Earticle

Since 2010, the number of housing construction permits and completion cases has increased due to a surge in the number of people entering Jeju Island, and the supply of apartments in Jeju area has also increased during this period, especially in the natural green area due to the lack of existing housing sites in Jeju City. However Since 2017, the number of completion cases has also decreased as population inflow has been on the decline, showing a pattern similar to net population movement. In this study, we investigated and analyzed the characteristics and patterns of tenement houses during ten-year through a study of tenement houses in Jeju, which experienced the changes in living environment and real estate due to the rapid changes in population. The project aims to present the direction and basic data of the future study of tenement houses in Jeju through research on the layout characteristics of tenement houses in Jeju city district.

This study develops and validates an algorithm that automates fire-protection design from architectural drawings. Building-summary tables and annotations are parsed with optical character recognition (OCR) and OpenCV to normalize occupancy, gross floor area, story count, and floor height. Doors and columns are detected by a You Only Look Once v4 (YOLO v4) convolutional neural network, and room boundaries are reconstructed to form space-level metadata. A rule engine derived from the National Fire Safety Code (NFSC) determines installation or exemption for each system and computes equipment placement and wiring. Outputs are written as computer-aided design (CAD) entities through the AutoCAD application programming interface. In tests, table structure and text recognition reached accuracy 0.91, precision 0.89, recall 0.99, F1 Score 0.94, and intersectionover-union 0.83. Average detection confidence was 0.89 for doors and 0.86?0.93 for columns. Checklist comparison yielded about 97% normal outputs, and repeated runs reproduced coordinates and connections, indicating reliable end-to-end automation from image inputs to CAD deliverables.