• Journal of KIISE
• /
• v.43 no.6
• /
• pp.686-691
• /
• 2016

In this paper, we introduced the adaptive spectral co-clustering, a spectral clustering for multiview data, especially data with more than three views. In the adaptive spectral co-clustering, the performance is improved by sharing information from diverse views. For the efficiency in information sharing, a co-training approach is adopted. In the co-training step, a set of parameters are estimated to make all views in data maximally independent, and then, information is shared with respect to estimated parameters. This co-training step increases the efficiency of information sharing comparing with ordinary feature concatenation and co-training methods that assume the independence among views. The adaptive spectral co-clustering was evaluated with synthetic dataset and multi lingual document dataset. The experimental results indicated the efficiency of the adaptive spectral co-clustering with the performances in every iterations and similarity matrix generated with information sharing.

• Asian Pacific Journal of Cancer Prevention
• /
• v.16 no.2
• /
• pp.753-756
• /
• 2015

Background: Red cell distribution width (RDW) is one of the standard parameters with blood cell counts. Much previous research has indicated that it increases in cases of systemic inflammation or cardiametabolic incident. However, information on the relation of RDW with solid tumors causing systemic inflammation is limited. In the present research, we examined the relation of RDW with malignant and benign lesions of the colon. Materials and Methods: 115 patients with colon polyps (group 1), and 30 with colon cancer (group 2) who were diagnosed histopathologically in our clinic between January 2010-January 2013 were scanned retrospectively. Patients with anemia, hematologic diseases and active inflammation were excluded. RDW, mean corpuscular volume (MCV), hemoglobin (Hgb) and platelet (Plt) measurements were recorded and their relations with the malignant and benign lesions of the colon were examined. Results: Both groups were similar in age and gender distribution. RDW values of patients with colon cancer were significantly higher than the patients with colon polyp (p=0,01). No significant differences were detected between the two groups in terms of MCV and Plt values (p>0,05). Conclusions: RDW can be used as an early warning biomarker for solid colon tumors. Further prospective research is required on the relations of cheap and easily measured RDW parameters with colon malignancies.

• Korean Journal of Remote Sensing
• /
• v.15 no.1
• /
• pp.39-50
• /
• 1999

It is complicate and time-consuming process to classify a multi-band satellite imagery according to the application. In addition, classification rate sensitively depends on the selection of training data set and features in a supervised classification process. This paper introduced a classification network adopting a fuzzy-based $\gamma$-model in order to select a training data set and to extract feature which highly contribute to an actual classification. The features used in the classification were gray-level histogram, textures, and NDVI(Normalized Difference Vegetation Index) of target imagery. Moreover, in order to minimize the errors in the classification network, the Gradient Descent method was used in the training process for the $\gamma$-parameters at each code used. The trained parameters made it possible to know the connectivity of each node and to delete the void features from all the possible input features.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.15 no.5
• /
• pp.380-386
• /
• 2022

This paper proposes a method for structuring the preprocessing process of a training image when color is applied using Pix2Pix, one of the adversarial generative neural network techniques. This paper concentrate on the prediction result can be damaged according to the degree of light reflection of the training image. Therefore, image preprocesisng and parameters for model optimization were configured before model application. In order to increase the image resolution of training and prediction results, it is necessary to modify the of the model so this part is designed to be tuned with parameters. In addition, in this paper, the logic that processes only the part where the prediction result is damaged by light reflection is configured together, and the pre-processing logic that does not distort the prediction result is also configured.Therefore, in order to improve the usability, the accuracy was improved through experiments on the part that applies the light reflection tuning filter to the training image of the Pix2Pix model and the parameter configuration.

• Journal of the Semiconductor & Display Technology
• /
• v.22 no.1
• /
• pp.11-17
• /
• 2023

This paper proposes a lightweight deep learning network for detecting an image splicing forgery. The research on image forgery detection using CNN, a deep learning network, and research on detecting and localizing forgery in pixel units are in progress. Among them, CAT-Net, which learns the discrete cosine transform coefficients of images together with images, was released in 2022. The DCT coefficients presented by CAT-Net are combined with the JPEG artifact learning module and the backbone model as pre-learning, and the weights are fixed. The dataset used for pre-training is not included in the public dataset, and the backbone model has a relatively large number of network parameters, which causes overfitting in a small dataset, hindering generalization performance. In this paper, this learning module is designed to learn the characterization depending on the DCT domain in real-time during network training without pre-training. The DCT RRU-Net proposed in this paper is a network that combines RRU-Net which detects forgery by learning only images and JPEG artifact learning module. It is confirmed that the network parameters are less than those of CAT-Net, the detection performance of forgery is better than that of RRU-Net, and the generalization performance for various datasets improves through the network architecture and training method of DCT RRU-Net.

• Journal of Intelligence and Information Systems
• /
• v.17 no.4
• /
• pp.241-254
• /
• 2011

Financial time-series forecasting is one of the most important issues because it is essential for the risk management of financial institutions. Therefore, researchers have tried to forecast financial time-series using various data mining techniques such as regression, artificial neural networks, decision trees, k-nearest neighbor etc. Recently, support vector machines (SVMs) are popularly applied to this research area because they have advantages that they don't require huge training data and have low possibility of overfitting. However, a user must determine several design factors by heuristics in order to use SVM. For example, the selection of appropriate kernel function and its parameters and proper feature subset selection are major design factors of SVM. Other than these factors, the proper selection of instance subset may also improve the forecasting performance of SVM by eliminating irrelevant and distorting training instances. Nonetheless, there have been few studies that have applied instance selection to SVM, especially in the domain of stock market prediction. Instance selection tries to choose proper instance subsets from original training data. It may be considered as a method of knowledge refinement and it maintains the instance-base. This study proposes the novel instance selection algorithm for SVMs. The proposed technique in this study uses genetic algorithm (GA) to optimize instance selection process with parameter optimization simultaneously. We call the model as ISVM (SVM with Instance selection) in this study. Experiments on stock market data are implemented using ISVM. In this study, the GA searches for optimal or near-optimal values of kernel parameters and relevant instances for SVMs. This study needs two sets of parameters in chromosomes in GA setting : The codes for kernel parameters and for instance selection. For the controlling parameters of the GA search, the population size is set at 50 organisms and the value of the crossover rate is set at 0.7 while the mutation rate is 0.1. As the stopping condition, 50 generations are permitted. The application data used in this study consists of technical indicators and the direction of change in the daily Korea stock price index (KOSPI). The total number of samples is 2218 trading days. We separate the whole data into three subsets as training, test, hold-out data set. The number of data in each subset is 1056, 581, 581 respectively. This study compares ISVM to several comparative models including logistic regression (logit), backpropagation neural networks (ANN), nearest neighbor (1-NN), conventional SVM (SVM) and SVM with the optimized parameters (PSVM). In especial, PSVM uses optimized kernel parameters by the genetic algorithm. The experimental results show that ISVM outperforms 1-NN by 15.32%, ANN by 6.89%, Logit and SVM by 5.34%, and PSVM by 4.82% for the holdout data. For ISVM, only 556 data from 1056 original training data are used to produce the result. In addition, the two-sample test for proportions is used to examine whether ISVM significantly outperforms other comparative models. The results indicate that ISVM outperforms ANN and 1-NN at the 1% statistical significance level. In addition, ISVM performs better than Logit, SVM and PSVM at the 5% statistical significance level.

• Proceedings of the KIEE Conference
• /
• 1998.07g
• /
• pp.2203-2205
• /
• 1998

This paper describes fuzzy radial basis function networks(FRBFN) extracting fuzzy rules through the learning from training data set. The proposed FRBFN is derived from the functional equivalence between RBF networks and fuzzy inference systems. The FRBFN learn by assigning new fuzzy rules and updating the parameters of existing fuzzy rules. The parameters of the FRBFN are adjusted using the standard LMS algorithm. The performance of the FRBFN is illustrated with function approximation and system identification.

• Proceedings of the IEEK Conference
• /
• 2007.07a
• /
• pp.307-308
• /
• 2007

This paper proposes a discriminative training algorithm for estimating hidden Markov model (HMM) parameters. The proposed algorithm estimates the Parameters by minimizing the p-norm of log-likelihood difference (PLD) between the utterance probability given the correct transcription and the most competitive transcription.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.13 no.2
• /
• pp.654-659
• /
• 2012

We target small businesses workers and identified a relationship of job satisfaction and verified that training is valid in the relationship of job satisfaction. So we have an object and it is basic data for provide improvinge workers' welfare policy. In this study, effectiveness, suitability, familiarity, clarity of training, and job satisfaction levels, organizational management and welfare, turnover attitude are of job satisfaction have a close correlation. So we can maximize the efficiency of business due to adjusting sub-variables of training adequately. This study has specific meaning that is uncovering the mediating effect of education and training for workers in small businesses. Now we can do policy implications and recommendations based job satisfaction factors, training factors, and the parameters of training scores.

• Korean Journal of Applied Biomechanics
• /
• v.23 no.4
• /
• pp.395-402
• /
• 2013

The purpose of this study was to investigate change of mechanical energy before and after training of half vinyasa yoga. Thirteen subjects (height: $163.4{\pm}3.9$ cm, body mass: $54.9{\pm}7.3$ kg, age: $20.0{\pm}0.49$ yrs) participated in this experiment. The motions of half vnyasa yoga were captured with Vicon system and parameters were calculated with Visual-3D. After training of half vinyasa yoga, the mechanical energies of body segments were increased and increments of mechanical energies in the lower segments were greater than the upper segments. The phase increments of mechanical energies increased phase 1, phase 2, and phase 3 in order. After training of half vinyasa yoga, phase contributions of body segments were similar before training of half vinyasa yoga. The contribution of mechanical energy on trunk segment in body was the greatest contribution of upper segments; also that of mechanical energy on thigh segment in body was the greatest contribution of lower segments. Before training, the coefficient of correlation between vertical center of gravity (CoGz) and mechanical energy of phase 3 was a -.559, but after training, the coefficient of correlation between CoGz and mechanical energy of phase 2 was a .587. These findings suggest that the training of half vinyasa yoga may be increasing the mechanical energies of body segments.