IdentifyingTraditional Malay Building Architectural Styles Using Vision Transformer Architecture

IdentifyingTraditional Malay Building Architectural Styles Using Vision Transformer Architecture

AutomaticIdentification,TraditionalMalayHouses,VisionTransformer, DeepLearning

The preservation and documentation of traditional Malay buildings is a significant challenge, especiallyinidentifyingdiversearchitecturalstyles,whichisoftendonemanually.Thisstudyaimsto optimizedigitalarchitecture usingVision Transformer(ViT) for identifyingMalayarchitectural styles, suchasRiauMalayandPontianakMalay,bymeasuringmodelperformanceusingPrecision,Recall, and F1-Score. The method used is ViT-based deep learning trained using a dataset of traditional building images. The data was divided using an 80:20 and 70:30 ratio for training and testing data. The model was optimized to improve accuracy and prevent overfitting using regularization techniques. Testing results show that the ViT model achieved excellent Precision, Recall, and F1-Scorevalues, with Precisionand Recallreaching 0.99 onthe training data, and 0.98for Riau Malay HouseTypesand0.97forPontianakMalayTraditionalHousesonthetestdata.ThisprovesthatViTcan automatically and accurately identify Malay architectural styles. This research has the potential to be applied in digital preservation, traditional building documentation, and the development of AI-basedapplications for the cultural and tourism sectors

HeriPramono1,SriWiniarti2,AbdulFadlil3,Sunardi4

https://ijicom.respati.ac.id/index.php/ijicom/article/view/195/126

nternationalJournalofInformaticsandComputation(IJICOM)

2025

Fajar bagus W

PDF

English

Text