Adaptive deep learning with optimization hybrid convolutional neural network and recurrent neural network for prediction lemon fruit ripeness

• Autorzy: Watnakornbuncha Darunee , Am-Dee Noppadol , Sangsongfa Adisak

Identyfikatory

DOI

10.15199/48.2024.03.36

Warianty tytułu

PL

Adaptacyjne głębokie uczenie się z optymalizacją hybrydowa splotowa sieć neuronowa i rekurencyjna sieć neuronowa do przewidywania dojrzałości owoców cytryny

• Języki publikacji: EN

Abstrakty

EN

emon is a valuable fruit in the citrus family; optimal usage requires careful selection. The study categorized lemon suitability prediction int 4 classes based on image data. A hybrid neural network, combining Convolutional and Recurrent Neural Networks, was optimized with the Particle Swarm Optimization algorithm. Experimental results were compared to using Convolutional Neural Network alone. The prediction yielded 89.83% training accuracy and 66.06% testing accuracy. However, combining the results increased training accuracy to 91.58% and testing accuracy to 86.76%.

PL

Cytryna to owoc należący do bardzo pożytecznej rodziny cytrusów, ale aby można było z niej korzystać w celu maksymalizacji korzyści płynących z cytryny, konieczne jest wybranie zachowania przydatności do spożycia. Dlatego w tym badaniu przewidywanie przydatności cytryny jest podzielone na 4 klasy przy użyciu obrazów jako danych do badań. Wyniki predykcji w badaniach z wykorzystaniem połączonej sieci neuronowej pomiędzy Convulotinal Nerual Network i Recurrent Nerual Network z optymalizacją parametrów algorytmem Particle Swarm Optimization, wyniki eksperymentalne porównano z wykorzystaniem wyłącznie Convulotinal Nerual Network. Dla predykcji wynik treningu to 89,83%, a wynik testu to 66,06%, natomiast wynik kombinacji wyników treningu to 91,58% i wynik testu to 86,76%.

Słowa kluczowe

EN

lemon; convolutional neural network; recurrent neural network

PL

cytryna; konwolucyjna sieć neuronowa; rekurencyjna sieć neuronowa

• Wydawca: Wydawnictwo SIGMA-NOT
• Czasopismo: Przegląd Elektrotechniczny
• Rocznik: 2024
• Tom: R. 100, nr 3
• Strony: 202--211
• Opis fizyczny: Bibliogr. 25 poz., rys., tab.

Twórcy

autor

Watnakornbuncha Darunee

• Doctoral Program in Industrial Technology Management, Muban Chom Bueng Rajabhat University, Thailand

• https://orcid.org/0009-0006-4616-5873

autor

Am-Dee Noppadol

• Doctoral Program in Industrial Technology Management, Muban Chom Bueng Rajabhat University, Thailand

• https://orcid.org/0000-0002-2413-1430

autor

Sangsongfa Adisak

• Doctoral Program in Industrial Technology Management, Muban Chom Bueng Rajabhat University, Thailand

• https://orcid.org/0000-0002-6231-4000

Bibliografia

• [1] R. Sharma, “A detailed guide on the meaning importance,j and future of neural networks,” Blog of Artificial Intelligence and Machine Learning, (2022), Available on https://emeritus:org/in/learn/ai-ml-neural-networks/
• [2] P. Anurak, “What is a deep learning neural network?” Thai Config Company Limited, (2023), Available on https://thaiconfig:com/artificial-intelligence-ai/what-is-deeplearning/
• [3] H. S. Gill and B. S. Khehra, “Fruit image classification using deep learning,” Research Square, vol. 1, pp. 1–9, (2022), available on https://doi:org/10:21203/rs:3:rs-574901/v1
• [4] M. Khatun, J. Nine, P. Sarker, and et.al., “Fruits classification using convolutional neural network,” Journals- Global Research and Development Journal for Engineering, (2020), vol. 5, no. 8, pp. 1–5.
• [5] R. Pathak and H. Makwana, “Classification of fruits using convolutional neural network and transfer learning models,” Journal of Management Information and Decision Sciences, (2021). vol. 24, no. S3, pp. 1–12.
• [6] M. Aznin, S. Ahmed, and et.al., “Fruits classification and detection application using deep learning,” Hindawi Scientific Programming, vol. 2022, pp. 1–16, (2022), https://doi:org/10:1155/ 2022/4194874
• [7] K. Shankar, S. Kumar, and et.al., “An automated hyperparameter tuning recurrent neural network model for fruit classification,” Mathematics (MDPI), (2022), vol. 10, no. 13, pp. 1–18. Available on: https://doi:org/10:3390/math10132358
• [8] G. Xue, S. Liu, and Y. Ma, “A hybrid deep learning-based fruit classification using attention model and convolution autoencoder,” Complex and Intelligent Systems, (2023), vol. 9, pp. 2209–2219. Available on: https://doi:org/10:1007/s40747- 020-00192-x
• [9] C. C. Ukwuoma, Q. Zhiguang, and et.al., “Recent advancements in fruit detection and classification using deep learning techniques,” Hindawi Mathematical Problems in Engineering, (2022), vol. 2022, pp. 1–29. Available on: https://doi:org/10:1155/2022/9210947
• [10] M. Ware, “How can lemons benefit your health?” Medical News Today, (2019), Available on https://www:medicalnewstoday:com/articles/283476
• [11] P. Greenhalgh, “Lemon,” IFEAT Socio-Economic Report, (2021), Available on https://ifeat:org/wp-content/ uploads/2021/09/Socio-Economic-Report-on-Lemon-2021:pdf
• [12] Y. H. R. Hung, H. J. Lin, and et.al., “Effect of lemon essential oil on the microbial control, physicochemical properties, and aroma profiles of peeled shrimp,” LWT Food Science and Technology, (2023), vol. 173, pp. 1–9.
• [13] C. Y. Hsieh, S. Hsieh, J. Y. Ciou, and et.al., “Lemon juice bioactivity in vitro increased with lactic acid fermentation,” International Journal of Food Properties, (2020), vol. 24, no. 1, pp. 28–40. Available on: https://doi:org/10:1080/10942912:2020:1861008
• [14] D. C. F. Rayner, “Optimization for heuristic search,” ERA, (2014), Available on https://era:library:ualberta:ca/ items/57ecc087-1494-41b0-aa98-8f3bedcaa25f
• [15] D. Karaboga and C. Ozturk, “A novel clustering approach: Artificial bee colony (abc) algorithm,” (2011), vol. 11, pp. 652– 657.
• [16] X.-S. Yang, “Nature-inspired algorithms,” in Nature-Inspired Optimization Algorithms, Ed. Oxford: Elsevier, (2014), p. i. ISBN 978-0-12-416743-8. [Online]. Available on: https://www:sciencedirect:com/science/article/pii/B9780124167 438000166
• [17] V. Kenny. “Heuristic algorithms,” Optimization, (2014), Available on: https://optimization:mccormick:northwestern:edu/index:php/ Heuristic/Algorithms
• [18] F. E. Fernandes and G. G. Yen, “Particle swarm optimization of deep neural networks architectures for image classification,” Swarm and Evolutionary Computation, (2019), vol. 49, pp. 62– 74. Available on https://doi:org/10:1016/j:swevo 05:010
• [19] A. Ghosh, A. Sufian, F. Sultana, and et.al., Fundamental Concepts of Convolutional Neural Network. ResearchGate, Jan (2020), DOI:10:1007/978-3-030-32644-9 36
• [20] Aishwarya, “Introduction to recurrent neural network,” Machine Larning, (2021), Available on: https://www:geeksforgeeks:org/introduction-to-recurrent-neural-network/
• [21] Shaadk7865, “Particle swarm optimization (pso) an overview,” GeeksforGeeks, (2023), Available on : https://www:geeksforgeeks:org/particle-swarm-optimizationpso-an-overview/#article-meta-div
• [22] Y. Lu, “Food image recognition by using convolutional neural networks (cnns),” Computer Vision and Pattern Recognition (cs arXiv:1612.00983), (2019), vol. 2, pp. 1–6. Available on: https://doi:org/10:48550/arXiv:1612:00983
• [23] S. Hou, Y. Feng, Z. Wang, and Vegfru, “A domain-specific dataset for fine-grained visual categorization,” In Proceedings of the 2017 IEEE International Conference on Computer Vision, (2017), pp. 541–549.
• [24] N. Aherwadai, U. Mittai, J. Singla, and et. al., “Prediction of fruit maturity, quality, and its life using deep learning algorithms,” Electronics 2022, (2022), vol. 11, no. 24, pp. 1–13. https://doi:org/10:3390/electronics11244100
• [25] T. Khan, J. Qiu, M. A. A. Qureahi, and et. al., “Agricultural fruit prediction using deep neural networks,” Procedia Computer Science, (2022), vol. 174, pp. 72–78. Available on: https://doi:org/10:1016/j:procs:2020:06:058

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki i promocja sportu (2025).