Jeong-Lae Kim

Design And Implementation of a Speech Recognition Interview Model based-on Opinion Mining Algorithm

The opinion mining is that to use the existing data mining technology also uploaded blog to web, to use product comment, the opinion mining can extract the author`s opinion therefore it not judge text`s subject, only judge subject`s emotion. In this paper, published opinion mining algorithms and the text using speech recognition API for non-voice data to judge the emotions suggested. The system is open and the Subject associated with Google Voice Recognition API sunwihwa algorithm, the algorithm determines the polarity through improved design, based on this interview, speech recognition, which implements the model.

Design and Implementation of a Efficient Search Engine Using Collaborative Filtering

Recently, due to the increasing demand for mobile devices, mobile searching market is rapidly growing. However, there is the limit of screen size, when searching for mobile devices, various results should be shown at a glance. The reason is that results are important given that up to 43 percent of people tend to check only first page. In this paper, a set of keywords for searching will be used to find out the users` interests. Users were divided into groups after going through Collaboration filtering. Therefore, the result of this experiment, reduced time for searching and improved quality of searching were confirmed.

Stabilizing of the Static Posture Balance Based on the Physical Control System

To design and test the physical signal control system that can sway a static state of body for a posture balance. It was necessary to develop and to separate a physical signal in the static posture for physical parameters such as eye open and close. This shows stability part become small unstable while closing the eyes. There was a small change in visual and vestibular. And then, there was a slight change in somatosensory and CNS. This system was evaluated a data through the stability and body sway. In the future, this system will be express to an assessment for body sway and balance. We hope to confirm a body activity and to control the physical condition.

Estimating of the Dynamic Postural Stability on the Bio-sensor Processing System

This presented stability part become less stable reacting high while closing the eyes in the posture change. Vision condition shows that the average was slightly lower with Vi-μ BENO. Vestibular condition present that the average was slightly larger with Ve-μ AENO. CNS condition shows that the average was diminutive more with C-μ BENO, and the outcome shows that the eye close situation has changed more than the eye open situation of body moving after. The average was slightly larger with C-μ AENO. This system consisted of a data acquisition system, data signal processing, and feedback system. This system was evaluated a data dynamic posture through the stability and body sway. This system will be expressed to an assessment for activity body. It was expected to confirm a body activity and to control bio-physical condition for a long time.

Intelligent Music Recommendation System Based on Cloud Computing

In this paper, intelligent music recommend system is proposed based on clouding computer. User- selected music is classified to similar tendency by algorithm of music genre classification, after total of 12 musical feature extraction on cloud. This system classified using Thayer’s model of mood and music was classified again suitable for current weather conditions. So, we suggested to music recommend system based on cloud computing system recommend for user and verified through simulation. The results of performance evaluation show that the proposed system can efficiently support weather condition and season information.

Handling Frequent Updates of Moving Objects Using the Dynamic Non-uniform Grid

For services related with the u-LBS and u-GIS, most previous works had try to solve frequent updates as a lot of moving objects by extending traditional R-tree. In related works, however, processing for a situation occurring partial denseness of many objects is so hard because these haven’t considering the non-uniform distribution. Thus, we proposed new scheme to solve problems above by using the dynamic non-uniform grid. Due to its result of split isn’t equal, our proposed scheme can allow distributed processing locally for dense moving objects. Also it has several in-memory buffers to handle frequent updates of massively moving objects lazily.