• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.16 no.4 s.109
• /
• pp.414-419
• /
• 2006

In this research, the test how the evaluation of the spacial image influenced by the environmental friendly elements included in the visual information, and how the selection of the sound changed depending on the characteristics of spacial image were carried out by the 40 subjects. Vast tracts of green land and the waterfront were highly preferred and impressive than the other spaces. The green music, signal with water sound and bird chirping sound were highly scored. In the frequency characteristics of the factors, the first factor was artificial sound (high at the low frequency band), the second was natural sound(uniform at all frequency band) and the third was water sound (high at the middle and high frequency band over 500 Hz) . This shows that the proposal of the sound which has the frequency characteristics fit to the spacial image should be selected for the soundscape of the target space.

• Journal of Information Processing Systems
• /
• v.16 no.5
• /
• pp.1223-1230
• /
• 2020

Recently, extensive studies have been conducted to apply deep learning to reinforcement learning to solve the state-space problem. If the state-space problem was solved, reinforcement learning would become applicable in various fields. For example, users can utilize dance-tutorial systems to learn how to dance by watching and imitating a virtual instructor. The instructor can perform the optimal dance to the music, to which reinforcement learning is applied. In this study, we propose a method of reinforcement learning in which the action space is dynamically adjusted. Because actions that are not performed or are unlikely to be optimal are not learned, and the state space is not allocated, the learning time can be shortened, and the state space can be reduced. In an experiment, the proposed method shows results similar to those of traditional Q-learning even when the state space of the proposed method is reduced to approximately 0.33% of that of Q-learning. Consequently, the proposed method reduces the cost and time required for learning. Traditional Q-learning requires 6 million state spaces for learning 100,000 times. In contrast, the proposed method requires only 20,000 state spaces. A higher winning rate can be achieved in a shorter period of time by retrieving 20,000 state spaces instead of 6 million.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.8
• /
• pp.3820-3841
• /
• 2018

Most of the accidents occur due to drowsiness while driving, avoiding road signs and due to driver's distraction. Driver's distraction depends on various factors which include talking with passengers while driving, mood disorder, nervousness, anger, over-excitement, anxiety, loud music, illness, fatigue and different driver's head rotations due to change in yaw, pitch and roll angle. The contribution of this paper is two-fold. Firstly, a data set is generated for conducting different experiments on driver's distraction. Secondly, novel approaches are presented that use features based on facial points; especially the features computed using motion vectors and interpolation to detect a special type of driver's distraction, i.e., driver's head rotation due to change in yaw angle. These facial points are detected by Active Shape Model (ASM) and Boosted Regression with Markov Networks (BoRMaN). Various types of classifiers are trained and tested on different frames to decide about a driver's distraction. These approaches are also scale invariant. The results show that the approach that uses the novel ideas of motion vectors and interpolation outperforms other approaches in detection of driver's head rotation. We are able to achieve a percentage accuracy of 98.45 using Neural Network.

• Journal of Information Technology Applications and Management
• /
• v.24 no.1
• /
• pp.33-43
• /
• 2017

The content curation service through big data analysis is receiving great attention in various content fields, such as film, game, music, and book. This service recommends personalized contents to the corresponding user based on user's preferences. The existing book curation systems recommended books to users by using bibliographic citation, user profile or user log data. However, these systems are difficult to recommend books related to character names or spatio-temporal information in text contents. Therefore, in this paper, we suggest a personalized book curation system based on integrated mining of a book. The proposed system consists of mining system, recommendation system, and visualization system. The mining system analyzes book text, user information or profile, and SNS data. The recommendation system recommends personalized books for users based on the analysed data in the mining system. This system can recommend related books using based on book keywords even if there is no user information like new customer. The visualization system visualizes book bibliographic information, mining data such as keyword, characters, character relations, and book recommendation results. In addition, this paper also includes the design and implementation of the proposed mining and recommendation module in the system. The proposed system is expected to broaden users' selection of books and encourage balanced consumption of book contents.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2003.05a
• /
• pp.1010-1013
• /
• 2003

It is said that the goal of the design of good acoustical environment is at first the reduction of undesirable sounds, and in addition the introduction of desirable sounds by which our minds are soothed. The task of creating the desirable sounds leads to the realization of a comfortable acoustic environment and the design of soundscape. It may be an important starting point of soundscape design to select suitable sounds for the target spaces, because each space has a different surrounding condition and requires a special ambient sound. This paper aims to survey preference of the environmental sounds suitable for the public spaces in urban areas such as parks, bus terminals. 35 kinds of natural sounds are rated by 26 pairs of adjectives. The results of psycho-acoustic experiments are as follows. 1. The proper adjectives for expressing the environmental sounds are classified into 6 groups of comfort, pleasure, fullness, variety, distinctness, naturalness. 2. Bird singing, murmuring of a stream, artificial sounds, singing of insects and animals are the affirmative order of preference. 3. Green musics consisted of music and natural sounds are preferred to the pure natural sounds. 4. Sound level relative to background noise causes various preferences to natural sounds in public spaces.

• Journal of the Ergonomics Society of Korea
• /
• v.25 no.4
• /
• pp.9-22
• /
• 2006

1/f fluctuation characteristics can be seen in various natural phenomena, such as breezes, streams, candle flames and the luminous patterns of fireflies. It is said that the 1/f fluctuation are comfortable for human beings. And they are introduced into many industrial products, such as an air conditioner, music, lighting, etc. This study focused on verifying the effects of 1/f fluctuation sound on comfort sensibility. Stimulus were divided into three groups(Group 1, 2, 3) by sound generation methodology. Fluctuation patterns of group 1, 2 were given by three types of fluctuation, 1/f0, 1/f1, 1/f2, and its of group 3 were given by two types of pure tone, 1/f1. In order to verify the effects, we measured the physiological responses of the subjects such as EEG(Electroencephalogram), ERP(Event-Related Potential), and these physiological responses were compared with subjective assessments, free answers. Consequently, we found that factor which had an effect on comfort sensibility was cognitive factor(for stimulus) rather than 1/f fluctuation sound pattern.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.7 no.8
• /
• pp.1714-1725
• /
• 2003

In this paper we propose reliable billing schemes between users and contents providers where a user is provided value­added service for a paid contents using mobile terminals. Our schemes support various types of services such as short messages, bell sounds, images or music data transmissions, and games in mobile communication environments. Using hash chain method, we also reduced the computational overhead of mobile terminals and the volume of data transmitted between the user and the content provider. Content providers can save memory space because they don't need to store each user's usage evidence but still can charge.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.11
• /
• pp.1980-1986
• /
• 2008

A digital watermarking technique used as a protection and certifying mechanism of copyrighted creations including music, still images, and videos in terms of lading any loss in data, reproduction and pursuit. This study suggests using a selected geometric invariant point through the whole processing procedure based on the invariant point so that it will be robust in a geometric transformation attack. The introduced algorithm here is based on a watershed splitting method in order to make medical images strong against RST transformation and other processing. This algorithm also proved that is has robustness against not only RST attack, but also JPEG compression attack and filtering attack.

• Journal of Multimedia Information System
• /
• v.4 no.4
• /
• pp.195-204
• /
• 2017

Mobile robots are used for years as a valuable research and educational tool in form of available open-platform designs and Do-It-Yourself kits. Rapid development and costs reduction of Unmanned Air Vehicles (UAV) and ground based mobile robots in recent years allowed researchers to utilize them as an affordable research platform. Despite of recent developments in the area of ground and airborne robotics, only few examples of Unmanned Surface Vehicle (USV) platforms targeted for research purposes can be found. Aim of this paper is to present the development of open-design USV drone with integrated multi-level control hardware architecture. Proposed catamaran - type water surface drone enables direct control over wireless radio link, separate development of algorithms for optimal propulsion control, navigation and communication with the ground-based control station. Whole design is highly modular, where each component can be replaced or modified according to desired task, payload or environmental conditions. Developed USV is planned to be utilized as a part of the system for detection and identification of marine and lake waste. Cameras mounted to the USV would record sea or lake surfaces, and recorded video sequences and images would be processed by state-of-the-art computer vision and machine learning algorithms in order to identify and classify marine and lake waste.

• Journal of Korea Game Society
• /
• v.6 no.2
• /
• pp.3-12
• /
• 2006

Recently, Many 3D augmented reality games that provide strengthened immersive have appeared in the 3D game environment. In this article, we describe a barehanded interaction method based on human hand gestures for augmented reality games. First, feature points are extracted from input video streams. Point features are tracked and motion of moving objects are computed. The shape of the motion trajectories are used to determine whether the motion is intended gestures. A long smooth trajectory toward one of virtual objects or menus is classified as an intended gesture and the corresponding action is invoked. To prove the validity of the proposed method, we implemented two simple augmented reality applications: a gesture-based music player and a virtual basketball game. In the music player, several menu icons are displayed on the top of the screen and an user can activate a menu by hand gestures. In the virtual basketball game, a virtual ball is bouncing in a virtual cube space and the real video stream is shown in the background. An user can hit the virtual ball with his hand gestures. From the experiments for three untrained users, it is shown that the accuracy of menu activation according to the intended gestures is 94% for normal speed gestures and 84% for fast and abrupt gestures.