Pub Date : 2017-05-05DOI: 10.1109/CCAA.2017.8229784
M. Devi, M. Dua
The research area of Question Answering (QA) is explored widely to provide an accurate answer to questions asked in natural languages. In the deep ocean of information, the Web, searching for a concise answer is quite a time taking task. The QA system does this task on behalf of the questioner. Recently with the introduction of the semantic web, the web is progressing towards linked data. This data is available in the form of Resource Description Format(RDF) and Web Ontology Language(OWL). Querying this data requires the query to be expressed in SPARQL Protocol and RDF Query Language(SPARQL). This paper presents a QA system on agriculture domain, the ADANS, to answer queries given in natural language. The system uses a combination of Natural Language Processing(NLP) and semantic web technologies. The system formulates an SPARQL from the queries given in natural language. The query loosening part of the system helps in retrieving some less precise answers in acceptable time.
{"title":"ADANS: An agriculture domain question answering system using ontologies","authors":"M. Devi, M. Dua","doi":"10.1109/CCAA.2017.8229784","DOIUrl":"https://doi.org/10.1109/CCAA.2017.8229784","url":null,"abstract":"The research area of Question Answering (QA) is explored widely to provide an accurate answer to questions asked in natural languages. In the deep ocean of information, the Web, searching for a concise answer is quite a time taking task. The QA system does this task on behalf of the questioner. Recently with the introduction of the semantic web, the web is progressing towards linked data. This data is available in the form of Resource Description Format(RDF) and Web Ontology Language(OWL). Querying this data requires the query to be expressed in SPARQL Protocol and RDF Query Language(SPARQL). This paper presents a QA system on agriculture domain, the ADANS, to answer queries given in natural language. The system uses a combination of Natural Language Processing(NLP) and semantic web technologies. The system formulates an SPARQL from the queries given in natural language. The query loosening part of the system helps in retrieving some less precise answers in acceptable time.","PeriodicalId":6627,"journal":{"name":"2017 International Conference on Computing, Communication and Automation (ICCCA)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82332301","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 : 2017-05-05DOI: 10.1109/CCAA.2017.8230005
Somansh Kumar, Ashish Jasuja
Air pollution is the largest environmental and public health challenge in the world today. Air pollution leads to adverse effects on Human health, climate and ecosystem. Air is getting polluted because of release of Toxic gases by industries, vehicular emissions and increased concentration of harmful gases and particulate matter in the atmosphere. Particulate matter is one of the most important parameter having the significant contribution to the increase in air pollution. This creates a need for measurement and analysis of real-time air quality monitoring so that appropriate decisions can be taken in a timely period. This paper presents a real-time standalone air quality monitoring system which includes various parameters: PM 2.5, carbon monoxide, carbon dioxide, temperature, humidity and air pressure. Internet of Things is nowadays finding profound use in each and every sector, plays a key role in our air quality monitoring system too. Internet of Things converging with cloud computing offers a novel technique for better management of data coming from different sensors, collected and transmitted by low power, low cost ARM based minicomputer Raspberry pi. The system is tested in Delhi and the measurements are compared with the data provided by the local environment control authority and are presented in a tabular form. The values of the parameters measured are shown in IBM Bluemix Cloud.
{"title":"Air quality monitoring system based on IoT using Raspberry Pi","authors":"Somansh Kumar, Ashish Jasuja","doi":"10.1109/CCAA.2017.8230005","DOIUrl":"https://doi.org/10.1109/CCAA.2017.8230005","url":null,"abstract":"Air pollution is the largest environmental and public health challenge in the world today. Air pollution leads to adverse effects on Human health, climate and ecosystem. Air is getting polluted because of release of Toxic gases by industries, vehicular emissions and increased concentration of harmful gases and particulate matter in the atmosphere. Particulate matter is one of the most important parameter having the significant contribution to the increase in air pollution. This creates a need for measurement and analysis of real-time air quality monitoring so that appropriate decisions can be taken in a timely period. This paper presents a real-time standalone air quality monitoring system which includes various parameters: PM 2.5, carbon monoxide, carbon dioxide, temperature, humidity and air pressure. Internet of Things is nowadays finding profound use in each and every sector, plays a key role in our air quality monitoring system too. Internet of Things converging with cloud computing offers a novel technique for better management of data coming from different sensors, collected and transmitted by low power, low cost ARM based minicomputer Raspberry pi. The system is tested in Delhi and the measurements are compared with the data provided by the local environment control authority and are presented in a tabular form. The values of the parameters measured are shown in IBM Bluemix Cloud.","PeriodicalId":6627,"journal":{"name":"2017 International Conference on Computing, Communication and Automation (ICCCA)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86287137","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 : 2017-05-05DOI: 10.1109/CCAA.2017.8229855
Rajendra Paudyal, S. Shakya
With Emergence of broadband access networks and powerful personal computer systems the demand for network-delivered full-motion streaming video is growing. People upload their home made videos. Different companies have started to offer software as service. Data traffic is increasing each day at an unprecedented rate creating congestion on the backbone part of the network. Backbone network congestion minimization approach is proposed to minimize the backbone network traffic by locally distributing the video files. Mininet emulator is used for simulation purpose. Custom network topology and Ryuretic framework for controller are used. Ryu controller pushes the rule when first time packet arrives to establish flow table on the switches. Server maintains the logs of video file downloaded by host. Based on its logs on database, server redirects the request towards host, P2P session is established and video file is uploaded. Uploaded data traffic flows through the access network part result on decreasing the network latency. File download rate is increased by 4 times and congestion is minimized by 66% in proposed congestion reduction approach than traditional client server approach in Software Defined Network based used topology. Validation of video file download from the server and from P2P host is verified by unique identifier MD5 checksum value.
{"title":"An approach towards backbone network congestion minimization in software defined network","authors":"Rajendra Paudyal, S. Shakya","doi":"10.1109/CCAA.2017.8229855","DOIUrl":"https://doi.org/10.1109/CCAA.2017.8229855","url":null,"abstract":"With Emergence of broadband access networks and powerful personal computer systems the demand for network-delivered full-motion streaming video is growing. People upload their home made videos. Different companies have started to offer software as service. Data traffic is increasing each day at an unprecedented rate creating congestion on the backbone part of the network. Backbone network congestion minimization approach is proposed to minimize the backbone network traffic by locally distributing the video files. Mininet emulator is used for simulation purpose. Custom network topology and Ryuretic framework for controller are used. Ryu controller pushes the rule when first time packet arrives to establish flow table on the switches. Server maintains the logs of video file downloaded by host. Based on its logs on database, server redirects the request towards host, P2P session is established and video file is uploaded. Uploaded data traffic flows through the access network part result on decreasing the network latency. File download rate is increased by 4 times and congestion is minimized by 66% in proposed congestion reduction approach than traditional client server approach in Software Defined Network based used topology. Validation of video file download from the server and from P2P host is verified by unique identifier MD5 checksum value.","PeriodicalId":6627,"journal":{"name":"2017 International Conference on Computing, Communication and Automation (ICCCA)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84620265","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 : 2017-05-05DOI: 10.1109/CCAA.2017.8230011
A. Jayaram
Inventory management is an important function of every global enterprise. Enterprises often make financial loss when the goods get misplaced and when they are lost. There is a need for a quality inventory management model that enterprises can implement easily. Enterprises can make more revenue when the inventory is managed efficiently with computational intelligence and predictive analytics. Industrial Internet of Things (IIoT) collects useful data from machines and sensors which can be used for demand forecasting of the enterprise and automation. The proposed IIoT Quality Inventory Management Model can be used for automation and demand forecasting of the inventories.
{"title":"An IIoT quality global enterprise inventory management model for automation and demand forecasting based on cloud","authors":"A. Jayaram","doi":"10.1109/CCAA.2017.8230011","DOIUrl":"https://doi.org/10.1109/CCAA.2017.8230011","url":null,"abstract":"Inventory management is an important function of every global enterprise. Enterprises often make financial loss when the goods get misplaced and when they are lost. There is a need for a quality inventory management model that enterprises can implement easily. Enterprises can make more revenue when the inventory is managed efficiently with computational intelligence and predictive analytics. Industrial Internet of Things (IIoT) collects useful data from machines and sensors which can be used for demand forecasting of the enterprise and automation. The proposed IIoT Quality Inventory Management Model can be used for automation and demand forecasting of the inventories.","PeriodicalId":6627,"journal":{"name":"2017 International Conference on Computing, Communication and Automation (ICCCA)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90263797","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 : 2017-05-05DOI: 10.1109/CCAA.2017.8229825
C. Chauhan, Smriti Sehgal
Sentiment analysis is used for Natural language Processing, text analysis, text preprocessing, Stemming etc. are the major research field in current time. Sentiment analysis using different techniques and tools for analyze the unstructured data in a manner that objective results can be generated from them. Basically, these techniques allow a computer to understand what is being said by humans. Sentiment analysis uses different techniques to determine the sentiment of a text or sentence. The Internet is a large repository of natural language. People share their thoughts and experiences which are subjective in nature. Many a time, getting suitable information about a product can became tedious for customers. Companies may not be fully aware of customer requirements. Product reviews can be analyzed to understand the sentiment of the people towards a particular topic. However, these are voluminous; therefore a summary of positive and negative reviews needs to be generated. In this paper, the main focus is on the review of algorithms and techniques used for extract feature wise summary of the product and analyzed them to form an authentic review. Future work will include more product reviews websites and will focus on higher level natural language processing tasks. Using best and new techniques or tool for more accurate result in which the system except only those keywords which are in dataset rest of the words are eliminated by the system.
{"title":"Sentiment analysis on product reviews","authors":"C. Chauhan, Smriti Sehgal","doi":"10.1109/CCAA.2017.8229825","DOIUrl":"https://doi.org/10.1109/CCAA.2017.8229825","url":null,"abstract":"Sentiment analysis is used for Natural language Processing, text analysis, text preprocessing, Stemming etc. are the major research field in current time. Sentiment analysis using different techniques and tools for analyze the unstructured data in a manner that objective results can be generated from them. Basically, these techniques allow a computer to understand what is being said by humans. Sentiment analysis uses different techniques to determine the sentiment of a text or sentence. The Internet is a large repository of natural language. People share their thoughts and experiences which are subjective in nature. Many a time, getting suitable information about a product can became tedious for customers. Companies may not be fully aware of customer requirements. Product reviews can be analyzed to understand the sentiment of the people towards a particular topic. However, these are voluminous; therefore a summary of positive and negative reviews needs to be generated. In this paper, the main focus is on the review of algorithms and techniques used for extract feature wise summary of the product and analyzed them to form an authentic review. Future work will include more product reviews websites and will focus on higher level natural language processing tasks. Using best and new techniques or tool for more accurate result in which the system except only those keywords which are in dataset rest of the words are eliminated by the system.","PeriodicalId":6627,"journal":{"name":"2017 International Conference on Computing, Communication and Automation (ICCCA)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73529055","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 : 2017-05-05DOI: 10.1109/CCAA.2017.8229926
Shreya Chadha, Utham Kumar
Ransomware is a malware that stealthily gets installed in your device and holds your files or operating system functions for ransom. It restricts you from using your PC or mobile device, by encrypting your files. Paying ransom (through Bitcoins) however, does not guarantee that you'll get your files back. Prevention is still way better than allowing yourself to be infected and then trying to find a cure. This paper aims at developing a self-learning algorithm using Machine Learning Techniques to detect Ransomware at various stages be it the Initial level, Network level or the Encryption Phase. Our approach (similar to SARVAM-semi-supervised) will be to have pro-active defence or detect early Intrusion.
{"title":"Ransomware: Let's fight back!","authors":"Shreya Chadha, Utham Kumar","doi":"10.1109/CCAA.2017.8229926","DOIUrl":"https://doi.org/10.1109/CCAA.2017.8229926","url":null,"abstract":"Ransomware is a malware that stealthily gets installed in your device and holds your files or operating system functions for ransom. It restricts you from using your PC or mobile device, by encrypting your files. Paying ransom (through Bitcoins) however, does not guarantee that you'll get your files back. Prevention is still way better than allowing yourself to be infected and then trying to find a cure. This paper aims at developing a self-learning algorithm using Machine Learning Techniques to detect Ransomware at various stages be it the Initial level, Network level or the Encryption Phase. Our approach (similar to SARVAM-semi-supervised) will be to have pro-active defence or detect early Intrusion.","PeriodicalId":6627,"journal":{"name":"2017 International Conference on Computing, Communication and Automation (ICCCA)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87442621","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 : 2017-05-05DOI: 10.1109/CCAA.2017.8229910
S. R. Basnet, S. Shakya
One of the major concerns on today's Software-Defined Network (SDN) is to enhance its security. Files sharing in SDN can be made much more secured against fraudulent activities by the implementation of blockchain technology. When the privacy of network's users is increased, the reliability of system increases correspondingly. Blockchain Security over SDN (BSS) is proposed which protects privacy and availability of resources against non-trusting members. Mininet emulator is used for simulating custom SDN network topology. OpenDaylight controller is integrated with OpenStack controller. For cloud data storage, OpenStack platform is used. For testing purpose of Blockchain, Pyethereum tester tool under Ethereum platform is implemented. Serpent programming is used for creating contract in the blockchain. BSS facilitates files sharing among SDN users in distributed peer-to-peer basis using OpenStack as a cloud storage platform.
{"title":"BSS: Blockchain security over software defined network","authors":"S. R. Basnet, S. Shakya","doi":"10.1109/CCAA.2017.8229910","DOIUrl":"https://doi.org/10.1109/CCAA.2017.8229910","url":null,"abstract":"One of the major concerns on today's Software-Defined Network (SDN) is to enhance its security. Files sharing in SDN can be made much more secured against fraudulent activities by the implementation of blockchain technology. When the privacy of network's users is increased, the reliability of system increases correspondingly. Blockchain Security over SDN (BSS) is proposed which protects privacy and availability of resources against non-trusting members. Mininet emulator is used for simulating custom SDN network topology. OpenDaylight controller is integrated with OpenStack controller. For cloud data storage, OpenStack platform is used. For testing purpose of Blockchain, Pyethereum tester tool under Ethereum platform is implemented. Serpent programming is used for creating contract in the blockchain. BSS facilitates files sharing among SDN users in distributed peer-to-peer basis using OpenStack as a cloud storage platform.","PeriodicalId":6627,"journal":{"name":"2017 International Conference on Computing, Communication and Automation (ICCCA)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74555527","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 : 2017-05-05DOI: 10.1109/CCAA.2017.8229770
Shriya Sahu, M. Chawla, N. Khare
In the growth of Information T echnology, Big data come forth as a blazing topic. The main source of human survival depends on agriculture; where it needs a key contribution in the field of crop data analysis. This paper gives a purpose about how to find experiences from accuracy agriculture information through big data approach. In this way, gathering the valuable data in an effective way drives a framework towards major computational challenges in crop analysis where information is remotely gathered. For the storage purpose of huge data availability in agriculture, we are intending Hadoop framework for our work to store a huge volume of crop data. This work gives a better prediction for the farmers to plant which kind of crops to their farm field based on their soil content to improve the productivity. The random forest algorithm is integrated with the MapReduce programming model in Hadoop framework.
{"title":"An efficient analysis of crop yield prediction using Hadoop framework based on random forest approach","authors":"Shriya Sahu, M. Chawla, N. Khare","doi":"10.1109/CCAA.2017.8229770","DOIUrl":"https://doi.org/10.1109/CCAA.2017.8229770","url":null,"abstract":"In the growth of Information T echnology, Big data come forth as a blazing topic. The main source of human survival depends on agriculture; where it needs a key contribution in the field of crop data analysis. This paper gives a purpose about how to find experiences from accuracy agriculture information through big data approach. In this way, gathering the valuable data in an effective way drives a framework towards major computational challenges in crop analysis where information is remotely gathered. For the storage purpose of huge data availability in agriculture, we are intending Hadoop framework for our work to store a huge volume of crop data. This work gives a better prediction for the farmers to plant which kind of crops to their farm field based on their soil content to improve the productivity. The random forest algorithm is integrated with the MapReduce programming model in Hadoop framework.","PeriodicalId":6627,"journal":{"name":"2017 International Conference on Computing, Communication and Automation (ICCCA)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91307292","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 : 2017-05-05DOI: 10.1109/CCAA.2017.8229817
U. K. Prodhan, Mohammad Zahidur Rahman, I. Jahan, Ahsin Abid, Mohtasim Bellah
At present telemedicine is widely used in developing countries for its variety of health services. In this paper, we have developed a low cost portable telemedicine tool kit for remote diagnosis of patients. Remote patient monitoring is one of the vital component of any telemedicine services. We have successfully able to collect patient data from any remote locations by using our developed tool kit. In this research, we have collected seven vital signs of patient's data such as blood pressure, pulse and oxygen in blood, blood glucose level, patient position and falls, body temperature, electrical and muscular functions of the heart through ECG and airflow: breathing through our device in an automated manner. Our developed device is portable and can be used easily with any telemedicine model. In this study, we have developed an android app for collecting the patient data from our device, controlling the device and sending data to the server for telemedicine application. We have made simple user interface of app for better understandability of users. Finally, we can say that our developed portable telemedicine tool kit can be an useful and integrated component of any telemedicine model which will assist the researchers for their applications.
{"title":"Development of a portable telemedicine tool for remote diagnosis of telemedicine application","authors":"U. K. Prodhan, Mohammad Zahidur Rahman, I. Jahan, Ahsin Abid, Mohtasim Bellah","doi":"10.1109/CCAA.2017.8229817","DOIUrl":"https://doi.org/10.1109/CCAA.2017.8229817","url":null,"abstract":"At present telemedicine is widely used in developing countries for its variety of health services. In this paper, we have developed a low cost portable telemedicine tool kit for remote diagnosis of patients. Remote patient monitoring is one of the vital component of any telemedicine services. We have successfully able to collect patient data from any remote locations by using our developed tool kit. In this research, we have collected seven vital signs of patient's data such as blood pressure, pulse and oxygen in blood, blood glucose level, patient position and falls, body temperature, electrical and muscular functions of the heart through ECG and airflow: breathing through our device in an automated manner. Our developed device is portable and can be used easily with any telemedicine model. In this study, we have developed an android app for collecting the patient data from our device, controlling the device and sending data to the server for telemedicine application. We have made simple user interface of app for better understandability of users. Finally, we can say that our developed portable telemedicine tool kit can be an useful and integrated component of any telemedicine model which will assist the researchers for their applications.","PeriodicalId":6627,"journal":{"name":"2017 International Conference on Computing, Communication and Automation (ICCCA)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84971129","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 : 2017-05-05DOI: 10.1109/CCAA.2017.8229917
N. Neupane, S. Shakya
The system security has turned into an extremely critical worry as system assaults have been extending with the ascent of hacking devices, inconvenience of systems and interruptions in number and brutality. This paper is centered around interruption identification by utilizing Multilayer Perceptron (MLP) with various calculation of backpropagation neural network. In this paper, performance of various backpropagation algorithms has been evaluated using KDDCup99 dataset. The dataset has been preprocessed to be made suitable for neural network input and the input set and target set are separated. The modified dataset has been used to evaluate the performance of BFGS Quasi-Newton, Levenberg-Marquardt, and Gradient Descent with Adaptive backpropagation algorithm. Different performance parameters such as mean square error, attack detection rate, recall rate, precision rate, epochs has been used for the algorithm comparison. Based on the evaluation results, the research purposes Levenberg-Marquardt backpropagation algorithm to be the best performing and efficient algorithm for the network intrusion detection for KDD Cup dataset. Different classes of attacks have been also determined comparing the output values obtained with the target set.
{"title":"Comparative analysis of backpropagation algorithm variants for network intrusion detection","authors":"N. Neupane, S. Shakya","doi":"10.1109/CCAA.2017.8229917","DOIUrl":"https://doi.org/10.1109/CCAA.2017.8229917","url":null,"abstract":"The system security has turned into an extremely critical worry as system assaults have been extending with the ascent of hacking devices, inconvenience of systems and interruptions in number and brutality. This paper is centered around interruption identification by utilizing Multilayer Perceptron (MLP) with various calculation of backpropagation neural network. In this paper, performance of various backpropagation algorithms has been evaluated using KDDCup99 dataset. The dataset has been preprocessed to be made suitable for neural network input and the input set and target set are separated. The modified dataset has been used to evaluate the performance of BFGS Quasi-Newton, Levenberg-Marquardt, and Gradient Descent with Adaptive backpropagation algorithm. Different performance parameters such as mean square error, attack detection rate, recall rate, precision rate, epochs has been used for the algorithm comparison. Based on the evaluation results, the research purposes Levenberg-Marquardt backpropagation algorithm to be the best performing and efficient algorithm for the network intrusion detection for KDD Cup dataset. Different classes of attacks have been also determined comparing the output values obtained with the target set.","PeriodicalId":6627,"journal":{"name":"2017 International Conference on Computing, Communication and Automation (ICCCA)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84002511","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：