• The Transactions of the Korea Information Processing Society
• /
• v.7 no.6
• /
• pp.1834-1843
• /
• 2000

In this paper, we propose a modular neural network based classification method for handwritten numerals utilizing rotated and translated images of an input image. The whole numeral pattern space is divided into smaller spaces which overlap each other and form multiple clusters. On these multiple clusters, multiple multilayer perceptrons (MLP) neural networks, specialized in those clusters, are constructed. Thus, each MLP acts as an expert network on the corresponding cluster. An MLP is also used as a gating network functioning as a mediator among the multiple MLPs. In the learning phase, an input numeral image is dithered by tow geometric operations of translation and rotation so that new numeral images similar to original one are generated. In the recognition phase, we utilize not only input numeral image, but also nearly generated images through the rotation and the translation of the original image. Thus, multiple output values for those generated images were combined to make class decision by various combination methods. The experimental results confirm the validity of the proposed method.

• Journal of KIISE:Computing Practices and Letters
• /
• v.14 no.3
• /
• pp.326-330
• /
• 2008

The study on combining multiple classifiers in the field of pattern recognition has mainly focused on how to combine multiple classifiers, but it has gradually turned to the study on how to select multiple classifiers from a classifier pool recently. Actually, the performance of multiple classifier system depends on the selected classifiers as well as the combination method of classifiers. Therefore, it is necessary to select a classifier set showing good performance, and an approach based on information theory has been tried to select the classifier set. In this paper, a classifier set candidate is made by the selection of classifiers, on the basis of mutual information between classifiers, and the classifier set candidate is compared with the other classifier sets chosen by the different selection methods in experiments.

• Journal of Korea Multimedia Society
• /
• v.18 no.4
• /
• pp.460-472
• /
• 2015

Most of previous visual attention system finds attention regions based on saliency map which is combined by multiple extracted features. The differences of these systems are in the methods of feature extraction and combination. This paper presents a new system which has an improvement in feature extraction method of color and motion, and in weight decision method of spatial and temporal features. Our system dynamically extracts one color which has the strongest response among two opponent colors, and detects the moving objects not moving pixels. As a combination method of spatial and temporal feature, the proposed system sets the weight dynamically by each features' relative activities. Comparative results show that our suggested feature extraction and integration method improved the detection rate of attention region.

• International Journal of Computer Science & Network Security
• /
• v.21 no.7
• /
• pp.324-330
• /
• 2021

Agriculture is one of the essential needs of human life on planet Earth. It is the source of food and earnings for many individuals around the world. The economy of many countries is associated with the agriculture sector. Lots of diseases exist that attack various fruits and crops. Apple Tree Leaves also suffer different types of pathological conditions that affect their production. These pathological conditions include apple scab, cedar apple rust, or multiple diseases, etc. In this paper, an automatic detection framework based on deep learning is investigated for apple leaves disease classification. Different pre-trained models, VGG16, ResNetV2, InceptionV3, and MobileNetV2, are considered for transfer learning. A combination of parameters like learning rate, batch size, and optimizer is analyzed, and the best combination of ResNetV2 with Adam optimizer provided the best classification accuracy of 94%.

• Journal of Biomedical Engineering Research
• /
• v.26 no.4
• /
• pp.231-241
• /
• 2005

New methods to register multiple hemispheric slices of the postmortem brain to anatomically corresponding in-vivo MRI slices within a 3D volumetric MRI are presented. Gel-embedding and fiducial markers are used to reduce geometrical distortions in the postmortem brain volume. The registration algorithm relies on a recursive extraction of warped MRI slices from the reference MRI volume using a modified non-linear polynomial transformation until matching slices are found. Eight different voxel similarity measures are tested to get the best co-registration cost and the results show that combination of two different similarity measures shows the best performance. After validating the implementation and approach through simulation studies, the presented methods are applied to real data. The results demonstrate the feasibility and practicability of the presented co­registration methods, thus providing a means of MR signal analysis and histological examination of tissue lesions via co­registered images of postmortem brain slices and their corresponding MRI sections. With this approach, it is possible to investigate the pathology of a disease through both routinely acquired MRls and postmortem brain slices, thus improving the understanding of the pathological substrates and their progression.

• Korean Journal of Clinical Pharmacy
• /
• v.32 no.2
• /
• pp.125-132
• /
• 2022

Background: Fixed-dose combinations have the advantage of improving patient compliance, but may increase the risk of duplicate prescriptions. As the use of fixed-dose combination antihypertensives increases, it is necessary to investigate the current status of class duplication prescriptions (CDP) in patients taking fixed-dose combination antihypertensives in Korea and to identify factors associated with CDP. Methods: We conducted a retrospective observational study using nationally representative claim data. Hypertensive patients aged 20 years or older taking fixed-dose combination antihypertensives were extracted. Among these patients, patients with CDP were identified. A chi-square test was applied to determine the differences between patients with CDP and non-CDP. The associated factors of CDP were identified through multiple logistic regression. Results: Of the 74,165 patients who were prescribed fixed-dose combination antihypertensives, 426 patients (0.6%) with CDP were identified. The most common antihypertensive class associated with CDP was calcium channel blockers (194 patients, 45.5%), followed by angiotensin II receptor blockers (136 patients, 31.9%). Patients aged 75 years or older (odds ratio [OR] 1.83, 95% confidence interval [CI] 1.02-3.52), chronic kidney disease (OR 4.45, 95% CI 2.15-8.25), chronic heart failure (OR 2.71, 95% CI 1.93-3.72), coronary artery disease (OR 2.22, 95% CI 1.60-3.03) and Medical Aid/Patriots and Veterans Insurance (OR 1.49, 95% CI 1.04-2.07) were significantly associated with increased CDP. Conclusions: The factors associated with CDP were the elderly, comorbidities, and low socioeconomic status. Since CDP can result in negative clinical outcomes, active intervention by the pharmacist is warranted.

• The Journal of Korean Medicine
• /
• v.41 no.3
• /
• pp.151-161
• /
• 2020

Objectives: The purpose of this study is to report the improvement of multiple rib fracture after korean medical treatment; adhesive treatment and herb-medicine treatment. Methods: A patient with multiple rib fracture was treated with Daewhangchija-paste(大黃梔子膏) adhesive and herb-medicine treatment. Verbal numeric rating scale, medical examination by interview and rib series x-ray were used to assess progress of treatment. And we took pictures of left flank after attaching Daewhangchija-paste to observe the changes of the skin colors. Results: Rib series x-ray taken after 2 months of treatment revealed hard callus which added stability against external force on rib cage. After taking off Daewhangchija-paste, left plank skin turned into blue, green and yellow. And the pain level(VNRS) of left plank decreased from 10 to 0.5 for 4 months. Conclusions: Pain reduction on trauma site and improvement of general health condition were observed during combination treatment of Daewhangchija-paste adhesive and herb-medicine.

• Structural Engineering and Mechanics
• /
• v.14 no.1
• /
• pp.85-98
• /
• 2002

The use of supplemental damping to dissipate seismic energy is one of the most economical and effective ways to mitigate the effects of earthquakes on structures. Both displacement-dependent and velocity-dependent devices dissipate earthquake-induced energy effectively. Combining displacement-dependent and velocity-dependent devices for seismic mitigation of structures minimizes the shortcomings of individual dampers, and is the most economical solution for seismic mitigation. However, there are few publications related to the optimum distributions of combined devices in a multiple-bay frame building. In this paper, the effectiveness of a building consisting of multiple bags equipped with combined displacement-dependent and velocity-dependent devices is investigated. A four-story building with six bays was selected as an example to examine the efficiency of the proposed combination methods. The parametric study shows that appropriate arrangements of different kinds of devices make the devices more efficient and economical.

• Nuclear Engineering and Technology
• /
• v.52 no.6
• /
• pp.1334-1339
• /
• 2020

This paper presents an empirical and comprehensive forecasting analysis of the uranium price. Prices are generally difficult to forecast, and the uranium price is not an exception because it is affected by many external factors, apart from imbalances between demand and supply. Therefore, a systematic analysis of multiple forecasting methods and combinations of them along repeated forecast origins is a way of discerning which method is most suitable. Results suggest that i) some sophisticated methods do not improve upon the Naïve's (horizontal) forecast and ii) Unobserved Components methods are the most powerful, although the gain in accuracy is not big. These two facts together imply that uranium prices are undoubtedly subject to many uncertainties.

• Steel and Composite Structures
• /
• v.51 no.4
• /
• pp.391-406
• /
• 2024

The present research investigates the combination resonance behaviors of porous FG shallow shells reinforced with oblique stiffeners and subjected to a two-term excitation. The oblique stiffeners considered in this research reinforce the shell internally and externally. To model the stiffeners, Lekhnitskii's smeared stiffeners technique is utilized. According to the first-order shear deformation theory (FSDT) and stress functions, a nonlinear model of the oblique stiffened shallow shell is established. With regard to the FSDT and von-Kármán nonlinear geometric assumptions, the stress-strain relationships for the present shell system are developed. Also, in order to discretize the nonlinear governing equations, the Galerkin method is implemented. To obtain the required relations for investigating the combination resonance theoretically, the method of multiple scales is applied. For verifying the results of the present research, generated results are compared with previous research. Additionally, a comparison with the P-T method is conducted to increase the validity of the generated results, as this method has illustrated advantages over other numerical methods in terms of accuracy and reliability. In this method, the piecewise constant argument is used jointly with the Taylor series expansion, which is why it is named the P-T method. The effects of stiffeners with different angles, and the effects of material parameters on the combination resonance behaviors of the present system are addressed. With the findings of this research, researchers and engineers in this field may use them as benchmarks for their design and research of porous FG shallow shells.