Pub Date : 2019-09-01DOI: 10.1109/ICCT46177.2019.8969060
Vrishabh Sharma, R. Khemnar, R. Kumari, B. Mohan
Stock price prediction has been a major area of research for many years. Accurate predictions can help investors take correct decisions about the selling/purchase of stocks. This paper aims to predict and gauge stock costs and patterns, utilizing the power of machine learning, content examination and fundamental analysis, to give traders a hands-on tool for keen speculations particularly for the volatile Indian Stock Market. We propose a technique to analyze and predict the stock price with the help of sentiment analysis and decomposable time series model along with multivariate-linear regression.
{"title":"Time Series with Sentiment Analysis for Stock Price Prediction","authors":"Vrishabh Sharma, R. Khemnar, R. Kumari, B. Mohan","doi":"10.1109/ICCT46177.2019.8969060","DOIUrl":"https://doi.org/10.1109/ICCT46177.2019.8969060","url":null,"abstract":"Stock price prediction has been a major area of research for many years. Accurate predictions can help investors take correct decisions about the selling/purchase of stocks. This paper aims to predict and gauge stock costs and patterns, utilizing the power of machine learning, content examination and fundamental analysis, to give traders a hands-on tool for keen speculations particularly for the volatile Indian Stock Market. We propose a technique to analyze and predict the stock price with the help of sentiment analysis and decomposable time series model along with multivariate-linear regression.","PeriodicalId":118655,"journal":{"name":"2019 2nd International Conference on Intelligent Communication and Computational Techniques (ICCT)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114236925","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 : 2019-09-01DOI: 10.1109/ICCT46177.2019.8969063
Sunil Kr. Maakar, Y. Singh, Rajeshwar Singh
Flying Ad Hoc Network (FANET) is a unique class of MANET that provides the communication between tiny flying drones called micro UAVs (unmanned aerial vehicle) facilitate with a camera, sensor, and communication system. FANET has a wide area of applications like reconnaissance and surveillance for military and civil purposes. FANETs along with its extraordinary features have some challenges and issues that should be considered. Implementation of three-dimensional models of FANETs is one such issue. Numbers of researchers have joined their hands in the field of FANET. Till now, experts try to implement two-dimensional FANET model only. So observance in this mind, we have a consideration about the implantation of three-dimensional models for FANET in this paper, by utilizing the Gauss Markov Mobility Model with AODV as routing protocol. Simulation experiment has been carried out using NS3.
{"title":"Implementation of Three Dimensional Model for Flying Ad Hoc Network","authors":"Sunil Kr. Maakar, Y. Singh, Rajeshwar Singh","doi":"10.1109/ICCT46177.2019.8969063","DOIUrl":"https://doi.org/10.1109/ICCT46177.2019.8969063","url":null,"abstract":"Flying Ad Hoc Network (FANET) is a unique class of MANET that provides the communication between tiny flying drones called micro UAVs (unmanned aerial vehicle) facilitate with a camera, sensor, and communication system. FANET has a wide area of applications like reconnaissance and surveillance for military and civil purposes. FANETs along with its extraordinary features have some challenges and issues that should be considered. Implementation of three-dimensional models of FANETs is one such issue. Numbers of researchers have joined their hands in the field of FANET. Till now, experts try to implement two-dimensional FANET model only. So observance in this mind, we have a consideration about the implantation of three-dimensional models for FANET in this paper, by utilizing the Gauss Markov Mobility Model with AODV as routing protocol. Simulation experiment has been carried out using NS3.","PeriodicalId":118655,"journal":{"name":"2019 2nd International Conference on Intelligent Communication and Computational Techniques (ICCT)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131557348","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 : 2019-09-01DOI: 10.1109/ICCT46177.2019.8969023
Roohani, Tushar Rana, P. Meel
Rumor propagation is an alarming problem that creates a lot of predicament and has significant impact on people’s lives. Earlier rumor could only be spread by the word of the mouth however in the current Web age, people are using electronics much more than they used to before, thereby resulting into lot of social interaction on the Web and hence spread of fake news is at its apex. This survey paper is written while keeping in mind the problem of fake news propagation and various approaches given to limit the spread up to a considerable extent. Fake news propagation is a new field of research and constant work is going on this field. Various models already given attempt to recognize the pattern of the news spread, correlates the rumor propagation with nature inspired phenomena. In this review paper, we also give the comparison between these models and their variants, this study leads us to see which areas are still challenging and what are the future prospects of rumor propagation.
{"title":"Rumor Propagation: A State-of-the-art Survey of Current Challenges and Opportunities","authors":"Roohani, Tushar Rana, P. Meel","doi":"10.1109/ICCT46177.2019.8969023","DOIUrl":"https://doi.org/10.1109/ICCT46177.2019.8969023","url":null,"abstract":"Rumor propagation is an alarming problem that creates a lot of predicament and has significant impact on people’s lives. Earlier rumor could only be spread by the word of the mouth however in the current Web age, people are using electronics much more than they used to before, thereby resulting into lot of social interaction on the Web and hence spread of fake news is at its apex. This survey paper is written while keeping in mind the problem of fake news propagation and various approaches given to limit the spread up to a considerable extent. Fake news propagation is a new field of research and constant work is going on this field. Various models already given attempt to recognize the pattern of the news spread, correlates the rumor propagation with nature inspired phenomena. In this review paper, we also give the comparison between these models and their variants, this study leads us to see which areas are still challenging and what are the future prospects of rumor propagation.","PeriodicalId":118655,"journal":{"name":"2019 2nd International Conference on Intelligent Communication and Computational Techniques (ICCT)","volume":"115 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128972543","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 : 2019-09-01DOI: 10.1109/ICCT46177.2019.8968780
Er. Kailash Aseri
In the current scenario, most of the services are deployed on web based services and these can be accessed using wireless technologies. The greater part of the corporate or business driven organizations is conveyed on web or cloud based condition. For such usage, the sites, versatile applications and cloud put together administrations are propelled with respect to the internet so that the whenever anyplace access to the administrations can be accessible. India is one of the greatest markets of cell phones and a worthwhile spot for the global organizations associated with the assembling of cell phones. From the examination investigation and reports from Statista.com, it is introduced that India is one of the key nations with tremendous market of versatile clients. In year 2017, around 134 millions cell phones were sold in India that is the enormous figure. From another exploration report, it is anticipated that the cell phone clients in India will increment to around 450 Millions by year 2022. To adapt up to the huge heap of cell phone remote systems, there is have to hoist the execution in current 4G and emerging 5G Networks advancements with the goal that the higher level of execution can be accomplished in the system condition. This original copy is having the emphasis on the delineation of the result from cutting edge remote systems of 4G and 5G with the reproduction utilizing the development execution apparatuses of cupcarbon.
{"title":"A Pragmatic Evaluation of 4G and 5G Wireless Networks in the Current Scenario","authors":"Er. Kailash Aseri","doi":"10.1109/ICCT46177.2019.8968780","DOIUrl":"https://doi.org/10.1109/ICCT46177.2019.8968780","url":null,"abstract":"In the current scenario, most of the services are deployed on web based services and these can be accessed using wireless technologies. The greater part of the corporate or business driven organizations is conveyed on web or cloud based condition. For such usage, the sites, versatile applications and cloud put together administrations are propelled with respect to the internet so that the whenever anyplace access to the administrations can be accessible. India is one of the greatest markets of cell phones and a worthwhile spot for the global organizations associated with the assembling of cell phones. From the examination investigation and reports from Statista.com, it is introduced that India is one of the key nations with tremendous market of versatile clients. In year 2017, around 134 millions cell phones were sold in India that is the enormous figure. From another exploration report, it is anticipated that the cell phone clients in India will increment to around 450 Millions by year 2022. To adapt up to the huge heap of cell phone remote systems, there is have to hoist the execution in current 4G and emerging 5G Networks advancements with the goal that the higher level of execution can be accomplished in the system condition. This original copy is having the emphasis on the delineation of the result from cutting edge remote systems of 4G and 5G with the reproduction utilizing the development execution apparatuses of cupcarbon.","PeriodicalId":118655,"journal":{"name":"2019 2nd International Conference on Intelligent Communication and Computational Techniques (ICCT)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134574033","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 : 2019-09-01DOI: 10.1109/ICCT46177.2019.8968787
G. Kumar, U. Prashanthi, K. Tejaswini, T. Gayathri
In this paper, a body area network (BAN) consisting of source and destination with multiple amplify and forward nodes called relays in between them are considered and the power allocation to the relays is investigated. This investigation has been done for Implant nodes considering two scenarios. In the first scenario, the objective is to maximize the effective signal to noise ratio (SNR) of the source-relay and the relay-destination links under the total relay power constraint. In the second scenario, the objective is to maximize the total power allocated for a given data rate. These objectives are aimed to show their results by means of error rate. Finally the results are correlated with respect to direct transmission and then concluded.
{"title":"Power Allocation Schemes for Implant Nodes in Cooperative Wireless Body Area Networks","authors":"G. Kumar, U. Prashanthi, K. Tejaswini, T. Gayathri","doi":"10.1109/ICCT46177.2019.8968787","DOIUrl":"https://doi.org/10.1109/ICCT46177.2019.8968787","url":null,"abstract":"In this paper, a body area network (BAN) consisting of source and destination with multiple amplify and forward nodes called relays in between them are considered and the power allocation to the relays is investigated. This investigation has been done for Implant nodes considering two scenarios. In the first scenario, the objective is to maximize the effective signal to noise ratio (SNR) of the source-relay and the relay-destination links under the total relay power constraint. In the second scenario, the objective is to maximize the total power allocated for a given data rate. These objectives are aimed to show their results by means of error rate. Finally the results are correlated with respect to direct transmission and then concluded.","PeriodicalId":118655,"journal":{"name":"2019 2nd International Conference on Intelligent Communication and Computational Techniques (ICCT)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122678954","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 : 2019-09-01DOI: 10.1109/ICCT46177.2019.8969054
Amandeep Kaur, A. Chauhan, A. Aggarwal
The duel for discovery of enhancer along with the beginning of next generation sequencing is a consequence of discovery simian virus 40 (SV40) that is believed to be first enhancers noticed in wide set of genomic data. Features for predicting enhancers such as marks for histone modification, elements mined from sequences characteristics, epigenetic marks right away from primary tissues are implemented with a capricious success rate. Though till date there is no distinct enhancer indicator fetching an agreement in discriminating and exposing enhancer from massive genomic data sets. Machine learning has arisen out to be one of the competent computational approaches with a diversity of supervised, unsupervised and hybrid architectures used for enhancer identification. In this paper, attention is given to the tools lately developed for enhancer prediction working on common feature of enhancer. Comparative analysis of methods for enhancer prediction and corresponding results are prepared amid functionally analogous counterparts.
{"title":"Machine Learning Based Comparative Analysis of Methods for Enhancer Prediction in Genomic Data","authors":"Amandeep Kaur, A. Chauhan, A. Aggarwal","doi":"10.1109/ICCT46177.2019.8969054","DOIUrl":"https://doi.org/10.1109/ICCT46177.2019.8969054","url":null,"abstract":"The duel for discovery of enhancer along with the beginning of next generation sequencing is a consequence of discovery simian virus 40 (SV40) that is believed to be first enhancers noticed in wide set of genomic data. Features for predicting enhancers such as marks for histone modification, elements mined from sequences characteristics, epigenetic marks right away from primary tissues are implemented with a capricious success rate. Though till date there is no distinct enhancer indicator fetching an agreement in discriminating and exposing enhancer from massive genomic data sets. Machine learning has arisen out to be one of the competent computational approaches with a diversity of supervised, unsupervised and hybrid architectures used for enhancer identification. In this paper, attention is given to the tools lately developed for enhancer prediction working on common feature of enhancer. Comparative analysis of methods for enhancer prediction and corresponding results are prepared amid functionally analogous counterparts.","PeriodicalId":118655,"journal":{"name":"2019 2nd International Conference on Intelligent Communication and Computational Techniques (ICCT)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129385626","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 : 2019-09-01DOI: 10.1109/ICCT46177.2019.8969055
A. Basan, E. Basan, Anton Gritsynin
The purpose of this work is to analyze the security problems of robotic systems and analyze the approaches to assessing the security of a wireless robotic system. The solution to this problem involves the use of developed frameworks. Prefixed frameworks assume that the robotic system is divided into levels and after that it is necessary to directly protect each level. Each level has its own features and drawbacks that must be taken into account when developing a security system for a robotic system.
{"title":"Analysis of the Security Problems of Robotic Systems","authors":"A. Basan, E. Basan, Anton Gritsynin","doi":"10.1109/ICCT46177.2019.8969055","DOIUrl":"https://doi.org/10.1109/ICCT46177.2019.8969055","url":null,"abstract":"The purpose of this work is to analyze the security problems of robotic systems and analyze the approaches to assessing the security of a wireless robotic system. The solution to this problem involves the use of developed frameworks. Prefixed frameworks assume that the robotic system is divided into levels and after that it is necessary to directly protect each level. Each level has its own features and drawbacks that must be taken into account when developing a security system for a robotic system.","PeriodicalId":118655,"journal":{"name":"2019 2nd International Conference on Intelligent Communication and Computational Techniques (ICCT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132155002","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 : 2019-09-01DOI: 10.1109/ICCT46177.2019.8969066
Shubham Kumar, S. Benedict, Srilakshmi Ajith
Internet of Things (IoT) based systems, most predominantly, the machine to machine communication based systems, have evolved in the recent past which helped to increase the efficiency of services offered without much necessity of human interaction. In general, IoT cloud-assisted solutions could serve several applications, including the Smart Home Automation, due to the availability of high-speed mobile networks coupled with cost effective, accessible and fast embedded hardware. In fact, there exists a few smart home solutions in the market that aim at automating the basic operations of home appliances. However, most of these systems focus on mimicking the basic operations of the electrical switches. This paper attempts to unfold a Smart Home Automation system using Natural Language Processing (NLP) and IoT cloud solutions. The proposed system was able to remotely control smart homes in a secure and in a customized manner; the approach could precisely monitor home devices with the application of GoogleAPI for integrating devices. Experiments were carried out at the IoT Cloud research lab of IIIT Kottayam such that a mini-Smart Home environment was setup to remotely control the sensors such as humidity and temperatures of Smart Homes. The paper described a method to create an end user product using 3D modeling and 3D printing facilities. In addition, the paper has unfolded the state-of-the-art research works carried out in the field of smart home automation using NLPs.
{"title":"Application of Natural Language Processing and IoTCloud in Smart Homes","authors":"Shubham Kumar, S. Benedict, Srilakshmi Ajith","doi":"10.1109/ICCT46177.2019.8969066","DOIUrl":"https://doi.org/10.1109/ICCT46177.2019.8969066","url":null,"abstract":"Internet of Things (IoT) based systems, most predominantly, the machine to machine communication based systems, have evolved in the recent past which helped to increase the efficiency of services offered without much necessity of human interaction. In general, IoT cloud-assisted solutions could serve several applications, including the Smart Home Automation, due to the availability of high-speed mobile networks coupled with cost effective, accessible and fast embedded hardware. In fact, there exists a few smart home solutions in the market that aim at automating the basic operations of home appliances. However, most of these systems focus on mimicking the basic operations of the electrical switches. This paper attempts to unfold a Smart Home Automation system using Natural Language Processing (NLP) and IoT cloud solutions. The proposed system was able to remotely control smart homes in a secure and in a customized manner; the approach could precisely monitor home devices with the application of GoogleAPI for integrating devices. Experiments were carried out at the IoT Cloud research lab of IIIT Kottayam such that a mini-Smart Home environment was setup to remotely control the sensors such as humidity and temperatures of Smart Homes. The paper described a method to create an end user product using 3D modeling and 3D printing facilities. In addition, the paper has unfolded the state-of-the-art research works carried out in the field of smart home automation using NLPs.","PeriodicalId":118655,"journal":{"name":"2019 2nd International Conference on Intelligent Communication and Computational Techniques (ICCT)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115156943","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 : 2019-08-20DOI: 10.1109/ICCT46177.2019.8969037
Chandra Churh Chatterjee, G. Krishna
Invasive ductal carcinoma (IDC), which is also sometimes known as the infiltrating ductal carcinoma, is the most regular form of breast cancer. It accounts to about 80% of all breast cancers. According to American Cancer Society [1], more than 180, 000 women in the United States are diagnosed with invasive breast cancer each year. The survival rate associated with this form of cancer is about 77% to 93% depending on the stage at which they are being diagnosed. The invasiveness and the frequency of the occurrence of these disease makes it one of the difficult cancers to be diagnosed. Our proposed methodology involves diagnosing the invasive ductal carcinoma with a deep residual convolution network to classify the IDC affected histopathological images from the normal images. The dataset for the purpose used is a benchmark dataset known as the Breast Histopathology Images [2]. The microscopic RGB images are converted into a seven channel image matrix, which are then fed to the network. The proposed model produces a 99.29% accurate approach towards prediction of IDC in the histopathology images with an AUROC score of 0.9996. Classification ability of the model is tested using standard performance metrics. The following methodology has been described in the next sections. Index Terms–Residual learning, CIELAB color space, Grad-CAM, Contrast adaptive histogram equalization (CLAHE), Gaussian filtering
{"title":"A Novel method for IDC Prediction in Breast Cancer Histopathology images using Deep Residual Neural Networks","authors":"Chandra Churh Chatterjee, G. Krishna","doi":"10.1109/ICCT46177.2019.8969037","DOIUrl":"https://doi.org/10.1109/ICCT46177.2019.8969037","url":null,"abstract":"Invasive ductal carcinoma (IDC), which is also sometimes known as the infiltrating ductal carcinoma, is the most regular form of breast cancer. It accounts to about 80% of all breast cancers. According to American Cancer Society [1], more than 180, 000 women in the United States are diagnosed with invasive breast cancer each year. The survival rate associated with this form of cancer is about 77% to 93% depending on the stage at which they are being diagnosed. The invasiveness and the frequency of the occurrence of these disease makes it one of the difficult cancers to be diagnosed. Our proposed methodology involves diagnosing the invasive ductal carcinoma with a deep residual convolution network to classify the IDC affected histopathological images from the normal images. The dataset for the purpose used is a benchmark dataset known as the Breast Histopathology Images [2]. The microscopic RGB images are converted into a seven channel image matrix, which are then fed to the network. The proposed model produces a 99.29% accurate approach towards prediction of IDC in the histopathology images with an AUROC score of 0.9996. Classification ability of the model is tested using standard performance metrics. The following methodology has been described in the next sections. Index Terms–Residual learning, CIELAB color space, Grad-CAM, Contrast adaptive histogram equalization (CLAHE), Gaussian filtering","PeriodicalId":118655,"journal":{"name":"2019 2nd International Conference on Intelligent Communication and Computational Techniques (ICCT)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127705041","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 : 1900-01-01DOI: 10.1109/ICCT46177.2019.8969031
A. Biswas, Sarnali Basak
Last few years in Bangladesh, the crime rate has increased rapidly. Hence it is an essential task to analyze and predict the crime so that the authority can minimize or prevent the crimes easily. In this situation, machine learning can perform a notable role to reveal the crime trends and patterns of Bangladesh. Here, various machine learning regression models i.e. linear regression, polynomial regression, and random forest regression are used to forecast the trends and patterns of crime in Bangladesh. Dataset used in this research is available for the public which is gathered from the Bangladesh police’s website. The dataset comprises record about various crime types i.e. dacoity, robbery, kidnapping, murder, women & child repression, theft, burglary, arms act, explosive, narcotics, and smuggling of Bangladesh. Firstly, training of regression models is done on the training dataset. After completion of the training, forecasting of crime is performed on the test data by the different regression models. Then we compare the forecasting results with the actual results and calculate the model evaluation metrics for the different applied regression models. After comparing the result, it is possible to find out the best-suited regression model for the crime-related data among all the applied regression models. Finally, it is observed that polynomial and random forest regression are better to predict the crime trends and patterns than the linear regression.
{"title":"Forecasting the Trends and Patterns of Crime in Bangladesh using Machine Learning Model","authors":"A. Biswas, Sarnali Basak","doi":"10.1109/ICCT46177.2019.8969031","DOIUrl":"https://doi.org/10.1109/ICCT46177.2019.8969031","url":null,"abstract":"Last few years in Bangladesh, the crime rate has increased rapidly. Hence it is an essential task to analyze and predict the crime so that the authority can minimize or prevent the crimes easily. In this situation, machine learning can perform a notable role to reveal the crime trends and patterns of Bangladesh. Here, various machine learning regression models i.e. linear regression, polynomial regression, and random forest regression are used to forecast the trends and patterns of crime in Bangladesh. Dataset used in this research is available for the public which is gathered from the Bangladesh police’s website. The dataset comprises record about various crime types i.e. dacoity, robbery, kidnapping, murder, women & child repression, theft, burglary, arms act, explosive, narcotics, and smuggling of Bangladesh. Firstly, training of regression models is done on the training dataset. After completion of the training, forecasting of crime is performed on the test data by the different regression models. Then we compare the forecasting results with the actual results and calculate the model evaluation metrics for the different applied regression models. After comparing the result, it is possible to find out the best-suited regression model for the crime-related data among all the applied regression models. Finally, it is observed that polynomial and random forest regression are better to predict the crime trends and patterns than the linear regression.","PeriodicalId":118655,"journal":{"name":"2019 2nd International Conference on Intelligent Communication and Computational Techniques (ICCT)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114358901","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：