Comparison of Cultural Attractions Classification Model Performance Nakhon Si Thammarat Province
Keywords:
Cultural attractions, Artificial Neural Networks, Deep learningAbstract
Nakhon Si Thammarat is an ancient city of historical significance in Southeast Asia, boasting diverse and unique cultural tourist attractions. This research aims to compile an image dataset of key cultural tourist sites in Nakhon Si Thammarat, including 8 noteworthy sites. The dataset is used for training and comparing the performance of various image classification models. The learning process involves two main steps: dimensionality reduction of image data through either image flattening or convolutional neural networks, and model training. Three models were evaluated: nearest neighbor, decision tree, and logistic regression. The study found that using convolutional neural networks for dimensionality reduction yielded higher performance compared to image flattening, and the logistic regression model achieved the highest accuracy at 93.75%.
References
Information and Communication Division Nakhon Si Thammarat Provincial Office. History of Nakhon Si Thammarat Province [Internet]. 2008. [updated 2008 October 20; cited 2023 September 21]. Available from: https://www.nakhonsithammarat.go.th/his.php.
Boonkidram S, Sriwiboon N. Physical quality investigation of germinated brown rice by using image processing. J Inform Sci Technol. 2020; 10(2): 101-109. Thai.
Tiendee S, Khamnipat K, Pramote O. A classification of crown flower using feature extraction and machine learning. J Inform Sci Technol. 2022; 12(2): 1-10. Thai.
Sriwiboon N. Improvement the performance of the chest x-ray image classification with convolutional neural network model by using image augmentations technique for covid-19 diagnosis. J Acad King Mongkut's North Bangkok. 2021; 31(1): 109-117. Thai.
Nakhon Si Thammarat Provincial Cultural Office. Ancient sites and objects [Internet]. 2022. [updated 2022 May 19; cited 2023 September 14]. Available from: https://nakhonsrithammarat.m-culture.go.th
/th/db_99_nakhonsrithammarat_43.
He K, Zhang X, Ren S, Sun J. Deep Residual Learning for Image Recognition. Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. 2016; 770-778.
Deng J, Dong W, Socher R, Li L-J, Li K, Fei-Fei L. Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition. 2009; 208-255.
Abadi M, Barham P, Chen J, Chen Z, Davis A, Dean J, et al.Tensorflow: A system for large-scale machine learning. In 12th Symposium on Operating Systems Design and Implementation. 2016; 265-283.
Chollet F. Keras. GitHub [Internet].2023. [cited 2023 September 21]. Available from: https://github.com/fchollet/keras.
Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, et el. Scikit-learn: Machine Learning in Python. J Mach Learn Res. 2011; 12: 2825-2830.
Sudjit B, Sukvaree T. Praneetpolgrang, P. Development and evaluation of process architecture for designing thai wisdom alphabet set and identityin 4 regions with artificial intelligence technology. J Sci Technol Royal Navy. 2022; 18(2): 57-72. Thai.
Downloads
Published
Issue
Section
License
Copyright (c) 2024 KKU Research Journal (Graduate Studies)
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.