Linear discriminant analysis (LDA) to clarifying vacant land allocations of Baiturraman district in Banda Aceh city

• Main Author: Rusdiana, Siti
• Format: Conference Proceeding
• Language: English
• Subjects: Allocations; Classification; Discriminant analysis; Land area; Land use; Machine learning; Pattern recognition
• ISSN: 0094-243X; 1551-7616
• DOI: 10.1063/1.4965191

Linear discriminant analysis (LDA) is a generalization of Fisher’s linear discriminant, a method used in statistics, pattern recognition and machine learning to find a linear combination of features that characterizes or separates two or more classes of objects or events. It is one of the methods offered in multivariable analysis can be helping in land classification. This research resulted functions and values discriminant that could be used for classification of sub-district land in Banda Aceh by using Fisher discriminant analysis. The functions and values discriminant that is obtained had been implemented on vacant land data in sub-district of Baiturrahman. Results of this research are sub-district of Baiturrahman having 340 vacant lands, by which 282 vacant lands are used as protected areas and 58 others are used as cultural areas. Vacant land area in sub-district of Baiturrahman is 40.54 Ha, where land area that can be used as protected area is 32.216 Ha and land area that can be used as cultural areas is 8.324 Ha. Furthermore, discriminant function that is obtained has the accuracy of classifying land of 62.82 %. This research is expected to be a recommendation to classify vacant land in Banda Aceh city, vacant land use for sub-district of Baiturrahman can be a consideration to government, so that further research can be done to classify vacant land directly into 11 land use in Banda Aceh city.