Pub Date : 2020-05-01DOI: 10.1109/ICCCS49078.2020.9118492
Xi Qian, Jiu-fen Liu, Chunxiang Gu, Yonghui Zheng
The Learning with Errors (LWE) Problem has received much attention since its introduction and been widely used in cryptography. However the error sampled from Gaussian distribution affects efficiency of application based on LWE, the LWE variants with errors taken from uniform distribution came into being in 2013, which has an asymptotic complexity analysis.An improved BKW algorithm has been proposed to the LWE problem with binary uniform errors, and a study of the complexity of the algorithm is given in the paper. As a result, new bounds are provided for the concrete hardness of cryptography based on the variant, and parameter choices for quiet a few important algorithm.
{"title":"An Improved BKW Algorithm For LWE With Binary Uniform Errors","authors":"Xi Qian, Jiu-fen Liu, Chunxiang Gu, Yonghui Zheng","doi":"10.1109/ICCCS49078.2020.9118492","DOIUrl":"https://doi.org/10.1109/ICCCS49078.2020.9118492","url":null,"abstract":"The Learning with Errors (LWE) Problem has received much attention since its introduction and been widely used in cryptography. However the error sampled from Gaussian distribution affects efficiency of application based on LWE, the LWE variants with errors taken from uniform distribution came into being in 2013, which has an asymptotic complexity analysis.An improved BKW algorithm has been proposed to the LWE problem with binary uniform errors, and a study of the complexity of the algorithm is given in the paper. As a result, new bounds are provided for the concrete hardness of cryptography based on the variant, and parameter choices for quiet a few important algorithm.","PeriodicalId":105556,"journal":{"name":"2020 5th International Conference on Computer and Communication Systems (ICCCS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123753206","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 : 2020-05-01DOI: 10.1109/ICCCS49078.2020.9118596
Jianwei Zhang, Tao Han, Yajun Li, Jinghu Li
SRAM-based Field Programmable Gate Array (FPGA) is vulnerable to the serious radiation effects represented by Single Event Upset (SEU) effect in space. Triple Modular Redundancy (TMR) and configuration scrubbing are effective methods of FPGA radiation protection, but each has its own shortcomings: TMR structure can’t correct errors, and scrub circuit, also called “scrubber”, is sensitive to radiation. In response to the problem, this paper proposes a Real-time Redundant Scrubbing (RRS) system. Based on the traditional configuration scrubbing, TMR structure is applied to the scrubber. And the error indicator is added to the traditional TMR structure. When the scrubber has errors due to SEU, the scrubber will be scrubbed in real-time to prevent error accumulation. In addition, the floorplan of the three redundant logic is distributed to avoid the influence of a SEU on multiple redundant logic at the same time. In this paper, the anti-radiation capability of the proposed RRS system is evaluated by random fault injection. The test results show that the anti-radiation capability of the RRS system is more than 2 times higher than that of traditional configuration scrubbing system.
{"title":"Real-Time Redundant Scrubbing (RRS) System for Radiation Protection on SRAM-Based FPGA","authors":"Jianwei Zhang, Tao Han, Yajun Li, Jinghu Li","doi":"10.1109/ICCCS49078.2020.9118596","DOIUrl":"https://doi.org/10.1109/ICCCS49078.2020.9118596","url":null,"abstract":"SRAM-based Field Programmable Gate Array (FPGA) is vulnerable to the serious radiation effects represented by Single Event Upset (SEU) effect in space. Triple Modular Redundancy (TMR) and configuration scrubbing are effective methods of FPGA radiation protection, but each has its own shortcomings: TMR structure can’t correct errors, and scrub circuit, also called “scrubber”, is sensitive to radiation. In response to the problem, this paper proposes a Real-time Redundant Scrubbing (RRS) system. Based on the traditional configuration scrubbing, TMR structure is applied to the scrubber. And the error indicator is added to the traditional TMR structure. When the scrubber has errors due to SEU, the scrubber will be scrubbed in real-time to prevent error accumulation. In addition, the floorplan of the three redundant logic is distributed to avoid the influence of a SEU on multiple redundant logic at the same time. In this paper, the anti-radiation capability of the proposed RRS system is evaluated by random fault injection. The test results show that the anti-radiation capability of the RRS system is more than 2 times higher than that of traditional configuration scrubbing system.","PeriodicalId":105556,"journal":{"name":"2020 5th International Conference on Computer and Communication Systems (ICCCS)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122409155","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 : 2020-05-01DOI: 10.1109/ICCCS49078.2020.9118456
Hua Zhang, Jiancun Zuo
In both 4G Long Term Evolution (LTE) and 5G New Radio (NR) systems, uplink power control (UPC) is a key feature of radio resource management to balance the inter-cell interference and guarantee the network performance, especially for physical uplink shared channel (PUSCH). In this paper, a methodology for optimizing UPC parameters is presented via network utility maximization (NUM). The network utility is defined as the sum of user utilities and is proven to be a concave function towards the two most important UPC parameters, i.e., nominal power level and channel path-loss compensation factor. Each cell optimizes its own UPC parameters semi-autonomously with only exchanging a few key variables via inter-cell coordination. Under the assumption of best effort traffic, results via system-level simulation show that network throughput performance with the proposed UPC mechanism is significantly improved when compared with typical fixed UPC parameter settings.
在4G LTE (Long Term Evolution, LTE)和5G NR (New Radio, NR)系统中，上行功率控制(UPC)是无线资源管理的关键特征，以平衡小区间干扰和保证网络性能，特别是对于物理上行共享信道(PUSCH)。本文提出了一种基于网络效用最大化的UPC参数优化方法。网络效用被定义为用户效用的总和，并被证明是两个最重要的UPC参数的凹函数，即标称功率电平和信道路径损耗补偿因子。每个细胞半自主地优化自己的UPC参数，仅通过细胞间协调交换几个关键变量。在最佳努力流量假设下，系统级仿真结果表明，与典型的固定UPC参数设置相比，采用该UPC机制的网络吞吐量性能有显著提高。
{"title":"Optimization of Uplink Power Control Parameters in Wireless Cellular Networks","authors":"Hua Zhang, Jiancun Zuo","doi":"10.1109/ICCCS49078.2020.9118456","DOIUrl":"https://doi.org/10.1109/ICCCS49078.2020.9118456","url":null,"abstract":"In both 4G Long Term Evolution (LTE) and 5G New Radio (NR) systems, uplink power control (UPC) is a key feature of radio resource management to balance the inter-cell interference and guarantee the network performance, especially for physical uplink shared channel (PUSCH). In this paper, a methodology for optimizing UPC parameters is presented via network utility maximization (NUM). The network utility is defined as the sum of user utilities and is proven to be a concave function towards the two most important UPC parameters, i.e., nominal power level and channel path-loss compensation factor. Each cell optimizes its own UPC parameters semi-autonomously with only exchanging a few key variables via inter-cell coordination. Under the assumption of best effort traffic, results via system-level simulation show that network throughput performance with the proposed UPC mechanism is significantly improved when compared with typical fixed UPC parameter settings.","PeriodicalId":105556,"journal":{"name":"2020 5th International Conference on Computer and Communication Systems (ICCCS)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126794779","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 : 2020-05-01DOI: 10.1109/ICCCS49078.2020.9118483
Yang Liu, O. Uchida, K. Utsu
During large-scale disasters, a large number of posts about damage reports and rescue requests are shared on social media. The utilization of the posts has become important for disaster response. Sina Weibo is the most famous microblogging service in China. In this study, we propose a web system to facilitate sharing disaster-related information on Sina Weibo. Using the system, users can easily share the information on Sina Weibo. Moreover, the posted information is listed on a Message board on the system to support rescue and assist activities by local governments and rescue experts.
{"title":"A Proposal on Disaster Information and Rescue Request Sharing Application Using Sina Weibo","authors":"Yang Liu, O. Uchida, K. Utsu","doi":"10.1109/ICCCS49078.2020.9118483","DOIUrl":"https://doi.org/10.1109/ICCCS49078.2020.9118483","url":null,"abstract":"During large-scale disasters, a large number of posts about damage reports and rescue requests are shared on social media. The utilization of the posts has become important for disaster response. Sina Weibo is the most famous microblogging service in China. In this study, we propose a web system to facilitate sharing disaster-related information on Sina Weibo. Using the system, users can easily share the information on Sina Weibo. Moreover, the posted information is listed on a Message board on the system to support rescue and assist activities by local governments and rescue experts.","PeriodicalId":105556,"journal":{"name":"2020 5th International Conference on Computer and Communication Systems (ICCCS)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126000708","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 : 2020-05-01DOI: 10.1109/ICCCS49078.2020.9118473
Quanyv Wang, Panpan Fu, Shouzhen Zhang
Towards the 5th generation wireless systems (5G) and beyond, polar codes have become a hot research topic in the field of communications. In our work, concatenated polar codes with different interleaving and decoding schemes are designed to improve the error performance of finite-length polar codes. In this paper, concatenated polar codes with outer BCH codes are first constructed, besides, concatenated LDPC codes and concatenated Turbo codes are also designed for comparison. At the same time, random interleaving (RI) scheme and blind interleaving (BI) scheme are proposed to construct the concatenated codes. From the simulation results of this paper, we can see that the bit error rate (BER) performance of concatenated codes using BI scheme is better than that of concatenated codes using RI scheme. Furthermore, the BER performance of concatenated polar codes outperforms that of concatenated LDPC codes, but not as good as that of concatenated Turbo codes. To improve the BER performance of concatenated polar codes, we adopt the CRC Aided Successive Cancellation List (CA-SCL) decoding scheme instead of the Successive Cancellation (SC) decoding scheme for inner polar decoding. The results of our study indicate that the BER performance of concatenated polar codes with CA-SCL outperforms that of concatenated polar codes with SC. In addition to this, with the same CRC code length, increasing the list size can improve the decoding performance of CA-SCL. However, there is also a bad side: the decoding complexity of CA-SCL increases rapidly as the list size increases. On the other hand, with the same list size, increasing the CRC code length adversely deteriorates the decoding performance of CA-SCL.
{"title":"A Comparison of Concatenated Polar Codes with Different Interleaving and Decoding Schemes","authors":"Quanyv Wang, Panpan Fu, Shouzhen Zhang","doi":"10.1109/ICCCS49078.2020.9118473","DOIUrl":"https://doi.org/10.1109/ICCCS49078.2020.9118473","url":null,"abstract":"Towards the 5th generation wireless systems (5G) and beyond, polar codes have become a hot research topic in the field of communications. In our work, concatenated polar codes with different interleaving and decoding schemes are designed to improve the error performance of finite-length polar codes. In this paper, concatenated polar codes with outer BCH codes are first constructed, besides, concatenated LDPC codes and concatenated Turbo codes are also designed for comparison. At the same time, random interleaving (RI) scheme and blind interleaving (BI) scheme are proposed to construct the concatenated codes. From the simulation results of this paper, we can see that the bit error rate (BER) performance of concatenated codes using BI scheme is better than that of concatenated codes using RI scheme. Furthermore, the BER performance of concatenated polar codes outperforms that of concatenated LDPC codes, but not as good as that of concatenated Turbo codes. To improve the BER performance of concatenated polar codes, we adopt the CRC Aided Successive Cancellation List (CA-SCL) decoding scheme instead of the Successive Cancellation (SC) decoding scheme for inner polar decoding. The results of our study indicate that the BER performance of concatenated polar codes with CA-SCL outperforms that of concatenated polar codes with SC. In addition to this, with the same CRC code length, increasing the list size can improve the decoding performance of CA-SCL. However, there is also a bad side: the decoding complexity of CA-SCL increases rapidly as the list size increases. On the other hand, with the same list size, increasing the CRC code length adversely deteriorates the decoding performance of CA-SCL.","PeriodicalId":105556,"journal":{"name":"2020 5th International Conference on Computer and Communication Systems (ICCCS)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125517188","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 : 2020-05-01DOI: 10.1109/ICCCS49078.2020.9118491
Wei Cheng, Qiyue Yin, Junge Zhang
This paper focuses on the task of opponent strategies recognition in Real-time Strategy (RTS) Game, which aims to predict opponent strategies by modeling the observable environmental information. It is a very challenging task due to two folds. (1) In RTS game, the information is imperfect due to the fog of war; and (2) the action and environment spaces of RTS game are too vast and complex to be modeled. This task is also significative since opponent strategies recognition is a crucial component of creating high-level AI system that can defeat high-level human players in RTS game. Most previous approaches focus on predicting tech tree, building order and strategies through game logs, where perfect information is utilized. Accordingly, these prediction methods cannot be applied to real AI systems confronting the fog of war. Furthermore, conventional approaches use machine learning techniques such as Hidden Markov Model (HMM) and Bayesian network, which is difficult to deal with higher-dimensional state spaces. Besides, the hand-crafted features are commonly used instead of high-dimensional feature of the complex environment, which leads to loss of information of the environment. To address these problems, we propose a deep feature fusion neural network to handle the above imperfect and complex information of the environment for opponent strategies recognition in RTS game. We test our method on the canonical RTS game, i.e., Starcraft II, and promising performance has been obtained.
{"title":"Opponent Strategy Recognition In Real Time Strategy Game Using Deep Feature Fusion Neural Network","authors":"Wei Cheng, Qiyue Yin, Junge Zhang","doi":"10.1109/ICCCS49078.2020.9118491","DOIUrl":"https://doi.org/10.1109/ICCCS49078.2020.9118491","url":null,"abstract":"This paper focuses on the task of opponent strategies recognition in Real-time Strategy (RTS) Game, which aims to predict opponent strategies by modeling the observable environmental information. It is a very challenging task due to two folds. (1) In RTS game, the information is imperfect due to the fog of war; and (2) the action and environment spaces of RTS game are too vast and complex to be modeled. This task is also significative since opponent strategies recognition is a crucial component of creating high-level AI system that can defeat high-level human players in RTS game. Most previous approaches focus on predicting tech tree, building order and strategies through game logs, where perfect information is utilized. Accordingly, these prediction methods cannot be applied to real AI systems confronting the fog of war. Furthermore, conventional approaches use machine learning techniques such as Hidden Markov Model (HMM) and Bayesian network, which is difficult to deal with higher-dimensional state spaces. Besides, the hand-crafted features are commonly used instead of high-dimensional feature of the complex environment, which leads to loss of information of the environment. To address these problems, we propose a deep feature fusion neural network to handle the above imperfect and complex information of the environment for opponent strategies recognition in RTS game. We test our method on the canonical RTS game, i.e., Starcraft II, and promising performance has been obtained.","PeriodicalId":105556,"journal":{"name":"2020 5th International Conference on Computer and Communication Systems (ICCCS)","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127882386","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 : 2020-05-01DOI: 10.1109/ICCCS49078.2020.9118581
Yunjie Fang, Jingcheng Ye, Hao Wang
In order to reduce the labor cost of invigilation, improve invigilation efficiency and deal with violations in real time, this paper designs and implements an intelligent invigilation system from two aspects of hardware and software. The system on the basis of the standardized test in video monitoring system, aiming at solving the problem that the traditional EM algorithm is sensitive to initial value, this paper puts forward an improved method to make supervised learning image and human body’s contour recognition, to extract and analyse the scene of the abnormal information feature, and use adaptive threshold algorithm to improve the accuracy of the automatic alarm. these technology make the monitor platform be able to find abnormal information, and timely feed them back to the On-site invigilators. Finally, it can realize intelligent invigilation, improve the precision of supervision system, and has promotion value.
{"title":"Realization of Intelligent Invigilation System Based on Adaptive Threshold","authors":"Yunjie Fang, Jingcheng Ye, Hao Wang","doi":"10.1109/ICCCS49078.2020.9118581","DOIUrl":"https://doi.org/10.1109/ICCCS49078.2020.9118581","url":null,"abstract":"In order to reduce the labor cost of invigilation, improve invigilation efficiency and deal with violations in real time, this paper designs and implements an intelligent invigilation system from two aspects of hardware and software. The system on the basis of the standardized test in video monitoring system, aiming at solving the problem that the traditional EM algorithm is sensitive to initial value, this paper puts forward an improved method to make supervised learning image and human body’s contour recognition, to extract and analyse the scene of the abnormal information feature, and use adaptive threshold algorithm to improve the accuracy of the automatic alarm. these technology make the monitor platform be able to find abnormal information, and timely feed them back to the On-site invigilators. Finally, it can realize intelligent invigilation, improve the precision of supervision system, and has promotion value.","PeriodicalId":105556,"journal":{"name":"2020 5th International Conference on Computer and Communication Systems (ICCCS)","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117281943","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 : 2020-05-01DOI: 10.1109/ICCCS49078.2020.9118576
U. Choi, Sung-Jin Cho, S. Kang
Due to the development of the Internet and the communication network environment, image transmissions occur very frequently. In such an environment, the color image is likely to be distorted by noise. Image shuffling is a technique which resists distortion and deletion attacks. In this paper, we propose a speed-up method for shuffling pixels in the color image encryption system. In that step of shuffling, we use 1-D MLCAs to shuffle the pixel position of an image. In fact 1-D MLCA is higher in randomness than the conventional chaotic map and faster than the 3-D generalized chaotic cat map. The comparison of the execution time between the proposed method and the existing method is made.
{"title":"High Speed Color Image Encryption Using Pixel Shuffling With 1-D MLCA","authors":"U. Choi, Sung-Jin Cho, S. Kang","doi":"10.1109/ICCCS49078.2020.9118576","DOIUrl":"https://doi.org/10.1109/ICCCS49078.2020.9118576","url":null,"abstract":"Due to the development of the Internet and the communication network environment, image transmissions occur very frequently. In such an environment, the color image is likely to be distorted by noise. Image shuffling is a technique which resists distortion and deletion attacks. In this paper, we propose a speed-up method for shuffling pixels in the color image encryption system. In that step of shuffling, we use 1-D MLCAs to shuffle the pixel position of an image. In fact 1-D MLCA is higher in randomness than the conventional chaotic map and faster than the 3-D generalized chaotic cat map. The comparison of the execution time between the proposed method and the existing method is made.","PeriodicalId":105556,"journal":{"name":"2020 5th International Conference on Computer and Communication Systems (ICCCS)","volume":"203 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132868886","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 : 2020-05-01DOI: 10.1109/ICCCS49078.2020.9118440
Qi-pei Qian, Kai-xuan Bao, Kai Zhao, Yin Lu
Predicting the impact of open residential roads will have significance not only for transportation planning and economic development, but also for the enhancement of human society. Aiming at the problem of different road and community structure, this paper considers the road length, road speed limit, traffic volume, traffic lights, and other factors to improve the traffic capability. Then uses nonlinear programming to obtain the optimal solution based on BPR road impedance model. Finally, based on different residential road structures and traffic pressure, the enhancement of open residential roads is compared to find out which road structure is optimal for opening.
{"title":"Research on the Impact of Open Residential Roads on Traffic Capability","authors":"Qi-pei Qian, Kai-xuan Bao, Kai Zhao, Yin Lu","doi":"10.1109/ICCCS49078.2020.9118440","DOIUrl":"https://doi.org/10.1109/ICCCS49078.2020.9118440","url":null,"abstract":"Predicting the impact of open residential roads will have significance not only for transportation planning and economic development, but also for the enhancement of human society. Aiming at the problem of different road and community structure, this paper considers the road length, road speed limit, traffic volume, traffic lights, and other factors to improve the traffic capability. Then uses nonlinear programming to obtain the optimal solution based on BPR road impedance model. Finally, based on different residential road structures and traffic pressure, the enhancement of open residential roads is compared to find out which road structure is optimal for opening.","PeriodicalId":105556,"journal":{"name":"2020 5th International Conference on Computer and Communication Systems (ICCCS)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133898659","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 : 2020-05-01DOI: 10.1109/ICCCS49078.2020.9118444
Kun Yue, Jiahui Wang, Xinbai Li, Kuang Hu
The method of knowledge graph completion (KGC) by adding external knowledge with new entities was discussed in this paper. Adopting the TransE-based representation of relations and triples in Knowledge Graph, we extract triples from open-world data and evaluate their correctness to fulfill KGC, where vectors are used for similarity evaluation. From the “structural” point of view, triples were first built from open-world data according to the similarity between TransE-based representation of pairs of entities and that of relations in KG. From the “semantic” point of view, the correctness of each external triple was evaluated by measuring the distance in the triple locally and ranking in the entire KG globally. ON the FreeBase and DBPedia KGs by different KG representation models and KGC methods, experimental results show that our proposal outperforms some state-of-the-art methods.
{"title":"Representation-Based Completion of Knowledge Graph with Open-World Data","authors":"Kun Yue, Jiahui Wang, Xinbai Li, Kuang Hu","doi":"10.1109/ICCCS49078.2020.9118444","DOIUrl":"https://doi.org/10.1109/ICCCS49078.2020.9118444","url":null,"abstract":"The method of knowledge graph completion (KGC) by adding external knowledge with new entities was discussed in this paper. Adopting the TransE-based representation of relations and triples in Knowledge Graph, we extract triples from open-world data and evaluate their correctness to fulfill KGC, where vectors are used for similarity evaluation. From the “structural” point of view, triples were first built from open-world data according to the similarity between TransE-based representation of pairs of entities and that of relations in KG. From the “semantic” point of view, the correctness of each external triple was evaluated by measuring the distance in the triple locally and ranking in the entire KG globally. ON the FreeBase and DBPedia KGs by different KG representation models and KGC methods, experimental results show that our proposal outperforms some state-of-the-art methods.","PeriodicalId":105556,"journal":{"name":"2020 5th International Conference on Computer and Communication Systems (ICCCS)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127864820","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：