2022 IEEE Latin-American Conference on Communications (LATINCOM)最新文献_第3页

A Socio-Temporal Cache Prefetching Policy for the Multi-access Edge Computing Architecture 一种面向多访问边缘计算架构的社会时序缓存预取策略

2022 IEEE Latin-American Conference on Communications (LATINCOM) Pub Date : 2022-11-30 DOI: 10.1109/LATINCOM56090.2022.10000591

Cleomar Márcio Marques de Oliveira, I. Moraes, C. Albuquerque, José Jerônimo de Menezes Lima

引用次数: 0

Wi-Fi CSI-based Human Presence Detection Using DTW Features and Machine Learning 使用DTW特征和机器学习的基于Wi-Fi csi的人类存在检测

2022 IEEE Latin-American Conference on Communications (LATINCOM) Pub Date : 2022-11-30 DOI: 10.1109/LATINCOM56090.2022.10000702

J. Soto, Iandra Galdino, Brenda G. Gouveia, Egberto Caballero, Vinicius C. Ferreira, D. Muchaluat-Saade, C. Albuquerque

引用次数: 2

A probabilistic Grant Free scheduling model to allocate resources for eXtreme URLLC applications 为eXtreme URLLC应用程序分配资源的概率Grant Free调度模型

2022 IEEE Latin-American Conference on Communications (LATINCOM) Pub Date : 2022-11-30 DOI: 10.1109/LATINCOM56090.2022.10000540

S. Eum, S. Arakawa, M. Murata

引用次数: 1

On Evaluation of Interpolation Between Reed-Muller and Polar Rate-Profiling in PAC Codes PAC代码中Reed-Muller与极性速率剖面插值的评价

2022 IEEE Latin-American Conference on Communications (LATINCOM) Pub Date : 2022-11-30 DOI: 10.1109/LATINCOM56090.2022.10000553

Tatiana Rykova, B. Göktepe, T. Schierl, C. Hellge

引用次数: 1

A Hybrid CNN-LSTM Model for IIoT Edge Privacy-Aware Intrusion Detection 工业物联网边缘隐私感知入侵检测的CNN-LSTM混合模型

2022 IEEE Latin-American Conference on Communications (LATINCOM) Pub Date : 2022-11-30 DOI: 10.1109/LATINCOM56090.2022.10000468

Erik Miguel de Elias, Vinicius Sanches Carriel, Guilherme Werneck de Oliveira, A. Santos, M. N. Lima, Roberto Hirata Junior, D. Batista

引用次数: 2

AI-enabled SD-WAN: the case of Reinforcement Learning 支持ai的SD-WAN:以强化学习为例

2022 IEEE Latin-American Conference on Communications (LATINCOM) Pub Date : 2022-11-30 DOI: 10.1109/LATINCOM56090.2022.10000667

A. Botta, R. Canonico, Annalisa Navarro, S. Ruggiero, G. Ventre

引用次数: 2

Decision Early-Exit: An Efficient Approach to Hasten Offloading in BranchyNets 决策早退出:一种加速分支网络卸载的有效方法

2022 IEEE Latin-American Conference on Communications (LATINCOM) Pub Date : 2022-11-30 DOI: 10.1109/LATINCOM56090.2022.10000430

Mariana S. M. Barbosa, R. G. Pacheco, R. S. Couto, Dianne S. V. Medeiros, M. Campista

{"title":"Decision Early-Exit: An Efficient Approach to Hasten Offloading in BranchyNets","authors":"Mariana S. M. Barbosa, R. G. Pacheco, R. S. Couto, Dianne S. V. Medeiros, M. Campista","doi":"10.1109/LATINCOM56090.2022.10000430","DOIUrl":"https://doi.org/10.1109/LATINCOM56090.2022.10000430","url":null,"abstract":"Many works study partitioning and early exits in Deep Neural Networks (DNNs) to improve the inference time. Early exits allow the inference of samples in advance, based on the fact that some features are learned at DNNs’ initial layers. However, usage of early exits can slightly decrease performance. Partitioning enables the shallowest part of the model to reside at the edge while the deeper layers reside in the cloud. Deciding whether samples must be sent to the cloud at each early exit is time consuming, increasing the total inference time. Hence, reducing this time while maintaining the model performance is currently an open challenge. In this paper, we propose a Decision Early Exit (DEEx), implemented at the first early exit, aiming to reduce the total inference time by skipping unnecessary evaluations at early exits, which may not able to improve the model’s performance. To this end, the DEEx compares a predefined decision threshold with the prediction confidence level for each sample and decides whether the sample must be offloaded. We assess DEEx through a comparative analysis that investigates the influence of different values for the decision threshold on the inference time. Our results show that there is a cost benefit between the inference time and the threshold. Using DEEx in a simulated BranchyNet, we can reduce the inference time by around 20% while maintaining the same accuracy achieved when the samples are offloaded.","PeriodicalId":221354,"journal":{"name":"2022 IEEE Latin-American Conference on Communications (LATINCOM)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130562518","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}

引用次数: 0

Traffic-Aware Beacon Interval for Position-Based Protocols in VANETs VANETs中基于位置协议的流量感知信标间隔

2022 IEEE Latin-American Conference on Communications (LATINCOM) Pub Date : 2022-11-30 DOI: 10.1109/LATINCOM56090.2022.10000575

Álvaro T. Amaya, Alexandre A. P. Pohl, M. Fonseca, R. Lüders

{"title":"Traffic-Aware Beacon Interval for Position-Based Protocols in VANETs","authors":"Álvaro T. Amaya, Alexandre A. P. Pohl, M. Fonseca, R. Lüders","doi":"10.1109/LATINCOM56090.2022.10000575","DOIUrl":"https://doi.org/10.1109/LATINCOM56090.2022.10000575","url":null,"abstract":"Position-based protocols in vehicular ad-hoc networks (VANETs) depend on the transmission of periodic beacon messages to keep the nodes informed about the current position of their neighbors. However, an excessive load of beacons can drastically deteriorate the network performance. This work presents a novel adaptive vehicular traffic-aware strategy to compute the beacon interval in a position-based protocol. The strategy relies on three mobility factors: vehicular density, the mean difference of speed among neighbors, and the spatial distribution of neighbors. Its effectiveness is proven through extensive simulations in an urban mobility scenario using the packet delivery ratio, the average end-to-end delay, overhead, and processing time as the performance metrics. The results show that our approach maintains a high delivery ratio and low End-To-End delay, overhead, and processing time regardless of the density of the surrounding vehicular traffic. The results also show that our method uses the available beacon interval range more efficiently than another traffic-aware approach.","PeriodicalId":221354,"journal":{"name":"2022 IEEE Latin-American Conference on Communications (LATINCOM)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129908837","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}

引用次数: 0

Energy Efficiency Aware Collaborative Multi-UAV Deployment for Intelligent Traffic Surveillance 基于节能意识的多无人机智能交通监控协同部署

2022 IEEE Latin-American Conference on Communications (LATINCOM) Pub Date : 2022-11-30 DOI: 10.1109/LATINCOM56090.2022.10000469

Xiang Cheng, Huaguang Shi, Zhanqi Jin, Nianwen Ning, Yanyu Zhang, Yi Zhou

{"title":"Energy Efficiency Aware Collaborative Multi-UAV Deployment for Intelligent Traffic Surveillance","authors":"Xiang Cheng, Huaguang Shi, Zhanqi Jin, Nianwen Ning, Yanyu Zhang, Yi Zhou","doi":"10.1109/LATINCOM56090.2022.10000469","DOIUrl":"https://doi.org/10.1109/LATINCOM56090.2022.10000469","url":null,"abstract":"The existing city traffic surveillance systems are mainly based on passive monitoring by using fixed sensors, which cannot fully meet the highly dynamic monitoring requirements of intelligent traffic. To address this concern, this paper employs flexible Unmanned Aerial Vehicles (UAVs) to provide active monitoring services in a cooperative way. Firstly, we comprehensively consider the energy consumption and network connectivity constraints of the UAV system to establish a multi-UAV-based mobile monitoring model aiming at maximizing task energy efficiency. Then, we formulate the collaborative multi-UAV surveillance problem as a multi-agent Markov decision process to determine the optimal strategies for UAVs. Next, we propose a Collaborative Multi-UAV Deployment (CMUD) algorithm based on Multi-Agent Deep Deterministic Policy Gradient (MADDPG) by designing an effective reward function and improving the experience replay scheme. In addition, we introduce a policy integration scheme for the proposed CMUD algorithm to solve the problem that the UAV overly relies on the movement strategies of other UAVs in the non-stationary multi-UAV traffic monitoring environment. Simulation results show that the proposed CMUD algorithm can effectively accelerate the exploration of movement strategies with the guarantee of stable connectivity and efficiently improve task energy efficiency.","PeriodicalId":221354,"journal":{"name":"2022 IEEE Latin-American Conference on Communications (LATINCOM)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132570555","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}

引用次数: 0

A Study on the Uncertainty in Estimation for Short-Length Communication 短长度通信估计中的不确定性研究

2022 IEEE Latin-American Conference on Communications (LATINCOM) Pub Date : 2022-11-30 DOI: 10.1109/LATINCOM56090.2022.10000490

Yan F. Coutinho, G. R. Colen, Túlio F. Moreira, M. Filomeno, Moises Vidal Ribeiro

引用次数: 0