• 전자공학회논문지B
• /
• 제31B권4호
• /
• pp.18-29
• /
• 1994

For the efficient recognition of Korean Alphabets, we proposed the tree structure algorithm which was based on K-tuple NRF-SDF using representative images as training images. Representative images consisted of ECP-SDF images of several consonants or vowels. To reduce the effect of sidelobe in the output correlation plane, we used the representative images as training images and obtained the elements of a vector inner product matrix using the peak value of AMPOF correlation of training images with one another. The proposed algorithm consisted of three main-step containing several substeps. In filter synthesis of each step, representative images were used as training images in the first and the second main-step and each consonant or vowel was used as training images in the third main-step. The performance of this algorithm is demonstrated by computer simulation and optical experiment.

• Journal of Information Processing Systems
• /
• 제14권5호
• /
• pp.1075-1086
• /
• 2018

In this paper a cross-validation algorithm for training probabilistic neural networks (PNNs) is presented in order to be applied to automatic face identification. Actually, standard PNNs perform pretty well for small and medium sized databases but they suffer from serious problems when it comes to using them with large databases like those encountered in biometrics applications. To address this issue, we proposed in this work a new training algorithm for PNNs to reduce the hidden layer's size and avoid over-fitting at the same time. The proposed training algorithm generates networks with a smaller hidden layer which contains only representative examples in the training data set. Moreover, adding new classes or samples after training does not require retraining, which is one of the main characteristics of this solution. Results presented in this work show a great improvement both in the processing speed and generalization of the proposed classifier. This improvement is mainly caused by reducing significantly the size of the hidden layer.

• 음성과학
• /
• 제11권4호
• /
• pp.43-52
• /
• 2004

Model parameters in HMM based speech recognition systems are normally estimated using Maximum Likelihood Estimation(MLE). The MLE method is based mainly on the principle of statistical data fitting in terms of increasing the HMM likelihood. The optimality of this training criterion is conditioned on the availability of infinite amount of training data and the correct choice of model. However, in practice, neither of these conditions is satisfied. In this paper, we propose a training algorithm, MCE(Minimum Classification Error), to improve the performance of a speech recognizer detecting mispronunciation of a foreign language. During the conventional MLE(Maximum Likelihood Estimation) training, the model parameters are adjusted to increase the likelihood of the word strings corresponding to the training utterances without taking account of the probability of other possible word strings. In contrast to MLE, the MCE training scheme takes account of possible competing word hypotheses and tries to reduce the probability of incorrect hypotheses. The discriminant training method using MCE shows better recognition results than the MLE method does.

• Journal of Welding and Joining
• /
• 제31권5호
• /
• pp.35-40
• /
• 2013

In this paper, we propose the Tangible Virtual Reality Representation Method to using haptic device and feature to morphology of created bead from Flux Cored Arc Welding. The virtual reality was started to rising for reduce to consumable materials and welding training risk. And, we will expected maximize virtual reality from virtual welding training. In this paper proposed method is get the database to changing the input factor such as work angle, travelling angle, speed, CTWD. And, it is visualization to bead from extract to optimal morphological feature information to using the Neural Network algorithm. The database was building without error to extract data from automatic robot welder. Also, the Neural Network algorithm was set a dataset of the highest accuracy from verification process in many times. The bead was created in virtual reality from extract to morphological feature information. We were implementation to final shape of bead and overlapped in process by time to using bead generation algorithm and calibration algorithm for generate to same bead shape to real database in process of generating bead. The best advantage of virtual welding training, it can be get the many data to training evaluation. In this paper, we were representation bead to similar shape from generated bead to Flux Cored Arc Welding. Therefore, we were reduce the gap to virtual welding training and real welding training. In addition, we were confirmed be able to maximize the performance of education from more effective evaluation system.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 1998년도 가을 학술발표논문집 Vol.25 No.2 (2)
• /
• pp.360-362
• /
• 1998

In the original mixtures of experts framework, the parameters of the network are determined by gradient descent, which is naturally slow. In [2], the Expectation-Maximization(EM) algorithm is used instead, to obtain the network parameters, resulting in substantially reduced training times. This paper presents the new EM algorithm for prediction. We show that an Efficient training algorithm may be derived for the HME network. To verify the utility of the algorithm we look at specific examples in time series prediction. The application of the new EM algorithm to time series prediction has been quiet successful.

• 한국구조물진단유지관리공학회 논문집
• /
• 제6권4호
• /
• pp.169-179
• /
• 2002

This paper presents an efficient algorithm for the estimation of damage location and severity in structure using Probabilistic Neural Network (PNN). Artificial neural network has been being used for damage assessment by many researchers, but there are still some barriers that must be overcome to improve its accuracy and efficiency. The major problems with the conventional neural network are the necessity of many training data for neural network learning and ambiguity in the relation of neural network architecture with convergence of solution. In this paper, PNN is used as a pattern classifier to overcome those problems in the conventional neural network. The basic idea of damage assessment algorithm proposed in this paper is that modal characteristics from a damaged structure are compared with the training patterns which represent the damage in specific element to determine how close it is to training patterns in terms of the probability from PNN. The training pattern that gives a maximum probability implies that the element used in producing the training pattern is considered as a damaged one. The proposed damage assessment algorithm using PNN is applied to a 2-span continuous beam model structure to verify the algorithm.

• 한국농공학회:학술대회논문집
• /
• 한국농공학회 2001년도 학술발표회 발표논문집
• /
• pp.59-64
• /
• 2001

The objectives of the thesis are to propose a pattern classification method for remote sensing data using artificial neural network. First, we apply the error back propagation algorithm to classify the remote sensing data. In this case, the classification performance depends on a training data set. Using the training data set and the error back propagation algorithm, a layered neural network is trained such that the training pattern are classified with a specified accuracy. After training the neural network, some pixels are deleted from the original training data set if they are incorrectly classified and a new training data set is built up. Once training is complete, a testing data set is classified by using the trained neural network. The classification results of Landsat TM data show that this approach produces excellent results which are more realistic and noiseless compared with a conventional Bayesian method.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2009년도 IWAIT
• /
• pp.355-359
• /
• 2009

In this paper, we describe self-training super-resolution. Our approach is based on example based algorithms. Example based algorithms need training images, and selection of those changes the result of the algorithm. Consequently it is important to choose training images. We propose self-training based super-resolution algorithm which use an input image itself as a training image. It seems like other example based super-resolution methods, but we consider training phase as the step to collect primitive information of the input image. And some artifacts along the edge are visible in applying example based algorithms. We reduce those artifacts giving weights in consideration of the edge direction. We demonstrate the performance of our approach is reasonable several synthetic images and real images.

• 한국멀티미디어학회논문지
• /
• 제23권8호
• /
• pp.1075-1087
• /
• 2020

Aviation ICT technology is a convergence technology between aviation and electronics, and has a wide variety of applications, including navigation and education. Among them, in the field of aerial pilot training, there are many problems such as the possibility of accidents during training and the lack of coping skills for various situations. This raises the need for a simulated pilot training system similar to actual training. In this paper, pilot training data were collected in pilot training system using VR/AR to increase immersion in flight training, and Customized Pilot Training Platform with Collaborative Deep Learning in VR/AR Environment that can recommend effective training courses to pilots is proposed. To verify the accuracy of the recommendation, the performance of the proposed collaborative deep learning algorithm with the existing recommendation algorithm was evaluated, and the flight test score was measured based on the pilot's training data base, and the deviations of each result were compared. The proposed service platform can expect more reliable recommendation results than previous studies, and the user survey for verification showed high satisfaction.

• 전기학회논문지
• /
• 제59권3호
• /
• pp.492-498
• /
• 2010

Since it is almost impossible to train the dispatchers with real power system, the dispatcher training simulator(DTS) is used for the training. Among various components of the DTS, the power system model(PSM) emulates the dynamic behavior of the power system to calculate the frequency and voltage. The frequency is calculated from various parameters such as mechanical power of power plants, load, inertia, and the damping of the power system. In the PSM, the power plants are modeled as differential equations, so the mechanical power of the power plants are calculated by the numerical methods. Conventionally, the fixed step-size algorithm has been used in the PSM, however it has some drawbacks. This paper develops the prototype PSM using the Matlab, and analyzes the problems of the fixed step-size algorithm by comparing the results with those of PSCAD simulation. In order to overcome the limitations, this paper proposes a modified frequency calculation method using the adaptive step-size algorithm. From the simulation using the proposed method, it is verified that the accuracy of frequency calculation increases substantially while the simulation time is not greatly increased.