MobileNet untuk Identifikasi Skala Kerapatan dan Transparansi Tajuk Pohon Daun Lebar
DOI:
https://doi.org/10.30865/klik.v4i3.1476Keywords:
CNN; Deep Learning; Broadleaf; FHM; MobileNetAbstract
Forest health is an essential aspect of maintaining global environmental balance. One method for measuring forest health is Forest Health Monitoring (FHM), which includes measuring crown condition (crown density and foliage transparency). The measurement of crown density and foliage transparency is currently conducted by forest health experts by comparing the intensity of sunlight under the trees with values on a scale card (magic card) and then recording it. This is less effective because it relies on direct observation and can only be done by experts.Deep learning technology, especially Convolutional Neural Networks (CNN) such as MobileNet, can be used to make these measurements easier. This research aims to identify the scale of crown density and foliage transparency of broadleaf tree. This dataset used consist of four broadlieaf tree types: cacao (Theobroma cacao), durian (Durio zibethinus), rubber (Havea brasiliensis), and candlenut (Aleurites moluccana) with 5,000 images per tree type. The data preprocessing is carried out by data augmentation to prepare the dataset. The dataset is divided into three parts, 70% training data, 10% validation data, and 20% test data. Experimental results show that the MobileNet model can measure crown density and foliage transparency with accuracy during training and validation for Theobroma cacao (94.20%), Durio zibethinus (83.60%), Havea brasiliensis (97.80%), and Aleurites moluccana (99.20%). Accuracy in the testing process on Theobroma cacao (94.20%), Durio zibethinus (87.50%), Havea brasiliensis (97.90%), and Aleurites moluccana (98.70%). These results show that the MobileNet model is able to identify scales of crown density and foliage transparency using the Forest Health Monitoring (FHM) method for broadleaf trees with very good performance. Therefore, this research with MobileNet shows the potential for using deep learning technology in monitoring forest health more effectively and efficiently.These results show the potential for using deep learning technology in monitoring forest health more effectively and efficiently.
Downloads
References
R. Safe’i, A. Darmawan, H. Kaskoyo, and C. F. G. Rezinda, “Analysis of Changes in Forest Health Status Values in Conservation Forest (Case Study: Plant and Animal Collection Blocks in Wan Abdul Rachman Forest Park (Tahura WAR)),” J Phys Conf Ser, vol. 1842, no. 1, p. 012049, Mar. 2021, doi: 10.1088/1742-6596/1842/1/012049.
R. Safe’i, C. Wulandari, and H. Kaskoyo, “Assessment of Forest Health in Various Forest Types in Lampung Province,” Jurnal Sylva Lestari, vol. 7, no. 1, p. 95, Feb. 2019, doi: 10.23960/jsl1795-109.
D. Pertiwi, R. Safe’i, H. Kaskoyo, and I. Indriyanto, “Identifikasi Tipe Kerusakan Pohon Menggunakan Metode Forest Health Monitoring (FHM),” PERENNIAL, vol. 15, no. 1, p. 1, Jul. 2019, doi: 10.24259/perennial.v15i1.6033.
N. G. Tallent-Halsell, “Forest Health Monitoring 1994 Field Methods Guide, EPA/620/R-94/027,” United States Environmental Protection Agency Washington, DC, 1994.
L. Alzubaidi et al., “Review of deep learning: concepts, CNN architectures, challenges, applications, future directions,” J Big Data, vol. 8, no. 1, p. 53, Mar. 2021, doi: 10.1186/s40537-021-00444-8.
A. G. Howard et al., “MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications,” CoRR, vol. abs/1704.04861, 2017.
D. Pertiwi, R. Safe’i, and H. Kaskoyo, “Kesehatan Hutan di Blok Koleksi Tumbuhan dan/atau Satwa Tahura Wan Abdul Rachman Provinsi Lampung,” Jurnal Hutan Tropis, vol. 8, no. 3, pp. 244–347, Nov. 2020.
Z. Nopriyanto, Ri. Andrian, R. Safei, and K. Muludi, “Implementasi Metode CNN Computer Vision Dalam Identifikasi Tipe Kerusakan Pohon Berbasis FHM,” InComTech: Jurnal Telekomunikasi dan Komputer, vol. 10, no. 1, pp. 15–22, 2022.
F. J. Moreno-Barea, J. M. Jerez, and L. Franco, “Improving classification accuracy using data augmentation on small data sets,” Expert Syst Appl, vol. 161, p. 113696, Dec. 2020, doi: 10.1016/j.eswa.2020.113696.
K. Ghosh, C. Bellinger, R. Corizzo, P. Branco, B. Krawczyk, and N. Japkowicz, “The class imbalance problem in deep learning,” Mach Learn, Dec. 2022, doi: 10.1007/s10994-022-06268-8.
V. Verma et al., “A Deep Learning-Based Intelligent Garbage Detection System Using an Unmanned Aerial Vehicle,” Symmetry (Basel), vol. 14, no. 5, p. 960, May 2022, doi: 10.3390/sym14050960.
S. Shafi and A. Assad, “Exploring the Relationship Between Learning Rate, Batch Size, and Epochs in Deep Learning: An Experimental Study,” 2023, pp. 201–209. doi: 10.1007/978-981-19-6525-8_16.
X. Xing, P. Song, K. Zhang, F. Yang, and Y. Dong, “ZooME: Efficient Melanoma Detection Using Zoom-in Attention and Metadata Embedding Deep Neural Network,” in 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), IEEE, Nov. 2021, pp. 4041–4044. doi: 10.1109/EMBC46164.2021.9630452.
A. E. Maxwell, T. A. Warner, and L. A. Guillén, “Accuracy Assessment in Convolutional Neural Network-Based Deep Learning Remote Sensing Studies—Part 1: Literature Review,” Remote Sens (Basel), vol. 13, no. 13, 2021, doi: 10.3390/rs13132450.
R. Ramadhan, I. Fibriani, and W. Cahyadi, “Penerapan Microexpressions Untuk Mengenali Hubungan Kekerabatan Menggunakan Extreme Learning Machine,” MALCOM: Indonesian Journal of Machine Learning and Computer Science, vol. 1, no. 2, pp. 162–169, Dec. 2021, doi: 10.57152/malcom.v1i2.101.
S. Afaq and S. Rao, “Significance Of Epochs On Training A Neural Network,” International Journal of Scientific & Technology Research, vol. 9, pp. 485–488, 2020.
D. Chicco and G. Jurman, “The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation,” BMC Genomics, vol. 21, no. 1, p. 6, 2020, doi: 10.1186/s12864-019-6413-7.
M. Grandini, E. Bagli, and G. Visani, “Metrics for Multi-Class Classification: an Overview,” Aug. 2020.
H. Wang, T. Li, Z. Zhuang, T. Chen, H. Liang, and J. Sun, “Early Stopping for Deep Image Prior,” Dec. 2021.
A. H. A. Zargari, M. AshrafiAmiri, M. Seo, S. M. P. Dinakarrao, M. E. Fouda, and F. Kurdahi, “CAPTIVE: Constrained Adversarial Perturbations to Thwart IC Reverse Engineering,” Oct. 2021.
Y. Feng, M. Gao, and Z. Zhang, “Web Service QoS Classification Based on Optimized Convolutional Neural Network,” in 2019 IEEE 14th International Conference on Intelligent Systems and Knowledge Engineering (ISKE), IEEE, Nov. 2019, pp. 584–590. doi: 10.1109/ISKE47853.2019.9170368.
C. Shiranthika, N. Premakumara, H.-L. Chiu, H. Samani, C. Shyalika, and C.-Y. Yang, “Human Activity Recognition Using CNN & LSTM,” in 2020 5th International Conference on Information Technology Research (ICITR), IEEE, Dec. 2020, pp. 1–6. doi: 10.1109/ICITR51448.2020.9310792.
J. N. Mogan, C. P. Lee, K. M. Lim, and K. S. Muthu, “VGG16-MLP: Gait Recognition with Fine-Tuned VGG-16 and Multilayer Perceptron,” Applied Sciences, vol. 12, no. 15, p. 7639, Jul. 2022, doi: 10.3390/app12157639.
A. R. Muhammad, H. P. Utomo, P. Hidayatullah, and N. Syakrani, “Early Stopping Effectiveness for YOLOv4,” Journal of Information Systems Engineering and Business Intelligence, vol. 8, no. 1, pp. 11–20, Apr. 2022, doi: 10.20473/jisebi.8.1.11-20.
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel MobileNet untuk Identifikasi Skala Kerapatan dan Transparansi Tajuk Pohon Daun Lebar
ARTICLE HISTORY
Issue
Section
Copyright (c) 2023 Fanirizki Sofiyana, Rico Andrian, Rahmat Safe'i
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (Refer to The Effect of Open Access).
