Pub Date : 2017-09-01DOI: 10.1109/ICRITO.2017.8342502
P. Pandey, Sarika Jain, S. Khatri
In this paper, a new enhancement process is introduced for medical images. The proposed technique will help the doctors and physicians to analyze the medical images more accurately. The medical images commonly include the issues of noise, bad quality and low intensity. Due to these issues, the surgeons and physicians always faces multiple complications to detect the exact disease. We introduce in this paper repetitive use of Kalman filter for improving the quality of various medical images. Results are shown with the help of pictures.
{"title":"Enhancement of medical images using Kalman filter","authors":"P. Pandey, Sarika Jain, S. Khatri","doi":"10.1109/ICRITO.2017.8342502","DOIUrl":"https://doi.org/10.1109/ICRITO.2017.8342502","url":null,"abstract":"In this paper, a new enhancement process is introduced for medical images. The proposed technique will help the doctors and physicians to analyze the medical images more accurately. The medical images commonly include the issues of noise, bad quality and low intensity. Due to these issues, the surgeons and physicians always faces multiple complications to detect the exact disease. We introduce in this paper repetitive use of Kalman filter for improving the quality of various medical images. Results are shown with the help of pictures.","PeriodicalId":357118,"journal":{"name":"2017 6th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions) (ICRITO)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116899302","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 : 2017-09-01DOI: 10.1109/ICRITO.2017.8342442
R. Malhotra, Anshul Khurana
Defect prediction of software is necessary to determine defective parts of software. Defect prediction models are elaborated with the help of software metrics when combined with defective data to predict the classes that are defective. In this paper we have used datasets that statistically resolve the relationship among software metrics and defect vulnerability. The main intent of this paper are 1) Feature selection for defect prediction using proposed evolutionary algorithm 2) Comparing machine learning techniques 3) Use of precision and recall as performance measure for defect prediction 4) 10- fold validation is performed on every model. In this discourse, we predict defective class using 5 machine learning techniques and 2 evolutionary techniques for feature selection. In this work, we have applied evolutionary algorithms for feature selection suitable for each of the classification techniques applied on five open source android packages. Finally, for validation of calculated results, 10-fold validation is used. The results show that using evolutionary algorithms for feature selection can improve precision and recall for RF, DT and SVM. Precision and recall have best rise using SVM model. The use of evolutionary algorithms don't effect precision and recall for statistical classifier. The results obtained from evaluation thus confirm about the prediction of default classes using evolutionary algorithms is better than using only machine learning techniques. The analyzed and calculated results gave us the view about the usage of evolutionary algorithm with statistical classifier is of no use.
{"title":"Analysis of evolutionary algorithms to improve software defect prediction","authors":"R. Malhotra, Anshul Khurana","doi":"10.1109/ICRITO.2017.8342442","DOIUrl":"https://doi.org/10.1109/ICRITO.2017.8342442","url":null,"abstract":"Defect prediction of software is necessary to determine defective parts of software. Defect prediction models are elaborated with the help of software metrics when combined with defective data to predict the classes that are defective. In this paper we have used datasets that statistically resolve the relationship among software metrics and defect vulnerability. The main intent of this paper are 1) Feature selection for defect prediction using proposed evolutionary algorithm 2) Comparing machine learning techniques 3) Use of precision and recall as performance measure for defect prediction 4) 10- fold validation is performed on every model. In this discourse, we predict defective class using 5 machine learning techniques and 2 evolutionary techniques for feature selection. In this work, we have applied evolutionary algorithms for feature selection suitable for each of the classification techniques applied on five open source android packages. Finally, for validation of calculated results, 10-fold validation is used. The results show that using evolutionary algorithms for feature selection can improve precision and recall for RF, DT and SVM. Precision and recall have best rise using SVM model. The use of evolutionary algorithms don't effect precision and recall for statistical classifier. The results obtained from evaluation thus confirm about the prediction of default classes using evolutionary algorithms is better than using only machine learning techniques. The analyzed and calculated results gave us the view about the usage of evolutionary algorithm with statistical classifier is of no use.","PeriodicalId":357118,"journal":{"name":"2017 6th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions) (ICRITO)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127840055","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 : 2017-09-01DOI: 10.1109/ICRITO.2017.8342453
P. Shrivas, U. Lilhore, Nitin Agrawal
As the quantity of web clients are expanding every day. This work concentrate on the retrieval of pictures by using the visual and annotation characteristics of the images. In this work two kind of features are utilized for the bunching of the picture dataset. So Based on the comparability of content and CCM components of the picture bunches are made. For bunching here genetic approach is utilized. Two phase learning genetic algorithm named as teacher learning based optimization was utilized for clustring. Here client pass two kind of queries first was content while other is image, this assistance in choosing suitable cluster for retrieval of picture. Analysis was done on genuine and artificial set of pictures. Result demonstrates that proposed work is better on various assessment parameters as contrast with existing strategies.
{"title":"Genetic approach based image retrieval by using CCM and textual features","authors":"P. Shrivas, U. Lilhore, Nitin Agrawal","doi":"10.1109/ICRITO.2017.8342453","DOIUrl":"https://doi.org/10.1109/ICRITO.2017.8342453","url":null,"abstract":"As the quantity of web clients are expanding every day. This work concentrate on the retrieval of pictures by using the visual and annotation characteristics of the images. In this work two kind of features are utilized for the bunching of the picture dataset. So Based on the comparability of content and CCM components of the picture bunches are made. For bunching here genetic approach is utilized. Two phase learning genetic algorithm named as teacher learning based optimization was utilized for clustring. Here client pass two kind of queries first was content while other is image, this assistance in choosing suitable cluster for retrieval of picture. Analysis was done on genuine and artificial set of pictures. Result demonstrates that proposed work is better on various assessment parameters as contrast with existing strategies.","PeriodicalId":357118,"journal":{"name":"2017 6th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions) (ICRITO)","volume":"8 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126041088","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 : 2017-09-01DOI: 10.1109/ICRITO.2017.8342500
Neetu Mittal, Sudhir Tanwar, S. Khatri
A skin lesion is a portion of skin with an abnormal growth or presence due to a skin disease. Skin diseases at their early stages can be cured very easily; otherwise they begin to spread to other parts of the body and may be deadly. An early detection of skin disease is essential for such patients. Due to the high cost involved in various dermatology testing procedures for every patient, an automated system is required to give better lesion images and vision to help the doctors to further diagnose and prescribe the correct prescription and medication. In this paper, an innovative approach for automatic identification of skin lesions is proposed. To improve the quality of skin lesion images, Median filtering and Sobel edge detection techniques have been implemented for filtering and segmentation. The efficacy of the proposed work has been verified by measuring the entropy of the resultant images obtained for different skin diseases. The performance is tested on a dataset of 70 samples from 150 medical images of different body parts with 10 different classes of skin diseases.
{"title":"Identification & enhancement of different skin lesion images by segmentation techniques","authors":"Neetu Mittal, Sudhir Tanwar, S. Khatri","doi":"10.1109/ICRITO.2017.8342500","DOIUrl":"https://doi.org/10.1109/ICRITO.2017.8342500","url":null,"abstract":"A skin lesion is a portion of skin with an abnormal growth or presence due to a skin disease. Skin diseases at their early stages can be cured very easily; otherwise they begin to spread to other parts of the body and may be deadly. An early detection of skin disease is essential for such patients. Due to the high cost involved in various dermatology testing procedures for every patient, an automated system is required to give better lesion images and vision to help the doctors to further diagnose and prescribe the correct prescription and medication. In this paper, an innovative approach for automatic identification of skin lesions is proposed. To improve the quality of skin lesion images, Median filtering and Sobel edge detection techniques have been implemented for filtering and segmentation. The efficacy of the proposed work has been verified by measuring the entropy of the resultant images obtained for different skin diseases. The performance is tested on a dataset of 70 samples from 150 medical images of different body parts with 10 different classes of skin diseases.","PeriodicalId":357118,"journal":{"name":"2017 6th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions) (ICRITO)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124695341","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 : 2017-09-01DOI: 10.1109/ICRITO.2017.8342421
A. Gudkov, D. Dadonov, E. Krotkov, V. Shchepinin, N. Didenko, V. Parkhomenko
Field observation results of current and voltage higher harmonics levels, flowing in electrical power supply systems cable lines of electric centrifugal pump units are given. The mathematical representation of the stationary thermal field calculation in underground three-phase cable lines 0,4 kV and the surrounding environment as backfill and natural soil during non-sinusoidal currents flow is developed. By means of finite-element method numeral computations is shown that cables heating in no small part is defined by soil heat conductivity. On the basis of thermographic inspection and virtual modeling in the software package ELCUT the thermal effect of cables isolation additional heating buried in backfill or natural soil of non-sinusoidal currents flow is shown. The developed technique could be used when determining output capacity of the designed buried service cable lines taking into account influence of the current and voltage higher harmonics and soil characteristics.
{"title":"Thermal wear of cable lines isolation research owing to current flow of the high harmonics at oil extraction electrical generating systems","authors":"A. Gudkov, D. Dadonov, E. Krotkov, V. Shchepinin, N. Didenko, V. Parkhomenko","doi":"10.1109/ICRITO.2017.8342421","DOIUrl":"https://doi.org/10.1109/ICRITO.2017.8342421","url":null,"abstract":"Field observation results of current and voltage higher harmonics levels, flowing in electrical power supply systems cable lines of electric centrifugal pump units are given. The mathematical representation of the stationary thermal field calculation in underground three-phase cable lines 0,4 kV and the surrounding environment as backfill and natural soil during non-sinusoidal currents flow is developed. By means of finite-element method numeral computations is shown that cables heating in no small part is defined by soil heat conductivity. On the basis of thermographic inspection and virtual modeling in the software package ELCUT the thermal effect of cables isolation additional heating buried in backfill or natural soil of non-sinusoidal currents flow is shown. The developed technique could be used when determining output capacity of the designed buried service cable lines taking into account influence of the current and voltage higher harmonics and soil characteristics.","PeriodicalId":357118,"journal":{"name":"2017 6th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions) (ICRITO)","volume":"201 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124403997","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 : 2017-09-01DOI: 10.1109/ICRITO.2017.8342510
Duaa Ali Al-Sabti, A. Singh, S. K. Jha
Social media is a technology that can be developed in a fast and flexible manner, where internet connections are transformed into interactive platforms. Social networking programs are increasingly spreading around the world. Facebook users reached 1.44 billion per month in 2015, which means that most of the people of the world have a stamp on social networking platforms. Social media platforms have become integral part of teens' daily life. 22% of teenagers are enrolled in social networking programs about 10 times a day. The remaining category, which makes up more than half of teenagers register more than once a day through the use of mobile phone, where the proportion of teenagers who have their own cell phones reach 75%. The results show by RSA that the rate of cybercrime reached 173% by mobile phones during the period 2013–2015. And, the RSA announce a large number of real examples of cybercrime that have occurred recently and continue to pose a major threat to society and specific to teenagers. Consequently, this paper review social media, society and business. Moreover, how he social media impact teenagers.
{"title":"Impact of social media on society in a large and specific to teenagers","authors":"Duaa Ali Al-Sabti, A. Singh, S. K. Jha","doi":"10.1109/ICRITO.2017.8342510","DOIUrl":"https://doi.org/10.1109/ICRITO.2017.8342510","url":null,"abstract":"Social media is a technology that can be developed in a fast and flexible manner, where internet connections are transformed into interactive platforms. Social networking programs are increasingly spreading around the world. Facebook users reached 1.44 billion per month in 2015, which means that most of the people of the world have a stamp on social networking platforms. Social media platforms have become integral part of teens' daily life. 22% of teenagers are enrolled in social networking programs about 10 times a day. The remaining category, which makes up more than half of teenagers register more than once a day through the use of mobile phone, where the proportion of teenagers who have their own cell phones reach 75%. The results show by RSA that the rate of cybercrime reached 173% by mobile phones during the period 2013–2015. And, the RSA announce a large number of real examples of cybercrime that have occurred recently and continue to pose a major threat to society and specific to teenagers. Consequently, this paper review social media, society and business. Moreover, how he social media impact teenagers.","PeriodicalId":357118,"journal":{"name":"2017 6th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions) (ICRITO)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132019633","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 : 2017-09-01DOI: 10.1109/ICRITO.2017.8342516
Mohammed Saud Al-Adhoobi, Manju Jose, A. Singh
The aim of this study is to conduct an evaluation of different measures and enforcements which are essential for road safety. Effect and need of speed and speed limit are critically examined. This research paper also examines the means of maximizing enforcement strategies for road safety. The role of vehicle safety in road safety is also analyzed and elaborated.
{"title":"A review of different road safety measures and enforcements","authors":"Mohammed Saud Al-Adhoobi, Manju Jose, A. Singh","doi":"10.1109/ICRITO.2017.8342516","DOIUrl":"https://doi.org/10.1109/ICRITO.2017.8342516","url":null,"abstract":"The aim of this study is to conduct an evaluation of different measures and enforcements which are essential for road safety. Effect and need of speed and speed limit are critically examined. This research paper also examines the means of maximizing enforcement strategies for road safety. The role of vehicle safety in road safety is also analyzed and elaborated.","PeriodicalId":357118,"journal":{"name":"2017 6th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions) (ICRITO)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132524024","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 : 2017-09-01DOI: 10.1109/ICRITO.2017.8342426
Kuiyuan Zhang, Jianping Li, E. J. Guo
For the semi-blind estimation problem of two-hop multi-input multi-output amplified forwarding (MIMO-AF) relay system, the parallel factor (PARAFAC) model is constructed for the received signal. Using the uniqueness of its decomposition, an ALS-LS algorithm is proposed. Based on the algorithm of least squares alternating (ALS) and adding relaxation factor, the ALS algorithm is used to achieve certain convergence conditions. The estimation result of the former algorithm is taken as the initial value, and then based on the ALS algorithm adding relaxation factor, using the relaxation factor to change the gradient direction, so as to speed up the convergence rate. And the performance of the channel model is analyzed by different parameters of the channel model. Simulation results show: compared with the existing least squares alternate algorithm, the complexity and iteration times of the algorithm are reduced, and the convergence speed of the algorithm is accelerated.
{"title":"Research on channel estimation algorithm of MIMO relay system based on PARAFAC model","authors":"Kuiyuan Zhang, Jianping Li, E. J. Guo","doi":"10.1109/ICRITO.2017.8342426","DOIUrl":"https://doi.org/10.1109/ICRITO.2017.8342426","url":null,"abstract":"For the semi-blind estimation problem of two-hop multi-input multi-output amplified forwarding (MIMO-AF) relay system, the parallel factor (PARAFAC) model is constructed for the received signal. Using the uniqueness of its decomposition, an ALS-LS algorithm is proposed. Based on the algorithm of least squares alternating (ALS) and adding relaxation factor, the ALS algorithm is used to achieve certain convergence conditions. The estimation result of the former algorithm is taken as the initial value, and then based on the ALS algorithm adding relaxation factor, using the relaxation factor to change the gradient direction, so as to speed up the convergence rate. And the performance of the channel model is analyzed by different parameters of the channel model. Simulation results show: compared with the existing least squares alternate algorithm, the complexity and iteration times of the algorithm are reduced, and the convergence speed of the algorithm is accelerated.","PeriodicalId":357118,"journal":{"name":"2017 6th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions) (ICRITO)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134071404","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 : 2017-09-01DOI: 10.1109/ICRITO.2017.8342423
Sai Satish Inala, P. Pushpalatha
As technology will increase as quality of circuits additionally will increase that tends face reliableness challenges and creates want for fault-tolerant implementations. Signal processing and communication circuits are effected by soft errors. The complexity increases as protection against soft errors increases in many applications. There are distinct advancements in VLSI technology i.e., number of circuits called Fast Fourier Transforms (FFTs) increased on a small chip. In this case we have to implement the fault tolerance in order to preserve the data efficiently. There are distinct techniques exist to achieve fault tolerance. The most used technique is algorithmic-primarily based fault tolerance (ABFT) techniques that attempt to use recursive properties to find and accurate errors. But in advanced systems it is not unusual that variety of the filters function in parallel, as an instance a filters having same response are connected in parallel and subjected to different inputs. ECC (error correction codes) is the one of the method to detect and correct errors in FFTs. We propose different multipliers in FFTs architecture for which multiplier is most suitable in whole design. In this proposed method each filter can be considered as a bit. This method allows most efficient protection when there is large number of parallel filters present. The method is evaluated employing a Array, changed booth, Wallace tree and Dadda multipliers showing the potency in terms of speed, low power consumption and space.
{"title":"Relative performance of multipliers: A fault tolerance perspective for parallel FFTs","authors":"Sai Satish Inala, P. Pushpalatha","doi":"10.1109/ICRITO.2017.8342423","DOIUrl":"https://doi.org/10.1109/ICRITO.2017.8342423","url":null,"abstract":"As technology will increase as quality of circuits additionally will increase that tends face reliableness challenges and creates want for fault-tolerant implementations. Signal processing and communication circuits are effected by soft errors. The complexity increases as protection against soft errors increases in many applications. There are distinct advancements in VLSI technology i.e., number of circuits called Fast Fourier Transforms (FFTs) increased on a small chip. In this case we have to implement the fault tolerance in order to preserve the data efficiently. There are distinct techniques exist to achieve fault tolerance. The most used technique is algorithmic-primarily based fault tolerance (ABFT) techniques that attempt to use recursive properties to find and accurate errors. But in advanced systems it is not unusual that variety of the filters function in parallel, as an instance a filters having same response are connected in parallel and subjected to different inputs. ECC (error correction codes) is the one of the method to detect and correct errors in FFTs. We propose different multipliers in FFTs architecture for which multiplier is most suitable in whole design. In this proposed method each filter can be considered as a bit. This method allows most efficient protection when there is large number of parallel filters present. The method is evaluated employing a Array, changed booth, Wallace tree and Dadda multipliers showing the potency in terms of speed, low power consumption and space.","PeriodicalId":357118,"journal":{"name":"2017 6th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions) (ICRITO)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115224264","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 : 2017-09-01DOI: 10.1109/ICRITO.2017.8342450
Nidhi Chandra, S. Khatri, S. Som
Billions of contributions are made every day across multiple online communities and social media websites in the form of social messages, social blogs and online discussion. The aim of this paper is to identify such comments and posts which are racist and malicious in nature so that they could be effetely banned and removed in order to counter them. This article uses set of documents with racist comments as text corpus on which appropriate machine learning algorithm is applied to detect racist comments or meaning. To detect anti-social content there is a need to find the extent of similarity between a pair of text messages as a source and classified terms which are antisocial or in discriminating terms. The approach devised in this article to detect antisocial behavior is a technique based on term frequency based content classification.
{"title":"Anti social comment classification based on kNN algorithm","authors":"Nidhi Chandra, S. Khatri, S. Som","doi":"10.1109/ICRITO.2017.8342450","DOIUrl":"https://doi.org/10.1109/ICRITO.2017.8342450","url":null,"abstract":"Billions of contributions are made every day across multiple online communities and social media websites in the form of social messages, social blogs and online discussion. The aim of this paper is to identify such comments and posts which are racist and malicious in nature so that they could be effetely banned and removed in order to counter them. This article uses set of documents with racist comments as text corpus on which appropriate machine learning algorithm is applied to detect racist comments or meaning. To detect anti-social content there is a need to find the extent of similarity between a pair of text messages as a source and classified terms which are antisocial or in discriminating terms. The approach devised in this article to detect antisocial behavior is a technique based on term frequency based content classification.","PeriodicalId":357118,"journal":{"name":"2017 6th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions) (ICRITO)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124899259","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：