Feature fusion strategy and improved GhostNet for accurate recognition of fish feeding behavior
•An LC-GhostNet lightweight network based on the GhostNet is proposed.•Fusion of Mel spectrogram, STFT feature map, and CQT feature map.•The method can quantify the feeding behavior of fish into four classes.•The feature fusion accuracy reaches 97.941%, which is higher than a single feature. In aqua...
Uložené v:
| Vydané v: | Computers and electronics in agriculture Ročník 214; s. 108310 |
|---|---|
| Hlavní autori: | , , , , , , , |
| Médium: | Journal Article |
| Jazyk: | English |
| Vydavateľské údaje: |
Elsevier B.V
01.11.2023
|
| Predmet: | |
| ISSN: | 0168-1699, 1872-7107 |
| On-line prístup: | Získať plný text |
| Tagy: |
Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
|
| Abstract | •An LC-GhostNet lightweight network based on the GhostNet is proposed.•Fusion of Mel spectrogram, STFT feature map, and CQT feature map.•The method can quantify the feeding behavior of fish into four classes.•The feature fusion accuracy reaches 97.941%, which is higher than a single feature.
In aquaculture, accurate detection of fish feeding intensity is a critical step for establishing an on-demand feeding system. In this paper, a novel fish feeding intensity detection method based on the fusion of multiple features (Mel spectrogram, STFT, and CQT feature map) and the LC-GhostNet lightweight network was proposed as an experimental object with Oplegnathus. First, a dataset of feeding sounds of Oplegnathus punctatus was built, in which there are four types: “strong”, “medium”, “weak” and “none”. Next, the Mel, STFT, and CQT feature maps of the feeding sound were extracted using the Librosa library, and then these feature maps were fused by feature image stitching. Lastly, the fused audio feature maps were fed to LC-GhostNet for further feature extraction and classification. Experimental results indicated that the accuracy of the fused feature maps was 97.941% when used as input, which was 4.053%, 7.207%, and 3.003% higher than that of the single feature Mel, STFT, and CQT, respectively. The method proposed in this paper is more lightweight and effective than the mainstream methods, and the accuracy has been improved. Based on this automatic and non-destructive method of obtaining fish feeding information, feeding decisions can be effectively optimized. |
|---|---|
| AbstractList | In aquaculture, accurate detection of fish feeding intensity is a critical step for establishing an on-demand feeding system. In this paper, a novel fish feeding intensity detection method based on the fusion of multiple features (Mel spectrogram, STFT, and CQT feature map) and the LC-GhostNet lightweight network was proposed as an experimental object with Oplegnathus. First, a dataset of feeding sounds of Oplegnathus punctatus was built, in which there are four types: “strong”, “medium”, “weak” and “none”. Next, the Mel, STFT, and CQT feature maps of the feeding sound were extracted using the Librosa library, and then these feature maps were fused by feature image stitching. Lastly, the fused audio feature maps were fed to LC-GhostNet for further feature extraction and classification. Experimental results indicated that the accuracy of the fused feature maps was 97.941% when used as input, which was 4.053%, 7.207%, and 3.003% higher than that of the single feature Mel, STFT, and CQT, respectively. The method proposed in this paper is more lightweight and effective than the mainstream methods, and the accuracy has been improved. Based on this automatic and non-destructive method of obtaining fish feeding information, feeding decisions can be effectively optimized. •An LC-GhostNet lightweight network based on the GhostNet is proposed.•Fusion of Mel spectrogram, STFT feature map, and CQT feature map.•The method can quantify the feeding behavior of fish into four classes.•The feature fusion accuracy reaches 97.941%, which is higher than a single feature. In aquaculture, accurate detection of fish feeding intensity is a critical step for establishing an on-demand feeding system. In this paper, a novel fish feeding intensity detection method based on the fusion of multiple features (Mel spectrogram, STFT, and CQT feature map) and the LC-GhostNet lightweight network was proposed as an experimental object with Oplegnathus. First, a dataset of feeding sounds of Oplegnathus punctatus was built, in which there are four types: “strong”, “medium”, “weak” and “none”. Next, the Mel, STFT, and CQT feature maps of the feeding sound were extracted using the Librosa library, and then these feature maps were fused by feature image stitching. Lastly, the fused audio feature maps were fed to LC-GhostNet for further feature extraction and classification. Experimental results indicated that the accuracy of the fused feature maps was 97.941% when used as input, which was 4.053%, 7.207%, and 3.003% higher than that of the single feature Mel, STFT, and CQT, respectively. The method proposed in this paper is more lightweight and effective than the mainstream methods, and the accuracy has been improved. Based on this automatic and non-destructive method of obtaining fish feeding information, feeding decisions can be effectively optimized. |
| ArticleNumber | 108310 |
| Author | Wang, Cong Xu, Xianbao Liu, Xiaohang Bai, Zhuangzhuang Li, Wanchao Hu, Yang Li, Daoliang Du, Zhuangzhuang |
| Author_xml | – sequence: 1 givenname: Zhuangzhuang surname: Du fullname: Du, Zhuangzhuang email: dzz643@cau.edu.cn organization: National Innovation Center for Digital Fishery, China Agricultural University, China – sequence: 2 givenname: Xianbao surname: Xu fullname: Xu, Xianbao email: 1184706116@qq.com organization: National Innovation Center for Digital Fishery, China Agricultural University, China – sequence: 3 givenname: Zhuangzhuang surname: Bai fullname: Bai, Zhuangzhuang email: zzbai1997@163.com organization: National Innovation Center for Digital Fishery, China Agricultural University, China – sequence: 4 givenname: Xiaohang surname: Liu fullname: Liu, Xiaohang email: lxhhaust@163.com organization: College of Information and Electrical Engineering, China Agricultural University, Beijing 100083, China – sequence: 5 givenname: Yang surname: Hu fullname: Hu, Yang email: yang_hu2000@126.com organization: National Innovation Center for Digital Fishery, China Agricultural University, China – sequence: 6 givenname: Wanchao surname: Li fullname: Li, Wanchao email: wanchao_li2023@163.com organization: College of Computer and Information Engineering, Tianjin Agricultural University, Tianjin 300392, China – sequence: 7 givenname: Cong surname: Wang fullname: Wang, Cong email: ndfic_wc@cau.edu.cn organization: National Innovation Center for Digital Fishery, China Agricultural University, China – sequence: 8 givenname: Daoliang orcidid: 0000-0002-1842-419X surname: Li fullname: Li, Daoliang email: dliangl@cau.edu.cn organization: National Innovation Center for Digital Fishery, China Agricultural University, China |
| BookMark | eNqFkEFPAjEQhRuDiYD-Aw89ellsu7BtPZgYImhC9KLnprSzUAJbbLsk_Hu7WU8edHpoZvLeZN43QoPGN4DQLSUTSmh1v5sYfzjqzYQRVuaRKCm5QEMqOCs4JXyAhlkmClpJeYVGMe5I7qXgQ6QWoFMbANdtdL7BMQWdYHPGurHYHY7Bn8Di5dbH9AYJ1z5gbUzbiXAA4zeNS53P17h2cYtrAOuaDV7DVp-cD9fostb7CDc__xh9Lp4_5i_F6n35On9aFaYsZSpsJUtuwBrO1hwk8FqadcWZllZoIoUoBawFSEY415TlmjGhrbEzwypdmXKM7vq9-eKvFmJSBxcN7Pe6Ad9GVZJpfrlmWfrQS03wMQaolXFJdylydrdXlKiOqtqpnqrqqKqeajZPf5mPwR10OP9ne-xtkBmcHAQVjYMmJ3aZYlLWu78XfAPb_5bH |
| CitedBy_id | crossref_primary_10_1016_j_compag_2024_108903 crossref_primary_10_3390_jmse12071132 crossref_primary_10_3390_jmse13050944 crossref_primary_10_1016_j_aquaeng_2025_102552 crossref_primary_10_3390_s25144374 crossref_primary_10_1016_j_wateco_2025_100008 crossref_primary_10_3390_ani14223197 crossref_primary_10_1016_j_biosystemseng_2024_08_001 crossref_primary_10_3389_fpsyg_2024_1459446 crossref_primary_10_1016_j_atech_2025_101078 crossref_primary_10_1016_j_compag_2024_109699 crossref_primary_10_1016_j_saa_2024_125653 crossref_primary_10_3390_foods14020258 crossref_primary_10_1007_s10499_025_02054_0 crossref_primary_10_3390_ani14111690 crossref_primary_10_1016_j_applanim_2025_106588 crossref_primary_10_1016_j_compag_2025_110038 crossref_primary_10_1016_j_jfoodeng_2024_112452 crossref_primary_10_1007_s11760_025_04139_y crossref_primary_10_1016_j_aquaculture_2025_742700 crossref_primary_10_1016_j_compag_2024_109367 crossref_primary_10_3389_fpls_2025_1609222 crossref_primary_10_1007_s10499_025_01913_0 crossref_primary_10_1016_j_inpa_2024_04_001 crossref_primary_10_1088_1361_6501_ae0061 |
| Cites_doi | 10.1016/j.compag.2022.106994 10.3390/app13074124 10.1016/j.aquaculture.2022.737913 10.1111/are.15317 10.1016/j.compag.2016.06.025 10.1016/j.compag.2021.106135 10.1080/09524622.2019.1606734 10.1016/j.compag.2022.107580 10.1109/ACCESS.2019.2940051 10.1109/CVPR46437.2021.01350 10.1109/EMBC.2018.8512408 10.21437/Interspeech.2019-1841 10.1016/j.aquaculture.2008.06.036 10.1002/etc.4242 10.1016/j.patcog.2007.10.026 10.1016/j.jclepro.2022.131632 10.1049/cje.2017.09.018 10.1016/j.aquaculture.2018.11.013 10.1016/j.compag.2022.106914 10.1016/j.compag.2023.107645 10.1109/TPAMI.2019.2913372 10.1016/j.aquaeng.2023.102345 10.1016/j.aquaeng.2021.102178 10.1016/j.aquaculture.2021.737326 10.1109/CVPR.2018.00291 10.1016/j.biosystemseng.2022.05.010 10.1109/TII.2022.3168887 10.1111/are.14907 10.1016/j.aquaculture.2016.06.045 10.1016/j.compag.2019.105087 10.1109/ICCV.2017.155 10.1016/j.specom.2020.12.009 10.1016/j.compag.2021.106316 10.1016/j.aquaeng.2022.102244 10.3389/fnins.2023.1183132 10.1111/raq.12546 10.1109/CVPR42600.2020.00165 10.1109/ACCESS.2020.3019529 10.1155/2016/6172453 10.13031/trans.59.11406 10.1016/j.aquaculture.2019.04.056 10.1016/j.apacoust.2020.107732 |
| ContentType | Journal Article |
| Copyright | 2023 Elsevier B.V. |
| Copyright_xml | – notice: 2023 Elsevier B.V. |
| DBID | AAYXX CITATION 7S9 L.6 |
| DOI | 10.1016/j.compag.2023.108310 |
| DatabaseName | CrossRef AGRICOLA AGRICOLA - Academic |
| DatabaseTitle | CrossRef AGRICOLA AGRICOLA - Academic |
| DatabaseTitleList | AGRICOLA |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Agriculture |
| EISSN | 1872-7107 |
| ExternalDocumentID | 10_1016_j_compag_2023_108310 S0168169923006981 |
| GroupedDBID | --K --M .DC .~1 0R~ 1B1 1RT 1~. 1~5 29F 4.4 457 4G. 5GY 5VS 6J9 7-5 71M 8P~ 9JM 9JN AABVA AACTN AAEDT AAEDW AAIAV AAIKJ AAKOC AALCJ AALRI AAOAW AAQFI AAQXK AATLK AAXUO AAYFN ABBOA ABBQC ABFNM ABFRF ABGRD ABJNI ABKYH ABLVK ABMAC ABMZM ABRWV ABXDB ABYKQ ACDAQ ACGFO ACGFS ACIUM ACIWK ACNNM ACRLP ACZNC ADBBV ADEZE ADJOM ADMUD ADQTV AEBSH AEFWE AEKER AENEX AEQOU AESVU AEXOQ AFKWA AFTJW AFXIZ AGHFR AGUBO AGYEJ AHHHB AHZHX AIALX AIEXJ AIKHN AITUG AJBFU AJOXV AJRQY ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ ANZVX AOUOD ASPBG AVWKF AXJTR AZFZN BKOJK BLXMC BNPGV CBWCG CS3 DU5 EBS EFJIC EFLBG EJD EO8 EO9 EP2 EP3 FDB FEDTE FGOYB FIRID FNPLU FYGXN G-2 G-Q GBLVA GBOLZ HLV HLZ HVGLF HZ~ IHE J1W KOM LCYCR LG9 LW9 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. PQQKQ Q38 QYZTP R2- RIG ROL RPZ SAB SBC SDF SDG SES SEW SNL SPC SPCBC SSA SSH SSV SSZ T5K UHS UNMZH WUQ Y6R ~G- ~KM 9DU AAHBH AATTM AAXKI AAYWO AAYXX ABWVN ACIEU ACLOT ACMHX ACRPL ACVFH ADCNI ADNMO ADSLC AEIPS AEUPX AFJKZ AFPUW AGQPQ AGWPP AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP CITATION EFKBS ~HD 7S9 L.6 |
| ID | FETCH-LOGICAL-c339t-d6937cedc72b7e9e7f9cb672a9d8a098838eb8e92077a12222528adcd5c26a6c3 |
| ISICitedReferencesCount | 30 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001096264100001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0168-1699 |
| IngestDate | Thu Oct 02 21:44:30 EDT 2025 Tue Nov 18 21:16:39 EST 2025 Sat Nov 29 07:25:46 EST 2025 Fri Feb 23 02:35:29 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | LC-GhostNet lightweight network Feature fusion Fish feeding intensity On-demand feeding system |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c339t-d6937cedc72b7e9e7f9cb672a9d8a098838eb8e92077a12222528adcd5c26a6c3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| ORCID | 0000-0002-1842-419X |
| PQID | 3040400005 |
| PQPubID | 24069 |
| ParticipantIDs | proquest_miscellaneous_3040400005 crossref_citationtrail_10_1016_j_compag_2023_108310 crossref_primary_10_1016_j_compag_2023_108310 elsevier_sciencedirect_doi_10_1016_j_compag_2023_108310 |
| PublicationCentury | 2000 |
| PublicationDate | November 2023 2023-11-00 20231101 |
| PublicationDateYYYYMMDD | 2023-11-01 |
| PublicationDate_xml | – month: 11 year: 2023 text: November 2023 |
| PublicationDecade | 2020 |
| PublicationTitle | Computers and electronics in agriculture |
| PublicationYear | 2023 |
| Publisher | Elsevier B.V |
| Publisher_xml | – name: Elsevier B.V |
| References | Usama, Xiao, Ahmad, Wan, Hassan, Alelaiwi (b0160) 2019 Xu, Wei, Zaidi, Ren, Yang (b0185) 2021; 174 Ko, K., Park, S., Ko, H., 2018. Convolutional Feature Vectors and Support Vector Machine for Animal Sound Classification. In: 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 376-379. doi:10.1109/EMBC.2018.8512408. Fore, Alver, Alfredsen, Marafioti, Senneset, Birkevold, Terjesen (b0040) 2016; 464 Hu, Liu, Zhao, Liu, Yang, Sun, Zhou (b0075) 2021; 185 Abdar, Fahami, Rundo, Radeva, Frangi, Acharya, Nahavandi (b0005) 2023; 19 Knight, Poo Hernandez, Bayne, Bulitko, Tucker (b0095) 2019; 29 Nisar, S., Khan, O.U., Tariq, M., 2016. An Efficient Adaptive Window Size Selection Method for Improving Spectrogram Visualization. Comput. Intell. Neurosci. 6172453. Retrieved from Yin, Ji, Wang, Shen, Dai, Kou, Liang (b0200) 2023; 205 Zhang, Tao, Chuang, Zhao (b0210) 2021; 127 Han, K., Wang, Y., Tian, Q., Guo, J., Xu, C., & Xu, C. (2020). GhostNet More Features from Cheap Operations. In: IEEE Conference on Computer Vision and Pattern Recognition, 1577-1586. doi:10.1109/CVPR42600.2020.00165. Wang, Li, You, Chen, Yuan, Feng (b0165) 2022; 197 Darodes de Tailly, Keitel, Owen, Alcaraz-Calero, Alexander, Sloman (b0025) 2021; 13 Zhou, Xu, Chen, Zhang, Sun, Yang, Wang (b0220) 2019; 507 Feng, Yang, Liu, Zhao, Liu, Yan, Zhou (b0035) 2022; 98 Hamilton, Silva, Costa Filho, Peixoto (b0050) 2021; 52 Pham, L., McLoughlin, I., Phan, H., & Palaniappan, R., 2019. A Robust Framework for Acoustic Scene Classification. Paper presented at the Interspeech 2019. Du, Cui, Wang, Liu, Xu, Bai, Li (b0030) 2023; 102 Cui, Liu, Zhao, Sun, Lian, Chen, Wang (b0020) 2022; 1–6 Jiang, Liu, Wen (b0090) 2018; 27 Xiong, Xie, Feng, Wang (b0180) 2022; 352 Wei, Lin, Chen, Su, Cheng (b0175) 2020; 8 An, Hao, Wei, Wang, Yu (b0010) 2020; 52 Tu, Liu, Zhao, Yan, Zou (b0150) 2023; 13 Shen, Ji, Yin, Dai, Tu, Sun, Zhao (b0135) 2022; 197 Ye, Zhao, Han, Zhu, Li, Lu, Ruan (b0195) 2016; 59 Ubina, Cheng, Chang, Chen (b0155) 2021; 94 He, Y., Zhang, X., Sun, J., 2017. Channel Pruning for Accelerating Very Deep Neural Networks. In: 2017 IEEE International Conference on Computer Vision (ICCV), 1398-1406. doi:10.1109/ICCV.2017.155. Yang, Yu, Cheng, Mei, Duan, Li, Chen (b0190) 2021; 187 Reis, Peixoto, Soares, Rhodes, Ching, Davis (b0125) 2022; 546 Temko, Macho, Nadeu (b0145) 2008; 41 Azim, Little (b0015) 2008; 283 doi:10.1155/2016/6172453. Gui, S., Wang, H., Yang, H., Yu, C., Wang, Z., Liu, J., … Garnett, R., 2019. Model Compression with Adversarial Robustness A Unified Optimization Framework. In: 33rd Conference on Neural Information Processing Systems (NeurIPS), 32. doi:10.48550/arXiv.1902.03538. Hou, Q., Zhou, D., Feng, J., 2021. Coordinate Attention for Efficient Mobile Network Design. In: Paper presented at the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Huang, G., Liu, S., Maaten, L. v. d., & Weinberger, K.Q., 2018. CondenseNet: An Efficient DenseNet Using Learned Group Convolutions. In: Paper presented at the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Silva, Hamilton, Rocha, Borie, Travassos, Soares, Peixoto (b0140) 2019; 501 Ji, Shen, Yin, Bao, Dai, Hou, Zhao (b0085) 2022; 219 Li, Luo, Wang, Liu, Sang (b0105) 2023; 17 Måløy, Aamodt, Misimi (b0110) 2019; 167 Wang, Yu, Liu, An, Wei (b0170) 2022; 551 Zeng, Yang, Pan, Zhu, Wang, Zhao, Zhou (b0205) 2023; 204 Hu, J., Shen, L., Albanie, S., Sun, G., Wu, E., 2020. Squeeze-and-excitation networks. Saari, Corrales, Haddad, Chambliss, Brooks (b0130) 2018; 37 Zhao, Gu, Shi, Lu, Li, Shen, Zhu (b0215) 2016; 127 (8), 2011-2023. doi:10.1109/TPAMI.2019.2913372. 10.1016/j.compag.2023.108310_b0070 Ubina (10.1016/j.compag.2023.108310_b0155) 2021; 94 Knight (10.1016/j.compag.2023.108310_b0095) 2019; 29 Reis (10.1016/j.compag.2023.108310_b0125) 2022; 546 Usama (10.1016/j.compag.2023.108310_b0160) 2019 Cui (10.1016/j.compag.2023.108310_b0020) 2022; 1–6 Li (10.1016/j.compag.2023.108310_b0105) 2023; 17 Ye (10.1016/j.compag.2023.108310_b0195) 2016; 59 An (10.1016/j.compag.2023.108310_b0010) 2020; 52 Hu (10.1016/j.compag.2023.108310_b0075) 2021; 185 Ji (10.1016/j.compag.2023.108310_b0085) 2022; 219 Zeng (10.1016/j.compag.2023.108310_b0205) 2023; 204 Wei (10.1016/j.compag.2023.108310_b0175) 2020; 8 Darodes de Tailly (10.1016/j.compag.2023.108310_b0025) 2021; 13 Feng (10.1016/j.compag.2023.108310_b0035) 2022; 98 Tu (10.1016/j.compag.2023.108310_b0150) 2023; 13 Zhao (10.1016/j.compag.2023.108310_b0215) 2016; 127 Azim (10.1016/j.compag.2023.108310_b0015) 2008; 283 Zhou (10.1016/j.compag.2023.108310_b0220) 2019; 507 10.1016/j.compag.2023.108310_b0055 Hamilton (10.1016/j.compag.2023.108310_b0050) 2021; 52 Måløy (10.1016/j.compag.2023.108310_b0110) 2019; 167 10.1016/j.compag.2023.108310_b0115 Yang (10.1016/j.compag.2023.108310_b0190) 2021; 187 Zhang (10.1016/j.compag.2023.108310_b0210) 2021; 127 10.1016/j.compag.2023.108310_b0080 Jiang (10.1016/j.compag.2023.108310_b0090) 2018; 27 Yin (10.1016/j.compag.2023.108310_b0200) 2023; 205 Silva (10.1016/j.compag.2023.108310_b0140) 2019; 501 10.1016/j.compag.2023.108310_b0060 Shen (10.1016/j.compag.2023.108310_b0135) 2022; 197 Wang (10.1016/j.compag.2023.108310_b0165) 2022; 197 Du (10.1016/j.compag.2023.108310_b0030) 2023; 102 Xiong (10.1016/j.compag.2023.108310_b0180) 2022; 352 Temko (10.1016/j.compag.2023.108310_b0145) 2008; 41 Abdar (10.1016/j.compag.2023.108310_b0005) 2023; 19 Xu (10.1016/j.compag.2023.108310_b0185) 2021; 174 10.1016/j.compag.2023.108310_b0045 10.1016/j.compag.2023.108310_b0100 Saari (10.1016/j.compag.2023.108310_b0130) 2018; 37 10.1016/j.compag.2023.108310_b0065 10.1016/j.compag.2023.108310_b0120 Wang (10.1016/j.compag.2023.108310_b0170) 2022; 551 Fore (10.1016/j.compag.2023.108310_b0040) 2016; 464 |
| References_xml | – reference: Hu, J., Shen, L., Albanie, S., Sun, G., Wu, E., 2020. Squeeze-and-excitation networks. – volume: 13 start-page: 1828 year: 2021 end-page: 1843 ident: b0025 article-title: Monitoring methods of feeding behaviour to answer key questions in penaeid shrimp feeding publication-title: Rev. Aquac. – volume: 27 start-page: 393 year: 2018 end-page: 398 ident: b0090 article-title: Speech Magnitude Spectrum Reconstruction from MFCCs Using Deep Neural Network publication-title: Chin. J. Electron. – volume: 205 year: 2023 ident: b0200 article-title: An investigation of fusion strategies for boosting pig cough sound recognition publication-title: Comput. Electron. Agric. – volume: 127 start-page: 73 year: 2021 end-page: 81 ident: b0210 article-title: Learning deep multimodal affective features for spontaneous speech emotion recognition publication-title: Speech Comm. – volume: 551 year: 2022 ident: b0170 article-title: Dynamic feeding method for aquaculture fish using multi-task neural network publication-title: Aquaculture – volume: 19 start-page: 274 year: 2023 end-page: 285 ident: b0005 article-title: Hercules: Deep Hierarchical Attentive Multilevel Fusion Model With Uncertainty Quantification for Medical Image Classification publication-title: IEEE Trans. Ind. Inf. – volume: 41 start-page: 1814 year: 2008 end-page: 1823 ident: b0145 article-title: Fuzzy integral based information fusion for classification of highly confusable non-speech sounds publication-title: Pattern Recogn. – volume: 29 start-page: 337 year: 2019 end-page: 355 ident: b0095 article-title: Pre-processing spectrogram parameters improve the accuracy of bioacoustic classification using convolutional neural networks publication-title: Bioacoustics – volume: 352 year: 2022 ident: b0180 article-title: Occurrence of microplastics in a pond-river-lake connection water system: How does the aquaculture process affect microplastics in natural water bodies publication-title: J. Clean. Prod. – volume: 546 year: 2022 ident: b0125 article-title: Passive acoustic monitoring as a tool to assess feed response and growth of shrimp in ponds and research systems publication-title: Aquaculture – volume: 127 start-page: 271 year: 2016 end-page: 280 ident: b0215 article-title: Spatial behavioral characteristics and statistics-based kinetic energy modeling in special behaviors detection of a shoal of fish in a recirculating aquaculture system publication-title: Comput. Electron. Agric. – volume: 94 year: 2021 ident: b0155 article-title: Evaluating fish feeding intensity in aquaculture with convolutional neural networks publication-title: Aquac. Eng. – volume: 37 start-page: 2835 year: 2018 end-page: 2850 ident: b0130 article-title: Influence of Diltiazem on Fathead Minnows Across Dissolved Oxygen Gradients publication-title: Environ. Toxicol. Chem. – volume: 219 start-page: 281 year: 2022 end-page: 293 ident: b0085 article-title: Investigation of acoustic and visual features for pig cough classification publication-title: Biosyst. Eng. – reference: Huang, G., Liu, S., Maaten, L. v. d., & Weinberger, K.Q., 2018. CondenseNet: An Efficient DenseNet Using Learned Group Convolutions. In: Paper presented at the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. – volume: 17 start-page: 1183132 year: 2023 ident: b0105 article-title: GCF(2)-Net: global-aware cross-modal feature fusion network for speech emotion recognition publication-title: Front Neurosci – reference: Pham, L., McLoughlin, I., Phan, H., & Palaniappan, R., 2019. A Robust Framework for Acoustic Scene Classification. Paper presented at the Interspeech 2019. – start-page: 140252 year: 2019 end-page: 140260 ident: b0160 article-title: Deep Learning Based Weighted Feature Fusion Approach for Sentiment Analysis publication-title: IEEE Access – reference: Gui, S., Wang, H., Yang, H., Yu, C., Wang, Z., Liu, J., … Garnett, R., 2019. Model Compression with Adversarial Robustness A Unified Optimization Framework. In: 33rd Conference on Neural Information Processing Systems (NeurIPS), 32. doi:10.48550/arXiv.1902.03538. – reference: . doi:10.1155/2016/6172453. – reference: Han, K., Wang, Y., Tian, Q., Guo, J., Xu, C., & Xu, C. (2020). GhostNet More Features from Cheap Operations. In: IEEE Conference on Computer Vision and Pattern Recognition, 1577-1586. doi:10.1109/CVPR42600.2020.00165. – reference: Ko, K., Park, S., Ko, H., 2018. Convolutional Feature Vectors and Support Vector Machine for Animal Sound Classification. In: 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 376-379. doi:10.1109/EMBC.2018.8512408. – reference: (8), 2011-2023. doi:10.1109/TPAMI.2019.2913372. – reference: He, Y., Zhang, X., Sun, J., 2017. Channel Pruning for Accelerating Very Deep Neural Networks. In: 2017 IEEE International Conference on Computer Vision (ICCV), 1398-1406. doi:10.1109/ICCV.2017.155. – volume: 197 year: 2022 ident: b0135 article-title: Fusion of acoustic and deep features for pig cough sound recognition publication-title: Comput. Electron. Agric. – volume: 187 year: 2021 ident: b0190 article-title: A dual attention network based on efficientNet-B2 for short-term fish school feeding behavior analysis in aquaculture publication-title: Comput. Electron. Agric. – volume: 185 year: 2021 ident: b0075 article-title: Real-time detection of uneaten feed pellets in underwater images for aquaculture using an improved YOLO-V4 network publication-title: Comput. Electron. Agric. – reference: Hou, Q., Zhou, D., Feng, J., 2021. Coordinate Attention for Efficient Mobile Network Design. In: Paper presented at the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). – volume: 59 start-page: 345 year: 2016 end-page: 355 ident: b0195 article-title: Behavioral Characteristics and Statistics-Based Imaging Techniques in the Assessment and Optimization of Tilapia Feeding in a Recirculating Aquaculture System publication-title: Trans. ASABE – volume: 501 start-page: 76 year: 2019 end-page: 81 ident: b0140 article-title: Acoustic characterization of feeding activity of Litopenaeus vannamei in captivity publication-title: Aquaculture – reference: Nisar, S., Khan, O.U., Tariq, M., 2016. An Efficient Adaptive Window Size Selection Method for Improving Spectrogram Visualization. Comput. Intell. Neurosci. 6172453. Retrieved from – volume: 52 start-page: 4841 year: 2021 end-page: 4848 ident: b0050 article-title: Sound emission of Macrobrachium rosenbergii during feeding activity publication-title: Aquac. Res. – volume: 204 year: 2023 ident: b0205 article-title: Fish school feeding behavior quantification using acoustic signal and improved Swin Transformer publication-title: Comput. Electron. Agric. – volume: 174 year: 2021 ident: b0185 article-title: Speech enhancement based on nonnegative matrix factorization in constant-Q frequency domain publication-title: Appl. Acoust. – volume: 167 year: 2019 ident: b0110 article-title: A spatio-temporal recurrent network for salmon feeding action recognition from underwater videos in aquaculture publication-title: Comput. Electron. Agric. – volume: 283 start-page: 29 year: 2008 end-page: 35 ident: b0015 article-title: The biofloc technology (BFT) in indoor tanks: Water quality, biofloc composition, and growth and welfare of Nile tilapia (Oreochromis niloticus) publication-title: Aquaculture – volume: 1–6 year: 2022 ident: b0020 article-title: Fish feeding intensity assessment in aquaculture a new audio dataset affia3k and a deep learning algorithm publication-title: IEEE Int. Workshop Mach. Learn. Signal Process. – volume: 464 start-page: 268 year: 2016 end-page: 278 ident: b0040 article-title: Modelling growth performance and feeding behaviour of Atlantic salmon (Salmo salar L.) in commercial-size aquaculture net pens: Model details and validation through full-scale experiments publication-title: Aquaculture – volume: 8 start-page: 156654 year: 2020 end-page: 156662 ident: b0175 article-title: Study on Feeding Activity of Litopenaeus Vannamei Based on Passive Acoustic Detection publication-title: IEEE Access – volume: 98 year: 2022 ident: b0035 article-title: Fish feeding intensity quantification using machine vision and a lightweight 3D ResNet-GloRe network publication-title: Aquac. Eng. – volume: 102 year: 2023 ident: b0030 article-title: Feeding intensity assessment of aquaculture fish using Mel Spectrogram and deep learning algorithms publication-title: Aquac. Eng. – volume: 197 year: 2022 ident: b0165 article-title: Fusing deep learning features of triplet leaf image patterns to boost soybean cultivar identification publication-title: Comput. Electron. Agric. – volume: 507 start-page: 457 year: 2019 end-page: 465 ident: b0220 article-title: Evaluation of fish feeding intensity in aquaculture using a convolutional neural network and machine vision publication-title: Aquaculture – volume: 13 year: 2023 ident: b0150 article-title: A Feature Fusion Model with Data Augmentation for Speech Emotion Recognition publication-title: Appl. Sci. – volume: 52 start-page: 423 year: 2020 end-page: 437 ident: b0010 article-title: Application of computer vision in fish intelligent feeding system—A review publication-title: Aquac. Res. – volume: 197 year: 2022 ident: 10.1016/j.compag.2023.108310_b0135 article-title: Fusion of acoustic and deep features for pig cough sound recognition publication-title: Comput. Electron. Agric. doi: 10.1016/j.compag.2022.106994 – volume: 13 issue: 7 year: 2023 ident: 10.1016/j.compag.2023.108310_b0150 article-title: A Feature Fusion Model with Data Augmentation for Speech Emotion Recognition publication-title: Appl. Sci. doi: 10.3390/app13074124 – volume: 551 year: 2022 ident: 10.1016/j.compag.2023.108310_b0170 article-title: Dynamic feeding method for aquaculture fish using multi-task neural network publication-title: Aquaculture doi: 10.1016/j.aquaculture.2022.737913 – volume: 52 start-page: 4841 issue: 10 year: 2021 ident: 10.1016/j.compag.2023.108310_b0050 article-title: Sound emission of Macrobrachium rosenbergii during feeding activity publication-title: Aquac. Res. doi: 10.1111/are.15317 – volume: 127 start-page: 271 year: 2016 ident: 10.1016/j.compag.2023.108310_b0215 article-title: Spatial behavioral characteristics and statistics-based kinetic energy modeling in special behaviors detection of a shoal of fish in a recirculating aquaculture system publication-title: Comput. Electron. Agric. doi: 10.1016/j.compag.2016.06.025 – volume: 185 year: 2021 ident: 10.1016/j.compag.2023.108310_b0075 article-title: Real-time detection of uneaten feed pellets in underwater images for aquaculture using an improved YOLO-V4 network publication-title: Comput. Electron. Agric. doi: 10.1016/j.compag.2021.106135 – volume: 29 start-page: 337 issue: 3 year: 2019 ident: 10.1016/j.compag.2023.108310_b0095 article-title: Pre-processing spectrogram parameters improve the accuracy of bioacoustic classification using convolutional neural networks publication-title: Bioacoustics doi: 10.1080/09524622.2019.1606734 – volume: 204 year: 2023 ident: 10.1016/j.compag.2023.108310_b0205 article-title: Fish school feeding behavior quantification using acoustic signal and improved Swin Transformer publication-title: Comput. Electron. Agric. doi: 10.1016/j.compag.2022.107580 – start-page: 140252 year: 2019 ident: 10.1016/j.compag.2023.108310_b0160 article-title: Deep Learning Based Weighted Feature Fusion Approach for Sentiment Analysis publication-title: IEEE Access doi: 10.1109/ACCESS.2019.2940051 – ident: 10.1016/j.compag.2023.108310_b0065 doi: 10.1109/CVPR46437.2021.01350 – ident: 10.1016/j.compag.2023.108310_b0100 doi: 10.1109/EMBC.2018.8512408 – ident: 10.1016/j.compag.2023.108310_b0120 doi: 10.21437/Interspeech.2019-1841 – volume: 283 start-page: 29 issue: 1–4 year: 2008 ident: 10.1016/j.compag.2023.108310_b0015 article-title: The biofloc technology (BFT) in indoor tanks: Water quality, biofloc composition, and growth and welfare of Nile tilapia (Oreochromis niloticus) publication-title: Aquaculture doi: 10.1016/j.aquaculture.2008.06.036 – volume: 37 start-page: 2835 issue: 11 year: 2018 ident: 10.1016/j.compag.2023.108310_b0130 article-title: Influence of Diltiazem on Fathead Minnows Across Dissolved Oxygen Gradients publication-title: Environ. Toxicol. Chem. doi: 10.1002/etc.4242 – volume: 41 start-page: 1814 issue: 5 year: 2008 ident: 10.1016/j.compag.2023.108310_b0145 article-title: Fuzzy integral based information fusion for classification of highly confusable non-speech sounds publication-title: Pattern Recogn. doi: 10.1016/j.patcog.2007.10.026 – volume: 352 year: 2022 ident: 10.1016/j.compag.2023.108310_b0180 article-title: Occurrence of microplastics in a pond-river-lake connection water system: How does the aquaculture process affect microplastics in natural water bodies publication-title: J. Clean. Prod. doi: 10.1016/j.jclepro.2022.131632 – volume: 27 start-page: 393 issue: 2 year: 2018 ident: 10.1016/j.compag.2023.108310_b0090 article-title: Speech Magnitude Spectrum Reconstruction from MFCCs Using Deep Neural Network publication-title: Chin. J. Electron. doi: 10.1049/cje.2017.09.018 – volume: 501 start-page: 76 year: 2019 ident: 10.1016/j.compag.2023.108310_b0140 article-title: Acoustic characterization of feeding activity of Litopenaeus vannamei in captivity publication-title: Aquaculture doi: 10.1016/j.aquaculture.2018.11.013 – volume: 197 year: 2022 ident: 10.1016/j.compag.2023.108310_b0165 article-title: Fusing deep learning features of triplet leaf image patterns to boost soybean cultivar identification publication-title: Comput. Electron. Agric. doi: 10.1016/j.compag.2022.106914 – volume: 205 year: 2023 ident: 10.1016/j.compag.2023.108310_b0200 article-title: An investigation of fusion strategies for boosting pig cough sound recognition publication-title: Comput. Electron. Agric. doi: 10.1016/j.compag.2023.107645 – ident: 10.1016/j.compag.2023.108310_b0070 doi: 10.1109/TPAMI.2019.2913372 – volume: 102 year: 2023 ident: 10.1016/j.compag.2023.108310_b0030 article-title: Feeding intensity assessment of aquaculture fish using Mel Spectrogram and deep learning algorithms publication-title: Aquac. Eng. doi: 10.1016/j.aquaeng.2023.102345 – volume: 94 year: 2021 ident: 10.1016/j.compag.2023.108310_b0155 article-title: Evaluating fish feeding intensity in aquaculture with convolutional neural networks publication-title: Aquac. Eng. doi: 10.1016/j.aquaeng.2021.102178 – volume: 546 year: 2022 ident: 10.1016/j.compag.2023.108310_b0125 article-title: Passive acoustic monitoring as a tool to assess feed response and growth of shrimp in ponds and research systems publication-title: Aquaculture doi: 10.1016/j.aquaculture.2021.737326 – ident: 10.1016/j.compag.2023.108310_b0080 doi: 10.1109/CVPR.2018.00291 – volume: 219 start-page: 281 year: 2022 ident: 10.1016/j.compag.2023.108310_b0085 article-title: Investigation of acoustic and visual features for pig cough classification publication-title: Biosyst. Eng. doi: 10.1016/j.biosystemseng.2022.05.010 – volume: 19 start-page: 274 issue: 1 year: 2023 ident: 10.1016/j.compag.2023.108310_b0005 article-title: Hercules: Deep Hierarchical Attentive Multilevel Fusion Model With Uncertainty Quantification for Medical Image Classification publication-title: IEEE Trans. Ind. Inf. doi: 10.1109/TII.2022.3168887 – volume: 52 start-page: 423 issue: 2 year: 2020 ident: 10.1016/j.compag.2023.108310_b0010 article-title: Application of computer vision in fish intelligent feeding system—A review publication-title: Aquac. Res. doi: 10.1111/are.14907 – volume: 464 start-page: 268 year: 2016 ident: 10.1016/j.compag.2023.108310_b0040 article-title: Modelling growth performance and feeding behaviour of Atlantic salmon (Salmo salar L.) in commercial-size aquaculture net pens: Model details and validation through full-scale experiments publication-title: Aquaculture doi: 10.1016/j.aquaculture.2016.06.045 – volume: 167 year: 2019 ident: 10.1016/j.compag.2023.108310_b0110 article-title: A spatio-temporal recurrent network for salmon feeding action recognition from underwater videos in aquaculture publication-title: Comput. Electron. Agric. doi: 10.1016/j.compag.2019.105087 – ident: 10.1016/j.compag.2023.108310_b0060 doi: 10.1109/ICCV.2017.155 – volume: 127 start-page: 73 year: 2021 ident: 10.1016/j.compag.2023.108310_b0210 article-title: Learning deep multimodal affective features for spontaneous speech emotion recognition publication-title: Speech Comm. doi: 10.1016/j.specom.2020.12.009 – volume: 187 year: 2021 ident: 10.1016/j.compag.2023.108310_b0190 article-title: A dual attention network based on efficientNet-B2 for short-term fish school feeding behavior analysis in aquaculture publication-title: Comput. Electron. Agric. doi: 10.1016/j.compag.2021.106316 – volume: 98 year: 2022 ident: 10.1016/j.compag.2023.108310_b0035 article-title: Fish feeding intensity quantification using machine vision and a lightweight 3D ResNet-GloRe network publication-title: Aquac. Eng. doi: 10.1016/j.aquaeng.2022.102244 – volume: 17 start-page: 1183132 year: 2023 ident: 10.1016/j.compag.2023.108310_b0105 article-title: GCF(2)-Net: global-aware cross-modal feature fusion network for speech emotion recognition publication-title: Front Neurosci doi: 10.3389/fnins.2023.1183132 – volume: 13 start-page: 1828 issue: 4 year: 2021 ident: 10.1016/j.compag.2023.108310_b0025 article-title: Monitoring methods of feeding behaviour to answer key questions in penaeid shrimp feeding publication-title: Rev. Aquac. doi: 10.1111/raq.12546 – volume: 1–6 year: 2022 ident: 10.1016/j.compag.2023.108310_b0020 article-title: Fish feeding intensity assessment in aquaculture a new audio dataset affia3k and a deep learning algorithm publication-title: IEEE Int. Workshop Mach. Learn. Signal Process. – ident: 10.1016/j.compag.2023.108310_b0055 doi: 10.1109/CVPR42600.2020.00165 – volume: 8 start-page: 156654 year: 2020 ident: 10.1016/j.compag.2023.108310_b0175 article-title: Study on Feeding Activity of Litopenaeus Vannamei Based on Passive Acoustic Detection publication-title: IEEE Access doi: 10.1109/ACCESS.2020.3019529 – ident: 10.1016/j.compag.2023.108310_b0045 – ident: 10.1016/j.compag.2023.108310_b0115 doi: 10.1155/2016/6172453 – volume: 59 start-page: 345 issue: 1 year: 2016 ident: 10.1016/j.compag.2023.108310_b0195 article-title: Behavioral Characteristics and Statistics-Based Imaging Techniques in the Assessment and Optimization of Tilapia Feeding in a Recirculating Aquaculture System publication-title: Trans. ASABE doi: 10.13031/trans.59.11406 – volume: 507 start-page: 457 year: 2019 ident: 10.1016/j.compag.2023.108310_b0220 article-title: Evaluation of fish feeding intensity in aquaculture using a convolutional neural network and machine vision publication-title: Aquaculture doi: 10.1016/j.aquaculture.2019.04.056 – volume: 174 year: 2021 ident: 10.1016/j.compag.2023.108310_b0185 article-title: Speech enhancement based on nonnegative matrix factorization in constant-Q frequency domain publication-title: Appl. Acoust. doi: 10.1016/j.apacoust.2020.107732 |
| SSID | ssj0016987 |
| Score | 2.5167274 |
| Snippet | •An LC-GhostNet lightweight network based on the GhostNet is proposed.•Fusion of Mel spectrogram, STFT feature map, and CQT feature map.•The method can... In aquaculture, accurate detection of fish feeding intensity is a critical step for establishing an on-demand feeding system. In this paper, a novel fish... |
| SourceID | proquest crossref elsevier |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 108310 |
| SubjectTerms | agriculture aquaculture data collection electronics Feature fusion fish Fish feeding intensity LC-GhostNet lightweight network nondestructive methods On-demand feeding system Oplegnathus |
| Title | Feature fusion strategy and improved GhostNet for accurate recognition of fish feeding behavior |
| URI | https://dx.doi.org/10.1016/j.compag.2023.108310 https://www.proquest.com/docview/3040400005 |
| Volume | 214 |
| WOSCitedRecordID | wos001096264100001&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: PRVESC databaseName: Elsevier SD Freedom Collection Journals 2021 customDbUrl: eissn: 1872-7107 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0016987 issn: 0168-1699 databaseCode: AIEXJ dateStart: 19950101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1JaxsxFBau00N7KF1puqFC6cVMcGaTdDSt0wXj9uDA3IS2cRzC2LU9weTX52kkzZi2IemhF2E00ozR-5A-vRWhD7mReVIKEUmqaJQaYSJWpjJShukETmxWMt0UmyDTKS0K9rPX24VYmMsLUlV0t2Or_ypq6ANh29DZfxB3-1LogN8gdGhB7NDeSfCW1FmrQFlbRdhg49LP-jRLjQoBOOYXG9wxNVvnRKlUbQcNWm8iRyJLm-2odMdbG8-_z2ZDSQiX57mrqNP42Ir52uf1aLHzuW5sIWe1qOZXTRueFM2TArAqxbLTri5uGj9ZhAnLs9DtdRdx4oP49tSZOdxhc1ciKezH8XE6WFnfR2Ce0V93eadwOD9q3PTnR_bNfnx3qgVL_vQHPzmdTPhsXMw-rn5Ftt6Ytcv74iv30EFMMkb76GD0bVx8by1QOaMu1N7_wxB22fgG_vnhm2jNbwd8w1pmj9Ejf93AIweTJ6hnqqfo4agTzTPEPWCwAwwOgMEgUxwAgwNgMAAGB8DgPcDgZYktYLAHDA6AeY5OT8azT18jX3YjUknCtpHOgbIqoxWJJTHMkJIpmZNYME3FkFGaUCOpYfGQEHEcW4VBTIVWOlNxLnKVvED9almZlwhrouH-qqXOpEhJJmSsNIULvywTKtkwP0RJWDWufE56Wxrlggfnw3Pu1prbteZurQ9R1M5auZwst4wnQSDc80rHFzkA6paZ74P8OGy71pYmKrOsNzyBwy-1ZC97dYcxr9GDDv5vUH-7rs1bdF9dbheb9TsPvWtJ5asE |
| linkProvider | Elsevier |
| 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=Feature+fusion+strategy+and+improved+GhostNet+for+accurate+recognition+of+fish+feeding+behavior&rft.jtitle=Computers+and+electronics+in+agriculture&rft.au=Du%2C+Zhuangzhuang&rft.au=Xu%2C+Xianbao&rft.au=Bai%2C+Zhuangzhuang&rft.au=Liu%2C+Xiaohang&rft.date=2023-11-01&rft.issn=0168-1699&rft.volume=214+p.108310-&rft_id=info:doi/10.1016%2Fj.compag.2023.108310&rft.externalDBID=NO_FULL_TEXT |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0168-1699&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0168-1699&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0168-1699&client=summon |