Nội dung được dịch bởi AI, chỉ mang tính chất tham khảo
Tri thức máy tính dựa trên học chuyển giao sâu cho phân loại thời gian thu hoạch trong thời gian thực và phát hiện tạp chất của Porphyra haitnensis
Springer Science and Business Media LLC - Trang 1-28 - 2024
Tóm tắt
Rong biển đã thu hút sự chú ý lớn với vai trò là thực phẩm lành mạnh và giàu dinh dưỡng. Các nhà máy chế biến rong biển truyền thống chủ yếu dựa vào kiểm tra trực quan bằng tay để xác định và loại bỏ rong biển kém chất lượng. Phân loại chính xác và nhanh chóng thời gian thu hoạch cũng như phát hiện tạp chất là chìa khóa để cải thiện năng suất và tốc độ chế biến trong các nhà máy chế biến rong biển. Mặc dù nhiều nghiên cứu về rong biển đã được thực hiện trong môi trường phòng thí nghiệm, hiện nay, các nhà máy thiếu các công cụ hiệu quả để thu thập thông tin về chất lượng rong biển một cách thời gian thực và đáng tin cậy. Để giải quyết thách thức này, phương pháp học sâu dựa trên chuyển giao đã được áp dụng để xác định rong biển kém chất lượng, bao gồm rong biển từ vụ thu hoạch thứ ba, thứ tư và rong biển bị nhiễm bẩn trong nghiên cứu này. Cụ thể, YOLOv8 và YOLOv5 được sử dụng làm mô hình học chuyển giao cơ bản. Bằng cách tải nhiều tệp trọng số đã được huấn luyện trước, nghiên cứu này đã có thể phân loại tự động Porphyra haitnensis thành bốn loại dựa trên thời gian thu hoạch và đồng thời phát hiện bốn loại tạp chất phổ biến trong đó. Trong số các mô hình đã thử nghiệm, YOLOv8n-cls đạt được sự cân bằng tốt nhất trong việc phân loại thời gian thu hoạch, với độ chính xác Top-1 đạt 93.5%. Điều này đại diện cho sự cải thiện đáng kể 16% so với hiệu suất mà không sử dụng học chuyển giao. Tốc độ phát hiện cho một hình ảnh đơn lẻ là 8.2 ms, và kích thước mô hình chỉ là 2.82 Mb. Mặt khác, YOLOv8n thể hiện hiệu suất xuất sắc trong việc phát hiện tạp chất, với độ chính xác trung bình là 99.14%, tốc độ phát hiện cho một hình ảnh đơn lẻ là 4.3 ms, và kích thước mô hình là 5.95 Mb. Kết quả chứng tỏ tiềm năng của YOLOv8 với học chuyển giao trong việc hỗ trợ khách quan hoặc thậm chí thay thế quyết định của công nhân trên dây chuyền lắp ráp. Nghiên cứu này không chỉ nâng cao kiểm soát chất lượng, hiệu quả sản xuất và lợi ích kinh tế của ngành chế biến rong biển mà còn thúc đẩy thiết bị và hệ thống tự động hóa của các doanh nghiệp liên quan đến rong biển tiến tới sự thông minh và hiệu quả lớn hơn.
Từ khóa
#rong biển #học sâu #phát hiện tạp chất #phân loại thời gian thu hoạch #YOLOv8 #YOLOv5 #Porphyra haitnensis #tự động hóaTài liệu tham khảo
Anusha Siddiqui S, Bahmid NA, Mahmud CMM, Boukid F, Lamri M, Gagaoua M (2023) Consumer acceptability of plant-, seaweed-, and insect-based foods as alternatives to meat: a critical compilation of a decade of research. Crit Rev Food Sci Nutr 63:6630–6651. https://doi.org/10.1080/10408398.2022.2036096
Nakamura E (2011) One hundred years since the discovery of the “umami” taste from seaweed broth by Kikunae Ikeda, who transcended his time. Chem–An Asian J 6:1659–1663. https://doi.org/10.1002/asia.201000899
Cai J, Lovatelli A, Aguilar-Manjarrez J, Cornish L, Dabbadie L, Desrochers A, Diffey S, Garrido Gamarro E, Geehan J, Hurtado A (2021) Seaweeds and microalgae: an overview for unlocking their potential in global aquaculture development. FAO Fish Aquacult Circular 1229:48. https://doi.org/10.4060/cb5670en
Cao R, Hu M, Zhao L, Wang L, Liu Q (2021) Flavor characteristics of different crops of laver (Porphyra yezoensis) during one harvest cycle. J Ocean Univ China 20:213–220. https://doi.org/10.1007/s11802-021-4447-3
Aberg P (1992) Size-based demography of the seaweed Ascophyllum nodosum in stochastic environments. Ecology 73:1488–1501. https://doi.org/10.2307/1940692
Marinho GS, Holdt SL, Angelidaki I (2015) Seasonal variations in the amino acid profile and protein nutritional value of Saccharina latissima cultivated in a commercial IMTA system. J Appl Phycol 27:1991–2000. https://doi.org/10.1007/s10811-015-0546-0
Network CQN (2022) Presence of foreign substances found in 4 packs of seaweed sold. Beijing Yongju Trading Co., Ltd. fined 50,000 yuan. China Quality News Network https://www.cqn.com.cn/index.htm/
Trienekens J, Zuurbier P (2008) Quality and safety standards in the food industry, developments and challenges. Int J Prod Econ 113:107–122. https://doi.org/10.1016/j.ijpe.2007.02.050
Das DK, Mukherjee R, Chakraborty C (2015) Computational microscopic imaging for malaria parasite detection: a systematic review. J Microsc 260:1–19. https://doi.org/10.1111/jmi.12270
Chen S, Wang Y, Zhu Q, Ni H, Cai H (2023) Fast recognition of the harvest period of Porphyra haitanensis based on mid-infrared spectroscopy and chemometrics. J Food Measure Character 17:5487–5496. https://doi.org/10.1007/s11694-023-01999-1
Cao X, Ding H, Yang L, Huang J, Zeng L, Tong H, Su L, Ji X, Wu M, Yang Y (2022) Near-infrared spectroscopy as a tool to assist Sargassum fusiforme quality grading: harvest time discrimination and polyphenol prediction. Postharvest Biol Technol 192:112030. https://doi.org/10.1016/j.postharvbio.2022.112030
Rioux L-E, Turgeon SL, Beaulieu M (2009) Effect of season on the composition of bioactive polysaccharides from the brown seaweed Saccharina longicruris. Phytochemistry 70:1069–1075. https://doi.org/10.1016/j.phytochem.2009.04.020
Benslima A, Sellimi S, Hamdi M, Nasri R, Jridi M, Cot D, Li S, Nasri M, Zouari N (2021) Brown seaweed Cystoseira schiffneri as a promising source of sulfated fucans: seasonal variability of structural, chemical, and antioxidant properties. Food Sci Nutr 9:1551–1563. https://doi.org/10.1002/fsn3.2130
Petersen M, Yu Z, Lu X (2021) Application of Raman spectroscopic methods in food safety: a review. Biosensors 11:187. https://doi.org/10.3390/bios11060187
Naseer S, Ali RF, Khan YD, Dominic P (2022) iGluK-Deep: computational identification of lysine glutarylation sites using deep neural networks with general pseudo amino acid compositions. J Biomol Struct Dyn 40:11691–11704. https://doi.org/10.1080/07391102.2021.1962738
Borges Oliveira DA, Ribeiro Pereira LG, Bresolin T, Pontes Ferreira RE, Reboucas Dorea JR (2021) A review of deep learning algorithms for computer vision systems in livestock. Livest Sci 253:104700. https://doi.org/10.1016/j.livsci.2021.104700
Kamath R, Balachandra M, Prabhu S (2018) Paddy crop and weed classification using color features for computer vision based precision agriculture. Int J Eng Technol (UAE) 7:2909–2916. https://doi.org/10.14419/ijet.v7i4.15679
Chaudhari D, Waghmare S (2022) Machine vision based fruit classification and grading—a review. Int J Comput Appl 170(9):775–781. https://doi.org/10.5120/ijca2017914937
Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 779–788
Khamparia A, Gupta D, de Albuquerque VHC, Sangaiah AK, Jhaveri RH (2020) Internet of health things-driven deep learning system for detection and classification of cervical cells using transfer learning. J Supercomput 76:8590–8608. https://doi.org/10.1007/s11227-020-03159-4
Simhadri CG, Kondaveeti HK (2023) Automatic recognition of rice leaf diseases using transfer learning. Agronomy 13:961. https://doi.org/10.3390/agronomy13040961
Zhao L, Zhi L, Zhao C, Zheng W (2022a) Fire-YOLO: a small target object detection method for fire inspection. Sustainability 14:4930. https://doi.org/10.3390/su14094930
Li Y, Li S, Du H, Chen L, Zhang D, Li Y (2020) YOLO-ACN: focusing on small target and occluded object detection. IEEE Access 8:227288–227303. https://doi.org/10.1109/ACCESS.2020.3046515
Ren X, Bai Y, Liu G, Zhang P (2023) YOLO-Lite: an efficient lightweight network for SAR ship detection. Remote Sens 15:3771. https://doi.org/10.3390/rs15153771
Ju M, Luo J, Wang Z, Luo H (2021) Adaptive feature fusion with attention mechanism for multi-scale target detection. Neural Comput Applic 33:2769–2781. https://doi.org/10.1007/s00521-020-05150-9
Qing Y, Liu W, Feng L, Gao W (2021) Improved Yolo network for free-angle remote sensing target detection. Remote Sens 13:2171. https://doi.org/10.3390/rs13112171
Lin C-J, Jhang J-Y (2022) Intelligent traffic-monitoring system based on YOLO and convolutional fuzzy neural networks. IEEE Access 10:14120–14133. https://doi.org/10.1109/ACCESS.2022.3147866
Bui TH, Thangavel B, Sharipov M, Chen K, Shin JH (2023) Smartphone-based portable bio-chemical sensors: exploring recent advancements. Chemosensors 11:468. https://doi.org/10.3390/chemosensors11090468
Zhang Y, Zhang H, Huang Q, Han Y, Zhao M (2024) DsP-YOLO: an anchor-free network with DsPAN for small object detection of multiscale defects. Expert Syst Appl 241:122669. https://doi.org/10.21203/rs.3.rs-3743453/v1
Miller KA, Pearse JS (2015) Ecological studies of seaweeds in McMurdo Sound, Antarctica. Am Zool 31:35–48. https://doi.org/10.1093/icb/31.1.35
Rimmer MA, Larson S, Lapong I, Purnomo AH, Pong-Masak PR, Swanepoel L, Paul NA (2021) Seaweed aquaculture in Indonesia contributes to social and economic aspects of livelihoods and community wellbeing. Sustainability 13:10946. https://doi.org/10.3390/su131910946
Gong J, Xie P (2020) Research progress in sources, analytical methods, eco-environmental effects, and control measures of microplastics. Chemosphere 254:126790. https://doi.org/10.1016/j.chemosphere.2020.126790
Hafting JT (1998) Strategies for growth management of Porphyra yezoensis (Ueda) blades in suspension cultures: a step towards land-based mariculture. University of British Columbia
Ling ALM, Yasir S, Matanjun P, Abu Bakar MF (2015) Effect of different drying techniques on the phytochemical content and antioxidant activity of Kappaphycus alvarezii. J Appl Phycol 27:1717–1723. https://doi.org/10.1007/s10811-014-0467-3
Karthikeyan M, Zhonghua W, Mujumdar AS (2009) Low-rank coal drying technologies—current status and new developments. Dry Technol 27:403–415. https://doi.org/10.1080/07373930802683005
Yue F, Chen C, Yan Z, Chen C, Guo Z, Zhang Z, Chen Z, Zhang F, Lv X (2020) Fourier transform infrared spectroscopy combined with deep learning and data enhancement for quick diagnosis of abnormal thyroid function. Photodiagn Photodyn Ther 32:101923. https://doi.org/10.1016/j.pdpdt.2020.101923
Schlett T, Rathgeb C, Busch C (2021) Deep learning-based single image face depth data enhancement. Comput Vis Image Underst 210:103247. https://doi.org/10.1016/j.cviu.2021.103247
Pain CD, Egan GF, Chen Z (2022) Deep learning-based image reconstruction and post-processing methods in positron emission tomography for low-dose imaging and resolution enhancement. Eur J Nucl Med Mol Imaging 49:3098–3118. https://doi.org/10.1007/s00259-022-05746-4
Affonso C, Rossi ALD, Vieira FHA, de Carvalho ACPLF (2017) Deep learning for biological image classification. Expert Syst Appl 85:114–122. https://doi.org/10.1016/j.eswa.2017.05.039
Zhang J, Xie Y, Wu Q, Xia Y (2019) Medical image classification using synergic deep learning. Med Image Anal 54:10–19. https://doi.org/10.1016/j.media.2019.02.010
Shen X, Luo J, Tang X, Chen B, Qin Y, Zhou Y, Xiao J (2022) Deep learning approach for diagnosing early osteonecrosis of the femoral head based on magnetic resonance imaging. J Arthroplast 38:2044–2050. https://doi.org/10.1016/j.arth.2022.10.003
Zhao Y, Chang M, Wang R, Xi IL, Chang K, Huang RY, Vallières M, Habibollahi P, Dagli MS, Palmer M, Zhang PJ, Silva AC, Yang L, Soulen MC, Zhang Z, Bai HX, Stavropoulos SW (2020) Deep learning based on MRI for differentiation of low- and high-grade in low-stage renal cell carcinoma. J Magn Reson Imaging 52:1542–1549. https://doi.org/10.1002/jmri.27153
Kumar S, Arif T, Ahamad G, Chaudhary AA, Khan S, Ali MA (2023) An efficient and effective framework for intestinal parasite egg detection using YOLOv5. Diagnostics 13:2978. https://doi.org/10.3390/diagnostics13182978
Jiang Y, Qu M, Chen Y (2023) Coral detection, ranging, and assessment (CDRA) algorithm-based automatic estimation of coral reef coverage. Mar Environ Res 191:106157. https://doi.org/10.1016/j.marenvres.2023.106157
Xu Y, Li D, Xie Q, Wu Q, Wang J (2021) Automatic defect detection and segmentation of tunnel surface using modified Mask R-CNN. Measurement 178:109316. https://doi.org/10.1016/j.measurement.2021.109316
Ren S, He K, Girshick R, Sun J (2015) Faster r-cnn: towards real-time object detection with region proposal networks. Adv Neural Inf Proces Syst 28:1137–1149. https://doi.org/10.1109/TPAMI.2016.2577031
Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu C-Y, Berg AC (2016) Ssd: Single shot multibox detector. In: Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, Proceedings, Part I 14. Springer, pp 21–37
Tamang S, Sen B, Pradhan A, Sharma K, Singh VK (2023) Enhancing COVID-19 safety: exploring yolov8 object detection for accurate face mask classification. Int J Intell Syst Appl Eng 11:892–897
Wang G, Chen Y, An P, Hong H, Hu J, Huang T (2023) UAV-YOLOv8: a small-object-detection model based on improved YOLOv8 for UAV aerial photography scenarios. Sensors 23:7190. https://doi.org/10.3390/s23167190
Karakuş S, Kaya M, Tuncer SA (2023) Real-time detection and identification of suspects in forensic imagery using advanced YOLOv8 object recognition models. Traitement du Signal 40:2029–2039. https://doi.org/10.18280/ts.400521
Knausgård KM, Wiklund A, Sørdalen TK, Halvorsen KT, Kleiven AR, Jiao L, Goodwin M (2022) Temperate fish detection and classification: a deep learning based approach. Appl Intell 52:6988–7001. https://doi.org/10.1007/s10489-020-02154-9
Xu P, Tan Q, Zhang Y, Zha X, Yang S, Yang R (2022) Research on maize seed classification and recognition based on machine vision and deep learning. Agriculture 12:232. https://doi.org/10.3390/agriculture12020232
Xiao B, Nguyen M, Yan WQ (2023) Fruit ripeness identification using YOLOv8 model. Multimed Tools Appl. https://doi.org/10.1007/s11042-023-16570-9
Shaloo M, Princz G (2023) Erol S Real-time color detection for automated production lines using CNN-based machine learning. In: Borgianni Y, Matt DT, Molinaro M, Orzes G (eds) Towards a Smart, Resilient and Sustainable Industry. Springer Nature Switzerland, Cham, pp 167–181. https://doi.org/10.1007/978-3-031-38274-1_15
Zhou J, Tian F, Li Y, Wang J, Tian Q, Zhang Q, Gao W, Zhuang Y (2023) Semiconductor laser chip damage detection based on the improved YOLOv8 algorithm. In: 2023 21st International Conference on Optical Communications and Networks (ICOCN), pp 1–3. https://doi.org/10.1109/ICOCN59242.2023.10236268
Liang T, Zhao Q, Lv Q, Sun H (2021) A novel wind speed prediction strategy based on Bi-LSTM, MOOFADA and transfer learning for centralized control centers. Energy 230:120904. https://doi.org/10.1016/j.energy.2021.120904
Zhao X, Li K, Li Y, Ma J, Zhang L (2022b) Identification method of vegetable diseases based on transfer learning and attention mechanism. Comput Electron Agric 193:106703. https://doi.org/10.1016/j.compag.2022.106703
Shao S, McAleer S, Yan R, Baldi P (2019) Highly accurate machine fault diagnosis using deep transfer learning. IEEE Trans Industr Inform 15:2446–2455. https://doi.org/10.1109/TII.2018.2864759
Ahmed I, Ahmad M, Ahmad A, Jeon G (2021) Top view multiple people tracking by detection using deep SORT and YOLOv3 with transfer learning: within 5G infrastructure. Int J Mach Learn Cybern 12:3053–3067. https://doi.org/10.1007/s13042-020-01220-5
Bai Y, Hou F, Fan X, Lin W, Lu J, Zhou J, Fan D, Li L (2023) An interpretable high-accuracy method for rice disease detection based on multi-source data and transfer learning. Agriculture 13:1812. https://doi.org/10.3390/plants12183273
Ramus J (1983) A physiological test of the theory of complementary chromatic adaptation. II. Brown, green and red seaweeds1. J Phycol 19:173–178
Koehl MA, Silk WK (2021) How kelp in drag lose their ruffles: environmental cues, growth kinematics, and mechanical constraints govern curvature. J Exp Bot 72:3677–3687. https://doi.org/10.1093/jxb/erab111
Arellano-Verdejo J, Lazcano-Hernández HE (2021) Collective view: mapping Sargassum distribution along beaches. PeerJ Comput Sci 7:e528. https://doi.org/10.7717/peerj-cs.528
Marquez L, Fragkopoulou E, Cavanaugh K, Houskeeper H, Assis J (2022) Artificial intelligence convolutional neural networks map giant kelp forests from satellite imagery. Sci Rep 12:22196. https://doi.org/10.1038/s41598-022-26439-w
Bearham D, Vanderklift MA, Gunson JR (2013) Temperature and light explain spatial variation in growth and productivity of the kelp Ecklonia radiata. Mar Ecol Prog Ser 476:59–70. https://doi.org/10.3354/meps10148
Carneiro G, Pu LZCT, Singh R, Burt A (2020) Deep learning uncertainty and confidence calibration for the five-class polyp classification from colonoscopy. Med Image Anal 62:101653. https://doi.org/10.1016/j.media.2020.101653
Finlay C, Oberman AM (2019) Empirical confidence estimates for classification by deep neural networks. arXiv:190309215. https://doi.org/10.48550/arXiv.1903.09215
Tóth N, Pataki B (2007) On classification confidence and ranking using decision trees. In: 2007 11th International Conference on Intelligent Engineering Systems. IEEE, pp 133–138. https://doi.org/10.1109/INES.2007.4283686
Shin Y, Choi Y, Won J, Hong T, Koo C (2024) A new benchmark model for the automated detection and classification of a wide range of heavy construction equipment. J Manag Eng 40:04023069. https://doi.org/10.1061/JMENEA.MEENG-5630
Bao W, Du X, Wang N, Yuan M, Yang X (2022) A defect detection method based on BC-YOLO for transmission line components in UAV remote sensing images. Remote Sens 14:5176. https://doi.org/10.3390/rs14205176
Casas GG, Ismail ZH, Limeira MMC, da Silva AAL, Leite HG (2023) Automatic detection and counting of stacked eucalypt timber using the YOLOv8 model. Forests 14:2369. https://doi.org/10.3390/f14122369
Ye L, Chen S (2023) GBForkDet: A lightweight object detector for forklift safety driving. IEEE Access 11:86509–86521. https://doi.org/10.1109/ACCESS.2023.3302909
Lou H, Duan X, Guo J, Liu H, Gu J, Bi L, Chen H (2023) DC-YOLOv8: small-size object detection algorithm based on camera sensor. Electronics 12:2323. https://doi.org/10.3390/electronics12102323