the people on using their BlogSpot or website or reading any news article. This recognition of facial expression is highly possible with the help of machine learning technology. This research study has developed a facial expression recognizing algorithm using Python programming language with the help of Keras software package. This algorithm is purely based on machine learning approach that enables the programmer to process the facial image and convert it into data that is helpful in prediction of facial expression using the fuzzy logic technique. The fuzzy logic technique is a prediction method that helps programmer to predict the intermediate data by providing the initial and ending conditions. For enabling the facial recognition to process any system or a mobile device the algorithm needs permission to access the camera, once the onto the access is permitted the algorithm retrieves the image from the Vision sensor and with the help of image processing technology of the machine learning algorithm the program the program converts the data from the vision sensor into required facial expression and emotional content.","PeriodicalId":126489,"journal":{"name":"2023 International Conference on Inventive Computation Technologies (ICICT)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122261069","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 : 2023-04-26DOI: 10.1109/ICICT57646.2023.10133972
Oreeti Khajuria, Rakesh Kumar, Meenu Gupta
Facial Emotion Recognition (FER) is a technique to recognize one's emotional state using facial expression. However, facial expressions are an effective way to recognize human emotions in diverse contexts, but manual FER challenges as it also depends on one's state of mind. Convolutional Neural Network (CNN) models are applied to analyze facial expressions like happy, Sad, surprised, etc. From vocal information, it is challenging to analyze a person's behavior. This work proposes VGG-16 with a transfer learning model to recognize FER. This process assists in the recognition of the position and motion of facial muscles. FER has various steps in which data is pre-processed, features are extracted, and facial emotions are classified. Machine learning algorithm is being used by different researchers to extract the facial emotions but did not get optimal accuracy. So Deep Learning model is proposed i.e. pattern based to achieve more accuracy than the earlier one. The dataset used in this work is collected from the Kaggle repository, which consists of 35,887 samples, in which 28,821 were used for training and 7066 were used for validation. The results shows that proposed model achieves accuracy of 91 percent which is approx. 20 percent higher than tradition machine learning models.
{"title":"Facial Emotion Recognition using CNN and VGG-16","authors":"Oreeti Khajuria, Rakesh Kumar, Meenu Gupta","doi":"10.1109/ICICT57646.2023.10133972","DOIUrl":"https://doi.org/10.1109/ICICT57646.2023.10133972","url":null,"abstract":"Facial Emotion Recognition (FER) is a technique to recognize one's emotional state using facial expression. However, facial expressions are an effective way to recognize human emotions in diverse contexts, but manual FER challenges as it also depends on one's state of mind. Convolutional Neural Network (CNN) models are applied to analyze facial expressions like happy, Sad, surprised, etc. From vocal information, it is challenging to analyze a person's behavior. This work proposes VGG-16 with a transfer learning model to recognize FER. This process assists in the recognition of the position and motion of facial muscles. FER has various steps in which data is pre-processed, features are extracted, and facial emotions are classified. Machine learning algorithm is being used by different researchers to extract the facial emotions but did not get optimal accuracy. So Deep Learning model is proposed i.e. pattern based to achieve more accuracy than the earlier one. The dataset used in this work is collected from the Kaggle repository, which consists of 35,887 samples, in which 28,821 were used for training and 7066 were used for validation. The results shows that proposed model achieves accuracy of 91 percent which is approx. 20 percent higher than tradition machine learning models.","PeriodicalId":126489,"journal":{"name":"2023 International Conference on Inventive Computation Technologies (ICICT)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120943700","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 : 2023-04-26DOI: 10.1109/ICICT57646.2023.10134519
Akash S, D. V, M. S, R. Srikanth
Student behavior analysis is an important research area that aims to understand and improve student outcomes. Machine learning has emerged as a powerful tool for analyzing student behavior, allowing researchers to identify important patterns and predict future behavior. Further, student behavior analysis can help to identify individual student needs and preferences, allowing for personalized learning experiences that are tailored to the unique needs of each student. This can improve engagement and motivation, and help students reach their full potential. This study provides an overview of various methods for student behavior analysis using machine learning, including clustering, classification, time-series analysis, recommender systems, and natural language processing. Moreover, steps involved in using these methods, including data collection, preprocessing, feature engineering, model training, and model evaluation is elaborated. Furthermore, discussion on the architecture, and ethical considerations for using machine learning in student behavior analysis depicted. Finally, the article highlights the importance of carefully choosing the appropriate method for each research question and considering the potential impact of machine learning on students and society.
{"title":"Systematic Review on Real-Time Students Behavior Monitoring using Machine Learning","authors":"Akash S, D. V, M. S, R. Srikanth","doi":"10.1109/ICICT57646.2023.10134519","DOIUrl":"https://doi.org/10.1109/ICICT57646.2023.10134519","url":null,"abstract":"Student behavior analysis is an important research area that aims to understand and improve student outcomes. Machine learning has emerged as a powerful tool for analyzing student behavior, allowing researchers to identify important patterns and predict future behavior. Further, student behavior analysis can help to identify individual student needs and preferences, allowing for personalized learning experiences that are tailored to the unique needs of each student. This can improve engagement and motivation, and help students reach their full potential. This study provides an overview of various methods for student behavior analysis using machine learning, including clustering, classification, time-series analysis, recommender systems, and natural language processing. Moreover, steps involved in using these methods, including data collection, preprocessing, feature engineering, model training, and model evaluation is elaborated. Furthermore, discussion on the architecture, and ethical considerations for using machine learning in student behavior analysis depicted. Finally, the article highlights the importance of carefully choosing the appropriate method for each research question and considering the potential impact of machine learning on students and society.","PeriodicalId":126489,"journal":{"name":"2023 International Conference on Inventive Computation Technologies (ICICT)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116157199","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：