2019 IEEE Sensors Applications Symposium (SAS)最新文献_第10页

360 Multisensor Object Fusion and Sensor-based Erroneous Data Management for Autonomous Vehicles 360多传感器目标融合与基于传感器的自动驾驶车辆错误数据管理

2019 IEEE Sensors Applications Symposium (SAS) Pub Date : 2019-03-01 DOI: 10.1109/SAS.2019.8705970

S. Durand, R. Benmokhtar, Xavier Perrotton

引用次数: 3

Object classification on raw radar data using convolutional neural networks 利用卷积神经网络对原始雷达数据进行目标分类

2019 IEEE Sensors Applications Symposium (SAS) Pub Date : 2019-03-01 DOI: 10.1109/SAS.2019.8706004

Heejae Han, Jeonghwan Kim, Junyoung Park, YuJin Lee, Hyunwoo Jo, Yonghyeon Park, E. Matson, Seongha Park

{"title":"Object classification on raw radar data using convolutional neural networks","authors":"Heejae Han, Jeonghwan Kim, Junyoung Park, YuJin Lee, Hyunwoo Jo, Yonghyeon Park, E. Matson, Seongha Park","doi":"10.1109/SAS.2019.8706004","DOIUrl":"https://doi.org/10.1109/SAS.2019.8706004","url":null,"abstract":"This paper evaluates the classification of objects given their signal data via a simple convolutional neural network (CNN). Many of the signal processing neural networks involve sound frequency data or Doppler signatures that contain the characteristic features of each object. In this study, we use frequency-intensity data within range-time domain from a Frequency-Modulated Continuous-Wave (FMCW) radar to classify detected objects. The application of various data augmentation methods mitigated the scarcity of labeled data from our field experiments. Time stretching, frequency shifting and noise addition preserved the semantic information of each rangetime data, further improving the models ability to generalize. Modifications applied to our data, which is then converted into a low-level log-scaled mel-spectrogram representation, are learned by CNN models with a set of convolutional and max-pooling layers along with fully-connected layers and selective residual module. Based on our experiments, we conclude that raw radar data can be used for training CNNs for classification and thus can be used to classify a car, a human, and an UAV.","PeriodicalId":360234,"journal":{"name":"2019 IEEE Sensors Applications Symposium (SAS)","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129045466","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

Improving NILM by Combining Sensor Data and Linear Programming 结合传感器数据和线性规划改进NILM

2019 IEEE Sensors Applications Symposium (SAS) Pub Date : 2019-03-01 DOI: 10.1109/SAS.2019.8706021

N. Roux, B. Vrigneau, O. Sentieys

引用次数: 9

Lensless Imaging Sensor Kit for Sperm Counting with Microfluidic Chip 微流控芯片精子计数无透镜成像传感器套件

2019 IEEE Sensors Applications Symposium (SAS) Pub Date : 2019-03-01 DOI: 10.1109/SAS.2019.8706105

Young Jae Kim, K. Chun

引用次数: 3

Evidential Multisensor Fusion and Erroneous Management of Lanes for Autonomous Driving 自动驾驶多传感器证据融合与车道错误管理

2019 IEEE Sensors Applications Symposium (SAS) Pub Date : 2019-03-01 DOI: 10.1109/SAS.2019.8706085

Salma Moujtahid, T. Liennard, R. Benmokhtar

引用次数: 1

An inkjet printed pressure sensor for applications in Active Ageing monitoring 一种用于主动老化监测的喷墨印刷压力传感器

2019 IEEE Sensors Applications Symposium (SAS) Pub Date : 2019-03-01 DOI: 10.1109/SAS.2019.8705972

B. Andò, S. Baglio, S. Castorina, R. Crispino, V. Marletta

引用次数: 2

Analysis of output signals of angular position sensors for the use of neural networks 用神经网络分析角度位置传感器的输出信号

2019 IEEE Sensors Applications Symposium (SAS) Pub Date : 2019-03-01 DOI: 10.1109/SAS.2019.8706010

Phil Meier, K. Rohrmann, Marvin Sandner, M. Prochaska

引用次数: 8

Susceptibility of atmospheric imaging lidars to external backgrounds, sensitive to the depth of field 大气成像激光雷达对外部背景的敏感性，对景深敏感

2019 IEEE Sensors Applications Symposium (SAS) Pub Date : 2019-03-01 DOI: 10.1109/SAS.2019.8706032

R. Agishev, V. Solovyev

{"title":"Susceptibility of atmospheric imaging lidars to external backgrounds, sensitive to the depth of field","authors":"R. Agishev, V. Solovyev","doi":"10.1109/SAS.2019.8706032","DOIUrl":"https://doi.org/10.1109/SAS.2019.8706032","url":null,"abstract":"In the tasks of laser remote sensing of the environment that are characterized by relatively \"weak\" scattered echo-signals coming from distant atmospheric layers, one of important indicators of the sensor efficiency is its resistance to the bright background of day sky. This is fully applicable to imaging lidars as a novel and promising class of remote sensors gradually expanding the interest in using as an alternative to traditional pulsed and frequency-modulated lidars for environmental monitoring.The paper examines the susceptibility of imaging lidars to external backgrounds based on studies of features of their spatial selectivity, the operation range required and optical weather conditions. Our analysis focuses attention on the distorting effect caused by external radiation and characterized by a possible significant unevenness of the background power received by single pixels of the array detector. When sensing light haze and less transparent atmospheric formations in the daytime conditions, there may be noticeable limitations on the accuracy of echo-signal measurements that cause subsequent distortion of the retrieval results of the range profiles of optical parameters under investigation. The implemented approach allows assessing both capabilities of atmospheric imaging lidars and limitations imposed by the real-life environment.","PeriodicalId":360234,"journal":{"name":"2019 IEEE Sensors Applications Symposium (SAS)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128006998","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

Classification of Non-ferrous Scrap Metal using Two Component Magnetic Induction Spectroscopy 利用双分量磁感应光谱法对有色金属废料进行分类

2019 IEEE Sensors Applications Symposium (SAS) Pub Date : 2019-03-01 DOI: 10.1109/SAS.2019.8706104

M. D. OrToole, A. Peyton

{"title":"Classification of Non-ferrous Scrap Metal using Two Component Magnetic Induction Spectroscopy","authors":"M. D. OrToole, A. Peyton","doi":"10.1109/SAS.2019.8706104","DOIUrl":"https://doi.org/10.1109/SAS.2019.8706104","url":null,"abstract":"Magnetic induction spectroscopy is the measurement of how a conductive object reflects and scatters a magnetic field over different frequencies in response to some excitation magnetic field. In recent work, we proposed using this technique to classify different non-ferrous metals for the recycling and resource recovery sector - specifically, to identify fragments of scrap aluminium, copper and brass in shredded waste streams for separation and recovery. We proposed a simple algorithm that used only two components of the spectra that gave strong purity and recovery-rates when tested on a manufactured control set cut from stock metals.In this paper, we re-examined this method using real scrap metal samples drawn from a commercial sorting line. We found moderate purity and recovery-rates of brass and copper of between around 70% and 90%. However, the classification of aluminium was poor with ≈55% and ≈80% purity and recovery rates respectively. Magnetic induction sensors are a natural fit for the specifications of the industry. They are capable of high-throughputs, are unaffected by dirt or contaminants and are mechanically and physically robust. Although our results are modest, they are not insignificant given the simplicity of the algorithm and the relatively low-cost of instrumentation. Our work suggests the MIS as a technique may have a significant role to play in the extraction and recovery of non-ferrous resources.","PeriodicalId":360234,"journal":{"name":"2019 IEEE Sensors Applications Symposium (SAS)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126640485","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: 5

Cluster of IoT Sensors for Smart Cities: Impact of the Communication Infrastructure over Computational Performance 智慧城市物联网传感器集群:通信基础设施对计算性能的影响

2019 IEEE Sensors Applications Symposium (SAS) Pub Date : 2019-03-01 DOI: 10.1109/SAS.2019.8706079

Federico Bonafini, S. Rinaldi, A. Depari, A. Flammini, P. Ferrari, E. Sisinni

{"title":"Cluster of IoT Sensors for Smart Cities: Impact of the Communication Infrastructure over Computational Performance","authors":"Federico Bonafini, S. Rinaldi, A. Depari, A. Flammini, P. Ferrari, E. Sisinni","doi":"10.1109/SAS.2019.8706079","DOIUrl":"https://doi.org/10.1109/SAS.2019.8706079","url":null,"abstract":"The Smart City (SC) paradigm is based on the integration of Information and Communication Technology (ICT) into the urban asset, for the optimal management of the energies and resources. The Internet of Thing (IoT) technology seems the proper solution to achieve this target, thanks to its capability to abstract the object in the real world. The deployment of IoT devices at different level in urban infrastructures is causing the presence of thousands of intelligent devices, large part of them with unused computational capabilities. Such devices could be integrated in a cluster in order to share the unused resources with other devices with limited computational resources. The use of a cluster of IoT Sensors has several benefits, including, but not limited to: high availability, sharing of computational resources, reduced response time with the respect of centralized cloud computing solution. The main bottleneck of this approach is represented by the communication infrastructure, typically based on wireless connection and, thus with a limited available bandwidth. The aim of the work related to this paper is to analyze the impact the communication infrastructure has on computational performance of a cluster of IoT sensors. An experimental set-up for the characterization of the performance of a cluster of low-cost off-the-shelf devices has been described. The experimental validation highlighted as the network infrastructure is loaded only during the data transfer and the maximum network load, with a cluster of ten IoT nodes is approximately 2 Mb/s with the considered benchmark.","PeriodicalId":360234,"journal":{"name":"2019 IEEE Sensors Applications Symposium (SAS)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129719028","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: 2