기계 학습 알고리즘을 적용한 국내 철근콘크리트 건물의 구조 유형 분류

다국어 초록 (Multilingual Abstract)

This study optimizes three machine learning models—Decision Tree, Random Forest (RF), and Gradient Boosting—to classify concrete structure types (C2, C3, C4, and C5) using information from a building register. Although the initial models achieved high overall accuracy, the minority class C5 exhibited relatively low performance due to class imbalance and inherent complexity. To address this, an exhaustive grid search over discrete parameter candidates was performed, and a class-weighting strategy was integrated into the RF model to prioritize accurate classification of the minority class. The optimized RF model preserved a high overall accuracy of 94% while markedly improving C5 recall from 0.81 to 0.86 and its F1-score from 0.85 to 0.87. These results demonstrate that strategic hyperparameter tuning with class weights can effectively enhance classification reliability for rare structural types. Future research should include feature importance analysis to refine data configurations and the expansion of minority class samples to further improve model robustness in practical applications.

목차 (Table of Contents)

• / A B S T R A C T /
• 1. 서 론
• 2. 구조 유형 분류를 위한 기계학습 알고리즘
• 3. 기존 구조 유형 분류 규칙
• 4. 건축물대장표제부 자료 분석 및 처리
• 5. 기계학습을 사용한 구조 유형 분류 결과
• 5.1 기계학습 적용 개요
• 5.2 기계학습 모델의 정확도 비교
• 5.3 하이퍼파라미터 튜닝을 통한 모델 최적화
• 5.4 기계학습 결과 요약 및 분석
• 6. 결 론
• / REFERENCES /