Major
Computer Science
Anticipated Graduation Year
2027
Access Type
Restricted Access
Abstract
This research investigates key slum characteristics to enhance detection accuracy using deep learning models. Four databases were reviewed with BOOLEAN operations and keyword combinations, following PRISMA guidelines. The data was organized and synthesized in Excel for clarity. The results show that standardized slum definitions improve model performance. Additionally, integrating spatial datasets and remote sensing techniques refines detection accuracy. This work demonstrates how deep learning, combined with GIS tools and census data, can improve slum identification and boundary delineation. The findings highlight the potential of these tools to support more precise and effective slum detection strategies.
Faculty Mentors & Instructors
Dr. Ifeoma D. Ozodiegwu, Assistant Professor, Health Informatics and Data Science
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 3.0 License.
Enhancing Slum Identification and Definition Through Deep Learning and Spatial Data Integration
This research investigates key slum characteristics to enhance detection accuracy using deep learning models. Four databases were reviewed with BOOLEAN operations and keyword combinations, following PRISMA guidelines. The data was organized and synthesized in Excel for clarity. The results show that standardized slum definitions improve model performance. Additionally, integrating spatial datasets and remote sensing techniques refines detection accuracy. This work demonstrates how deep learning, combined with GIS tools and census data, can improve slum identification and boundary delineation. The findings highlight the potential of these tools to support more precise and effective slum detection strategies.