{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T00:50:01Z","timestamp":1776905401563,"version":"3.51.2"},"reference-count":57,"publisher":"MDPI AG","issue":"21","license":[{"start":{"date-parts":[[2022,10,28]],"date-time":"2022-10-28T00:00:00Z","timestamp":1666915200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Northern Gulf Institute at Mississippi State University from NOAA\u2019s Office of Oceanic and Atmospheric Research, U.S. Department of Commerce","award":["NA16OAR4320199"],"award-info":[{"award-number":["NA16OAR4320199"]}]},{"name":"Northern Gulf Institute at Mississippi State University from NOAA\u2019s Office of Oceanic and Atmospheric Research, U.S. Department of Commerce","award":["NA21OAR4320190"],"award-info":[{"award-number":["NA21OAR4320190"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Fish species recognition is crucial to identifying the abundance of fish species in a specific area, controlling production management, and monitoring the ecosystem, especially identifying the endangered species, which makes accurate fish species recognition essential. In this work, the fish species recognition problem is formulated as an object detection model to handle multiple fish in a single image, which is challenging to classify using a simple classification network. The proposed model consists of MobileNetv3-large and VGG16 backbone networks and an SSD detection head. Moreover, a class-aware loss function is proposed to solve the class imbalance problem of our dataset. The class-aware loss takes the number of instances in each species into account and gives more weight to those species with a smaller number of instances. This loss function can be applied to any classification or object detection task with an imbalanced dataset. The experimental result on the large-scale reef fish dataset, SEAMAPD21, shows that the class-aware loss improves the model over the original loss by up to 79.7%. The experimental result on the Pascal VOC dataset also shows the model outperforms the original SSD object detection model.<\/jats:p>","DOI":"10.3390\/s22218268","type":"journal-article","created":{"date-parts":[[2022,10,30]],"date-time":"2022-10-30T10:47:57Z","timestamp":1667126877000},"page":"8268","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":58,"title":["Class-Aware Fish Species Recognition Using Deep Learning for an Imbalanced Dataset"],"prefix":"10.3390","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3796-3201","authenticated-orcid":false,"given":"Simegnew Yihunie","family":"Alaba","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, James Worth Bagley College of Engineering, Mississippi State University, Starkville, MS 39762, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5910-2501","authenticated-orcid":false,"given":"M M","family":"Nabi","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, James Worth Bagley College of Engineering, Mississippi State University, Starkville, MS 39762, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7712-8585","authenticated-orcid":false,"given":"Chiranjibi","family":"Shah","sequence":"additional","affiliation":[{"name":"Northern Gulf Institute, Mississippi State University, Starkville, MS 39759, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6945-9763","authenticated-orcid":false,"given":"Jack","family":"Prior","sequence":"additional","affiliation":[{"name":"Northern Gulf Institute, Mississippi State University, Starkville, MS 39759, USA"}]},{"given":"Matthew D.","family":"Campbell","sequence":"additional","affiliation":[{"name":"NOAA\u2014National Marine Fisheries Service, Southeast Fisheries Science Center, 3209 Frederic Street, Pascagoula, MS 39567, USA"}]},{"given":"Farron","family":"Wallace","sequence":"additional","affiliation":[{"name":"NOAA Fisheries, 4700 Avenue U, Galveston, TX 77551, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6774-4851","authenticated-orcid":false,"given":"John E.","family":"Ball","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, James Worth Bagley College of Engineering, Mississippi State University, Starkville, MS 39762, USA"}]},{"given":"Robert","family":"Moorhead","sequence":"additional","affiliation":[{"name":"Northern Gulf Institute, Mississippi State University, Starkville, MS 39759, USA"}]}],"member":"1968","published-online":{"date-parts":[[2022,10,28]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"343","DOI":"10.1016\/j.aquaeng.2004.07.004","article-title":"Development of an intelligent feeding controller for indoor intensive culturing of eel","volume":"32","author":"Chang","year":"2005","journal-title":"Aquac. Eng."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1119","DOI":"10.1093\/icesjms\/fsp009","article-title":"Artificial neural networks for fish-species identification","volume":"66","author":"Cabreira","year":"2009","journal-title":"ICES J. Mar. Sci."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"591","DOI":"10.5343\/bms.2016.1039","article-title":"Surveying the distribution and abundance of flying fishes and other epipelagics in the northern Gulf of Mexico using airborne lidar","volume":"93","author":"Churnside","year":"2017","journal-title":"Bull. Mar. Sci."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1016\/j.fishres.2015.04.009","article-title":"Predictive mapping of abalone fishing grounds using remotely-sensed LiDAR and commercial catch data","volume":"169","author":"Jalali","year":"2015","journal-title":"Fish. Res."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"799","DOI":"10.1577\/M07-116.1","article-title":"A semiautomated approach to estimating fish size, abundance, and behavior from dual-frequency identification sonar (DIDSON) data","volume":"28","author":"Boswell","year":"2008","journal-title":"N. Am. J. Fish. Manag."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Villon, S., Chaumont, M., Subsol, G., Vill\u00e9ger, S., Claverie, T., and Mouillot, D. (2016, January 24\u201327). Coral reef fish detection and recognition in underwater videos by supervised machine learning: Comparison between Deep Learning and HOG+ SVM methods. Proceedings of the International Conference on Advanced Concepts for Intelligent Vision Systems, ACIVS 2016, Lecce, Italy.","DOI":"10.1007\/978-3-319-48680-2_15"},{"key":"ref_7","unstructured":"Boulais, O., Alaba, S.Y., Ball, J.E., Campbell, M., Iftekhar, A.T., Moorehead, R., Primrose, J., Prior, J., Wallace, F., and Yu, H. (2021, January 25). SEAMAPD21: A large-scale reef fish dataset for fine-grained categorization. Proceedings of the FGVC8: The Eight Workshop on Fine-Grained Visual Categorization, Online."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"132","DOI":"10.1016\/j.ecss.2017.10.003","article-title":"Umbrellas can work under water: Using threatened species as indicator and management surrogates can improve coastal conservation","volume":"199","author":"Gilby","year":"2017","journal-title":"Estuar. Coast. Shelf Sci."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1401","DOI":"10.1111\/2041-210X.13470","article-title":"A field and video annotation guide for Baited Remote Underwater stereo-video surveys of Demersal Fish Assemblages","volume":"11","author":"Langlois","year":"2020","journal-title":"Methods Ecol. Evol."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1007\/s11160-016-9450-1","article-title":"What is big bruvver up to? methods and uses of Baited Underwater Video","volume":"27","author":"Whitmarsh","year":"2016","journal-title":"Rev. Fish Biol. Fish."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"440","DOI":"10.3389\/fmars.2017.00440","article-title":"Habitat connectivity of fish in temperate shallow-water seascapes","volume":"4","author":"Perry","year":"2017","journal-title":"Front. Mar. Sci."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"594","DOI":"10.1016\/j.ocecoaman.2008.06.006","article-title":"Coastal Habitat support to fish and fisheries in Sweden: Integrating ecosystem functions into fisheries management","volume":"51","author":"Paulsen","year":"2008","journal-title":"Ocean Coast. Manag."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"6867","DOI":"10.1109\/JSTARS.2022.3196658","article-title":"Deep Learning-Based Soil Moisture Retrieval in CONUS Using CYGNSS Delay\u2013Doppler Maps","volume":"15","author":"Nabi","year":"2022","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Zhao, M., Chang, C.H., Xie, W., Xie, Z., and Hu, J. (2020). Cloud shape classification system based on multi-channel cnn and improved fdm. IEEE Access, 44111\u201344124.","DOI":"10.1109\/ACCESS.2020.2978090"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"You, L., Jiang, H., Hu, J., Chang, C.H., Chen, L., Cui, X., and Zhao, M. (July, January 27). GPU-accelerated Faster Mean Shift with euclidean distance metrics. Proceedings of the 2022 IEEE 46th Annual Computers, Software, and Applications Conference (COMPSAC), Alamitos, CA, USA.","DOI":"10.1109\/COMPSAC54236.2022.00037"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Jin, B., Cruz, L., and Gon\u00e7alves, N. (2022). Pseudo RGB-D Face Recognition. IEEE Sens. J.","DOI":"10.1109\/JSEN.2022.3197235"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"107079","DOI":"10.1016\/j.compag.2022.107079","article-title":"Rachis detection and three-dimensional localization of cut off point for vision-based banana robot","volume":"198","author":"Wu","year":"2022","journal-title":"Comput. Electron. Agric."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"118573","DOI":"10.1016\/j.eswa.2022.118573","article-title":"Fruit detection and positioning technology for a Camellia oleifera C. Abel orchard based on improved YOLOv4-tiny model and binocular stereo vision","volume":"211","author":"Tang","year":"2022","journal-title":"Expert Syst. Appl."},{"key":"ref_19","unstructured":"Huang, P.X., Boom, B.J., and Fisher, R.B. (2012, January 5\u20139). Underwater live fish recognition using a balance-guaranteed optimized tree. Proceedings of the Asian Conference on Computer Vision\u2014ACCV 2012, Daejeon, Korea."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Fisher, R.B., Chen-Burger, Y.H., Giordano, D., Hardman, L., and Lin, F.P. (2016). Fish4knowledge: Collecting and Analyzing Massive Coral Reef Fish Video Data, Springer.","DOI":"10.1007\/978-3-319-30208-9"},{"key":"ref_21","unstructured":"J\u00e4ger, J., Rodner, E., Denzler, J., Wolff, V., and Fricke-Neuderth, K. (2016, January 5\u20138). SeaCLEF 2016: Object Proposal Classification for Fish Detection in Underwater Videos. Proceedings of the Working Notes of CLEF 2016, \u00c9vora, Portugal."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Joly, A., Go\u00ebau, H., Glotin, H., Spampinato, C., Bonnet, P., Vellinga, W.P., Planqu\u00e9, R., Rauber, A., Palazzo, S., and Fisher, B. (2015, January 8\u201311). LifeCLEF 2015: Multimedia life species identification challenges. Proceedings of the International Conference of the Cross-Language Evaluation Forum for European Languages, Toulouse, France.","DOI":"10.1007\/978-3-319-24027-5_46"},{"key":"ref_23","unstructured":"Zhuang, P., Xing, L., Liu, Y., Guo, S., and Qiao, Y. (2017, January 11\u201314). Marine Animal Detection and Recognition with Advanced Deep Learning Models. Proceedings of the CLEF 2017, Dublin, Ireland."},{"key":"ref_24","unstructured":"Howard, A., Sandler, M., Chu, G., Chen, L.C., Chen, B., Tan, M., Wang, W., Zhu, Y., Pang, R., and Vasudevan, V. (November, January 27). Searching for mobilenetv3. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Seoul, Korea."},{"key":"ref_25","unstructured":"Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv."},{"key":"ref_26","first-page":"75","article-title":"Fish classification using support vector machine","volume":"8","author":"Ogunlana","year":"2015","journal-title":"Afr. J. Comput. ICT"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1016\/0262-8856(93)90027-E","article-title":"Recognition of fish species by colour and shape","volume":"11","author":"Strachan","year":"1993","journal-title":"Image Vis. Comput."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1016\/j.fishres.2006.04.009","article-title":"Automated measurement of species and length of fish by computer vision","volume":"80","author":"White","year":"2006","journal-title":"Fish. Res."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"570","DOI":"10.1002\/lom3.10113","article-title":"Fish species classification in unconstrained underwater environments based on deep learning","volume":"14","author":"Salman","year":"2016","journal-title":"Limnol. Oceanogr. Methods"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Labao, A.B., and Naval, P.C. (2019, January 8\u201311). Simultaneous localization and segmentation of fish objects using multi-task CNN and dense CRF. Proceedings of the Asian Conference on Intelligent Information and Database Systems, Yogyakarta, Indonesia.","DOI":"10.1007\/978-3-030-14799-0_52"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Rekha, B., Srinivasan, G., Reddy, S.K., Kakwani, D., and Bhattad, N. (2019, January 25\u201326). Fish detection and classification using convolutional neural networks. Proceedings of the International Conference on Computational Vision and Bio Inspired Computing, Coimbatore, India.","DOI":"10.1007\/978-3-030-37218-7_128"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Nery, M.S., Machado, A., Campos, M.F.M., P\u00e1dua, F.L., Carceroni, R., and Queiroz-Neto, J.P. (2005, January 9\u201312). Determining the appropriate feature set for fish classification tasks. Proceedings of the XVIII Brazilian Symposium on Computer Graphics and Image Processing (SIBGRAPI\u201905), IEEE, Natal, Rio Grande do Norte, Brazil.","DOI":"10.1109\/SIBGRAPI.2005.25"},{"key":"ref_33","unstructured":"Li, X., Shang, M., Qin, H., and Chen, L. (2015, January 19\u201322). Fast accurate fish detection and recognition of underwater images with fast r-cnn. Proceedings of the OCEANS 2015-MTS\/IEEE Washington, Washington, DC, USA."},{"key":"ref_34","unstructured":"Ren, S., He, K., Girshick, R., and Sun, J. (2015). Faster r-cnn: Towards real-time object detection with region proposal networks. Adv. Neural Inf. Process. Syst., 28."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Alaba, S., and Ball, J. (2022). Deep Learning-based Image 3D Object Detection for Autonomous Driving: Review. TechRxiv.","DOI":"10.36227\/techrxiv.20442858.v3"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Redmon, J., and Farhadi, A. (2017, January 21\u201326). Yolo9000: Better, faster, stronger. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.690"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., and Berg, A.C. (2016, January 11\u201314). Ssd: Single shot multibox detector. Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands.","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Alaba, S., Gurbuz, A., and Ball, J. (2022). A Comprehensive Survey of Deep Learning Multisensor Fusion-based 3D Object Detection for Autonomous Driving: Methods, Challenges, Open Issues, and Future Directions. TechRxiv.","DOI":"10.36227\/techrxiv.20443107"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1613\/jair.953","article-title":"SMOTE: Synthetic minority over-sampling technique","volume":"16","author":"Chawla","year":"2002","journal-title":"J. Artif. Intell. Res."},{"key":"ref_40","unstructured":"He, H., Bai, Y., Garcia, E.A., and Li, S. (2008, January 1\u20136). ADASYN: Adaptive synthetic sampling approach for imbalanced learning. Proceedings of the 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence), Hong Kong, China."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Zou, Y., Yu, Z., Kumar, B., and Wang, J. (2018, January 8\u201314). Unsupervised domain adaptation for semantic segmentation via class-balanced self-training. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01219-9_18"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Cui, Y., Jia, M., Lin, T.Y., Song, Y., and Belongie, S. (2019, January 15\u201320). Class-balanced loss based on effective number of samples. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00949"},{"key":"ref_43","unstructured":"Krizhevsky, A., and Hinton, G. (2009). Learning Multiple Layers of Features from Tiny Images, University of Toronto. Technical Report TR-2009."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Li, Y., Wang, T., Kang, B., Tang, S., Wang, C., Li, J., and Feng, J. (2020, January 13\u201319). Overcoming classifier imbalance for long-tail object detection with balanced group softmax. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.01100"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"100977","DOI":"10.1016\/j.ecoinf.2019.100977","article-title":"Improving Pantanal fish species recognition through taxonomic ranks in convolutional neural networks","volume":"53","year":"2019","journal-title":"Ecol. Inform."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1016\/j.compag.2012.07.008","article-title":"Fish species classification by color, texture and multi-class support vector machine using computer vision","volume":"88","author":"Hu","year":"2012","journal-title":"Comput. Electron. Agric."},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_48","unstructured":"Tan, M., and Le, Q. (2019, January 10\u201315). Efficientnet: Rethinking model scaling for convolutional neural networks. Proceedings of the International Conference on Machine Learning, Long Beach, CA, USA."},{"key":"ref_49","unstructured":"Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., and Adam, H. (2017). Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv."},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Yang, T.J., Howard, A., Chen, B., Zhang, X., Go, A., Sandler, M., Sze, V., and Adam, H. (2018, January 8\u201314). Netadapt: Platform-aware neural network adaptation for mobile applications. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01249-6_18"},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Avenash, R., and Viswanath, P. (2019, January 25\u201327). Semantic Segmentation of Satellite Images using a Modified CNN with Hard-Swish Activation Function. Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, Prague, Czech Republic.","DOI":"10.5220\/0007469600002108"},{"key":"ref_52","doi-asserted-by":"crossref","unstructured":"Alaba, S.Y., and Ball, J.E. (2022). WCNN3D: Wavelet Convolutional Neural Network-Based 3D Object Detection for Autonomous Driving. Sensors, 22.","DOI":"10.20944\/preprints202209.0060.v1"},{"key":"ref_53","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., and Doll\u00e1r, P. (2017, January 22\u201329). Focal loss for dense object detection. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref_54","doi-asserted-by":"crossref","unstructured":"Girshick, R. (2015, January 7\u201313). Fast r-cnn. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"15844","DOI":"10.1109\/ACCESS.2018.2810849","article-title":"Improvement of generalization ability of deep CNN via implicit regularization in two-stage training process","volume":"6","author":"Zheng","year":"2018","journal-title":"IEEE Access"},{"key":"ref_56","unstructured":"Goyal, P., Doll\u00e1r, P., Girshick, R., Noordhuis, P., Wesolowski, L., Kyrola, A., Tulloch, A., Jia, Y., and He, K. (2017). Accurate, large minibatch sgd: Training imagenet in 1 hour. arXiv."},{"key":"ref_57","unstructured":"(2022, September 20). Congcong Li High Quality, Fast, Modular Reference Implementation of SSD in PyTorch. Available online: https:\/\/github.com\/lufficc\/SSD."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/21\/8268\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T01:04:53Z","timestamp":1760144693000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/21\/8268"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,28]]},"references-count":57,"journal-issue":{"issue":"21","published-online":{"date-parts":[[2022,11]]}},"alternative-id":["s22218268"],"URL":"https:\/\/doi.org\/10.3390\/s22218268","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10,28]]}}}