• Proceedings of the Korea Information Processing Society Conference
• /
• 2008.11a
• /
• pp.27-29
• /
• 2008

시스템 분석에 주로 사용하는 자료 중에는 비선형 자료와 시계열 등이 있다. 이들 자료는 그 함축적인 관계가 매우 복잡하여 전통적인 통계분석 도구로 분석하는데 어려움이 많다. 본 연구에서는 현실 세계에서 다양하게 나타나는 복잡성을 다루기 위하여 하이브리드 진화 신경망 모델링 접근 방법으로 자료를 모형화 하고 이를 통한 학습의 적합도를 살펴본다. 비선형 자료 등을 모형화하기 위한 학습은 역전파 신경망 기법을 이용한다. 학습의 효율을 높이기 의해서 격자감소 학습 알고리즘과 함께 이용하는 유전자 알고리즘은 네트워크 구조를 최적화 시킬 수 있는 초기가중값을 이용한 전역 최소값을 찾는데 이용한다. 학습 결과를 통해 제안된 하이브리드형 접근방법의 학습이 보다 효율적임을 살펴보기 위하여 유전자 알고리즘으로 최적화된 신경망 학습 알고리즘을 비선형 모의자료의 학습에 적용하여 보았다.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2007.11a
• /
• pp.23-27
• /
• 2007

Many trials have been used to model room impulse responses, all attempting to provide efficient representations of room acoustics. The traditional model designs for room impulse response seem to fail in accuracy, controllability, or computational efficiency. In time domain, a room impulse response is generally considered as the combination of three parts having different acoustic characteristics, initial time delay, early reflection, and late reverberation. This paper introduces new learning hybrid model for the room impulse response. In this proposed model, those three parts are modeled using different models with learning algorithms that determine the length or boundary of each model in the hybrid model. By the simulation with measured room impulse responses, it was examined that the performance of proposed model shows the best efficiency in views of both the parameter numbers and modeling error.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.9 no.5
• /
• pp.555-565
• /
• 1999

The optimal identification algorithm of fuzzy systems is presented for rule-based fuzzy modeling of nonlinear complex systems. Nonlinear systems are expressed using the identification of structure such as input variables and fuzzy input subspaces, and parameters of a fuzzy model. In this paper, the rule-based fuzzy modeling implements system structure and parameter identification using the fuzzy inference methods and hybrid structure combined with two types of optimization theories for nonlinear systems. Two types of inference methods of a fuzzy model are the simplified inference and linear inference. The proposed hybrid optimal identification algorithm is carried out using both a genetic algorithm and the improved complex method. Here, a genetic algorithm is utilized for determining initial parameters of membership function of premise fuzzy rules, and the improved complex method which is a powerful auto-tuning algorithm is carried out to obtain fine parameters of membership function. Accordingly, in order to optimize fuzzy model, we use the optimal algorithm with a hybrid type for the identification of premise parameters and standard least square method for the identification of consequence parameters of a fuzzy model. Also, an aggregate performance index with weighting factor is proposed to achieve a balance between performance results of fuzzy model produced for the training and testing data. Two numerical examples are used to evaluate the performance of the proposed model.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.36C no.6
• /
• pp.44-51
• /
• 1999

The HMM-Net is a neural network architecture that implements the computation of output probabilities of a hidden Markov model (HMM). The architecture is developed for the purpose of combining the discriminant power of neural networks with the time-domain modeling capability of HMMs. Criteria of maximum likehood(ML) and minimization of mean squared error(MMSE) are used for learning HMM-Net classifiers. The criterion MMSE is better than ML when initial learning condition is well established. However Ml is more useful one when the condition is incomplete[3]. Therefore we propose an efficient learning method of HMM-Net classifiers using a hybrid criterion(ML/MMSE). In the method, we begin a learning with ML in order to get a stable start-point. After then, we continue the learning with MMSE to search an optimal or near-optimal solution. Experimental results for the isolated numeric digits from /0/ to /9/, a training and testing time-series pattern set, show that the performance of the proposed method is better than the others in the respects of learning and recognition rates.

• Journal of Energy Engineering
• /
• v.21 no.1
• /
• pp.33-42
• /
• 2012

In this study, long-term greenhouse gas reductions expected passenger sector was used for the MESSAGE. Green Car road map proposed BAU scenario, Enhanced diffusion green car scenario, and price 1, 2 scenarios was configured with four scenarios. Enhanced diffusion green car in the scenario, in 2050 compared to BAU scenario 13% of the emissions will decrease. Price 1 and Price 2 scenario is emissions reduction of 14% compared to BAU. This study consists of six chapters. Introduction of MESSAGE, creation and RES in the year and the target year set a different base line and the passenger building materials sector activities, steps for passenger sector scenario and Based on the results of running the emissions reductions were to describe.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.48 no.10
• /
• pp.773-782
• /
• 2020

The development of joint FE models for deep learning neural network (DLNN)-based hybrid FEA is presented. Material models of bolts and bearings in the front axle of tractor, showing complex behavior induced by various tightening conditions, were replaced with DLNN models. Bolts are modeled as one-dimensional Timoshenko beam elements with six degrees of freedom, and bearings as three-dimensional solid elements. Stress-strain data were extracted from all elements after finite element analysis subjected to various load conditions, and DLNN for bolts and bearing were trained with Tensorflow. The DLNN-based joint models were implemented in the ABAQUS user subroutines where stresses from the next increment are updated and the algorithmic tangent stiffness matrix is calculated. Generalization of the trained DLNN in the FE model was verified by subjecting it to a new loading condition. Finally, the DLNN-based FEA for the front axle of the tractor was conducted and the feasibility was verified by comparing with results of a static structural experiment of the actual tractor.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.48 no.10
• /
• pp.1293-1302
• /
• 1999

In this paper, an on-line process scheme is presented for implementation of a intelligent on-line modeling of nonlinear complex system. The proposed on-line process scheme is composed of FNN-based model algorithm and PLC-based simulator, Here, an adaptive fuzzy-neural networks and HCM(Hard C-Means) clustering method are used as an intelligent identification algorithm for on-line modeling. The adaptive fuzzy-neural networks consists of two distinct modifiable sturctures such as the premise and the consequence part. The parameters of two structures are adapted by a combined hybrid learning algorithm of gradient decent method and least square method. Also we design an interface S/W between PLC(Proguammable Logic Controller) and main PC computer, and construct a monitoring and control simulator for real process system. Accordingly the on-line identification algorithm and interface S/W are used to obtain the on-line FNN model structure and to accomplish the on-line modeling. And using some I/O data gathered partly in the field(plant), computer simulation is carried out to evaluate the performance of FNN model structure generated by the on-line identification algorithm. This simulation results show that the proposed technique can produce the optimal fuzzy model with higher accuracy and feasibility than other works achieved previously.

• Journal of Internet Computing and Services
• /
• v.23 no.4
• /
• pp.21-33
• /
• 2022

Recently, the recommender system has been widely used in various fields such as movies, music, online shopping, and social media, and in the meantime, the recommender model has been developed from correlation analysis through the Apriori model, which can be said to be the first-generation model in the recommender system field. In 2005, many models have been proposed, including deep learning-based models, which are receiving a lot of attention within the recommender model. The recommender model can be classified into a collaborative filtering method, a content-based method, and a hybrid method that uses these two methods integrally. However, these basic methods are gradually losing their status as methodologies in the field as they fail to adapt to internal and external changing factors such as the rapidly changing user-item interaction and the development of big data. On the other hand, the importance of deep learning methodologies in recommender systems is increasing because of its advantages such as nonlinear transformation, representation learning, sequence modeling, and flexibility. In this paper, among deep learning methodologies, RNN, CNN, and GAN-based models suitable for sequential modeling that can accurately and flexibly analyze user-item interactions are classified, compared, and analyzed.

• Geophysics and Geophysical Exploration
• /
• v.25 no.1
• /
• pp.26-37
• /
• 2022

Recently, multiple methods using small aircraft for geophysical exploration have been suggested as a result of the development of information and communication technology. In this study, we introduce the hybrid unmanned aircraft electromagnetic system of the Korea Institute of Geosciences and Mineral resources, which is under development. Additionally, data processing and interpretation methods are suggested via the analysis of datasets obtained using the system under development to verify the system. Because the system uses a three-component receiver hanging from a drone, the effects of rotation on the obtained data are significant and were therefore corrected using a rotation matrix. During the survey, the heights of the source and the receiver and their offsets vary in real time and the measured data are contaminated with noise. The noise makes it difficult to interpret the data using the conventional method. Therefore, we developed a recurrent neural network (RNN) model to enable rapid predictions of the apparent resistivity using magnetic field data. Field data noise is included in the training datasets of the RNN model to improve its performance on noise-contaminated field data. Compared with the results of the electrical resistivity survey, the trained RNN model predicted similar apparent resistivities for the test field dataset.