• Proceedings of the Korean Society of Near Infrared Spectroscopy Conference
• /
• 2001.06a
• /
• pp.1042-1042
• /
• 2001

In linear discriminant analysis there are two important properties concerning the effectiveness of discriminant function modeling. The first is the separability of the discriminant function for different classes. The separability reaches its optimum by maximizing the ratio of between-class to within-class variance. The second is the stability of the discriminant function against noises present in the measurement variables. One can optimize the stability by exploring the discriminant variates in a principal variation subspace, i. e., the directions that account for a majority of the total variation of the data. An unstable discriminant function will exhibit inflated variance in the prediction of future unclassified objects, exposed to a significantly increased risk of erroneous prediction. Therefore, an ideal discriminant function should not only separate different classes with a minimum misclassification rate for the training set, but also possess a good stability such that the prediction variance for unclassified objects can be as small as possible. In other words, an optimal classifier should find a balance between the separability and the stability. This is of special significance for multivariate spectroscopy-based classification where multicollinearity always leads to discriminant directions located in low-spread subspaces. A new regularized discriminant analysis technique, the principal discriminant variate (PDV) method, has been developed for handling effectively multicollinear data commonly encountered in multivariate spectroscopy-based classification. The motivation behind this method is to seek a sequence of discriminant directions that not only optimize the separability between different classes, but also account for a maximized variation present in the data. Three different formulations for the PDV methods are suggested, and an effective computing procedure is proposed for a PDV method. Near-infrared (NIR) spectra of blood plasma samples from daily monitoring of two Japanese cows have been used to evaluate the behavior of the PDV method in comparison with principal component analysis (PCA), discriminant partial least squares (DPLS), soft independent modeling of class analogies (SIMCA) and Fisher linear discriminant analysis (FLDA). Results obtained demonstrate that the PDV method exhibits improved stability in prediction without significant loss of separability. The NIR spectra of blood plasma samples from two cows are clearly discriminated between by the PDV method. Moreover, the proposed method provides superior performance to PCA, DPLS, SIMCA md FLDA, indicating that PDV is a promising tool in discriminant analysis of spectra-characterized samples with only small compositional difference.

• Journal of Institute of Control, Robotics and Systems
• /
• v.19 no.6
• /
• pp.527-533
• /
• 2013

BCI (Brain-Computer Interface) is a system that transforms a subject's brain signal related to their intention into a control signal by classifying EEG (electroencephalograph) signals obtained during the imagination of movement of a subject's limbs. The BCI system allows us to control machines such as robot arms or wheelchairs only by imaging limbs. With the exact same experiment environment, activated brain regions of each subjects are totally different. In that case, a simple approach is to use as many channels as possible when measuring brain signals. However the problem is that using many channels also causes other problems. When applying a CSP (Common Spatial Pattern), which is an EEG extraction method, many channels cause an overfitting problem, and in addition there is difficulty using this technique for medical analysis. To overcome these problems, we suggest an optimal channel selection method using a BPSO (Binary Particle Swarm Optimization), BPSO with channel impact factor, and GA. This paper examined optimal selected channels among all channels using three optimization methods and compared the classification accuracy and the number of selected channels between BPSO, BPSO with channel impact factor, and GA by SVM (Support Vector Machine). The result showed that BPSO with channel impact factor selected 2 fewer channels and even improved accuracy by 10.17~11.34% compared with BPSO and GA.

• Journal of the Korean Society of Industry Convergence
• /
• v.26 no.6_3
• /
• pp.1279-1288
• /
• 2023

Recently, domestic leisure boats have been actively researching eco-friendly product development to enter the global market. Since the hulls of existing leisure boats are mainly made of fiber reinforced plastic (FRP) or aluminum, design techniques for securing structural safety by applying related materials have been mainly studied. In this study, an initial structural design safety assessment of a trimaran pontoon leisure boat with a modular hull structure and eco-friendly high-density polyethylene (HDPE) material was conducted, and sensitivity evaluation and optimization analysis for lightweight design were performed. The initial structural design safety assessment was carried out by creating a finite element analysis model and applying the loading conditions specified in the ship classification regulation to check whether the specified allowable stresses are satisfied. For the sensitivity evaluation, the influence of stress and weight of each hull structural member was evaluated using the orthogonal array design of experiments method, and an approximate model based on the response surface method was generated using the results of the design of experiments. The optimization analysis set the thickness of the hull structural members as the design variable and considered the optimal design formulation to minimize the weight while satisfying the allowable stress. The algorithm of the optimization analysis applied the Gradient-population Based Optimizer (GBO) to improve the accuracy of the optimal solution convergence while reducing the numerical cost. Through this study, the optimal design of a newly developed eco-friendly trimaran pontoon leisure boat with a weight reduction of 10% was presented.

• Smart Media Journal
• /
• v.12 no.11
• /
• pp.113-124
• /
• 2023

With the advent of 5G and B5G (Beyond 5G) networks, network virtualization technology that can overcome the limitations of existing networks is attracting attention. The purpose of network virtualization is to provide solutions for efficient network resource utilization and various services. Existing heuristic-based VNE (Virtual Network Embedding) techniques have been studied, but the flexibility is limited. Therefore, in this paper, we propose a GNN-based network slicing classification scheme to meet various service requirements and a RL-based VNE scheme for optimal resource allocation. The proposed method performs optimal VNE using an Actor-Critic network. Finally, to evaluate the performance of the proposed technique, we compare it with Node Rank, MCST-VNE, and GCN-VNE techniques. Through performance analysis, it was shown that the GNN and RL-based VNE techniques are better than the existing techniques in terms of acceptance rate and resource efficiency.

• Journal of the Korea Convergence Society
• /
• v.9 no.2
• /
• pp.13-18
• /
• 2018

This paper is based on a simple approach that the most efficient learning of a multi-layered network is the process of finding the optimal set of weight vectors. To overcome the disadvantages of general learning problems, the proposed model uses a combination of features of EBP and OVSSA. In other words, the proposed method can construct a single model by taking advantage of each algorithm so that it can escape to the probability theory of OVSSA in order to reinforce the property that EBP falls into local minimum value. In the proposed algorithm, methods for reducing errors in EBP are used as energy functions and the energy is minimized to OVSSA. A simple experimental result confirms that two algorithms with different properties can be combined.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.28B no.10
• /
• pp.831-841
• /
• 1991

A combined model of probabilistic and MLP(multi layer perceptron) model is proposed for the pattern classification of EMG( electromyogram) signals. The MLP model has a problem of not guaranteeing the global minima of error and different quality of approximations to Bayesian probabilities. The probabilistic model is, however, closely related to the estimation error of model parameters and the fidelity of assumptions. A proper combination of these will reduce the effects of the problems and be robust to input variations. Proposed model is able to get the MAP(maximum a posteriori probability) in the probabilistic model by estimating a priori probability distribution using the MLP model adaptively. This method minimize the error probability of the probabilistic model as long as the realization of the MLP model is optimal, and this is a good combination of the probabilistic model and the MLP model for the usage of MLP model reliability. Simulation results show the benefit of the proposed model compared to use the Mlp and the probabilistic model seperately and the average calculation time fro classification is about 50ms in the case of combined motion using an IBM PC 25 MHz 386model.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2006.05a
• /
• pp.784-787
• /
• 2006

In this paper, we propose a method for nonlinear grapheme segmentation in Korean printed character type classification. The characters are subdivided into six types based on character type information. The feature vector is consist of mesh features, vertical projection features and horizontal projection features which are extracted from gray-level images. We classify characters into 6 types using Back propagation. Character segmentation regions are determined based on character type information. Then, an optimal nonlinear grapheme segmentation path is found using multi-stage graph search algorithm. As the result, a proposed methodology is proper to classify character type and to find nonlinear char segmentation paths.

• ETRI Journal
• /
• v.41 no.3
• /
• pp.358-370
• /
• 2019

The main aim of this study is to select the optimal set of genes from microarray cancer datasets that contribute to the prediction of specific cancer types. This study proposes the enhancement of the feature selection filter algorithm based on Joe's normalized mutual information and its use for gene selection. The proposed algorithm is implemented and evaluated on seven benchmark microarray cancer datasets, namely, central nervous system, leukemia (binary), leukemia (3 class), leukemia (4 class), lymphoma, mixed lineage leukemia, and small round blue cell tumor, using five well-known classifiers, including the naive Bayes, radial basis function network, instance-based classifier, decision-based table, and decision tree. An average increase in the prediction accuracy of 5.1% is observed on all seven datasets averaged over all five classifiers. The average reduction in training time is 2.86 seconds. The performance of the proposed method is also compared with those of three other popular mutual information-based feature selection filters, namely, information gain, gain ratio, and symmetric uncertainty. The results are impressive when all five classifiers are used on all the datasets.

• Journal of radiological science and technology
• /
• v.45 no.4
• /
• pp.341-346
• /
• 2022

The color overlay pattern of thyroid shear wave elastography applied in this study distinguishes benign and malignant nodules based on the optimal cut-off value of 74.2 kPa. From august 2021 to september 2021, thyroid ultrasound and elastography were performed on 57 patients with thyroid lesions using an ultrasound device RS85 prestige (Samsung Medison, Korea) and a 2-14 MHz linear transducer. In addition, the results of classification by K-TIRADS for each thyroid nodule and the results of classification by color overlay pattern according to the kPa value of acoustic ultrasound were compared and analyzed. In the color overlay pattern, the results classified as 40 people from dark blue to light blue and 17 people from green to red were similar to the K-TIRADS category results, which were classified as 42 benign and 15 malignant. Between blue and light blue, benign, and between green and red, malignant. If the shear wave elastography method is applied before the fine-needle aspiration cytology of the thyroid nodule is performed, the differential diagnosis of thyroid tissue from benign and malignant can be predicted in advance, and it will help to reduce unnecessary invasive tests.

• Transactions of the Korean Society of Pressure Vessels and Piping
• /
• v.18 no.2
• /
• pp.69-76
• /
• 2022

In order to prepare for a future nuclear market, research for developing floating small modular reactor has been initiated with the aim of differentiating it from large nuclear power plants such as distributed power, heat supply to remote communities and sea water desalination. Depending on the characteristics of the small modular reactor, it is necessary to design a plate and shell heat exchanger that can be manufactured smaller than the U-tube recirculation method. In this study, 12 cases are selected by changing the diameter of the heat plate, the thickness of the device body and the size of the stiffener. Finite element analysis is performed by setting the stress classification lines for the point at which deformation is expected under external pressure conditions for these analysis cases. For the basic design of the plate and shell heat exchanger, the optimal conditions are derived by analyzing the tendency of stress change in the device body and stiffener.