Epoch Tuning Hyperparameter in Fire Image Classification at University Sjakhyakirti

DOI

10.2991/978-94-6463-118-0_37How to use a DOI?

Keywords

Hyperparameter tuning; Epoch; Image Processing; Fire Image Classification

Abstract

Epoch is a factor that affects the time of training an AI model and affects the accuracy value of the AI model. In this study, hyperparameter tuning of the epoch value was carried out to see the optimization of the resulting accuracy value. The object to be observed is the condition of the fire image which is classified in the position of (1) Fire Condition, and (2) Non-Fire Condition. The image data observed were 4650 fire images sourced from environmental images of the University Sjakhyakirti as well as fire conditions from public sources like Google images and Kaggle. So the formulation of the problem from this research is how to measure the Epoch value in producing fire image prediction accuracy. The purpose of this study is to measure the best accuracy value by performing hyperparameter tuning on the Epoch. The stages of the research are (1) Dataset Integration; (2) Image Augmentation; (3) Data Pre-processing; (4) CNN modelling; (5) Hyperparameter Tuning; (6) Determination of Accuracy Value. The tuning hyperparameters carried out are with values of 30, 50, 75, 100 and 120. From the results of the Epoch tuning hyperparameter, based on the effectiveness of the time required along with the accuracy results, the epoch 30 value has an optimal accuracy result of 82.5% of the test data testing, and has The effective time duration is relatively short, namely 30 min assuming the time required is ±1 min for one epoch.

Copyright

© 2023 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Ahmad Bahri Joni Malyan
AU  - Rian Rahmanda Putra
AU  - Ema Laila
AU  - Agum Try Wardhana
AU  - Muhammad Fikri
AU  - Indra Griha Tofik Isa
PY  - 2023
DA  - 2023/06/26
TI  - Epoch Tuning Hyperparameter in Fire Image Classification at University Sjakhyakirti
BT  - Proceedings of the 6th FIRST 2022 International Conference (FIRST-ESCSI-22)
PB  - Atlantis Press
SP  - 355
EP  - 364
SN  - 2589-4943
UR  - https://doi.org/10.2991/978-94-6463-118-0_37
DO  - 10.2991/978-94-6463-118-0_37
ID  - Malyan2023
ER  -