Jeonghoon Mo

The extensive utilization of electronic health records (EHRs) and the growth of enormous open biomedical datasets has readied the area for applications of computational and machine learning techniques to reveal fundamental patterns. This study’s goal is to develop a medical treatment recommendation system using Korean EHRs along with the Markov decision process (MDP). The sharing of EHRs by the National Health Insurance Sharing Service (NHISS) of Korea has made it possible to analyze Koreans’ medical data which include treatments, prescriptions, and medical check-up. After considering the merits and effectiveness of such data, we analyzed patients’ medical information and recommended optimal pharmaceutical prescriptions for diabetes, which is known to be the most burdensome disease for Koreans. We also proposed an MDP-based treatment recommendation system for diabetic patients to help doctors when prescribing diabetes medications. To build the model, we used the 11-year Korean NHISS database. To overcome the challenge of designing an MDP model, we carefully designed the states, actions, reward functions, and transition probability matrices, which were chosen to balance the tradeoffs between reality and the curse of dimensionality issues.

Terrestrial broadcasting network is the main delivery platform of terrestrial broadcasters and its coverage represents the capacity. We study economic impacts of coverage on TV service markets, which consist of broadcasters and pay‐TV operators with retransmission, by dividing the market into “inside” and “outside” the coverage.Our results suggest that the broadcaster ends up with two extreme options in equilibrium: not operating networks or operating networks at a full capacity. However, the former option is not desirable if the retransmission fee changes according to the coverage. On the basis of the main results derived, implications for broadcasters and the government are discussed.

Media publishers that have commonly relied on profits from advertisements and content sales to fund their operations are not only content providers (manufacturers) to media aggregator platforms (retailers) but are also competing service providers (rival retailers) in the digital video supply chain. Different from a traditional media supply chain, they can easily operate their own direct distribution channels in the Internet era. In the digital video supply chain, it is not clear whether commercialization of the direct distribution channel would be beneficial for the media publisher because it would decrease profits from advertisements. The choice about commercialization should be investigated thoroughly because it is closely related to the media publishers’ sustainability as a public medium in a digital environment. In this study, we analyze the impacts of commercializing the direct distribution channel based on a game-theoretic approach. Specifically, we compare the profits of a media publisher with and without the commercialization of the channel from analyses of sequentially defined games. Our results show that media publishers prefer to use a free service on their direct channel if the content they provide is not highly valued. They can also choose not to provide their content to the media aggregator with a paid service.

In this article, the problems of test sequence generation and scheduling optimization for a tester with parallel devices are considered in order to reduce inspection times. Two optimization problems are formulated for test sequence generation and the scheduling of parallel devices, and then algorithms to address these problems are proposed. The proposed algorithms were tested via simulation and experiments. The test results show two to four times improvement over existing methods.

We propose a rendezvous scheme based on multi-level orthogonal hopping for multi-channel medium access control protocols. Its benefits compared to random hopping are higher throughput due to higher rendezvous probability. Furthermore, it offers improved fairness over other orthogonal hopping schemes.