Deep Neural Network Initialization Methods for Micro-Doppler Classification With Low Training Sample Support
Deep neural networks (DNNs) require large-scale labeled data sets to prevent overfitting while having good generalization. In radar applications, however, acquiring a measured data set of the order of thousands is challenging due to constraints on manpower, cost, and other resources. In this letter,...
Saved in:
| Published in: | IEEE geoscience and remote sensing letters Vol. 14; no. 12; pp. 2462 - 2466 |
|---|---|
| Main Authors: | , |
| Format: | Journal Article |
| Language: | English |
| Published: |
Piscataway
IEEE
01.12.2017
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Subjects: | |
| ISSN: | 1545-598X, 1558-0571 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | Deep neural networks (DNNs) require large-scale labeled data sets to prevent overfitting while having good generalization. In radar applications, however, acquiring a measured data set of the order of thousands is challenging due to constraints on manpower, cost, and other resources. In this letter, the efficacy of two neural network initialization techniques-unsupervised pretraining and transfer learning-for dealing with training DNNs on small data sets is compared. Unsupervised pretraining is implemented through the design of a convolutional autoencoder (CAE), while transfer learning from two popular convolutional neural network architectures (VGGNet and GoogleNet) is used to augment measured RF data for training. A 12-class problem for discrimination of micro-Doppler signatures for indoor human activities is utilized to analyze activation maps, bottleneck features, class model, and classification accuracy with respect to training sample size. Results show that on meager data sets, transfer learning outperforms unsupervised pretraining and random initialization by 10% and 25%, respectively, but that when the sample size exceeds 650, unsupervised pretraining surpasses transfer learning and random initialization by 5% and 10%, respectively. Visualization of activation layers and learned models reveals how the CAE succeeds in representing the micro-Doppler signature. |
|---|---|
| AbstractList | Deep neural networks (DNNs) require large-scale labeled data sets to prevent overfitting while having good generalization. In radar applications, however, acquiring a measured data set of the order of thousands is challenging due to constraints on manpower, cost, and other resources. In this letter, the efficacy of two neural network initialization techniques-unsupervised pretraining and transfer learning-for dealing with training DNNs on small data sets is compared. Unsupervised pretraining is implemented through the design of a convolutional autoencoder (CAE), while transfer learning from two popular convolutional neural network architectures (VGGNet and GoogleNet) is used to augment measured RF data for training. A 12-class problem for discrimination of micro-Doppler signatures for indoor human activities is utilized to analyze activation maps, bottleneck features, class model, and classification accuracy with respect to training sample size. Results show that on meager data sets, transfer learning outperforms unsupervised pretraining and random initialization by 10% and 25%, respectively, but that when the sample size exceeds 650, unsupervised pretraining surpasses transfer learning and random initialization by 5% and 10%, respectively. Visualization of activation layers and learned models reveals how the CAE succeeds in representing the micro-Doppler signature. |
| Author | Seyfioglu, Mehmet Saygin Gurbuz, Sevgi Zubeyde |
| Author_xml | – sequence: 1 givenname: Mehmet Saygin surname: Seyfioglu fullname: Seyfioglu, Mehmet Saygin email: msseyfioglu@etu.edu.tr organization: Dept. of Electr. Electron. Eng., TOBB Univ. of Econ. & Technol., Ankara, Turkey – sequence: 2 givenname: Sevgi Zubeyde surname: Gurbuz fullname: Gurbuz, Sevgi Zubeyde email: szgurbuz@ua.edu organization: Dept. of Electr. & Comput. Eng., Univ. of Alabama, Tuscaloosa, AL, USA |
| BookMark | eNp9kDFPwzAQhS0EEm3hByAWS8wptmPHyYhaKJVakGgRbJHrONQljYPtqIJfj0sqBgamu5O-d_fu9cFxbWoFwAVGQ4xRdj2bPC2GBGE-JJxjitgR6GHG0ggxjo_3PWURy9LXU9B3boMQoWnKe6AaK9XAB9VaUYXid8a-w2mtvRaV_hJemxrOlV-bwsHSWDjX0ppobJqmUhaOKuGcLrXswBft13BmdnBpha51_QYXYhtAuGibxlh_Bk5KUTl1fqgD8Hx3uxzdR7PHyXR0M4skyWIfUZlgpQjLMBGrFceJRFShlBOSUcXSuGByRZFAMk7KMJYFQwUvsjARmbIiiQfgqtvbWPPRKufzjWltHU7mOOOU0phiEijeUeEj56wqc6n9zyM-2K9yjPJ9tPk-2nwfbX6INijxH2Vj9VbYz381l51GK6V--RQHQ3EcfwNmaodK |
| CODEN | IGRSBY |
| CitedBy_id | crossref_primary_10_1109_LGRS_2024_3354973 crossref_primary_10_3390_electronics14163264 crossref_primary_10_1109_JSEN_2021_3100635 crossref_primary_10_3390_app12020633 crossref_primary_10_1109_TAES_2018_2883847 crossref_primary_10_1109_TCSII_2023_3328422 crossref_primary_10_1109_JSEN_2021_3078339 crossref_primary_10_1109_MAES_2021_3140064 crossref_primary_10_1109_TAES_2021_3139848 crossref_primary_10_1002_mop_32125 crossref_primary_10_1080_01431161_2020_1766149 crossref_primary_10_1109_LGRS_2019_2930636 crossref_primary_10_1109_ACCESS_2021_3061424 crossref_primary_10_1109_JSEN_2022_3162590 crossref_primary_10_1109_JSEN_2022_3210956 crossref_primary_10_1109_TCCN_2020_2999811 crossref_primary_10_1109_JSEN_2022_3141213 crossref_primary_10_1109_LSENS_2021_3061561 crossref_primary_10_1016_j_measurement_2024_114939 crossref_primary_10_1109_JMW_2025_3575723 crossref_primary_10_1049_rsn2_12182 crossref_primary_10_1049_iet_rsn_2018_0103 crossref_primary_10_3390_electronics14050875 crossref_primary_10_1109_TGRS_2021_3105124 crossref_primary_10_1109_ACCESS_2018_2857007 crossref_primary_10_1038_s41598_023_30631_x crossref_primary_10_3390_rs11091068 crossref_primary_10_1109_LGRS_2019_2917301 crossref_primary_10_1049_iet_rsn_2019_0044 crossref_primary_10_1109_MSP_2018_2890128 crossref_primary_10_3390_rs16173121 crossref_primary_10_1049_iet_rsn_2019_0240 crossref_primary_10_1109_LGRS_2022_3173951 crossref_primary_10_1109_ACCESS_2019_2943567 crossref_primary_10_3103_S1068335621100080 crossref_primary_10_1016_j_dsp_2019_01_013 crossref_primary_10_1109_TAES_2020_2969579 crossref_primary_10_1049_iet_rsn_2018_5054 crossref_primary_10_1109_ACCESS_2024_3370671 crossref_primary_10_1109_JSEN_2019_2895538 crossref_primary_10_1109_LGRS_2020_3045176 crossref_primary_10_1109_MSP_2019_2926573 crossref_primary_10_1109_JSTARS_2021_3073678 crossref_primary_10_1109_LGRS_2020_2974821 crossref_primary_10_1109_JIOT_2021_3063504 crossref_primary_10_1109_ACCESS_2020_2971064 crossref_primary_10_1109_TGRS_2021_3100482 crossref_primary_10_1109_TIM_2023_3238749 crossref_primary_10_3390_s20195466 crossref_primary_10_1109_LGRS_2023_3321216 crossref_primary_10_1016_j_asoc_2024_112316 crossref_primary_10_1109_LGRS_2019_2942097 crossref_primary_10_1049_iet_rsn_2019_0493 crossref_primary_10_1109_TNNLS_2021_3055991 crossref_primary_10_1109_JSEN_2020_2971626 crossref_primary_10_1109_JSEN_2023_3327963 crossref_primary_10_1109_LSENS_2019_2896072 crossref_primary_10_1515_freq_2022_0237 crossref_primary_10_7717_peerj_cs_782 crossref_primary_10_1049_rsn2_12161 crossref_primary_10_3390_electronics11010156 crossref_primary_10_3390_s20123504 crossref_primary_10_3390_s21144772 crossref_primary_10_1109_TAP_2022_3172759 crossref_primary_10_1109_TMTT_2024_3441591 crossref_primary_10_1109_TMTT_2024_3473317 |
| Cites_doi | 10.1109/ACCESS.2016.2617282 10.1109/TAES.2014.130082 10.1109/LGRS.2014.2311819 10.1109/TPAMI.2013.50 10.1109/ICASSP.2017.7952265 10.1109/TPAMI.2012.231 10.1109/CVPR.2015.7298594 10.1109/MILCOM.2016.7795448 10.1038/nature14539 10.1109/LGRS.2016.2539386 10.1109/MRRS.2011.6053628 10.1109/TGRS.2009.2012849 10.1109/RADAR.2016.7485147 10.1109/ACCESS.2017.2689058 10.3390/s16121990 10.1109/ICCV.2011.6126474 10.1109/LGRS.2015.2491329 10.1007/978-3-642-25085-9_33 10.1109/TKDE.2009.191 10.1109/LGRS.2014.2336231 |
| ContentType | Journal Article |
| Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2017 |
| Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2017 |
| DBID | 97E RIA RIE AAYXX CITATION 7SC 7SP 7TG 7UA 8FD C1K F1W FR3 H8D H96 JQ2 KL. KR7 L.G L7M L~C L~D |
| DOI | 10.1109/LGRS.2017.2771405 |
| DatabaseName | IEEE All-Society Periodicals Package (ASPP) 2005-present IEEE All-Society Periodicals Package (ASPP) 1998-Present IEEE Electronic Library (IEL) CrossRef Computer and Information Systems Abstracts Electronics & Communications Abstracts Meteorological & Geoastrophysical Abstracts Water Resources Abstracts Technology Research Database Environmental Sciences and Pollution Management ASFA: Aquatic Sciences and Fisheries Abstracts Engineering Research Database Aerospace Database Aquatic Science & Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy & Non-Living Resources ProQuest Computer Science Collection Meteorological & Geoastrophysical Abstracts - Academic Civil Engineering Abstracts Aquatic Science & Fisheries Abstracts (ASFA) Professional Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional |
| DatabaseTitle | CrossRef Civil Engineering Abstracts Aquatic Science & Fisheries Abstracts (ASFA) Professional Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Water Resources Abstracts Environmental Sciences and Pollution Management Computer and Information Systems Abstracts Professional Aerospace Database Meteorological & Geoastrophysical Abstracts Aquatic Science & Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy & Non-Living Resources ASFA: Aquatic Sciences and Fisheries Abstracts Engineering Research Database Advanced Technologies Database with Aerospace Meteorological & Geoastrophysical Abstracts - Academic |
| DatabaseTitleList | Civil Engineering Abstracts |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Geography Geology |
| EISSN | 1558-0571 |
| EndPage | 2466 |
| ExternalDocumentID | 10_1109_LGRS_2017_2771405 8119733 |
| Genre | orig-research |
| GroupedDBID | 0R~ 29I 4.4 5GY 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACIWK AENEX AETIX AFRAH AGQYO AGSQL AHBIQ AIBXA AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 EBS EJD HZ~ H~9 IFIPE IPLJI JAVBF LAI M43 O9- OCL P2P RIA RIE RNS ~02 AAYXX CITATION 7SC 7SP 7TG 7UA 8FD C1K F1W FR3 H8D H96 JQ2 KL. KR7 L.G L7M L~C L~D RIG |
| ID | FETCH-LOGICAL-c293t-4c61ee25912abb716c04e0872294e583d5cb40a0c36f583fd50d7d936f2c85d63 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 97 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000418116500059&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1545-598X |
| IngestDate | Mon Jun 30 08:31:50 EDT 2025 Sat Nov 29 05:53:54 EST 2025 Tue Nov 18 22:18:55 EST 2025 Tue Aug 26 17:04:00 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 12 |
| Language | English |
| License | https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c293t-4c61ee25912abb716c04e0872294e583d5cb40a0c36f583fd50d7d936f2c85d63 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| ORCID | 0000-0001-7487-9087 |
| PQID | 1974443412 |
| PQPubID | 75725 |
| PageCount | 5 |
| ParticipantIDs | crossref_citationtrail_10_1109_LGRS_2017_2771405 crossref_primary_10_1109_LGRS_2017_2771405 ieee_primary_8119733 proquest_journals_1974443412 |
| PublicationCentury | 2000 |
| PublicationDate | 2017-12-01 |
| PublicationDateYYYYMMDD | 2017-12-01 |
| PublicationDate_xml | – month: 12 year: 2017 text: 2017-12-01 day: 01 |
| PublicationDecade | 2010 |
| PublicationPlace | Piscataway |
| PublicationPlace_xml | – name: Piscataway |
| PublicationTitle | IEEE geoscience and remote sensing letters |
| PublicationTitleAbbrev | LGRS |
| PublicationYear | 2017 |
| Publisher | IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Publisher_xml | – name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| References | ref13 ref12 ref14 krizhevsky (ref19) 2012 ref11 seyfio?lu (ref10) 2017 chollet (ref30) 2015 kim (ref4) 2009; 47 ref2 ref1 ref17 ref18 bengio (ref21) 2007; 19 ref24 ref23 trommel (ref15) 2016 simonyan (ref20) 2014 erhan (ref22) 2010; 11 ref25 abadi (ref31) 2016 ref28 simonyan (ref32) 2014 ref27 srivastava (ref26) 2014; 15 ref8 ref7 ref9 ref6 kingma (ref29) 2015 ref5 bengio (ref16) 2007; 34 kim (ref3) 2015; 12 |
| References_xml | – start-page: 81 year: 2016 ident: ref15 article-title: Multi-target human gait classification using deep convolutional neural networks on micro-Doppler spectrograms publication-title: Proc Eur Radar Conf – ident: ref14 doi: 10.1109/ACCESS.2016.2617282 – start-page: 1 year: 2015 ident: ref29 article-title: Adam: A method for stochastic optimization publication-title: Proc Int Conf Learn Represent – ident: ref8 doi: 10.1109/TAES.2014.130082 – ident: ref7 doi: 10.1109/LGRS.2014.2311819 – ident: ref27 doi: 10.1109/TPAMI.2013.50 – ident: ref23 doi: 10.1109/ICASSP.2017.7952265 – ident: ref2 doi: 10.1109/TPAMI.2012.231 – ident: ref25 doi: 10.1109/CVPR.2015.7298594 – ident: ref13 doi: 10.1109/MILCOM.2016.7795448 – ident: ref1 doi: 10.1038/nature14539 – ident: ref9 doi: 10.1109/LGRS.2016.2539386 – volume: 11 start-page: 625 year: 2010 ident: ref22 article-title: Why does unsupervised pre-training help deep learning? publication-title: J Mach Learn Res – start-page: 1097 year: 2012 ident: ref19 article-title: ImageNet classification with deep convolutional neural networks publication-title: Proc Adv Neural Inf Process Syst – ident: ref5 doi: 10.1109/MRRS.2011.6053628 – volume: 47 start-page: 1328 year: 2009 ident: ref4 article-title: Human activity classification based on micro-Doppler signatures using a support vector machine publication-title: IEEE Trans Geosci Remote Sens doi: 10.1109/TGRS.2009.2012849 – ident: ref12 doi: 10.1109/RADAR.2016.7485147 – ident: ref24 doi: 10.1109/ACCESS.2017.2689058 – year: 2015 ident: ref30 publication-title: Keras – start-page: 1125 year: 2017 ident: ref10 article-title: Deep learning of micro-Doppler features for aided and unaided gait recognition publication-title: Proc IEEE Radar Conf – ident: ref18 doi: 10.3390/s16121990 – ident: ref28 doi: 10.1109/ICCV.2011.6126474 – start-page: 265 year: 2016 ident: ref31 article-title: TensorFlow: Large-scale machine learning on heterogeneous distributed systems publication-title: Proc 11th USENIX Conf Oper Syst Design Implement – ident: ref11 doi: 10.1109/LGRS.2015.2491329 – ident: ref6 doi: 10.1007/978-3-642-25085-9_33 – volume: 15 start-page: 1929 year: 2014 ident: ref26 article-title: Dropout: A simple way to prevent neural networks from overfitting publication-title: J Mach Learn Res – ident: ref17 doi: 10.1109/TKDE.2009.191 – year: 2014 ident: ref32 article-title: Deep inside convolutional networks: Visualising image classification models and saliency maps publication-title: Proc Int Conf Learn Represent – volume: 19 start-page: 153 year: 2007 ident: ref21 article-title: Greedy layer-wise training of deep networks publication-title: Advances in neural information processing systems – volume: 12 start-page: 289 year: 2015 ident: ref3 article-title: Human detection using Doppler radar based on physical characteristics of targets publication-title: IEEE Geosci Remote Sens Lett doi: 10.1109/LGRS.2014.2336231 – volume: 34 start-page: 1 year: 2007 ident: ref16 article-title: Scaling learning algorithms towards AI publication-title: Large Scale Kernel Machines – start-page: 1 year: 2014 ident: ref20 article-title: Very deep convolutional networks for large-scale image recognition publication-title: Proc Int Conf Learn Represent |
| SSID | ssj0024887 |
| Score | 2.523142 |
| Snippet | Deep neural networks (DNNs) require large-scale labeled data sets to prevent overfitting while having good generalization. In radar applications, however,... |
| SourceID | proquest crossref ieee |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 2462 |
| SubjectTerms | Artificial neural networks Classification Convolutional autoencoders (CAEs) convolutional neural networks (CNN) Data Data acquisition Data transfer (computers) Datasets Decoding Doppler sonar Feature extraction gait classification Learning Manpower micro-Doppler Model accuracy Neural networks Radar Radar imaging Radar signatures Spectrogram Training Transfer learning vGGNet |
| Title | Deep Neural Network Initialization Methods for Micro-Doppler Classification With Low Training Sample Support |
| URI | https://ieeexplore.ieee.org/document/8119733 https://www.proquest.com/docview/1974443412 |
| Volume | 14 |
| WOSCitedRecordID | wos000418116500059&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 1558-0571 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0024887 issn: 1545-598X databaseCode: RIE dateStart: 20040101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3fT9swED4BGmIvsPFDK4PJD3uaCLhJHNuP0_ixSaWaBht9ixz7KpCqFrVlE__97hzTCYGQ9hYr5yjKJb7vcp_vA_iYK8yHQ8NUKXQZRShH66A1maNcwlEAlCZWz3_1dL9vBgP7fQkOFnthEDGSz_CQD2MtP0z8Hf8qOzJc8yqKZVjWWrd7tf711TNRDI8RQaasGaQKZlfao97ZjwsmcenDXHN_OvUoBkVRlScrcQwvpxv_d2NvYD3BSPG59ftbWMLxJqwlRfPr-01YPYuSvfdbMDpGvBXchIMm9FvWt_jGnCE3SpswxXnUkZ4JQrDinCl62fGE4ClORRTNZDpRa3h1M78WvckfcZmkJcSF4_7CgtVBCclvw8_Tk8svX7OksZB5CvTzrPRVF5FyoG7umoaSJy9LlEbnuS1RmSIo35TSSV9UQxoOg5JBB0uj3BsVqmIHVsaTMb4DQUBQoSLE4kJTNtLZyrsiOK-NrJwNqgPy4anXPjUgZx2MUR0TEWlrdlTNjqqTozrwaTHltu2-8ZLxFntmYZic0oG9B9fW6fuc1XSmLEuK4Pnu87Pew2u-dktc2YOV-fQO9-GV_z2_mU0_xFfvL-_G1a4 |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3fb9MwED6NMTReGNtAFDbww54Q2VzHTuxHxNgPkVYTK9C3yLGv2qSqndpu0_57fI5XhJgm8RYrZyXKJb7vcp_vA9gTCsVopIkqhTYLEcqGddDozIZcwoYAyHWsnv-syn5fD4fmbAU-LffCIGIkn-E-HcZavp-6a_pVdqCp5pXnT-CpklJ0291afzrr6SiHR5ggU0YPUw2zy81Bdfz9nGhc5b4oqUOd-isKRVmVf9biGGCONv7v1l7CiwQk2efW85uwgpMtWE-a5hd3W_DsOIr23m3D-BDxilEbjjCh3_K-2Smxhuw4bcNkvagkPWcBw7IekfSyw2kAqDhjUTaTCEWt4a_LxQWrprdskMQl2LmlDsOM9EEDln8FP46-Dr6cZEllIXMh1C8y6YouYsiCusI2TUifHJfIdSmEkah07pVrJLfc5cUoDEdecV96E0bCaeWL_DWsTqYTfAMsQEGFKmAW6xvZcGsKZ3NvXal5YY1XHeD3T712qQU5KWGM65iKcFOTo2pyVJ0c1YGPyylXbf-Nx4y3yTNLw-SUDuzcu7ZOX-i8DmeklCGGi7cPz_oA6yeDXlVXp_1v7-A5XaelsezA6mJ2jbuw5m4Wl_PZ-_ga_gY0C9j1 |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Deep+Neural+Network+Initialization+Methods+for+Micro-Doppler+Classification+With+Low+Training+Sample+Support&rft.jtitle=IEEE+geoscience+and+remote+sensing+letters&rft.au=Seyfioglu%2C+Mehmet+Saygin&rft.au=Gurbuz%2C+Sevgi+Zubeyde&rft.date=2017-12-01&rft.issn=1545-598X&rft.eissn=1558-0571&rft.volume=14&rft.issue=12&rft.spage=2462&rft.epage=2466&rft_id=info:doi/10.1109%2FLGRS.2017.2771405&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_LGRS_2017_2771405 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1545-598X&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1545-598X&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1545-598X&client=summon |