• Journal of the Korean Institute of Intelligent Systems
• /
• v.5 no.3
• /
• pp.36-51
• /
• 1995

An approach to robot hybrid position/force control, which allows force manipulations to be realized without overshoot and overdamping while in the presence of unknown environment, is given in this paper. The manin idea is to used dynamic compensation for known robot parts and fuzzy compensation for unknown environment so as to improve system performance. The fuzzy compensation is implemented by using rule based fuzzy approach to identify the unknown environment. The establishment of proposed control system consists of following two stages. First, similar to the resovled acceleration control method, dynamic compensation and PD control based on known robot dynamics, kinematics and estimated environment stiffness is introduced. To avoid overshoot the whole control system is constructed with overdamping. In the second stage, the unknown environment stiffness is identified by using fuzzy reasoning, where the fuzzy compensation rules are obtained priori as the expression of the relationship betweenenvironment stiffness and system. Based on the simulation result, comparison between cases with or without fuzzy identifications are given, which illustrate the improvement achieced.

• The Journal of Information Systems
• /
• v.10 no.2
• /
• pp.151-164
• /
• 2001

현재의 항공사 기내식 수요예측 시스템으로는 항공기 운항의 지연이나 초과 주문으로 인한 손실 문제를 해결하기 힘든 것으로 알려져 있다. 이러한 문제를 해결하기 위해 본 연구에서는 항공기 기내식 시계열 자료만을 입력변수로 사용한 단순인공신경망모형(simple neural network model), 단순인공신경망모형에 전통적인 시계열 기법(본 연구에서는 지수 평활법)의 예측 결과를 입력변수로 추가한 혼합인공신경망모형(hybrid neural network model), 그리고 혼합인공신경 망 모형에 상관관계가 높은 다른 시계열 자료(본 논문에서는 유사 노선의 다른 항공기 기내식 시계열 자료)를 인공신경망의 입력변수로 추가시킨 하이퍼혼합인공신경망모형(hyper hybrid neural network model)을 새로운 항공기 기내식 수요예측 기법으로 제안하고, 이들 모형의 예측력을 비교 분석하였다. 분석 결과 하이퍼혼합인공신경망 모형의 예측력이 가장 우수한 것으로 나타나, 인공신경 망을 기반으로 한 수요예측에 있어 상관관계가 높은 다른 시계열 자료를 입력변수로 추가함으로써 인공신경망모형의 예측력을 개선시킬 수 있음을 알 수 있었다

• Journal of information and communication convergence engineering
• /
• v.10 no.2
• /
• pp.117-122
• /
• 2012

We propose a hybrid multiple access (HMA) for uplink orthogonal frequency division multiple access (OFDMA) systems, which combines two resource sharing schemes: a scheduling-based resource allocation (SBRA) scheme and a contentionbased resource allocation (CBRA) scheme. The SBRA scheme is appropriate for non-real time high data rate traffic, and, CBRA is appropriate for near-real time low/medium data rate traffic. Thus, the proposed HMA scheme supports various types of traffic. As a CBRA scheme, our proposed random frequency hopping (RFH)-OFDMA scheme was presented. Simulation results show that the proposed HMA yields the best performance among various resource allocation schemes for uplink OFDMA systems.

• Asia pacific journal of information systems
• /
• v.14 no.2
• /
• pp.131-149
• /
• 2004

Collaborative filtering is one of popular techniques for personalized recommendation in e-commerce sites. An advantage of collaborative filtering is that the technique can work with sparse evaluation data to predict preference scores of new alternative contents or advertisements. There is, however, no in-depth study about the sparsity effect of customer's evaluation data to the performance of recommendation. In this study, we investigate the sparsity effect and hybrid usages of customers' evaluation data and purchase data using an experiment result. The result of the analysis shows that the performance of recommendation decreases monotonically as the sparsity increases, and also the hybrid usage of two different types of data; customers' evaluation data and purchase data helps to increase the performance of recommendation in sparsity situation.

• International journal of advanced smart convergence
• /
• v.9 no.2
• /
• pp.58-67
• /
• 2020

In this paper, we propose a data-driven-based beam selection scheme for massive multiple-input and multiple-output (MIMO) systems in ultra-dense networks (UDN), which is capable of addressing the problem of high computational cost of conventional coordinated beamforming approaches. We consider highly dense small-cell scenarios with more small cells than mobile stations, in the millimetre-wave band. The analog beam selection for hybrid beamforming is a key issue in realizing millimetre-wave UDN MIMO systems. To reduce the computation complexity for the analog beam selection, in this paper, two deep neural network models are used. The channel samples, channel gains, and radio frequency beamforming vectors between the access points and mobile stations are collected at the central/cloud unit that is connected to all the small-cell access points, and are used to train the networks. The proposed machine-learning-based scheme provides an approach for the effective implementation of massive MIMO system in UDN environment.

• Asia pacific journal of information systems
• /
• v.10 no.1
• /
• pp.19-35
• /
• 2000

Data Envelopment Analysis(DEA), a non-parametric productivity analysis tool, has become an accepted approach for assessing efficiency in a wide range of fields. Despite of its extensive applications, some features of DEA remain bothersome. DEA offers no guidelines to where relatively inefficient DMU(Decision Making Unit) improve since a reference set of an inefficient DMU consists of several efficient DMUs and it doesn't provide a stepwise path for improving the efficiency of each inefficient DMU considering the difference of efficiency. We aim to show that DEA can be used to evaluate the efficiency of System Integration Projects and suggest the methodology which overcomes the limitation of DEA through hybrid analysis utilizing DEA along with machine learning.

• Asia pacific journal of information systems
• /
• v.5 no.1
• /
• pp.36-51
• /
• 1995

본 논문에서는 비구조적인 의사결정문제를 효과적으로 해결하기 위하여 감독학습 인공신경망 모형과 비감독학습 인공신경망 모형을 결합한 하이브리드 인공신경망 모형인 HYNEN(HYbrid NEural Network) 모형을 제안한다. HYNEN모형은 주어진 자료를 클러스터화 하는 CNN(Clustering Neural Network)과 최종적인 출력을 제공하는 ONN(Output Neural Network)의 2단계로 구성되어 있다. 먼저 CNN에서는 주어진 자료로부터 적정한 퍼지규칙을 찾기 위하여 클러스터를 구성한다. 그리고 이러한 클러스터를 지식베이스로하여 ONN에서 최종적인 의사결정을 한다. CNN에서는 SOFM(Self Organizing Feature Map)과 LVQ(Learning Vector Quantization)를 클러스터를 만든 후 역전파학습 인공신경망 모형으로 이를 학습한다. ONN에서는 역전파학습 인공신경망 모형을 이용하여 각 클러스터의 내용을 학습한다. 제안된 HYNEN 모형을 우리나라 기업의 도산자료에 적용하여 그 결과를 다변량 판별분석법(MDA:Multivariate Discriminant Analysis)과 ACLS(Analog Concept Learning System) 퍼지 ARTMAP 그리고 기존의 역전파학습 인공신경망에 의한 실험결과와 비교하였다.

• Proceedings of the Korea Society for Industrial Systems Conference
• /
• 2006.05a
• /
• pp.77-88
• /
• 2006

Data Envelopment Analysis (DEA), a non-parametric productivity analysis tool, has become an accepted approach for assessing efficiency in a wide range of fields. Despite of its extensive applications, some features of DEA remain bothersome. DEA offers no guidelines to where relatively inefficient DMU(Decision Making Unit) improve since a reference set of an inefficient DMU consists of several efficient DMUs and it doesn't provide a stepwise path for improving the efficiency of each inefficient DMU considering the difference of efficiency. We aim to show that DEA can be used to evaluate the efficiency of System Integration Projects and suggest the methodology which overcomes the limitation of DEA through hybrid analysis utilizing DEA along with machine learning.

• Journal of Institute of Control, Robotics and Systems
• /
• v.16 no.7
• /
• pp.681-687
• /
• 2010

In this paper, an implementation of force control for a slave mobile robot in tele-operation environment is presented. A mobile robot is built to have a force control capability with a force sensor and tested for force tracking control performances. Both position and contact force are regulated by a PID based hybrid control method and the impedance force control method. To minimize accumulated errors due to the adaptive impedance force control method, the novel force control method with a weighted function is proposed. Experimental studies of regulating contact forces for different control algorithms are tested and their performances are compared.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.8 no.3
• /
• pp.83-90
• /
• 2009

This paper presents the design and measurement of a flight model for a Ku-Band Linearized Channel Amplifier. All MMICs, Variable Gain Amplifier (VGA), Variable Voltage Attenuator ('.IVA), Branch line Coupler and Detector for Pre-distorter are fabricated using a Thin-Film Hybrid process. The performance of the fabricated module is verified through the radio frequency circuit simulation tool and electrical function test in space environment.