IDENTIFIKASI JENIS KURMA DENGAN TRANSFER LEARNING DENSENET-201

• KUSNADI
• 14002633

---

ABSTRAK

 

ABSTRAK Nama : Kusnadi NIM : 14002633 Program Studi : Ilmu Komputer Jenjang : Strata Dua (S2) Konsentrasi : Image Processing Judul Tesis : “Identifikasi Jenis Kurma Dengan Transfer
Learning DenseNet-201” Jumlah jenis kurma di seluruh dunia lebih dari 400 jenis, sebagian besar berasal dari berbagai negara yang tersebar di wilayah Timur Tengah dan Afrika Utara. Negara Indonesia yang bermayoritas muslim menjadi salah satu pengimpor komoditi kurma. Jauhnya jarak pertanian kurma, jumlah jenis kurma dan adanya kemiripan antar kurma dari segi bentuk, ukuran, warna dan tekstur menyebabkan warga negara Indonesia tidak mudah dalam membedakannya. Identifikasi dengan kecerdasan buatan dapat mempermudah dalam membedakan jenis kurma. Pada makalah ini, kami mengusulkan metode transfer learning DenseNet-201 dengan model freeze all the pre-trained layers, re-train all the pre-trained layers dan
hyperparameter untuk identifikasi jenis kurma. Dataset kami kumpulkan dari kurma yang beredar di pasaran. Data image yang digunakan adalah citra tunggal kurma berjumlah 3.300 citra dengan 11 kelas meliputi Ajwa, Bam, Golden, Khalas, Khenaizi, Lulu, Mabroum, Medjool, Safawi, Sukari dan Tunisia. Penelitian ini bertujuan untuk mengidentifikasi dan mengevaluasi model pada metode yang diusulkan, serta membandingkan dan merekomendasikan dari hasil performa model untuk mengidentifikasi jenis kurma. Model dari Algoritma DenseNet-201 yang diusulkan telah menghasilkan tingkat akurasi pada model freeze all the pre-trained
layers sebesar 96,36%, re-train all the pre-trained layers sebesar 98,79%, dan
hyperparameter sebesar 99,09 %. Keseluruhan model berhasil mengidentifikasi jenis kurma dengan baik karena tingkat akurasi diatas 95%. Kata kunci: Buah Kurma, Identifikasi, Transfer Learning, Hyperparameter
 

KATA KUNCI

Transfer Learning,DENSENET-201

---

DAFTAR PUSTAKA

 

DAFTAR PUSTAKA [1] O. Aiadi and M. L. Kherfi, “A new method for automatic date fruit classification,” Int. J. Comput. Vis. Robot., vol. 7, no. 6, pp. 692–711, 2017. [2] D. M. Ibrahim and N. M. Elshennawy, “Improving Date Fruit Classification Using CycleGAN-Generated Dataset,” C. - Comput. Model. Eng. Sci. , vol. 130, no. 3, 2022. [3] M. Faisal, M. Alsulaiman, M. Arafah, and M. A. Mekhtiche, “IHDS: Intelligent harvesting decision system for date fruit based on maturity stage using deep learning and computer vision,” IEEE Access, vol. 8, pp. 167985– 167997, 2020. [4] A. Nasiri, A. Taheri-Garavand, and Y. D. Zhang, “Image-based deep learning automated sorting of date fruit,” Postharvest Biol. Technol., vol. 153, no. April, pp. 133–141, 2019. [5] M. Koklu, R. Kursun, Y. S. Taspinar, and I. Cinar, “Classification of Date Fruits into Genetic Varieties Using Image Analysis,” Math. Probl. Eng., vol. 2021, 2021. [6] S. Al-abri, L. Khriji, A. Ammari, and M. Awadalla, “Classification of Omani ’ s Dates Varieties Using Artificial Intelligence Techniques,” Conf. Open
Innov. Assoc., pp. 407–412, 2017. [7] H. Altaheri, M. Alsulaiman, and G. Muhammad, “Date Fruit Classification for Robotic Harvesting in a Natural Environment Using Deep Learning,”
IEEE Access, vol. 7, pp. 117115–117133, 2019. [8] Data Indonesia, "Indonesia Impor Kurma Sebanyak 50,133 Ton 2021", [Online], Available: https://dataindonesia.id/sektor-riil/detail/, diakses tanggal 22 Juni 2022. [9] T. Najeeb and M. Safar, “Dates maturity status and classification using image processing,” 2018 Int. Conf. Comput. Sci. Eng. ICCSE 2018 - Proc., pp. 1–6, 2018. [10] M. S. Hossain, G. Muhammad, and S. U. Amin, “Improving consumer satisfaction in smart cities using edge computing and caching: A case study of date fruits classification,” Futur. Gener. Comput. Syst. , vol. 88, pp. 333– 341, 2018. 62
Program Studi Ilmu Komputer (S2) Universitas Nusa Mandiri [11] G. Huang, Z. Liu, L. Van der Maaten, and Kilian Q. Weinberger, “Densely Connected Convolutional Networks Gao,” Proc. IEEE Conf. Comput. Vis.
pattern recognition. , vol. 39, pp. 4700–4708, 2017. [12] K. Zhang, Y. Guo, X. Wang, J. Yuan, and Q. Ding, “Multiple feature reweight DenseNet for image classification,” IEEE Access, vol. 7, pp. 9872– 9880, 2019. [13] R. Kundu, H. Basak, A. Koilada, S. Chattopadhyay, S. Chakraborty, and N. Das, “Ensemble of CNN classifiers using Sugeno Fuzzy Integral Technique for Cervical Cytology Image Classification,” arXiv Prepr., pp. 1–16, 2021. [14] T. Lu, B. Han, L. Chen, F. Yu, and C. Xue, “A generic intelligent tomato classification system for practical applications using DenseNet-201 with transfer learning,” Sci. Rep., vol. 11, no. 1, pp. 1 –8, 2021. [15] E. M. Dogo, O. J. Afolabi, N. I. Nwulu, B. Twala, and C. O. Aigbavboa, “A Comparative Analysis of Gradient Descent-Based Optimization Algorithms on Convolutional Neural Networks,” Proc. Int. Conf. Comput. Tech.
Electron. Mech. Syst. CTEMS 2018, no. 1, pp. 92–99, 2018. [16] B. D. Pérez-Pérez, J. P. García Vázquez, and R. Salomón-Torres, “Evaluation of convolutional neural networks’ hyperparameters with transfer learning to determine sorting of ripe medjool dates,” Agric., vol. 11, no. 2, pp. 1–12, 2021. [17] S. Bera and V. K. Shrivastava, “Analysis of various optimizers on deep convolutional neural network models in the application of hyperspectral remote sensing image classification,” Int. J. Remote Sens. , vol. 41, no. 7, pp. 2664–2683, 2020. [18] B. X. Jie, M. A. Zulkifley, and N. A. Mohamed, “Remote Sensing Approach to Oil Palm Plantations Detection Using Xception,” 2020 11th IEEE Control
Syst. Grad. Res. Colloquium, ICSGRC 2020 - Proc., no. August, pp. 38–42, 2020. [19] R. Geirhos, D. H. J. Janssen, H. H. Schütt, J. Rauber, M. Bethge, and F. A. Wichmann, “Comparing deep neural networks against humans: object recognition when the signal gets weaker,” 2017. [20] M. Farooq and E. Sazonov, “Feature extraction using deep learning for food 63
Program Studi Ilmu Komputer (S2) Universitas Nusa Mandiri type recognition,” Lect. Notes Comput. Sci. (including Subser. Lect. Notes
Artif. Intell. Lect. Notes Bioinformatics), vol. 10208 LNCS, pp. 464–472, 2017. [21] M. Rahnemoonfar and C. Sheppard, “Deep count: Fruit counting based on deep simulated learning,” Sensors (Switzerland), vol. 17, no. 4, pp. 1 –12, 2017. [22] F. Zhuang et al., “A Comprehensive Survey on Transfer Learning,” Proc.
IEEE, vol. 109, no. 1, pp. 43–76, 2021. [23] M. F. Naufal and S. F. Kusuma, “Pendeteksi Citra Masker Wajah Menggunakan CNN dan Transfer Learning,” J. Teknol. Inf. dan Ilmu
Komputer, vol. 8, no. 6, p. 1293, 2021. [24] V. A. Meshram, K. Patil, and S. D. Ramteke, “MNet: A framework to reduce fruit image misclassification,” Ing. des Syst. d’Information, vol. 26, no. 2, pp. 159–170, 2021. [25] A. E. Wijaya, W. Swastika, and O. H. Kelana, “Implementasi Transfer Learning Pada Convolutional Neural Network Untuk Diagnosis Covid-19 Dan Pneumonia Pada Citra X-Ray,” Sainsbertek J. Ilm. Sains Teknol. , vol. 2, no. 1, pp. 10–15, 2021. [26] N. Sharma, V. Jain, and A. Mishra, “An Analysis of Convolutional Neural Networks for Image Classification,” Procedia Comput. Sci., vol. 132, no. Iccids, pp. 377–384, 2018. [27] Z. Ul Abideen et al., “Uncertainty assisted robust tuberculosis identification with bayesian convolutional neural networks,” IEEE Access, vol. 8, pp. 22812–22825, 2020. [28] M. Sahu and R. Dash, A survey on deep learning: Convolution neural
network (cnn), vol. 153, no. September 2020. Springer Singapore, 2021. [29] R. S. Latha et al., “Automatic Fruit Detection System using Multilayer Deep Convolution Neural Network,” 2021 Int. Conf. Comput. Commun.
Informatics, ICCCI 2021, no. January, 2021. [30] T. Chen, Z. Zhang, X. Ouyang, Z. Liu, Z. Shen, and Z. Wang, “‘BNN - BN =??’: Training binary neural networks without batch normalization,” IEEE
Comput. Soc. Conf. Comput. Vis. Pattern Recognit. Work. , pp. 4614–4624, 64
Program Studi Ilmu Komputer (S2) Universitas Nusa Mandiri 2021. [31] I. El Jaafari, A. Ellahyani, and S. Charfi, “Rectified non-linear unit for convolution neural network,” J. Phys. Conf. Ser. , vol. 1743, no. 1, 2021. [32] L. Wu and G. Perin, “On the Importance of Pooling Layer Tuning for Profiling Side-Channel Analysis,” Lect. Notes Comput. Sci. (including
Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 12809 LNCS, pp. 114–132, 2021. [33] S. H. S. Basha, S. R. Dubey, V. Pulabaigari, and S. Mukherjee, “Impact of fully connected layers on performance of convolutional neural networks for image classification,” Neurocomputing, vol. 378, pp. 112–119, 2020. [34] S. H. Wang, K. Muhammad, J. Hong, A. K. Sangaiah, and Y. D. Zhang, “Alcoholism identification via convolutional neural network based on parametric ReLU, dropout, and batch normalization,” Neural Comput. Appl., vol. 32, no. 3, pp. 665–680, 2020. [35] K. Murata, M. Mito, D. Eguchi, Y. Mori and M. Toyonaga, "A Single Filter CNN Performance for Basic Shape Classification," 2018 9th International
Conference on Awareness Science and Technology (iCAST), 2018, pp. 139- 143, doi: 10.1109/ICAwST.2018.8517219. [36] G. Huang, Z. Liu, L. Van Der Maaten, and K. Q. Weinberger, “Densely connected convolutional networks,” Proc. - 30th IEEE Conf. Comput. Vis.
Pattern Recognition, CVPR 2017, vol. 2017-January, pp. 2261–2269, 2017. [37] S. Sharma, S. Sharma, and A. Anidhya, “Understanding Activation Functions in Neural Networks,” Int. J. Eng. Appl. Sci. Technol. , vol. 4, no. 12, pp. 310–316, 2020. [38] J. G. Carney and P. Cunningham, “The Epoch Interpretation of Learning,” p. 5, 1998. [39] N. S. Keskar, J. Nocedal, P. T. P. Tang, D. Mudigere, and M. Smelyanskiy, “On large-batch training for deep learning: Generalization gap and sharp minima,” 5th Int. Conf. Learn. Represent. ICLR 2017 - Conf. Track Proc., pp. 1–16, 2017. [40] J. Brownlee, "Understand the Impact of Learning Rate on Neural Network Performance", 2020, [Online], Available: 65
Program Studi Ilmu Komputer (S2) Universitas Nusa Mandiri https://machinelearningmastery.com/understand-the-dynamics-of-learningrate-on-deep-learning-neural-networks/2020, di akses 22 Juni 2022. [41] W. S. N. Alhamdan and J. M. Howe, “Classification of Date Fruits in a Controlled Environment Using Convolutional Neural Networks,” Adv. Intell.
Syst. Comput., vol. 1339, pp. 154–163, 2021. [42] K. Shankar, Y. Zhang, Y. Liu, L. Wu, and C. H. Chen, “Hyperparameter Tuning Deep Learning for Diabetic Retinopathy Fundus Image Classification,” IEEE Access, vol. 8, pp. 118164–118173, 2020. [43] W. Abbes, D. Sellami, S. Marc-Zwecker, and C. Zanni-Merk, “Fuzzy decision ontology for melanoma diagnosis using KNN classifier,” Multimed.
Tools Appl., vol. 80, no. 17, pp. 25517–25538, 2021. [44] S. Farhad Khorshid and A. Mohsin Abdulazeez, “Breast Cancer Diagnosis Based on K-Nearest Neighbors: a Review,” J. Archaeol. Egypt/Egyptology, vol. 18, no. 4, pp. 1927–1951, 2021. [45] A. Tharwat, “Classification assessment methods,” Appl. Comput.
Informatics, vol. 17, no. 1, pp. 168–192, 2018. [46] M. E. Atik, Z. Duran, and D. Z. Seker, “Machine learning-based supervised classification of point clouds using multiscale geometric features,” ISPRS
Int. J. Geo-Information, vol. 10, no. 3, 2021. [47] Y. N. Nabusa, “Pengolahan Citra Digital Perbandingan Metode Histogram Equalization Dan Spesification Pada Citra Abu-Abu,” J-Icon, vol. 7, no. 1, pp. 87–95, 2019. [48] M. Asad, A. Mahmood, and M. Usman, “A machine learning-based framework for Predicting Treatment Failure in tuberculosis: A case study of six countries,” Tuberculosis (Edinb). , vol. 123, pp. 1 –14, 2020. [49] F. Uysal, F. Hardalaç, O. Peker, T. Tolunay, and N. Tokgöz, “Classification of fracture and normal shoulder bone X-Ray images using ensemble and transfer learning with deep learning models based on convolutional neural networks,” arXiv, vol. XX, pp. 1–17, 2021. [50] D. M. W. Powers, “Evaluation: From Precision, Recall and F-Measure to ROC, Informedness, Markedness & Correlation,” J. Mach. Learn. Technol. , vol. 2, no. 1, pp. 37–63, 2011. 66
Program Studi Ilmu Komputer (S2) Universitas Nusa Mandiri [51] T. Djatna, M. K. D. Hardhienata, and A. F. N. Masthuriyah, “An intuitionistic fuzzy diagnosis analytics for stroke disease,” J. Big Data, vol. 5, no. 1, 2018. [52] O. Rochmawanti, F. Utaminingrum, and F. A. Bachtiar, “Analisis Performa Pre-Trained Model Convolutional Neural Network dalam Mendeteksi Penyakit Tuberkulosis,” J. Teknol. Inf. dan Ilmu Komputer, vol. 8, no. 4, p. 805, 2021. [53] B. A. M. Ashqar and S. S. Abu-Naser, “Identifying Images of Invasive Hydrangea Using Pre-Trained Deep Convolutional Neural Networks,” Int. J.
Control Autom., vol. 12, no. 4, pp. 15–28, 2019. [54] L. N. Smith, “A disciplined approach to neural network hyper-parameters: Part 1 -- learning rate, batch size, momentum, and weight decay,” pp. 1 –21, 2018.