Utilisation of convolutional neural network on deep learning in predicting digital image to tree damage type

被引：0
作者：
Safe’i R. [1 ]
Andrian R. [2 ]
Maryono T. [3 ]
Nopriyanto Z. [2 ]
机构：
[1] Forestry Master Study Program, Faculty of Agriculture, University of Lampung, Lampung
[2] Department of Computer Science, Faculty of Mathematics and Natural Science, University of Lampung, Lampung
[3] Department of Agrotechnology, Faculty of Agriculture, University of Lampung, Lampung
来源：
International Journal of Internet Manufacturing and Services | 2024年 / 10卷 / 01期
关键词：
computer vision; convolutional neural network; deep learning; FHM; forest health monitoring; mobile-net; type of tree damage;
D O I：
10.1504/IJIMS.2024.136721
中图分类号：
学科分类号：
摘要：
Damage is often defined as a condition where there is a change in an object or shape. Damage does not only occur to objects, it can occur to living things, including trees. Damage to trees is seen in the physical shape of the tree that has changed shape, to find out it requires deep learning. One way that can be used is by modelling through computers through artificial intelligence, namely creating a deep learning model that can retrieve image information to recognise objects. This research aims to utilise convolutional neural network algorithm in deep learning to identify tree damage. The research stages carried out are input, feature extraction and classification, and output. The final result obtained is the successful identification of trees in deep learning on the model with an accuracy of 99.06% with a detection error of 0.94%. Detection errors occur due to similarities in terms of patterns, etc. This can be minimised by combining hyperparameters. Copyright © 2024 Inderscience Enterprises Ltd.
引用
收藏
页码：77 / 90
页数：13
相关论文
共 24 条
  • [1] Abimanyu B., Safei R., Application of forest health monitoring method in assessing tree damage in metro city forest, Bandar Lampung, Journal Sylva Lestari, 7, 3, pp. 289-298, (2019)
  • [2] Acharya U.R., Oh S.L., Hagiwara Y., Tan J.H., Adam M., Gertych A., Tan R.S., A deep convolutional neural network model to classify heartbeats, Comput. Biol. Med, 89, 1, pp. 389-396, (2017)
  • [3] Angulo A.A., Vega-Fernandez J.A., Aguilar-Lobo L.M., Natraj S., Ochoa-Ruiz G., Road Damage Detection Acquisition System Based on Deep Neural Network for Physical Asset Management, (2019)
  • [4] Arpit D., Et al., A closer look at memorization in deep networks, Proc. 34th Int. Conf. Mach. Learn, 6, 1, pp. 233-242, (2017)
  • [5] Babatunde H.O., Armstrong L., Leng J., Diepeveen D., A Survey of computer- based vision systems for automatic identification of plant species, Journal of Agricultural Informatics, pp. 61-71, (2015)
  • [6] Chung J., Choi W., Park J., Ghosh S., Domain wall memory-based design of deep neural network convolutional layers, Journal IEEE Access, 8, 3, pp. 19783-19798, (2020)
  • [7] Dutta S., Ghosh S., Forest fire detection using combined architecture of separable convolution and image processing, International Conference on Artificial Intellligence and Data Analytics, (2021)
  • [8] Janabi A.H., Kanakis T., Johnson M., Convolutional neural network based algorithm for early warning proactive system security in software defined networks, Journal IEEE Access, 10, 1, pp. 14301-14310, (2022)
  • [9] Kumar N.P.N., Leafsnap: A Computer Vision System for Automatic PlantSpecies Identification, (2012)
  • [10] Laith A., Zhang J., Humaidi A.J., Al-Dujaili A., Duan Y., Al-Shamma O., Et al., Review of deep learning: concepts, CNN architecture, challenges, applications, future directions, Journal of Big Data, 8, 53, pp. 1-74, (2021)
123