OPTIMASI MODEL PENGKLASIFIKASI BIBIT KELAPA LOKAL DENGAN ALGORITMA DEEP LEARNING CONVOLUTIONAL NEURAL NETWORK
Keywords:
Deep Learning; Convolutional Neural Network; Bibit Kelapa Lokal; Klasifikasi; Pertanian Cerdas.
Abstract
Klasifikasi bibit kelapa lokal masih mengandalkan metode manual yang subjektif dan tidak konsisten. Penelitian ini mengembangkan model Convolutional Neural Network (CNN) yang dioptimasi untuk klasifikasi empat kelas kualitas bibit: Premium, Standard, Low, dan Rejected. Dataset berisi 4.004 citra, dengan augmentasi dan stratified splitting untuk menjaga distribusi kelas. Model terdiri dari tiga blok konvolusi dengan batch normalization, max-pooling, dropout, dan fully connected layer, berjumlah 495.108 parameter terlatih. Optimasi dilakukan melalui fine-tuning, hyperparameter tuning, dan regularisasi. Hasil menunjukkan akurasi 96%, precision, recall, dan F1-score tinggi, serta ROC-AUC mendekati 1.00 untuk semua kelas, menandakan kemampuan klasifikasi yang akurat dan generalisasi baik. Model ini efisien secara komputasi, siap diterapkan di lapangan untuk mendukung peningkatan kualitas bibit kelapa lokal.
Downloads
Download data is not yet available.
References
[1] Badan Pusat Statistik Provinsi Riau. Provinsi Riau dalam angka 2024. Riau: BPS-Statistics Riau Province; 2024. Available from: https://riau.bps.go.id/id/publication/2024/02/28/b75ed69ddf689a2e23f46207/provinsi-riau-dalam-angka-2024.html.
[2] Badan Pusat Statistik Kabupaten Indragiri Hilir. Statistik daerah Kabupaten Indragiri Hilir 2024. Indragiri Hilir: BPS-Statistics Indragiri Hilir; 2024. Available from: https://inhilkab.bps.go.id/id/publication/2024/09/26/10308813891de11918eb9e53/statistik-daerah-kabupaten-indragiri-hilir-2024.html.
[3] Ridha MR, Yunita F. Pemilihan Bibit Kelapa Menggunakan Metode Nearest Mean Classifier Untuk Masyarakat Petani Kelapa Di Kabupaten Indragiri Hilir. J Perangkat Lunak. 2020;2(3):101–14. doi:10.32520/jupel.v2i3.1306.
[4] Usman U, Yunita F, Ridha MR. Improving classification accuracy of local coconut fruits with image augmentation and deep learning algorithm convolutional neural networks (CNN). J Appl Data Sci. 2025;6(1):1-19. doi:10.47738/jads.v6i1.389.
[5] Kaur A, Kukreja V, Garg N, Rajput K, Sharma R. Multi-class classification of coconut leaf disease using fine-tuned ResNet50 model. In: 2024 IEEE 9th International Conference for Convergence in Technology (I2CT); 2024. doi:10.1109/I2CT61223.2024.10544047.
[6] Hasan H, Al Kakoun R, Massaad G, Awad M. Advancing Agricultural Sustainability Through an AI-Powered Classification Framework of Plant Pests and Diseases. IFIP Adv Inf Commun Technol, IFIPAICT. 2024;715:349-62. Cited 0 times. doi:10.1007/978-3-031-63227-3_25.
[7] Megalingam RK, Manoharan SK, Maruthababu RB. Integrated fuzzy and deep learning model for identification of coconut maturity without human intervention. Neural Comput Appl. 2024;36(11):6133-45. doi:10.1007/s00521-023-09402-2.
[8] Amin M, Bindas A. Pengklasifikasi bibit kelapa menggunakan algoritma deep learning convolutional neural network. J Perangkat Lunak. 2024;6(3):405-13. doi:10.32520/jupel.v6i3.3654.
[9] Singh P, Verma A, Alex JSR. Disease and pest infection detection in coconut tree through deep learning techniques. Comput Electron Agric. 2021;182:105986. doi:10.1016/j.compag.2021.105986.
[10] Kumar RR, Singh A. Utilizing Hybrid Intelligence: A CNN-SVM Method for Accurate Classification of Neem Leaf Diseases. 2024 IEEE 3rd World Conf Appl Intell Comput AIC. 2024:1530-3. doi:10.1109/AIC61668.2024.10730833.
[11] Kavithamani V, UmaMaheswari S. Investigation of deep learning for whitefly identification in coconut tree leaves. Intell Syst Appl. 2023;20:200290. doi:10.1016/j.iswa.2023.200290.
[12] Yao Z, Huang M. Deep learning in tropical leaf disease detection: advantages and applications. Trop Plants. 2024;3(1):e020. doi:10.48130/tp-0024-0018.
[13] Muni A, Amin M. Deteksi dan klasifikasi hama dan penyakit tanaman kelapa menggunakan Nearest Mean Classifier di Kabupaten Indragiri Hilir. J Perangkat Lunak. 2024;6(3):414-27. doi:10.32520/jupel.v6i3.3655.
[14] Muni A, Jibril M. Penerapan metode Naive Bayes classifier dalam pemilihan kualitas bibit kelapa untuk masyarakat petani kelapa di Indragiri Hilir. J Perangkat Lunak. 2023;5(3):313-22. doi:10.32520/jupel.v5i3.2780.
[15] Liu Q, Zhang Y, Chen J, Sun C, Huang M, Che M, Li C, Lin S. An improved DeepLab V3+ network-based coconut CT image segmentation method. Front Plant Sci. 2023;14:1139666. doi:10.3389/fpls.2023.1139666.
[16] Megalingam RK, Kuttankulangara Manoharan S, Babu DHTA, Sriram G, Lokesh K, Kariparambil Sudheesh S. Coconut trees classification based on height, inclination, and orientation using MIN-SVM algorithm. Neural Comput Appl. 2023;35(16):12055-12071. doi:10.1007/s00521-023-08339-w.
[17] Hieu NTT, Trieu NM, Thinh NT. Using Artificial Neural Network to grade internal quality of coconuts based on density. Lect Notes Mech Eng. 2022;413-23. Doi: 10.1007/978-981-19-1968-8_33.
[18] Prasetyo DY, Rianto B, Rais MS, Suwanti N. Diagnosa Dini Penyakit Mata Menerapkan Metode Case Based Reasoning (CBR). J. Media Inform. Budidarma. 2021 Apr;5(2):360-9.
[19] Yodrot T, Sutacha C, Orachon T, Jangjongdee N, Boonyasuwanno S. A study on the potency of hybrid models: Detecting diseases in cucumber leaves with pre-trained CNNs and SVM. In: 12th International Electrical Engineering Congress (iEECON 2024). 2024. doi: 10.1109/iEECON60677.2024.10537828.
[20] Kumar RR, Chauhan R, Dhondiyal SA, Singh A. Deep learning-driven diagnosis: A CNN-SVM hybrid approach for automated detection of strawberry leaf diseases. In: 2024 IEEE 3rd World Conference on Applied Intelligence and Computing (AIC). 2024. p. 1467-70. doi: 10.1109/AIC61668.2024.10731051.
[21] Geng M, Wang Y, Tian Y, Huang T. CNUSVM: Hybrid CNN-uneven SVM model for imbalanced visual learning. In: 2016 IEEE 2nd International Conference on Multimedia Big Data (BigMM). 2016. p. 186-93. doi: 10.1109/BigMM.2016.19.
[22] Özgür F, Arikan N, Karadaǧ OO. Comparison of a deep learning and a hybrid model for classification of an unbalanced urgent cases dataset for human faces. In: 9th International Conference on Computer Science and Engineering (UBMK); 2024. p. 563-8. doi: 10.1109/UBMK63289.2024.10773568.
[23] Datt RM, Kukreja V. Pre-trained CNN and SVM based hybrid model for apple crops phenological phase recognition. In: ICAN 2022 - 3rd International Conference on Computing, Analytics and Networks - Proceedings. 2022. doi: 10.1109/ICAN56228.2022.10007213.
[24] Hegazy AE, Makhlouf MA, El-Tawel GS. Improved salp swarm algorithm for feature selection. J King Saud Univ Comput Inf Sci. 2020;32(3):335-344. doi:10.1016/j.jksuci.2018.06.003.
[25] Banerjee D, Kukreja V, Hariharan S, Jain V, Vats S. Mango Disease Detection System Using CNN and SVM: A Comparative Study with Traditional Diagnostic Methods. In: 2023 World Conference on Communication and Computing, WCONF 2023. 2023. doi:10.1109/WCONF58270.2023.10235224.
[26] Wu J. Improve light weight convolutional neural networks for face recognition with multi-style recalibration module. Proc SPIE Int Soc Opt Eng. 2023;12602:126023F. doi:10.1117/12.2668275.
[27] Pham H, Tan Y, Singh T, Pavlopoulos V, Patnayakuni R. A multi-head attention-like feature selection approach for tabular data. Knowl-Based Syst. 2024;301:112250. doi:10.1016/j.knosys.2024.112250.
[2] Badan Pusat Statistik Kabupaten Indragiri Hilir. Statistik daerah Kabupaten Indragiri Hilir 2024. Indragiri Hilir: BPS-Statistics Indragiri Hilir; 2024. Available from: https://inhilkab.bps.go.id/id/publication/2024/09/26/10308813891de11918eb9e53/statistik-daerah-kabupaten-indragiri-hilir-2024.html.
[3] Ridha MR, Yunita F. Pemilihan Bibit Kelapa Menggunakan Metode Nearest Mean Classifier Untuk Masyarakat Petani Kelapa Di Kabupaten Indragiri Hilir. J Perangkat Lunak. 2020;2(3):101–14. doi:10.32520/jupel.v2i3.1306.
[4] Usman U, Yunita F, Ridha MR. Improving classification accuracy of local coconut fruits with image augmentation and deep learning algorithm convolutional neural networks (CNN). J Appl Data Sci. 2025;6(1):1-19. doi:10.47738/jads.v6i1.389.
[5] Kaur A, Kukreja V, Garg N, Rajput K, Sharma R. Multi-class classification of coconut leaf disease using fine-tuned ResNet50 model. In: 2024 IEEE 9th International Conference for Convergence in Technology (I2CT); 2024. doi:10.1109/I2CT61223.2024.10544047.
[6] Hasan H, Al Kakoun R, Massaad G, Awad M. Advancing Agricultural Sustainability Through an AI-Powered Classification Framework of Plant Pests and Diseases. IFIP Adv Inf Commun Technol, IFIPAICT. 2024;715:349-62. Cited 0 times. doi:10.1007/978-3-031-63227-3_25.
[7] Megalingam RK, Manoharan SK, Maruthababu RB. Integrated fuzzy and deep learning model for identification of coconut maturity without human intervention. Neural Comput Appl. 2024;36(11):6133-45. doi:10.1007/s00521-023-09402-2.
[8] Amin M, Bindas A. Pengklasifikasi bibit kelapa menggunakan algoritma deep learning convolutional neural network. J Perangkat Lunak. 2024;6(3):405-13. doi:10.32520/jupel.v6i3.3654.
[9] Singh P, Verma A, Alex JSR. Disease and pest infection detection in coconut tree through deep learning techniques. Comput Electron Agric. 2021;182:105986. doi:10.1016/j.compag.2021.105986.
[10] Kumar RR, Singh A. Utilizing Hybrid Intelligence: A CNN-SVM Method for Accurate Classification of Neem Leaf Diseases. 2024 IEEE 3rd World Conf Appl Intell Comput AIC. 2024:1530-3. doi:10.1109/AIC61668.2024.10730833.
[11] Kavithamani V, UmaMaheswari S. Investigation of deep learning for whitefly identification in coconut tree leaves. Intell Syst Appl. 2023;20:200290. doi:10.1016/j.iswa.2023.200290.
[12] Yao Z, Huang M. Deep learning in tropical leaf disease detection: advantages and applications. Trop Plants. 2024;3(1):e020. doi:10.48130/tp-0024-0018.
[13] Muni A, Amin M. Deteksi dan klasifikasi hama dan penyakit tanaman kelapa menggunakan Nearest Mean Classifier di Kabupaten Indragiri Hilir. J Perangkat Lunak. 2024;6(3):414-27. doi:10.32520/jupel.v6i3.3655.
[14] Muni A, Jibril M. Penerapan metode Naive Bayes classifier dalam pemilihan kualitas bibit kelapa untuk masyarakat petani kelapa di Indragiri Hilir. J Perangkat Lunak. 2023;5(3):313-22. doi:10.32520/jupel.v5i3.2780.
[15] Liu Q, Zhang Y, Chen J, Sun C, Huang M, Che M, Li C, Lin S. An improved DeepLab V3+ network-based coconut CT image segmentation method. Front Plant Sci. 2023;14:1139666. doi:10.3389/fpls.2023.1139666.
[16] Megalingam RK, Kuttankulangara Manoharan S, Babu DHTA, Sriram G, Lokesh K, Kariparambil Sudheesh S. Coconut trees classification based on height, inclination, and orientation using MIN-SVM algorithm. Neural Comput Appl. 2023;35(16):12055-12071. doi:10.1007/s00521-023-08339-w.
[17] Hieu NTT, Trieu NM, Thinh NT. Using Artificial Neural Network to grade internal quality of coconuts based on density. Lect Notes Mech Eng. 2022;413-23. Doi: 10.1007/978-981-19-1968-8_33.
[18] Prasetyo DY, Rianto B, Rais MS, Suwanti N. Diagnosa Dini Penyakit Mata Menerapkan Metode Case Based Reasoning (CBR). J. Media Inform. Budidarma. 2021 Apr;5(2):360-9.
[19] Yodrot T, Sutacha C, Orachon T, Jangjongdee N, Boonyasuwanno S. A study on the potency of hybrid models: Detecting diseases in cucumber leaves with pre-trained CNNs and SVM. In: 12th International Electrical Engineering Congress (iEECON 2024). 2024. doi: 10.1109/iEECON60677.2024.10537828.
[20] Kumar RR, Chauhan R, Dhondiyal SA, Singh A. Deep learning-driven diagnosis: A CNN-SVM hybrid approach for automated detection of strawberry leaf diseases. In: 2024 IEEE 3rd World Conference on Applied Intelligence and Computing (AIC). 2024. p. 1467-70. doi: 10.1109/AIC61668.2024.10731051.
[21] Geng M, Wang Y, Tian Y, Huang T. CNUSVM: Hybrid CNN-uneven SVM model for imbalanced visual learning. In: 2016 IEEE 2nd International Conference on Multimedia Big Data (BigMM). 2016. p. 186-93. doi: 10.1109/BigMM.2016.19.
[22] Özgür F, Arikan N, Karadaǧ OO. Comparison of a deep learning and a hybrid model for classification of an unbalanced urgent cases dataset for human faces. In: 9th International Conference on Computer Science and Engineering (UBMK); 2024. p. 563-8. doi: 10.1109/UBMK63289.2024.10773568.
[23] Datt RM, Kukreja V. Pre-trained CNN and SVM based hybrid model for apple crops phenological phase recognition. In: ICAN 2022 - 3rd International Conference on Computing, Analytics and Networks - Proceedings. 2022. doi: 10.1109/ICAN56228.2022.10007213.
[24] Hegazy AE, Makhlouf MA, El-Tawel GS. Improved salp swarm algorithm for feature selection. J King Saud Univ Comput Inf Sci. 2020;32(3):335-344. doi:10.1016/j.jksuci.2018.06.003.
[25] Banerjee D, Kukreja V, Hariharan S, Jain V, Vats S. Mango Disease Detection System Using CNN and SVM: A Comparative Study with Traditional Diagnostic Methods. In: 2023 World Conference on Communication and Computing, WCONF 2023. 2023. doi:10.1109/WCONF58270.2023.10235224.
[26] Wu J. Improve light weight convolutional neural networks for face recognition with multi-style recalibration module. Proc SPIE Int Soc Opt Eng. 2023;12602:126023F. doi:10.1117/12.2668275.
[27] Pham H, Tan Y, Singh T, Pavlopoulos V, Patnayakuni R. A multi-head attention-like feature selection approach for tabular data. Knowl-Based Syst. 2024;301:112250. doi:10.1016/j.knosys.2024.112250.
Published
2025-10-31
How to Cite
Jibril, M., & Isya Alfassa, A. (2025). OPTIMASI MODEL PENGKLASIFIKASI BIBIT KELAPA LOKAL DENGAN ALGORITMA DEEP LEARNING CONVOLUTIONAL NEURAL NETWORK. JURNAL PERANGKAT LUNAK, 7(3), 273-282. https://doi.org/10.32520/jupel.v7i3.4684
Section
Articles
Copyright (c) 2025 Muhammad Jibril, Achamd Isya Alfassa
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
