Citation :

Aditya J Parida, Manas Ranjan Senapati, Soumya Das, "Optimized Radial Basis Function Neural Network for Automated Classification of Apple Quality," International Journal of Computer Trends and Technology (IJCTT), vol. 73, no. 11, pp. 30-36, 2025. Crossref, https://doi.org/10.14445/22312803/IJCTT-V73I11P105

Abstract

Apples are still very much a global health food, which also plays a large role in agriculture. We must see to it that we have the same high standards in sorting and distribution, which in turn will do much to reduce post-harvest waste. This study reports on a developed “Radial Basis Function Neural Network (RBFNN)” model for the automatic classification of apples into good and defective. We have put together a system that uses a set of numerical features from our data, which includes size, weight, sugar content, crispness, juice content, ripeness, and acid level, which also serves to eliminate the need for extra feature extraction or image processing. We also report that we have improved upon radial center and spread parameters, which in turn have improved the accuracy and learning convergence. The model achieves notable performance on 1200 test samples, recording an accuracy of 89.83%, precision of 94.14%, recall of 88.33%, specificity of 92.06%, and an F1-score of 91.12%. The findings demonstrate that the optimized RBFNN effectively balances computational efficiency with predictive reliability, making it a suitable solution for real-time quality inspection in automated fruit sorting and supply chain systems.

Keywords

Acidity, Apple quality classification, Classification accuracy, Radial basis function neural network, Real-time assessment.

References

[1] Yanfei Li et al., “Apple Quality Identification and Classification by Image Processing Based on Convolutional Neural Networks,” Scientific Reports, vol. 11, pp. 1-18, 2021.
[CrossRef] [Google Scholar] [Publisher Link]

[2] Mirko Agarla, Paolo Napoletano, and Raimondo Schettini, “Quasi Real-Time Apple Defect Segmentation Using Deep Networks,” Sensors, vol. 23, no. 18, pp. 1-19, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[3] Xiangyun Hu et al., “Automatic Detection of Small-Sample Apple Surface Defects Using ASDINet,” Foods, vol. 12, no. 6, pp. 1-29, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[4] Haiping Si et al., “Apple Surface Defect Detection Method Based on Weight Comparison Transfer Learning with MobileNetV3,” Agriculture, vol. 13, no. 4, pp. 1-26, 2023.
[CrossRef] [Google Scholar] [Publisher Link] 

[5] Wei Shan, and Yurong Yue, “Apple Defect Detection in Complex Environments,” Electronics, vol. 13, no. 23, pp. 1-17, 2024.
[CrossRef] [Google Scholar] [Publisher Link] 

[6] Bhumica Dhiman, Yogesh Kumar, and Munish Kumar, “Fruit Quality Evaluation Using Machine Learning Techniques: Review, Motivation and Future Perspectives,” Multimedia Tools and Applications, vol. 81, pp. 16255-16277, 2022.
[CrossRef] [Google Scholar] [Publisher Link] 

[7] Ioannis D. Apostolopoulos, Mpesi Tzani, and Sokratis I. Aznaouridis, “A General Machine Learning Model for Assessing Fruit Quality Using Deep Image Features,” AI, vol. 4, no. 4, pp. 1-19, 2023.
[CrossRef] [Google Scholar] [Publisher Link] 

[8] Peipei Cao et al., “Classification of Fruit Varieties Based on Deep Learning,” CEUR Workshop Proceedings, vol. 3304, pp. 300-306, 2022.
[Publisher Link] 

[9] Abiban Kumari, and Jaswinder Singh, “Postharvest Quality Classification of Fruits Using Machine Learning – A Review,” Journal of Electrical Systems, vol. 20, no. 3, pp. 7259-7274, 2024.
[Publisher Link]

[10] Khalid M. Alrajeh, and Tamer. A. A. Alzohairy, “Date Fruits Classification Using MLP and RBF Neural Networks,” International Journal of Computer Applications, vol. 41, no. 10, pp. 36-41, 2012.
[CrossRef] [Google Scholar] [Publisher Link] 

[11] Tejpal, Apple Quality Analysis Dataset, Kaggle, 2023. [Online]. Available: https://www.kaggle.com/datasets/tejpal123/apple-quality-analysis-dataset

[12] Yanxia Yang, Pu Wang, and Xuejin Ga, “A Novel Radial Basis Function Neural Network with High Generalization Performance for Nonlinear Process Modelling,” Processes, vol. 10, no. 1, pp. 1-16, 2022.
[CrossRef] [Google Scholar] [Publisher Link] 

[13] Jia-Chao Wu, “An Evolutionary Self-organizing Cost-Sensitive Radial Basis Function Neural Network for Imbalanced Medical Data,” International Journal of Computer and Information Security, pp. 1-11, 2020.
[CrossRef] [Google Scholar] [Publisher Link] 

[14] Tulika Chutia, and Nomi Baruah, “A Review on Emotion Detection by Using Deep Learning,” Artificial Intelligence Review, vol. 57, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[15] D. Vidya, Shivanand Rumma, and Mallikarjun Hangargi, “Apple Classification Based on MRI Images Using VGG16 Convolutional Deep Learning Model,” 2023.
[CrossRef] [Publisher Link] 

[16] M. Çakmak, Classification of Apple Quality Using XGBoost Machine Learning Model, 2024.
[Publisher Link] 

[17] Silvia Krug, and Tino Hutschenreuther, “A Case Study Toward Apple Cultivar Classification Using Deep Learning,” AgriEngineering, vol. 5, pp. 2, pp. 814-828, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[18] Ming-Chih Chen, Yin-Ting Cheng, and Chun-Yu Liu, “Implementation of a Fruit Quality Classification Application,” Sensors and Materials, vol. 34, no. 1, pp. 151-162, 2022.
[CrossRef] [Google Scholar] [Publisher Link]