Digital Library[ Search Result ]

Search : [ author: 김문권 ] (2)

Methods for Analyzing Preference Tendencies and Activity Patterns with Audio Contexts

Hyun Jung La, Moon Kwon Kim, Han Ter Jung, Soo Dong Kim

http://doi.org/10.5626/JOK.2018.45.4.348

Recently, there has been a trend for collecting various rich personal contexts, such as social network services (SNS), user created contents (UCC), and digital diaries. Because of this trend, much more attention to semantic analysis with personal contexts is being paid. The semantic analysis allows users to analyze and understand diverse aspects of their lives such as their lifestyle and quality of life which are not easily recognized by them. Hence, in this paper, we propose a process to infer semantics from personal contexts, more specifically, audio contexts. This paper is focused on proposing detailed algorithms for analyzing user’s preference tendencies and activity patterns. To evaluate the proposed methods, we apply them to developing a system, called Smart Diary System, which is used to analyze a user’s preference tendency and activity pattern from audio diaries, and we present experiment results with the system. We expect to use the proposed process and algorithms in various application domains such as personal secretary service, recommendation services, and advertising services.

A Design of Effective Inference Methods and Their Application Guidelines for Supporting Various Medical Analytics Schemes

Moon Kwon Kim, Hyun Jung La, Soo Dong Kim

http://doi.org/

As a variety of personal medical devices appear, it is possible to acquire a large number of diverse medical contexts from the devices. There have been efforts to analyze the medical contexts via software applications. In this paper, we propose a generic model of medical analytics schemes that are used by medical experts, identify inference methods for realizing each medical analytics scheme, and present guidelines for applying the inference methods to the medical analytics schemes. Additionally, we develop a PoC inference system and analyze real medical contexts to diagnose relevant diseases so that we can validate the feasibility and effectiveness of the proposed medical analytics schemes and guidelines of applying inference methods.


Search




Journal of KIISE

  • ISSN : 2383-630X(Print)
  • ISSN : 2383-6296(Electronic)
  • KCI Accredited Journal

Editorial Office

  • Tel. +82-2-588-9240
  • Fax. +82-2-521-1352
  • E-mail. chwoo@kiise.or.kr