Pub Date : 2020-06-01DOI: 10.1109/ICAICA50127.2020.9182670
Ying Xu, Baihan Zou
In order to more fully evaluate the anti-destructive performance of the dependent network under different attacks, three one-to-one, one-to-many, and many-to-many edge-connection methods, as well as three types of degree homology, degree heterogeneity and randomness Coupling way to construct different network models. Under four different attack methods, the natural connectivity is used as a measure of the indestructibility of the dependent network, and the dependent network models of different connected edges are compared to each other based on the intentional attack of the degree and the median when they face different attack strategies. The anti-destructive effect is greater, and the dependent network has the best anti-destructive performance when the number of attack nodes is small. In addition, by changing the coupling strength between the sub-networks, it is found that the anti-destructiveness of the dependent network also increases as the coupling strength increases. Based on natural connectivity, the concept of node dispersion was proposed to evaluate the comprehensive survivability of dependent networks, and it was found that the dependent network was the most robust when one-to-many homogeneous coupling was used.
{"title":"Survivability Analysis and Optimization of Dependent Networks Based on Natural Connectivity","authors":"Ying Xu, Baihan Zou","doi":"10.1109/ICAICA50127.2020.9182670","DOIUrl":"https://doi.org/10.1109/ICAICA50127.2020.9182670","url":null,"abstract":"In order to more fully evaluate the anti-destructive performance of the dependent network under different attacks, three one-to-one, one-to-many, and many-to-many edge-connection methods, as well as three types of degree homology, degree heterogeneity and randomness Coupling way to construct different network models. Under four different attack methods, the natural connectivity is used as a measure of the indestructibility of the dependent network, and the dependent network models of different connected edges are compared to each other based on the intentional attack of the degree and the median when they face different attack strategies. The anti-destructive effect is greater, and the dependent network has the best anti-destructive performance when the number of attack nodes is small. In addition, by changing the coupling strength between the sub-networks, it is found that the anti-destructiveness of the dependent network also increases as the coupling strength increases. Based on natural connectivity, the concept of node dispersion was proposed to evaluate the comprehensive survivability of dependent networks, and it was found that the dependent network was the most robust when one-to-many homogeneous coupling was used.","PeriodicalId":113564,"journal":{"name":"2020 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115234885","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-01DOI: 10.1109/ICAICA50127.2020.9182522
J. Gong, Yong Mei, Yong Zhou
Target tracking is one of the most concerned computer problems, but it is also challenging with few training samples, fast moving objects and some other issues. The kernelized correlation filter (KCF) algorithm proposed by the team of Joao F. Henriques had applied to address this problem for tracking successfully. The method has expanded the number of negative samples to enhance the performance of the tracker and used the fast Fourier transform to accelerate the calculation of the algorithm. However, the features used by the KCF have limited ability to express the target with complex background. We propose improved KCF algorithm for tracking. The pre-trained deep convolutional neural network (CNN) is introduced in extracting the layer information respectively to describe the spatial and semantic features of the target. Experiments are performed on OTB-2015 benchmark datasets, and the results show that in comparison with the existing tracking algorithms, the proposed improved algorithm can deal with the challenges much better performance compared to original KCF and KCF-S method.
目标跟踪是最受关注的计算机问题之一，但由于训练样本少、目标移动快等问题，目标跟踪也具有挑战性。Joao F. Henriques团队提出的核化相关滤波器(KCF)算法成功地解决了这一问题。该方法扩大了负样本的数量，提高了跟踪器的性能，并利用快速傅立叶变换加快了算法的计算速度。然而，KCF所使用的特征对复杂背景下目标的表达能力有限。我们提出了改进的KCF算法用于跟踪。引入预训练深度卷积神经网络(CNN)分别提取层信息来描述目标的空间特征和语义特征。在OTB-2015基准数据集上进行了实验，结果表明，与现有的跟踪算法相比，改进后的算法能够更好地应对挑战，性能优于原始的KCF和KCF- s方法。
{"title":"Research on an Improved KCF Target Tracking Algorithm Based on CNN Feature Extraction","authors":"J. Gong, Yong Mei, Yong Zhou","doi":"10.1109/ICAICA50127.2020.9182522","DOIUrl":"https://doi.org/10.1109/ICAICA50127.2020.9182522","url":null,"abstract":"Target tracking is one of the most concerned computer problems, but it is also challenging with few training samples, fast moving objects and some other issues. The kernelized correlation filter (KCF) algorithm proposed by the team of Joao F. Henriques had applied to address this problem for tracking successfully. The method has expanded the number of negative samples to enhance the performance of the tracker and used the fast Fourier transform to accelerate the calculation of the algorithm. However, the features used by the KCF have limited ability to express the target with complex background. We propose improved KCF algorithm for tracking. The pre-trained deep convolutional neural network (CNN) is introduced in extracting the layer information respectively to describe the spatial and semantic features of the target. Experiments are performed on OTB-2015 benchmark datasets, and the results show that in comparison with the existing tracking algorithms, the proposed improved algorithm can deal with the challenges much better performance compared to original KCF and KCF-S method.","PeriodicalId":113564,"journal":{"name":"2020 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA)","volume":"243 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123437230","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-01DOI: 10.1109/ICAICA50127.2020.9182622
Ming Tan, X. Zhong, Liang Xie, Bo Ma, Wenxuan Liu, Hongxia Xia
Deep Affinity Network (DAN) is a novel approach in multi-object tracking (MOT) designed to jointly modeling object appearances and affinities end to end. But tracking accuracy of DAN tracker is greatly limited since it neglects unreliable detection. Exploiting predictions of tracks has emerged as a popular approach to tackle the task of tracking-by-detection. However, it's observed that missing detection has not been solved well enough which would significantly influence tracking accuracy. Thus, obtaining more reliable tracking candidates is concerned to further address the problem of missing detection. In this paper, we propose Candidate Selection-based Deep Affinity Network (CSDAN) tracker for MOT. It collects candidates from detection, predictions of tracks and backward tracking simultaneously so that they can complement each other in different scenarios. Moreover, we propose a deep learned candidate selection model (DCSM) with a unified scoring function suitable for CSDAN, which can well handle candidates from three sources separately and select those for data association. Experiments conducted on MOT17 benchmark demonstrate that our extensions can significantly address the unreliable detection problem in DAN tracker, and our CSDAN tracker demonstrates competitive tracking performance.
{"title":"Candidate Selection-based Deep Affinity Network for Multi-object Tracking","authors":"Ming Tan, X. Zhong, Liang Xie, Bo Ma, Wenxuan Liu, Hongxia Xia","doi":"10.1109/ICAICA50127.2020.9182622","DOIUrl":"https://doi.org/10.1109/ICAICA50127.2020.9182622","url":null,"abstract":"Deep Affinity Network (DAN) is a novel approach in multi-object tracking (MOT) designed to jointly modeling object appearances and affinities end to end. But tracking accuracy of DAN tracker is greatly limited since it neglects unreliable detection. Exploiting predictions of tracks has emerged as a popular approach to tackle the task of tracking-by-detection. However, it's observed that missing detection has not been solved well enough which would significantly influence tracking accuracy. Thus, obtaining more reliable tracking candidates is concerned to further address the problem of missing detection. In this paper, we propose Candidate Selection-based Deep Affinity Network (CSDAN) tracker for MOT. It collects candidates from detection, predictions of tracks and backward tracking simultaneously so that they can complement each other in different scenarios. Moreover, we propose a deep learned candidate selection model (DCSM) with a unified scoring function suitable for CSDAN, which can well handle candidates from three sources separately and select those for data association. Experiments conducted on MOT17 benchmark demonstrate that our extensions can significantly address the unreliable detection problem in DAN tracker, and our CSDAN tracker demonstrates competitive tracking performance.","PeriodicalId":113564,"journal":{"name":"2020 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123479190","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-01DOI: 10.1109/ICAICA50127.2020.9182601
Chungui Deng, Xiaonan Luo, Y. Zhong
In order to solve the problems of the inaccuracy of RGB-D SLAM closed-loop and the map sparse outliers, this paper proposes an improved algorithm of Closed-loop Detection and Octomap mapping. In the improved algorithm, the curvature of the robot's motion trajectory is combined with the cyclic closure detection algorithm to eliminate the difficulties of the front-end cumulative error to the back-end Closed-loop Detection; in the aspect of map sparse outliers, in order to make the map more compact and easy to adjust, the two side confidence interval of Gaussian distribution is combined with statistical filtering to give the initial statistical value. We have done a series of experiments in the open TUM RGB-D data set. The memory and outliers of point cloud map are reduced by 11.4%, 11.3% respectively, and the memory and outliers of Octomap are reduced by 26.7%, 27.3% respectively, and the validity of accurate closed-loop is verified.
{"title":"Improved closed-loop detection and Octomap algorithm based on RGB-D SLAM","authors":"Chungui Deng, Xiaonan Luo, Y. Zhong","doi":"10.1109/ICAICA50127.2020.9182601","DOIUrl":"https://doi.org/10.1109/ICAICA50127.2020.9182601","url":null,"abstract":"In order to solve the problems of the inaccuracy of RGB-D SLAM closed-loop and the map sparse outliers, this paper proposes an improved algorithm of Closed-loop Detection and Octomap mapping. In the improved algorithm, the curvature of the robot's motion trajectory is combined with the cyclic closure detection algorithm to eliminate the difficulties of the front-end cumulative error to the back-end Closed-loop Detection; in the aspect of map sparse outliers, in order to make the map more compact and easy to adjust, the two side confidence interval of Gaussian distribution is combined with statistical filtering to give the initial statistical value. We have done a series of experiments in the open TUM RGB-D data set. The memory and outliers of point cloud map are reduced by 11.4%, 11.3% respectively, and the memory and outliers of Octomap are reduced by 26.7%, 27.3% respectively, and the validity of accurate closed-loop is verified.","PeriodicalId":113564,"journal":{"name":"2020 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124030569","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-01DOI: 10.1109/ICAICA50127.2020.9182417
Yanyan Zhu, Xiao Chen
With the continuous development of mobile communication technology, people pursue faster, more convenient and cheaper communication methods. Visible light communication is a kind of wireless communication method, which has wide application prospect in broadening spectrum resources. The transmitting and receiving circuits for visible light communication are designed. White LED is the light source of the transmitting circuit. The signal is amplified and coupled to the LED, and the constant current source is used to drive the LED to realize illumination and signal transmission. Point-to-point communication is adopted in space to reduce inter-symbol interference. The receiving circuit receives the optical signal and converts it into electrical signal through PIN photodiode. After amplification and filtering, the original signal is restored. The transmission of visible light communication is realized. The design circuit is simple in structure and low in manufacturing cost. It provides reference for the research of visible light communication.
{"title":"Visible Light Communication System Based on White LED","authors":"Yanyan Zhu, Xiao Chen","doi":"10.1109/ICAICA50127.2020.9182417","DOIUrl":"https://doi.org/10.1109/ICAICA50127.2020.9182417","url":null,"abstract":"With the continuous development of mobile communication technology, people pursue faster, more convenient and cheaper communication methods. Visible light communication is a kind of wireless communication method, which has wide application prospect in broadening spectrum resources. The transmitting and receiving circuits for visible light communication are designed. White LED is the light source of the transmitting circuit. The signal is amplified and coupled to the LED, and the constant current source is used to drive the LED to realize illumination and signal transmission. Point-to-point communication is adopted in space to reduce inter-symbol interference. The receiving circuit receives the optical signal and converts it into electrical signal through PIN photodiode. After amplification and filtering, the original signal is restored. The transmission of visible light communication is realized. The design circuit is simple in structure and low in manufacturing cost. It provides reference for the research of visible light communication.","PeriodicalId":113564,"journal":{"name":"2020 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125869896","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-01DOI: 10.1109/ICAICA50127.2020.9182645
Zhengwu Wang, Wansuo Liu
It was important for the ground crew to forecast the rate of the aircraft grounded due to maintenance. Using the neural network to forecast the index, it depended on the network structure, the algorithm, the training samples quantity and representation ability. The paper ameliorated the network configuration and arithmetic, It constructed the modified network to forecast the value and used the ameliorated method to enlarge its ability during the forecast process. The results showed the method could solve the generalization capability and the sample problems, the forecast results was meaningful.
{"title":"Rate Forecast about Aircraft Grounded due to Maintenance with Modified Neural Network","authors":"Zhengwu Wang, Wansuo Liu","doi":"10.1109/ICAICA50127.2020.9182645","DOIUrl":"https://doi.org/10.1109/ICAICA50127.2020.9182645","url":null,"abstract":"It was important for the ground crew to forecast the rate of the aircraft grounded due to maintenance. Using the neural network to forecast the index, it depended on the network structure, the algorithm, the training samples quantity and representation ability. The paper ameliorated the network configuration and arithmetic, It constructed the modified network to forecast the value and used the ameliorated method to enlarge its ability during the forecast process. The results showed the method could solve the generalization capability and the sample problems, the forecast results was meaningful.","PeriodicalId":113564,"journal":{"name":"2020 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126016110","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-01DOI: 10.1109/ICAICA50127.2020.9182521
Han Wei-yue, L. Xiaohong
Object detection has made impressive progress in recent years where Faster R-CNN is the mainstream framework for region-based object detection methods. However, a single Faster R-CNN framework no longer has advantages compared with the latest detection models. So based on Faster R-CNN, a model that focuses on features, normalization methods, and anchor sizes is proposed to improve detection results. The model integrates Feature Pyramid Networks (FPN), Group Normalization (GN) with k-means clustering. FPN is used to produce a multi-scale feature representation, which enables the model to detect objects across a wide range of scales. GN addresses the problem of the small training batch size effectively. K-means clustering algorithm is used finally to determine anchor sizes of the network on the purpose of making the network do bounding-box regression more easily. Without bells and whistles, the detection model achieves state-of-the-art object detection accuracy on the MSCOCO datasets.
{"title":"Clustering Anchor for Faster R-CNN to Improve Detection Results","authors":"Han Wei-yue, L. Xiaohong","doi":"10.1109/ICAICA50127.2020.9182521","DOIUrl":"https://doi.org/10.1109/ICAICA50127.2020.9182521","url":null,"abstract":"Object detection has made impressive progress in recent years where Faster R-CNN is the mainstream framework for region-based object detection methods. However, a single Faster R-CNN framework no longer has advantages compared with the latest detection models. So based on Faster R-CNN, a model that focuses on features, normalization methods, and anchor sizes is proposed to improve detection results. The model integrates Feature Pyramid Networks (FPN), Group Normalization (GN) with k-means clustering. FPN is used to produce a multi-scale feature representation, which enables the model to detect objects across a wide range of scales. GN addresses the problem of the small training batch size effectively. K-means clustering algorithm is used finally to determine anchor sizes of the network on the purpose of making the network do bounding-box regression more easily. Without bells and whistles, the detection model achieves state-of-the-art object detection accuracy on the MSCOCO datasets.","PeriodicalId":113564,"journal":{"name":"2020 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126177048","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-01DOI: 10.1109/ICAICA50127.2020.9182369
Junfeng Mei, Ying Chen, Taoli Ye, Chenglong Huang, H. Ye
Along with the age of the Internet the rapid development of diversified business model and market segments, facing high customer cost and the double challenges of high turnover rate, a third-party service access to statistical data insecurity, buried point higher cost problems, be badly in need of precise positioning for guest channels, fine operation, and through the study of the statistics, analysis of these data, we may discover the laws of users to use the product, and the law and website marketing strategy, product features, operation strategy, the combination of optimization of user experience, to achieve more accurate operation and marketing, make products better growth. Based on the buried point and the mobile network environment detection tool based on the client SDK technology, this paper will provide the visual statistical effect through the analysis of the user behavior module, with simple operation and accurate data. Based on Eclipse, Hadoop, Spark and other technologies, the user behavior analysis platform is established to meet users' needs for data security and accuracy.
{"title":"Research on User Behavior Analysis Model of Financial Industry in Big Data Environment","authors":"Junfeng Mei, Ying Chen, Taoli Ye, Chenglong Huang, H. Ye","doi":"10.1109/ICAICA50127.2020.9182369","DOIUrl":"https://doi.org/10.1109/ICAICA50127.2020.9182369","url":null,"abstract":"Along with the age of the Internet the rapid development of diversified business model and market segments, facing high customer cost and the double challenges of high turnover rate, a third-party service access to statistical data insecurity, buried point higher cost problems, be badly in need of precise positioning for guest channels, fine operation, and through the study of the statistics, analysis of these data, we may discover the laws of users to use the product, and the law and website marketing strategy, product features, operation strategy, the combination of optimization of user experience, to achieve more accurate operation and marketing, make products better growth. Based on the buried point and the mobile network environment detection tool based on the client SDK technology, this paper will provide the visual statistical effect through the analysis of the user behavior module, with simple operation and accurate data. Based on Eclipse, Hadoop, Spark and other technologies, the user behavior analysis platform is established to meet users' needs for data security and accuracy.","PeriodicalId":113564,"journal":{"name":"2020 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA)","volume":"330 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124651787","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-01DOI: 10.1109/ICAICA50127.2020.9182508
Li Li
With the rapid development of new generation information technologies such as cloud computing, Internet of Things and big data, the fourth generation data center based on cloud computing is also growing rapidly. Cloud computing provides users with a flexible, reliable, ultra-large and scalable pool of computing resources. In the cloud computing environment, the Internet transfers information and data to direct transfer services. Since the emergence of cloud computing, through the continuous development of science and technology. Data center is an architecture that integrates network communication, storage and high performance computing. It can provide users with a variety of storage, computing and network services. How to deal with massive data and services, to facilitate users to complete all kinds of business more quickly and with higher experience, has become a major problem in the era of Internet development. This paper designs the cloud computing architecture of the Internet of things data center, hoping to propose a new scheduling mechanism for the intelligent management of the data center.
{"title":"Cloud Computing Data Center Structure Based on Internet of Things and Its Scheduling Mechanism","authors":"Li Li","doi":"10.1109/ICAICA50127.2020.9182508","DOIUrl":"https://doi.org/10.1109/ICAICA50127.2020.9182508","url":null,"abstract":"With the rapid development of new generation information technologies such as cloud computing, Internet of Things and big data, the fourth generation data center based on cloud computing is also growing rapidly. Cloud computing provides users with a flexible, reliable, ultra-large and scalable pool of computing resources. In the cloud computing environment, the Internet transfers information and data to direct transfer services. Since the emergence of cloud computing, through the continuous development of science and technology. Data center is an architecture that integrates network communication, storage and high performance computing. It can provide users with a variety of storage, computing and network services. How to deal with massive data and services, to facilitate users to complete all kinds of business more quickly and with higher experience, has become a major problem in the era of Internet development. This paper designs the cloud computing architecture of the Internet of things data center, hoping to propose a new scheduling mechanism for the intelligent management of the data center.","PeriodicalId":113564,"journal":{"name":"2020 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129367237","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-01DOI: 10.1109/ICAICA50127.2020.9182646
Zhengdong Li
In this paper, we discuss an unmanned aerial vehicle enabled Amplify-and-Forward Relaying System, where a fixed-wing UAV flies is used as mobile relay, and circular trajectories are set. The system employs a fixed-wing UAV to ferry data from source node to destination node with limited energy consumption. We also choose the amplify-and-forward (AF) as the method of cooperative communication. By adjusting the orbital radius to minimize the propulsion energy consumption of UAV while contenting the communication throughput requirement. To save this, we transform the problem into a discretized equivalent, and discuss its optimal solution depends on whether the problem is convex. By using the algorithm and analyzing the function monotonicity and extremum to get the conclusion. Numerical results show that the precise orbital radius could significantly improve communication performance. And the proposed cache-enabled AF strategy model can provide more communication throughput in the same case, compared to the no cache-enabled AF strategy.
{"title":"Trajectory Optimization for UAV-Enabled Amplify-and-Forward Relaying System Based on Communication Performance","authors":"Zhengdong Li","doi":"10.1109/ICAICA50127.2020.9182646","DOIUrl":"https://doi.org/10.1109/ICAICA50127.2020.9182646","url":null,"abstract":"In this paper, we discuss an unmanned aerial vehicle enabled Amplify-and-Forward Relaying System, where a fixed-wing UAV flies is used as mobile relay, and circular trajectories are set. The system employs a fixed-wing UAV to ferry data from source node to destination node with limited energy consumption. We also choose the amplify-and-forward (AF) as the method of cooperative communication. By adjusting the orbital radius to minimize the propulsion energy consumption of UAV while contenting the communication throughput requirement. To save this, we transform the problem into a discretized equivalent, and discuss its optimal solution depends on whether the problem is convex. By using the algorithm and analyzing the function monotonicity and extremum to get the conclusion. Numerical results show that the precise orbital radius could significantly improve communication performance. And the proposed cache-enabled AF strategy model can provide more communication throughput in the same case, compared to the no cache-enabled AF strategy.","PeriodicalId":113564,"journal":{"name":"2020 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130582018","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：