Go to the main menu
Skip to content
Go to bottom
REFERENCE LINKING PLATFORM OF KOREA S&T JOURNALS
> Journal Vol & Issue
The KIPS Transactions:PartB
Journal Basic Information
Journal DOI :
Korea Information Processing Society
Editor in Chief :
Volume & Issues
Volume 9B, Issue 6 - Dec 2002
Volume 9B, Issue 5 - Oct 2002
Volume 9B, Issue 4 - Aug 2002
Volume 9B, Issue 3 - Jun 2002
Volume 9B, Issue 2 - Apr 2002
Volume 9B, Issue 1 - Feb 2002
Selecting the target year
Design and implementation of Robot Soccer Agent Based on Reinforcement Learning
Kim, In-Cheol ;
The KIPS Transactions:PartB, volume 9B, issue 2, 2002, Pages 139~146
DOI : 10.3745/KIPSTB.2002.9B.2.139
The robot soccer simulation game is a dynamic multi-agent environment. In this paper we suggest a new reinforcement learning approach to each agent's dynamic positioning in such dynamic environment. Reinforcement learning is the machine learning in which an agent learns from indirect, delayed reward an optimal policy to choose sequences of actions that produce the greatest cumulative reward. Therefore the reinforcement learning is different from supervised learning in the sense that there is no presentation of input-output pairs as training examples. Furthermore, model-free reinforcement learning algorithms like Q-learning do not require defining or learning any models of the surrounding environment. Nevertheless these algorithms can learn the optimal policy if the agent can visit every state-action pair infinitely. However, the biggest problem of monolithic reinforcement learning is that its straightforward applications do not successfully scale up to more complex environments due to the intractable large space of states. In order to address this problem, we suggest Adaptive Mediation-based Modular Q-Learning (AMMQL) as an improvement of the existing Modular Q-Learning (MQL). While simple modular Q-learning combines the results from each learning module in a fixed way, AMMQL combines them in a more flexible way by assigning different weight to each module according to its contribution to rewards. Therefore in addition to resolving the problem of large state space effectively, AMMQL can show higher adaptability to environmental changes than pure MQL. In this paper we use the AMMQL algorithn as a learning method for dynamic positioning of the robot soccer agent, and implement a robot soccer agent system called Cogitoniks.
A Study to Generate a Theory of Coordination for Intelligent Agent Societies
Kim, Eun-Gyung ;
The KIPS Transactions:PartB, volume 9B, issue 2, 2002, Pages 147~154
DOI : 10.3745/KIPSTB.2002.9B.2.147
In bulding Intelligent Agent Societies (IAS), it is very important to design and implement coordination in accordance with the known requirement and anticipated working conditions. Coordination consists of a set of mechanisms necessary for the effective operation of IAS. Currently, there is little theoretical support that could help in this research is to generate an empirically-based solving systems in which all agent share an identical goal structure and fully cooperate. And we developed a simulation model called "P-System" which produces basic data to be used for statistical analysis to generate a theory of coordination. Coordination among agent in the P-System is dependent on 23 control variables calld TEs(tweakable emtities.)And the level of coordination is represennted by an independent variabe called QMC (Quality Measure Coordination) expressed in numerical terms according tn the definiion of this study. Also, we have studied how to select unbiased subset from the huge total experimental space of the P-System and how to decide the scale of the subset.
Online Reinforcement Learning to Search the Shortest Path in Maze Environments
Kim, Byeong-Cheon ; Kim, Sam-Geun ; Yun, Byeong-Ju ;
The KIPS Transactions:PartB, volume 9B, issue 2, 2002, Pages 155~162
DOI : 10.3745/KIPSTB.2002.9B.2.155
Reinforcement learning is a learning method that uses trial-and-error to perform Learning by interacting with dynamic environments. It is classified into online reinforcement learning and delayed reinforcement learning. In this paper, we propose an online reinforcement learning system (ONRELS : Outline REinforcement Learning System). ONRELS updates the estimate-value about all the selectable (state, action) pairs before making state-transition at the current state. The ONRELS learns by interacting with the compressed environments through trial-and-error after it compresses the state space of the mage environments. Through experiments, we can see that ONRELS can search the shortest path faster than Q-learning using TD-ewor and
in the maze environments.
A User Interface Model for B2B Negotiation
Im, Gi-Yeong ; Go, Seong-Beom ; Won, Il-Yong ; Lee, Chang-Hun ;
The KIPS Transactions:PartB, volume 9B, issue 2, 2002, Pages 163~172
DOI : 10.3745/KIPSTB.2002.9B.2.163
One of the characteristics the agent-based negotiation model has is that we have to input the related parameters together. Considering such properties as vagueness, incompleteness and dynamism B2B domain inherently has this may be an unreasonable request. In this paper we suggested a user interface model for B2B negotiation which mainly focussed on this problem. The suggested model supports such functions as a two dimensional negotiation space, diverse negotiation modes and emotion-based control mechanism. In this paper, we tried to show how these three functions can be used for improving the usefulness of the existing agent-based negotiation model.
An Effective Training Pattern Processing Method for ATM Connection Admission Control Using the Neural Network
Kwon, Oh-Jun ; Jeon, Hyoung-Goo ; Kwon, Soon-Kak ; Kim, Tai-Suk ; Lee, Jeong-Bae ;
The KIPS Transactions:PartB, volume 9B, issue 2, 2002, Pages 173~180
DOI : 10.3745/KIPSTB.2002.9B.2.173
The virtual cell loss rate was introduced for the training pattern of the neural network in the VOB(Virtual Output Buffer) model. The VOB model shows that the neural network can find the connection admission boundary without the real cell loss rate. But the VOB model tends to overestimate the cell loss rate, so the utilization of network is low. In this paper, we uses the reference curve of the cell loss rate, which contains the information about the cell loss rate at the connection admission boundary. We process the patterns of the virtual cell loss rate using the reference curve, We performed the simulation with two major ATM traffic classes. One is On-Off traffic class that has the traffic characteristic of LAN data and other is Auto-Regressive traffic class that has the traffic characteristic of a video image communication.
Multimedia System for Streaming Time-Continuous Screen Images and Audio
Hwang, Ki-Tae ;
The KIPS Transactions:PartB, volume 9B, issue 2, 2002, Pages 181~190
DOI : 10.3745/KIPSTB.2002.9B.2.181
This paper proposes a motion-video multimedia system needed for computer applications like remote lecturing, distance learning, product demonstrations, and so on. The applications need a multimedia system which can author and play a motion-Video that is composed with computer screen images and audio continuously varing as time flows, not with real motion videos. Since the computer screen images are not like the real world video images in several rejects, MPEG is not competent as a compression algorithm for computer screen images raring continuously In this paper a new compression algorithm has been proposed, and a multimedia system that authors and plays a motion-video file which contains computer screen images and audio has been implemented. Also this paper shows the result of performance evaluation of both the compression algorithm and the multimedia system implemented in the paper.
Experimental Analysis of RAID Architecture for Real-Time Multimedia Data
Jeon, Sang-Hoon ; Ahn, Byoung-Chul ;
The KIPS Transactions:PartB, volume 9B, issue 2, 2002, Pages 191~198
DOI : 10.3745/KIPSTB.2002.9B.2.191
Recently, Usage of multimedia server is rapidly increased with expansion of internet that real-time displaying service for multimedia data, MPEG and etc. For these multimedia real-time applications, it is necessary to use a disk array as a storage system. For providing requested service to much more clients at the same time in a multimedia data storage server, considerable varied strategies in a several parts. But especially it is important feature to various parameters for disk array such as relation of striping block size as a system environment and characteristics of video data. In this paper, we implemented real environment of multimedia server which provides MPEG-1 files and evaluated the suitable storage system architectures by applying synthetically generated workloads in the various parameters for disk array.
An Adaptive Block Matching Algorithm Based on Temporal Correlations
Yoon, Hyo-Sun ; Lee, Guee-Sang ;
The KIPS Transactions:PartB, volume 9B, issue 2, 2002, Pages 199~204
DOI : 10.3745/KIPSTB.2002.9B.2.199
Since motion estimation and motion compensation methods remove the redundant data to employ the temporal redundancy in images, it plays an important role in digital video compression. Because of its high computational complexity, however, it is difficult to apply to high-resolution applications in real time environments. If we have information about the motion of an image block before the motion estimation, the location of a better starting point for the search of an exact motion vector can be determined to expedite the searching process. In this paper, we present an adaptive motion estimation approach bated on temporal correlations of consecutive image frames that defines the search pattern and determines the location of the initial search point adaptively. Through experiments, compared with DS(Diamond Search) algorithm, the proposed algorithm is about 0.1∼0.5(dB) better than DS in terms of PSNR(Peak Signal to Noise Ratio) and improves as high as 50% compared with DS in terms of average number of search point per motion vector estimation.
A Study on the Modified FCM Algorithm using Intracluster
Ahn, Kang-Sik ; Cho, Seok-Je ;
The KIPS Transactions:PartB, volume 9B, issue 2, 2002, Pages 202~214
DOI : 10.3745/KIPSTB.2002.9B.2.202
In this paper, we propose a modified FCM (MFCM) algorithm to solve the problems of the FCM algorithm and the fuzzy clustering algorithm using an average intracluster distance (FCAID). The MFCM algorithm grants the regular grade of membership in the small size of cluster. And it clears up the convergence problem of objective function because its objective function is designed according to the grade of membership of it, verified, and used for clustering data. So, it can solve the problem of the FCM algorithm in different size of cluster and the FCAID algorithm in the convergence problem of objective function. To verify the MFCM algorithm, we compared with the result of the FCM and the FCAID algorithm in data clustering. From the experimental results, the MFCM algorithm has a good performance compared with others by classification entropy.
Phonetic Acoustic Knowledge and Divide And Conquer Based Segmentation Algorithm
Koo, Chan-Mo ; Wang, Gi-Nam ;
The KIPS Transactions:PartB, volume 9B, issue 2, 2002, Pages 215~222
DOI : 10.3745/KIPSTB.2002.9B.2.215
This paper presents a reliable fully automatic labeling system which fits well with languages having well-developed syllables such as in Korean. The ASL System utilize DAC (Divide and Conquer), a control mechanism, based segmentation algorithm to use phonetic and acoustic information with greater efficiency. The segmentation algorithm is to devide speech signals into speechlets which is localized speech signal pieces and to segment each speechlet for speech boundaries. While HMM method has uniform and definite efficiencies, the suggested method gives framework to steadily develope and improve specified acoustic knowledges as a component. Without using statistical method such as HMM, this new method use only phonetic-acoustic information. Therefore, this method has high speed performance, is consistent extending the specific acoustic knowledge component, and can be applied in efficient way. we show experiment result to verify suggested method at the end.
A Study on TSIUVC Approximate-Synthesis Method using Least Mean Square
Lee, See-Woo ;
The KIPS Transactions:PartB, volume 9B, issue 2, 2002, Pages 223~230
DOI : 10.3745/KIPSTB.2002.9B.2.223
In a speech coding system using excitation source of voiced and unvoiced, it would be involves a distortion of speech waveform in case coexist with a voiced and an unvoiced consonants in a frame. This paper present a new method of TSIUVC (Transition Segment Including Unvoiced Consonant) approximate-synthesis by using Least Mean Square. The TSIUVC extraction is based on a zero crossing rate and IPP (Individual Pitch Pulses) extraction algorithm using residual signal of FIR-STREAK Digital Filter. As a result, This method obtain a high Quality approximation-synthesis waveform by using Least Mean Square. The important thing is that the frequency signals in a maximum error signal can be made with low distortion approximation-synthesis waveform. This method has the capability of being applied to a new speech coding of Voiced/Silence/TSIUVC, speech analysis and speech synthesis.
A Study on Extracting Valid Speech Sounds by the Discrete Wavelet Transform
Kim, Jin-Ok ; Hwang, Dae-Jun ; Baek, Han-Uk ; Jeong, Jin-Hyeon ;
The KIPS Transactions:PartB, volume 9B, issue 2, 2002, Pages 231~236
DOI : 10.3745/KIPSTB.2002.9B.2.231
The classification of the speech-sound block comes from the multi-resolution analysis property of the discrete wavelet transform, which is used to reduce the computational time for the pre-processing of speech recognition. The merging algorithm is proposed to extract vapid speech-sounds in terms of position and frequency range. It performs unvoiced/voiced classification and denoising. Since the merging algorithm can decide the processing parameters relating to voices only and is independent of system noises, it is useful for extracting valid speech-sounds. The merging algorithm has an adaptive feature for arbitrary system noises and an excellent denoising signal-to-noise ratio and a useful system tuning for the system implementation.
A Stereo Image Recognition-Based Method for measuring the volume of 3D Object
Jeong, Yun-Su ; Lee, Hae-Won ; Kim, Jin-Seok ; Won, Jong-Un ;
The KIPS Transactions:PartB, volume 9B, issue 2, 2002, Pages 237~244
DOI : 10.3745/KIPSTB.2002.9B.2.237
In this paper, we propose a stereo image recognition-based method for measuring the volume of the rectangular parallelepiped. The method measures the volume from two images captured with two CCD (charge coupled device) cameras by sequential processes such as ROI (region of interest) extraction, feature extraction, and stereo matching-based vortex recognition. The proposed method makes it possible to measure the volume of the 3D object at high speed because only a few features are used in the process of stereo matching. From experimental results, it is demonstrated that this method is very effective for measuring the volume of the rectangular parallelepiped at high speed.
An Adaptive Multi-Level Thresholding and Dynamic Matching Unit Selection for IC Package Marking Inspection
Kim, Min-Ki ;
The KIPS Transactions:PartB, volume 9B, issue 2, 2002, Pages 245~254
DOI : 10.3745/KIPSTB.2002.9B.2.245
IC package marking inspection system using machine vision locates and identifies the target elements from input image, and decides the quality of marking by comparing the extracted target elements with the standard patterns. This paper proposes an adaptive multi-level thresholding (AMLT) method which is suitable for a series of operations such as locating the target IC package, extracting the characters, and detecting the Pinl dimple. It also proposes a dynamic matching unit selection (DMUS) method which is robust to noises as well as effective to catch out the local marking errors. The main idea of the AMLT method is to restrict the inputs of Otsu's thresholding algorithm within a specified area and a partial range of gray values. Doing so, it can adapt to the specific domain. The DMUS method dynamically selects the matching unit according to the result of character extraction and layout analysis. Therefore, in spite of the various erroneous situation occurred in the process of character extraction and layout analysis, it can select minimal matching unit in any environment. In an experiment with 280 IC package images of eight types, the correct extracting rate of IC package and Pinl dimple was 100% and the correct decision rate of marking quality was 98.8%. This result shows that the proposed methods are effective to IC package marking inspection.
Application of Image Based VR Technique for Volume Data Web Service
Kim, Yeon-Ho ; Park, Jong-Gu ;
The KIPS Transactions:PartB, volume 9B, issue 2, 2002, Pages 255~262
DOI : 10.3745/KIPSTB.2002.9B.2.255
The Virtual Reality (VR) is an appealing subject which can be applied to various areas because of its merit - removal of time limits and space. Recently, as the technology of xDSL spreads widely, a concern of VR is on the on-line service of 3D model data in real time. But, the immensity of 3D model is an obstacle to achieve these endeavors. To solve these problems, the image based VR technique is applied. The proposed method in this paper is one of solutions on the immensity problem of 3D model data in the on-line services. This paper exploits the mixed technique of image based VR and surface rendering based on volume rendering. By using the proposed method, we can solve the immensity problem. Consequently, tole service user can explore virtual 2D volume model with almost equal to reality of 3D volume model. Furthermore, this paper explains a method to implement this service on general web environments. Of course, to fulfill these procedures, additional skills which reduce consuming time in data mining are also mentioned. The contribution of this paper is to provide a practical method for handling of large volume data web service in real-time. illustrative examples are presented to show the effectiveness of the proposed method.