PBFT is a consensus algorithm based on Byzantine fault tolerance that is widely used in current systems like blockchains. However, this algorithm has some problems that slow down its use on a large scale. In the interest of solving its problems, we have combined it with the Distributed Proof of Stake (DPoS) algorithm and smart contract technology to improve it and make it better. For this, Smart contracts were deployed in the network to improve the selection process of accounting nodes and participated in the operating process of the PBFT algorithm in order to make the selection process more transparent, incorruptible, and secure. Concerning the problem of the scalability of the nodes of the system, it will be possible to make a readjustment of the consensus algorithm to make it more flexible. The modification can be done by implementing readjustment counters, which will count the number of nodes in the network each time a consensus is reached or a node is ejected from the network, then automatically distributes the list of new nodes in the network. This new list of nodes will constitute the new network on which the new consensus will be based. To make it more secure and more sensitive to Byzantine faults, the sensitivity margin is improved.
{"title":"Research on an improved practical byzantine fault tolerance algorithm","authors":"Seybou Sakho, Jian-biao Zhang, Firdaous Essaf, Khalid Badiss, Tchewafei Abide, Julius Kibet Kiprop","doi":"10.1109/CTISC49998.2020.00035","DOIUrl":"https://doi.org/10.1109/CTISC49998.2020.00035","url":null,"abstract":"PBFT is a consensus algorithm based on Byzantine fault tolerance that is widely used in current systems like blockchains. However, this algorithm has some problems that slow down its use on a large scale. In the interest of solving its problems, we have combined it with the Distributed Proof of Stake (DPoS) algorithm and smart contract technology to improve it and make it better. For this, Smart contracts were deployed in the network to improve the selection process of accounting nodes and participated in the operating process of the PBFT algorithm in order to make the selection process more transparent, incorruptible, and secure. Concerning the problem of the scalability of the nodes of the system, it will be possible to make a readjustment of the consensus algorithm to make it more flexible. The modification can be done by implementing readjustment counters, which will count the number of nodes in the network each time a consensus is reached or a node is ejected from the network, then automatically distributes the list of new nodes in the network. This new list of nodes will constitute the new network on which the new consensus will be based. To make it more secure and more sensitive to Byzantine faults, the sensitivity margin is improved.","PeriodicalId":266384,"journal":{"name":"2020 2nd International Conference on Advances in Computer Technology, Information Science and Communications (CTISC)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128810880","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 : 2020-03-01DOI: 10.1109/CTISC49998.2020.00031
Shicheng Zu, LinTao Wan, Dong Li, Zhongfeng Qiu
Since most state-of-the-art road mappers pose the road network extraction as a binary segmentation trained on the RGB dataset, our proposed ‘RoadRouter’ system pushes the frontier by classifying the roads into seven categories based on the SpaceNet annotations. Our system is built with the Red/Near-Infrared dataset, making use of the asphalt’s spectral signature to differentiate roads from other influential noises. For addressing the disconnected road gaps problem, we propose the stacked hourglass network with dual supervision. Inspired by the human behavior of tracing the road networks via a constant orientation, incorporating the orientation learning as auxiliary loss leads to more robust and synergistic representations favorable for road connectivity refinement. The intermediate supervision provided by stacking the hourglass modules successively also serves as a connectivity refinement mechanism. In the case of modeling the long-range interaction among the per-pixel predictions, the traditional color-based appearance kernel is not useful in CRF post-processing. We propose the pixel-wise orientation CRF specific for bridging the fragmented road segments. We also formalize an image transformation protocol to parse the topology from the road segmentation. The undirected closed graphs can thereby be constructed from probabilistic inferences. Various graph-based algorithms, e.g., the shortest path searching, can be implemented on the road graph representations.
{"title":"RoadRouter: Multi-Task Learning of Road Network Extraction with Graph Representation","authors":"Shicheng Zu, LinTao Wan, Dong Li, Zhongfeng Qiu","doi":"10.1109/CTISC49998.2020.00031","DOIUrl":"https://doi.org/10.1109/CTISC49998.2020.00031","url":null,"abstract":"Since most state-of-the-art road mappers pose the road network extraction as a binary segmentation trained on the RGB dataset, our proposed ‘RoadRouter’ system pushes the frontier by classifying the roads into seven categories based on the SpaceNet annotations. Our system is built with the Red/Near-Infrared dataset, making use of the asphalt’s spectral signature to differentiate roads from other influential noises. For addressing the disconnected road gaps problem, we propose the stacked hourglass network with dual supervision. Inspired by the human behavior of tracing the road networks via a constant orientation, incorporating the orientation learning as auxiliary loss leads to more robust and synergistic representations favorable for road connectivity refinement. The intermediate supervision provided by stacking the hourglass modules successively also serves as a connectivity refinement mechanism. In the case of modeling the long-range interaction among the per-pixel predictions, the traditional color-based appearance kernel is not useful in CRF post-processing. We propose the pixel-wise orientation CRF specific for bridging the fragmented road segments. We also formalize an image transformation protocol to parse the topology from the road segmentation. The undirected closed graphs can thereby be constructed from probabilistic inferences. Various graph-based algorithms, e.g., the shortest path searching, can be implemented on the road graph representations.","PeriodicalId":266384,"journal":{"name":"2020 2nd International Conference on Advances in Computer Technology, Information Science and Communications (CTISC)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127427413","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}
In this paper, we propose a power allocation scheme in order to improve both secure and reliable performance in the wireless two-hop threshold-selection decode-and-forward (DF) relaying networks, which is so crucial to set a threshold value related the signal-to-noise ratio (SNR) of the source signal at relay nodes for perfect decoding. We adapt the maximal-ratio combining (MRC) receiving SNR from the direct and relaying paths both at the destination and at the eavesdropper. Particularly worth mentioning is that the closed expression form of outage probability and intercept probability is driven, which can quantify the security and reliability, respectively. We also make endeavors to utilize a metric to tradeoff the security and the reliability (SRT) and find out the relevance between them in the balanced case. But beyond that, in the pursuit of tradeoff performance, power allocation tends to depend on the threshold value. In other words, it provides a new method optimizing total power to the source and the relay by the threshold value. The results are obtained from analysis, confirmed by simulation, and predicted by artificial neural networks (ANNs), which is trained with back propagation (BP) algorithm, and thus the feasibility of the proposed method is verified.
{"title":"Prediction of Optimal Power Allocation for Enhancing Security-Reliability Tradeoff with the Application of Artificial Neural Networks","authors":"Xiaoyu Wang, Yuanyuan Gao, Guangna Zhang, Mingxi Guo","doi":"10.1109/CTISC49998.2020.00013","DOIUrl":"https://doi.org/10.1109/CTISC49998.2020.00013","url":null,"abstract":"In this paper, we propose a power allocation scheme in order to improve both secure and reliable performance in the wireless two-hop threshold-selection decode-and-forward (DF) relaying networks, which is so crucial to set a threshold value related the signal-to-noise ratio (SNR) of the source signal at relay nodes for perfect decoding. We adapt the maximal-ratio combining (MRC) receiving SNR from the direct and relaying paths both at the destination and at the eavesdropper. Particularly worth mentioning is that the closed expression form of outage probability and intercept probability is driven, which can quantify the security and reliability, respectively. We also make endeavors to utilize a metric to tradeoff the security and the reliability (SRT) and find out the relevance between them in the balanced case. But beyond that, in the pursuit of tradeoff performance, power allocation tends to depend on the threshold value. In other words, it provides a new method optimizing total power to the source and the relay by the threshold value. The results are obtained from analysis, confirmed by simulation, and predicted by artificial neural networks (ANNs), which is trained with back propagation (BP) algorithm, and thus the feasibility of the proposed method is verified.","PeriodicalId":266384,"journal":{"name":"2020 2nd International Conference on Advances in Computer Technology, Information Science and Communications (CTISC)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122076460","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 : 2020-03-01DOI: 10.1109/CTISC49998.2020.00024
Shigeo Akashi, Yao Tong
Web masquerade is defined as the network skill enabling to display various kinds of web contents on the monitors without changing URLs which are input into the web browsers. It is well known that there is a method of web masquerade which can change the web contents according to a change of the switchport to which a personal computer is directly connected. In this paper, we introduce another method of web masquerade which can change the web contents according to a change of the MAC address attached to a personal computer. In other words, we introduce the new system playing the role at the datalink layer which is analogous to the role being played by the vlan membership policy system at the network layer.
Web masquerade是一种能够在不改变输入到Web浏览器的url的情况下在监视器上显示各种Web内容的网络技能。众所周知，有一种网络伪装的方法，可以根据个人电脑直接连接的交换机端口的变化来改变网络内容。本文介绍了另一种网络伪装的方法，该方法可以根据附加在个人计算机上的MAC地址的变化来改变网络内容。换句话说，我们引入了在数据链路层扮演类似于vlan成员策略系统在网络层扮演的角色的新系统。
{"title":"Web Masquerade Based on the MAC Addresses : How to change the web contents without changing the corresponding uniform resource locators","authors":"Shigeo Akashi, Yao Tong","doi":"10.1109/CTISC49998.2020.00024","DOIUrl":"https://doi.org/10.1109/CTISC49998.2020.00024","url":null,"abstract":"Web masquerade is defined as the network skill enabling to display various kinds of web contents on the monitors without changing URLs which are input into the web browsers. It is well known that there is a method of web masquerade which can change the web contents according to a change of the switchport to which a personal computer is directly connected. In this paper, we introduce another method of web masquerade which can change the web contents according to a change of the MAC address attached to a personal computer. In other words, we introduce the new system playing the role at the datalink layer which is analogous to the role being played by the vlan membership policy system at the network layer.","PeriodicalId":266384,"journal":{"name":"2020 2nd International Conference on Advances in Computer Technology, Information Science and Communications (CTISC)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129487713","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 : 2020-03-01DOI: 10.1109/CTISC49998.2020.00009
Ge Yu, Bin Wu, Xinxin Niu
Practical Byzantine Fault Tolerance (PBFT) is a blockchain consensus mechanism that is widely used at present, but the confidence of blockchain node in PBFT cannot be guaranteed, and a large amount of communication resources will be consumed in the process of reaching consensus. The paper proposes a new consensus mechanism, namely the Dynamic Grouping Byzantine Fault Tolerance Mechanism (DGBFT) based on confidence. The principles of DGBFT are as follows: 1) By extending the node’s attributes with the confidence, and designing a mechanism to evaluate the node’s confidence, therefore, the confidence adjustment and grouping adjustment can be performed on the nodes in the system. By grouping the confidence nodes by the confidence group, the communication complexity is greatly reduced, and the malicious nodes can be effectively excluded. Finally, the experimental results show that the blockchain applying the improved mechanism can significantly improve the communication efficiency of the system and the overall confidence of the system.
{"title":"Improved Blockchain Consensus Mechanism Based on PBFT Algorithm","authors":"Ge Yu, Bin Wu, Xinxin Niu","doi":"10.1109/CTISC49998.2020.00009","DOIUrl":"https://doi.org/10.1109/CTISC49998.2020.00009","url":null,"abstract":"Practical Byzantine Fault Tolerance (PBFT) is a blockchain consensus mechanism that is widely used at present, but the confidence of blockchain node in PBFT cannot be guaranteed, and a large amount of communication resources will be consumed in the process of reaching consensus. The paper proposes a new consensus mechanism, namely the Dynamic Grouping Byzantine Fault Tolerance Mechanism (DGBFT) based on confidence. The principles of DGBFT are as follows: 1) By extending the node’s attributes with the confidence, and designing a mechanism to evaluate the node’s confidence, therefore, the confidence adjustment and grouping adjustment can be performed on the nodes in the system. By grouping the confidence nodes by the confidence group, the communication complexity is greatly reduced, and the malicious nodes can be effectively excluded. Finally, the experimental results show that the blockchain applying the improved mechanism can significantly improve the communication efficiency of the system and the overall confidence of the system.","PeriodicalId":266384,"journal":{"name":"2020 2nd International Conference on Advances in Computer Technology, Information Science and Communications (CTISC)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117262755","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}
International Technical Program Committees William (Michael) Pace, Texas A&M University, USA Francesco Colace, University of Salerno, Itlay Bok-Min Goi (SMIEEE), Universiti Tunku Abdul Rahman (UTAR), Malaysia Emanuel S. Grant, University of North Dakota, US Hosam El-Ocla (SMIEEE), Lakehead University, Canada Yung-Hui Li, National Central University, Taiwan Wai Lam Hoo, University of Malaya, Malaysia Jain-shing Liu, Providence University, Taiwan Xin Lou, Advanced Digital Sciences Center, Singapore Muhammad Roil Bilad, Universiti Teknologi Petronas, Malaysia Hussain Al-Aqrabi, University of Huddersfield, UK Bohumil Brtník, University of Pardubice, Czech Republic Zainb Dawod, Brunel University London, UK Cathryn Peoples, The Open University, UK Ahmad El-Banna, Benha University, Egypt Zakariya Chabani, Istanbul University, Turkey Seppo Sirkemaa, University of Turku, Finland Juryon Paik, Pyeongtaek University, South Korea Anas M.R. AlSobeh, Yarmouk University, Jordan Shamsul Jamel Elias, Universiti Teknologi MARA, Malaysia Syed Farooq Ali, University of Management and Technology, Pakistan Hadi Sutopo, Kalbis Institute, Indonesia Turi, Michael, California State University, Fullerton, USA Anastasia Anagnostou, Brunel University London, UK
{"title":"CTISC 2020 Committees","authors":"S. Hsieh, Shigeo Akashi, Ping Guo, Xiaochen Yuan, Bo-Hao Chen, Yuan Ze, Jiankang Ren","doi":"10.1109/ctisc49998.2020.00006","DOIUrl":"https://doi.org/10.1109/ctisc49998.2020.00006","url":null,"abstract":"International Technical Program Committees William (Michael) Pace, Texas A&M University, USA Francesco Colace, University of Salerno, Itlay Bok-Min Goi (SMIEEE), Universiti Tunku Abdul Rahman (UTAR), Malaysia Emanuel S. Grant, University of North Dakota, US Hosam El-Ocla (SMIEEE), Lakehead University, Canada Yung-Hui Li, National Central University, Taiwan Wai Lam Hoo, University of Malaya, Malaysia Jain-shing Liu, Providence University, Taiwan Xin Lou, Advanced Digital Sciences Center, Singapore Muhammad Roil Bilad, Universiti Teknologi Petronas, Malaysia Hussain Al-Aqrabi, University of Huddersfield, UK Bohumil Brtník, University of Pardubice, Czech Republic Zainb Dawod, Brunel University London, UK Cathryn Peoples, The Open University, UK Ahmad El-Banna, Benha University, Egypt Zakariya Chabani, Istanbul University, Turkey Seppo Sirkemaa, University of Turku, Finland Juryon Paik, Pyeongtaek University, South Korea Anas M.R. AlSobeh, Yarmouk University, Jordan Shamsul Jamel Elias, Universiti Teknologi MARA, Malaysia Syed Farooq Ali, University of Management and Technology, Pakistan Hadi Sutopo, Kalbis Institute, Indonesia Turi, Michael, California State University, Fullerton, USA Anastasia Anagnostou, Brunel University London, UK","PeriodicalId":266384,"journal":{"name":"2020 2nd International Conference on Advances in Computer Technology, Information Science and Communications (CTISC)","volume":"347 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124278773","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 : 2020-03-01DOI: 10.1109/CTISC49998.2020.00030
Ben Wang
Visual fiducial systems are a key component of many robotics and AR/VR applications for 6-DOF monocular relative pose estimation and target identification. This paper presents LFTag, a visual fiducial system based on topological detection and relative position data encoding which optimizes data density within spatial frequency constraints. The marker is constructed to resolve rotational ambiguity, which combined with the robust geometric and topological false positive rejection, allows all marker bits to be used for data.When compared to existing state-of-the-art square binary markers (AprilTag) and topological markers (TopoTag) in simulation, the proposed fiducial system (LFTag) offers significant advances in dictionary size and range. LFTag 3×3 achieves 546 times the dictionary size of AprilTag 25h9 and LFTag 4×4 achieves 126 thousand times the dictionary size of AprilTag 41h12 while simultaneously achieving longer detection range. LFTag 3×3 also achieves more than twice the detection range of TopoTag 4×4 at the same dictionary size.
{"title":"LFTag: A Scalable Visual Fiducial System with Low Spatial Frequency","authors":"Ben Wang","doi":"10.1109/CTISC49998.2020.00030","DOIUrl":"https://doi.org/10.1109/CTISC49998.2020.00030","url":null,"abstract":"Visual fiducial systems are a key component of many robotics and AR/VR applications for 6-DOF monocular relative pose estimation and target identification. This paper presents LFTag, a visual fiducial system based on topological detection and relative position data encoding which optimizes data density within spatial frequency constraints. The marker is constructed to resolve rotational ambiguity, which combined with the robust geometric and topological false positive rejection, allows all marker bits to be used for data.When compared to existing state-of-the-art square binary markers (AprilTag) and topological markers (TopoTag) in simulation, the proposed fiducial system (LFTag) offers significant advances in dictionary size and range. LFTag 3×3 achieves 546 times the dictionary size of AprilTag 25h9 and LFTag 4×4 achieves 126 thousand times the dictionary size of AprilTag 41h12 while simultaneously achieving longer detection range. LFTag 3×3 also achieves more than twice the detection range of TopoTag 4×4 at the same dictionary size.","PeriodicalId":266384,"journal":{"name":"2020 2nd International Conference on Advances in Computer Technology, Information Science and Communications (CTISC)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124299244","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 : 2020-03-01DOI: 10.1109/CTISC49998.2020.00014
Xing Yongchang, Hong Wei, Zhang Heng, Ding Youfeng, Sun Bin, Hu Wankun
In this paper, we proposed a novel algorithm based on the generalized cyclic stationary characteristics for estimating sinusoidal frequency-modulated (SFM) signals in the presence of heavy-tailed noise. The properties of the cyclic autocorrelation function for parameter estimation are first investigated. Then, the modulation frequency of the SFM signal is estimated based on the generalized cyclic stationary characteristics. Finally, the carrier frequency and modulation index are achieved by constructing the reference signal. Theoretical analysis and numerical simulation indicate that the proposed method can significantly improve the performance of parameters estimation of SFM signals in the presence of heavy-tailed noise.
{"title":"Parameter Estimation of Sinusoid Frequency Modulation Signal in Heavy-tailed Noise","authors":"Xing Yongchang, Hong Wei, Zhang Heng, Ding Youfeng, Sun Bin, Hu Wankun","doi":"10.1109/CTISC49998.2020.00014","DOIUrl":"https://doi.org/10.1109/CTISC49998.2020.00014","url":null,"abstract":"In this paper, we proposed a novel algorithm based on the generalized cyclic stationary characteristics for estimating sinusoidal frequency-modulated (SFM) signals in the presence of heavy-tailed noise. The properties of the cyclic autocorrelation function for parameter estimation are first investigated. Then, the modulation frequency of the SFM signal is estimated based on the generalized cyclic stationary characteristics. Finally, the carrier frequency and modulation index are achieved by constructing the reference signal. Theoretical analysis and numerical simulation indicate that the proposed method can significantly improve the performance of parameters estimation of SFM signals in the presence of heavy-tailed noise.","PeriodicalId":266384,"journal":{"name":"2020 2nd International Conference on Advances in Computer Technology, Information Science and Communications (CTISC)","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122891049","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 : 2020-03-01DOI: 10.1109/CTISC49998.2020.00026
Wenchao Zhao, Qiang Zhang, Haihan Li, Bin Li, Jiaohao Zhang
Illegal flight of unmanned aerial vehicles (UAVs) poses serious threats to the public and national security. With the characteristics of small size and low flight height, UAVs are difficult for the traditional air-defense system to detect. Therefore, to deal with the illegal UAV flight, this paper proposed a state-of-the art low-altitude UAV detection method. Firstly, a large-scale UAV data set including multiple kinds of UAVs is collected and constructed. Then, based on one stage detection framework, the UAV detection (UAVDet) network is presented with the improvement of more detection scales, utilization of focal loss and specific data augmentation. Experiment results show that the proposed UAV detection method has significant improvement on UAV detection performance, and it is competent to achieve real-time and effective UAV detection.
{"title":"Low-altitude UAV Detection Method Based on One-staged Detection Framework","authors":"Wenchao Zhao, Qiang Zhang, Haihan Li, Bin Li, Jiaohao Zhang","doi":"10.1109/CTISC49998.2020.00026","DOIUrl":"https://doi.org/10.1109/CTISC49998.2020.00026","url":null,"abstract":"Illegal flight of unmanned aerial vehicles (UAVs) poses serious threats to the public and national security. With the characteristics of small size and low flight height, UAVs are difficult for the traditional air-defense system to detect. Therefore, to deal with the illegal UAV flight, this paper proposed a state-of-the art low-altitude UAV detection method. Firstly, a large-scale UAV data set including multiple kinds of UAVs is collected and constructed. Then, based on one stage detection framework, the UAV detection (UAVDet) network is presented with the improvement of more detection scales, utilization of focal loss and specific data augmentation. Experiment results show that the proposed UAV detection method has significant improvement on UAV detection performance, and it is competent to achieve real-time and effective UAV detection.","PeriodicalId":266384,"journal":{"name":"2020 2nd International Conference on Advances in Computer Technology, Information Science and Communications (CTISC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129362425","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 : 2020-03-01DOI: 10.1109/CTISC49998.2020.00010
Long Zhang, Min Zhao, Cheng Tan, Gang Li, Chunying Lv
Electromagnetic spectrum sensing is an important component of electromagnetic spectrum capability. With the development of spectrum sensing technology, there are still many problems and challenges in practical applications. For example, though the spectrum sensing field has diversified, the system is still based on manual operation; there are massive and diverse data, but the depth and breadth of data mining are insufficient; there is a large amount of historical data, multiple heterogeneous and unlabeled data types, and multidimensional non fusion platforms. The above difficulties hinder the construction of electromagnetic spectrum sensing ability and efficiency. Therefore, we propose a spectrum sensing system based on composite neural network architecture, the overall architecture includes three layers; spectrum sensing layer, data processing layer and situation analysis layer, which realizes the bottom data processing and high-dimensional spectrum sensing analysis. With the development of artificial intelligence technology [1], the above problems can be further improved and the development from artificial to intelligent can be realized gradually by using deep learning algorithm framework and exploring the advanced artificial intelligence technology. Finally, a three-dimensional electromagnetic situation map is formed from the time dimension, space dimension and spectrum dimension, so as to realize intelligence.
{"title":"Research on Spectrum Sensing System Based on Composite Neural Network","authors":"Long Zhang, Min Zhao, Cheng Tan, Gang Li, Chunying Lv","doi":"10.1109/CTISC49998.2020.00010","DOIUrl":"https://doi.org/10.1109/CTISC49998.2020.00010","url":null,"abstract":"Electromagnetic spectrum sensing is an important component of electromagnetic spectrum capability. With the development of spectrum sensing technology, there are still many problems and challenges in practical applications. For example, though the spectrum sensing field has diversified, the system is still based on manual operation; there are massive and diverse data, but the depth and breadth of data mining are insufficient; there is a large amount of historical data, multiple heterogeneous and unlabeled data types, and multidimensional non fusion platforms. The above difficulties hinder the construction of electromagnetic spectrum sensing ability and efficiency. Therefore, we propose a spectrum sensing system based on composite neural network architecture, the overall architecture includes three layers; spectrum sensing layer, data processing layer and situation analysis layer, which realizes the bottom data processing and high-dimensional spectrum sensing analysis. With the development of artificial intelligence technology [1], the above problems can be further improved and the development from artificial to intelligent can be realized gradually by using deep learning algorithm framework and exploring the advanced artificial intelligence technology. Finally, a three-dimensional electromagnetic situation map is formed from the time dimension, space dimension and spectrum dimension, so as to realize intelligence.","PeriodicalId":266384,"journal":{"name":"2020 2nd International Conference on Advances in Computer Technology, Information Science and Communications (CTISC)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122727355","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：