Machine Learning

Image Retrieval Systems based on Color Similarity and Edge Detection

This project was conducted in 2008 for my bachelor's thesis in the Department of Electrical Engineering at Seoul National University (it was more like a capstone project rather than a thesis, since the focus of the project was mainly at implementing algorithms rather than analyzing the performance of algorithms using concrete measures, e.g., recall and precision). I implemented an image retrieval system prototype that takes an image as input, and outputs most similar images from the image database.

This Is Not Just a Café: Toward Capturing the Dynamics of Urban Places

Social media has provided a huge amount of user-generated data in capturing urban dynamics. Among them, place-level human behavior has been largely detected through people’s check-in records at certain places. Conventionally, places are characterized by a set of pre-defined features, often specified by the owner of the places. In this paper, we argue that capturing socially-meaningful features and dynamics of an urban place may also be done by analyzing human activity traces.

On Information Deserts

Information accessibility problems include diverse types of human- and system-driven barriers that make it difficult for individuals to access desired information. These issues have been studied in two main streams: (1) a human-centered view based on the understand­ing of individual-level characteristics such as physical impairment and economic status, and (2) a technology-focused view that emphasizes system-based factors such as the information filtering techniques and interface designs.

Pages