Pub Date : 2020-12-11DOI: 10.1109/ICCC51575.2020.9345000
J. Zhang, Zhongmin Pei, Wei Xiong, Zhangkai Luo
In the knowledge graph question answering, the graph neural network can be used to encode the subgraph nodes related to the question entity to select the correct answer node. However, existing researches mainly focus on the modalities for the node encoding with graph neural network, ignoring that different types of subgraphs have different requirements for encoding information. To overcome the problem, this paper divides the subgraph into two types: the searching graph and the extending graph. Then we propose an answer extraction method with graph attention network for the searching graph, which can weight the information of neighbor nodes with different attention instead of the average. The hierarchical attention is also introduced to integrate question information into the subgraph node embedding to obtain the node presentation with question dependency. The accuracy of 48.2% is achieved on the CommonsenseQA dataset, which is much higher than the random guess (20%). In addition, the accuracy of the simplified model with no hierarchical attention decreases by 3.5%, which indicates the hierarchical attention mechanism can improve the predictive performance of the proposed model.
{"title":"Answer Extraction with Graph Attention Network for Knowledge Graph Question Answering","authors":"J. Zhang, Zhongmin Pei, Wei Xiong, Zhangkai Luo","doi":"10.1109/ICCC51575.2020.9345000","DOIUrl":"https://doi.org/10.1109/ICCC51575.2020.9345000","url":null,"abstract":"In the knowledge graph question answering, the graph neural network can be used to encode the subgraph nodes related to the question entity to select the correct answer node. However, existing researches mainly focus on the modalities for the node encoding with graph neural network, ignoring that different types of subgraphs have different requirements for encoding information. To overcome the problem, this paper divides the subgraph into two types: the searching graph and the extending graph. Then we propose an answer extraction method with graph attention network for the searching graph, which can weight the information of neighbor nodes with different attention instead of the average. The hierarchical attention is also introduced to integrate question information into the subgraph node embedding to obtain the node presentation with question dependency. The accuracy of 48.2% is achieved on the CommonsenseQA dataset, which is much higher than the random guess (20%). In addition, the accuracy of the simplified model with no hierarchical attention decreases by 3.5%, which indicates the hierarchical attention mechanism can improve the predictive performance of the proposed model.","PeriodicalId":386048,"journal":{"name":"2020 IEEE 6th International Conference on Computer and Communications (ICCC)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123262186","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}
During the production and processing of the intelligent production line system of the Industrial Internet of Things (IIoT), it is easy to generate risks such as the unauthorized acquisition, tampering and unauthorized control of sensitive information by a third party in the communication. This paper propose and construct a dynamic attribute collaborative security access control strategy for sensitive resources of intelligent production line system in view of the risks and requirements of security access control of perceived information between intelligent production line equipment in the IIoT environment. Based on this strategy, a D-RSBAC (Dynamic-role&sensitivity based access control) model for intelligent production line system security is further established. This strategy realize the relative isolation of equipment processing control information on the basis of ensuring the overall performance of the communication system. This strategy allocate data access permissions dynamically based on roles and resource security levels to prevent sensitive information on the production line from being illegally obtained and tampered with by third parties during communications. This strategy can improve the security and reliability of information access effectively.
工业物联网(IIoT)智能生产线系统在生产加工过程中，在通信过程中容易产生敏感信息被第三方擅自获取、篡改、控制等风险。针对IIoT环境下智能生产线设备间感知信息安全访问控制的风险和需求，提出并构建了智能生产线系统敏感资源的动态属性协同安全访问控制策略。在此基础上，进一步建立了智能生产线系统安全的D-RSBAC (Dynamic-role&sensitivity Based access control)模型。该策略在保证通信系统整体性能的基础上实现了设备处理控制信息的相对隔离。该策略根据角色和资源安全级别动态分配数据访问权限，防止生产线上的敏感信息在通信过程中被第三方非法获取和篡改。该策略可以有效地提高信息访问的安全性和可靠性。
{"title":"A Security Access Strategy for Sensitive Resource of Intelligent Production Line System with Dynamic Attribute Collaboration","authors":"Mingshi Li, Yue Ma, Zhenyu Yin, Anying Chai, Mengjia Lian, Chunxiao Wang","doi":"10.1109/ICCC51575.2020.9345298","DOIUrl":"https://doi.org/10.1109/ICCC51575.2020.9345298","url":null,"abstract":"During the production and processing of the intelligent production line system of the Industrial Internet of Things (IIoT), it is easy to generate risks such as the unauthorized acquisition, tampering and unauthorized control of sensitive information by a third party in the communication. This paper propose and construct a dynamic attribute collaborative security access control strategy for sensitive resources of intelligent production line system in view of the risks and requirements of security access control of perceived information between intelligent production line equipment in the IIoT environment. Based on this strategy, a D-RSBAC (Dynamic-role&sensitivity based access control) model for intelligent production line system security is further established. This strategy realize the relative isolation of equipment processing control information on the basis of ensuring the overall performance of the communication system. This strategy allocate data access permissions dynamically based on roles and resource security levels to prevent sensitive information on the production line from being illegally obtained and tampered with by third parties during communications. This strategy can improve the security and reliability of information access effectively.","PeriodicalId":386048,"journal":{"name":"2020 IEEE 6th International Conference on Computer and Communications (ICCC)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125397909","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 : 2020-12-11DOI: 10.1109/ICCC51575.2020.9345170
Chen Han, A. Liu, Xiaohu Liang, Lang Ruan, Kaixin Cheng
Large unmanned aerial vehicle (UAV) performs reconnaissance and data collection missions against hostile jamming in satellite-UAV coordination Networks. In this case, the ground base station (BS) is unable to provide access service to the UAV, thus the UAV has to rely on information support from the satellite communication system. Low earth orbit (LEO) satellites provide access beams for UAVs, and the UAV transmits the collected data to the satellite via uplink. Due to the unknown and uncertain environment, it is difficult for large UAV to get an effective planned flight trajectory, and the presence of malicious jamming further exacerbates the complexity of trajectory control. To address this problem, a reinforcement learning (RL) based trajectory control approach is proposed to explore the unknown jamming environment and realize autonomous trajectory planning. Finally, the simulation results prove the effectiveness of the proposed approach.
{"title":"UAV Trajectory Control Against Hostile Jamming in Satellite-UAV Coordination Networks","authors":"Chen Han, A. Liu, Xiaohu Liang, Lang Ruan, Kaixin Cheng","doi":"10.1109/ICCC51575.2020.9345170","DOIUrl":"https://doi.org/10.1109/ICCC51575.2020.9345170","url":null,"abstract":"Large unmanned aerial vehicle (UAV) performs reconnaissance and data collection missions against hostile jamming in satellite-UAV coordination Networks. In this case, the ground base station (BS) is unable to provide access service to the UAV, thus the UAV has to rely on information support from the satellite communication system. Low earth orbit (LEO) satellites provide access beams for UAVs, and the UAV transmits the collected data to the satellite via uplink. Due to the unknown and uncertain environment, it is difficult for large UAV to get an effective planned flight trajectory, and the presence of malicious jamming further exacerbates the complexity of trajectory control. To address this problem, a reinforcement learning (RL) based trajectory control approach is proposed to explore the unknown jamming environment and realize autonomous trajectory planning. Finally, the simulation results prove the effectiveness of the proposed approach.","PeriodicalId":386048,"journal":{"name":"2020 IEEE 6th International Conference on Computer and Communications (ICCC)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127032178","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 : 2020-12-11DOI: 10.1109/ICCC51575.2020.9344925
Haien Wang, Jing Zhang, Yang Zhao, Jun Wang, Xiaorong Du
Classification of high-voltage electric switches is an important operation in industrial manufacturing. However, the electrical shock hazards make it dangerous to human. Therefore, classifying high-voltage electric switches automatically is of great interest for factories. For this purpose, we designed a system based on k-nearest neighbor algorithm and bag of visual words model, which performs well in classifying 3 states of highvoltage electric switches. We achieve the classifying task by 3 steps: extracting features of high-voltage electric switch pictures by using SIFT algorithm; clustering SIFT features of all training pictures as visual words and set up a bag of visual words model; calculating the visual words frequency of each picture and using them as inputs of k-nearest neighbor classifier. With the trained model, we extract SIFT features and count visual words frequency of a new picture to be classified, then predict its state by looking for the k nearest training pictures. An experimental study performed on a set of pictures reveals some good performance of this system, compared to other classification methods such as SVM and VGG-16.
{"title":"A High-Voltage Electric Switch Classification System Based on K-Nearest Neighbor Classifier","authors":"Haien Wang, Jing Zhang, Yang Zhao, Jun Wang, Xiaorong Du","doi":"10.1109/ICCC51575.2020.9344925","DOIUrl":"https://doi.org/10.1109/ICCC51575.2020.9344925","url":null,"abstract":"Classification of high-voltage electric switches is an important operation in industrial manufacturing. However, the electrical shock hazards make it dangerous to human. Therefore, classifying high-voltage electric switches automatically is of great interest for factories. For this purpose, we designed a system based on k-nearest neighbor algorithm and bag of visual words model, which performs well in classifying 3 states of highvoltage electric switches. We achieve the classifying task by 3 steps: extracting features of high-voltage electric switch pictures by using SIFT algorithm; clustering SIFT features of all training pictures as visual words and set up a bag of visual words model; calculating the visual words frequency of each picture and using them as inputs of k-nearest neighbor classifier. With the trained model, we extract SIFT features and count visual words frequency of a new picture to be classified, then predict its state by looking for the k nearest training pictures. An experimental study performed on a set of pictures reveals some good performance of this system, compared to other classification methods such as SVM and VGG-16.","PeriodicalId":386048,"journal":{"name":"2020 IEEE 6th International Conference on Computer and Communications (ICCC)","volume":"107 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114899337","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 : 2020-12-11DOI: 10.1109/ICCC51575.2020.9345053
Ying Wang, Jidong Zhang, Jiang Liu, Hua Lu, Tao Huang
The fifth generation networks (5G) can support a variety of vertical industries, such as autonomous driving, telemedicine and industrial automation. Network Slicing (NS) is a promising technology for 5G that can provide customized end-to-end network services for multi-tenants. To provide services to tenants according to different service requirements, we model delay and reliability of NS. We propose a method for service-customized deployment of network slicing (SCD-NS), which allocates resources according to different types of network slices. When deploying a network slice, we adopt a two-stage deployment method, in which first stage is virtual node deployment and second stage is virtual link deployment. Since the problem of network slices deployment is usually NP-Hard, we encode the virtual node deployment solution as a chromosome and use genetic algorithms to solve this problem. In the stage of virtual node deployment, we obtain the initial solutions through minimizing the average number of hops between nodes. In the stage of virtual link deployment, we provide adaptive deployment based on the types of network slices. The simulation results show that SCD-NS realizes better service customization and higher network utilization compared with current algorithm.
{"title":"SCD-NS: Service Customized Deployment of Network Slicing","authors":"Ying Wang, Jidong Zhang, Jiang Liu, Hua Lu, Tao Huang","doi":"10.1109/ICCC51575.2020.9345053","DOIUrl":"https://doi.org/10.1109/ICCC51575.2020.9345053","url":null,"abstract":"The fifth generation networks (5G) can support a variety of vertical industries, such as autonomous driving, telemedicine and industrial automation. Network Slicing (NS) is a promising technology for 5G that can provide customized end-to-end network services for multi-tenants. To provide services to tenants according to different service requirements, we model delay and reliability of NS. We propose a method for service-customized deployment of network slicing (SCD-NS), which allocates resources according to different types of network slices. When deploying a network slice, we adopt a two-stage deployment method, in which first stage is virtual node deployment and second stage is virtual link deployment. Since the problem of network slices deployment is usually NP-Hard, we encode the virtual node deployment solution as a chromosome and use genetic algorithms to solve this problem. In the stage of virtual node deployment, we obtain the initial solutions through minimizing the average number of hops between nodes. In the stage of virtual link deployment, we provide adaptive deployment based on the types of network slices. The simulation results show that SCD-NS realizes better service customization and higher network utilization compared with current algorithm.","PeriodicalId":386048,"journal":{"name":"2020 IEEE 6th International Conference on Computer and Communications (ICCC)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115195590","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 : 2020-12-11DOI: 10.1109/iccc51575.2020.9345145
Yiwen Xu, Quanfei Zheng, Qingxu Lin, Kai Wang, Tiesong Zhao
As a new type of immersion interaction method, haptic communication technology has been widely applied in various fields. Data loss is inevitable during haptic communication, which will have significant negative impact on user's experience. Error resilience algorithm (ERA) is an effective method to solve this problem. However, traditional ERAs are based on linear prediction methods. Existing studies have verified that haptic data is not linear. Therefore, there still leave gaps to improve the performance of ERAs for haptic communication. To this end, this paper proposes an ERA of haptic communication based on an improved long short-term memory (LSTM) neural network. Firstly, an improved LSTM network is constructed by adding remedy gates to realize haptic data prediction, which effectively reduces the prediction error. Then, the presented ERA is implemented with the prediction model. Finally, we establish a simulation platform to compare the performance of the proposed algorithm with the popular-used ERAs in haptic communication. Experimental results show that our algorithm.
{"title":"Error Resilience Algorithm for Haptic Communication Based on Remedy-LSTM","authors":"Yiwen Xu, Quanfei Zheng, Qingxu Lin, Kai Wang, Tiesong Zhao","doi":"10.1109/iccc51575.2020.9345145","DOIUrl":"https://doi.org/10.1109/iccc51575.2020.9345145","url":null,"abstract":"As a new type of immersion interaction method, haptic communication technology has been widely applied in various fields. Data loss is inevitable during haptic communication, which will have significant negative impact on user's experience. Error resilience algorithm (ERA) is an effective method to solve this problem. However, traditional ERAs are based on linear prediction methods. Existing studies have verified that haptic data is not linear. Therefore, there still leave gaps to improve the performance of ERAs for haptic communication. To this end, this paper proposes an ERA of haptic communication based on an improved long short-term memory (LSTM) neural network. Firstly, an improved LSTM network is constructed by adding remedy gates to realize haptic data prediction, which effectively reduces the prediction error. Then, the presented ERA is implemented with the prediction model. Finally, we establish a simulation platform to compare the performance of the proposed algorithm with the popular-used ERAs in haptic communication. Experimental results show that our algorithm.","PeriodicalId":386048,"journal":{"name":"2020 IEEE 6th International Conference on Computer and Communications (ICCC)","volume":"94 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115999045","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 : 2020-12-11DOI: 10.1109/ICCC51575.2020.9345158
Wei Dai, Yanlei Shang
Network embedding (or graph embedding) has been researched and used widely in recent years especially in academic and e-commerce area. Most methods pay more attention to homogeneous networks with single-typed nodes or edges. However, networks in real world are more complex and larger, consisting of multiple types of nodes, edges and even node attributes. Existing algorithms treat these multiplex heterogeneous networks as homogeneous network, ignoring correlations among different node types and edge types even deep semantic information. In light of these issues, we developed a new framework to solve heterogeneous network embedding problems. We mainly focus on Attributed Multiplex Heterogeneous Network but our method can apply to both heterogeneous and homogeneous networks. We also propose an edge-concerned metapath strategy to guide random walk, providing walking guidance among different layers separated by edge type and then leverages a heterogeneous skip-gram model to compute overall node embeddings. We conduct quantitative experiments to evaluate our method on four public dataset: Amazon, Youtube, DBLP and Movielens. As demonstrated by experimental results, our method achieves statistically significant improvements over compared previous methods on link prediction tasks. We also explore the parameter sensitivity of our proposed model to figure out function fluctuation while tuning parameters.
{"title":"Edge-Concerned Embedding for Multiplex Heterogeneous Network","authors":"Wei Dai, Yanlei Shang","doi":"10.1109/ICCC51575.2020.9345158","DOIUrl":"https://doi.org/10.1109/ICCC51575.2020.9345158","url":null,"abstract":"Network embedding (or graph embedding) has been researched and used widely in recent years especially in academic and e-commerce area. Most methods pay more attention to homogeneous networks with single-typed nodes or edges. However, networks in real world are more complex and larger, consisting of multiple types of nodes, edges and even node attributes. Existing algorithms treat these multiplex heterogeneous networks as homogeneous network, ignoring correlations among different node types and edge types even deep semantic information. In light of these issues, we developed a new framework to solve heterogeneous network embedding problems. We mainly focus on Attributed Multiplex Heterogeneous Network but our method can apply to both heterogeneous and homogeneous networks. We also propose an edge-concerned metapath strategy to guide random walk, providing walking guidance among different layers separated by edge type and then leverages a heterogeneous skip-gram model to compute overall node embeddings. We conduct quantitative experiments to evaluate our method on four public dataset: Amazon, Youtube, DBLP and Movielens. As demonstrated by experimental results, our method achieves statistically significant improvements over compared previous methods on link prediction tasks. We also explore the parameter sensitivity of our proposed model to figure out function fluctuation while tuning parameters.","PeriodicalId":386048,"journal":{"name":"2020 IEEE 6th International Conference on Computer and Communications (ICCC)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122497414","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 : 2020-12-11DOI: 10.1109/ICCC51575.2020.9345046
Danying Guo, Xinxin Feng, Haifeng Zheng
Based on the popularity of intelligent embedded devices, mobile crowdsensing emerged as a new paradigm of crowdsourcing perception. However, it often faces the problem of low data quality caused by the insufficient number of participators. In this paper, we propose an incentive mechanism for mobile crowdsensing considering social networks. Our mechanism takes into account the social networks of mobile users, which is not only to reward users for data contribution, but also for solicitation behavior, so as to expand the number of participators under budget constraints, and to select users with high-capability. We prove by the theory that the proposed mechanism satisfies individual rationality, truthfulness, solicitation incentives, and budget effectiveness. Besides, the simulation results show that the mechanism can effectively motivate users' long-term participation and high-quality data collection.
{"title":"Incentive Mechanism Design for Mobile Crowdsensing Considering Social Networks","authors":"Danying Guo, Xinxin Feng, Haifeng Zheng","doi":"10.1109/ICCC51575.2020.9345046","DOIUrl":"https://doi.org/10.1109/ICCC51575.2020.9345046","url":null,"abstract":"Based on the popularity of intelligent embedded devices, mobile crowdsensing emerged as a new paradigm of crowdsourcing perception. However, it often faces the problem of low data quality caused by the insufficient number of participators. In this paper, we propose an incentive mechanism for mobile crowdsensing considering social networks. Our mechanism takes into account the social networks of mobile users, which is not only to reward users for data contribution, but also for solicitation behavior, so as to expand the number of participators under budget constraints, and to select users with high-capability. We prove by the theory that the proposed mechanism satisfies individual rationality, truthfulness, solicitation incentives, and budget effectiveness. Besides, the simulation results show that the mechanism can effectively motivate users' long-term participation and high-quality data collection.","PeriodicalId":386048,"journal":{"name":"2020 IEEE 6th International Conference on Computer and Communications (ICCC)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121907296","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 : 2020-12-11DOI: 10.1109/ICCC51575.2020.9344880
Bohong Xiang, Feng Yan, Yaping Zhu, Tao Wu, Weiwei Xia, Jingming Pang, Wanzhu Liu, Gang Heng, Lianfeng Shen
In recent years, the research of high-precision positioning with wireless sensor networks has attracted a lot of attention, especially in the scenarios of UAV (unmanned aerial vehicles) assisted positioning. This paper proposes a new method of getting more accurate range information. In contrast to existing traditional works, we use multiple range information instead of a single distance information. First, a UAV transmits beacon packets to each sensor node at random positions and all nodes record RSSI (Received Signal Strength Indicator) vectors. We can estimate the distance between nodes by comparing the similarity of RSSI vectors. Second, we estimate the distance between two nodes by means of comparing their CSI (channel state Information) to UAV. Finally, we use Kalman filter to fuse the two-range information. And we can get more accurate range information for positioning. Simulations validate high localization accuracy of the proposed algorithm. Besides, the numbers of beacons transmitted by UAV and the energy consumption can be reduced in the simulation.
近年来，利用无线传感器网络进行高精度定位的研究备受关注，特别是在无人机辅助定位的场景下。本文提出了一种获取更精确距离信息的新方法。与现有的传统作品相比，我们使用了多个距离信息而不是单一的距离信息。首先，无人机向随机位置的每个传感器节点发送信标数据包，所有节点记录RSSI (Received Signal Strength Indicator，接收信号强度指标)向量。我们可以通过比较RSSI向量的相似性来估计节点之间的距离。其次，我们通过将两个节点的信道状态信息CSI (channel state Information)与无人机进行比较来估计节点之间的距离。最后，利用卡尔曼滤波对双量程信息进行融合。并且可以得到更精确的距离信息进行定位。仿真结果表明，该算法具有较高的定位精度。此外，仿真还可以减少无人机发射信标的数量和能耗。
{"title":"UAV Assisted Localization Scheme of WSNs Using RSSI and CSI Information","authors":"Bohong Xiang, Feng Yan, Yaping Zhu, Tao Wu, Weiwei Xia, Jingming Pang, Wanzhu Liu, Gang Heng, Lianfeng Shen","doi":"10.1109/ICCC51575.2020.9344880","DOIUrl":"https://doi.org/10.1109/ICCC51575.2020.9344880","url":null,"abstract":"In recent years, the research of high-precision positioning with wireless sensor networks has attracted a lot of attention, especially in the scenarios of UAV (unmanned aerial vehicles) assisted positioning. This paper proposes a new method of getting more accurate range information. In contrast to existing traditional works, we use multiple range information instead of a single distance information. First, a UAV transmits beacon packets to each sensor node at random positions and all nodes record RSSI (Received Signal Strength Indicator) vectors. We can estimate the distance between nodes by comparing the similarity of RSSI vectors. Second, we estimate the distance between two nodes by means of comparing their CSI (channel state Information) to UAV. Finally, we use Kalman filter to fuse the two-range information. And we can get more accurate range information for positioning. Simulations validate high localization accuracy of the proposed algorithm. Besides, the numbers of beacons transmitted by UAV and the energy consumption can be reduced in the simulation.","PeriodicalId":386048,"journal":{"name":"2020 IEEE 6th International Conference on Computer and Communications (ICCC)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116814594","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 : 2020-12-11DOI: 10.1109/ICCC51575.2020.9345174
Chong Cong, Rongrong Qian, Wenping Ren
We propose a beamforming method based on Support Vector Regression (SVR) for uniform linear arrays (ULAs). In the proposed algorithm, a diagonal value is added to the covariance matrix of the structural risk item, to ensure the matrix invertible. Moreover, the proposed method not only carries out the minimum output energy, but also averts the low robustness caused by the direction of arrival mismatch and the limited number of snapshots. Performance of the proposed algorithm is evaluated by numerical simulations, which is compared with the minimum variance distortionless response (MVDR). It is illustrated that the SVR-based algorithm performs better than MVDR with small samples and high signal-to-noise ratio (SNR) scenarios.
{"title":"Minimum Output Energy Beamforming Based on Support Vector Regression","authors":"Chong Cong, Rongrong Qian, Wenping Ren","doi":"10.1109/ICCC51575.2020.9345174","DOIUrl":"https://doi.org/10.1109/ICCC51575.2020.9345174","url":null,"abstract":"We propose a beamforming method based on Support Vector Regression (SVR) for uniform linear arrays (ULAs). In the proposed algorithm, a diagonal value is added to the covariance matrix of the structural risk item, to ensure the matrix invertible. Moreover, the proposed method not only carries out the minimum output energy, but also averts the low robustness caused by the direction of arrival mismatch and the limited number of snapshots. Performance of the proposed algorithm is evaluated by numerical simulations, which is compared with the minimum variance distortionless response (MVDR). It is illustrated that the SVR-based algorithm performs better than MVDR with small samples and high signal-to-noise ratio (SNR) scenarios.","PeriodicalId":386048,"journal":{"name":"2020 IEEE 6th International Conference on Computer and Communications (ICCC)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128225599","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：