Pub Date : 2020-06-01DOI: 10.1109/ICCCI49374.2020.9145991
Li-min Peng, Zhenhua Liu
In this paper, a novel node design based on smart antenna is investigated. Normally, the ad-hoc consists of many nodes, in which there are source nodes (SNs), destination nodes (DNs) and relay nodes (RNs). To improve the performance of ad-hoc network, smart antenna is introduced to increase the relay links in transmission. In traditional node design, the nodes would use analog beamforming (ABF)to form multi beams to transmit services. But there are three disadvantages in traditional node design, one is the high cost of beams, second is the limitation in beam number, and third is the high service loss probability. In our proposed novel node design, we use digital beamforming (DBF) method to reduce the beam costs. We combine DBF with overlay/underlay mode and introduce overlay/underlay beams to increase the beam number. Also, we take differentiated treatment to different services and transmit different services in proper overlay/underlay beams. Using this novel node design, the ad-hoc network could get more relay links and have low service loss probability, and that leads to more service capacity of ad-hoc network, while the network cost is low. Simulation results show that our proposed novel node design has a better performance than the traditional node design.
{"title":"A Novel Node Design Based on Smart Antenna in Ad-hoc Network","authors":"Li-min Peng, Zhenhua Liu","doi":"10.1109/ICCCI49374.2020.9145991","DOIUrl":"https://doi.org/10.1109/ICCCI49374.2020.9145991","url":null,"abstract":"In this paper, a novel node design based on smart antenna is investigated. Normally, the ad-hoc consists of many nodes, in which there are source nodes (SNs), destination nodes (DNs) and relay nodes (RNs). To improve the performance of ad-hoc network, smart antenna is introduced to increase the relay links in transmission. In traditional node design, the nodes would use analog beamforming (ABF)to form multi beams to transmit services. But there are three disadvantages in traditional node design, one is the high cost of beams, second is the limitation in beam number, and third is the high service loss probability. In our proposed novel node design, we use digital beamforming (DBF) method to reduce the beam costs. We combine DBF with overlay/underlay mode and introduce overlay/underlay beams to increase the beam number. Also, we take differentiated treatment to different services and transmit different services in proper overlay/underlay beams. Using this novel node design, the ad-hoc network could get more relay links and have low service loss probability, and that leads to more service capacity of ad-hoc network, while the network cost is low. Simulation results show that our proposed novel node design has a better performance than the traditional node design.","PeriodicalId":153290,"journal":{"name":"2020 2nd International Conference on Computer Communication and the Internet (ICCCI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124258140","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 : 2020-06-01DOI: 10.1109/ICCCI49374.2020.9145989
Kazuma Matsuoka, Tsunehiko Suzuki
We propose a new lookup system using blockchain and Distributed Hash Table (DHT). Blockchain allows this system to communicate from one node to another node directly without a trusted third party. DHT allows nodes participating in this system to store data distributedly and to propagate data efficiently. The maximum capacity of the blockchain of this system does not increase by adopting a mechanism setting an expiration period of data. In this paper, we describe our current system structure and report the result of measuring how the query time required for a lookup to any data changes depending on the network size and the ratio of off-line nodes.
{"title":"Blockchain and DHT Based Lookup System Aiming for Alternative DNS","authors":"Kazuma Matsuoka, Tsunehiko Suzuki","doi":"10.1109/ICCCI49374.2020.9145989","DOIUrl":"https://doi.org/10.1109/ICCCI49374.2020.9145989","url":null,"abstract":"We propose a new lookup system using blockchain and Distributed Hash Table (DHT). Blockchain allows this system to communicate from one node to another node directly without a trusted third party. DHT allows nodes participating in this system to store data distributedly and to propagate data efficiently. The maximum capacity of the blockchain of this system does not increase by adopting a mechanism setting an expiration period of data. In this paper, we describe our current system structure and report the result of measuring how the query time required for a lookup to any data changes depending on the network size and the ratio of off-line nodes.","PeriodicalId":153290,"journal":{"name":"2020 2nd International Conference on Computer Communication and the Internet (ICCCI)","volume":"281 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133924875","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 : 2020-06-01DOI: 10.1109/ICCCI49374.2020.9145987
Vasileios A. Memos, Georgios M. Minopoulos, C. Stergiou, Konstantinos E. Psannis, Y. Ishibashi
Nowadays, the traditional teacher-centered way of teaching seems to be anachronistic. Disabled people, and not only, face difficulties to follow the current educational methods. The evolution of technology can offer significant benefits in these problems. Cutting-edge technologies, such as as Internet of Things (IoT), Cloud Computing (CC), Wireless Sensor Networks (WSN), Big Data Analytics (BDA), Compressed Sensing (CS), Augmented Reality/Virtual Reality (AR/VR) and 5G Networking can contribute in the field of smart education. However, smart education is currently in an embryonic 2D data representational state. In this paper, we propose a new Revolutionary Interactive Smart Classroom (RISC) which will provide a virtual environment for enhanced learning experience, based on 5G Network. This classroom will also make use of 3D virtual services in combination with haptic equipment and sensors, in order to carry out augmented human sensing information and touch into the virtual class. The advantages of such a classroom will be the sustainability in many fields, such as Society, Education, Environment, Economics, Technology and Cultural Tourism.
{"title":"A Revolutionary Interactive Smart Classroom (RISC) with the Use of Emerging Technologies","authors":"Vasileios A. Memos, Georgios M. Minopoulos, C. Stergiou, Konstantinos E. Psannis, Y. Ishibashi","doi":"10.1109/ICCCI49374.2020.9145987","DOIUrl":"https://doi.org/10.1109/ICCCI49374.2020.9145987","url":null,"abstract":"Nowadays, the traditional teacher-centered way of teaching seems to be anachronistic. Disabled people, and not only, face difficulties to follow the current educational methods. The evolution of technology can offer significant benefits in these problems. Cutting-edge technologies, such as as Internet of Things (IoT), Cloud Computing (CC), Wireless Sensor Networks (WSN), Big Data Analytics (BDA), Compressed Sensing (CS), Augmented Reality/Virtual Reality (AR/VR) and 5G Networking can contribute in the field of smart education. However, smart education is currently in an embryonic 2D data representational state. In this paper, we propose a new Revolutionary Interactive Smart Classroom (RISC) which will provide a virtual environment for enhanced learning experience, based on 5G Network. This classroom will also make use of 3D virtual services in combination with haptic equipment and sensors, in order to carry out augmented human sensing information and touch into the virtual class. The advantages of such a classroom will be the sustainability in many fields, such as Society, Education, Environment, Economics, Technology and Cultural Tourism.","PeriodicalId":153290,"journal":{"name":"2020 2nd International Conference on Computer Communication and the Internet (ICCCI)","volume":"421 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133191376","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 : 2020-06-01DOI: 10.1109/ICCCI49374.2020.9145992
Shogo Ishii, Sota Tatsumi, M. Tanaka, Y. Okumura, Tatsuya Kochi
We are developing a rice cultivation management systems using a field server to reduce the workload of farmers. The feature of our field server is a reasonable price. In order to achieve the reasonable price, the accuracy of time synchronization is sacrificed. At present, it is possible to manage environmental data for crops and fields using sensors. However, there are some points to be improved in the current field server. The first is transmission scheduling in advance is had to set up. The second is that field servers cannot be added during the operation. This paper describes a method to notify all nodes of additional field server information and scheduling to solve the above problem. Simultaneous transmission type flooding method is described in detail. We will also report the experimental results. This protocol is robust for the rice cultivation management systems because the field server is stable. Therefore, it meets farmers' expectation to utilize a reasonable field server.
{"title":"New Field Server Addition Method for Low-Price Rice Cultivation Management System","authors":"Shogo Ishii, Sota Tatsumi, M. Tanaka, Y. Okumura, Tatsuya Kochi","doi":"10.1109/ICCCI49374.2020.9145992","DOIUrl":"https://doi.org/10.1109/ICCCI49374.2020.9145992","url":null,"abstract":"We are developing a rice cultivation management systems using a field server to reduce the workload of farmers. The feature of our field server is a reasonable price. In order to achieve the reasonable price, the accuracy of time synchronization is sacrificed. At present, it is possible to manage environmental data for crops and fields using sensors. However, there are some points to be improved in the current field server. The first is transmission scheduling in advance is had to set up. The second is that field servers cannot be added during the operation. This paper describes a method to notify all nodes of additional field server information and scheduling to solve the above problem. Simultaneous transmission type flooding method is described in detail. We will also report the experimental results. This protocol is robust for the rice cultivation management systems because the field server is stable. Therefore, it meets farmers' expectation to utilize a reasonable field server.","PeriodicalId":153290,"journal":{"name":"2020 2nd International Conference on Computer Communication and the Internet (ICCCI)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131138580","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 : 2020-06-01DOI: 10.1109/ICCCI49374.2020.9145972
C. Lin, Huan Zhang, Jain-Shing Liu, Shih-Huang Chen
Currently, the online video conference system usually needs to install this application software. Therefore, the software needs to be developed duplicate version for different operating systems (OS), e.g., Android, Windows and MacOS. However, web-based video conference system is OS independent so as to save development cost. In the paper, we present an implementation of a web-based video conference solution by using WebRTC [1]. It can be used for meeting and chat with a browser. Instead of client-server centralized design, in a cyber-video meeting, each member transmits media stream to each other peer-to-peer. Additionally, the media stream is encrypted, and a management mechanism is developed to manage the entry of conference room personnel and achieve a secure multi-party video conference. We also overcome peer-to-peer (P2P)web NAT traversal of media transmission. Our solution covers four main features: P2P Web NAT traversal, dynamic join and leave, access control, dynamic video resolution adjustment.
目前，在线视频会议系统通常需要安装该应用软件。因此，该软件需要针对不同的操作系统(如Android、Windows和MacOS)开发副本版本。而基于web的视频会议系统是独立于操作系统的，可以节省开发成本。在本文中，我们使用WebRTC实现了基于web的视频会议解决方案[1]。它可以用浏览器开会和聊天。在网络视频会议中，每个成员彼此点对点地传输媒体流，而不是客户端-服务器集中式设计。并对媒体流进行加密，开发管理机制，对会议室人员的出入进行管理，实现安全的多方视频会议。我们还克服了媒体传输的点对点(P2P)网络NAT穿越。我们的解决方案包括四个主要特性:P2P Web NAT穿越、动态加入和离开、访问控制、动态视频分辨率调整。
{"title":"Implementation of Secure Web Conferencing","authors":"C. Lin, Huan Zhang, Jain-Shing Liu, Shih-Huang Chen","doi":"10.1109/ICCCI49374.2020.9145972","DOIUrl":"https://doi.org/10.1109/ICCCI49374.2020.9145972","url":null,"abstract":"Currently, the online video conference system usually needs to install this application software. Therefore, the software needs to be developed duplicate version for different operating systems (OS), e.g., Android, Windows and MacOS. However, web-based video conference system is OS independent so as to save development cost. In the paper, we present an implementation of a web-based video conference solution by using WebRTC [1]. It can be used for meeting and chat with a browser. Instead of client-server centralized design, in a cyber-video meeting, each member transmits media stream to each other peer-to-peer. Additionally, the media stream is encrypted, and a management mechanism is developed to manage the entry of conference room personnel and achieve a secure multi-party video conference. We also overcome peer-to-peer (P2P)web NAT traversal of media transmission. Our solution covers four main features: P2P Web NAT traversal, dynamic join and leave, access control, dynamic video resolution adjustment.","PeriodicalId":153290,"journal":{"name":"2020 2nd International Conference on Computer Communication and the Internet (ICCCI)","volume":"112 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128622346","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 : 2020-06-01DOI: 10.1109/ICCCI49374.2020.9145968
Chuan-Mu Tseng, Tzu-Wei Huang, Tzong-Jye Liu
In machine learning, supervised learning methods for classifiers have to need sufficient labeled training data. However, it is quite labor-intensive and expensive to manually label a great number of training data. At the moment, there are two types of research related to data labeling: co-training and tri-training. The former primarily uses the voting system based on two algorithms to obtain the labeled results, and the latter is applied to improving co-training. When the two algorithms produce inconsistent results, they will not be able to label the data correctly. Hence, the method of tri-training makes use of the third algorithm to help judge. Our proposed method, Novel Decision Module of Tri-training (NDMTT), uses the output of their architecture to filter the results with threshold conditions, so the validity of the labeling can be improved. When it is improved, one of the classifications can be relatively increased.
{"title":"Data Labeling with Novel Decision Module of Tri-training","authors":"Chuan-Mu Tseng, Tzu-Wei Huang, Tzong-Jye Liu","doi":"10.1109/ICCCI49374.2020.9145968","DOIUrl":"https://doi.org/10.1109/ICCCI49374.2020.9145968","url":null,"abstract":"In machine learning, supervised learning methods for classifiers have to need sufficient labeled training data. However, it is quite labor-intensive and expensive to manually label a great number of training data. At the moment, there are two types of research related to data labeling: co-training and tri-training. The former primarily uses the voting system based on two algorithms to obtain the labeled results, and the latter is applied to improving co-training. When the two algorithms produce inconsistent results, they will not be able to label the data correctly. Hence, the method of tri-training makes use of the third algorithm to help judge. Our proposed method, Novel Decision Module of Tri-training (NDMTT), uses the output of their architecture to filter the results with threshold conditions, so the validity of the labeling can be improved. When it is improved, one of the classifications can be relatively increased.","PeriodicalId":153290,"journal":{"name":"2020 2nd International Conference on Computer Communication and the Internet (ICCCI)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128043597","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 : 2020-06-01DOI: 10.1109/ICCCI49374.2020.9145982
Huu Dang Quoc, Loc Nguyen The, Cuong Nguyen Doan, Toan Phan Thanh
The Resource-Constrained Project Scheduling Problem (RCPSP) is a classical combinational optimization problem that has many practical applications. In this paper, we consider an extension of the RCPSP which called Multi-Skill Resource-Constrained Project Scheduling Problem (MS-RCPSP). In the past few years, various approaches have been proposed to solve this problem such as Genetic Algorithm and Ant Colony Optimization. However, reducing the likelihood of premature convergence is the challenge facing researchers. In this paper, we present a novel algorithm called DEM in order to solve the MS-RCPSP problem. Besides using the differential evolution metaheuristic, we also develop the Reassignment function to improve the solution quality at the end of each iteration, so that proposed algorithm converges rapidly to global extremum. Moreover, proposed algorithm also avoids getting trapped in a local extremum. The experiments were conducted to evaluate the performance of the proposed algorithm, as well as to compare the DEM with previous algorithms such as GreedyDO, HAntCO, and GA. Experimental results show that the proposed algorithm can effectively enhance searching efficiently.
{"title":"New Effective Differential Evolution Algorithm for the Project Scheduling Problem","authors":"Huu Dang Quoc, Loc Nguyen The, Cuong Nguyen Doan, Toan Phan Thanh","doi":"10.1109/ICCCI49374.2020.9145982","DOIUrl":"https://doi.org/10.1109/ICCCI49374.2020.9145982","url":null,"abstract":"The Resource-Constrained Project Scheduling Problem (RCPSP) is a classical combinational optimization problem that has many practical applications. In this paper, we consider an extension of the RCPSP which called Multi-Skill Resource-Constrained Project Scheduling Problem (MS-RCPSP). In the past few years, various approaches have been proposed to solve this problem such as Genetic Algorithm and Ant Colony Optimization. However, reducing the likelihood of premature convergence is the challenge facing researchers. In this paper, we present a novel algorithm called DEM in order to solve the MS-RCPSP problem. Besides using the differential evolution metaheuristic, we also develop the Reassignment function to improve the solution quality at the end of each iteration, so that proposed algorithm converges rapidly to global extremum. Moreover, proposed algorithm also avoids getting trapped in a local extremum. The experiments were conducted to evaluate the performance of the proposed algorithm, as well as to compare the DEM with previous algorithms such as GreedyDO, HAntCO, and GA. Experimental results show that the proposed algorithm can effectively enhance searching efficiently.","PeriodicalId":153290,"journal":{"name":"2020 2nd International Conference on Computer Communication and the Internet (ICCCI)","volume":"285 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123291306","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 : 2020-06-01DOI: 10.1109/ICCCI49374.2020.9145967
Takaya Furuta, R. Takahashi, Y. Fukazawa
The number of devices connected to the Internet is increasing rapidly in the Internet of Things era. Consequently, many packets with a small data size are created and sent over a network. Due to the small data size, the header data of packets has a big impact on the entire traffic when such packets are sent in the same network. The arrival of many packets wastes communication resources. Packet aggregation is one solution to deal with this problem, but it also causes delays. This study focuses on an acceptable waiting time, which is unique to the application, and a packet aggregation scheme for communication networks mainly consisting of low-latency-required packets is proposed.
{"title":"A Packet Aggregation Scheme for Communication Networks Consisted of Mainly Low-Latency Required Packets","authors":"Takaya Furuta, R. Takahashi, Y. Fukazawa","doi":"10.1109/ICCCI49374.2020.9145967","DOIUrl":"https://doi.org/10.1109/ICCCI49374.2020.9145967","url":null,"abstract":"The number of devices connected to the Internet is increasing rapidly in the Internet of Things era. Consequently, many packets with a small data size are created and sent over a network. Due to the small data size, the header data of packets has a big impact on the entire traffic when such packets are sent in the same network. The arrival of many packets wastes communication resources. Packet aggregation is one solution to deal with this problem, but it also causes delays. This study focuses on an acceptable waiting time, which is unique to the application, and a packet aggregation scheme for communication networks mainly consisting of low-latency-required packets is proposed.","PeriodicalId":153290,"journal":{"name":"2020 2nd International Conference on Computer Communication and the Internet (ICCCI)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123640786","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 : 2020-06-01DOI: 10.1109/ICCCI49374.2020.9145976
Hecan Zhang, Xin Guo, C. Yi, Yue Dou, Dong Chen, Nannan Tong, Jiandong Wang
Patent analysis is widely used in many kinds of research, such as competitive intelligence analysis, technology trends perceiving, industrial distribution planning, macro-economy regulations, and so on. Based on the patent data, this paper proposed a novel algorithm, which named PeTIT, to perceive the technological innovation trends by applying the heuristic community detection model. The PeTIT algorithm included four steps: patent ontology extraction, technological innovation tree construction, technological innovation community detection, and technological innovation trends perceiving. We implemented the PeTIT algorithm on the real dataset of invention patents in the field of artificial intelligence in China, which ranged from Jun 1st, 2000 to May 1st, 2019. The results showed that the innovation situation of artificial intelligent was mainly concentrated in 10 fields. Moreover, the application field of intelligent driving has become one of the fastest-growing industries. Finally, the experimental results demonstrated that the cubic exponential smoothing model had a higher performance by perceiving the technological innovation trends.
{"title":"PeTIT: Perceiving the Technological Innovation Trends via the Heuristic Model of Community Detection","authors":"Hecan Zhang, Xin Guo, C. Yi, Yue Dou, Dong Chen, Nannan Tong, Jiandong Wang","doi":"10.1109/ICCCI49374.2020.9145976","DOIUrl":"https://doi.org/10.1109/ICCCI49374.2020.9145976","url":null,"abstract":"Patent analysis is widely used in many kinds of research, such as competitive intelligence analysis, technology trends perceiving, industrial distribution planning, macro-economy regulations, and so on. Based on the patent data, this paper proposed a novel algorithm, which named PeTIT, to perceive the technological innovation trends by applying the heuristic community detection model. The PeTIT algorithm included four steps: patent ontology extraction, technological innovation tree construction, technological innovation community detection, and technological innovation trends perceiving. We implemented the PeTIT algorithm on the real dataset of invention patents in the field of artificial intelligence in China, which ranged from Jun 1st, 2000 to May 1st, 2019. The results showed that the innovation situation of artificial intelligent was mainly concentrated in 10 fields. Moreover, the application field of intelligent driving has become one of the fastest-growing industries. Finally, the experimental results demonstrated that the cubic exponential smoothing model had a higher performance by perceiving the technological innovation trends.","PeriodicalId":153290,"journal":{"name":"2020 2nd International Conference on Computer Communication and the Internet (ICCCI)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123723276","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 : 2020-06-01DOI: 10.1109/ICCCI49374.2020.9145971
Ali Malik, Ruairí de Fréin, Mohammed Al-Zeyadi, Javier Andreu-Perez
Accurate traffic classification is fundamentally important for various network activities such as fine-grained network management and resource utilisation. Port-based approaches, deep packet inspection and machine learning are widely used techniques to classify and analyze network traffic flows. However, over the past several years, the growth of Internet traffic has been explosive due to the greatly increased number of Internet users. Therefore, both port-based and deep packet inspection approaches have become inefficient due to the exponential growth of the Internet applications that incurs high computational cost. The emerging paradigm of software-defined networking has reshaped the network architecture by detaching the control plane from the data plane to result in a centralised network controller that maintains a global view over the whole network on its domain. In this paper, we propose a new deep learning model for software-defined networks that can accurately identify a wide range of traffic applications in a short time, called Deep-SDN. The performance of the proposed model was compared against the state-of-the-art and better results were reported in terms of accuracy, precision, recall, and f-measure. It has been found that 96% as an overall accuracy can be achieved with the proposed model. Based on the obtained results, some further directions are suggested towards achieving further advances in this research area.
{"title":"Intelligent SDN Traffic Classification Using Deep Learning: Deep-SDN","authors":"Ali Malik, Ruairí de Fréin, Mohammed Al-Zeyadi, Javier Andreu-Perez","doi":"10.1109/ICCCI49374.2020.9145971","DOIUrl":"https://doi.org/10.1109/ICCCI49374.2020.9145971","url":null,"abstract":"Accurate traffic classification is fundamentally important for various network activities such as fine-grained network management and resource utilisation. Port-based approaches, deep packet inspection and machine learning are widely used techniques to classify and analyze network traffic flows. However, over the past several years, the growth of Internet traffic has been explosive due to the greatly increased number of Internet users. Therefore, both port-based and deep packet inspection approaches have become inefficient due to the exponential growth of the Internet applications that incurs high computational cost. The emerging paradigm of software-defined networking has reshaped the network architecture by detaching the control plane from the data plane to result in a centralised network controller that maintains a global view over the whole network on its domain. In this paper, we propose a new deep learning model for software-defined networks that can accurately identify a wide range of traffic applications in a short time, called Deep-SDN. The performance of the proposed model was compared against the state-of-the-art and better results were reported in terms of accuracy, precision, recall, and f-measure. It has been found that 96% as an overall accuracy can be achieved with the proposed model. Based on the obtained results, some further directions are suggested towards achieving further advances in this research area.","PeriodicalId":153290,"journal":{"name":"2020 2nd International Conference on Computer Communication and the Internet (ICCCI)","volume":"98 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127471649","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：