Pub Date : 2018-03-23DOI: 10.1109/INFOCT.2018.8356848
Silvia Bravo, D. Mauricio
DDoS attacks are one of the most damaging computer aggressions of recent times. Attackers send large number of requests to saturate a victim machine and it stops providing its services to legitimate users. In general attacks are directed to the network layer and the application layer, the latter has been increasing due mainly to its easy execution and difficult detection. The present work proposes a low cost detection approach that uses the characteristics of the Web User for the detection of attacks. To do this, the features are extracted in real time using functions designed in PHP and JavaScript. They are evaluated by an order 1 classifier to differentiate a real user from a DDoS attack. A real user is identified by making requests interacting with the computer system, while DDoS attacks are requests sent by robots to overload the system with indiscriminate requests. The tests were executed on a computer system using requests from real users and attacks using the LOIC, OWASP and GoldenEye tools. The results show that the proposed method has a detection efficiency of 100%, and that the characteristics of the web user allow to differentiate between a real user and a robot.
{"title":"DDoS attack detection mechanism in the application layer using user features","authors":"Silvia Bravo, D. Mauricio","doi":"10.1109/INFOCT.2018.8356848","DOIUrl":"https://doi.org/10.1109/INFOCT.2018.8356848","url":null,"abstract":"DDoS attacks are one of the most damaging computer aggressions of recent times. Attackers send large number of requests to saturate a victim machine and it stops providing its services to legitimate users. In general attacks are directed to the network layer and the application layer, the latter has been increasing due mainly to its easy execution and difficult detection. The present work proposes a low cost detection approach that uses the characteristics of the Web User for the detection of attacks. To do this, the features are extracted in real time using functions designed in PHP and JavaScript. They are evaluated by an order 1 classifier to differentiate a real user from a DDoS attack. A real user is identified by making requests interacting with the computer system, while DDoS attacks are requests sent by robots to overload the system with indiscriminate requests. The tests were executed on a computer system using requests from real users and attacks using the LOIC, OWASP and GoldenEye tools. The results show that the proposed method has a detection efficiency of 100%, and that the characteristics of the web user allow to differentiate between a real user and a robot.","PeriodicalId":376443,"journal":{"name":"2018 International Conference on Information and Computer Technologies (ICICT)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115088899","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 : 2018-03-23DOI: 10.1109/INFOCT.2018.8356852
Takafumi Katayama, Kazuki Kuroda, Wen Shi, Tian Song, T. Shimamoto
In this paper, we propose a fast coding unit (CU) size decision algorithm for high efficiency video coding (HEVC) based on convolutional neural network. The proposed fast algorithm contributes to decrease no less than two CU partition modes in each coding tree unit for full rate-distortion optimization processing, thereby reducing the encoder hardware complexity. Moreover, our algorithm use only texture information and it does not depend on the correlations among CU depths or spatially nearby CUs. It is friendly to the parallel processing and it can improve the pipeline process of RDO. The proposed algorithm is implemented in the reference software of HEVC (HM16.7). The simulation results show that the proposed algorithm can achieve over 67.3% computation complexity reduction comparing to the original HEVC algorithm.
{"title":"Low-complexity intra coding algorithm based on convolutional neural network for HEVC","authors":"Takafumi Katayama, Kazuki Kuroda, Wen Shi, Tian Song, T. Shimamoto","doi":"10.1109/INFOCT.2018.8356852","DOIUrl":"https://doi.org/10.1109/INFOCT.2018.8356852","url":null,"abstract":"In this paper, we propose a fast coding unit (CU) size decision algorithm for high efficiency video coding (HEVC) based on convolutional neural network. The proposed fast algorithm contributes to decrease no less than two CU partition modes in each coding tree unit for full rate-distortion optimization processing, thereby reducing the encoder hardware complexity. Moreover, our algorithm use only texture information and it does not depend on the correlations among CU depths or spatially nearby CUs. It is friendly to the parallel processing and it can improve the pipeline process of RDO. The proposed algorithm is implemented in the reference software of HEVC (HM16.7). The simulation results show that the proposed algorithm can achieve over 67.3% computation complexity reduction comparing to the original HEVC algorithm.","PeriodicalId":376443,"journal":{"name":"2018 International Conference on Information and Computer Technologies (ICICT)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124683852","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 : 2018-03-23DOI: 10.1109/INFOCT.2018.8356832
Mahwish Amjad, Faisal Iradat
Big data generated from wireless devices bring distinct challenges for the researchers due to its inherent spatial temporal nature. Reviewing existing literature on wireless big data, two major challenges are identified, processing and storage. To address these challenges various methodologies/approaches have been proposed and presented in the recent literature. To present the existing state of research on challenges associated with wireless big data, we present a systematic literature review of selected publications that address these issues. We also present areas which have not been addressed in the existing literature.
{"title":"A brief review of methods and approaches proposed in existing literature to address issues in wireless big data","authors":"Mahwish Amjad, Faisal Iradat","doi":"10.1109/INFOCT.2018.8356832","DOIUrl":"https://doi.org/10.1109/INFOCT.2018.8356832","url":null,"abstract":"Big data generated from wireless devices bring distinct challenges for the researchers due to its inherent spatial temporal nature. Reviewing existing literature on wireless big data, two major challenges are identified, processing and storage. To address these challenges various methodologies/approaches have been proposed and presented in the recent literature. To present the existing state of research on challenges associated with wireless big data, we present a systematic literature review of selected publications that address these issues. We also present areas which have not been addressed in the existing literature.","PeriodicalId":376443,"journal":{"name":"2018 International Conference on Information and Computer Technologies (ICICT)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129685540","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 : 2018-03-23DOI: 10.1109/INFOCT.2018.8356835
R. Bulusu, Pallav Jain, Pravin Pawar, M. Afzal, Sanjay Wandhekar
Today High-Performance Computing (HPC) market is finding an increasing rate of adoption of the technology in a number of industries and verticals. With the increased adoption of the HPC technology, there is also rise in the concerns with the security aspects of this technology. Many of the system engineers and technologists that worked closely with the HPC technology believes HPC security posture is in parity with traditional computer infrastructure security. The goal of this paper is to share the learning of common security gaps and also to increase awareness in the market on how best to alleviate the security concerns for the HPC deployments. After analyzing many of the HPC deployments, at Centre for Development of Advanced Computing (CDAC), Indian Institutes of Technology (IITs), and National Institutes of Technology (NITs) in India, CDAC team has identified many common security loopholes and corresponding solutions for better security environment without fundamentally changing how they have deployed and way of using the HPC infrastructure.
{"title":"Addressing security aspects for HPC infrastructure","authors":"R. Bulusu, Pallav Jain, Pravin Pawar, M. Afzal, Sanjay Wandhekar","doi":"10.1109/INFOCT.2018.8356835","DOIUrl":"https://doi.org/10.1109/INFOCT.2018.8356835","url":null,"abstract":"Today High-Performance Computing (HPC) market is finding an increasing rate of adoption of the technology in a number of industries and verticals. With the increased adoption of the HPC technology, there is also rise in the concerns with the security aspects of this technology. Many of the system engineers and technologists that worked closely with the HPC technology believes HPC security posture is in parity with traditional computer infrastructure security. The goal of this paper is to share the learning of common security gaps and also to increase awareness in the market on how best to alleviate the security concerns for the HPC deployments. After analyzing many of the HPC deployments, at Centre for Development of Advanced Computing (CDAC), Indian Institutes of Technology (IITs), and National Institutes of Technology (NITs) in India, CDAC team has identified many common security loopholes and corresponding solutions for better security environment without fundamentally changing how they have deployed and way of using the HPC infrastructure.","PeriodicalId":376443,"journal":{"name":"2018 International Conference on Information and Computer Technologies (ICICT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129158457","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 : 2018-03-23DOI: 10.1109/INFOCT.2018.8356836
Xiankai Meng, QingPing Tan, Z. Shao, N. Zhang, Jianjun Xu, -Haoyu Zhang
In the space environment, computer is easily affected by high-energy particle irradiation, which may incur transient faults, also known as soft errors. Soft error is one of the serious problems for space computation, making the space computer system unreliable. Many efforts have been made in this research area. One of them is fault injection technique, an experimental method for software reliability evaluation. To evaluate the software reliability running on x86/x64 architecture, we have designed a fault injection framework SEInjector. Like many other fault injection tools, SEInjector has been designed as making statistically sampling by randomized selection of fault locations. But, in some cases, we need detail analysis for fault-tolerance related design decisions, and full fault space exploration is required. However, the vast fault space makes the complete fault space exploration impractical. In this paper, we propose several methods to prune the fault space. We prune the known-outcome faults by the registers usage information, and we prune faults leading to the same outcome by classify the faults into equivalence classes. Experiment and calculation show that using these methods, the full fault space coverage time consumption can be largely reduced.
{"title":"Optimization methods for the fault injection tool SEInjector","authors":"Xiankai Meng, QingPing Tan, Z. Shao, N. Zhang, Jianjun Xu, -Haoyu Zhang","doi":"10.1109/INFOCT.2018.8356836","DOIUrl":"https://doi.org/10.1109/INFOCT.2018.8356836","url":null,"abstract":"In the space environment, computer is easily affected by high-energy particle irradiation, which may incur transient faults, also known as soft errors. Soft error is one of the serious problems for space computation, making the space computer system unreliable. Many efforts have been made in this research area. One of them is fault injection technique, an experimental method for software reliability evaluation. To evaluate the software reliability running on x86/x64 architecture, we have designed a fault injection framework SEInjector. Like many other fault injection tools, SEInjector has been designed as making statistically sampling by randomized selection of fault locations. But, in some cases, we need detail analysis for fault-tolerance related design decisions, and full fault space exploration is required. However, the vast fault space makes the complete fault space exploration impractical. In this paper, we propose several methods to prune the fault space. We prune the known-outcome faults by the registers usage information, and we prune faults leading to the same outcome by classify the faults into equivalence classes. Experiment and calculation show that using these methods, the full fault space coverage time consumption can be largely reduced.","PeriodicalId":376443,"journal":{"name":"2018 International Conference on Information and Computer Technologies (ICICT)","volume":"82 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133872899","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 : 2018-03-23DOI: 10.1109/INFOCT.2018.8356846
Dawei Li, Jie Wu, Dajin Wang
In this paper, we consider IP fast recovery from single-link failures in a given network topology. The basic idea is to replace some existing routers with a designated switch. When a link fails, the affected router will send all the affected traffic to the designated switch (through pre-configured IP tunnels), which will deliver the affected traffic to its destination without using the failed link. The goal of the approach is to achieve faster failure recovery than traditional routing protocols that employ reactive computing upon link failures. Software-Defined Networking (SDN) switches can serve as the designated switches because they can flexibly redirect affected traffic to other routes, instead of only to the shortest paths in the network. However, SDN switches are very expensive. Our objective is to minimize the number of SDN switches needed and to guarantee that the network can still recover from any single-link failure. For networks with uniform link costs, we show that using normal non-SDN switches with IP tunneling capability as designated switches can guarantee recovery from any single-link failure. For networks with general link costs, we show that by using SDN switches only when necessary, we can reduce the total number of SDN switches needed compared to an existing work.
{"title":"Single-link failure recovery with or without software-defined networking switches","authors":"Dawei Li, Jie Wu, Dajin Wang","doi":"10.1109/INFOCT.2018.8356846","DOIUrl":"https://doi.org/10.1109/INFOCT.2018.8356846","url":null,"abstract":"In this paper, we consider IP fast recovery from single-link failures in a given network topology. The basic idea is to replace some existing routers with a designated switch. When a link fails, the affected router will send all the affected traffic to the designated switch (through pre-configured IP tunnels), which will deliver the affected traffic to its destination without using the failed link. The goal of the approach is to achieve faster failure recovery than traditional routing protocols that employ reactive computing upon link failures. Software-Defined Networking (SDN) switches can serve as the designated switches because they can flexibly redirect affected traffic to other routes, instead of only to the shortest paths in the network. However, SDN switches are very expensive. Our objective is to minimize the number of SDN switches needed and to guarantee that the network can still recover from any single-link failure. For networks with uniform link costs, we show that using normal non-SDN switches with IP tunneling capability as designated switches can guarantee recovery from any single-link failure. For networks with general link costs, we show that by using SDN switches only when necessary, we can reduce the total number of SDN switches needed compared to an existing work.","PeriodicalId":376443,"journal":{"name":"2018 International Conference on Information and Computer Technologies (ICICT)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123667944","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 : 2018-03-23DOI: 10.1109/INFOCT.2018.8356843
Badr Alsamani, Husam Lahza
Potential Security and Privacy concerns are widely discussed in the community of Internet of Things (IoT); however, the issue is still not fully addressed, and the demands for new methods of investigation are highly appraised. The current published research focused more on identifying the security issues associated with early type of IoT's applications based on sensors, such as RFID and WSN. However, todays IoT commercial applications are more advanced and use different of integrated objects. This research paper utilizes Design Science Research (DSR) methodology to better understand the security and privacy issue in IoT through creating an artifact. The purpose of this study is to propose taxonomy in order to categorize IoT's objects, so security and privacy issues would be fully addressed.
{"title":"A taxonomy of IoT: Security and privacy threats","authors":"Badr Alsamani, Husam Lahza","doi":"10.1109/INFOCT.2018.8356843","DOIUrl":"https://doi.org/10.1109/INFOCT.2018.8356843","url":null,"abstract":"Potential Security and Privacy concerns are widely discussed in the community of Internet of Things (IoT); however, the issue is still not fully addressed, and the demands for new methods of investigation are highly appraised. The current published research focused more on identifying the security issues associated with early type of IoT's applications based on sensors, such as RFID and WSN. However, todays IoT commercial applications are more advanced and use different of integrated objects. This research paper utilizes Design Science Research (DSR) methodology to better understand the security and privacy issue in IoT through creating an artifact. The purpose of this study is to propose taxonomy in order to categorize IoT's objects, so security and privacy issues would be fully addressed.","PeriodicalId":376443,"journal":{"name":"2018 International Conference on Information and Computer Technologies (ICICT)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115056008","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 : 2018-03-23DOI: 10.1109/INFOCT.2018.8356844
Amit Banerjee, Farhan Sufyanf, Mohammad Shoaib Nayel, S. Sagar
The recent advancement in home automation technologies and inter-connectivity of smart appliances has contributed immensely in developing intelligent home environment. The complex smart home environment consists of smart devices from different vendors having different configuration and communication standards that introduce the problem of a heterogeneous subsystem in a smart home. A need is emerging for a central management system to control all these various devices. In this paper, we propose an action-based framework that acts as a middleware between the user and smart appliances which allow the user to control these heterogeneous devices in a federated manner. The proposed framework is based on a controller, for accepting user input and sending instructions to the intended smart devices. Framework maintains the integrity of an instruction send to the device and employs the mechanism so that only authentic user can access them. We also incorporate Human System Interaction (HSI) in our framework, by developing an Android application which receives input in the form of motion gestures, to fulfill the human-centric interaction requirements of the user to communicate with the smart home appliances. We evaluate the performance of our framework by implementing the controller in a local home network and the cloud.
{"title":"Centralized framework for controlling heterogeneous appliances in a smart home environment","authors":"Amit Banerjee, Farhan Sufyanf, Mohammad Shoaib Nayel, S. Sagar","doi":"10.1109/INFOCT.2018.8356844","DOIUrl":"https://doi.org/10.1109/INFOCT.2018.8356844","url":null,"abstract":"The recent advancement in home automation technologies and inter-connectivity of smart appliances has contributed immensely in developing intelligent home environment. The complex smart home environment consists of smart devices from different vendors having different configuration and communication standards that introduce the problem of a heterogeneous subsystem in a smart home. A need is emerging for a central management system to control all these various devices. In this paper, we propose an action-based framework that acts as a middleware between the user and smart appliances which allow the user to control these heterogeneous devices in a federated manner. The proposed framework is based on a controller, for accepting user input and sending instructions to the intended smart devices. Framework maintains the integrity of an instruction send to the device and employs the mechanism so that only authentic user can access them. We also incorporate Human System Interaction (HSI) in our framework, by developing an Android application which receives input in the form of motion gestures, to fulfill the human-centric interaction requirements of the user to communicate with the smart home appliances. We evaluate the performance of our framework by implementing the controller in a local home network and the cloud.","PeriodicalId":376443,"journal":{"name":"2018 International Conference on Information and Computer Technologies (ICICT)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130314009","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 : 2018-03-23DOI: 10.1109/INFOCT.2018.8356845
Cheng-Wei Hu, Zhiqing Huang, Zhuying Lin
In the general architecture of software defined networks, controller often uses traditional OSPF (Open Shortest Path First) routing algorithm selecting the shortest path as the final single path when calculate networks' topology. This may cause the busy nodes will still receive large amount of transmission data requests when they had already blocked by current works. Especially in the environment of the mobile networks, the differences in data requests can suddenly cause some node data to be congested, while the other part is idle, both waste the resources of network and influence the quality of network service. This paper designs an all pairs shortest paths algorithm to calculate the topology information in the nodes of software defined networks regularly and put forward a congestion control strategy based on OpenFlow protocol to solve the problem of loading imbalanced of the data center networking of the software defined mobile networks. We elaborate on its overall framework and algorithm implementation process, and is proved by experimental simulation that the algorithm can relieve network congestion, improve network utilization and enhance the effectiveness of network stability.
{"title":"An information transport dynamic load balancing policy based on software defined mobile networks","authors":"Cheng-Wei Hu, Zhiqing Huang, Zhuying Lin","doi":"10.1109/INFOCT.2018.8356845","DOIUrl":"https://doi.org/10.1109/INFOCT.2018.8356845","url":null,"abstract":"In the general architecture of software defined networks, controller often uses traditional OSPF (Open Shortest Path First) routing algorithm selecting the shortest path as the final single path when calculate networks' topology. This may cause the busy nodes will still receive large amount of transmission data requests when they had already blocked by current works. Especially in the environment of the mobile networks, the differences in data requests can suddenly cause some node data to be congested, while the other part is idle, both waste the resources of network and influence the quality of network service. This paper designs an all pairs shortest paths algorithm to calculate the topology information in the nodes of software defined networks regularly and put forward a congestion control strategy based on OpenFlow protocol to solve the problem of loading imbalanced of the data center networking of the software defined mobile networks. We elaborate on its overall framework and algorithm implementation process, and is proved by experimental simulation that the algorithm can relieve network congestion, improve network utilization and enhance the effectiveness of network stability.","PeriodicalId":376443,"journal":{"name":"2018 International Conference on Information and Computer Technologies (ICICT)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133252593","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 : 2018-03-23DOI: 10.1109/INFOCT.2018.8356831
Nagdev Amruthnath, Tarun Gupta
Manufacturing industries have been on a steady path considering for new methods to achieve near-zero downtime to have flexibility in the manufacturing process and being economical. In the last decade with the availability of industrial internet of things (IIoT) devices, this has made it possible to monitor the machine continuously using wireless sensors, assess the degradation and predict the failures of time. Condition-based predictive maintenance has made a significant influence in monitoring the asset and predicting the failure of time. This has minimized the impact on production, quality, and maintenance cost. Numerous approaches have been in proposed over the years and implemented in supervised learning. In this paper, challenges of supervised learning such as need for historical data and incapable of classifying new faults accurately will be overcome with a new methodology using unsupervised learning for rapid implementation of predictive maintenance activity which includes fault prediction and fault class detection for known and unknown faults using density estimation via Gaussian Mixture Model Clustering and K-means algorithm and compare their results with a real case vibration data.
{"title":"Fault class prediction in unsupervised learning using model-based clustering approach","authors":"Nagdev Amruthnath, Tarun Gupta","doi":"10.1109/INFOCT.2018.8356831","DOIUrl":"https://doi.org/10.1109/INFOCT.2018.8356831","url":null,"abstract":"Manufacturing industries have been on a steady path considering for new methods to achieve near-zero downtime to have flexibility in the manufacturing process and being economical. In the last decade with the availability of industrial internet of things (IIoT) devices, this has made it possible to monitor the machine continuously using wireless sensors, assess the degradation and predict the failures of time. Condition-based predictive maintenance has made a significant influence in monitoring the asset and predicting the failure of time. This has minimized the impact on production, quality, and maintenance cost. Numerous approaches have been in proposed over the years and implemented in supervised learning. In this paper, challenges of supervised learning such as need for historical data and incapable of classifying new faults accurately will be overcome with a new methodology using unsupervised learning for rapid implementation of predictive maintenance activity which includes fault prediction and fault class detection for known and unknown faults using density estimation via Gaussian Mixture Model Clustering and K-means algorithm and compare their results with a real case vibration data.","PeriodicalId":376443,"journal":{"name":"2018 International Conference on Information and Computer Technologies (ICICT)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134056789","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：