Pub Date : 2019-10-01DOI: 10.1109/ICCCIS48478.2019.8974511
Archit Tiwari, Nikhil Sharma, I. Kaushik, Ratik Tiwari
Big Data, as the name suggests is a process of collection of information in a very large amount and storing it in a multidimensional database of various organizations and thereby performing Analytical operations on it to increase their efficiency and enhance their ability of decision making. Strategies can be made using this technology which uses real time using Big Data Analytics. The main advantage of the technology of big data is that the user gets a complete and an accurate view of answers to all those questions raised by the user in processes related to business decisions. Moreover, the errors which exist within any organization can be identified with the help of this technology. This is due to the real time intuition which helps the organizations identify the errors. Also, in case if any on sanctioned user intends to cheat the organization with the valuable data stored at the database of the organization, the it can be detected at the instant it happens and so suitable measures can be taken against that unsanctioned user. Despite of having so many advantages, it has some limitations also. One of the main issues of concern of this technology is Privacy security. This paper focuses on identifying the threats related to data privacy information stored on the database of the organization and access control systems.
{"title":"Privacy Issues & Security Techniques in Big Data","authors":"Archit Tiwari, Nikhil Sharma, I. Kaushik, Ratik Tiwari","doi":"10.1109/ICCCIS48478.2019.8974511","DOIUrl":"https://doi.org/10.1109/ICCCIS48478.2019.8974511","url":null,"abstract":"Big Data, as the name suggests is a process of collection of information in a very large amount and storing it in a multidimensional database of various organizations and thereby performing Analytical operations on it to increase their efficiency and enhance their ability of decision making. Strategies can be made using this technology which uses real time using Big Data Analytics. The main advantage of the technology of big data is that the user gets a complete and an accurate view of answers to all those questions raised by the user in processes related to business decisions. Moreover, the errors which exist within any organization can be identified with the help of this technology. This is due to the real time intuition which helps the organizations identify the errors. Also, in case if any on sanctioned user intends to cheat the organization with the valuable data stored at the database of the organization, the it can be detected at the instant it happens and so suitable measures can be taken against that unsanctioned user. Despite of having so many advantages, it has some limitations also. One of the main issues of concern of this technology is Privacy security. This paper focuses on identifying the threats related to data privacy information stored on the database of the organization and access control systems.","PeriodicalId":436154,"journal":{"name":"2019 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127795459","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 : 2019-10-01DOI: 10.1109/ICCCIS48478.2019.8974545
Hasan Mujtaba Research Scholar, Pallavi Gupta, Gajendra Singh
Path planning contributes a significant role in a mobile robot. The accuracy of path depends upon mapping and limitation of an indoor environment. Various methodology are now in applications like A* Algorithms, D* Algorithm (Heuristic Approach), Dijkstra’s Algorithm (Deterministic methodology), Cell Decomposition Technique. This paper considers the path planning strategy with different target point. Global path planning method always considers the static obstacles in fixed environment where the indoor environment matrix of 50X50 with static obstacles has taken for simulation. In this paper, we propose a multi-objective method for solving the path planning problem using A* algorithm. It is a multi objective algorithm and handles three particular objectives(multiple destinations, minimum distance and safety).Consider two initial distance point on the grid, that construct a minimum distance path by using A* algorithm. At the destination node the minimum path has been calculated by adding all the minimum distance of two consecutive-nodes. For a safe simulation of path planning also virtual cell are consider around the static obstacles, so for the collision free or safe path has been created with shortest distance at multiple nodes or target.
{"title":"Path Planning of An Autonomous Mobile Robot With Multiobjective Functions","authors":"Hasan Mujtaba Research Scholar, Pallavi Gupta, Gajendra Singh","doi":"10.1109/ICCCIS48478.2019.8974545","DOIUrl":"https://doi.org/10.1109/ICCCIS48478.2019.8974545","url":null,"abstract":"Path planning contributes a significant role in a mobile robot. The accuracy of path depends upon mapping and limitation of an indoor environment. Various methodology are now in applications like A* Algorithms, D* Algorithm (Heuristic Approach), Dijkstra’s Algorithm (Deterministic methodology), Cell Decomposition Technique. This paper considers the path planning strategy with different target point. Global path planning method always considers the static obstacles in fixed environment where the indoor environment matrix of 50X50 with static obstacles has taken for simulation. In this paper, we propose a multi-objective method for solving the path planning problem using A* algorithm. It is a multi objective algorithm and handles three particular objectives(multiple destinations, minimum distance and safety).Consider two initial distance point on the grid, that construct a minimum distance path by using A* algorithm. At the destination node the minimum path has been calculated by adding all the minimum distance of two consecutive-nodes. For a safe simulation of path planning also virtual cell are consider around the static obstacles, so for the collision free or safe path has been created with shortest distance at multiple nodes or target.","PeriodicalId":436154,"journal":{"name":"2019 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS)","volume":"112 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131776449","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 : 2019-10-01DOI: 10.1109/ICCCIS48478.2019.8974555
S. Soni, Amisha Kaushik, V. Niranjan, Ashwini Kumar
This Paper presents proposed noble technology to perform fast operation of CMOS Operational transconductance amplifier (OTA). In this paper Gain enhancement technique implies positive feedback system to enhance the overall performance of the circuit output. For fast operation of OTA NMOS adaptive biasing is used with 5.5$mu$ A Quiescent current source (IB). Miller frequency compensation is used to provide stability to the circuit. Comparative study has been done in tabular and graphical form. This work has been done on 18$theta$ nm technology using EDA Cadence Virtuoso for schematic designing and other analysis. At input 1. 8V supply voltage 94. 12dB gain is measured with 294nW with 35.23$displaystyle frac{V}{mu s}$ and-37.5 $displaystyle frac{gamma}{mu s}$ positive and negative slew rate respectively. Power consumption and load capacitance CL is of 2 $theta$ pf is used to take output.
{"title":"High Speed Power Efficient, Noble Performance OTA Using Adaptive Biasing Technique","authors":"S. Soni, Amisha Kaushik, V. Niranjan, Ashwini Kumar","doi":"10.1109/ICCCIS48478.2019.8974555","DOIUrl":"https://doi.org/10.1109/ICCCIS48478.2019.8974555","url":null,"abstract":"This Paper presents proposed noble technology to perform fast operation of CMOS Operational transconductance amplifier (OTA). In this paper Gain enhancement technique implies positive feedback system to enhance the overall performance of the circuit output. For fast operation of OTA NMOS adaptive biasing is used with 5.5$mu$ A Quiescent current source (IB). Miller frequency compensation is used to provide stability to the circuit. Comparative study has been done in tabular and graphical form. This work has been done on 18$theta$ nm technology using EDA Cadence Virtuoso for schematic designing and other analysis. At input 1. 8V supply voltage 94. 12dB gain is measured with 294nW with 35.23$displaystyle frac{V}{mu s}$ and-37.5 $displaystyle frac{gamma}{mu s}$ positive and negative slew rate respectively. Power consumption and load capacitance CL is of 2 $theta$ pf is used to take output.","PeriodicalId":436154,"journal":{"name":"2019 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134584005","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 : 2019-10-01DOI: 10.1109/ICCCIS48478.2019.8974486
Wudu Worku, A. Mishra, R. Priyadarshini
The integration of wireless sensors and wireless communication technology are important components for the development of automatic weather stations. These devices have a significant role in gathering real weather information provided by the automatic weather device. This paper is focused on analyzing the sensors type and different wireless communication performance based on power consumption, data rate, range and accuracy to carry out cost effective, long term stable, best performance communication device and select highly sensitive sensors for hardware automatic weather station development.
{"title":"Qualitative analysis for sensors and wireless communications modules for development of weather station monitoring system","authors":"Wudu Worku, A. Mishra, R. Priyadarshini","doi":"10.1109/ICCCIS48478.2019.8974486","DOIUrl":"https://doi.org/10.1109/ICCCIS48478.2019.8974486","url":null,"abstract":"The integration of wireless sensors and wireless communication technology are important components for the development of automatic weather stations. These devices have a significant role in gathering real weather information provided by the automatic weather device. This paper is focused on analyzing the sensors type and different wireless communication performance based on power consumption, data rate, range and accuracy to carry out cost effective, long term stable, best performance communication device and select highly sensitive sensors for hardware automatic weather station development.","PeriodicalId":436154,"journal":{"name":"2019 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS)","volume":"300 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123751175","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 : 2019-10-01DOI: 10.1109/ICCCIS48478.2019.8974498
M. Gorai, M. Nene
Data plays the most significant role to attain efficiency in performing a task using Machine Learning (ML) techniques. Metadata (MD) represents data of data. MD extraction and data attribute selection play a vital role in defining the performance of ML models. The study in this paper focuses on the role of MD, data attributes and data models that define the learning capability of ML to evolve with human-like capability to learn and draw inferences. To evolve with such artificially intelligent autonomous systems, the study in this paper is a preliminary step towards applying ML techniques on textual data for performing syntactic analysis, further to evolve with semantic and behavioral analysis. Based on the rigorous survey study and observations, this paper concludes with the description of the parameters to quantify the performance of ML model which are essential to define the performance characteristics of ML. The increased deployment of ML is observed in the recent Artificial Intelligence arena, and hence the study contributes towards evolving performance parameters in applications that employ ML techniquestextbf.
{"title":"Utilization of Metadata and Data Models to Enhance Machine Learning","authors":"M. Gorai, M. Nene","doi":"10.1109/ICCCIS48478.2019.8974498","DOIUrl":"https://doi.org/10.1109/ICCCIS48478.2019.8974498","url":null,"abstract":"Data plays the most significant role to attain efficiency in performing a task using Machine Learning (ML) techniques. Metadata (MD) represents data of data. MD extraction and data attribute selection play a vital role in defining the performance of ML models. The study in this paper focuses on the role of MD, data attributes and data models that define the learning capability of ML to evolve with human-like capability to learn and draw inferences. To evolve with such artificially intelligent autonomous systems, the study in this paper is a preliminary step towards applying ML techniques on textual data for performing syntactic analysis, further to evolve with semantic and behavioral analysis. Based on the rigorous survey study and observations, this paper concludes with the description of the parameters to quantify the performance of ML model which are essential to define the performance characteristics of ML. The increased deployment of ML is observed in the recent Artificial Intelligence arena, and hence the study contributes towards evolving performance parameters in applications that employ ML techniquestextbf.","PeriodicalId":436154,"journal":{"name":"2019 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125278434","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 : 2019-10-01DOI: 10.1109/ICCCIS48478.2019.8974481
Ratik Tiwari, Nikhil Sharma, I. Kaushik, Archit Tiwari, B. Bhushan
In today’s world, we are surrounded by enormous devices that sense some sort of data and gives a particular output. To track the record and manage that data by connecting all devices in a network in such an efficient manner that it can be utilized in favour of mankind, this is what we call as Internet of Things. It is very difficult task to manage such a huge amount of data with great efficiency, but here the Internet of Things along with concepts of Deep Learning plays a vital role in successful completion of the task. In this paper, you are about see an absolute overview about the analytics that are used to maintain and process huge amount of input data using the concepts of Deep Learning in the very domain of Internet of Things. Firstly, we start by giving a brief description about Internet of Things and some characteristics and requirements possessed by it. We will also explain some major key factors that make deep learning a good choice for implementation of Internet of Things. Also, we have discussed about the concept of Big Data and what role it has in Internet of Things. We have evaluated some research attempts made in the very domain of Internet of Things and Deep Learning. Finally, we have explained some real-life applications and the concept behind them in this paper.
{"title":"Evolution of IoT & Data Analytics using Deep Learning","authors":"Ratik Tiwari, Nikhil Sharma, I. Kaushik, Archit Tiwari, B. Bhushan","doi":"10.1109/ICCCIS48478.2019.8974481","DOIUrl":"https://doi.org/10.1109/ICCCIS48478.2019.8974481","url":null,"abstract":"In today’s world, we are surrounded by enormous devices that sense some sort of data and gives a particular output. To track the record and manage that data by connecting all devices in a network in such an efficient manner that it can be utilized in favour of mankind, this is what we call as Internet of Things. It is very difficult task to manage such a huge amount of data with great efficiency, but here the Internet of Things along with concepts of Deep Learning plays a vital role in successful completion of the task. In this paper, you are about see an absolute overview about the analytics that are used to maintain and process huge amount of input data using the concepts of Deep Learning in the very domain of Internet of Things. Firstly, we start by giving a brief description about Internet of Things and some characteristics and requirements possessed by it. We will also explain some major key factors that make deep learning a good choice for implementation of Internet of Things. Also, we have discussed about the concept of Big Data and what role it has in Internet of Things. We have evaluated some research attempts made in the very domain of Internet of Things and Deep Learning. Finally, we have explained some real-life applications and the concept behind them in this paper.","PeriodicalId":436154,"journal":{"name":"2019 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130826844","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 : 2019-10-01DOI: 10.1109/ICCCIS48478.2019.8974509
Ksh. Nilakanta Singh, L. S. Singh, K. Singh
This paper presents a decision support system for post mortem inspection of slaughtered pigs to help pig abattoirs in producing quality pork. Valuable information on pig health can be achieved by means of computer application. A noble method for decision making on post mortem inspection of pigs using different machine learning techniques is presented here. It is important to make an accurate decision for pork consumption from the post mortem finding of the pig to prevent consumption of unhealthy meat. The proposed system collects the comprehensive information regarding the post mortem decisions related to pig from the veterinary experts. Different models of Machine Learning Algorithms are trained in this system to perform a comparative study in terms of different performance measures. It is found that the predictive model with Support Vector Machine(SVM) is the best performing model for making a decision on the post mortem health of a pig for the pig datasets. By using the developed predictive machine learning model, it is able to take a decision on normal, partial condemnation or total condemnation of a post mortem pig with high accuracy.
{"title":"Machine Learning based Decision Support System for Post Mortem Inspection of Pig Health","authors":"Ksh. Nilakanta Singh, L. S. Singh, K. Singh","doi":"10.1109/ICCCIS48478.2019.8974509","DOIUrl":"https://doi.org/10.1109/ICCCIS48478.2019.8974509","url":null,"abstract":"This paper presents a decision support system for post mortem inspection of slaughtered pigs to help pig abattoirs in producing quality pork. Valuable information on pig health can be achieved by means of computer application. A noble method for decision making on post mortem inspection of pigs using different machine learning techniques is presented here. It is important to make an accurate decision for pork consumption from the post mortem finding of the pig to prevent consumption of unhealthy meat. The proposed system collects the comprehensive information regarding the post mortem decisions related to pig from the veterinary experts. Different models of Machine Learning Algorithms are trained in this system to perform a comparative study in terms of different performance measures. It is found that the predictive model with Support Vector Machine(SVM) is the best performing model for making a decision on the post mortem health of a pig for the pig datasets. By using the developed predictive machine learning model, it is able to take a decision on normal, partial condemnation or total condemnation of a post mortem pig with high accuracy.","PeriodicalId":436154,"journal":{"name":"2019 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117012360","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 : 2019-10-01DOI: 10.1109/ICCCIS48478.2019.8974475
Ishita Parashar, Pinky Kaushik, V. Niranjan
The percentage of the aged people in the world’s population is rising continuously. Hence, there is a need to provide better technological support to elderly. A modern global objective with the purpose of providing better help to the aged people is seen wherein a good deal of research has been taking place in the areas of ambient intelligence.We propose an ambient intelligent model circuit for the elderly by utilizing sensors, GSM module and a speaker interfaced with Arduino Uno. This model provides assistance to the elderly by alerting the person himself or care taker in the vicinityusing a speaker. This also helps old people with poor vision to get to know about an abnormal condition immediately. At the same time, a message is sent to alert the friends, family or caregiver in the situation of emergency.
{"title":"Intelligent System for Health Monitoring Applications","authors":"Ishita Parashar, Pinky Kaushik, V. Niranjan","doi":"10.1109/ICCCIS48478.2019.8974475","DOIUrl":"https://doi.org/10.1109/ICCCIS48478.2019.8974475","url":null,"abstract":"The percentage of the aged people in the world’s population is rising continuously. Hence, there is a need to provide better technological support to elderly. A modern global objective with the purpose of providing better help to the aged people is seen wherein a good deal of research has been taking place in the areas of ambient intelligence.We propose an ambient intelligent model circuit for the elderly by utilizing sensors, GSM module and a speaker interfaced with Arduino Uno. This model provides assistance to the elderly by alerting the person himself or care taker in the vicinityusing a speaker. This also helps old people with poor vision to get to know about an abnormal condition immediately. At the same time, a message is sent to alert the friends, family or caregiver in the situation of emergency.","PeriodicalId":436154,"journal":{"name":"2019 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133311558","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 : 2019-10-01DOI: 10.1109/ICCCIS48478.2019.8974471
Mohd. Yousuf Ansari, Mainuddin, Anand Prakash
Clustering is a method to discover inherent natural structure in a set of objects involved in any phenomenon. In this study, we extended DBSCAN algorithm for spatiotemporal data by defining attribute based mass function, density function and hence modifying definition of core objects for clustering. The proposed work generalizes the concept of using an attribute to define notion of relative importance of an object to define density in the dataset. We have used a real fire dataset to validate the proposed approach. We also compare our algorithm with DBSCAN based algorithm which is extended for spatiotemporal data. The experimental results reveal that our proposed algorithm is able to identify intrinsic information based hidden clusters, which DBSCAN based algorithm is unable to identify.
{"title":"Density Based Algorithm for Spatiotemporal Data","authors":"Mohd. Yousuf Ansari, Mainuddin, Anand Prakash","doi":"10.1109/ICCCIS48478.2019.8974471","DOIUrl":"https://doi.org/10.1109/ICCCIS48478.2019.8974471","url":null,"abstract":"Clustering is a method to discover inherent natural structure in a set of objects involved in any phenomenon. In this study, we extended DBSCAN algorithm for spatiotemporal data by defining attribute based mass function, density function and hence modifying definition of core objects for clustering. The proposed work generalizes the concept of using an attribute to define notion of relative importance of an object to define density in the dataset. We have used a real fire dataset to validate the proposed approach. We also compare our algorithm with DBSCAN based algorithm which is extended for spatiotemporal data. The experimental results reveal that our proposed algorithm is able to identify intrinsic information based hidden clusters, which DBSCAN based algorithm is unable to identify.","PeriodicalId":436154,"journal":{"name":"2019 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS)","volume":"111 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132314923","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 : 2019-10-01DOI: 10.1109/ICCCIS48478.2019.8974514
Gurjyot Singh Kalra, Ramandeep Singh Kathuria, Amit Kumar
YouTube has a library of millions if not billions of videos and keeping a track of the types of videos for effective retrieval and use can be quite difficult. YouTube videos can be classified into different classes based on the title and descriptions of the videos. To classify so many videos, an effective scalable algorithm is required. This can be achieved by using a Random Forest Classifier along with Natural Language Processing techniques like Bag of Words, Word Stemming etc. This paper also discusses method to scrape YouTube videos using packages like selenium, requests and Beautiful Soup for videos and their metadata. At the end we discuss various evaluation metrics for Random Forest Classifiers.
{"title":"YouTube Video Classification based on Title and Description Text","authors":"Gurjyot Singh Kalra, Ramandeep Singh Kathuria, Amit Kumar","doi":"10.1109/ICCCIS48478.2019.8974514","DOIUrl":"https://doi.org/10.1109/ICCCIS48478.2019.8974514","url":null,"abstract":"YouTube has a library of millions if not billions of videos and keeping a track of the types of videos for effective retrieval and use can be quite difficult. YouTube videos can be classified into different classes based on the title and descriptions of the videos. To classify so many videos, an effective scalable algorithm is required. This can be achieved by using a Random Forest Classifier along with Natural Language Processing techniques like Bag of Words, Word Stemming etc. This paper also discusses method to scrape YouTube videos using packages like selenium, requests and Beautiful Soup for videos and their metadata. At the end we discuss various evaluation metrics for Random Forest Classifiers.","PeriodicalId":436154,"journal":{"name":"2019 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS)","volume":"130 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114284952","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：