TRANSFER LEARNING BERBASIS MOBILENET UNTUK DETEKSI PENYAKIT TANAMAN EUCALYPTUS PELLITA

• DEVIANA SELY WITA
• 14002609

---

ABSTRAK

 

ABSTRAK Nama : Deviana Sely Wita NIM : 14002609 Program Studi : Ilmu Komputer Fakultas : Teknologi Informasi Jenjang : Strata Dua (S2) Konsentrasi : Image Processing Judul Tesis : “Transfer Learning Berbasis MobileNet Untuk Deteksi Penyakit Tanaman Eucalyptus Pellita” Saat ini industri pulp di Indonesia menduduki peringkat kedelapan dunia dan industri kertas peringkat keenam dunia. Salah satu keunggulan dalam mendukung industri tersebut adalah karena Indonesia memiliki Hutan Tanaman Industri (HTI) yang luas dimana tanaman untuk bahan baku pulp dan kertas berasal. Jenis Eucalyptus pellita yang termasuk dalam famili Myrtaceae merupakan salah satu jenis prioritas untuk Hutan Tanaman Industri (HTI) karena daya adaptasinya dan kayunya dapat digunakan sebagai bahan baku pulp. Hutan Tanaman Industri dengan jenis ini dapat ditemukan terutama di Kalimantan dan Sumatera. Jenis tersebut menunjukkan pertumbuhan yang baik pada bentuk batang, kecepatan tumbuh dan kualitas kayu yang baik serta memiliki daya kecambah yang tinggi serta memiliki siklus tebang yang lebih pendek sekitar 7-8 tahun sehingga cepat dipanen. Pencegahan dan pengobatan penyakit daun merupakan salah satu proses utama penanaman. Diagnosis dini dan pengenalan akurat penyakit Eucalyptus Pellita dapat mengendalikan penyebaran penyakit dan mengurangi biaya produksi dan biaya pengobatan. Deteksi penyakit pada daun Eucalyptus pellita dapat dilakukan secara otomatis lebih cepat dengan memanfaatkan pengolahan citra digital dan kecerdasan buatan. Dalam penelitian ini, kami mengusulkan metode deteksi dengan arsitektur Deep Learning. Metode yang kami usulkan didasarkan pada pembelajaran transfer menggunakan MobileNet yang telah dilatih sebelumnya. Dataset citra dari lahan PT.Surya Hutani Jaya di Kalimantan Timur digunakan untuk melatih model tersebut. Dataset dibagi tiga kelas dimana 1 kelas daun sehat dan 2 kelas daun sakit yatu Bakteri Xanthomonas dan Jamur Cylindrocladium. Dengan rasio dataset 70 : 20 : 10 jumlah dataset training sejumlah 2370, validasi sejumlah 591, dan Testing sejumlah 177. Skenario Hyperparameter dilakukan pada model MobileNet untuk mengoptimalkan kinerjanya pada dataset daun Eucalyptus Pellita. Hasil eksperimen menunjukkan akurasi yang cukup baik yaitu mencapai 98%. Kata kunci : Industri Pulp, Eucalyptus Pellita, Deep Learning, Transfer Learning, MobileNet
 

KATA KUNCI

Transfer Learning,Mobile

---

DAFTAR PUSTAKA

 

DAFTAR PUSTAKA [1] M. A. Inail, E. B. Hardiyanto, and D. S. Mendham, “Growth Responses of Eucalyptus pellita F. Muell Plantations in South Sumatra to Macronutrient Fertilisers Following Several Rotations of Acacia mangium Willd.,” Forests, vol. 10, no. 12, p. 1054, Nov. 2019, doi: 10.3390/f10121054. [2] R. Gallo et al., “Growth and wood quality traits in the genetic selection of potential Eucalyptus dunnii Maiden clones for pulp production,” Industrial Crops and Products, vol. 123, pp. 434–441, Nov. 2018, doi: 10.1016/j.indcrop.2018.07.016. [3] E. D. Sulichantini, “PERTUMBUHAN TANAMAN Eucalyptus pellita F. Muell DI LAPANGAN DENGAN MENGGUNAKAN BIBIT HASIL PERBANYAKAN DENGAN METODE KULTUR JARINGAN, STEK PUCUK, DAN BIJI,” vol. 41, p. 7, 2016. [4] L. E. B. Blum, J. C. Dianese, and C. L. Costa, “Leaf Diseases On Eucalyptus Pellita F. Muell In Plantation Of Pt Surya Hutani Jaya At Sebulu, East Kalimantan,” Tropical Pest
Management, vol. 38, no. 2, pp. 155–159, Jan. 1992, doi: 10.1080/09670879209371674. [5] Department of Information Technology, Pyay Technological University, Y. M. Oo, N. C. Htun, and Department of Information Technology, Pyay Technological University, “Plant Leaf Disease Detection and Classification using Image Processing,” IJRE, vol. 5, no. 9, pp. 516–523, Nov. 2018, doi: 10.21276/ijre.2018.5.9.4. [6] AAA Fiber R&D, Y. Yuvika, A. Nasution, AAA Fiber R&D, A. Gafur, and AAA Fiber R&D, “Isolasi dan Penapisan in Vitro Aktinomiset untuk Mengendalikan Xanthomonas,” jfi, vol. 9, no. 5, pp. 160–164, Oct. 2013, doi: 10.14692/jfi.9.5.160. [7] P. I. R. Dalimunthe, E. B. M. Siregar, and N. Anna, “RESPON CYLINDROCLADIUM SP. TERHADAP FUNGISIDA BERBAHAN AKTIF MANCOZEB SECARA IN VITRO,” p. 11. [8] H. Hamdani, A. Septiarini, A. Sunyoto, S. Suyanto, and F. Utaminingrum, “Detection of oil palm leaf disease based on color histogram and supervised classifier,” Optik, vol. 245, p. 167753, Nov. 2021, doi: 10.1016/j.ijleo.2021.167753. [9] K. Muchtar, Chairuman, Yudha Nurdin, and Afdhal Afdhal, “Pendeteksian Septoria pada Tanaman Tomat dengan Metode Deep Learning berbasis Raspberry Pi,” RESTI, vol. 5, no. 1, pp. 107–113, Feb. 2021, doi: 10.29207/resti.v5i1.2831. [10] L. B. da Costa, O. L. F. de Carvalho, A. O. de Albuquerque, R. A. T. Gomes, R. F. Guimarães, and O. A. de Carvalho Júnior, “Deep semantic segmentation for detecting eucalyptus planted forests in the Brazilian territory using sentinel-2 imagery,” Geocarto International, pp. 1–13, Jun. 2021, doi: 10.1080/1 0106049.2021.1943009. [11] P. Yudha Adi Putra Wirabuana, R. Sadono, and S. Juniarso, “Planting depth management increases early growth, aboveground biomass, and carbon storage of Eucalyptus pellita at Ultisols in South Sumatra,” J.Degrade.Min.Land Manage. , vol. 7, no. 4, pp. 2253–2261, Jul. 2020, doi: 10.15243/jdmlm.2020.074.2253. [12] H. Indrayadi and Mardai, “Hama dan Penyakit Tanaman Acacia crassicarpa, Acacia mangium, dan Eucalyptus sp. di Plantation,” in Hama dan Penyakit Tanaman Acacia
crassicarpa, Acacia mangium, dan Eucalyptus sp. di Plantation, Edisi 1 (2007); Edisi 2 (2012); Edisi 3 (2016)., Divisi Penelitian Dan Pengembangan Kehutanan (R&D) Sinarmas Forestry. [13] R. R. Kusuma and L. Q. Aini, “KAJIAN MIKROBA RIZOSFER DI KAWASAN PERTANIAN ORGANIK KEBUN PERCOBAAN CANGAR,” p. 7. [14] E. F. Hutajulu, N. Anna, and E. B. M. Siregar, “Uji Infeksi Cylindrocladium sp pada Tiga Klon Hibrid Eucalyptus grandis x eucalyptus pellita,” p. 10. [15] M. I. Rosadi and M. Lutfi, “Identifikasi Jenis Penyakit Daun Jagung Menggunakan Deep Learning Pre- Trained Model,” p. 8, 2021. [16] F. Chollet, Deep learning with Python. Shelter Island, New York: Manning Publications Co, 2018. [17] S. Savalia and V. Emamian, “Cardiac Arrhythmia Classification by Multi-Layer Perceptron and Convolution Neural Networks,” Bioengineering, vol. 5, no. 2, p. 35, May 2018, doi: 10.3390/bioengineering5020035. [18] M. Sardogan, A. Tuncer, and Y. Ozen, “Plant Leaf Disease Detection and Classification Based on CNN with LVQ Algorithm,” in 2018 3rd International Conference on Computer
Science and Engineering (UBMK), Sarajevo, Sep. 2018, pp. 382–385. doi: 10.1109/UBMK.2018.8566635. [19] S. Zhang, W. Huang, and C. Zhang, “Three-channel convolutional neural networks for vegetable leaf disease recognition,” Cognitive Systems Research, vol. 53, pp. 31 –41, Jan. 2019, doi: 10.1016/j.cogsys.2018.04.006. [20] W. S. Eka Putra, “Klasifikasi Citra Menggunakan Convolutional Neural Network (CNN) pada Caltech 101,” JTITS, vol. 5, no. 1, Mar. 2016, doi: 10.12962/j23373539.v5i1.15696. [21] K. H. Mahmud and S. A. Faraby, “Klasifikasi Citra Multi-Kelas Menggunakan Convolutional Neural Network,” p. 10. [22] G. Shrestha, Deepsikha, M. Das, and N. Dey, “Plant Disease Detection Using CNN,” in 2020
IEEE Applied Signal Processing Conference (ASPCON), Kolkata, India, Oct. 2020, pp. 109– 113. doi: 10.1109/ASPCON49795.2020.9276722. [23] E. L. Da Rocha, L. Rodrigues, and J. F. Mari, “Maize leaf disease classification using convolutional neural networks and hyperparameter optimization,” in Anais do XVI Workshop
de Visão Computacional (WVC 2020), Brasil, Oct. 2020, pp. 104–110. doi: 10.5753/wvc.2020.13489. [24] Technological University of the Philippines, Manila 1000, Philippines and J. Velasco, “A Smartphone-Based Skin Disease Classification Using MobileNet CNN,” IJATCSE, pp. 2632–2637, Oct. 2019, doi: 10.30534/ijatcse/2019/116852019. [25] H. Abdurrohman, R. Dini, and A. P. Muharram, “Evaluasi Performa metode Deep Learning untuk Klasifikasi Citra Lesi Kulit The,” p. 6, 2018. [26] A. A. Jaelani and D. F. Y. Supratman, “PERANCANGAN APLIKASI UNTUK KLASIFIKASI KLON DAUN TEH SERI GAMBUNG (GMB) MENGGUNAKAN ALGORITMA CONVOLUTIONAL NEURAL NETWORK,” p. 9. [27] W. Sae-Lim, W. Wettayaprasit, and P. Aiyarak, “Convolutional Neural Networks Using MobileNet for Skin Lesion Classification,” in 2019 16th International Joint Conference on
Computer Science and Software Engineering (JCSSE), Chonburi, Thailand, Jul. 2019, pp. 242–247. doi: 10.1109/JCSSE.2019.8864155. [28] M. A. Z. Foeady, “Automated Diagnosis System of Diabetic Retinopathy Using GLCM Method and SVM Classifier,” p. 7, 2018. [29] Chen, J, Liu, Q., and Gao, L., “Visual tea leaf disease recognition using a convolutional neural network model,” Symmetry, 11, 2019, doi: https://doi. org/10.3390/sym11030343. [30] Y. Lu, S. Yi, N. Zeng, Y. Liu, and Y. Zhang, “Identification of rice diseases using deep convolutional neural networks,” Neurocomputing, vol. 267, pp. 378–384, Dec. 2017, doi: 10.1016/j.neucom.2017.06.023. [31] B. Liu, Y. Zhang, D. He, and Y. Li, “Identification of Apple Leaf Diseases Based on Deep Convolutional Neural Networks,” Symmetry, vol. 10, no. 1, p. 11, Dec. 2017, doi: 10.3390/sym10010011. [32] J. Ma, K. Du, F. Zheng, L. Zhang, Z. Gong, and Z. Sun, “A recognition method for cucumber diseases using leaf symptom images based on deep convolutional neural network,”
Computers and Electronics in Agriculture, vol. 154, pp. 18–24, Nov. 2018, doi: 10.1016/j.compag.2018.08.048. [33] K. P. Ferentinos, “Deep learning models for plant disease detection and diagnosis,”
Computers and Electronics in Agriculture, vol. 145, pp. 311–318, Feb. 2018, doi: 10.1016/j.compag.2018.01.009. [34] A. Picon, A. Alvarez-Gila, M. Seitz, A. Ortiz-Barredo, J. Echazarra, and A. Johannes, “Deep convolutional neural networks for mobile capture device-based crop disease classification in the wild,” Computers and Electronics in Agriculture, vol. 161, pp. 280–290, Jun. 2019, doi: 10.1016/j.compag.2018.04.002. [35] W. Liang, H. Zhang, G. Zhang, and H. Cao, “Rice Blast Disease Recognition Using a Deep Convolutional Neural Network,” Sci Rep, vol. 9, no. 1 , p. 2869, Dec. 2019, doi: 10.1038/s41598-019-38966-0. [36] A. Rajbongshi, T. Sarker, Md. M. Ahamad, and Md. M. Rahman, “Rose Diseases Recognition using MobileNet,” in 2020 4th International Symposium on Multidisciplinary
Studies and Innovative Technologies (ISMSIT), Istanbul, Turkey, Oct. 2020, pp. 1 –7. doi: 10.1109/ISMSIT50672.2020.9254420. [37] A. Elhassouny and F. Smarandache, “Smart mobile application to recognize tomato leaf diseases using Convolutional Neural Networks,” in 2019 International Conference of
Computer Science and Renewable Energies (ICCSRE), Agadir, Morocco, Jul. 2019, pp. 1 –4. doi: 10.1109/ICCSRE.2019.8807737. [38] J. G. A. Barbedo, “Impact of dataset size and variety on the effectiveness of deep learning and transfer learning for plant disease classification,” Computers and Electronics in
Agriculture, vol. 153, pp. 46–53, Oct. 2018, doi: 10.1016/j.compag.2018.08.013. [39] E. C. Too, L. Yujian, S. Njuki, and L. Yingchun, “A comparative study of fine-tuning deep learning models for plant disease identification,” Computers and Electronics in Agriculture, vol. 161, pp. 272–279, Jun. 2019, doi: 10.1016/j.compag.2018.03.032. [40] K. R. Aravind, P. Raja, R. Aniirudh, K. V. Mukesh, R. Ashiwin, and G. Vikas, “Grape Crop Disease Classification Using Transfer Learning Approach,” in Proceedings of the
International Conference on ISMAC in Computational Vision and Bio-Engineering 2018
(ISMAC-CVB), vol. 30, D. Pandian, X. Fernando, Z. Baig, and F. Shi, Eds. Cham: Springer International Publishing, 2019, pp. 1623–1633. doi: 10.1007/978-3-030-00665-5_150. [41] A. Krishnaswamy Rangarajan and R. Purushothaman, “Disease Classification in Eggplant Using Pre-trained VGG16 and MSVM,” Sci Rep, vol. 10, no. 1, p. 2322, Dec. 2020, doi: 10.1038/s41598-020-59108-x. [42] H. Alaa, K. Waleed, M. Samir, M. Tarek, H. Sobeah, and M. Abdul, “An Intelligent Approach for Detecting Palm Trees Diseases using Image Processing and Machine Learning,” IJACSA, vol. 11, no. 7, 2020, doi: 10.14569/IJACSA.2020.0110757. [43] R. A. Sholihati, I. A. Sulistijono, A. Risnumawan, and E. Kusumawati, “Potato Leaf Disease Classification Using Deep Learning Approach,” in 2020 International Electronics
Symposium (IES), Surabaya, Indonesia, Sep. 2020, pp. 392–397. doi: 10.1109/IES50839.2020.9231784. [44] Hengki Dharmawijaya, “Ringkasan Publik PT. Surya Hutani Jaya.” 2018. [Online]. Available: https://docplayer.info/74468156-Ringkasan-publik-pt-surya-hutani-jayaringkasan-publik-pt-surya-hutani-jaya.html [45] J. Komisaris and K. Utama, “Informasi Umum PT. Surya Hutani Jaya,” p. 19. [46] W. Hastomo, “CONVOLUTION NEURAL NETWORK ARSITEKTUR MOBILENET-V2 UNTUK MENDETEKSI TUMOR OTAK,” vol. 5, p. 5, 2021. [47] A. G. Howard et al., “MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications.” arXiv, Apr. 16, 2017. Accessed: Jun. 30, 2022. [Online]. Available: http://arxiv.org/abs/1704.04861 [48] C. Nisa’, E. Y. Puspaningrum, and H. Maulana, “Penerapan Metode Convolutional Neural Network untuk Klasifikasi Penyakit Daun Apel pada Imbalanced Data,” santika, vol. 1, pp. 169–175, Nov. 2020, doi: 10.33005/santika.v1i0.46.