• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 2000.04b
• /
• pp.449-457
• /
• 2000

The paper describes the study of global approximate optimization utilizing soft computing techniques such as genetic algorithms (GA's), neural networks (NN's), and fuzzy inference systems(FIS). GA's provide the increasing probability of locating a global optimum over the entire design space associated with multimodality and nonlinearity. NN's can be used as a tool for function approximations, a rapid reanalysis model for subsequent use in design optimization. FIS facilitates to handle the quantitative design information under the case where the training data samples are not sufficiently provided or uncertain information is included in design modeling. Properties of soft computing techniques affect the quality of global approximate model. Evolutionary fuzzy modeling (EFM) and adaptive neuro-fuzzy inference system (ANFIS) are briefly introduced for structural optimization problem in this context. The paper presents the success of EFM depends on how optimally the fuzzy membership parameters are selected and how fuzzy rules are generated.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.8 no.6
• /
• pp.106-118
• /
• 1998

The study concerns a design procedure of rule-based systems. The proposed rule-based fuzzy modeling implements system structure and parameter identification in the efficient from of "IF..., THEN..." statements, and exploits the theory of system optimization and fuzzy implication rules. The method for rule-based fuzzy modeling concerns the from of the conclusion part of the the rules that can be constant. Both triangular and Gaussian-like membership function are studied. The optimization hinges on an autotuning algorithm that covers as a modified constrained optimization method known as a complex method. The study introduces a weighted performance index (objective function) that helps achieve a sound balance between the quality of results produced for the training and testing set. This methodology sheds light on the role and impact of different parameters of the model on its performance. The study is illustrated with the aid of two representative numerical examples.

• Speech Sciences
• /
• v.14 no.1
• /
• pp.151-162
• /
• 2007

This study focuses on the classification of pathological voice using GMM (Gaussian Mixture Model) and compares the results to the previous work which was done by ANN (Artificial Neural Network). Speech data from normal people and patients were collected, then diagnosed and classified into two different categories. Six characteristic parameters (Jitter, Shimmer, NHR, SPI, APQ and RAP) were chosen. Then the classification method based on the artificial neural network and Gaussian mixture method was employed to discriminate the data into normal and pathological speech. The GMM method attained 98.4% average correct classification rate with training data and 95.2% average correct classification rate with test data. The different mixture number (3 to 15) of GMM was used in order to obtain an optimal condition for classification. We also compared the average classification rate based on GMM, ANN and HMM. The proper number of mixtures on Gaussian model needs to be investigated in our future work.

• Journal of the Korean Data and Information Science Society
• /
• v.27 no.2
• /
• pp.549-557
• /
• 2016

In this paper we propose multiclassification method for large data sets by ensembling least squares support vector machines (LS-SVM) with principal components instead of raw input vector. We use the revised one-vs-all method for multiclassification, which is one of voting scheme based on combining several binary classifications. The revised one-vs-all method is performed by using the hat matrix of LS-SVM ensemble, which is obtained by ensembling LS-SVMs trained using each random sample from the whole large training data. The leave-one-out cross validation (CV) function is used for the optimal values of hyper-parameters which affect the performance of multiclass LS-SVM ensemble. We present the generalized cross validation function to reduce computational burden of leave-one-out CV functions. Experimental results from real data sets are then obtained to illustrate the performance of the proposed multiclass LS-SVM ensemble.

• Journal of Electrical Engineering and Technology
• /
• v.2 no.3
• /
• pp.353-357
• /
• 2007

The bearing diagnostics method is presented in this paper using fuzzy inference based on vibration data. Both time-domain and frequency-domain features are used as input data for bearing fault detection. The Adaptive Network based Fuzzy Inference System (ANFIS) and Genetic Algorithm (GA) have been proposed to select the fuzzy model input and output parameters. Training results give the optimized fuzzy inference system for bearing diagnosis based on measured vibration data. The result is also tested with other sets of bearing data to illustrate the reliability of the chosen model.

• Proceedings of the KIPE Conference
• /
• 2000.07a
• /
• pp.620-623
• /
• 2000

A very simple control approach using neural network for the robust position control of a Permanent Magnet Synchronous Motor(PMSM) is presented The linear quadratic controller plus feedforward neural network is employed to obtain the robust PMSM system approximately linearized using field-orientation method for an AC servo. The neural network is trained in on-line phases and this neural network is composed by a fedforward recall and error back-propagation training. Since the total number of nodes are only eight this system can be easily realized by the general microprocessor. During the normal operation the input-output response is sampled and the weighting value is trained multi-times by error back-propagation method at each sample period to accommodate the possible variations in the parameters or load torque. And the state space analysis is performed to obtain the state feedback gains systematically. IN addition the robustness is also obtained without affecting overall system response. This method is realized by a floating-point Digital Singal Processor DS1102 Board (TMS320C31) The basic DSP software is used to write C program which is compiled by using ANSI-C style function prototypes.

• Journal of the Korean Society for Aviation and Aeronautics
• /
• v.26 no.2
• /
• pp.83-90
• /
• 2018

This paper describes a case study on the design factor analysis of vertical wind tunnel for skydiver's training or experiencing of paradropping exercise in the air. The case study of vertical wind tunnel design is to provide the knowledges on effects of parameter's variation when it is applied to overall or partial duct of tunnel circuit. The analysis of design parameters based on pressure loss are produced one by one through the tunnel components from the flight chamber because the wind tunnel must satisfy the requirement of flight chamber such as flow speed, quality and quantity. Results shows the various effects of parameter variation with pressure loss in the wind tunnel circuit. Pressure loss should be based on the determination of fan and power system which can be selected from market or new design.

• Journal of Korean Institute of Industrial Engineers
• /
• v.41 no.1
• /
• pp.10-16
• /
• 2015

In this study, we suggest a method to predict probability distribution of a new customer's degree of loyalty using C-CRF that reflects the RFM score and similarity to the neighbors of the customer. An RFM score prediction model is introduced to construct the first feature function of C-CRF. Integrating demographical similarity, purchasing characteristic similarity and purchase history similarity, we make a unified similarity variable to configure the second feature function of C-CRF. Then parameters of each feature function are estimated and we train our C-CRF model by training data set and suggest a probabilistic distribution to estimate a new customer's degree of loyalty. An example is provided to illustrate our model.

• Steel and Composite Structures
• /
• v.9 no.5
• /
• pp.445-455
• /
• 2009

This study proposes a system identification technique for a fiber-reinforced polymer deck with neural networks. Neural networks are trained for system identification and the identified structure gives training data in return. This process is repeated until the identified parameters converge. Hence, the proposed algorithm is called an iterative neural network scheme. The proposed algorithm also relies on recent developments in the experimental design of the response surface method. The proposed strategy is verified with known systems and applied to a fiber-reinforced polymer bridge deck with experimental data.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1998.06e
• /
• pp.373-376
• /
• 1998

통신 수단의 발달로 휴대단말기의 사용이 증가하고 있으며, 이와 함께 휴대단말기에서의 음성인식에 대한 수요도 증가하고 있다. 휴대단말기의 경우 저 전송율을 가지는 음성 부호화기를 사용하게 되며, 이러한 저전송율의 음성 부호화기에서의 음성인식을 수행할 경우 인식 성능이 저하되는 현상을 보이게 된다. 본 논문에서는 이러한 문제를 해결하기 위하여 LSP 파라메터 기반의 거리척도에 관하여 비교 검토하였으며, 적은 훈련 데이터에서 사용 가능한 화자 종속 음성인식 방법으로 Dynamic Time Warping(DTW)과 변형된 Hidden Markov Model(HMM)에 관하여 검토하였다. QCELP 음성 부호화기에서 인식 어휘 당 2번의 훈련 데이터만을 이용한 화자종속 인식방법을 사용한 결과 95% 이상의 인식 성능을 얻을 수 있었다.