• Journal of Korea Society of Industrial Information Systems
• /
• v.27 no.4
• /
• pp.37-45
• /
• 2022

In this paper, a multi agent-multi task assignment problem, which is a representative problem of combinatorial optimization, is presented. The objective of the problem is to determine the coordinated agent-task assignment that maximizes the sum of the achievement rates of each task. The achievement rate is represented as a concave down increasing function according to the number of agents assigned to the task. The problem is expressed as an NP-hard problem with a non-linear objective function. In this paper, to solve the assignment problem, we propose a hybrid cross-entropy algorithm as an effective and efficient solution methodology. In fact, the general cross-entropy algorithm might have drawbacks (e.g., slow update of parameters and premature convergence) according to problem situations. Compared to the general cross-entropy algorithm, the proposed method is designed to be less likely to have the two drawbacks. We show that the performances of the proposed methods are better than those of the general cross-entropy algorithm through numerical experiments.

• Journal of Korea Society of Industrial Information Systems
• /
• v.28 no.5
• /
• pp.67-75
• /
• 2023

This paper deals with the operation of air taxis, which is one of the latest innovative technologies aimed at solving the issue of traffic congestion in cities. A key challenge for the successful introduction of the technology and efficient operation is a vertiport location problem. This paper employs a discrete choice model to calculate choice probabilities of transportation modes for each route, taking into account factors such as cost and travel time associated with different modes. Based on this probability, a mathematical formulation to maximize the utilization rate for air taxi is proposed. However, the proposed model is NP-hard, effective and efficient solution methodology is required. Compared to previous studies that simply proposed the optimization models, this study presents a solution methodology using the cross-entropy algorithm and confirms the effectiveness and efficiency of the algorith through numerical experiments. In addition to the academic excellence of the algorithm, it suggests that decision-making that considers actual data and air taxi utilization plans can increase the practial usability.

• Journal of the Korean Society for Precision Engineering
• /
• v.21 no.4
• /
• pp.202-209
• /
• 2004

Quality control is essential to the final product in BGA-type PCB fabrication. So, many automatic vision systems have been developed to achieve speedy, low cost and high quality inspection. A multiple threshold selection algorithm is a very important technique for machine vision based inspection. In this paper, an inspected image is modeled by using fuzzy sets and then the parameters of specified membership functions are estimated to be in maximum fuzzy entropy with the probability of the fuzzy sets, using the exhausted search method. Fuzzy c-partitions with the estimated parameters are automatically generated, and then multiple thresholds are selected as the crossover points of the fuzzy sets that form the estimated fuzzy partitions. Several experiments related to flip chip BGA images show that the proposed algorithm outperforms previous ones using both entropy and variance, and also can be successfully applied to AVI systems.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.10 no.5
• /
• pp.57-62
• /
• 2010

Recently, decision tree techniques have been studied in terms of quick searching and extracting of massive data in medical fields. Although many different techniques have been developed such as CART, C4.5 and CHAID which are belong to a pie in Clermont decision tree classification algorithm, those methods can jeopardize remained data by the binary method during procedures. In brief, C4.5 method composes a decision tree by entropy levels. In contrast, CART method does by entropy matrix in categorical or continuous data. Therefore, we compared C4.5 and CART methods which were belong to a same pie using breast cancer data to evaluate their performance respectively. To convince data accuracy, we performed cross-validation of results in this paper.

• Journal of IKEEE
• /
• v.26 no.4
• /
• pp.531-536
• /
• 2022

In order to efficeintly manage a battery, it is important to accurately estimate and manage the SOH(State of Health) and RUL(Remaining Useful Life) of the batteries. Even if the batteries are of the same type, the characteristics such as facility capacity and voltage are different, and when the battery for the training model and the battery for prediction through the model are different, there is a limit to measuring the accuracy. In this paper, We proposed the entropy index using voltage distribution and discharge time is generalized, and four batteries are defined as a training set and a test set alternately one by one to predict the health status of batteries through linear regression analysis of machine learning. The proposed method showed a high accuracy of more than 95% using the MAPE(Mean Absolute Percentage Error).

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1998.08a
• /
• pp.281-286
• /
• 1998

ETRI에서 개발 중인 대화체 음성언어번역 시스템에 대하여 기술한다. 현재, ETRI는 DAM성언어번역 국제 공동 연구콘서시움인 C-STAR에 핵심참가기관으로 참여하여, 한일, 한영음성언어번역 시스템을 개발하고 있으며 1999년 국제 공동시험을 계획하고 이？. 최근의 연구 진행상황을 간추리면, 먼저 음성인식분야에서 유무성음 및 묵음정보를 미리 추출하여 이를 탐색에 활용하였으며, 음향모델 규모의 설정을 위한 교차 엔트로피 기반 변이음 군집화 알고리즘이 구현되었다. 또한 대상어휘의 확장을 위하여 의사형태소의 개념을 도입하였다. 언어번역분야에서는 이전과 같은 개념기반의 번역을 시도하고 있으며, C-STAR 회원기관과 공동으로 중간언어 규격을 정의하고 있다. 음성합성분야에서는 훈련형 합성기를 개발하여 합성데이타베이스 구축기간을 현저하게 줄였다.

• Journal of Digital Convergence
• /
• v.20 no.4
• /
• pp.389-396
• /
• 2022

Deep Learning is based on a perceptron, and is currently being used in various fields such as image recognition, voice recognition, object detection, and drug development. Accordingly, a variety of learning algorithms have been proposed, and the number of neurons constituting a neural network varies greatly among researchers. This study analyzed the learning characteristics according to the number of neurons of the currently used SGD, momentum methods, AdaGrad, RMSProp, and Adam methods. To this end, a neural network was constructed with one input layer, three hidden layers, and one output layer. ReLU was applied to the activation function, cross entropy error (CEE) was applied to the loss function, and MNIST was used for the experimental dataset. As a result, it was concluded that the number of neurons 100-300, the algorithm Adam, and the number of learning (iteraction) 200 would be the most efficient in deep learning learning. This study will provide implications for the algorithm to be developed and the reference value of the number of neurons given new learning data in the future.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.2
• /
• pp.189-194
• /
• 2020

This paper analyzes the gradient descent method, which is the one most used for learning neural networks. Learning means updating a parameter so the loss function is at its minimum. The loss function quantifies the difference between actual and predicted values. The gradient descent method uses the slope of the loss function to update the parameter to minimize error, and is currently used in libraries that provide the best deep learning algorithms. However, these algorithms are provided in the form of a black box, making it difficult to identify the advantages and disadvantages of various gradient descent methods. This paper analyzes the characteristics of the stochastic gradient descent method, the momentum method, the AdaGrad method, and the Adadelta method, which are currently used gradient descent methods. The experimental data used a modified National Institute of Standards and Technology (MNIST) data set that is widely used to verify neural networks. The hidden layer consists of two layers: the first with 500 neurons, and the second with 300. The activation function of the output layer is the softmax function, and the rectified linear unit function is used for the remaining input and hidden layers. The loss function uses cross-entropy error.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.10 no.6
• /
• pp.683-690
• /
• 2015

In Rough set, attribute missing values have several problems such as reduct and core estimation. Further, they do not give some discernable pattern for decision tree construction. Now, there are several methods such as substitutions of typical attribute values, assignment of every possible value, event covering, C4.5 and special LEMS algorithm. However, they are mainly substitutions into frequently appearing values or common attribute ones. Thus, decision rules with high information loss are derived in case that important attribute values are missing in pattern matching. In particular, there is difficult to implement cross validation of the decision rules. In this paper we suggest new method for substituting the missing attribute values into high information gain by using entropy variation among given attributes, and thereby completing the information table. The suggested method is validated by conducting the same rough set analysis on the incomplete information system using the software ROSE.