Pub Date : 2020-07-01DOI: 10.1109/ICCSP48568.2020.9182043
Alana Paul Cruz, A. Pradeep, Kavali Riya Sivasankar, K.S Krishnaveni
In our work we propose a machine learning model based on human bio signals to detect human stress. Detecting stress properly can help in preventing a large number of mental and physical scenarios which lead to abnormalities in cardiac rhythm or depression and more. In our work we selected ECG as the bio signal and extracted its features. The advantage of taking ECG as the bio signal is, information about respiratory signals EDR (ECG Derived Respiration) feature can be easily derived without any extra sensors. Among those unique features we chose ECG derived Respiration, Respiration Rate, QT interval. For training and validation of our new model we used Physionet’s “drivedb” database. Our proposed model uses Optimised Support Vector Machines (SVM) using decision trees. Our experimentation results show better accuracy in detecting stress
{"title":"A Decision Tree Optimised SVM Model for Stress Detection using Biosignals","authors":"Alana Paul Cruz, A. Pradeep, Kavali Riya Sivasankar, K.S Krishnaveni","doi":"10.1109/ICCSP48568.2020.9182043","DOIUrl":"https://doi.org/10.1109/ICCSP48568.2020.9182043","url":null,"abstract":"In our work we propose a machine learning model based on human bio signals to detect human stress. Detecting stress properly can help in preventing a large number of mental and physical scenarios which lead to abnormalities in cardiac rhythm or depression and more. In our work we selected ECG as the bio signal and extracted its features. The advantage of taking ECG as the bio signal is, information about respiratory signals EDR (ECG Derived Respiration) feature can be easily derived without any extra sensors. Among those unique features we chose ECG derived Respiration, Respiration Rate, QT interval. For training and validation of our new model we used Physionet’s “drivedb” database. Our proposed model uses Optimised Support Vector Machines (SVM) using decision trees. Our experimentation results show better accuracy in detecting stress","PeriodicalId":321133,"journal":{"name":"2020 International Conference on Communication and Signal Processing (ICCSP)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116595612","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 : 2020-07-01DOI: 10.1109/ICCSP48568.2020.9182189
Saumendra Kumar Mohapatra, S. Behera, M. Mohanty
Accurate and early diagnosis of cardiac disease is necessary to prevent the death rate. Support vector machine (SVM) is one of the most powerful data classification technique which has been used by the researchers for classifying different types of data. The authors in this paper have compared the performance of SVM with four different types of kernels for classifying cardiac data. The data has been collected from the University of California Irvine (UCI) machine learning repository. From the result, it can be noticed that SVM with the polynomial kernel is performing better as compared to the other three. The proposed result is also compared with some earlier works.
{"title":"A Comparative Analysis of Cardiac Data Classification using Support Vector Machine with Various Kernels","authors":"Saumendra Kumar Mohapatra, S. Behera, M. Mohanty","doi":"10.1109/ICCSP48568.2020.9182189","DOIUrl":"https://doi.org/10.1109/ICCSP48568.2020.9182189","url":null,"abstract":"Accurate and early diagnosis of cardiac disease is necessary to prevent the death rate. Support vector machine (SVM) is one of the most powerful data classification technique which has been used by the researchers for classifying different types of data. The authors in this paper have compared the performance of SVM with four different types of kernels for classifying cardiac data. The data has been collected from the University of California Irvine (UCI) machine learning repository. From the result, it can be noticed that SVM with the polynomial kernel is performing better as compared to the other three. The proposed result is also compared with some earlier works.","PeriodicalId":321133,"journal":{"name":"2020 International Conference on Communication and Signal Processing (ICCSP)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116788970","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 : 2020-07-01DOI: 10.1109/ICCSP48568.2020.9182342
Rukhiya Fahmidha, Sajeev K. Jose
The tracking procedure of vehicles and people on foot through computerized video as of now has quite a while of utilization and has situated both economically and scholastically. Video based vehicle and person on foot recognition innovation is an essential piece of insightful transportation framework. Vehicles and person on foot are to be followed, ordered and checked to guarantee better traffic control. The appropriate following of these can help us in keeping away from street mishaps to the most extreme. Congested roads can likewise be controlled to a degree by this video-following. This video following can even be reached out to create independent driving in vehicles.
{"title":"Vehicle and Pedestrian Video-tracking: A Review","authors":"Rukhiya Fahmidha, Sajeev K. Jose","doi":"10.1109/ICCSP48568.2020.9182342","DOIUrl":"https://doi.org/10.1109/ICCSP48568.2020.9182342","url":null,"abstract":"The tracking procedure of vehicles and people on foot through computerized video as of now has quite a while of utilization and has situated both economically and scholastically. Video based vehicle and person on foot recognition innovation is an essential piece of insightful transportation framework. Vehicles and person on foot are to be followed, ordered and checked to guarantee better traffic control. The appropriate following of these can help us in keeping away from street mishaps to the most extreme. Congested roads can likewise be controlled to a degree by this video-following. This video following can even be reached out to create independent driving in vehicles.","PeriodicalId":321133,"journal":{"name":"2020 International Conference on Communication and Signal Processing (ICCSP)","volume":"16 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120912691","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}
Cloud heralds a new era of computing. Cloud provides flexible, cost effective service. Cloud service is also referred as “On Demand Service” or “Pay as you go Service”. Mobile cloud computing is emerging branch of cloud computing which delivers services to mobile devices. As the smart phone usage has tremendously increased, the multimedia information such as pictures and video that is downloaded/uploaded from the cloud has also seen the rise. As our personal/sensitive information is with the third party, however, a significant question is, can we trust the cloud? There are many traditional security approaches are available to secure the data exchange between the users and the media cloud. But still there are instances of security breaches. This paper addresses the issues of security. Here we are proposing a hybrid encryption technique to secure the images. The scheme uses Elliptic Curve Cryptography to generate the secret key, which in turn used for DES and AES algorithms.
{"title":"A Comparative Analysis of Hybrid Encryption Technique for Images in the Cloud Environment","authors":"Pallavi Kulkarni, Rajashri Khanai, Gururaj Bindagi","doi":"10.1109/ICCSP48568.2020.9182153","DOIUrl":"https://doi.org/10.1109/ICCSP48568.2020.9182153","url":null,"abstract":"Cloud heralds a new era of computing. Cloud provides flexible, cost effective service. Cloud service is also referred as “On Demand Service” or “Pay as you go Service”. Mobile cloud computing is emerging branch of cloud computing which delivers services to mobile devices. As the smart phone usage has tremendously increased, the multimedia information such as pictures and video that is downloaded/uploaded from the cloud has also seen the rise. As our personal/sensitive information is with the third party, however, a significant question is, can we trust the cloud? There are many traditional security approaches are available to secure the data exchange between the users and the media cloud. But still there are instances of security breaches. This paper addresses the issues of security. Here we are proposing a hybrid encryption technique to secure the images. The scheme uses Elliptic Curve Cryptography to generate the secret key, which in turn used for DES and AES algorithms.","PeriodicalId":321133,"journal":{"name":"2020 International Conference on Communication and Signal Processing (ICCSP)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120935182","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 : 2020-07-01DOI: 10.1109/ICCSP48568.2020.9182104
K. Sankaran, K. Kavitha, S. Priya
In this paper, a new indexing and retrieval system for digital pictures has been presented with speech notes based on syllable-converted picture-like samples. The growth in reputation of digital camera spots in the direction of growing number of customers with huge album of digital images in their computers which includes gloss and retrieval, has become known as vital trouble in management of virtual photographs. Usually, customers must type such advanced content manually and repetitively to comment on their snap shots. Multidimensional scaling is used to identify n-best users to deal with recognition errors and is converted into an image-like sample. Though the availability of an integrated microphone in maximum virtual cameras, consumer can now articulate about their pictures onto the spot and records these observations into machine readable documents. Recently in automatic voice recognition technology, speech gloss and retrieval gives an option and predictable strategy for existing photograph ordering, recovery methods and supplanting the repetitive work of manual writing. In speech annotation and retrieval, a hybrid mechanism is utilized to assimilate picture-like styles, syllables, words and characters.
{"title":"Content Based Image Retrieval Process for Speech Annotated Digital Images","authors":"K. Sankaran, K. Kavitha, S. Priya","doi":"10.1109/ICCSP48568.2020.9182104","DOIUrl":"https://doi.org/10.1109/ICCSP48568.2020.9182104","url":null,"abstract":"In this paper, a new indexing and retrieval system for digital pictures has been presented with speech notes based on syllable-converted picture-like samples. The growth in reputation of digital camera spots in the direction of growing number of customers with huge album of digital images in their computers which includes gloss and retrieval, has become known as vital trouble in management of virtual photographs. Usually, customers must type such advanced content manually and repetitively to comment on their snap shots. Multidimensional scaling is used to identify n-best users to deal with recognition errors and is converted into an image-like sample. Though the availability of an integrated microphone in maximum virtual cameras, consumer can now articulate about their pictures onto the spot and records these observations into machine readable documents. Recently in automatic voice recognition technology, speech gloss and retrieval gives an option and predictable strategy for existing photograph ordering, recovery methods and supplanting the repetitive work of manual writing. In speech annotation and retrieval, a hybrid mechanism is utilized to assimilate picture-like styles, syllables, words and characters.","PeriodicalId":321133,"journal":{"name":"2020 International Conference on Communication and Signal Processing (ICCSP)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121114091","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 : 2020-07-01DOI: 10.1109/ICCSP48568.2020.9182297
Prateek Majagavi, A. Tigadi, S. Kulkarni
The increasing count of motor vehicles mainly in urban areas have become prominent reason for unhealthy environment and causing illness due to pollution. Systematic flow of vehicles will help in reduction of pollution. Use of technology is a solution in handling traffic, sensing pollutants like carbon dioxide and carbon monoxide in the pathway of transit will help in decision making for the traffic authorities as well as to the commuters. The proposed method is a stand-alone IoT system to measure few weather parameters at a dense location with heavy traffic and provide the corresponding live data. The system uses a low-power mini-computer Raspberry Pi 3B+. The various sensors are used to sense different parameters like temperature, pressure, carbon dioxide, carbon monoxide and humidity. The data collected by the Raspberry Pi is sent to the cloud and stored which can be viewed by anyone and anywhere at any time. Future measures can be taken using available recorded-data if there are unhealthy readings measured by the system set up at a location.
{"title":"Traffic Management by Monitoring Weather Parameters and Pollutants Remotely using Raspberry Pi","authors":"Prateek Majagavi, A. Tigadi, S. Kulkarni","doi":"10.1109/ICCSP48568.2020.9182297","DOIUrl":"https://doi.org/10.1109/ICCSP48568.2020.9182297","url":null,"abstract":"The increasing count of motor vehicles mainly in urban areas have become prominent reason for unhealthy environment and causing illness due to pollution. Systematic flow of vehicles will help in reduction of pollution. Use of technology is a solution in handling traffic, sensing pollutants like carbon dioxide and carbon monoxide in the pathway of transit will help in decision making for the traffic authorities as well as to the commuters. The proposed method is a stand-alone IoT system to measure few weather parameters at a dense location with heavy traffic and provide the corresponding live data. The system uses a low-power mini-computer Raspberry Pi 3B+. The various sensors are used to sense different parameters like temperature, pressure, carbon dioxide, carbon monoxide and humidity. The data collected by the Raspberry Pi is sent to the cloud and stored which can be viewed by anyone and anywhere at any time. Future measures can be taken using available recorded-data if there are unhealthy readings measured by the system set up at a location.","PeriodicalId":321133,"journal":{"name":"2020 International Conference on Communication and Signal Processing (ICCSP)","volume":"343 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126030685","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 : 2020-07-01DOI: 10.1109/ICCSP48568.2020.9182167
Inturi Meghana, J. Meghana, Ramesh Jayaraman
An implementation of smart attendance management system using Radio Frequency Identification (RFID) is presented to reduce time consuming, avoid malpractices and human errors during attendance taking process. In real time applications to reduce the human efforts there are many existing technologies in the world. Amongst the RFID is the most efficient and cost reducing technology, it uses wireless communication between the reader and the tag. It is needed for accurate attendance recording for all the sectors. The proposed technique is used to development of attendance simulation in any field using RFID that connected directly to the excel sheet. The performance of the smart attendance management system is found satisfactory with the proposed technique which is commonly used in all sectors.
{"title":"Smart Attendance Management System using Radio Frequency Identification","authors":"Inturi Meghana, J. Meghana, Ramesh Jayaraman","doi":"10.1109/ICCSP48568.2020.9182167","DOIUrl":"https://doi.org/10.1109/ICCSP48568.2020.9182167","url":null,"abstract":"An implementation of smart attendance management system using Radio Frequency Identification (RFID) is presented to reduce time consuming, avoid malpractices and human errors during attendance taking process. In real time applications to reduce the human efforts there are many existing technologies in the world. Amongst the RFID is the most efficient and cost reducing technology, it uses wireless communication between the reader and the tag. It is needed for accurate attendance recording for all the sectors. The proposed technique is used to development of attendance simulation in any field using RFID that connected directly to the excel sheet. The performance of the smart attendance management system is found satisfactory with the proposed technique which is commonly used in all sectors.","PeriodicalId":321133,"journal":{"name":"2020 International Conference on Communication and Signal Processing (ICCSP)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122346252","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 : 2020-07-01DOI: 10.1109/ICCSP48568.2020.9182447
U. Snekhalatha, Bhargavee Guhan, S. Sowmiya, T. Rajalakshmi
Heel fissures are a common foot condition that causes discomfort, pain and may lead to lower confidence levels. Hence people suffering from heel fissures generally seek some therapy for relief. Several methods of treatment are available for cracked heels. In this study, we have applied a traditional method of treating heel fissures, by soaking the feet in a warm water bath along with a few ingredients to smooth the skin. Thermal images of the heels were acquired and analyzed to determine whether there is a significant difference in the temperature of the heel fissures before and after therapy. Further, we applied image processing techniques for feature extractions and analysis. It was observed that there is a 2.2% decrease in the average temperature of the left heel, whereas in the right heel there is a 2.6% decrease in the average temperature. Hence, thermal imaging was used as a potential tool in the diagnosis of cracked heels and was found to be applicable for evaluation of the heel therapy process.
{"title":"Analysis of Heel Fissure Therapy using Thermal Imaging and Image Processing","authors":"U. Snekhalatha, Bhargavee Guhan, S. Sowmiya, T. Rajalakshmi","doi":"10.1109/ICCSP48568.2020.9182447","DOIUrl":"https://doi.org/10.1109/ICCSP48568.2020.9182447","url":null,"abstract":"Heel fissures are a common foot condition that causes discomfort, pain and may lead to lower confidence levels. Hence people suffering from heel fissures generally seek some therapy for relief. Several methods of treatment are available for cracked heels. In this study, we have applied a traditional method of treating heel fissures, by soaking the feet in a warm water bath along with a few ingredients to smooth the skin. Thermal images of the heels were acquired and analyzed to determine whether there is a significant difference in the temperature of the heel fissures before and after therapy. Further, we applied image processing techniques for feature extractions and analysis. It was observed that there is a 2.2% decrease in the average temperature of the left heel, whereas in the right heel there is a 2.6% decrease in the average temperature. Hence, thermal imaging was used as a potential tool in the diagnosis of cracked heels and was found to be applicable for evaluation of the heel therapy process.","PeriodicalId":321133,"journal":{"name":"2020 International Conference on Communication and Signal Processing (ICCSP)","volume":"160 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114243090","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 : 2020-07-01DOI: 10.1109/ICCSP48568.2020.9182350
Dhivyadharshini, B. Gopalakrishnan
The wireless nodes often share the information through communication channel with other wireless technologies. Since the transmission medium is an open medium, nodes must transmit the information in a secured manner and to achieve better transmission rates in the presence of static and dynamic interference. The FHSS technique plays a major role to mitigate interference. In FHSS, if the current hop is corrupted by the interference, the node can send the data successfully when it switch to another new channel. But, when number of channels corrupted by interference are more, then the performance of FHSS gets degraded. So to overcome this issue a Chaotic Frequency Hopping (CFH) technique is used. The CFH selects the hopping channel based on the chaotic map. The CFH technique increases security in the presence of static and dynamic interference. In this paper, we performed a comparative analysis of FHSS and CFHSS in presence of different jammers.
{"title":"Comparative Analysis of FH and CFH Spread Spectrum Under Different Jammers","authors":"Dhivyadharshini, B. Gopalakrishnan","doi":"10.1109/ICCSP48568.2020.9182350","DOIUrl":"https://doi.org/10.1109/ICCSP48568.2020.9182350","url":null,"abstract":"The wireless nodes often share the information through communication channel with other wireless technologies. Since the transmission medium is an open medium, nodes must transmit the information in a secured manner and to achieve better transmission rates in the presence of static and dynamic interference. The FHSS technique plays a major role to mitigate interference. In FHSS, if the current hop is corrupted by the interference, the node can send the data successfully when it switch to another new channel. But, when number of channels corrupted by interference are more, then the performance of FHSS gets degraded. So to overcome this issue a Chaotic Frequency Hopping (CFH) technique is used. The CFH selects the hopping channel based on the chaotic map. The CFH technique increases security in the presence of static and dynamic interference. In this paper, we performed a comparative analysis of FHSS and CFHSS in presence of different jammers.","PeriodicalId":321133,"journal":{"name":"2020 International Conference on Communication and Signal Processing (ICCSP)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122191757","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 : 2020-07-01DOI: 10.1109/ICCSP48568.2020.9182362
B. V. Namrutha Sridhar, K. Mrinalini, P. Vijayalakshmi
In recent years, sentiment or emotion analysis has become a key research area due to its vast potential applications in getting insights from social media comments, marketing, political science, psychology, human-computer interaction, and artificial intelligence. Emotion analysis deals with identifying the emotions in any given data such as text, speech, or image. The current work proposes to identify and associate social media text to multiple emotions with varying degrees. The data collection and annotation process employed in the proposed work is a combination of manual and semi-supervised annotation method where each tweet is mapped to a six dimensional emotion vector. Totally six human emotions such as happy, sad, anger, disgust, surprise, and fear are considered for emotion-tagging. Word mover‘s distance (WMD) based on twitter word embeddings (word2vec) is proposed to develop a labelled dataset in the current work. A set of classifiers is developed on the labelled dataset to identify emotions at the tweet-level in any given text data. In the current work, KNN, tree-based, and neural network classifiers are developed.
{"title":"Data Annotation and Multi-Emotion Classification for Social Media Text","authors":"B. V. Namrutha Sridhar, K. Mrinalini, P. Vijayalakshmi","doi":"10.1109/ICCSP48568.2020.9182362","DOIUrl":"https://doi.org/10.1109/ICCSP48568.2020.9182362","url":null,"abstract":"In recent years, sentiment or emotion analysis has become a key research area due to its vast potential applications in getting insights from social media comments, marketing, political science, psychology, human-computer interaction, and artificial intelligence. Emotion analysis deals with identifying the emotions in any given data such as text, speech, or image. The current work proposes to identify and associate social media text to multiple emotions with varying degrees. The data collection and annotation process employed in the proposed work is a combination of manual and semi-supervised annotation method where each tweet is mapped to a six dimensional emotion vector. Totally six human emotions such as happy, sad, anger, disgust, surprise, and fear are considered for emotion-tagging. Word mover‘s distance (WMD) based on twitter word embeddings (word2vec) is proposed to develop a labelled dataset in the current work. A set of classifiers is developed on the labelled dataset to identify emotions at the tweet-level in any given text data. In the current work, KNN, tree-based, and neural network classifiers are developed.","PeriodicalId":321133,"journal":{"name":"2020 International Conference on Communication and Signal Processing (ICCSP)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117009575","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：