Go to the main menu
Skip to content
Go to bottom
REFERENCE LINKING PLATFORM OF KOREA S&T JOURNALS
> Journal Vol & Issue
Journal of Korean Institute of Intelligent Systems
Journal Basic Information
Journal DOI :
Korean Institute of Intelligent Systems
Editor in Chief :
Volume & Issues
Volume 25, Issue 6 - Dec 2015
Volume 25, Issue 5 - Oct 2015
Volume 25, Issue 4 - Aug 2015
Volume 25, Issue 3 - Jun 2015
Volume 25, Issue 2 - Apr 2015
Volume 25, Issue 1 - Feb 2015
Selecting the target year
Balancing Control of a Single-wheel Mobile Robot by Compensation of a Fuzzified Balancing Angle
Ha, Minsu ; Jung, Seul ;
Journal of Korean Institute of Intelligent Systems, volume 25, issue 1, 2015, Pages 1~6
DOI : 10.5391/JKIIS.2015.25.1.001
In this paper, a fuzzy control method is used for balancing a single-wheel robot. A single-wheel robot controlled by the PD control method becomes easily unstable since the flywheel tends to lean against one direction. In the previous research, we have used the gain scheduling method. To remedy this problem, in this paper, a fuzzy compensation technique is proposed to compensate for the balancing angle. The fuzzy control method compensates offset values at the balancing angle to prevent the gimbal from falling against one direction. Experimental studies of the balancing control performance of a single-wheel mobile robot validate the proposed control method.
High Gain Observer-based Robust Tracking Control of LIM for High Performance Automatic Picking System
Choi, Jung-Hyun ; Kim, Jung-Su ; Kim, Sanghoon ; Yoo, Dong Sang ; Kim, Kyeong-Hwa ;
Journal of Korean Institute of Intelligent Systems, volume 25, issue 1, 2015, Pages 7~14
DOI : 10.5391/JKIIS.2015.25.1.007
To implement an automatic picking system (APS) in distribution center with high precision and high dynamics, this paper presents a high gain observer-based robust speed controller design for a linear induction motor (LIM) drive. The force disturbance as well as the mechanical parameter variations such as the mass and friction coefficient gives a direct influence on the speed control performance of APS. To guarantee a robust control performance, the system uncertainty caused by the force disturbance and mechanical parameter variations is estimated through a high gain disturbance observer and compensated by a feedforward manner. While a time-varying disturbance due to the mass variation can not be effectively compensated by using the conventional disturbance observer, the proposed scheme shows a robust performance in the presence of such uncertainty. A Simulink library has been developed for the LIM model from the state equation. Through comparative simulations based on Matlab - Simulink, it is proved that the proposed scheme has a robust control nature and is most suitable for APS.
Parameter Tuning in Support Vector Regression for Large Scale Problems
Ryu, Jee-Youl ; Kwak, Minjung ; Yoon, Min ;
Journal of Korean Institute of Intelligent Systems, volume 25, issue 1, 2015, Pages 15~21
DOI : 10.5391/JKIIS.2015.25.1.015
In support vector machine, the values of parameters included in kernels affect strongly generalization ability. It is often difficult to determine appropriate values of those parameters in advance. It has been observed through our studies that the burden for deciding the values of those parameters in support vector regression can be reduced by utilizing ensemble learning. However, the straightforward application of the method to large scale problems is too time consuming. In this paper, we propose a method in which the original data set is decomposed into a certain number of sub data set in order to reduce the burden for parameter tuning in support vector regression with large scale data sets and imbalanced data set, particularly.
Evolution of Behavioral Logic of Artificial Individuals Using Cell-level Evolution Framework
Jung, Bo-Sun ; Jung, Sung Hoon ;
Journal of Korean Institute of Intelligent Systems, volume 25, issue 1, 2015, Pages 22~28
DOI : 10.5391/JKIIS.2015.25.1.022
In this paper, we studied the evolution of behavioral logic of artificial individuals using cell-level evolution framework. We first implemented cell-level evolution framework and then investigated the evolution of behavioral logic that artificial individuals ate foods on the framework. A logic frame for behavioral decisions of artificial individuals was devised and applied to the framework. From extensive tests, we found that most artificial individuals could evolve the behavioral logic that they could eat food in a short generation. It was also confirmed that most behavioral logics showed nearly same behaviors of artificial individuals in most tests. Our method has the differences from existing algorithms using evolutionary algorithms and evolvable hardwares in that it is a basically different approach. These results showed that our framework could be a good tool for investigating the evolution of artificial individuals in a cell-level.
EEG Feature Classification for Precise Motion Control of Artificial Hand
Kim, Dong-Eun ; Yu, Je-Hun ; Sim, Kwee-Bo ;
Journal of Korean Institute of Intelligent Systems, volume 25, issue 1, 2015, Pages 29~34
DOI : 10.5391/JKIIS.2015.25.1.029
Brain-computer interface (BCI) is being studied for convenient life in various application fields. The purpose of this study is to investigate a changing electroencephalography (EEG) for precise motion of a robot or an artificial arm. Three subjects who participated in this experiment performed three-task: Grip, Move, Relax. Acquired EEG data was extracted feature data using two feature extraction algorithm (power spectrum analysis and multi-common spatial pattern). Support vector machine (SVM) were applied the extracted feature data for classification. The classification accuracy was the highest at Grip class of two subjects. The results of this research are expected to be useful for patients required prosthetic limb using EEG.
Moving Objects Tracking Method using Spatial Projection in Intelligent Video Traffic Surveillance System
Hong, Kyung Taek ; Shim, Jae Homg ; Cho, Young Im ;
Journal of Korean Institute of Intelligent Systems, volume 25, issue 1, 2015, Pages 35~41
DOI : 10.5391/JKIIS.2015.25.1.035
When a video surveillance system tracks a specific object, it is very important to get quickly the information of the object through fast image processing. Usually one camera surveillance system for tracking the object made results in various problems such like occlusion, image noise during the tracking process. It makes difficulties on image based moving object tracking. Therefore, to overcome the difficulties the multi video surveillance system which installed several camera within interested area and looking the same object from multi angles of view could be considered as a solution. If multi cameras are used for tracking object, it is capable of making a decision having high accuracy in more wide space. This paper proposes a method of recognizing and tracking a specific object like a car using the homography in which multi cameras are installed at the crossroad.
Rank-based Formation for Multiple Robots in a Local Coordinate System
Jung, Hahmin ; Kim, Dong Hun ;
Journal of Korean Institute of Intelligent Systems, volume 25, issue 1, 2015, Pages 42~47
DOI : 10.5391/JKIIS.2015.25.1.042
This paper presents a rank-based formation for multiple agents based on potential functions, where the proposed method uses the relative position of two neighboring agents. The conventional formation scheme of multiple systems requires communication between agents and a central computer to get the positions of all multiple agents. In the study, differently from previous studies, the formation scheme uses the relative position of two neighboring agents in a local coordinate system. In addition, it introduces a singular agent association that considers only the relative position between an agent and its neighboring agents, instead of multiple associations among all information about all agents. Furthermore, the proposed framework explores the benefits of different formation types. Extensive simulation results show that the proposed approach verifies the viability and effectiveness of the proposed formation.
Implementation of a Smartphone Interface for a Personal Mobility System Using a Magnetic Compass Sensor and Wireless Communication
Kim, Yeongyun ; Kim, Dong Hun ;
Journal of Korean Institute of Intelligent Systems, volume 25, issue 1, 2015, Pages 48~56
DOI : 10.5391/JKIIS.2015.25.1.048
In the paper, a smartphone-controlled personal mobility system(PMS) based on a compass sensor is developed. The use of a magnetic compass sensor makes the PMS move according to the heading direction of a smartphone controlled by a rider. The proposed smartphone-controlled PMS allows more intuitive interface than PMS controlled by pushing a button. As well, the magnetic compass sensor makes a role in compensating for the mechanical characteristics of motors mounted on the PMS. For adequate control of the robot, two methods: absolute and relative direction methods based on the magnetic compass sensor and wireless communication are presented. Experimental results show that the PMS is conveniently and effectively controlled by the proposed two methods.
Design of Fuzzy Inference-based Deterioration Diagnosis System through Different Image
Kim, Jong-Bum ; Choi, Woo-Yong ; Oh, Sung-Kwun ; Kim, Young-Il ;
Journal of Korean Institute of Intelligent Systems, volume 25, issue 1, 2015, Pages 57~62
DOI : 10.5391/JKIIS.2015.25.1.057
In this paper, we design fuzzy inference-based deterioration diagnosis system through different image for rapid as well as efficient diagnosis of electrical equipments. When the deterioration diagnosis of the electrical equipment starts, abnormal state of assigned area is detected by comparing with the temperature of the first normal state of the area. Deterioration state of detected area is diagnosed by using fuzzy inference algorithm. In the fuzzy inference algorithm, fuzzy rules are defined by If-then form and are described as look-up table. Both temperature and its ensuing variation are used as input variables. While triangular membership function is used for the fuzzy input variables of fuzzy rules, singleton membership function is used for the output variable of fuzzy rules. The final output is calculated by using the center of gravity of fuzzy inference method. Experimental data acquired from individual electrical equipments is used in order to evaluate the output performance of the proposed system.
Pattern and Instance Generation for Self-knowledge Learning in Korean
Yoon, Hee-Geun ; Park, Seong-Bae ;
Journal of Korean Institute of Intelligent Systems, volume 25, issue 1, 2015, Pages 63~69
DOI : 10.5391/JKIIS.2015.25.1.063
There are various researches which proposed an automatic instance generation from freetext on the web. Existing researches that focused on English, adopts pattern representation which is generated by simple rules and regular expression. These simple patterns achieves high performance, but it is not suitable in Korean due to differences of characteristics between Korean and English. Thus, this paper proposes a novel method for generating patterns and instances which focuses on Korean. A proposed method generates high quality patterns by taking advantages of dependency relations in a target sentences. In addition, a proposed method overcome restrictions from high degree of freedom of word order in Korean by utilizing postposition and it identifies a subject and an object more reliably. In experiment results, a proposed method shows higher precision than baseline and it is implies that proposed approache is suitable for self-knowledge learning system.
Implementation and Performance Comparison for an Underwater Robot Localization Methods Using Seabed Terrain Information
Noh, Sung Woo ; Ko, Nak Yong ; Choi, Hyun Taek ;
Journal of Korean Institute of Intelligent Systems, volume 25, issue 1, 2015, Pages 70~77
DOI : 10.5391/JKIIS.2015.25.1.070
This paper proposes an application of unscented Kalman filter(UKF) for localization of an underwater robot. The method compares the bathymetric measurement from the robot with the seabed terrain information. For the measurement of bathymetric range to seabed, it uses a DVL which typically yields four range data together with velocity of the robot. Usual extended Kalman filter is not appropriated for application in case of terrain navigation, since it is not feasible to derive Jacobian for the bathymetric range measurement. Though particle filter(PF) is a nice solution which doesn`t require Jacobian and can deal with non-linear and non-Gaussian system and measurement, it suffers from heavy computational burden. The paper compares the localization performance and the computation time of the UKF approach and PF approach. Though there have been some UKF methods which are used for underwater navigation, application of the UKF for bathymetric localization is rare. Especially, the proposed method uses only four range data whereas many of the bathymetric navigation methods have used multibeam sonar which yields hundreds of scanned range data. The result shows feasibility of the UKF approach for terrain-based navigation using small numbers of range data.
Boundary Depth Estimation Using Hough Transform and Focus Measure
Kwon, Dae-Sun ; Lee, Dae-Jong ; Chun, Myung-Geun ;
Journal of Korean Institute of Intelligent Systems, volume 25, issue 1, 2015, Pages 78~84
DOI : 10.5391/JKIIS.2015.25.1.078
Depth estimation is often required for robot vision, 3D modeling, and motion control. Previous method is based on the focus measures which are calculated for a series of image by a single camera at different distance between and object. This method, however, has disadvantage of taking a long time for calculating the focus measure since the mask operation is performed for every pixel in the image. In this paper, we estimates the depth by using the focus measure of the boundary pixels located between the objects in order to minimize the depth estimate time. To detect the boundary of an object consisting of a straight line and a circle, we use the Hough transform and estimate the depth by using the focus measure. We performed various experiments for PCB images and obtained more effective depth estimation results than previous ones.
Structure Analysis for Core Competency of CEO
Park, Young-Man ; Hwan, Seung-Gook ;
Journal of Korean Institute of Intelligent Systems, volume 25, issue 1, 2015, Pages 85~90
DOI : 10.5391/JKIIS.2015.25.1.085
In this paper, the structural analysis, which used Fuzzy Structural Modeling, was conducted about the 24 core cometencies of CEO of SME. It classified them into five groups. Also, regression analysis was conducted to evaluate the relationship beween the job capability and core competencies of the CEO. The characteristic of this paper is to know the relationship beween the structure and classification of the layers for the core competency of CEO, and is to know that each competency group has an influence on the job capability of CEO.
Design of Robust Face Recognition System with Illumination Variation Realized with the Aid of CT Preprocessing Method
Jin, Yong-Tak ; Oh, Sung-Kwun ; Kim, Hyun-Ki ;
Journal of Korean Institute of Intelligent Systems, volume 25, issue 1, 2015, Pages 91~96
DOI : 10.5391/JKIIS.2015.25.1.091
In this study, we introduce robust face recognition system with illumination variation realized with the aid of CT preprocessing method. As preprocessing algorithm, Census Transform(CT) algorithm is used to extract locally facial features under unilluminated condition. The dimension reduction of the preprocessed data is carried out by using
PCA which is the extended type of PCA. Feature data extracted through dimension algorithm is used as the inputs of proposed radial basis function neural networks. The hidden layer of the radial basis function neural networks(RBFNN) is built up by fuzzy c-means(FCM) clustering algorithm and the connection weights of the networks are described as the coefficients of linear polynomial function. The essential design parameters (including the number of inputs and fuzzification coefficient) of the proposed networks are optimized by means of artificial bee colony(ABC) algorithm. This study is experimented with both Yale Face database B and CMU PIE database to evaluate the performance of the proposed system.
Unsupervised Incremental Learning of Associative Cubes with Orthogonal Kernels
Kang, Hoon ; Ha, Joonsoo ; Shin, Jangbeom ; Lee, Hong Gi ; Wang, Yang ;
Journal of Korean Institute of Intelligent Systems, volume 25, issue 1, 2015, Pages 97~104
DOI : 10.5391/JKIIS.2015.25.1.097
An `associative cube`, a class of auto-associative memories, is revisited here, in which training data and hidden orthogonal basis functions such as wavelet packets or Fourier kernels, are combined in the weight cube. This weight cube has hidden units in its depth, represented by a three dimensional cubic structure. We develop an unsupervised incremental learning mechanism based upon the adaptive least squares method. Training data are mapped into orthogonal basis vectors in a least-squares sense by updating the weights which minimize an energy function. Therefore, a prescribed orthogonal kernel is incrementally assigned to an incoming data. Next, we show how a decoding procedure finds the closest one with a competitive network in the hidden layer. As noisy test data are applied to an associative cube, the nearest one among the original training data are restored in an optimal sense. The simulation results confirm robustness of associative cubes even if test data are heavily distorted by various types of noise.