Pub Date : 2020-12-16DOI: 10.1109/PuneCon50868.2020.9362475
S. Jaiswal, Ayush Jain, G. Nandi
Recognizing human emotion is a complex task and is being researched upon since couple of decades. The problem has still gained popularity because of its need in various domains, when it comes to human computer interaction or human robot interaction. As per researchers, human predict other persons state of mind by observing various parameters, 70% of them being non-verbal. Human have emotions embedded in their speech, pose, gesture, context, facial expressions, and even the past history of conversation or situation. These all sub problems can be beautifully solved using learning based techniques. Predicting emotion in multi party audio based conversation aids complexity to the problem, which needs to predict intent of speech, culture, accent of talking, gender and many other diversities. There are various attempts made by researchers to classify human audio into required classes, using Support Vector Machine model, Long Short Term Memeory (LSTM) and bi-LSTM on audio input. We propose an image based emotional classification approach for an audio conversation. Spectrogram of an audio signal plotted as an image is used as a input to Convolutional Neural Network model obtaining the pattern for classification. The proposed approach is able to provide an accuracy of around 86% on test dataset, which is considerable improvement over state of the art models.
{"title":"Image based Emotional State Prediction from Multiparty Audio Conversation","authors":"S. Jaiswal, Ayush Jain, G. Nandi","doi":"10.1109/PuneCon50868.2020.9362475","DOIUrl":"https://doi.org/10.1109/PuneCon50868.2020.9362475","url":null,"abstract":"Recognizing human emotion is a complex task and is being researched upon since couple of decades. The problem has still gained popularity because of its need in various domains, when it comes to human computer interaction or human robot interaction. As per researchers, human predict other persons state of mind by observing various parameters, 70% of them being non-verbal. Human have emotions embedded in their speech, pose, gesture, context, facial expressions, and even the past history of conversation or situation. These all sub problems can be beautifully solved using learning based techniques. Predicting emotion in multi party audio based conversation aids complexity to the problem, which needs to predict intent of speech, culture, accent of talking, gender and many other diversities. There are various attempts made by researchers to classify human audio into required classes, using Support Vector Machine model, Long Short Term Memeory (LSTM) and bi-LSTM on audio input. We propose an image based emotional classification approach for an audio conversation. Spectrogram of an audio signal plotted as an image is used as a input to Convolutional Neural Network model obtaining the pattern for classification. The proposed approach is able to provide an accuracy of around 86% on test dataset, which is considerable improvement over state of the art models.","PeriodicalId":368862,"journal":{"name":"2020 IEEE Pune Section International Conference (PuneCon)","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130621531","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 : 2020-12-16DOI: 10.1109/PuneCon50868.2020.9362386
Rushali R. Thakkar, Y. Rao, Rajendra R.Sawant
Electrical equivalent circuit models of battery helps us to understand the behavior in terms of its electrical characteristics, charging status and battery capacity to improve the system performance and increase the overall efficiency. In this paper different models of lithium-ion battery are discussed and their performance analysis is studied along with the benefits and demerits which will help us to select an ideal model which will suit best to a power electronics application. It is also observed that accurate electrical equivalent model is best suited for power applications as it takes into account the battery life time in its model. Charging and discharging characteristics of an ideal lithium-ion battery model are plotted using matlab to match the performance with the battery model specifications of lithium ion battery.
{"title":"Performance Analysis of Electrical Equivalent Circuit Models of Lithium-ion Battery","authors":"Rushali R. Thakkar, Y. Rao, Rajendra R.Sawant","doi":"10.1109/PuneCon50868.2020.9362386","DOIUrl":"https://doi.org/10.1109/PuneCon50868.2020.9362386","url":null,"abstract":"Electrical equivalent circuit models of battery helps us to understand the behavior in terms of its electrical characteristics, charging status and battery capacity to improve the system performance and increase the overall efficiency. In this paper different models of lithium-ion battery are discussed and their performance analysis is studied along with the benefits and demerits which will help us to select an ideal model which will suit best to a power electronics application. It is also observed that accurate electrical equivalent model is best suited for power applications as it takes into account the battery life time in its model. Charging and discharging characteristics of an ideal lithium-ion battery model are plotted using matlab to match the performance with the battery model specifications of lithium ion battery.","PeriodicalId":368862,"journal":{"name":"2020 IEEE Pune Section International Conference (PuneCon)","volume":"108 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133659387","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 : 2020-12-16DOI: 10.1109/PuneCon50868.2020.9362383
Disha Gangadia, Varsha Chamaria, V. Doshi, Jigyasa Gandhi
People with speech and hearing disabilities approximately constitute 1 percentage of the total Indian population. A person who is hearing and speech impaired is not able to compete or work with a normal person in a normal environment because of the lack of a proper communication medium.Sign Language is used for communication amongst them. Sign Language is the most natural and expressive way for the hearing and speech impaired. This paper proposes a method that recognizes Sign Language and converts it to normal text and speech for fast and improved communication amongst them and also with others. The focus is on the Indian Sign Language (ISL) specifically as there is no substantial work on ISL rendering the above requirements for these people.The paper focuses on developing a real-time hands-on system that takes video inputs of gestures in the specified ROI and performs gesture recognition using various feature extraction techniques and Hybrid-CNN model trained using the ISL database created. The correctly identified gesture tokens are sent to a Rule-Based Grammar and for Web Search query to generate various sentences and a Multi-Headed BERT grammar corrector provides grammatically precise and correct sentences as the final output.
{"title":"Indian Sign Language Interpretation and Sentence Formation","authors":"Disha Gangadia, Varsha Chamaria, V. Doshi, Jigyasa Gandhi","doi":"10.1109/PuneCon50868.2020.9362383","DOIUrl":"https://doi.org/10.1109/PuneCon50868.2020.9362383","url":null,"abstract":"People with speech and hearing disabilities approximately constitute 1 percentage of the total Indian population. A person who is hearing and speech impaired is not able to compete or work with a normal person in a normal environment because of the lack of a proper communication medium.Sign Language is used for communication amongst them. Sign Language is the most natural and expressive way for the hearing and speech impaired. This paper proposes a method that recognizes Sign Language and converts it to normal text and speech for fast and improved communication amongst them and also with others. The focus is on the Indian Sign Language (ISL) specifically as there is no substantial work on ISL rendering the above requirements for these people.The paper focuses on developing a real-time hands-on system that takes video inputs of gestures in the specified ROI and performs gesture recognition using various feature extraction techniques and Hybrid-CNN model trained using the ISL database created. The correctly identified gesture tokens are sent to a Rule-Based Grammar and for Web Search query to generate various sentences and a Multi-Headed BERT grammar corrector provides grammatically precise and correct sentences as the final output.","PeriodicalId":368862,"journal":{"name":"2020 IEEE Pune Section International Conference (PuneCon)","volume":"726 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129550216","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 : 2020-12-16DOI: 10.1109/PuneCon50868.2020.9362360
Rashmi Lad, P. Metkewar
Machine learning and artificial neural network is a growing field in medical imaging or neuroimaging in the present decade. Structural and functional neuroimaging is involved in the investigation of diagnosis of brain tumor and mental illness. To acquire the knowledge from previous experience and perception is called learning. Supervised and unsupervised machine learning algorithm also works on the same principles. It trains neuroimaging techniques like fMRI, EEG, MEG & PET data to extract features from the existing information and then predicts or makes decision that are useful for diagnoses in the medical field. The objective of this study is to give overview of machine learning toolbox that is used for analyzing the neuroimaging data without the deep knowledge of programming languages. These entire machine learning tools helps the experts, researchers for further investigation in the field of neuroimaging data.
{"title":"Review of Machine Learning Classifier Toolbox of Neuroimaging Data","authors":"Rashmi Lad, P. Metkewar","doi":"10.1109/PuneCon50868.2020.9362360","DOIUrl":"https://doi.org/10.1109/PuneCon50868.2020.9362360","url":null,"abstract":"Machine learning and artificial neural network is a growing field in medical imaging or neuroimaging in the present decade. Structural and functional neuroimaging is involved in the investigation of diagnosis of brain tumor and mental illness. To acquire the knowledge from previous experience and perception is called learning. Supervised and unsupervised machine learning algorithm also works on the same principles. It trains neuroimaging techniques like fMRI, EEG, MEG & PET data to extract features from the existing information and then predicts or makes decision that are useful for diagnoses in the medical field. The objective of this study is to give overview of machine learning toolbox that is used for analyzing the neuroimaging data without the deep knowledge of programming languages. These entire machine learning tools helps the experts, researchers for further investigation in the field of neuroimaging data.","PeriodicalId":368862,"journal":{"name":"2020 IEEE Pune Section International Conference (PuneCon)","volume":"116 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117223640","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}
India is the world’s largest democracy with nearly 900 million eligible voters. The election period in India spans over nearly six weeks for general elections and there is no alternative system working for eligible voters who are at outstations or willing to cast their vote but not able to do so due to location constraints. Moreover, there is no special provision made for NRI voter / overseas elector for whom it is difficult to vote in person at the polling station. Service voters have to use postal ballot and go through a tedious process to cast their vote and this process is also prone to human errors. Our system is an e-Voting system that will use fingerprint and face verification along with a combination of firebase-database and server-side file-system at its back-end. Our system is designed especially for NRI voters and Service voters for whom it is difficult to cast their votes through the existing system. It provides an efficient, convenient, and secure mechanism for voters to cast their votes. The design of this system will make the voting process more convenient and may, therefore, lead to improving the turnout.
{"title":"An Approach for e-Voting using Face and Fingerprint Verification","authors":"Shubham Shinde, Manas Shende, Jeet Shah, Harshdeep Shelar","doi":"10.1109/PuneCon50868.2020.9362470","DOIUrl":"https://doi.org/10.1109/PuneCon50868.2020.9362470","url":null,"abstract":"India is the world’s largest democracy with nearly 900 million eligible voters. The election period in India spans over nearly six weeks for general elections and there is no alternative system working for eligible voters who are at outstations or willing to cast their vote but not able to do so due to location constraints. Moreover, there is no special provision made for NRI voter / overseas elector for whom it is difficult to vote in person at the polling station. Service voters have to use postal ballot and go through a tedious process to cast their vote and this process is also prone to human errors. Our system is an e-Voting system that will use fingerprint and face verification along with a combination of firebase-database and server-side file-system at its back-end. Our system is designed especially for NRI voters and Service voters for whom it is difficult to cast their votes through the existing system. It provides an efficient, convenient, and secure mechanism for voters to cast their votes. The design of this system will make the voting process more convenient and may, therefore, lead to improving the turnout.","PeriodicalId":368862,"journal":{"name":"2020 IEEE Pune Section International Conference (PuneCon)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130325293","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 : 2020-12-16DOI: 10.1109/PuneCon50868.2020.9362387
Pushpalata, M. Sasikala
In India, traffic is growing multiple times quicker than the population. Wellbeing of streets has turned into a fundamental issue for governments and transport system for past twenty years. Due to increasing population, number of vehicles also have increased heavily, so vehicles traffic on street has turned into a fundamental issue. To beat these issues, in this article we study different traffic assessment techniques such as image processing by collecting the texture features, machine learning (Naive Bayes classifier, K-Nearest Neighborhood), Artificial Neural Network (ANN) and Deep learning approaches (Deep Neural Network, GSA-DNN). The framework is implemented in MATLAB 2015a and the results shows that it can be considerably applied to real time application for assessing the traffic.
{"title":"Real Time Traffic Assesment using Image Processing","authors":"Pushpalata, M. Sasikala","doi":"10.1109/PuneCon50868.2020.9362387","DOIUrl":"https://doi.org/10.1109/PuneCon50868.2020.9362387","url":null,"abstract":"In India, traffic is growing multiple times quicker than the population. Wellbeing of streets has turned into a fundamental issue for governments and transport system for past twenty years. Due to increasing population, number of vehicles also have increased heavily, so vehicles traffic on street has turned into a fundamental issue. To beat these issues, in this article we study different traffic assessment techniques such as image processing by collecting the texture features, machine learning (Naive Bayes classifier, K-Nearest Neighborhood), Artificial Neural Network (ANN) and Deep learning approaches (Deep Neural Network, GSA-DNN). The framework is implemented in MATLAB 2015a and the results shows that it can be considerably applied to real time application for assessing the traffic.","PeriodicalId":368862,"journal":{"name":"2020 IEEE Pune Section International Conference (PuneCon)","volume":"123 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132031999","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 : 2020-12-16DOI: 10.1109/PuneCon50868.2020.9362472
V. Prajwal
“Vehicle Detection and Collision Avoidance System in Hair Pin Curves” is a system which is used to detect the vehicles on one side of the hair pin curve and assist the vehicles on the other side of hair pin curve using traffic signals. Traffic Congestion and Accidents are very much common in hair pin curves due to lack of communication between the vehicles and zero visibility over the hair pin bends. Existing prototypes do offer solution for collision avoidance, but fails in effective traffic management which is most essential in hilly areas. The purpose of this paper is to intellectually detect and classify the vehicles, avoid collision using traffic signals and effective traffic management using vehicle class information. In this paper, we provide systematic approach to the above problem statement, outline the drawback of existing models and explain the need of effective traffic management in hairpin curves.
{"title":"Vehicle Detection and Collision Avoidance in Hairpin Curves","authors":"V. Prajwal","doi":"10.1109/PuneCon50868.2020.9362472","DOIUrl":"https://doi.org/10.1109/PuneCon50868.2020.9362472","url":null,"abstract":"“Vehicle Detection and Collision Avoidance System in Hair Pin Curves” is a system which is used to detect the vehicles on one side of the hair pin curve and assist the vehicles on the other side of hair pin curve using traffic signals. Traffic Congestion and Accidents are very much common in hair pin curves due to lack of communication between the vehicles and zero visibility over the hair pin bends. Existing prototypes do offer solution for collision avoidance, but fails in effective traffic management which is most essential in hilly areas. The purpose of this paper is to intellectually detect and classify the vehicles, avoid collision using traffic signals and effective traffic management using vehicle class information. In this paper, we provide systematic approach to the above problem statement, outline the drawback of existing models and explain the need of effective traffic management in hairpin curves.","PeriodicalId":368862,"journal":{"name":"2020 IEEE Pune Section International Conference (PuneCon)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131192406","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 : 2020-12-16DOI: 10.1109/PuneCon50868.2020.9362459
S. Bhagwat, Omkar Karlekar, S. Padalkar, Shruti Chaudhari, Ketki Kulkarni
From the packaging industry to the everyday household requirements of carrying and storing commodities, plastics have always dominated and have become a crucial part of our lives. But plastics causes many environmental hazards hence, people are searching for better replacement to plastics. One of the replacements can be paper which is environmentally friendly and can be recycled. Many researches are going on to increase the strength of the paper and to make paper more machinable to meet the need of manufacturing of packaging bags. Various parameters contribute to the strength of the paper such as CSF, consistency, beating time etc. We studied the parameters beating time and CSF of paper. The results for the tested samples through experimentations gave relationship between above mentioned two parameters, which will be useful in order to find proper beating time for required CSF value paper.
{"title":"Nature of CSF based on Beating Time in Fibre Reinforced Cotton Rag","authors":"S. Bhagwat, Omkar Karlekar, S. Padalkar, Shruti Chaudhari, Ketki Kulkarni","doi":"10.1109/PuneCon50868.2020.9362459","DOIUrl":"https://doi.org/10.1109/PuneCon50868.2020.9362459","url":null,"abstract":"From the packaging industry to the everyday household requirements of carrying and storing commodities, plastics have always dominated and have become a crucial part of our lives. But plastics causes many environmental hazards hence, people are searching for better replacement to plastics. One of the replacements can be paper which is environmentally friendly and can be recycled. Many researches are going on to increase the strength of the paper and to make paper more machinable to meet the need of manufacturing of packaging bags. Various parameters contribute to the strength of the paper such as CSF, consistency, beating time etc. We studied the parameters beating time and CSF of paper. The results for the tested samples through experimentations gave relationship between above mentioned two parameters, which will be useful in order to find proper beating time for required CSF value paper.","PeriodicalId":368862,"journal":{"name":"2020 IEEE Pune Section International Conference (PuneCon)","volume":"115 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115259721","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：