No Cover Image

Journal article 587 views 105 downloads

Study of the Application of Deep Convolutional Neural Networks (CNNs) in Processing Sensor Data and Biomedical Images

Weijun Hu, Yan Zhang, Lijie Li Orcid Logo

Sensors, Volume: 19, Issue: 16, Start page: 3584

Swansea University Author: Lijie Li Orcid Logo

  • sensors-19-03584.pdf

    PDF | Version of Record

    This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).

    Download (2.57MB)

Check full text

DOI (Published version): 10.3390/s19163584

Abstract

The fast progress in research and development of multifunctional, distributed sensor networks has brought challenges in processing data from a large number of sensors. Using deep learning methods such as convolutional neural networks (CNN), it is possible to build smarter systems to forecasting futu...

Full description

Published in: Sensors
ISSN: 1424-8220
Published: 2019
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa51483
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2019-08-19T21:29:08Z
last_indexed 2019-09-03T14:51:45Z
id cronfa51483
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2019-09-03T10:02:21.1065652</datestamp><bib-version>v2</bib-version><id>51483</id><entry>2019-08-19</entry><title>Study of the Application of Deep Convolutional Neural Networks (CNNs) in Processing Sensor Data and Biomedical Images</title><swanseaauthors><author><sid>ed2c658b77679a28e4c1dcf95af06bd6</sid><ORCID>0000-0003-4630-7692</ORCID><firstname>Lijie</firstname><surname>Li</surname><name>Lijie Li</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2019-08-19</date><deptcode>EEEG</deptcode><abstract>The fast progress in research and development of multifunctional, distributed sensor networks has brought challenges in processing data from a large number of sensors. Using deep learning methods such as convolutional neural networks (CNN), it is possible to build smarter systems to forecasting future situations as well as precisely classify large amounts of data from sensors. Multi-sensor data from atmospheric pollutants measurements that involves five criteria, with the underlying analytic model unknown, need to be categorized, so do the Diabetic Retinopathy (DR) fundus images dataset. In this work, we created automatic classifiers based on a deep convolutional neural network (CNN) with two models, a simpler feedforward model with dual modules and an Inception Resnet v2 model, and various structural tweaks for classifying the data from the two tasks. For segregating multi-sensor data, we trained a deep CNN-based classifier on an image dataset extracted from the data by a novel image generating method. We created two deepened and one reductive feedforward network for DR phase classification. The validation accuracies and visualization results show that increasing deep CNN structure depth or kernels number in convolutional layers will not indefinitely improve the classification quality and that a more sophisticated model does not necessarily achieve higher performance when training datasets are quantitatively limited, while increasing training image resolution can induce higher classification accuracies for trained CNNs. The methodology aims at providing support for devising classification networks powering intelligent sensors.</abstract><type>Journal Article</type><journal>Sensors</journal><volume>19</volume><journalNumber>16</journalNumber><paginationStart>3584</paginationStart><publisher/><issnElectronic>1424-8220</issnElectronic><keywords>convolutional neural network; images processing; multi-sensor; diabetic retinopathy</keywords><publishedDay>17</publishedDay><publishedMonth>8</publishedMonth><publishedYear>2019</publishedYear><publishedDate>2019-08-17</publishedDate><doi>10.3390/s19163584</doi><url/><notes/><college>COLLEGE NANME</college><department>Electronic and Electrical Engineering</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>EEEG</DepartmentCode><institution>Swansea University</institution><apcterm/><lastEdited>2019-09-03T10:02:21.1065652</lastEdited><Created>2019-08-19T16:13:25.3857258</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Electronic and Electrical Engineering</level></path><authors><author><firstname>Weijun</firstname><surname>Hu</surname><order>1</order></author><author><firstname>Yan</firstname><surname>Zhang</surname><order>2</order></author><author><firstname>Lijie</firstname><surname>Li</surname><orcid>0000-0003-4630-7692</orcid><order>3</order></author></authors><documents><document><filename>0051483-19082019161513.pdf</filename><originalFilename>sensors-19-03584.pdf</originalFilename><uploaded>2019-08-19T16:15:13.0800000</uploaded><type>Output</type><contentLength>2643135</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><embargoDate>2019-08-19T00:00:00.0000000</embargoDate><documentNotes>This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>http://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling 2019-09-03T10:02:21.1065652 v2 51483 2019-08-19 Study of the Application of Deep Convolutional Neural Networks (CNNs) in Processing Sensor Data and Biomedical Images ed2c658b77679a28e4c1dcf95af06bd6 0000-0003-4630-7692 Lijie Li Lijie Li true false 2019-08-19 EEEG The fast progress in research and development of multifunctional, distributed sensor networks has brought challenges in processing data from a large number of sensors. Using deep learning methods such as convolutional neural networks (CNN), it is possible to build smarter systems to forecasting future situations as well as precisely classify large amounts of data from sensors. Multi-sensor data from atmospheric pollutants measurements that involves five criteria, with the underlying analytic model unknown, need to be categorized, so do the Diabetic Retinopathy (DR) fundus images dataset. In this work, we created automatic classifiers based on a deep convolutional neural network (CNN) with two models, a simpler feedforward model with dual modules and an Inception Resnet v2 model, and various structural tweaks for classifying the data from the two tasks. For segregating multi-sensor data, we trained a deep CNN-based classifier on an image dataset extracted from the data by a novel image generating method. We created two deepened and one reductive feedforward network for DR phase classification. The validation accuracies and visualization results show that increasing deep CNN structure depth or kernels number in convolutional layers will not indefinitely improve the classification quality and that a more sophisticated model does not necessarily achieve higher performance when training datasets are quantitatively limited, while increasing training image resolution can induce higher classification accuracies for trained CNNs. The methodology aims at providing support for devising classification networks powering intelligent sensors. Journal Article Sensors 19 16 3584 1424-8220 convolutional neural network; images processing; multi-sensor; diabetic retinopathy 17 8 2019 2019-08-17 10.3390/s19163584 COLLEGE NANME Electronic and Electrical Engineering COLLEGE CODE EEEG Swansea University 2019-09-03T10:02:21.1065652 2019-08-19T16:13:25.3857258 Faculty of Science and Engineering School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Electronic and Electrical Engineering Weijun Hu 1 Yan Zhang 2 Lijie Li 0000-0003-4630-7692 3 0051483-19082019161513.pdf sensors-19-03584.pdf 2019-08-19T16:15:13.0800000 Output 2643135 application/pdf Version of Record true 2019-08-19T00:00:00.0000000 This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/). true eng http://creativecommons.org/licenses/by/4.0/
title Study of the Application of Deep Convolutional Neural Networks (CNNs) in Processing Sensor Data and Biomedical Images
spellingShingle Study of the Application of Deep Convolutional Neural Networks (CNNs) in Processing Sensor Data and Biomedical Images
Lijie Li
title_short Study of the Application of Deep Convolutional Neural Networks (CNNs) in Processing Sensor Data and Biomedical Images
title_full Study of the Application of Deep Convolutional Neural Networks (CNNs) in Processing Sensor Data and Biomedical Images
title_fullStr Study of the Application of Deep Convolutional Neural Networks (CNNs) in Processing Sensor Data and Biomedical Images
title_full_unstemmed Study of the Application of Deep Convolutional Neural Networks (CNNs) in Processing Sensor Data and Biomedical Images
title_sort Study of the Application of Deep Convolutional Neural Networks (CNNs) in Processing Sensor Data and Biomedical Images
author_id_str_mv ed2c658b77679a28e4c1dcf95af06bd6
author_id_fullname_str_mv ed2c658b77679a28e4c1dcf95af06bd6_***_Lijie Li
author Lijie Li
author2 Weijun Hu
Yan Zhang
Lijie Li
format Journal article
container_title Sensors
container_volume 19
container_issue 16
container_start_page 3584
publishDate 2019
institution Swansea University
issn 1424-8220
doi_str_mv 10.3390/s19163584
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Electronic and Electrical Engineering{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Electronic and Electrical Engineering
document_store_str 1
active_str 0
description The fast progress in research and development of multifunctional, distributed sensor networks has brought challenges in processing data from a large number of sensors. Using deep learning methods such as convolutional neural networks (CNN), it is possible to build smarter systems to forecasting future situations as well as precisely classify large amounts of data from sensors. Multi-sensor data from atmospheric pollutants measurements that involves five criteria, with the underlying analytic model unknown, need to be categorized, so do the Diabetic Retinopathy (DR) fundus images dataset. In this work, we created automatic classifiers based on a deep convolutional neural network (CNN) with two models, a simpler feedforward model with dual modules and an Inception Resnet v2 model, and various structural tweaks for classifying the data from the two tasks. For segregating multi-sensor data, we trained a deep CNN-based classifier on an image dataset extracted from the data by a novel image generating method. We created two deepened and one reductive feedforward network for DR phase classification. The validation accuracies and visualization results show that increasing deep CNN structure depth or kernels number in convolutional layers will not indefinitely improve the classification quality and that a more sophisticated model does not necessarily achieve higher performance when training datasets are quantitatively limited, while increasing training image resolution can induce higher classification accuracies for trained CNNs. The methodology aims at providing support for devising classification networks powering intelligent sensors.
published_date 2019-08-17T04:03:22Z
_version_ 1763753279229001728
score 11.013148

Similar Items