Stacked Deep Learning-Based Quality Classification of Dried Fish Products for Post Harvest Loss Reduction and Value Chain Enhancement

Ebru Ergün

doi:10.15832/ankutbd.1638118

Stacked Deep Learning-Based Quality Classification of Dried Fish Products for Post Harvest Loss Reduction and Value Chain Enhancement

Abstract

This study addresses critical inefficiencies in traditional fish drying practices by developing an artificial intelligence (AI)-powered classification system to standardize quality control and enhance market competitiveness for coastal communities. Unlike existing works that rely solely on isolated classifiers, this study introduces a hybrid stacked architecture incorporating both deep and traditional machine learning models, enabling improved interpretability and robustness. Using a threestage computational methodology, we integrated deep learning with feature optimization to overcome the longstanding challenges of manual quality assessment. The framework consists of: (1) the utilization of a publicly available dataset containing 8,290 high-resolution images of five commercially important species under controlled drying conditions, (2) hierarchical feature extraction using ResNet50 with Lasso regression (LR) for dimensionality reduction, and (3) a novel ensemble learning strategy based on stacked generalization, combining four diverse classifiers trained on optimized deep feature representations. Unlike prior studies that use off-the-shelf convolutional neural network (CNN), our model integrates LR atop CNN embeddings before stacking, thereby redefining classifier synergy in the dried fish domain. The proposed model achieved 99.94% classification accuracy, outperforming conventional single-algorithm approaches by 0.06%, while reducing computational overhead by 34% through optimized feature selection. This study introduces a novel integration of deep features and ensemble stacking methods for dried seafood authentication. This novel design effectively addresses critical texture and color variability issues arising from inconsistent drying processes. The non-destructive nature of this approach enables real-time species identification with a 0.06% misclassification risk, aligning with FAO priorities to minimize postharvest losses in small-scale fisheries. Furthermore, this study offers a replicable AI blueprint for other agricultural commodities, demonstrating methodological scalability and domain adaptability. By integrating ancestral preservation techniques with Industry 4.0 innovations, this framework enhances processing efficiency, ensures product traceability, and promotes equitable income distribution for artisanal producers.

Keywords

References

Adityatama R & Putra A T (2023). Image classification of human face shapes using convolutional neural network Xception architecture with transfer learning. Recursive Journal of Informatics 1(2):102–109. https://doi.org/10.15294/rji.v1i2.70774
Al Muksit A, Hasan F & Emon M F H B (2022). YOLO-Fish: A robust fish detection model to detect fish in realistic underwater environment. Ecological Informatics 72: 101847. https://doi.org/10.1016/j.ecoinf.2022.101847
Arabi D S, Hamdy O & Abdel-Salam Z A (2022). Utilization of spectrochemical analysis and diffuse optical techniques to reveal adulteration of alike fish species and their microbial contamination. Food Analytical Methods 15(4): 1062–1073. https://doi.org/10.1007/s12161-021 02212-z
Aydemir Ö (2016). Common spatial pattern-based feature extraction from the best time segment of BCI data. Turkish Journal of Electrical Engineering and Computer Sciences 24(5):3976–3986. https://doi.org/10.3906/elk-1502-162
Cozzolino D (2022). Advantages, opportunities, and challenges of vibrational spectroscopy as tool to monitor sustainable food systems. Food Analytical Methods 15(5): 1390–1396. https://doi.org/10.1007/s12161-021-02207-w
Dharshana D, Natarajan B & Bhuvaneswari R (2023). A novel approach for detection and classification of fish species. In 2023 Second International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT) (pp. 1–7). IEEE.
Ergün E & Aydemir Ö (2018). Classification of motor imaginary based near-infrared spectroscopy signals. In 2018 26th Signal Processing and Communications Applications Conference (SIU) (pp. 1-4). IEEE.
Ergün E (2024a). Artificial intelligence approaches for accurate assessment of insulator cleanliness in high-voltage electrical systems. Electrical Engineering 1–16. https://doi.org/10.1007/s00202-024-02691-3

Ergün E (2024b). Deep learning based multiclass classification for citrus anomaly detection in agriculture. Signal, Image and Video Processing 18: 8077–8088. https://doi.org/10.1007/s11760-024-03452-2
Ergün E (2025). High precision banana variety identification using vision transformer based feature extraction and support vector machine. Scientific Reports 15: 1-10366. https://doi.org/10.1038/s41598-025-95466-0
Francescangeli M, Marini S & Martínez E (2023). Image dataset for benchmarking automated fish detection and classification algorithms. Scientific Data 10(1):5. https://doi.org/10.1038/s41597-022-01906-1
Guenther J & Sawodny O (2019). Feature selection for thermal comfort modeling based on constrained LASSO regression. IFAC PapersOnLine 52(15): 400–405. https://doi.org/10.1016/j.ifacol.2019.11.708
Guo Y, Wang W & Wang X (2021). A robust linear regression feature selection method for data sets with unknown noise. IEEE Transactions on Knowledge and Data Engineering 35(1):31–44. https://doi.org/10.1109/TKDE.2021.3076891
Hans C (2011). Elastic net regression modeling with the orthant normal prior. Journal of the American Statistical Association 106(496): 1383 1393. https://doi.org/10.1198/jasa.2011.tm09241
Hindarto D (2023). Exploring YOLOv8 pretrain for real-time detection of Indonesian native fish species. Sinkron: Jurnal dan Penelitian Teknik Informatika 7(4):2776–2785. https://doi.org/10.33395/sinkron.v8i4.13100
Hou H, Chen X & Li M (2021). Prediction of user outage under typhoon disaster based on multi-algorithm stacking integration. International Journal of Electrical Power & Energy Systems 131: 107123. https://doi.org/10.1016/j.ijepes.2021.107123
Hu J, Li D & Duan Q (2012). Fish species classification by color, texture and multi-class support vector machine using computer vision. Computers and Electronics in Agriculture 88: 133–140. https://doi.org/10.1016/j.compag.2012.07.008
Irmak G & Saygılı A (2024). A Novel Approach for Tomato Leaf Disease Classification with Deep Convolutional Neural Networks. Journal of Agricultural Sciences 30: 2-367-385. https://doi.org/10.15832/ankutbd.1332675
Jalal A, Salman A & Mian A (2020). Fish detection and species classification in underwater environments using deep learning with temporal information. Ecological Informatics 57:101088. https://doi.org/10.1016/j.ecoinf.2020.101088
Kaya V, Akgül İ & Tanır ÖZ (2023). IsVoNet8: A proposed deep learning model for classification of some fish species. Journal of Agricultural Sciences 29(1): 298–307. https://doi.org/10.15832/ankutbd.1031130
Knausgad K M, Wiklund A & Sørdalen T K (2022). Temperate fish detection and classification: A deep learning based approach. Applied Intelligence 52(6): 6988–7001. https://doi.org/10.1007/s10489-020-02154-9
Kuswantori A, Suesut T & Tangsrirat W (2023). Fish detection and classification for automatic sorting system with an optimized YOLO algorithm. Applied Sciences 13(6):3812. https://doi.org/10.3390/app13063812
Laboni M A, Rimi I F & Deb S (2022). Dried fish classification using deep learning. In 2022 Second International Conference on Advances in Electrical, Computing, Communication and Sustainable Technologies (ICAECT) (pp. 1–6). IEEE.
Li D, Wang Q & Li X (2022). Recent advances of machine vision technology in fish classification. ICES Journal of Marine Science 79(2): 263–284. https://doi.org/10.1093/icesjms/fsab264
Louka N, Juhel F & Fazilleau V (2004). A novel colorimetry analysis used to compare different drying fish processes. Food Control 15(5):327 334. https://doi.org/10.1016/S0956-7135(02)00119-6
Luo H, Fang Y & Wang J (2023). Combined prediction of rockburst based on multiple factors and stacking ensemble algorithm. Underground Space 13: 241–261. https://doi.org/10.1016/j.undsp.2023.05.003
Mandal A & Ghosh A R (2024). Role of artificial intelligence (AI) in fish growth and health status monitoring: A review on sustainable aquaculture. Aquaculture International 32(3): 2791–2820. https://doi.org/10.1007/s10499-023-01297-z
Monteiro F, Bexiga V & Chaves P (2023). Classification of fish species using multispectral data from a low-cost camera and machine learning. Remote Sensing 15(16): 3952. https://doi.org/10.3390/rs15163952
Paygude P, Gayakwad M & Wategaonkar D (2024). Dried fish dataset for Indian seafood: A machine learning application. Data in Brief 110563. https://doi.org/10.1016/j.dib.2024.110563
Prasetyo E, Suciati N & Fatichah C (2022). Multi-level residual network VGGNet for fish species classification. Journal of King Saud University-Computer and Information Sciences 34(8): 5286–5295. https://doi.org/10.1016/j.jksuci.2021.05.015
Prasenan P & Suriyakala C D (2023). Novel modified convolutional neural network and FFA algorithm for fish species classification. Journal of Combinatorial Optimization 45(1):16. https://doi.org/10.1007/s10878-022-00952-0
Reis H C & Turk V (2024). Integrated deep learning and ensemble learning model for deep feature-based wheat disease detection. Microchemical Journal 197: 109790. https://doi.org/10.1016/j.microc.2023.109790
Rohani A, Taki M & Bahrami G (2019). Application of artificial intelligence for separation of live and dead rainbow trout fish eggs. Artificial Intelligence in Agriculture 1: 27–34. https://doi.org/10.1016/j.aiia.2019.03.002
Saqib M, Khokher M R & Yuan X (2024). A lightweight fish species classification model using deep learning techniques for mobile applications. Sustainability 16(6): 4228. https://doi.org/10.3390/su16064228
Sofuoğlu İ & Bırant D (2024). Potato Plant Leaf Disease Detection Using Deep Learning Method. Journal of Agricultural Sciences 30(1): 153 165. https://doi.org/10.15832/ankutbd.1276722
Tharwat A, Hemedan A A & Hassanien A E (2018). A biometric-based model for fish species classification. Fisheries Research 204: 324–336. https://doi.org/10.1016/j.fishres.2018.03.008
Upasana C, Tewari A S & Singh J P (2023). An attention-based pneumothorax classification using modified Xception model. Procedia Computer Science 218: 74–82. https://doi.org/10.1016/j.procs.2022.12.403
Wood M V, Carvalho F M & Castello L (2024). Fishing shrinks the size structure of exploited coral reef fishes in Brazil. Fisheries Research 275:107029. https://doi.org/10.1016/j.fishres.2024.107029
Zhang Z, Lai Z & Xu Y (2017). Discriminative elastic-net regularized linear regression. IEEE Transactions on Image Processing 26(3): 1466 1481. https://doi.org/10.1109/TIP.2017.2651396
Zhang H, Wang J & Sun Z (2019). Feature selection for neural networks using group lasso regularization. IEEE Transactions on Knowledge and Data Engineering 32(4): 659–673. https://doi.org/10.1109/TKDE.2019.2893266

Details

Primary Language

English

Subjects

Precision Agriculture Technologies, Post-Harvest Fisheries Technologies (Incl. Transportation), Sustainable Agricultural Development

Journal Section

Research Article

Authors

Ebru Ergün ^*
0000-0002-5371-7238
Türkiye

Publication Date

January 20, 2026

Submission Date

February 11, 2025

Acceptance Date

June 20, 2025

Published in Issue

Year 2026 Volume: 32 Number: 1

DOI

https://doi.org/10.15832/ankutbd.1638118

IZ

https://izlik.org/JA59DY72RE

Cite

RIS / Bibtex

APA

Ergün, E. (2026). Stacked Deep Learning-Based Quality Classification of Dried Fish Products for Post Harvest Loss Reduction and Value Chain Enhancement. Journal of Agricultural Sciences, 32(1), 42-56. https://doi.org/10.15832/ankutbd.1638118

AMA

1.Ergün E. Stacked Deep Learning-Based Quality Classification of Dried Fish Products for Post Harvest Loss Reduction and Value Chain Enhancement. J Agr Sci-Tarim Bili. 2026;32(1):42-56. doi:10.15832/ankutbd.1638118

Chicago

Ergün, Ebru. 2026. “Stacked Deep Learning-Based Quality Classification of Dried Fish Products for Post Harvest Loss Reduction and Value Chain Enhancement”. Journal of Agricultural Sciences 32 (1): 42-56. https://doi.org/10.15832/ankutbd.1638118.

EndNote

Ergün E (January 1, 2026) Stacked Deep Learning-Based Quality Classification of Dried Fish Products for Post Harvest Loss Reduction and Value Chain Enhancement. Journal of Agricultural Sciences 32 1 42–56.

IEEE

[1]E. Ergün, “Stacked Deep Learning-Based Quality Classification of Dried Fish Products for Post Harvest Loss Reduction and Value Chain Enhancement”, J Agr Sci-Tarim Bili, vol. 32, no. 1, pp. 42–56, Jan. 2026, doi: 10.15832/ankutbd.1638118.

ISNAD

Ergün, Ebru. “Stacked Deep Learning-Based Quality Classification of Dried Fish Products for Post Harvest Loss Reduction and Value Chain Enhancement”. Journal of Agricultural Sciences 32/1 (January 1, 2026): 42-56. https://doi.org/10.15832/ankutbd.1638118.

JAMA

1.Ergün E. Stacked Deep Learning-Based Quality Classification of Dried Fish Products for Post Harvest Loss Reduction and Value Chain Enhancement. J Agr Sci-Tarim Bili. 2026;32:42–56.

MLA

Ergün, Ebru. “Stacked Deep Learning-Based Quality Classification of Dried Fish Products for Post Harvest Loss Reduction and Value Chain Enhancement”. Journal of Agricultural Sciences, vol. 32, no. 1, Jan. 2026, pp. 42-56, doi:10.15832/ankutbd.1638118.

Vancouver

1.Ebru Ergün. Stacked Deep Learning-Based Quality Classification of Dried Fish Products for Post Harvest Loss Reduction and Value Chain Enhancement. J Agr Sci-Tarim Bili. 2026 Jan. 1;32(1):42-56. doi:10.15832/ankutbd.1638118