Applying Deep Learning Networks to Identify Optimized Paths in Gymnastic Movement Techniques

The study adopts the OpenPose algorithm in deep learning to extract and recognize gymnastics movements, and it initially constructs the OpenPose gymnastics movement recognition model. The MobileNet-V3 network is introduced to replace VGG-19, which was the feature extraction network in the original m...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Applied mathematics and nonlinear sciences Ročník 10; číslo 1
Hlavní autori: Mo, Dan, Wang, Yintong, Zhang, Bowen
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Beirut Sciendo 01.01.2025
De Gruyter Brill Sp. z o.o., Paradigm Publishing Services
Predmet:
ISSN:2444-8656, 2444-8656
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract The study adopts the OpenPose algorithm in deep learning to extract and recognize gymnastics movements, and it initially constructs the OpenPose gymnastics movement recognition model. The MobileNet-V3 network is introduced to replace VGG-19, which was the feature extraction network in the original model, in order to optimize the accuracy of OpenPose in recognizing gymnastics actions and to construct an OpenPose-MobileNet-V3 gymnastics action recognition model. The original model is compared with the optimized OpenPose-MobileNet-V3 model for comparison experiments in action recognition, and then the OpenPose-MobileNet-V3 model is compared with other recognition models to examine its effectiveness in action recognition. Finally, the parameter sensitivities of MobileNet-V3 and cosine annealing strategies are compared to explore the optimization effect of the two strategies on the OpenPose model.The OpenPose-MobileNet-V3 algorithm improves its recognition accuracy by 6.857% over the pre-optimization OpenPose algorithm.The recognition accuracy of the OpenPose-MobileNet-V3 is improved by 6.857% on the two datasets, which have accuracies of 95.786% and 94.572%, respectively, which are significantly better than other recognition models. The cosine annealing strategy-trained model is 2.143 percentage points less accurate than the OpenPose-MobileNet-V3 model at recognizing gymnastics movements, and MobileNet-V3 is better optimized.
AbstractList The study adopts the OpenPose algorithm in deep learning to extract and recognize gymnastics movements, and it initially constructs the OpenPose gymnastics movement recognition model. The MobileNet-V3 network is introduced to replace VGG-19, which was the feature extraction network in the original model, in order to optimize the accuracy of OpenPose in recognizing gymnastics actions and to construct an OpenPose-MobileNet-V3 gymnastics action recognition model. The original model is compared with the optimized OpenPose-MobileNet-V3 model for comparison experiments in action recognition, and then the OpenPose-MobileNet-V3 model is compared with other recognition models to examine its effectiveness in action recognition. Finally, the parameter sensitivities of MobileNet-V3 and cosine annealing strategies are compared to explore the optimization effect of the two strategies on the OpenPose model.The OpenPose-MobileNet-V3 algorithm improves its recognition accuracy by 6.857% over the pre-optimization OpenPose algorithm.The recognition accuracy of the OpenPose-MobileNet-V3 is improved by 6.857% on the two datasets, which have accuracies of 95.786% and 94.572%, respectively, which are significantly better than other recognition models. The cosine annealing strategy-trained model is 2.143 percentage points less accurate than the OpenPose-MobileNet-V3 model at recognizing gymnastics movements, and MobileNet-V3 is better optimized.
Author Mo, Dan
Wang, Yintong
Zhang, Bowen
Author_xml – sequence: 1
  givenname: Dan
  surname: Mo
  fullname: Mo, Dan
  email: momo0909415@163.com
  organization: College of Sports Arts, Jilin Sport University, Changchun, Jilin, 130022, China
– sequence: 2
  givenname: Yintong
  surname: Wang
  fullname: Wang, Yintong
  organization: Graduate Office, Jilin Sport University, Changchun, Jilin, 130022, China
– sequence: 3
  givenname: Bowen
  surname: Zhang
  fullname: Zhang, Bowen
  organization: Department of Physical Education, Hebei Software Vocational and Technical College, Baoding, Hebei, 071000, China
BookMark eNptUMtOwkAUnRhMRGTrehLXxXn1tSSoSILiAncmk3kVBum0zhRJ_XrbYKILV_fcm_O4OZdg4CpnALjGaEJYmt2K0oWIIBJHiCTxGRgSxliUJXEy-IMvwDiEHUKIUEyThAzB27Su9611G3hnTA2XRnjXb8-mOVb-PcCmggttXGOLFq7qxpb2y2j4IpptgNbBeVs6ERqr4FP1acqOCNdGbZ39OJhwBc4LsQ9m_DNH4PXhfj17jJar-WI2XUYKxymOSC6xpCrXCUZCIiSJzFVGFJKx1pJhnFGV4kKhnMYiLbpDkTNtpCaIIkwNHYGbk2_tqz634bvq4F0XySnOEaMpS1jHmpxYylcheFPw2ttS-JZjxPsSeV8i70vkfYmdID8JjmLfGK_Nxh_aDvy6_y_E3VPfOvl6ZQ
Cites_doi 10.1016/j.humov.2014.01.001
10.14569/IJACSA.2024.0150113
10.3390/bioengineering9060261
10.1016/j.robot.2021.103830
10.1109/TMM.2022.3232034
10.1007/s00521-020-05632-w
10.1109/ACCESS.2018.2890150
10.1145/3343031.3350910
10.1109/TCBB.2014.2343960
10.52783/jes.1387
10.3390/app9020226
10.3390/app12104847
10.1016/j.jvcir.2024.104227
10.1109/ACCESS.2018.2817253
10.1016/j.eswa.2023.121978
10.1155/2021/1215065
10.1109/JSEN.2021.3114758
10.1007/978-3-031-62881-8_19
10.1016/j.bdr.2024.100477
ContentType Journal Article
Copyright 2025. This work is published under http://creativecommons.org/licenses/by/4.0 (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
Copyright_xml – notice: 2025. This work is published under http://creativecommons.org/licenses/by/4.0 (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
DBID AAYXX
CITATION
ABUWG
AFKRA
AZQEC
BENPR
CCPQU
DWQXO
PHGZM
PHGZT
PIMPY
PKEHL
PQEST
PQQKQ
PQUKI
PRINS
DOI 10.2478/amns-2025-0265
DatabaseName CrossRef
ProQuest Central (Alumni)
ProQuest Central UK/Ireland
ProQuest Central Essentials
ProQuest Central
ProQuest One Community College
ProQuest Central
ProQuest Central Premium
ProQuest One Academic
Publicly Available Content Database (ProQuest)
ProQuest One Academic Middle East (New)
ProQuest One Academic Eastern Edition (DO NOT USE)
ProQuest One Academic (retired)
ProQuest One Academic UKI Edition
ProQuest Central China
DatabaseTitle CrossRef
Publicly Available Content Database
ProQuest One Academic Middle East (New)
ProQuest Central Essentials
ProQuest One Academic Eastern Edition
ProQuest Central (Alumni Edition)
ProQuest One Community College
ProQuest Central China
ProQuest Central
ProQuest One Academic UKI Edition
ProQuest Central Korea
ProQuest Central (New)
ProQuest One Academic
ProQuest One Academic (New)
DatabaseTitleList
CrossRef
Publicly Available Content Database
Database_xml – sequence: 1
  dbid: PIMPY
  name: Publicly Available Content Database
  url: http://search.proquest.com/publiccontent
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Applied Sciences
EISSN 2444-8656
ExternalDocumentID 10_2478_amns_2025_0265
10_2478_amns_2025_0265101
GroupedDBID 9WM
AATOW
ABFKT
ADBLJ
AFFHD
AFKRA
AHGSO
ALMA_UNASSIGNED_HOLDINGS
AMVHM
ARCSS
BENPR
CCPQU
EBS
M~E
OK1
PHGZM
PHGZT
PIMPY
QD8
SLJYH
AAYXX
CITATION
ABUWG
AZQEC
DWQXO
PKEHL
PQEST
PQQKQ
PQUKI
PRINS
ID FETCH-LOGICAL-c1571-29b1b3c9d610ab00b2b9c82c0b5ddb41183c71fc0935a7f411f94debd203013e3
IEDL.DBID PIMPY
ISSN 2444-8656
IngestDate Sun Oct 19 01:29:23 EDT 2025
Sat Nov 29 08:01:46 EST 2025
Sat Nov 29 01:24:10 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 1
Language English
License This work is licensed under the Creative Commons Attribution 4.0 International License.
http://creativecommons.org/licenses/by/4.0
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c1571-29b1b3c9d610ab00b2b9c82c0b5ddb41183c71fc0935a7f411f94debd203013e3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
OpenAccessLink https://www.proquest.com/publiccontent/docview/3190437464?pq-origsite=%requestingapplication%
PQID 3190437464
PQPubID 6761185
PageCount 18
ParticipantIDs proquest_journals_3190437464
crossref_primary_10_2478_amns_2025_0265
walterdegruyter_journals_10_2478_amns_2025_0265101
PublicationCentury 2000
PublicationDate 2025-01-01
20250101
PublicationDateYYYYMMDD 2025-01-01
PublicationDate_xml – month: 01
  year: 2025
  text: 2025-01-01
  day: 01
PublicationDecade 2020
PublicationPlace Beirut
PublicationPlace_xml – name: Beirut
PublicationTitle Applied mathematics and nonlinear sciences
PublicationYear 2025
Publisher Sciendo
De Gruyter Brill Sp. z o.o., Paradigm Publishing Services
Publisher_xml – name: Sciendo
– name: De Gruyter Brill Sp. z o.o., Paradigm Publishing Services
References (j_amns-2025-0265_ref_009) 2022; 34
(j_amns-2025-0265_ref_005) 2021; 21
(j_amns-2025-0265_ref_002) 2018; 7
(j_amns-2025-0265_ref_015) 2019; 9
(j_amns-2025-0265_ref_001) 2014; 12
(j_amns-2025-0265_ref_010) 2024; 238
(j_amns-2025-0265_ref_016) 2018; 6
(j_amns-2025-0265_ref_008) 2021; 143
(j_amns-2025-0265_ref_004) 2014; 34
(j_amns-2025-0265_ref_017) 2022
(j_amns-2025-0265_ref_012) 2021; 2021
(j_amns-2025-0265_ref_019) 2022
(j_amns-2025-0265_ref_013) 2024; 103
(j_amns-2025-0265_ref_014) 2024; 15
(j_amns-2025-0265_ref_007) 2024; 20
(j_amns-2025-0265_ref_006) 2022; 25
2025040409092416987_j_amns-2025-0265_ref_009
2025040409092416987_j_amns-2025-0265_ref_008
2025040409092416987_j_amns-2025-0265_ref_019
2025040409092416987_j_amns-2025-0265_ref_007
2025040409092416987_j_amns-2025-0265_ref_018
2025040409092416987_j_amns-2025-0265_ref_006
2025040409092416987_j_amns-2025-0265_ref_017
2025040409092416987_j_amns-2025-0265_ref_005
2025040409092416987_j_amns-2025-0265_ref_016
2025040409092416987_j_amns-2025-0265_ref_004
2025040409092416987_j_amns-2025-0265_ref_015
2025040409092416987_j_amns-2025-0265_ref_003
2025040409092416987_j_amns-2025-0265_ref_014
2025040409092416987_j_amns-2025-0265_ref_002
2025040409092416987_j_amns-2025-0265_ref_013
2025040409092416987_j_amns-2025-0265_ref_001
2025040409092416987_j_amns-2025-0265_ref_012
2025040409092416987_j_amns-2025-0265_ref_011
2025040409092416987_j_amns-2025-0265_ref_010
References_xml – start-page: 4847
  issue: 10
  year: 2022
  end-page: 4847
  ident: j_amns-2025-0265_ref_017
  article-title: Quality Evaluation Algorithm for Chest Compressions Based on OpenPose Model
  publication-title: Applied Sciences
– volume: 20
  start-page: 880
  issue: 3
  year: 2024
  end-page: 898
  ident: j_amns-2025-0265_ref_007
  article-title: 3D Convolutional Neural Networks based Movement Evaluation System for Gymnasts in Computer Vision Applications
  publication-title: Journal of Electrical Systems
– volume: 12
  start-page: 103
  issue: 1
  year: 2014
  end-page: 112
  ident: j_amns-2025-0265_ref_001
  article-title: A deep learning network approach to ab initio protein secondary structure prediction
  publication-title: IEEE/ACM transactions on computational biology and bioinformatics
– volume: 21
  start-page: 24531
  issue: 21
  year: 2021
  end-page: 24539
  ident: j_amns-2025-0265_ref_005
  article-title: Quantitative evaluation of gymnastics based on multiple MEMS sensors
  publication-title: IEEE Sensors Journal
– volume: 143
  start-page: 103830
  year: 2021
  ident: j_amns-2025-0265_ref_008
  article-title: Visual recognition of gymnastic exercise sequences
  publication-title: Application to supervision and robot learning by demonstration. Robotics and Autonomous Systems
– volume: 25
  start-page: 7943
  year: 2022
  end-page: 7966
  ident: j_amns-2025-0265_ref_006
  article-title: A survey on video action recognition in sports: Datasets, methods and applications
  publication-title: IEEE Transactions on Multimedia
– volume: 15
  issue: 1
  year: 2024
  ident: j_amns-2025-0265_ref_014
  article-title: Application Effect of Human-Computer Interactive Gymnastic Sports Action Recognition System Based on PTP-CNN Algorithm
  publication-title: International Journal of Advanced Computer Science & Applications
– volume: 7
  start-page: 7823
  year: 2018
  end-page: 7859
  ident: j_amns-2025-0265_ref_002
  article-title: FPGA-based accelerators of deep learning networks for learning and classification: A review
  publication-title: ieee Access
– volume: 6
  start-page: 17913
  year: 2018
  end-page: 17922
  ident: j_amns-2025-0265_ref_016
  article-title: Human action recognition by learning spatio-temporal features with deep neural networks
  publication-title: IEEE access
– volume: 103
  start-page: 104227
  year: 2024
  ident: j_amns-2025-0265_ref_013
  article-title: Design and optimization of an aerobics movement recognition system based on high-dimensional biotechnological data using neural networks
  publication-title: Journal of Visual Communication and Image Representation
– start-page: 261
  issue: 6
  year: 2022
  end-page: 261
  ident: j_amns-2025-0265_ref_019
  article-title: BM-Net: CNN-Based MobileNet-V3 and Bilinear Structure for Breast Cancer Detection in Whole Slide Images
  publication-title: Bioengineering
– volume: 34
  start-page: 3337
  issue: 5
  year: 2022
  end-page: 3348
  ident: j_amns-2025-0265_ref_009
  article-title: Aerobics posture recognition based on neural network and sensors
  publication-title: Neural Computing and Applications
– volume: 2021
  start-page: 1215065
  issue: 1
  year: 2021
  ident: j_amns-2025-0265_ref_012
  article-title: Trampoline motion decomposition method based on deep learning image recognition
  publication-title: Scientific Programming
– volume: 238
  start-page: 121978
  year: 2024
  ident: j_amns-2025-0265_ref_010
  article-title: Image expression of time series data of wearable IMU sensor and fusion classification of gymnastics action
  publication-title: Expert Systems with Applications
– volume: 9
  start-page: 226
  issue: 2
  year: 2019
  ident: j_amns-2025-0265_ref_015
  article-title: Wearables, biomechanical feedback, and human motor-skills’ learning & optimization
  publication-title: Applied Sciences
– volume: 34
  start-page: 63
  year: 2014
  end-page: 80
  ident: j_amns-2025-0265_ref_004
  article-title: Automatic recognition and scoring of olympic rhythmic gymnastic movements
  publication-title: Human movement science
– ident: 2025040409092416987_j_amns-2025-0265_ref_004
  doi: 10.1016/j.humov.2014.01.001
– ident: 2025040409092416987_j_amns-2025-0265_ref_014
  doi: 10.14569/IJACSA.2024.0150113
– ident: 2025040409092416987_j_amns-2025-0265_ref_019
  doi: 10.3390/bioengineering9060261
– ident: 2025040409092416987_j_amns-2025-0265_ref_008
  doi: 10.1016/j.robot.2021.103830
– ident: 2025040409092416987_j_amns-2025-0265_ref_006
  doi: 10.1109/TMM.2022.3232034
– ident: 2025040409092416987_j_amns-2025-0265_ref_009
  doi: 10.1007/s00521-020-05632-w
– ident: 2025040409092416987_j_amns-2025-0265_ref_002
  doi: 10.1109/ACCESS.2018.2890150
– ident: 2025040409092416987_j_amns-2025-0265_ref_003
  doi: 10.1145/3343031.3350910
– ident: 2025040409092416987_j_amns-2025-0265_ref_001
  doi: 10.1109/TCBB.2014.2343960
– ident: 2025040409092416987_j_amns-2025-0265_ref_007
  doi: 10.52783/jes.1387
– ident: 2025040409092416987_j_amns-2025-0265_ref_015
  doi: 10.3390/app9020226
– ident: 2025040409092416987_j_amns-2025-0265_ref_017
  doi: 10.3390/app12104847
– ident: 2025040409092416987_j_amns-2025-0265_ref_013
  doi: 10.1016/j.jvcir.2024.104227
– ident: 2025040409092416987_j_amns-2025-0265_ref_016
  doi: 10.1109/ACCESS.2018.2817253
– ident: 2025040409092416987_j_amns-2025-0265_ref_010
  doi: 10.1016/j.eswa.2023.121978
– ident: 2025040409092416987_j_amns-2025-0265_ref_012
  doi: 10.1155/2021/1215065
– ident: 2025040409092416987_j_amns-2025-0265_ref_005
  doi: 10.1109/JSEN.2021.3114758
– ident: 2025040409092416987_j_amns-2025-0265_ref_011
  doi: 10.1007/978-3-031-62881-8_19
– ident: 2025040409092416987_j_amns-2025-0265_ref_018
  doi: 10.1016/j.bdr.2024.100477
SSID ssj0002313662
Score 2.2783735
Snippet The study adopts the OpenPose algorithm in deep learning to extract and recognize gymnastics movements, and it initially constructs the OpenPose gymnastics...
SourceID proquest
crossref
walterdegruyter
SourceType Aggregation Database
Index Database
Publisher
SubjectTerms 68T07
Accuracy
Algorithms
Deep learning
Gymnastics
Gymnastics action recognition
MobileNet-V3 network
OpenPose algorithm
Title Applying Deep Learning Networks to Identify Optimized Paths in Gymnastic Movement Techniques
URI https://reference-global.com/article/10.2478/amns-2025-0265
https://www.proquest.com/docview/3190437464
Volume 10
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 2444-8656
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002313662
  issn: 2444-8656
  databaseCode: M~E
  dateStart: 20160101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
– providerCode: PRVPQU
  databaseName: AUTh Library subscriptions: ProQuest Central
  customDbUrl:
  eissn: 2444-8656
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002313662
  issn: 2444-8656
  databaseCode: BENPR
  dateStart: 20160101
  isFulltext: true
  titleUrlDefault: https://www.proquest.com/central
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Publicly Available Content Database
  customDbUrl:
  eissn: 2444-8656
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002313662
  issn: 2444-8656
  databaseCode: PIMPY
  dateStart: 20160101
  isFulltext: true
  titleUrlDefault: http://search.proquest.com/publiccontent
  providerName: ProQuest
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LT9tAEB7RpIdeoLQgQinaA1JPVrwPv06ItrwOBAuBRCUky_twlEOcEBtQ-PXdsdcNqhAnritrZO28Z3a-ATgQfmFCRbUXKR14QgWBJ2Uee4LmXLGCG0N1s2wiGo3i29skdePRlXtW2dnExlC3aM_4btsa4aGeKayYD63gICiPCMXh_N7DHVLYa3ULNT5AH4G3_B700_OL9M-_mouNZXgYsha7kYkoHubTsrKCwnBKGf3LS9-0CjjXn5rWtTbjxcOy7lqljQc62Xjff_8M6y4SJUet6GzCmim_wIaLSonT-eor3OERDkOR38bMiQNkHZNR-4C8IvWMtOO-xZJcWgs0nTxbAqkNLSsyKcnpclrmiAZNLmYNOHlNrjvg2GoLbk6Or3-deW4ng6doEFGPJZJKrhJtw67cqqxkMlExU74MtJbCpitcRbRQ2F_No8IeFInQRmqGuRc3fBt65aw0O0AoL4TmoQi5VKKIw9yXOdOxzdWRjE8H8KPjRjZvoTcym7Ig3zLkW4Z8y5BvA9jr7j1zKlhlq2seAPuPgauvXido7dTu2zS_wadWbLAYswe9evFgvsNH9VhPqsU-9H8ej9KrfSeAfwEBUe0k
linkProvider ProQuest
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1Z1LT9tAEMdHNFQqF0IfiFAoe2jVk4X34dcBIQQFIkiaQypRqZLrfTjKIU6IDVH6ofiM7PjRVFXFjUOvK2ske36a_e-OZwbgo3BT4yuqnUBpzxHK8xwpk9ARNOGKpdwYqsthE0G_H97cRIM1eGhqYfC3yiYmloFaTxXekR9aVLANj_DF8ezWwalRmF1tRmhUWFyZ5cIe2fKj7pn17yfGzr8MTy-deqqAo6gXUIdFkkquIm2FQ2Khk0xGKmTKlZ7WUljBzVVAU4UZwiRI7UIaCW2kZnh64IZbuy9gXVjY3RasD7q9wffftzpWLXHfZ1V3SCaC8DCZZLlFkWEdNO5gf-5-K0m7uSiT49qM5nfLoknGlnvceft_-zpbsFmraXJS4f8a1kz2Btq1siZ13Mrfwg9cwoIucmbMjNRNZUekX_0En5NiSqqS5XRJvtooOhn_sgYGVh7nZJyRi-UkS7CjNelNywbrBRk2zW_zd_DtWd5xG1rZNDM7QChPhea-8LlUIg39xJUJ02EgGJpxaQc-N_6OZ1X7kNgeu5CMGMmIkYwYyejAXuPZuA4jebxyawfYX4isnvq3QRtrd5-2eQCvLoe96_i62796DxsVpHi5tAetYn5n9uGlui_G-fxDjTmBn8_NziNwyDwE
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=Applying+Deep+Learning+Networks+to+Identify+Optimized+Paths+in+Gymnastic+Movement+Techniques&rft.jtitle=Applied+mathematics+and+nonlinear+sciences&rft.au=Mo%2C+Dan&rft.au=Wang%2C+Yintong&rft.au=Zhang%2C+Bowen&rft.date=2025-01-01&rft.issn=2444-8656&rft.eissn=2444-8656&rft.volume=10&rft.issue=1&rft_id=info:doi/10.2478%2Famns-2025-0265&rft.externalDBID=n%2Fa&rft.externalDocID=10_2478_amns_2025_0265
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2444-8656&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2444-8656&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2444-8656&client=summon