Pub Date : 2020-06-01DOI: 10.1109/incet49848.2020.9154054
Meria Mathew, J. Jacob, R. Ramchand
In this paper, a backstepping controller with state estimator is proposed to achieve formation acquisition of multi robotic vehicles. On achieving formation acquisition, the multi robotic vehicles are expected to attain a predefined geometrical shape. Rigid graph approach with backstepping technique is exploited to design a formation controller. A state estimator is then developed through unscented Kalman filter (UKF) algorithm to filter out noises (process noise, measurement noise) in the system. The output of the estimator is given to the controller thereby making the controlled system robust to noises. The stability of controlled system is analysed using Lyapunov theory. Simulation results validate the effectiveness of the proposed controller and state estimator in exhibiting superior performance in the presence of process and measurement noise.
{"title":"Formation Acquisition of Multi Robotic Vehicles with Unscented Kalman Filter Based Noise Filtering","authors":"Meria Mathew, J. Jacob, R. Ramchand","doi":"10.1109/incet49848.2020.9154054","DOIUrl":"https://doi.org/10.1109/incet49848.2020.9154054","url":null,"abstract":"In this paper, a backstepping controller with state estimator is proposed to achieve formation acquisition of multi robotic vehicles. On achieving formation acquisition, the multi robotic vehicles are expected to attain a predefined geometrical shape. Rigid graph approach with backstepping technique is exploited to design a formation controller. A state estimator is then developed through unscented Kalman filter (UKF) algorithm to filter out noises (process noise, measurement noise) in the system. The output of the estimator is given to the controller thereby making the controlled system robust to noises. The stability of controlled system is analysed using Lyapunov theory. Simulation results validate the effectiveness of the proposed controller and state estimator in exhibiting superior performance in the presence of process and measurement noise.","PeriodicalId":174411,"journal":{"name":"2020 International Conference for Emerging Technology (INCET)","volume":"413 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132105922","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 : 2020-06-01DOI: 10.1109/INCET49848.2020.9154173
Aiman Jan, S. A. Parah, B. A. Malik
Information sharing through internet has becoming challenge due to high-risk factor of attacks to the information being transferred. In this paper, a novel image-encryption edge based Image steganography technique is proposed. The proposed algorithm uses logistic map for encrypting the information prior to transmission. Laplacian of Gaussian (LoG) edge operator is used to find edge areas of the colored-cover-image. Simulation analysis demonstrates that the proposed algorithm has a good amount of payload along with better results of security analysis. The proposed scheme is compared with the existing-methods.
{"title":"A Novel Laplacian of Gaussian (LoG) and Chaotic Encryption Based Image Steganography Technique","authors":"Aiman Jan, S. A. Parah, B. A. Malik","doi":"10.1109/INCET49848.2020.9154173","DOIUrl":"https://doi.org/10.1109/INCET49848.2020.9154173","url":null,"abstract":"Information sharing through internet has becoming challenge due to high-risk factor of attacks to the information being transferred. In this paper, a novel image-encryption edge based Image steganography technique is proposed. The proposed algorithm uses logistic map for encrypting the information prior to transmission. Laplacian of Gaussian (LoG) edge operator is used to find edge areas of the colored-cover-image. Simulation analysis demonstrates that the proposed algorithm has a good amount of payload along with better results of security analysis. The proposed scheme is compared with the existing-methods.","PeriodicalId":174411,"journal":{"name":"2020 International Conference for Emerging Technology (INCET)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115684524","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 : 2020-06-01DOI: 10.1109/incet49848.2020.9153971
Anil Kunchala, D. A. Kumar, M. Venkatanarayana
Automatic detection of leaves from digital images has become important technique for identifying phenotypic changes in plants. Application of Machine learning concepts for automatic detection of leaves from images is the latest advancement in computer vision. Deep neural networks (DNNs) such as Google Nets, Alex Nets and Mobile Nets which belong to machine learning concepts are known for identifying the leaves in an image. The limitation of existing DNNs is that they do not handle uncertainty in the image during the classification stage. Class Wise Belongingness granulation of input image would effectively handles the uncertainty and improves the accuracy of classifier. In the present study, we propose a Transfer learning based Fuzzy Deep Neural Networks (TLFDNNs) model for identifying the leaves in digital Images. In the proposed model, the input image is fuzzy granulated based on class wise belongingness (CWB). Furthermore, the leaves in fuzzy granulated image are detected using Mobile Nets. The CWB based granulation of proposed model produces better results in comparison with conventional deep neural network models such as Google Nets, Alex Nets and Mobile Nets. The improvement in performance of TLFDNN model over other type of deep neural network models is justified by testing on three leaf image datasets such as Citrus, Azadirachta indica and Psidium guajava. The performance of models was evaluated using the metrics like average percentage of leaves detected in an image and the standard deviation of average percentage of leaves detected in the test images.
{"title":"Transfer Learning based Fuzzy Deep Neural Networks for leaves detection from Digital Images","authors":"Anil Kunchala, D. A. Kumar, M. Venkatanarayana","doi":"10.1109/incet49848.2020.9153971","DOIUrl":"https://doi.org/10.1109/incet49848.2020.9153971","url":null,"abstract":"Automatic detection of leaves from digital images has become important technique for identifying phenotypic changes in plants. Application of Machine learning concepts for automatic detection of leaves from images is the latest advancement in computer vision. Deep neural networks (DNNs) such as Google Nets, Alex Nets and Mobile Nets which belong to machine learning concepts are known for identifying the leaves in an image. The limitation of existing DNNs is that they do not handle uncertainty in the image during the classification stage. Class Wise Belongingness granulation of input image would effectively handles the uncertainty and improves the accuracy of classifier. In the present study, we propose a Transfer learning based Fuzzy Deep Neural Networks (TLFDNNs) model for identifying the leaves in digital Images. In the proposed model, the input image is fuzzy granulated based on class wise belongingness (CWB). Furthermore, the leaves in fuzzy granulated image are detected using Mobile Nets. The CWB based granulation of proposed model produces better results in comparison with conventional deep neural network models such as Google Nets, Alex Nets and Mobile Nets. The improvement in performance of TLFDNN model over other type of deep neural network models is justified by testing on three leaf image datasets such as Citrus, Azadirachta indica and Psidium guajava. The performance of models was evaluated using the metrics like average percentage of leaves detected in an image and the standard deviation of average percentage of leaves detected in the test images.","PeriodicalId":174411,"journal":{"name":"2020 International Conference for Emerging Technology (INCET)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115792725","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 : 2020-06-01DOI: 10.1109/incet49848.2020.9154085
Mansuri Abid E., Shaikh Mo. Suhel, Rajpurohit Vipul N., Sethia Smriti S.
This paper presents comparative study of various scalar Pulse Width Modulation (PWM) techniques that are utilized in three-phase drives application. In this paper, various PWM methods are analysed and implemented namely Sinusoidal PWM (SPWM), Zero Sequence PWM (ZSPWM), Conventional Space Vector Modulation (CSVM) and Discontinuous SVM (DSVM). This study includes two new switching sequences referred in this paper as DSVM 15 and Hybrid SVM (HSVM) techniques. Initially, simulation study is carried out with the help of Simulink model. This study includes the effect of different PWM techniques on stator current distortion and switching loss of inverter. Hardware implementations of all mentioned methods, with the help of STM34F407 microcontroller and the auto code generation block set called ‘WAIJUNG’, have been accomplished. Results obtain from the experimentation are compared and analysed on the basis of quality of stator current waveforms and switching losses of inverter.
{"title":"Analysis of Various PWM Techniques for Three-phase Asynchronous Motor","authors":"Mansuri Abid E., Shaikh Mo. Suhel, Rajpurohit Vipul N., Sethia Smriti S.","doi":"10.1109/incet49848.2020.9154085","DOIUrl":"https://doi.org/10.1109/incet49848.2020.9154085","url":null,"abstract":"This paper presents comparative study of various scalar Pulse Width Modulation (PWM) techniques that are utilized in three-phase drives application. In this paper, various PWM methods are analysed and implemented namely Sinusoidal PWM (SPWM), Zero Sequence PWM (ZSPWM), Conventional Space Vector Modulation (CSVM) and Discontinuous SVM (DSVM). This study includes two new switching sequences referred in this paper as DSVM 15 and Hybrid SVM (HSVM) techniques. Initially, simulation study is carried out with the help of Simulink model. This study includes the effect of different PWM techniques on stator current distortion and switching loss of inverter. Hardware implementations of all mentioned methods, with the help of STM34F407 microcontroller and the auto code generation block set called ‘WAIJUNG’, have been accomplished. Results obtain from the experimentation are compared and analysed on the basis of quality of stator current waveforms and switching losses of inverter.","PeriodicalId":174411,"journal":{"name":"2020 International Conference for Emerging Technology (INCET)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124194202","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 : 2020-06-01DOI: 10.1109/incet49848.2020.9154112
Jatin C. Modh, Jatinderkumar R. Saini
Gujarati language is the official language of the state of Gujarat located on the western region of India. Machine Translation System (MTS) translates text from one language to other language. Based on our review, we found that very few machine translation systems are available that converts Gujarati text into English language. This paper focuses on the translation of Gujarati trigram idioms. Idiom is defined as a token-sequence whose meaning is different from the literal meaning of the individual tokens. The proposed Gujarati to English Idioms translator accurately translates the trigram and bigram idioms. We have created the corpus of nearly 3000 n-gram idioms and from this corpus we have found nearly 890 trigram idioms and 1735 bigram idioms. This paper studies the translation of trigram and bigram idioms.
{"title":"Context Based MTS for Translating Gujarati Trigram and Bigram Idioms to English","authors":"Jatin C. Modh, Jatinderkumar R. Saini","doi":"10.1109/incet49848.2020.9154112","DOIUrl":"https://doi.org/10.1109/incet49848.2020.9154112","url":null,"abstract":"Gujarati language is the official language of the state of Gujarat located on the western region of India. Machine Translation System (MTS) translates text from one language to other language. Based on our review, we found that very few machine translation systems are available that converts Gujarati text into English language. This paper focuses on the translation of Gujarati trigram idioms. Idiom is defined as a token-sequence whose meaning is different from the literal meaning of the individual tokens. The proposed Gujarati to English Idioms translator accurately translates the trigram and bigram idioms. We have created the corpus of nearly 3000 n-gram idioms and from this corpus we have found nearly 890 trigram idioms and 1735 bigram idioms. This paper studies the translation of trigram and bigram idioms.","PeriodicalId":174411,"journal":{"name":"2020 International Conference for Emerging Technology (INCET)","volume":"501 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124452130","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 : 2020-06-01DOI: 10.1109/incet49848.2020.9154064
R. Yadav, R. Bharti, R. Nagar, Sanchit Kumar
This model aims to develop an efficient way to recapitulate large audio messages or clips for valuable insights. With increase in utilization of audio/visual data day by day, there is a need to handle audio files more intelligently. In this document, a novel approach is presented to build a summarized audio for a given long audio file. This method is composed primarily of three modules namely: Conversion of Speech into Text, Text summarization, and lastly conversion of text into speech. Each module is fed by the output of another module except speech to text conversion where input is the given audio file for which summary has to be formed. The first step in audio recapitulation is conversion of given audio to text. This is made possible by sending asynchronous requests to Google Cloud speech API. The next module accomplishes its task of extracting important sentences from the transcript by using the Text Rank algorithm. The last module is to convert the summarized text generated from the output of text summarization module to an audio file. This whole method is given a suitable User Interface using flask and thus a web application is formed for helping users to interact with this model.
{"title":"A Model For Recapitulating Audio Messages Using Machine Learning","authors":"R. Yadav, R. Bharti, R. Nagar, Sanchit Kumar","doi":"10.1109/incet49848.2020.9154064","DOIUrl":"https://doi.org/10.1109/incet49848.2020.9154064","url":null,"abstract":"This model aims to develop an efficient way to recapitulate large audio messages or clips for valuable insights. With increase in utilization of audio/visual data day by day, there is a need to handle audio files more intelligently. In this document, a novel approach is presented to build a summarized audio for a given long audio file. This method is composed primarily of three modules namely: Conversion of Speech into Text, Text summarization, and lastly conversion of text into speech. Each module is fed by the output of another module except speech to text conversion where input is the given audio file for which summary has to be formed. The first step in audio recapitulation is conversion of given audio to text. This is made possible by sending asynchronous requests to Google Cloud speech API. The next module accomplishes its task of extracting important sentences from the transcript by using the Text Rank algorithm. The last module is to convert the summarized text generated from the output of text summarization module to an audio file. This whole method is given a suitable User Interface using flask and thus a web application is formed for helping users to interact with this model.","PeriodicalId":174411,"journal":{"name":"2020 International Conference for Emerging Technology (INCET)","volume":"94 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114595620","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 : 2020-06-01DOI: 10.1109/incet49848.2020.9154020
R. K. Megalingam, Vineeth Prithvi Darla, Chaitanya Sai Kumar Nimmala
Interior wall painting is a common work in construction which consumes a lot of time and human effort. By replacing human manual operation, robotic painting was introduced to improve the accuracy, efficiency and to reduce the cost. In this paper, we introduce an autonomous wall painting robot which can paint the interior walls of a room, using paint sprayer with the help of a cascade lift mechanism. This cascade lift mechanism assists the paint sprayer to reach the required heights. The mecanum wheels with dc motors that are attached to the base of the robot, helps in easy movement of the robot, to move in all six directions with 2 DOF (degrees of freedom). The robot uses ultrasonic sensors to detect the distance and adjust to the walls, and to check whether the sprayer reached the top of the wall. The master controller controls the ultrasonic sensors, mecanum wheels, and all other parts of the robot. The overall system runs on AC power supply.
{"title":"Autonomous Wall Painting Robot","authors":"R. K. Megalingam, Vineeth Prithvi Darla, Chaitanya Sai Kumar Nimmala","doi":"10.1109/incet49848.2020.9154020","DOIUrl":"https://doi.org/10.1109/incet49848.2020.9154020","url":null,"abstract":"Interior wall painting is a common work in construction which consumes a lot of time and human effort. By replacing human manual operation, robotic painting was introduced to improve the accuracy, efficiency and to reduce the cost. In this paper, we introduce an autonomous wall painting robot which can paint the interior walls of a room, using paint sprayer with the help of a cascade lift mechanism. This cascade lift mechanism assists the paint sprayer to reach the required heights. The mecanum wheels with dc motors that are attached to the base of the robot, helps in easy movement of the robot, to move in all six directions with 2 DOF (degrees of freedom). The robot uses ultrasonic sensors to detect the distance and adjust to the walls, and to check whether the sprayer reached the top of the wall. The master controller controls the ultrasonic sensors, mecanum wheels, and all other parts of the robot. The overall system runs on AC power supply.","PeriodicalId":174411,"journal":{"name":"2020 International Conference for Emerging Technology (INCET)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114539080","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 : 2020-06-01DOI: 10.1109/incet49848.2020.9154038
Rahil Sheth, Mukund Vora, Rohit Sharma, Mohit Thaker, P. Bhavathankar
The proposed system manages the stocks of organizations and helps them to better analyze the data pertaining to the storage and sales of goods to generate relevant insights from it. With the proper utilization of technology, the system can be used to store and update the details of the inventory, stock maintenance, and generate sales reports daily, weekly or monthly in the form of various visualization charts. It proposes the formation of a system for storing the data by recording the information regarding the stocks of products identified by various brands and categories. The system identifies a need to require an input device, a locked enclosure, a computing device, a data store, and a portal site or an application for providing an all-round environment for efficient warehouse and inventory management. An internet connection or a distributed network connects the portal and application to the computing device and the data store is also required. The system provides a method that will use the concept of data analysis to give information about the most selling, profitable and dull stocks. This system thus helps the inventory managers to optimize their functioning with several data analytics algorithms such as regression modeling, market basket analysis, and other machine learning techniques to provide an all-round solution to their needs.
{"title":"A Proficient Process for Systematic Inventory Management","authors":"Rahil Sheth, Mukund Vora, Rohit Sharma, Mohit Thaker, P. Bhavathankar","doi":"10.1109/incet49848.2020.9154038","DOIUrl":"https://doi.org/10.1109/incet49848.2020.9154038","url":null,"abstract":"The proposed system manages the stocks of organizations and helps them to better analyze the data pertaining to the storage and sales of goods to generate relevant insights from it. With the proper utilization of technology, the system can be used to store and update the details of the inventory, stock maintenance, and generate sales reports daily, weekly or monthly in the form of various visualization charts. It proposes the formation of a system for storing the data by recording the information regarding the stocks of products identified by various brands and categories. The system identifies a need to require an input device, a locked enclosure, a computing device, a data store, and a portal site or an application for providing an all-round environment for efficient warehouse and inventory management. An internet connection or a distributed network connects the portal and application to the computing device and the data store is also required. The system provides a method that will use the concept of data analysis to give information about the most selling, profitable and dull stocks. This system thus helps the inventory managers to optimize their functioning with several data analytics algorithms such as regression modeling, market basket analysis, and other machine learning techniques to provide an all-round solution to their needs.","PeriodicalId":174411,"journal":{"name":"2020 International Conference for Emerging Technology (INCET)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115057199","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 : 2020-06-01DOI: 10.1109/incet49848.2020.9154130
Sneha Grampurohit, Chetan Sagarnal
The development and exploitation of several prominent Data mining techniques in numerous real-world application areas (e.g. Industry, Healthcare and Bio science) has led to the utilization of such techniques in machine learning environments, in order to extract useful pieces of information of the specified data in healthcare communities, biomedical fields etc. The accurate analysis of medical database benefits in early disease prediction, patient care and community services. The techniques of machine learning have been successfully employed in assorted applications including Disease prediction. The aim of developing classifier system using machine learning algorithms is to immensely help to solve the health-related issues by assisting the physicians to predict and diagnose diseases at an early stage. A Sample data of 4920 patients’ records diagnosed with 41 diseases was selected for analysis. A dependent variable was composed of 41 diseases. 95 of 132 independent variables(symptoms) closely related to diseases were selected and optimized. This research work carried out demonstrates the disease prediction system developed using Machine learning algorithms such as Decision Tree classifier, Random forest classifier, and Naïve Bayes classifier. The paper presents the comparative study of the results of the above algorithms used.
{"title":"Disease Prediction using Machine Learning Algorithms","authors":"Sneha Grampurohit, Chetan Sagarnal","doi":"10.1109/incet49848.2020.9154130","DOIUrl":"https://doi.org/10.1109/incet49848.2020.9154130","url":null,"abstract":"The development and exploitation of several prominent Data mining techniques in numerous real-world application areas (e.g. Industry, Healthcare and Bio science) has led to the utilization of such techniques in machine learning environments, in order to extract useful pieces of information of the specified data in healthcare communities, biomedical fields etc. The accurate analysis of medical database benefits in early disease prediction, patient care and community services. The techniques of machine learning have been successfully employed in assorted applications including Disease prediction. The aim of developing classifier system using machine learning algorithms is to immensely help to solve the health-related issues by assisting the physicians to predict and diagnose diseases at an early stage. A Sample data of 4920 patients’ records diagnosed with 41 diseases was selected for analysis. A dependent variable was composed of 41 diseases. 95 of 132 independent variables(symptoms) closely related to diseases were selected and optimized. This research work carried out demonstrates the disease prediction system developed using Machine learning algorithms such as Decision Tree classifier, Random forest classifier, and Naïve Bayes classifier. The paper presents the comparative study of the results of the above algorithms used.","PeriodicalId":174411,"journal":{"name":"2020 International Conference for Emerging Technology (INCET)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116041098","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 : 2020-06-01DOI: 10.1109/incet49848.2020.9154092
Alwin T. Aind, Akashdeep Ramnaney, Divyashikha Sethia
With the ever-increasing involvement of people into social media and online gaming, Cyberbullying has become a serious issue affecting almost all parts of the demographic. Cyberbullying can cause severe mental and emotional impacts on a person, especially on minors; hence, there is a requirement of having intelligent automated systems to detect questionable content present on social media platforms and remove it. In this paper, we introduce our novel algorithm Q-Bully which can automatically detect cyberbullying on various social media and online gaming platforms using Reinforcement Learning along with Natural Language Processing techniques. Previously the techniques used to detect cyberbullying have a good accuracy related to the text they have been trained on and do not incorporate new word patterns without complete retraining of model. In this paper, we incorporated the use of Reinforcement Learning and have conducted an experimental study in which we feed the messages and posts of bullies as well as victims to a Reinforcement Learning Agent for classification. We compare our model with the other baseline models on based on F1 scores (0.86 a benchmark dataset of 16K annotated tweets) and are able to infer that our model outperforms other state-of-the-art models when the dataset is highly dynamic and populated with words which are deliberately misspelled to trick the conventional detection systems.
{"title":"Q-Bully: A Reinforcement Learning based Cyberbullying Detection Framework","authors":"Alwin T. Aind, Akashdeep Ramnaney, Divyashikha Sethia","doi":"10.1109/incet49848.2020.9154092","DOIUrl":"https://doi.org/10.1109/incet49848.2020.9154092","url":null,"abstract":"With the ever-increasing involvement of people into social media and online gaming, Cyberbullying has become a serious issue affecting almost all parts of the demographic. Cyberbullying can cause severe mental and emotional impacts on a person, especially on minors; hence, there is a requirement of having intelligent automated systems to detect questionable content present on social media platforms and remove it. In this paper, we introduce our novel algorithm Q-Bully which can automatically detect cyberbullying on various social media and online gaming platforms using Reinforcement Learning along with Natural Language Processing techniques. Previously the techniques used to detect cyberbullying have a good accuracy related to the text they have been trained on and do not incorporate new word patterns without complete retraining of model. In this paper, we incorporated the use of Reinforcement Learning and have conducted an experimental study in which we feed the messages and posts of bullies as well as victims to a Reinforcement Learning Agent for classification. We compare our model with the other baseline models on based on F1 scores (0.86 a benchmark dataset of 16K annotated tweets) and are able to infer that our model outperforms other state-of-the-art models when the dataset is highly dynamic and populated with words which are deliberately misspelled to trick the conventional detection systems.","PeriodicalId":174411,"journal":{"name":"2020 International Conference for Emerging Technology (INCET)","volume":"105 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124858978","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：