• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.2027-2032
• /
• 2003

For action selection as well as learning, simple associations between stimulus and response have been employed in most of literatures. But, for a successful task accomplishment, it is required that an animat can learn and express behavioral sequences. In this paper, we propose a novel action-selection-mechanism to deal with sequential behaviors. For this, we define behavioral motivation as a primitive node for action selection, and then hierarchically construct a network with behavioral motivations. The vertical path of the network represents behavioral sequences. Here, such a tree for our proposed ASM can be newly generated and/or updated, whenever a new sequential behaviors is learned. To show the validity of our proposed ASM, three 2-D grid world simulations will be illustrated.

• 한국BIM학회 논문집
• /
• 제5권2호
• /
• pp.34-45
• /
• 2015

As buildings become larger and more complicated, construction costs have increased with a considerable effect on buildings' Life Cycle Cost (LCC). However, there has been little consideration on economic aspects in the selection of construction materials due to limited information on the materials and dependency in architects' experience and inefficiency in cost estimation, causing design changes, increase in maintenance cost, difficulty in budgeting, and decrease in building performance. To solve these problems, this study proposed a BIM-based material selection model which reflects the comprehensive economic efficiency of building materials. Our cost prediction model can estimates the material-related cost during the entire building life cycle. Furthermore, we implemented the proposed model in connection with BIM, which can analyze and compare LCC by material. Through the validation of the model, we could confirm the necessity of LCC-based material selection in comparison with the conventional cost-centered material selection.

• International Journal of Internet, Broadcasting and Communication
• /
• 제9권4호
• /
• pp.51-58
• /
• 2017

This paper deals with the improvement of cluster head selection method in L-SEP for heterogeneous nodes among hierarchical routing protocols of wireless sensor network. Wireless sensor networks are classified into homogeneous and heterogeneous network. In heterogeneous network, SEP, L-SEP are mainly used because cluster head selection probability is different depending on node type. But, since protocol based on SEP has different cluster head selection probabilities depending on the node type, clusters that transmit data inefficiently can be formed. to improve this, it is necessary to select the cluster head that minimizes the transmission distance of member node and the cluster head. Therefore, we propose a protocol that improve the cluster head selection method.

• Journal of the Korean Data and Information Science Society
• /
• 제16권2호
• /
• pp.195-205
• /
• 2005

In decision tree analysis, C4.5 and CART algorithm have some problems of computational complexity and bias on variable selection. But QUEST algorithm solves these problems by dividing the step of variable selection and split point selection. When input variables are continuous, QUEST algorithm uses ANOVA F-test under the assumption of normality and homogeneity of variances. In this paper, we investigate the influence of violation of normality assumption and effect of the transformation of variables in the QUEST algorithm. In the simulation study, we obtained the empirical powers of variable selection and the empirical bias of variable selection after transformation of variables having various type of underlying distributions.

• International journal of advanced smart convergence
• /
• 제10권1호
• /
• pp.56-61
• /
• 2021

Neighbor path selection is to pre-select alternate routes in case geographically correlated failures occur simultaneously on the communication network. Conventional heuristic-based algorithms no longer improve solutions because they cannot sufficiently utilize historical failure information. We present a novel solution model for neighbor path selection by using machine learning technique. Our proposed machine learning neighbor path selection (ML-NPS) model is composed of five modules- random graph generation, data set creation, machine learning modeling, neighbor path prediction, and path information acquisition. It is implemented by Python with Keras on Tensorflow and executed on the tiny computer, Raspberry PI 4B. Performance evaluations via numerical simulation show that the neighbor path communication success probability of our model is better than that of the conventional heuristic by 26% on the average.

• Journal of the Korean Data and Information Science Society
• /
• 제28권5호
• /
• pp.1099-1107
• /
• 2017

본 연구에서는 한국고용정보원에서 실시한 "2014년 대졸자 직업이동 경로조사" 자료를 활용하여 대졸자의 임금결정요인을 분석하였다. 일반적으로 임금은 개인의 취업여부와 임금의 크기에 대한 두 가지의 복합적인 정보를 담고 있으나, 많은 선행연구에서는 임금의 크기에 대한 정보만을 활용하여 선형 회귀분석을 수행함으로써 표본선택에 위한 편의 (sample selection bias) 문제가 발생하게 된다. 이런 문제점을 극복하기 위해 본 연구에서는 Heckman의 표본선택 모형을 분석에 활용하였다. 주요 분석 결과를 요약하면 다음과 같다. 먼저 Heckman의 표본선택 모형에 대한 타당성은 통계적으로 유의함을 알 수 있었다. 남자는 여자에 비해서 취업확률과 임금의 크기 모두 통계적으로 유의하게 높게 나타났으며, 연령이 증가하고 부모의 소득이 증가 할수록 취업확률과 임금의 크기 모두 높게 나타났다. 또한 대학만족도가 높아질수록, 그리고 취득한 자격증 수가 증가할수록 취업확률과 임금 모두 증가하는 경향이 있는 것으로 나타났다.

• 한국정보통신학회논문지
• /
• 제20권12호
• /
• pp.2213-2218
• /
• 2016

본 논문은 복수 개의 중계기와 도청자가 존재하는 중계기 통신 네트워크에서 보안 오류 확률을 낮출 수 있는 새로운 중계기 선택 기법을 제안한다. 도청자의 복호 확률을 낮추기 위해서 데이터와 함께 재밍 신호를 전송하는 기존의 중계기 선택 방식에서는 수신자의 데이터 복호 확률도 낮아지는 문제점이 있었다. 본 논문에서 제안하는 새로운 중계기 선택 기법은 수신자의 복호 확률을 높이면서 동시에 도청자의 복호 확률을 낮출 수 있는 중계기를 쌍으로 선택하여 보안 오류 확률을 개선하였다. Monte-Carlo 기반 컴퓨터 시뮬레이션을 통한 성능 분석 결과에 따르면, 제안 중계기 선택 방식은 기존 중계기 선택 방식 대비 보안 오류 확률을 약 10~50배 개선시킬 수 있음을 확인하였다.

• 한국경영과학회지
• /
• 제10권1호
• /
• pp.79-83
• /
• 1985

This purpose of this study is to suggest a tentative model for project selection of information system. In constructing a mathematical model, quantification of decision criteria is tried to lessen difficulties of measuring benefits of information system project. Suggested model enables us to select projects in the context of portfolio and information system policy.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제13권1호
• /
• pp.73-82
• /
• 2013

In pattern classification, feature selection is an important factor in the performance of classifiers. In particular, when classifying a large number of features or variables, the accuracy and computational time of the classifier can be improved by using the relevant feature subset to remove the irrelevant, redundant, or noisy data. The proposed method consists of two parts: a wrapper part with an improved genetic algorithm(GA) using a new reproduction method and a filter part using mutual information. We also considered feature selection methods based on mutual information(MI) to improve computational complexity. Experimental results show that this method can achieve better performance in pattern recognition problems than other conventional solutions.

• Journal of information and communication convergence engineering
• /
• 제9권2호
• /
• pp.193-196
• /
• 2011

Transmit antenna selection techniques are prominent since they exploit the spatial selectivity at the transmitter side. In the literature, antenna selection techniques assume full knowledge of the channel state information (CSI). In this paper, we consider that the CSI is not perfectly known at the transmitter; however, a quantized version of the channel coefficients is fed back by the users. We employ the non-uniform Lloyd-Max quantization algorithm which takes into consideration the distribution of the channel coefficients. Simulation results show that the degradation in the BER of the system with imperfect CSI at the transmitter is tolerable, especially when the transmit diversity order is high.