• Journal of Multimedia Information System
• /
• v.9 no.1
• /
• pp.21-32
• /
• 2022

Early-stage diagnosis of Alzheimer's Disease (AD) from Cognitively Normal (CN) patients is crucial because treatment at an early stage of AD can prevent further progress in the AD's severity in the future. Recently, computer-aided diagnosis using magnetic resonance image (MRI) has shown better performance in the classification of AD. However, these methods use a traditional machine learning algorithm that requires supervision and uses a combination of many complicated processes. In recent research, the performance of deep neural networks has outperformed the traditional machine learning algorithms. The ability to learn from the data and extract features on its own makes the neural networks less prone to errors. In this paper, a dense neural network is designed for binary classification of Alzheimer's disease. To create a classifier with better results, we studied result of different activation functions in the prediction. We obtained results from 5-folds validations with combinations of different activation functions and compared with each other, and the one with the best validation score is used to classify the test data. In this experiment, features used to train the model are obtained from the ADNI database after processing them using FreeSurfer software. For 5-folds validation, two groups: AD and CN are classified. The proposed DNN obtained better accuracy than the traditional machine learning algorithms and the compared previous studies for AD vs. CN, AD vs. Mild Cognitive Impairment (MCI), and MCI vs. CN classifications, respectively. This neural network is robust and better.

• Korean Journal of Childcare and Education
• /
• v.18 no.1
• /
• pp.23-50
• /
• 2022

Objective: The purpose of this study was to develop an early childhood teacher's autonomy scale in the implementation of the Early Childhood Curriculum and to verify its validity and reliability. Methods: A literature review and a delphi survey were conducted in order to explore conceptual characteristics and develop a preliminary questionnaire. A main survey was conducted on 375 early childhood teacher to test their item quality, validity and reliability. Results: The final scale was composed of 24 items with four factors: 'support for child-centered play environment and interaction' (7 items), 'use of learning community' (4 items), 'cooperation and participation with family and local community' (6 items), and 'flexible daily management' (7 items). And the scale was verified as a stable and reliable tool. Conclusion/Implications: This is expected to contribute to the correct understanding of children's education and to actively realize the autonomy of early childhood teachers in the implementation of the Early Childhood Curriculum.

• Journal of Biomedical Engineering Research
• /
• v.43 no.5
• /
• pp.299-307
• /
• 2022

In this paper, we propose a pre-processing method that converts to Spider Chart image data for classification of gripping movement using EMG (electromyography) sensors and Convolution Neural Networks (CNN) deep learning. First, raw data for six hand gestures are extracted from five test subjects using an 8-channel armband and converted into Spider Chart data of octagonal shapes, which are divided into several sliding windows and are learned. In classifying six hand gestures, the classification performance is compared with the proposed pre-processing method and the existing methods. Deep learning was performed on the dataset by dividing 70% of the total into training, 15% as testing, and 15% as validation. For system performance evaluation, five cross-validations were applied by dividing 80% of the entire dataset by training and 20% by testing. The proposed method generates 97% and 94.54% in cross-validation and general tests, respectively, using the Spider Chart preprocessing, which was better results than the conventional methods.

• Korean Journal of Pharmacognosy
• /
• v.54 no.1
• /
• pp.38-43
• /
• 2023

A simple and accurate assay was developed for the quantitative analysis of 1-deoxynojirimycin (1-DNJ) derived from the silkworm (Bombyx mori). Normal-phase high-performance liquid chromatography coupled with an evaporative light scattering detector (HPLC-ELSD) and a hydrophilic interaction liquid chromatography column was used. Various parameters were applied to optimize the analysis method. The limits of detection and quantification of 1-DNJ were 2.97 × 10^-3 and 9.00 × 10^-3 mg/mL, respectively. The calibration curve showed good linearity results. The concentration range and the r² value were 0.0625-1.0 mg/mL and 0.9997, respectively. The accuracy test demonstrated a significantly high recovery rate (89.95-103.22%). The relative standard deviation was ≤ 1.00%. Thus, a method for the accurate identification and quantitative analysis of 1-DNJ in silkworms was developed. Moreover, in this procedure, the process of derivatization of 1-DNJ, which was required in previous experiments, could be eliminated. This technique may be actively utilized for the development of pharmaceuticals and health functional foods using 1-DNJ.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.516-518
• /
• 2022

In this paper, we introduce a dependence of number of nodes of hidden-layer in fall detection system using Long Short-Term Memory that can detect falls. Its training is carried out using the parameter theta(θ), which indicates the angle formed by the x, y, and z-axis data for the direction of gravity using a 3-axis acceleration sensor. In its learning, validation is performed and divided into training data and test data in a ratio of 8:2, and training is performed by changing the number of nodes in the hidden layer to increase efficiency. When the number of nodes is 128, the best accuracy is shown with Accuracy = 99.82%, Specificity = 99.58%, and Sensitivity = 100%.

• Geomechanics and Engineering
• /
• v.31 no.3
• /
• pp.265-279
• /
• 2022

Tunnel convergence prediction is essential for the safe construction and design of tunnels. This study proposes five machine learning models of deep neural network (DNN), K-nearest neighbors (KNN), Gaussian process regression (GPR), support vector regression (SVR), and decision trees (DT) to predict the convergence phenomenon during or shortly after the excavation of tunnels. In this respect, a database including 650 datasets (440 for training, 110 for validation, and 100 for test) was gathered from the previously constructed tunnels. In the database, 12 effective parameters on the tunnel convergence and a target of tunnel wall convergence were considered. Both 5-fold and hold-out cross validation methods were used to analyze the predicted outcomes in the ML models. Finally, the DNN method was proposed as the most robust model. Also, to assess each parameter's contribution to the prediction problem, the backward selection method was used. The results showed that the highest and lowest impact parameters for tunnel convergence are tunnel depth and tunnel width, respectively.

• International conference on construction engineering and project management
• /
• 2013.01a
• /
• pp.475-478
• /
• 2013

To carry out a one-off construction project successfully, effective and accurate early cost estimation is crucial, especially during the conceptual stage where very limited minimum information of construction project is given. As the level of accuracy of the early cost estimation has huge impacts on precise budgeting and cost management of a project, in other words, reducing the risk of a project, cost must be managed with special awareness. In an effort to improve the estimate accuracy of cost during the conceptual stage, this research introduces a Parameter Impact (PI) which can quantify weights of parameters and rank them; and PI development derived from the principle of impulse in physics is explicated. For a case study, 76 public apartment building cases in Korea are analyzed. To examine the validity of the proposed PI, a validation in terms of CBR applicability test and estimate accuracy comparisons using 10-nearest neighbor cases are carried out. The validation results support that the suggested PI can be applied in quantifying the weights of the parameters and CBR method for early cost estimation.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.475-478
• /
• 2023

컴퓨터 단층촬영(CT)을 활용한 골격근 단면적은 근감소증과 관련된 기능을 평가하는 데 사용된다. 일반적인 근감소증 연구는 요추 3번의 골격근량을 주로 보지만 암 또는 폐절제술과의 상관관계를 예측하기 위한 다양한 연구에서는 흉추 4번, 7번, 8번, 10번, 12번 다양한 수준의 골격근량으로 연구를 진행하고 있음을 알 수 있다. 본 논문에서는 흉부와 복부 CT 영상에서 근감소증 진단을 위해서 흉추와 요추의 영역별 슬라이스를 검출하기 위해서 CNN 구조의 EfficientNetV2를 전이학습하여 인공지능 모듈을 개발하였다. 인공지능 모듈은 전체 흉부 및 복부 CT 영상에서 Cervical, T1, T2, T3, T4, T5, T6, T7, T8, T9, T10, T11, T12, L1, L2, L3, L4, L5, Sacral 총 19 클래스를 검출하도록 하였다. Test 데이터셋을 사용하여 Confusion Matrix와 Grad-CAM으로 모델의 정확도를 시각화하여 보였으며 검증으로 인공지능 모듈의 정확성을 측정하였다. 끝으로 우리가 개발한 다기관 공동연구 지원플랫폼에 적용하여 시각화된 결과를 보였다.

• Journal of Korean Academy of Nursing
• /
• v.30 no.2
• /
• pp.380-390
• /
• 2000

This study was performed to evaluate the effectiveness of music therapy as one of the psychiatric nursing intervention tools, with addtional information in relieving anxiety during the procedure. Data were collected through nonequivalent pre-and post tests from July 1, 1998 to September 30 1998 in 90 patients (test group A: 28 patients, test group B: 27 patients, control group: 33 patients) who were hospitalized in DongSan Medical Center in order to have cardiac catheterization. The Subjects were informed by educational videos, which were modified according to the sensory information of the 10 study patients. They were based on the informative booklet by Kim keum-soon (1989). The procedural information was also modified according to the hospital`s customs. Provided the music for patients suitable to their tastes, and measured their blood pressure, heart rate, the degree of anxiety using the Spielberger`s measurement device of anxiety, and behavioral response of Finesilver`s. The statistical significance was analyzed using chi-square test and ANOVA. The results of this study were as follows : Hypothesis 1 : There are significant differences in the degree of anxiety among test group A, Test group A was provided only information, Test group B was provided information and the control group was provided neither. Hypothesis 2 : There are significant differences in systolic blood pressure among test group A, test group B, and control group.: non-significant. Hypothesis 3 : There are significant differences in diastolic blood pressure among test group A, test group B, and control group.: significant(F=1.31, p=.27, interaction; F=3.80, p=.00). Hypothesis 4 : There are significant differences in heart rate among test group A, test group B, and control group.: non-significant. Hypothesis 5 : There are significant differences in behavioral responses among test group A, test group B, and control group.: significant(F=10.05, p=.00). Further validation study is required with other subjects and other settings.

• Computers and Concrete
• /
• v.32 no.5
• /
• pp.465-474
• /
• 2023

The point load test (PLT) is a widely-used alternative method in the field to determine the uniaxial compressive strength due to its simple testing machine and procedure. The point load test index can estimate the uniaxial compressive strength through conversion factors based on the rock types. However, the mechanism correlating these two parameters and the influence of the mechanical properties on PLT results are still not well understood. This study proposed a theoretical model to understand the mechanism of PLT serving as an alternative to the UCS test based on laboratory observation and literature survey. This model found that the point load test is a self-confined compression test. There is a compressive ellipsoid near the loading axis, whose dilation forms a tensile ring that provides confinement on this ellipsoid. The peak load of a point load test is linearly positive correlated to the tensile strength and negatively correlated to the Poisson ratio. The model was then verified using numerical and experimental approaches. In numerical verification, the PLT discs were simulated using flat-joint BPM of PFC3D to model the force distribution, crack propagation and BPM properties' effect with calibrated micro-parameters from laboratory UCS test and point load test of Berea sandstones. It further verified the mechanism experimentally by conducting a uniaxial compressive test, Brazilian test, and point load test on four different rocks. The findings from this study can explain the mechanism and improve the understanding of point load in determining uniaxial compressive strength.