J
Jun-Ki Min
Researcher at Yonsei University
Publications - 31
Citations - 775
Jun-Ki Min is an academic researcher from Yonsei University. The author has contributed to research in topics: Support vector machine & Mobile device. The author has an hindex of 12, co-authored 30 publications receiving 697 citations. Previous affiliations of Jun-Ki Min include Carnegie Mellon University.
Papers
More filters
Proceedings ArticleDOI
Toss 'n' turn: smartphone as sleep and sleep quality detector
TL;DR: The rapid adoption of smartphones along with a growing habit for using these devices as alarm clocks presents an opportunity to use this device as a sleep detector, and individual models performed better than generally trained models on detecting sleep and sleep quality.
Journal ArticleDOI
Fingerprint classification using one-vs-all support vector machines dynamically ordered with naïve Bayes classifiers
TL;DR: A novel method in which the SVMs are generated with the one-vs-all (OVA) scheme and dynamically ordered with nai@?ve Bayes classifiers to break the ties that frequently occur when working with multi-class classification systems that use OVA SVMs is proposed.
Proceedings ArticleDOI
Mining smartphone data to classify life-facets of social relationships
TL;DR: This paper uses call and text message logs from mobile phones to classify contacts according to life facet (family, work, and social), and extracts various features such as communication intensity, regularity, medium, and temporal tendency and classify the relationships using machine-learning techniques.
Proceedings ArticleDOI
"You Never Call, You Never Write": Call and SMS Logs Do Not Always Indicate Tie Strength
TL;DR: It is found that frequent or long-duration communication likely indicates a strong tie, however, the use of call and SMS logs produced many errors in separating strong and weak ties, suggesting this approach is incomplete.
Proceedings ArticleDOI
Detection of behavior change in people with depression
TL;DR: The design of Big Black Dog, a smartphone-based system for gathering data about social and sleep behaviors and the results of a pilot evaluation to understand the feasibility of gathering and using data from smartphones for inferring the onset of depression are reported on.