Pub Date : 2021-06-01DOI: 10.1109/ICCWorkshops50388.2021.9473482
J. Mao, Arman Farhang, Lei Zhang, Zheng Chu, P. Xiao, Sai Gu
Multi-numerology multi-carrier (MN-MC) techniques are considered as essential enablers for RAN slicing in fifth-generation (5G) communication systems and beyond. However, utilization of mixed numerologies breaks the orthogonality principle defined for single-numerology orthogonal frequency division multiplexing (SN-OFDM) systems with a unified subcarrier spacing. This leads to interference between different numerologies, i.e., inter-numerology interference (INI). This paper develops metrics to quantify the level of the INI using a continuous-time approach. The derived analytical expressions of INI in terms of mean square error (MSE) and error vector magnitude (EVM) directly reveal the main contributing factors to INI, which can not be shown explicitly in a matrix form INI based on discrete-time calculations. Moreover, the study of power offset between different numerologies shows a significant impact on INI, especially for high order modulation schemes. The finding in this paper provides analytical guidance in designing multi-numerology (MN) systems, for instance, developing resource allocation schemes and interference mitigation techniques.
{"title":"Interference Analysis in Multi-Numerology OFDM Systems: A Continuous-Time Approach","authors":"J. Mao, Arman Farhang, Lei Zhang, Zheng Chu, P. Xiao, Sai Gu","doi":"10.1109/ICCWorkshops50388.2021.9473482","DOIUrl":"https://doi.org/10.1109/ICCWorkshops50388.2021.9473482","url":null,"abstract":"Multi-numerology multi-carrier (MN-MC) techniques are considered as essential enablers for RAN slicing in fifth-generation (5G) communication systems and beyond. However, utilization of mixed numerologies breaks the orthogonality principle defined for single-numerology orthogonal frequency division multiplexing (SN-OFDM) systems with a unified subcarrier spacing. This leads to interference between different numerologies, i.e., inter-numerology interference (INI). This paper develops metrics to quantify the level of the INI using a continuous-time approach. The derived analytical expressions of INI in terms of mean square error (MSE) and error vector magnitude (EVM) directly reveal the main contributing factors to INI, which can not be shown explicitly in a matrix form INI based on discrete-time calculations. Moreover, the study of power offset between different numerologies shows a significant impact on INI, especially for high order modulation schemes. The finding in this paper provides analytical guidance in designing multi-numerology (MN) systems, for instance, developing resource allocation schemes and interference mitigation techniques.","PeriodicalId":127186,"journal":{"name":"2021 IEEE International Conference on Communications Workshops (ICC Workshops)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132585282","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 : 2021-06-01DOI: 10.1109/ICCWorkshops50388.2021.9473522
Kohei Kato, Katsuya Suto, Koya Sato
A remote driving system (RDS) via wireless net- works is a promising solution to guarantee the safety of autonomous vehicles. In the system, a remote operator controls vehicles while watching video frames transmitted from the controlled vehicles. The conventional video streaming method decides the video resolution using the statistical quality of services (QoS) to guarantee the delay constraints; however, it may yield a long delay in best-effort wireless networks if the quality of the wireless channel suddenly changes. To cope with the issue, we propose a deterministic networking approach. A base station (BS) predicts a future QoS using a radio map and driving route of vehicles to decides the adequate video resolution that satisfies the delay constraints of RDS. BS also has a super-resolution (SR) function to enhance the quality of experience (QoE) in video streaming. Thanks to the proposed QoS prediction and video frame resolution decision, BS can use the adequate SR model for each video frame, further enhancing QoE. Using the measurement datasets of radio access networks, we confirm that the proposed RDS can provide high-quality video streaming while satisfying the delay constraints in any time-series wireless channel situations.
{"title":"Deterministic Video Streaming with Deep Learning Enabled Base Station Intervention for Stable Remote Driving System","authors":"Kohei Kato, Katsuya Suto, Koya Sato","doi":"10.1109/ICCWorkshops50388.2021.9473522","DOIUrl":"https://doi.org/10.1109/ICCWorkshops50388.2021.9473522","url":null,"abstract":"A remote driving system (RDS) via wireless net- works is a promising solution to guarantee the safety of autonomous vehicles. In the system, a remote operator controls vehicles while watching video frames transmitted from the controlled vehicles. The conventional video streaming method decides the video resolution using the statistical quality of services (QoS) to guarantee the delay constraints; however, it may yield a long delay in best-effort wireless networks if the quality of the wireless channel suddenly changes. To cope with the issue, we propose a deterministic networking approach. A base station (BS) predicts a future QoS using a radio map and driving route of vehicles to decides the adequate video resolution that satisfies the delay constraints of RDS. BS also has a super-resolution (SR) function to enhance the quality of experience (QoE) in video streaming. Thanks to the proposed QoS prediction and video frame resolution decision, BS can use the adequate SR model for each video frame, further enhancing QoE. Using the measurement datasets of radio access networks, we confirm that the proposed RDS can provide high-quality video streaming while satisfying the delay constraints in any time-series wireless channel situations.","PeriodicalId":127186,"journal":{"name":"2021 IEEE International Conference on Communications Workshops (ICC Workshops)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132822537","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 : 2021-06-01DOI: 10.1109/ICCWorkshops50388.2021.9473576
M. Cox, Abderrahmen Trichili, B. Ooi, Mohamed-Slim Alouini
The effect of atmospheric turbulence on Orbital Angular Momentum (OAM) modes, which are a subset of the Laguerre-Gaussian (LG) modes, has been thoroughly studied. Other high-order basis sets such as Hermite-Gaussian (HG, which have a rectangular shape) and Ince-Gaussian modes (which have an elliptical shape) have received relatively little attention. In this work, comparative experimental measurements of low order OAM, Ince-, and Hermite-Gaussian modes in turbulence are presented. It is found that the performance of the mode sets vary dramatically in the same turbulence. Surprisingly, Ince-Gaussian modes experience lower crosstalk and mode dependent loss than LG and HG modes of similar order. This warrants further investigation: could there be an optimal basis set for optical communications in turbulence?
{"title":"Higher-Order Spatial Modes in Turbulence: Alternatives to Orbital Angular Momentum","authors":"M. Cox, Abderrahmen Trichili, B. Ooi, Mohamed-Slim Alouini","doi":"10.1109/ICCWorkshops50388.2021.9473576","DOIUrl":"https://doi.org/10.1109/ICCWorkshops50388.2021.9473576","url":null,"abstract":"The effect of atmospheric turbulence on Orbital Angular Momentum (OAM) modes, which are a subset of the Laguerre-Gaussian (LG) modes, has been thoroughly studied. Other high-order basis sets such as Hermite-Gaussian (HG, which have a rectangular shape) and Ince-Gaussian modes (which have an elliptical shape) have received relatively little attention. In this work, comparative experimental measurements of low order OAM, Ince-, and Hermite-Gaussian modes in turbulence are presented. It is found that the performance of the mode sets vary dramatically in the same turbulence. Surprisingly, Ince-Gaussian modes experience lower crosstalk and mode dependent loss than LG and HG modes of similar order. This warrants further investigation: could there be an optimal basis set for optical communications in turbulence?","PeriodicalId":127186,"journal":{"name":"2021 IEEE International Conference on Communications Workshops (ICC Workshops)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133752577","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 : 2021-06-01DOI: 10.1109/ICCWorkshops50388.2021.9473738
Hua Wu, Lu Wang, Guang Cheng, Xiaoyan Hu
Traffic classification can detect the source of traffic and can be used for network management and network security. Methods based on manually extracting features and using machine learning have become mainstream. These methods have poor results in classifying applications that use standard web services, which can cause ambiguities in application classification. In this paper, we propose the TLS Flow Sequence Network (TFSN), which can automatically learn representative features from the original TLS flow sequence and complete the classification. In addition, we also used the attention mechanism to reinforce the learned features. Compared with other similar researches, we can further identify the web services corresponding to encrypted flows in detail, and are no longer limited to application classification. We conducted experiments on the real network traffic dataset of 11 types of Google applications and 9 types of Apple applications that contain the same standard web services. It shows that TFSN has excellent performance, and the accuracy of web service recognition is more than 98%.
{"title":"Mobile Application Encryption Traffic Classification Based On TLS Flow Sequence Network","authors":"Hua Wu, Lu Wang, Guang Cheng, Xiaoyan Hu","doi":"10.1109/ICCWorkshops50388.2021.9473738","DOIUrl":"https://doi.org/10.1109/ICCWorkshops50388.2021.9473738","url":null,"abstract":"Traffic classification can detect the source of traffic and can be used for network management and network security. Methods based on manually extracting features and using machine learning have become mainstream. These methods have poor results in classifying applications that use standard web services, which can cause ambiguities in application classification. In this paper, we propose the TLS Flow Sequence Network (TFSN), which can automatically learn representative features from the original TLS flow sequence and complete the classification. In addition, we also used the attention mechanism to reinforce the learned features. Compared with other similar researches, we can further identify the web services corresponding to encrypted flows in detail, and are no longer limited to application classification. We conducted experiments on the real network traffic dataset of 11 types of Google applications and 9 types of Apple applications that contain the same standard web services. It shows that TFSN has excellent performance, and the accuracy of web service recognition is more than 98%.","PeriodicalId":127186,"journal":{"name":"2021 IEEE International Conference on Communications Workshops (ICC Workshops)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134513394","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}
Rate splitting multiple access (RSMA) is promising to achieve high spectral efficiency with a higher flexibility relative to non-orthogonal multiple access (NOMA) and orthogonal multiple access (OMA). In this paper, a novel RSMA-based secure transmission scheme with artificial noise (AN) and an adaptive beamforming is developed with the aim of maximizing the secrecy sum rate (SSR) of the considered system subject to specific constraints. The joint optimization of the power allocation between useful messages and AN signals, rate splitting between the two legitimate receivers, and the two mastering parameters of the beamforming design is tackled. To solve such a non-convex problem, we first analytically reveal some properties of the solution and then focus on an asymptotic scenario with a sufficiently large number of transmit antennas to derive closed-form expressions for the optimal power allocation coefficients. This enables us to develop an efficient method to identify the optimal rate splitting and beamforming parameters. Our examinations demonstrate that the proposed RSMA-based scheme outperforms two benchmark schemes in terms of achieving a higher SSR and the achievable performance gain is exceptional when the number of transmit antennas is small.
{"title":"Resource Allocation for Secure Rate-Splitting Multiple Access with Adaptive Beamforming","authors":"Tenghao Cai, Jia Zhang, Shihao Yan, Lili Meng, Jiande Sun, N. Al-Dhahir","doi":"10.1109/ICCWorkshops50388.2021.9473880","DOIUrl":"https://doi.org/10.1109/ICCWorkshops50388.2021.9473880","url":null,"abstract":"Rate splitting multiple access (RSMA) is promising to achieve high spectral efficiency with a higher flexibility relative to non-orthogonal multiple access (NOMA) and orthogonal multiple access (OMA). In this paper, a novel RSMA-based secure transmission scheme with artificial noise (AN) and an adaptive beamforming is developed with the aim of maximizing the secrecy sum rate (SSR) of the considered system subject to specific constraints. The joint optimization of the power allocation between useful messages and AN signals, rate splitting between the two legitimate receivers, and the two mastering parameters of the beamforming design is tackled. To solve such a non-convex problem, we first analytically reveal some properties of the solution and then focus on an asymptotic scenario with a sufficiently large number of transmit antennas to derive closed-form expressions for the optimal power allocation coefficients. This enables us to develop an efficient method to identify the optimal rate splitting and beamforming parameters. Our examinations demonstrate that the proposed RSMA-based scheme outperforms two benchmark schemes in terms of achieving a higher SSR and the achievable performance gain is exceptional when the number of transmit antennas is small.","PeriodicalId":127186,"journal":{"name":"2021 IEEE International Conference on Communications Workshops (ICC Workshops)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115557180","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 : 2021-06-01DOI: 10.1109/ICCWorkshops50388.2021.9473554
Fahime Khoramnejad, Roghayeh Joda, M. Erol-Kantarci
Multi-Access Edge Computing (MEC) along with "learning at the edge" brings unique opportunities for enhancing the utilization of resources in the next generation wireless networks. Using Network Function Virtualization (NFV), Service Function Chains (SFCs), a set of ordered virtual network functions (VNFs), can be deployed within the MEC infrastructure. The user equipment (UEs) can offload VNFs with intense computational load to the MEC servers with rich storage and computation resources. In this paper, we address the problem of partial offloading of a chain of services where each VNF of the SFC request can be either performed locally or offloaded onto a MEC server. The objective is to concurrently minimize the long-term cost of the UEs which is given in terms of both delay and energy consumption. This problem is highly complex and calls for distributed multi-agent learning techniques. We formulate the problem as a distributed multi-agent reinforcement learning problem and use double deep Q-network (DDQN) algorithm to solve it. Our simulation results show that the proposed DDQN-based solution has comparable results to an exhaustive search algorithm.
多接入边缘计算(MEC)以及“边缘学习”为提高下一代无线网络的资源利用率带来了独特的机会。通过网络功能虚拟化(Network Function Virtualization, NFV)，业务功能链(Service Function Chains, sfc)是一组有序的虚拟网络功能(virtual Network functions, VNFs)，可以部署在MEC基础设施中。用户设备(ue)可以将计算负荷较大的VNFs卸载到具有丰富存储和计算资源的MEC服务器上。在本文中，我们解决了服务链的部分卸载问题，其中每个SFC请求的VNF可以在本地执行，也可以卸载到MEC服务器上。目标是同时最小化终端的长期成本，这是根据延迟和能源消耗给出的。该问题非常复杂，需要采用分布式多智能体学习技术。我们将该问题表述为分布式多智能体强化学习问题，并使用双深度q -网络(DDQN)算法来解决该问题。仿真结果表明，所提出的基于ddqn的解决方案与穷举搜索算法具有相当的结果。
{"title":"Distributed Multi-Agent Learning for Service Function Chain Partial Offloading at the Edge","authors":"Fahime Khoramnejad, Roghayeh Joda, M. Erol-Kantarci","doi":"10.1109/ICCWorkshops50388.2021.9473554","DOIUrl":"https://doi.org/10.1109/ICCWorkshops50388.2021.9473554","url":null,"abstract":"Multi-Access Edge Computing (MEC) along with \"learning at the edge\" brings unique opportunities for enhancing the utilization of resources in the next generation wireless networks. Using Network Function Virtualization (NFV), Service Function Chains (SFCs), a set of ordered virtual network functions (VNFs), can be deployed within the MEC infrastructure. The user equipment (UEs) can offload VNFs with intense computational load to the MEC servers with rich storage and computation resources. In this paper, we address the problem of partial offloading of a chain of services where each VNF of the SFC request can be either performed locally or offloaded onto a MEC server. The objective is to concurrently minimize the long-term cost of the UEs which is given in terms of both delay and energy consumption. This problem is highly complex and calls for distributed multi-agent learning techniques. We formulate the problem as a distributed multi-agent reinforcement learning problem and use double deep Q-network (DDQN) algorithm to solve it. Our simulation results show that the proposed DDQN-based solution has comparable results to an exhaustive search algorithm.","PeriodicalId":127186,"journal":{"name":"2021 IEEE International Conference on Communications Workshops (ICC Workshops)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114304705","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 : 2021-06-01DOI: 10.1109/ICCWorkshops50388.2021.9473509
Jiayi Cong, Bin Li, Xianzhen Guo, Ruonan Zhang
In this paper, we consider a general UAV-enabled wireless communication system where a solar-powered UAV is deployed to provide continuous communication services for the ground users (GUs). To get better aerodynamic effect and longer maintaining-flight time, the fixed-wing UAV with thin-film solar cells is adopted for the ground coverage. We first divide the energy component of solar-powered UAV as the aerodynamic energy consumption, communication energy consumption and solar energy harvesting from solar cells. Then, we provide the communication capacity of the GUs in our UAV communication system. In order to obtain better throughput capacity under the precondition of continuous flight, we maximize the capacity by jointly optimizing all of the energy components of UAV and three-dimensional (3-D) flight trajectory. To solve the optimization problem, we employ deep Q-Network (DQN) to simplify the decision-making processes and improve the computational efficiency. Furthermore, we compared different retained energy and intensity variations to explore the performance of communications system. The numerical results show that the DQN algorithm can receive great reward in both maintaining-flight time and the capacity.
{"title":"Energy Management Strategy based on Deep Q-network in the Solar-powered UAV Communications System","authors":"Jiayi Cong, Bin Li, Xianzhen Guo, Ruonan Zhang","doi":"10.1109/ICCWorkshops50388.2021.9473509","DOIUrl":"https://doi.org/10.1109/ICCWorkshops50388.2021.9473509","url":null,"abstract":"In this paper, we consider a general UAV-enabled wireless communication system where a solar-powered UAV is deployed to provide continuous communication services for the ground users (GUs). To get better aerodynamic effect and longer maintaining-flight time, the fixed-wing UAV with thin-film solar cells is adopted for the ground coverage. We first divide the energy component of solar-powered UAV as the aerodynamic energy consumption, communication energy consumption and solar energy harvesting from solar cells. Then, we provide the communication capacity of the GUs in our UAV communication system. In order to obtain better throughput capacity under the precondition of continuous flight, we maximize the capacity by jointly optimizing all of the energy components of UAV and three-dimensional (3-D) flight trajectory. To solve the optimization problem, we employ deep Q-Network (DQN) to simplify the decision-making processes and improve the computational efficiency. Furthermore, we compared different retained energy and intensity variations to explore the performance of communications system. The numerical results show that the DQN algorithm can receive great reward in both maintaining-flight time and the capacity.","PeriodicalId":127186,"journal":{"name":"2021 IEEE International Conference on Communications Workshops (ICC Workshops)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115467701","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 : 2021-06-01DOI: 10.1109/ICCWorkshops50388.2021.9473819
Jared Miller, S. Uludag
The Unmanned Aerial Vehicle (UAV) has recently appeared as a good candidate for providing wireless network connectivity, with several advantages over traditional ground infrastructure. With the addition of on-board energy harvesting, such platforms have the potential for perpetual-endurance flight and wireless connectivity. Yet, UAV modeling, especially with respect to this combination of capabilities, is not well-understood. In this paper, we demonstrate a framework for analyzing the energy balance of simplified trajectories in three dimensions for fixed-wing aircraft with on-board solar energy harvesting, as well as integrating the trajectory into the NS3 simulator to evaluate network performance. This framework is applied to a small number of trajectory designs, showing that benefits may exist for non-circle trajectories, as well as some advantages and disadvantages of using altitude to conserve additional energy.
{"title":"Energy-Efficiency Framework for Fixed-Wing UAV Communications With Variable Altitude","authors":"Jared Miller, S. Uludag","doi":"10.1109/ICCWorkshops50388.2021.9473819","DOIUrl":"https://doi.org/10.1109/ICCWorkshops50388.2021.9473819","url":null,"abstract":"The Unmanned Aerial Vehicle (UAV) has recently appeared as a good candidate for providing wireless network connectivity, with several advantages over traditional ground infrastructure. With the addition of on-board energy harvesting, such platforms have the potential for perpetual-endurance flight and wireless connectivity. Yet, UAV modeling, especially with respect to this combination of capabilities, is not well-understood. In this paper, we demonstrate a framework for analyzing the energy balance of simplified trajectories in three dimensions for fixed-wing aircraft with on-board solar energy harvesting, as well as integrating the trajectory into the NS3 simulator to evaluate network performance. This framework is applied to a small number of trajectory designs, showing that benefits may exist for non-circle trajectories, as well as some advantages and disadvantages of using altitude to conserve additional energy.","PeriodicalId":127186,"journal":{"name":"2021 IEEE International Conference on Communications Workshops (ICC Workshops)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115504645","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}
Epidemiological investigation is one of the main means of controlling the outbreak of COVID-19. It has been proven to be effective, however, has a bottleneck that the infected person has to be questioned about his recent trajectory before any quarantine action could be taken, while sometimes trajectory information might not be timely and accurately obtained. In this paper, we propose an epidemiological investigation method which resort to artificial intelligence for extracting people’s preferences and social relationship from their historical trajectory patterns. Trajectory data used in our epidemiological investigation method may include time, location, Point-of-Interest (POI), as well as Behavior-of-Interest (BOI). All of these attributes in human’s trajectory are embedded into different channels in the proposed model and then fed into a classifier or a clusterer for serving different purposes. In our experiments, we applied the proposed method on a synthetic data set to conduct a classification task, and on a real data set for a clustering task. Both tasks confirm that the proposed method is effective and thus could be used to guide the preventive measures.
{"title":"Mining Trajectory Patterns with Point-of-Interest and Behavior-of-Interest","authors":"Sissi Xiaoxiao Wu, Zixian Wu, Weilin Zhu, Xiaokui Yang, Yong Li","doi":"10.1109/ICCWorkshops50388.2021.9473612","DOIUrl":"https://doi.org/10.1109/ICCWorkshops50388.2021.9473612","url":null,"abstract":"Epidemiological investigation is one of the main means of controlling the outbreak of COVID-19. It has been proven to be effective, however, has a bottleneck that the infected person has to be questioned about his recent trajectory before any quarantine action could be taken, while sometimes trajectory information might not be timely and accurately obtained. In this paper, we propose an epidemiological investigation method which resort to artificial intelligence for extracting people’s preferences and social relationship from their historical trajectory patterns. Trajectory data used in our epidemiological investigation method may include time, location, Point-of-Interest (POI), as well as Behavior-of-Interest (BOI). All of these attributes in human’s trajectory are embedded into different channels in the proposed model and then fed into a classifier or a clusterer for serving different purposes. In our experiments, we applied the proposed method on a synthetic data set to conduct a classification task, and on a real data set for a clustering task. Both tasks confirm that the proposed method is effective and thus could be used to guide the preventive measures.","PeriodicalId":127186,"journal":{"name":"2021 IEEE International Conference on Communications Workshops (ICC Workshops)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123185219","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 : 2021-06-01DOI: 10.1109/ICCWorkshops50388.2021.9473734
Jian-ji Ren, Junshuai Sun, Hui Tian, Wanli Ni, Gaofeng Nie, Yingying Wang
Federated learning (FL) and edge computing are both important technologies to support the future Internet of Things (IoT). Despite that the network supported by edge computing has great potential to promote FL, it is more challenging to achieve efficient FL due to more complex resource coupling in it. Focus on this problem, we formulate a problem which minimizes the weighted sum of system cost and learning cost by jointly optimizing bandwidth, computation frequency, transmission power allocation and subcarrier assignment. In order to solve this mixed-integer non-linear problem, we first decouple the bandwidth allocation subproblem from the original problem and obtain a closed-form solution. Further considering the remaining joint optimization problem of computation frequency, transmission power and subcarrier, an iterative algorithm with polynomial time complexity is designed. In an iteration, the latency and computation frequency optimization subproblem and transmission power and subcarrier optimization subproblem are solved using the proposed algorithms in turn. The iterative algorithm is repeated until convergence. Finally, to verify the performance of the algorithm, we compare the proposed algorithm with five baselines. Numerical results show the significant performance gain and the robustness of the proposed algorithm.
{"title":"Joint Resource Allocation for Efficient Federated Learning in Internet of Things Supported by Edge Computing","authors":"Jian-ji Ren, Junshuai Sun, Hui Tian, Wanli Ni, Gaofeng Nie, Yingying Wang","doi":"10.1109/ICCWorkshops50388.2021.9473734","DOIUrl":"https://doi.org/10.1109/ICCWorkshops50388.2021.9473734","url":null,"abstract":"Federated learning (FL) and edge computing are both important technologies to support the future Internet of Things (IoT). Despite that the network supported by edge computing has great potential to promote FL, it is more challenging to achieve efficient FL due to more complex resource coupling in it. Focus on this problem, we formulate a problem which minimizes the weighted sum of system cost and learning cost by jointly optimizing bandwidth, computation frequency, transmission power allocation and subcarrier assignment. In order to solve this mixed-integer non-linear problem, we first decouple the bandwidth allocation subproblem from the original problem and obtain a closed-form solution. Further considering the remaining joint optimization problem of computation frequency, transmission power and subcarrier, an iterative algorithm with polynomial time complexity is designed. In an iteration, the latency and computation frequency optimization subproblem and transmission power and subcarrier optimization subproblem are solved using the proposed algorithms in turn. The iterative algorithm is repeated until convergence. Finally, to verify the performance of the algorithm, we compare the proposed algorithm with five baselines. Numerical results show the significant performance gain and the robustness of the proposed algorithm.","PeriodicalId":127186,"journal":{"name":"2021 IEEE International Conference on Communications Workshops (ICC Workshops)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122103154","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：