Comparative Analysis of CNN Algorithms for Mushroom Classification with Proposed Lightweight CNN Model

Ahmet Namlı; Didem Ölçer

doi:10.18016/ksutarimdoga.vi.1486797

EN TR

Comparative Analysis of CNN Algorithms for Mushroom Classification with Proposed Lightweight CNN Model

Abstract

The classification of mushroom species presents significant ecologic and health-related challenges; advancement in classification techniques is required to gain reliable identifications. This study aims to explain a methodology that was devised and evaluated in the development of a novel, lightweight Convolutional Neural Network (CNN) designed specifically for the task of mushroom classification. The paper provides a custom CNN model that is computationally cost-effective and capable of high-precision classification, fit for real-time usage. Hence, the proposed model was evaluated on this dataset of curated mushroom images with traditional classifiers and state-of-the-art CNN architectures, such as EfficientNet-B7, ResNet50, InceptionV3, and MobileNetV2. The custom model is depth-wise separations engineered in such a way that while they reduce the computational load, they don't compromise the effectiveness of the model. The custom model achieved a test score of 0.68, which is moderate compared to more established models such as EfficientNet-B7 or ResNet50. This approach helps the model function effectively even on platforms having low computational resources. A comprehensive evaluation reveals that a custom CNN has reasonable accuracy in the identification of different mushroom species vis-à-vis existing models, but also significantly lightens the classification process.

Keywords

CNN Algoritmalarının Mantar Sınıflandırmada Önerilen Hafif CNN Modeli ile Karşılaştırmalı Analizi

Öz

Mantar türlerinin sınıflandırılması, ekolojik ve sağlıkla ilgili önemli zorluklar ortaya koymaktadır; güvenilir tanımlamalar elde etmek için sınıflandırma tekniklerinde ilerleme kaydedilmesi gerekmektedir. Bu çalışma, mantar sınıflandırma görevi için özel olarak tasarlanmış yeni, hafif bir Evrişimsel Sinir Ağının (CNN) geliştirilmesi üzere tasarlanan ve değerlendirilen bir metodolojiyi açıklamayı amaçlamaktadır. Makale, hesaplama açısından uygun maliyetli ve yüksek hassasiyetli sınıflandırma yapabilen, gerçek zamanlı kullanıma uygun özel bir CNN modeli sunmaktadır. Bu nedenle, önerilen model, geleneksel sınıflandırıcılar ve EfficientNet-B7, ResNet50, InceptionV3 ve MobileNetV2 gibi son teknoloji CNN mimarileri ile mantar görüntülerinden oluşan bu veri kümesi üzerinde değerlendirilmiştir. Özel modelin, hesaplama karmaşıklığını azaltırken modelin etkinliğinden ve yeteneğinden ödün vermeyecek şekilde tasarlanmasına özen gösterilmiştir. Özel model, EfficientNet-B7 veya ResNet50 gibi daha yerleşik modellerle karşılaştırıldığında orta düzeyde bir değer olan 0,68'lik bir test puanı elde etti. Bu yaklaşım, modelin düşük hesaplama kaynaklarına sahip platformlarda bile etkili bir şekilde çalışmasına yardımcı olur. Kapsamlı bir değerlendirme, tasarlanan CNN'in yalnızca mevcut modellere kıyasla farklı mantar türlerinin tanımlanmasında makul bir doğruluğa sahip olduğunu değil, aynı zamanda sınıflandırma sürecini de önemli ölçüde hafiflettiğini ortaya koymaktadır.

Anahtar Kelimeler

References

Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., ... & Zheng, X. (2015). TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems. Retrieved from https://www.tensorflow. org
Boyacı, S., Ertugrul, O., Ertuğrul, G. Ö., & Gökalp, D. D. (2023). Kırşehir İlinde Seralarda Kullanılan Sulama Sularının Kalite Parametrelerinin Belirlenmesi. Kahramanmaraş Sütçü İmam Üniversitesi Tarım ve Doğa Dergisi, 26(5), 1178-1185.
Chollet, F., (2015). Keras: Deep learning for humans. GitHub. Inc.
Clevert, D. A., Unterthiner, T., & Hochreiter, S. (2016). Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs). 4th International Conference on Learning Representations, ICLR 2016 - Conference Track Proceedings. Retrieved from https://arxiv.org/ abs/1511.07289v5
Dan, K. (2020). The Nutritional Value and Application Progress of Edible Fungi. Modern Food, 15, 53–55. Hawksworth, D. L., & Lücking, R. (2017). Fungal Diversity Revisited: 2.2 to 3.8 Million Species. Microbiol Spectr, 5(4), 10-1128. doi: 10.1128/ MICROBIOLSPEC.FUNK-0052-2016.
He, K., Zhang, X., Ren, S., & Sun, J. (2015). Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification. CoRR, abs/1502.01852. Retrieved from http://arxiv.org/ abs/1502.01852
He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep Residual Learning for Image Recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 770–778). doi: 10.1109/CVPR.2016.90.
Hibbett, D. S., Binder, M., Bischoff, J. F., Blackwell, M., Cannon, P. F., Eriksson, O. E., ... & Zhang, N. (2007). A higher-level phylogenetic classification of the Fungi. Mycol Res, 111(5), 509–547. doi: 10.1016/J.MYCRES.2007.03.004.

Ioffe, S., & Szegedy, C. (2015). Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. 32nd International Conference on Machine Learning, ICML 2015, 1, 448–456. Retrieved from https://arxiv.org/abs/ 1502.03167v3
Kamilaris, A., & Prenafeta-Boldú, F. X. (2018). Deep learning in agriculture: A survey. Comput Electron Agric, 147, 70–90. doi: 10.1016/J.COMPAG.2018. 02.016.
Karadaş, K., & Bulut, O. D. (2024). Comparison of Predictive Performance of Data Mining Algorithms in Predicting Tomato Yield with the A Case Study in Igdir. Kahramanmaraş Sütçü İmam Üniversitesi Tarım ve Doğa Dergisi, 27(2), 443-452.
Ketwongsa, W., Boonlue, S., & Kokaew, U. (2022). A New Deep Learning Model for The Classification of Poisonous and Edible Mushrooms Based on Improved AlexNet Convolutional Neural Network. Applied Sciences (Switzerland), 12(7), 3409. doi: 10.3390/app12073409.
Liu, N. G., Ariyawansa, H. A., Hyde, K. D., Maharachchikumbura, S. S. N., Zhao, R. L., Phillips, A. J. L., ... & Jumpathong, J. (2016). Perspectives into the value of genera, families and orders in classification. mycosphere, 7, 1649–1668. doi: 10.5943/mycosphere/7/11/3.
Long, C., Yu, P., Li, H., & Li, H. (2023). Wild mushroom classification based on improved MobileViT_v2. In Proceedings of 2023 IEEE 3rd International Conference on Information Technology, Big Data and Artificial Intelligence, ICIBA 2023 (pp. 12–18). IEEE. doi: 10.1109/ICIBA56860.2023.10165212.
Ma, L., Gao, R., Han, H., Chen, C., Yan, Z., Zhao, J., ... & Xie, L. (2020). Efficient identification of Bachu mushroom by flourier transform infrared (FT-IR) spectroscopy coupled with PLS-GS-SVM. Optik (Stuttg), 224, 165712. doi: 10.1016/ J.IJLEO.2020.165712.
Peng, Y., Xu, Y., Shi, J., & Jiang, S. (2023). Wild Mushroom Classification Based on Improved MobileViT Deep Learning. Applied Sciences (Switzerland), 13(8), 4680. doi: 10.3390/ app13084680.
Portugal, I., Alencar, P., & Cowan, D. (2018). The use of machine learning algorithms in recommender systems: A systematic review. Expert Syst Appl, 97, 205–227. doi: 10.1016/J.ESWA.2017.12.020.
Ria, N. J., Badhon, S. M. S. I., Khushbu, S. A., Akter, S., & Hossain, S. A. (2021). State of art Research in Edible and Poisonous Mushroom Recognition. In 2021 12th International Conference on Computing Communication and Networking Technologies, ICCCNT 2021. Institute of Electrical and Electronics Engineers Inc. doi: 10.1109/ ICCCNT51525.2021.9579987.
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L. C. (2018). MobileNetV2: Inverted Residuals and Linear Bottlenecks. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 4510–4520. doi: 10.1109/CVPR.2018.00474.
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. (2014). Dropout: A Simple Way to Prevent Neural Networks from Overfitting. Journal of Machine Learning Research, 15(56), 1929–1958. Retrieved from http://jmlr.org/papers/ v15/srivastava14a.html
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016). Rethinking the Inception Architecture for Computer Vision. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2818–2826. doi: 10.1109/CVPR.2016.308.
Tan, M., & Le, Q. (2019). Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning (pp. 6105-6114). PMLR.
Tarawneh, O., Tarawneh, M., Sharrab, Y., & Husni, M. (2023). Mushroom classification using machine-learning techniques. AIP Conf Proc, 2979(1), e030003. doi: 10.1063/5.0174721.
Tutuncu, K., Cinar, I., Kursun, R., & Koklu, M. (2022). Edible and Poisonous Mushrooms Classification by Machine Learning Algorithms. In 2022 11th Mediterranean Conference on Embedded Computing, MECO 2022. Institute of Electrical and Electronics Engineers Inc. doi: 10.1109/MECO55406.2022.9797212.
Wang, B. (2022). Automatic Mushroom Species Classification Model for Foodborne Disease Prevention Based on Vision Transformer. Journal of Food Quality, 2022(1), 1173102. doi: 10.1155/ 2022/1173102.
Yan, Z., Liu, H., Li, J., & Wang, Y. (2023). Application of Identification and Evaluation Techniques for Edible Mushrooms: A Review. Critical Reviews in Analytical Chemistry, 53(3), 634–654. doi: 10.1080/10408347.2021.1969886.
Yu, Q., Guo, M., Zhang, B., Wu, H., Zhang, Y., & Zhang, L. (2020). Analysis of Nutritional Composition in 23 Kinds of Edible Fungi. Journal of Food Quality, 2020, 8821315. doi: 10.1155/ 2020/8821315.
Zahan, N., Hasan, M. Z., Malek, M. A., & Reya, S. S. (2021). A Deep Learning-Based Approach for Edible, Inedible and Poisonous Mushroom Classification. In 2021 International Conference on Information and Communication Technology for Sustainable Development, ICICT4SD 2021 - Proceedings (pp. 440–444). Institute of Electrical and Electronics Engineers Inc. doi: 10.1109/ICICT4SD50815.2021.9396845.
Zhang, Y., Mo, M., Yang, L., Mi, F., Cao, Y., Liu, C., ... & Xu, J. (2021). Exploring the Species Diversity of Edible Mushrooms in Yunnan, Southwestern China, by DNA Barcoding. J Fungi (Basel), 7(4), 310. doi: 10.3390/JOF7040310.
Zhao, H., Ge, F., Yu, P., & Li, H. (2021). Identification of Wild Mushroom Based on Ensemble Learning. In 2021 IEEE 4th International Conference on Big Data and Artificial Intelligence, BDAI 2021 (pp. 43–47). IEEE. doi: 10.1109/BDAI52447.2021. 9515225.
Zhecheng, L. (2023). Mushroom Classification Dataset. Retrieved from https://www.kaggle.com/ datasets/lizhecheng/mushroom-classification, Accessed: Apr. 30, 2024.

Details

Primary Language

English

Subjects

Agricultural Economics (Other)

Journal Section

Research Article

Authors

Ahmet Namlı
0000-0002-4649-3299
Türkiye

Didem Ölçer ^*
0000-0001-7736-1021
Türkiye

Early Pub Date

September 15, 2024

Publication Date

December 25, 2024

Submission Date

May 20, 2024

Acceptance Date

August 14, 2024

Published in Issue

Year 2024 Volume: 27 Number: Ek Sayı 1 (Suppl 1)

DOI

https://doi.org/10.18016/ksutarimdoga.vi.1486797

IZ

https://izlik.org/JA43XS44FY

Cite

RIS / Bibtex

APA

Namlı, A., & Ölçer, D. (2024). Comparative Analysis of CNN Algorithms for Mushroom Classification with Proposed Lightweight CNN Model. Kahramanmaraş Sütçü İmam Üniversitesi Tarım Ve Doğa Dergisi, 27(Ek Sayı 1 (Suppl 1), 243-253. https://doi.org/10.18016/ksutarimdoga.vi.1486797

Cited By

Prediction of Egg Weight in Japanese Quails (Coturnix coturnix japonica) with Internal Quality Traits Using Machine Learning Algorithms

Kahramanmaraş Sütçü İmam Üniversitesi Tarım ve Doğa Dergisi

https://doi.org/10.18016/ksutarimdoga.vi.1695149