Perancangan Aplikasi Untuk Klasifikasi Klon Daun Teh Seri Gambung (gmb) Menggunakan Algoritma Convolutional Neural Network
DOI:
https://doi.org/10.34818/eoe.v7i2.13008Abstract
Abstrak Pusat Penelitian Teh dan Kina PPTK Gambung di Indonesia membuat sebelas seri klon teh unggul gambung. Tiap seri klon gambung mempunyai cara menanam yang berbeda. Cara menanam yang salah akan menimbulkan gagal panen. Untuk menghindari adanya gagal panen, perlu adanya pengetahuan tentang tipe klon yang akan diproses. Untuk mengatasi permasalah tersebut, dibuat aplikasi berbasis android untuk klasifikasi tipe klon gambung berdasarkan foto daun yang akan diproses secara real time. Algoritma yang digunakan untuk klasifikasi adalah convolutional neural network dengan arsitektur mobilenet. Penelitian ini menggunakan dua jenis dataset dimana dataset pertama memiliki jumlah data sebanyak 1136 foto dan dataset kedua memiliki jumlah data sebanyak 830 foto. Parameter yang digunakan adalah learning rate 0.0001, optimizer adam, epoch 100 dan 204 neuron dalam hidden layer. Dari hasil pengujian yang dilakukan, diperoleh akurasi sebesar 60% dan hasil pengujian aplikasi sebesar 25%. Kata kunci : Jenis klon teh seri gambung, Klasifikasi, Convolutional Neural Network,Mobilenet Abstract The PPTK Gambung Tea and Quinine Research Center in Indonesia makes eleven series of superior gastric tea clones. Each series has a different way of planting. The wrong way to plant will lead to crop failure. To avoid crop failure, knowledge of the type of clone to be processed is needed. To overcome these problems, an Androidbased application is made for the classification of types of stomach clones based on leaf photos which will be processed in real time. The algorithm used for classification is a convolutional neural network with a mobilenet architecture. This study uses two types of data, the first dataset has 1136 photos and the second dataset has 830 photos. The parameters used are the learning rate of 0.0001, adam optimizer, epoch 100 and 204 neurons in the hidden layer. From the results of tests carried out, obtained by 60% testing and application testing results by 25%. Keywords: Types of series tea clones, Classification, Convolutional Neural Network, MobilenetDownloads
References
[1] D. Setyamidjaja, Teh Budidaya & Pengolahan Pascapanen, Yogyakarta: Kanisius, 2000.
[2] R. L. RUHIAT, Klasifikasi Citra Klon Teh Seri Gmb 1, Gmb 3, Gmb 4, Gmb 7, Gmb 9 Menggunakan MetodeGabor Wavelet Dan Support Vector Machine, Bandung: Universitas Telkom, 2019 .
[3] D. S. Effendi, M. Syakir, M. Yusron and Wiratno, Budidaya dan Pasca Panen, Bogor: Pusat Penelitian dan Pengembangan Perkebunan, 2010.
[4] Pusat Penelitian Teh dan Kina Gambung, "Pengenalan dan Identifikasi klon unggul seri GMB dan GMBS," Bandung.
[5] R. A. Rahman, A. Arifianto and K. N. Ramdhani, Klasifikasi Ras berdasarkan Citra Wajah menggunakan Convolutional Neural Network, Bandung: Universitas Telkom.
[6] I. S. Abdurrazaq, Suyanto and D. Q. Utama, Image-Based Classification of Snake Species Using Convolutional Neural Network, Bandung : Universitas Telkom, 2018.
[7] S. H. Lee, C. S. Chan, P. Wilkin and P. Remagnino, "Deep-Plant: Plant Identification With Convolutional Neural Networks," Proceedings - International Conference on Image Processing, ICIP, Vols. 2015-Decem, pp. 452-456, 2015.
[8] A.Oktaria, Klasifikasi Jenis Kayu Dengan Convolutional Neural Network (Cnn) Pada Citra Makroskopis Dengan Berbagai Tipe Arsitektur, Bandung: Universitas Telkom, 2019.
[9] R.Pratama, Deteksi Kadar Kolesterol Berdasarkan Kelopak Mata Dengan Menggunakan Metode Convolutional Neural Network Pada Klasifikasi Citra Berbasis Android, Bandung: Universiatas Telkom, 2019.
[10] S. L. Rabano, M. K. Cabatuan, E. Sybingco, E. P. Dadios and E. J. Calilung, "Common Garbage Classification Using Mobilenet," 2018 IEEE 10th International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment and Management, HNICEM 2018, pp. 1-4, 2018.
[11] CS231n: Convolutional Neural Networks for Visual Recognition, Dept. of Comp. Sci., Stanford University, Palo Alto, CA, USA, spring 2017. [Online].
[12] H. H. Aghdam and E. J. Heravi, Guide to Convolutional Neural Networks- A Practical Application to Traffic-Sign Detection and Classification.2017, Switzerland: Springer, 2017.
[13] A. F. Gad, Practical Computer Vision Applications Using Deep Learning with CNNs With Detailed Examples in Python Using TensorFlow and Kiv, Apress, 2018.
[14] A. G. Howard, M. Zhu, B. Chen, D. Kalenichenko, W. Wang, T. Weyand, M. Andreetto and H. Adam, Mobilenets: Efficient Convolutional Neural Networks for Mobile Vision, New York: Cornell University, 2017.
[15] L.Perez, J.Wang.The Effectiveness of Data Augmentation in Image Classification using Deep Learning.2017
[16] D.P.Kingma, J.Ba.Adam: A Method for Stochastic Optimization.ICLR 2015 International Conference on Learning
Representation.2014.
[17]J.G.Carney, P.Cunningham.The Epoch Interpretation of Learning. IEE Transaction On Neural Networks.1998
[18]A.Geron. Hands On Machine Learning With Scikit Learn And Tensorflow. O’Reilly Media, Inc.2017
[19]J.Brownlee. Deep Learning for Computer Vision: Image Classification,Object Detection,and Face Recognition in Python. Machine learning mastery. 2019



