CNN Pruning for Edge Computing-Based Corn Disease Detection with a Novel NG-Mean Accuracy Loss Optimization

Aji Gautama Putrada, Ikke Dian Oktaviani, Mohamad Nurkamal Fauzan, Nur Alamsyah

Abstract


Plant disease detection studies disease attacks in plants detected on the leaves using computer vision. However, some plant disease detection solutions still utilize cloud computing, where the problems include slow processing times and misuse of data privacy. This study aims to evaluate the performance of convolutional neural network (CNN) pruning in edge computing-based plant disease detection. We use Kaggle's plant disease image dataset, which contains three corn diseases. We also created an edge computing system architecture for plant disease detection utilizing the latest communication technology and middleware. Next, we developed an optimal CNN model for plant disease detection using grid search. We pruned the CNN model in the final step and tested its performance. In this step, we developed a novel normalized-geometric mean (NG-mean) method for accuracy loss optimization. The test results show that class weights can optimize specificity and g-mean on the imbalanced dataset, with values of 0.995 and 0.983, respectively. The grid search results then optimize the optimization method's hyperparameters, learning rate, batch size, and epoch to achieve the highest accuracy of 0.947. Applying pruning produces several models with variations in sparsity and scheduling methods. We used the new NG-mean method to find the best compressed model. It had constant scheduling, 0.8 sparsity, a mean accuracy loss of 1.05%, and a CR of 2.71×. This study enhances the efficiency and privacy of plant disease detection by utilizing edge computing and optimizing CNN models, leading to faster processing and better data security. Future work could explore the application of the novel NG-Mean method in other domains and the integration of additional plant species and diseases into the detection system.

Keywords


Convolutional Neural Network; Pruning; Edge Computing; Corn Disease Detection; Accuracy Loss Optimization

Full Text:

Link Download

References


Ahia, O., Kreutzer, J., & Hooker, S. (2021). The Low-Resource Double Bind: An Empirical Study of Pruning for Low-Resource Machine Translation (arXiv:2110.03036). arXiv. https://doi.org/10.48550/arXiv.2110.03036

Al-Adhaileh, M. H., Verma, A., Aldhyani, T. H., & Koundal, D. (2023). Potato blight detection using fine-tuned CNN architecture. Mathematics, 11(6), 1516. https://doi.org/10.3390/math11061516

Anim-Ayeko, A. O., Schillaci, C., & Lipani, A. (2023). Automatic blight disease detection in potato (Solanum tuberosum L.) and tomato (Solanum lycopersicum, L. 1753) plants using deep learning. Smart Agricultural Technology, 4, 100178. https://doi.org/10.1016/j.atech.2023.100178

Ashwini, C., & Sellam, V. (2023). Analyzing The Prediction Accuracy Of Corn Leaf Diseases Using A Pre-Trained Network Model. 2023 International Conference on Advancement in Computation & Computer Technologies (InCACCT), 87–91. https://doi.org/10.1109/InCACCT57535.2023.10141840

Choudhary, K., Nersisyan, N., Lin, E., Chandrasekaran, S., Mayani, R., Pottier, L., Murillo, A. P., Virdone, N. K., Kee, K., & Deelman, E. (2022). Application of Edge-to-Cloud Methods Toward Deep Learning. 2022 IEEE 18th International Conference on E-Science (e-Science), 415–416. https://doi.org/10.1109/eScience55777.2022.00065

Cui, L., Su, X., Ming, Z., Chen, Z., Yang, S., Zhou, Y., & Xiao, W. (2022). CREAT: Blockchain-Assisted Compression Algorithm of Federated Learning for Content Caching in Edge Computing. IEEE Internet of Things Journal, 9(16), 14151–14161. https://doi.org/10.1109/JIOT.2020.3014370

Dagwale, S. S., & Adakane, P. (2023). Prediction of Leaf Species & Disease Using Ai for Various Plants. Int. J. Multidiscip. Res, 5, 23034169. https://doi.org/10.36948/ijfmr.2023.v05i03.4169.

Degani, O., Movshowitz, D., Dor, S., Meerson, A., & Rabinovitz, O. (2018). Evaluating Azoxystrobin Seed Coating Against Maize Late Wilt Disease Using a Sensitive qPCR-Based Method. Plant Disease, 103. https://doi.org/10.1094/PDIS-05-18-0759-RE

Dong, X., Li, B., & Song, Y. (2023). An Optimization Method For Pruning Rates of Each Layer in CNN Based on the GA-SMSM. https://doi.org/10.21203/rs.3.rs-2738666/v1

Escobar, L., Gallardo, P., González-Anaya, J., González, J. L., Montúfar, G., & Morales, A. H. (2022). Enumeration of max-pooling responses with generalized permutohedra. https://doi.org/10.48550/ARXIV.2209.14978

Fan, W., Chu, F., Wang, H., & Yu, P. S. (2002). Pruning and dynamic scheduling of cost-sensitive ensembles. AAAI/IAAI, 146–151. https://cdn.aaai.org/AAAI/2002/AAAI02-023.pdf

Fernando, K. R. M., & Tsokos, C. P. (2022). Dynamically Weighted Balanced Loss: Class Imbalanced Learning and Confidence Calibration of Deep Neural Networks. IEEE Transactions on Neural Networks and Learning Systems, 33(7), 2940–2951. https://doi.org/10.1109/TNNLS.2020.3047335

Gajjar, R., Gajjar, N., Thakor, V. J., Patel, N. P., & Ruparelia, S. (2022). Real-time detection and identification of plant leaf diseases using convolutional neural networks on an embedded platform. The Visual Computer, 38(8), 2923–2938. https://doi.org/10.1007/s00371-021-02164-9

Gangopadhyay, B., Dasgupta, P., & Dey, S. (2023). Safety Aware Neural Pruning for Deep Reinforcement Learning (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 37(13), 16212–16213. https://doi.org/10.1609/aaai.v37i13.26966

Jia, Y., Liu, B., Dou, W., Xu, X., Zhou, X., Qi, L., & Yan, Z. (2022). CroApp: A CNN-based resource optimization approach in edge computing environment. IEEE Transactions on Industrial Informatics, 18(9), 6300–6307. https://doi.org/10.1109/TII.2022.3154473.

Jiang, H., Zhang, L. L., Li, Y., Wu, Y., Cao, S., Cao, T., Yang, Y., Li, J., Yang, M., & Qiu, L. (2023). Accurate and Structured Pruning for Efficient Automatic Speech Recognition. https://doi.org/10.48550/ARXIV.2305.19549

Joardar, B. K., Doppa, J. R., Li, H., Chakrabarty, K., & Pande, P. P. (2023). ReaLPrune: ReRAM Crossbar-Aware Lottery Ticket Pruning for CNNs. IEEE Transactions on Emerging Topics in Computing, 11(2), 303–317. https://doi.org/10.1109/TETC.2022.3223630

Kurtic, E., Campos, D., Nguyen, T., Frantar, E., Kurtz, M., Fineran, B., Goin, M., & Alistarh, D. (2022). The Optimal BERT Surgeon: Scalable and Accurate Second-Order Pruning for Large Language Models. https://doi.org/10.48550/ARXIV.2203.07259

Lei, F., Liu, X., Dai, Q., & Ling, B. W.-K. (2020). Shallow convolutional neural network for image classification. SN Applied Sciences, 2(1), 97. https://doi.org/10.1007/s42452-019-1903-4

Liu, W., Mo, J., & Zhong, F. (2023). Class Imbalanced Medical Image Classification Based on Semi-Supervised Federated Learning. Applied Sciences, 13(4), Article 4. https://doi.org/10.3390/app13042109

Luo, J.-H., Zhang, H., Zhou, H.-Y., Xie, C.-W., Wu, J., & Lin, W. (2018). ThiNet: Pruning CNN filters for a thinner net. IEEE Transactions on Pattern Analysis and Machine Intelligence, 41(10), 2525–2538. https://doi.org/10.1109/TPAMI.2018.2858232.

Moon, S., Byun, Y., Park, J., Lee, S., & Lee, Y. (2019). Memory-reduced network stacking for edge-level CNN architecture with structured weight pruning. IEEE Journal on Emerging and Selected Topics in Circuits and Systems, 9(4), 735–746. https://doi.org/10.1109/JETCAS.2019.2952137.

Nagarajan, P., Warnell, G., & Stone, P. (2019). Deterministic Implementations for Reproducibility in Deep Reinforcement Learning (arXiv:1809.05676). arXiv. http://arxiv.org/abs/1809.05676

Pamungkas, W. G., Wardhana, M. I. P., Sari, Z., & Azhar, Y. (2023). Leaf Image Identification: CNN with EfficientNet-B0 and ResNet-50 Used to Classified Corn Disease. Jurnal RESTI (Rekayasa Sistem Dan Teknologi Informasi), 7(2), 326–333. https://doi.org/10.29207/resti.v7i2.4736.

Pandey, G., & Dukkipati, A. (2017). Unsupervised feature learning with discriminative encoder. 2017 IEEE International Conference on Data Mining (ICDM), 367–376. https://doi.org/10.1109/ICDM.2017.46.

Pane, S. F., Ramdan, J., Putrada, A. G., Fauzan, M. N., Awangga, R. M., & Alamsyah, N. (2022). A Hybrid CNN-LSTM Model With Word-Emoji Embedding For Improving The Twitter Sentiment Analysis on Indonesia’s PPKM Policy. 2022 6th International Conference on Information Technology, Information Systems and Electrical Engineering (ICITISEE), 51–56. https://doi.org/10.1109/ICITISEE57756.2022.10057720

Prabowo, S., Putrada, A. G., Oktaviani, I. D., & Abdurohman, M. (2023). Camera-Based Smart Lighting System that complies with Indonesia’s Personal Data Protection Act. 2023 International Conference on Advancement in Data Science, E-Learning and Information System (ICADEIS), 1–6. https://doi.org/10.1109/ICADEIS58666.2023.10271086.

Putrada, A. G., Abdurohman, M., Perdana, D., & Nuha, H. H. (2023a). EdgeSL: Edge-Computing Architecture on Smart Lighting Control With Distilled KNN for Optimum Processing Time. IEEE Access, 11, 64697–64712. https://doi.org/10.1109/ACCESS.2023.3288425

Putrada, A. G., Abdurohman, M., Perdana, D., & Nuha, H. H. (2023b). Shuffle Split-Edited Nearest Neighbor: A Novel Intelligent Control Model Compression for Smart Lighting in Edge Computing Environment. In Information Systems for Intelligent Systems: Proceedings of ISBM 2022 (pp. 219–227). Springer. https://doi.org/10.1007/978-981-19-7447-2_20.

Putrada, A. G., Abdurohman, M., Perdana, D., & Nuha, H. H. (2024). Q8KNN: A Novel 8-Bit KNN Quantization Method for Edge Computing in Smart Lighting Systems with NodeMCU. In K. Arai (Ed.), Intelligent Systems and Applications (Vol. 824, pp. 598–615). Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-47715-7_41

Putrada, A. G., Alamsyah, N., Pane, S. F., Fauzan, M. N., & Perdana, D. (2023). Knowledge Distillation for a Lightweight Deep Learning-Based Indoor Positioning System on Edge Environments. 2023 International Seminar on Intelligent Technology and Its Applications (ISITIA), 370–375. https://doi.org/10.1109/ISITIA59021.2023.10220996

Qin, L., & Sun, J. (2023). Model Compression for Data Compression: Neural Network Based Lossless Compressor Made Practical. 2023 Data Compression Conference (DCC), 52–61. https://doi.org/10.1109/DCC55655.2023.00013

Sharma, S., & Vardhan, M. (2023). Hyperparameter Tuned Hybrid Convolutional Neural Network (H-CNN) for Accurate Plant Disease Classification. 2023 International Conference on Communication, Circuits, and Systems (IC3S), 1–6. https://doi.org/10.1109/IC3S57698.2023.10169257

Shrestha, U., Peter, D. T. J., Manandhar, S., Rajbanshi, S., Padal, S., & Student, U. (2020). System Design for Identification of Plant Leaf Diseases using Deep Learning for Web and Mobile Platform. https://www.semanticscholar.org/paper/System-Design-for-Identification-of-Plant-Leaf-Deep-Shrestha-Peter/97948b361657578fe0619fa33cb36e4d2efad442

Siahroudi, S. K., & Kudenko, D. (2023). An effective single-model learning for multi-label data. Expert Systems with Applications, 232, 120887. https://doi.org/10.1016/j.eswa.2023.120887

Tang, J., Liu, S., Liu, L., Yu, B., & Shi, W. (2020). LoPECS: A Low-Power Edge Computing System for Real-Time Autonomous Driving Services. IEEE Access, 8, 30467–30479. https://doi.org/10.1109/ACCESS.2020.2970728

Thanh, T. (2021). Grid Search of Convolutional Neural Network model in the case of load forecasting. Archives of Electrical Engineering, 70. https://doi.org/10.24425/aee.2021.136050

Velmurugan, S., Moorthy, R. S., & Angel, S. (2023). Computer Vision based Plant Disease Detection using Machine Learning Technique. International Journal, 11(7). https://www.academia.edu/download/104134478/ijeter021172023.pdf

Vocaturo, E., Zumpano, E., & Veltri, P. (2018). Image pre-processing in computer vision systems for melanoma detection. 2018 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2117–2124. https://doi.org/10.1109/BIBM.2018.8621507

Widianto, B., Utami, E., & Ariatmanto, D. (2023). Identifikasi Penyakit Tanaman Jagung Berdasarkan Citra Daun Menggunakan Convolutional Neural Network. Techno. Com, 22(3), 599–608. https://doi.org/10.33633/tc.v22i3.8425.

Ye, Y., Li, S., Liu, F., Tang, Y., & Hu, W. (2020). EdgeFed: Optimized federated learning based on edge computing. IEEE Access, 8, 209191–209198. https://doi.org/10.1109/ACCESS.2020.3038287.

Yucky, E. D. D., Putrada, A. G., & Abdurohman, M. (2021). IoT drone camera for a paddy crop health detector with RGB comparison. 2021 9th International Conference on Information and Communication Technology (ICoICT), 155–159. https://doi.org/10.1109/ICoICT52021.2021.9527421.

Zhan, T. (2022). Hyper-Parameter Tuning in Deep Neural Network Learning. Artificial Intelligence and Applications, 95–101. https://doi.org/10.5121/csit.2022.121809




DOI: http://dx.doi.org/10.35671/telematika.v17i2.2899

Refbacks

  • There are currently no refbacks.


 


Indexed by:

 

Telematika
ISSN: 2442-4528 (online) | ISSN: 1979-925X (print)
Published by : Universitas Amikom Purwokerto
Jl. Let. Jend. POL SUMARTO Watumas, Purwonegoro - Purwokerto, Indonesia


Creative Commons License This work is licensed under a Creative Commons Attribution 4.0 International License .