2022 18th International Conference on Distributed Computing in Sensor Systems (DCOSS)最新文献_第7页

Software Radio with MATLAB Toolbox for 5G NR Waveform Generation 软件无线电与MATLAB工具箱的5G NR波形生成

2022 18th International Conference on Distributed Computing in Sensor Systems (DCOSS) Pub Date : 2022-05-01 DOI: 10.1109/DCOSS54816.2022.00078

Walaa AlQwider, Ajaya Dahal, V. Marojevic

引用次数: 1

Analysis of Pandemic Atmosphere Pollution Data Using Virtual Sensors in São Paulo City 利用虚拟传感器分析<s:1>圣保罗市大流行大气污染数据

2022 18th International Conference on Distributed Computing in Sensor Systems (DCOSS) Pub Date : 2022-05-01 DOI: 10.1109/DCOSS54816.2022.00058

Gabriel Oliveira Campos, L. Villas, F. D. Cunha

引用次数: 0

Hardware-aware Partitioning of Convolutional Neural Network Inference for Embedded AI Applications 嵌入式人工智能应用中卷积神经网络推理的硬件感知划分

2022 18th International Conference on Distributed Computing in Sensor Systems (DCOSS) Pub Date : 2022-05-01 DOI: 10.1109/DCOSS54816.2022.00034

Fabian Kreß, Julian Höfer, Tim Hotfilter, Iris Walter, V. Sidorenko, T. Harbaum, J. Becker

{"title":"Hardware-aware Partitioning of Convolutional Neural Network Inference for Embedded AI Applications","authors":"Fabian Kreß, Julian Höfer, Tim Hotfilter, Iris Walter, V. Sidorenko, T. Harbaum, J. Becker","doi":"10.1109/DCOSS54816.2022.00034","DOIUrl":"https://doi.org/10.1109/DCOSS54816.2022.00034","url":null,"abstract":"Embedded image processing applications like multicamera-based object detection or semantic segmentation are often based on Convolutional Neural Networks (CNNs) to provide precise and reliable results. The deployment of CNNs in embedded systems, however, imposes additional constraints such as latency restrictions and limited energy consumption in the sensor platform. These requirements have to be considered during hardware/software co-design of embedded Artifical Intelligence (AI) applications. In addition, the transmission of uncompressed image data from the sensor to a central edge node requires large bandwidth on the link, which must also be taken into account during the design phase.Therefore, we present a simulation toolchain for fast evaluation of hardware-aware CNN partitioning for embedded AI applications. This approach explores an efficient workload distribution between sensor nodes and a central edge node. Neither processing all layers close to the sensor nor transmitting all uncompressed raw data to the edge node is an optimal solution for each use case. Hence, our proposed simulation toolchain evaluates power and performance metrics for each reasonable partitioning point in a CNN. In contrast to the state of the art, our approach does not only consider the neural network architecture. In the evaluation, our simulation toolchain additionally takes into account hardware components such as special accelerators and memories that are implemented in the sensor node.Exemplary, we show the simulation results for three commonly used CNNs in embedded systems. Thereby, we identify advantageous partitioning points regarding inference latency and energy consumption. With the support of the toolchain, we are able to identify three beneficial partitioning points for FCN ResNet-50 and two for GoogLeNet as well as for SqueezeNet V1.1.","PeriodicalId":300416,"journal":{"name":"2022 18th International Conference on Distributed Computing in Sensor Systems (DCOSS)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117262468","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: 3

Design and Deployment Experiences of a Versatile Industrial WSN and Testbed 通用工业无线传感器网络与试验台的设计与部署经验

2022 18th International Conference on Distributed Computing in Sensor Systems (DCOSS) Pub Date : 2022-05-01 DOI: 10.1109/DCOSS54816.2022.00043

J. Schlichter, Lars C. Wolf

引用次数: 2

Keeping Information Alive: Hovering Information and Floating Content Paradigms for Vehicular Networks 保持信息的活力:车辆网络的悬停信息和浮动内容范式

2022 18th International Conference on Distributed Computing in Sensor Systems (DCOSS) Pub Date : 2022-05-01 DOI: 10.1109/DCOSS54816.2022.00055

Lachlan Johnston, R. Pazzi

引用次数: 0

Digital Twin Driven Blockchain Based Reliable and Efficient 6G Edge Network 基于可靠高效的6G边缘网络的数字孪生驱动区块链

2022 18th International Conference on Distributed Computing in Sensor Systems (DCOSS) Pub Date : 2022-05-01 DOI: 10.1109/DCOSS54816.2022.00062

Mehmet Ozgen Ozdogan, Levent Çarkacioglu, B. Canberk

引用次数: 5

A Middleware for Digital Twin-Enabled Flying Network Simulations Using UBSim and UB-ANC 基于UBSim和UB-ANC的数字双机飞行网络仿真中间件

2022 18th International Conference on Distributed Computing in Sensor Systems (DCOSS) Pub Date : 2022-05-01 DOI: 10.1109/DCOSS54816.2022.00059

Sabarish Krishna Moorthy, Ankush Harindranath, Maxwell Mcmanus, Zhangyu Guan, Nicholas Mastronarde, E. Bentley, M. Medley

{"title":"A Middleware for Digital Twin-Enabled Flying Network Simulations Using UBSim and UB-ANC","authors":"Sabarish Krishna Moorthy, Ankush Harindranath, Maxwell Mcmanus, Zhangyu Guan, Nicholas Mastronarde, E. Bentley, M. Medley","doi":"10.1109/DCOSS54816.2022.00059","DOIUrl":"https://doi.org/10.1109/DCOSS54816.2022.00059","url":null,"abstract":"Data-driven control based on AI/ML techniques has a great potential to enable zero-touch automated modeling, optimization and control of complex wireless systems. However, it is challenging to collect network traces in the real world because of high time and labor cost, weather limitations as well as safety concerns. In this work we attempt to tackle this challenge by designing a multi-fidelity simulator taking wireless Unmanned Aerial Vehicle (UAV) networks into consideration. We design the simulator by interfacing two Unmanned Aerial System (UAS) simulators we have developed in prior years: UBSim and UB-ANC. The former focuses on UAV network optimization and policy training by considering explicitly the network environments such as blockage dynamics, while the latter focuses more on high-fidelity UAV flight control. We first develop a coordination interface referred to as SimSocket for signaling exchanges between UBSim and UB-ANC in simulations, and then showcase coordinated simulations based on UBSim and UB-ANC. The new research that can be enabled by the integrated simulator is also discussed for digital twin-based UAS systems.","PeriodicalId":300416,"journal":{"name":"2022 18th International Conference on Distributed Computing in Sensor Systems (DCOSS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126223416","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: 1

An IoT-based Framework for Low-Cost and Light-Weight Vehicle Detection 基于物联网的低成本轻量化车辆检测框架

2022 18th International Conference on Distributed Computing in Sensor Systems (DCOSS) Pub Date : 2022-05-01 DOI: 10.1109/DCOSS54816.2022.00023

C. Shekhar, S. Saha

引用次数: 1

Network Economics-based Crowdsourcing in UAV-assisted Smart Cities Environments 无人机辅助智慧城市环境下基于网络经济学的众包

2022 18th International Conference on Distributed Computing in Sensor Systems (DCOSS) Pub Date : 2022-05-01 DOI: 10.1109/DCOSS54816.2022.00030

Fisayo Sangoleye, Md Sahabul Hossain, Eirini-Eleni Tsiropoulou, J. Plusquellic

{"title":"Network Economics-based Crowdsourcing in UAV-assisted Smart Cities Environments","authors":"Fisayo Sangoleye, Md Sahabul Hossain, Eirini-Eleni Tsiropoulou, J. Plusquellic","doi":"10.1109/DCOSS54816.2022.00030","DOIUrl":"https://doi.org/10.1109/DCOSS54816.2022.00030","url":null,"abstract":"In this paper, a novel crowdsourcing mechanism is introduced in Unmanned Aerial Vehicles (UAVs)-assisted smart cities environments based on the principles of Contract Theory and Reinforcement Learning. Initially, a contract-theoretic mechanism is proposed to enable the UAVs to incentivize the Internet of Things (IoT) nodes to report their collected data (i.e., effort) via providing personalized rewards to them. This novel mechanism exploits the IoT nodes’ physical and social characteristics in order to design optimal personalized contracts, i.e., pairs of {effort, reward}, while jointly optimizing the benefits of the UAVs and the IoT nodes from the crowdsourcing process. Additionally, a reinforcement learning-based mechanism is designed to enable the IoT nodes to select a UAV to report their data, while considering the received rewards in the crowdsourcing process. A set of detailed numerical and comparative results are presented to demonstrate the operational characteristics of the proposed crowdsourcing framework, as well as its drawbacks and benefits compared to the state of the art.","PeriodicalId":300416,"journal":{"name":"2022 18th International Conference on Distributed Computing in Sensor Systems (DCOSS)","volume":"207 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114924284","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

Taking ROCKET on an Efficiency Mission: Multivariate Time Series Classification with LightWaveS 让ROCKET实现效率任务:基于光波的多元时间序列分类

2022 18th International Conference on Distributed Computing in Sensor Systems (DCOSS) Pub Date : 2022-04-04 DOI: 10.1109/DCOSS54816.2022.00036

Leonardos Pantiskas, K. Verstoep, M. Hoogendoorn, H. Bal

{"title":"Taking ROCKET on an Efficiency Mission: Multivariate Time Series Classification with LightWaveS","authors":"Leonardos Pantiskas, K. Verstoep, M. Hoogendoorn, H. Bal","doi":"10.1109/DCOSS54816.2022.00036","DOIUrl":"https://doi.org/10.1109/DCOSS54816.2022.00036","url":null,"abstract":"Nowadays, with the rising number of sensor signals in sectors such as healthcare and industry, the problem of multivariate time series classification (MTSC) is getting increasingly relevant and is a prime target for machine and deep learning approaches. Their expanding adoption in real-world environments is causing a shift in focus from the pursuit of everhigher prediction accuracy with complex models towards practical, deployable solutions that balance accuracy and parameters such as prediction speed. An MTSC model that has attracted attention recently is ROCKET, based on random convolutional kernels, both because of its very fast training process and its state-of-the-art accuracy. However, the large number of features it utilizes may be detrimental to inference time. Examining its theoretical background and limitations enables us to address potential drawbacks and present LightWaveS: a framework for accurate MTSC, which is fast both during training and inference. We show that LightWaveS achieves accuracy comparable to recent MTSC models and speedup ranging from 9x to 53x compared to ROCKET during inference on an edge device, on datasets with comparable accuracy.","PeriodicalId":300416,"journal":{"name":"2022 18th International Conference on Distributed Computing in Sensor Systems (DCOSS)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126648168","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: 3