• Journal of the Korea Convergence Society
• /
• v.9 no.5
• /
• pp.33-41
• /
• 2018

The purpose of this study is to develop more accurate and robust emotion prediction neural network (EPNN) model by combining heart rate variability (HRV) and neural network. For the sake of improving the prediction performance more reliably, the proposed EPNN model is based on various types of activation functions like hyperbolic tangent, linear, and Gaussian functions, all of which are embedded in hidden nodes to improve its performance. In order to verify the validity of the proposed EPNN model, a number of HRV metrics were calculated from 20 valid and qualified participants whose emotions were induced by using money game. To add more rigor to the experiment, the participants' valence and arousal were checked and used as output node of the EPNN. The experiment results reveal that the F-Measure for Valence and Arousal is 80% and 95%, respectively, proving that the EPNN yields very robust and well-balanced performance. The EPNN performance was compared with competing models like neural network, logistic regression, support vector machine, and random forest. The EPNN was more accurate and reliable than those of the competing models. The results of this study can be effectively applied to many types of wearable computing devices when ubiquitous digital health environment becomes feasible and permeating into our everyday lives.

• Journal of Internet Computing and Services
• /
• v.18 no.1
• /
• pp.65-75
• /
• 2017

The Detection Model is the model to find the result of a certain purpose using artificial intelligent, data mining, intelligent algorithms In Cyber Security, it usually uses to detect intrusion, malwares, cyber incident, and attacks etc. There are an amount of unlabeled data that are collected in a real environment such as security data. Since the most of data are not defined the class labels, it is difficult to know type of data. Therefore, the label determination process is required to detect and analysis with accuracy. In this paper, we proposed a KDFL(K-means and D-S Fusion based Labeling) method using D-S inference and k-means(unsupervised) algorithms to decide label of data records by fusion, and a detection model architecture using a proposed labeling method. A proposed method has shown better performance on detection rate, accuracy, F1-measure index than other methods. In addition, since it has shown the improved results in error rate, we have verified good performance of our proposed method.

• Journal of Food Hygiene and Safety
• /
• v.20 no.2
• /
• pp.73-76
• /
• 2005

Center for Food Standard Evaluation, Korea Food and Drug AdministrationThis study was performed to compare analytical methods of nine synthetic food colors and six food color lakes in Korea, Japan, Joint FAO/WHO Expert Committee of Food Additives (JECFA), and USA. The experimental protocol of this study consists of three parts: titration method with titanium chloride, gravimetric and spectrophotometric method. To measure the total contents of food colors, Korea and Japan used titration method with titanium chloride, USA used the average value of titration method with titanium chloride equipped with Kipp generator and spectrophotometric method. Also, JECFA used titration method with titanium chloride equipped with KiPP generator. However, All the low organizations used gravimetric method to measure the total content of coloring matter on Food Red No.3. Although all organizations use various methods for analysis of coloring matters, total contents of coloring matter on food colors tested fell into the standard showing $85.08-96.40\%$ in synthetic food colors and $10.00-36.86\%$ in food color lakes.

• The Korean Journal of Emergency Medical Services
• /
• v.13 no.2
• /
• pp.73-86
• /
• 2009

Purpose : This study is a descriptive correlation study to offer the basic materials for developing the preventive program of continuously increasing AIDS in the young people by examining the knowledge and attitude of AIDS in college students. Methods : The period of data collection was from May 1 to 15, 2009, 300 freshman, sophomore and junior students who understood the purpose of the research and agreed to participate in the questionnaire were randomly sampled, structured questionnaire was distributed to them and their responses were collected. Instruments used for this study included those used by Kim and Lee and revised and complemented by this researcher to measure the knowledge of AIDS and those by Yun and Lee revised and complemented by the researcher to measure the attitude of AIDS. For data analysis, it measured technical statistics, t-test, ANOVA, and Pearson's correlation coefficient using SPSS/PC 12.0. Results : The results of this study are summarized as follows. 1. The whole knowledge of AIDS the subjects had scored 58.9 and their average attitude scored $3.78(1{\pm}25)$. 2. In the degree of knowledge of AIDS depending on general characteristics and health-related characteristics of the subjects, it was found that the students at the department of emergency medical showed higher knowledge(t=3.638, p=.001) and positive attitude of AIDS(t=3.330, p=.001) compared to students at other majors. 3. In the degree of knowledge of AIDS depending on AIDS-related education, subjects who had experienced AIDS education(t=1.973, p=.050), those with the experience of theory education(F=4.057, p=.008), those who felt the necessity of AIDS education(t=4.588, p=.000), and those who were willing to take part in AIDS education(t=2.898, p=.004) showed higher know1edge of AIDS. In the attitude of AIDS, subjects with theory-oriented AIDS education(F=3.012, p=.032), those who felt the necessity of AIDS education(t=2.445, p=.015), and those who were willing to take part in AIDS education(t=2.379, p=.018) showed positive attitude of AIDS education. 4. As the knowledge of AIDS the subjects was higher(r=.329, p=.000), they showed more positive attitude of AIDS and it meant that there was positive correlations. Conclusion : Consequently, systematic, concrete and continuous education of AIDS suitable to the requirements of college students is needed to induce changes of their knowledge and attitude of AIDS and for this, AIDS education program which can be used properly by the developmental stages of college students who belong to late adolescence should be developed in the field of school and if possible, curriculum of sex education including AIDS education should be established in all departments of college.

• Research in Community and Public Health Nursing
• /
• v.14 no.3
• /
• pp.432-444
• /
• 2003

Purpose: This study attempted to verify the effect of Koryo hand therapy on menstrual cramps and dysmenorrhea among college students. Method: This study performed the quasi-experimental design with nonequivalent control group and the pre and post-test design from August 28 to November 4, 2002. The subjects of this experimental study consisted of 64 college students in the nursing college of K University in D city and K college students in K city, who had more than 5.0 GRS score of menstrual cramps. Among them, 16 people belonged to the experimental group A by using Ceramic Seo Am moxa therapy, 16 to the experimental group B by using Seo Am pellet therapy, 16 to the experimental group C by using combination of Ceramic Seo Am moxa therapy and Seo Am pellet therapy and 16 to the control group. Three different kinds of methods were used three times per week for $5{\sim}6$ weeks(a total of $15{\sim}18$ times) interventions were completed. For the experimental group, A Ceramic Seo Am moxa therapy was given for 40 minutes per each treatment; for the experimental group, B Seo Am pellet therapy was given for 4 hours: for the experimental group, C combination of Ceramic Seo Am moxa therapy and Seo Am pellet therapy was given. To measure menstrual cramps, the graphic rating scale (GRS) was used and to measure dysmenorrheal, a dysmenorrhea scale (15 contents) was used, which was modified from Han &Hur's scale (13 contents). Cronbach's was 0.78 in the pre-test, 0.83 in the first post-test, 0.89 in the following post-test. Data were analyzed by one-way ANOVA, 2 test, repeated measures ANOVA, time contrast test and Sheffe test with the SPSS/Win 11.0 program. Results: ? The first hypothesis, 'Among the experimental group A by using Ceramic Seo Am moxa therapy, the experimental group B by using Seo Am pellet therapy and the experimental group C by using combination of Ceramic Seo Am moxa therapy and Seo Am pellet therapy will have different graphic rating scores of menstrual cramps', was supported (F=6.77, p=0.000, Interaction: p=0.000). ? The second hypothesis, 'Among the experimental group A by using Ceramic Seo Am moxa therapy, the experimental group B by using Seo Am pellet therapy, the experimental group C by using combination of Ceramic Seo Am moxa therapy and Seo Am pellet therapy and the control group will have a significantly different level of dysmenorrhea', was supported (F=6.88, p=0.000, Interaction: p=0.000). From the above results, it can be an effective nursing intervention to give Koryo hand therapy to college students who have menstrual cramps and dysmenorrhea. Conclusion: These findings indicate that Koryo hand therapy could be applied to improve the quality of life and to prevent drug misuse among college students who are physically, mentally and psychologically suffering from menstrual cramps and dysmenorrhea. Furthermore, Koryo hand therapy could be developed as an effective Korean alternative and complementary care in the future. and it could also provide a guideline to apply Koryo hand therapy to other pain and difficulties.

• Journal of the Korea Convergence Society
• /
• v.12 no.1
• /
• pp.99-104
• /
• 2021

In this paper, we propose health risk management using feature extraction and cluster analysis considering time flow. The proposed method proceeds in three steps. The first is the pre-processing and feature extraction step. It collects user's lifelog using a wearable device, removes incomplete data, errors, noise, and contradictory data, and processes missing values. Then, for feature extraction, important variables are selected through principal component analysis, and data similar to the relationship between the data are classified through correlation coefficient and covariance. In order to analyze the features extracted from the lifelog, dynamic clustering is performed through the K-means algorithm in consideration of the passage of time. The new data is clustered through the similarity distance measurement method based on the increment of the sum of squared errors. Next is to extract information about the cluster by considering the passage of time. Therefore, using the health decision-making system through feature clusters, risks able to managed through factors such as physical characteristics, lifestyle habits, disease status, health care event occurrence risk, and predictability. The performance evaluation compares the proposed method using Precision, Recall, and F-measure with the fuzzy and kernel-based clustering. As a result of the evaluation, the proposed method is excellently evaluated. Therefore, through the proposed method, it is possible to accurately predict and appropriately manage the user's potential health risk by using the similarity with the patient.

• Journal of the Korean Electrochemical Society
• /
• v.25 no.2
• /
• pp.88-94
• /
• 2022

The anion exchange membrane used in alkaline membrane fuel cells transports hydroxide ions, and ion conductivity affects fuel cell performance. Thus, the measurement of absolute hydroxide ion conductivity is essential. However, it is challenging to accurately measure hydroxide ion conductivity since hydroxide ions are easily poisoned in the form of bicarbonate by carbon dioxide in the atmosphere. In this study, we applied electrochemical ion exchange treatment to measure the absolute hydroxide ion conductivity of the anion exchange membrane. In addition, we investigated the effect of carbon dioxide poisoning of hydroxide ions on electrochemical performance by measuring bicarbonate conductivity. Commercial anion exchange membranes (FAA-3-50 and Orion TM1) and polyphenylene-based block copolymer (QPP-6F) were used.

• Journal of the Korean Society for Library and Information Science
• /
• v.57 no.1
• /
• pp.93-114
• /
• 2023

Information extraction can facilitate the intensive analysis of documents by providing semantic triples which consist of named entities and their relations recognized in the texts. However, most of the research so far has been carried out separately for named entity recognition and relation extraction as individual studies, and as a result, the effective performance evaluation of the entire information extraction systems was not performed properly. This paper introduces two models of end-to-end information extraction that can extract various entity names in clinical records and their relationships in the form of semantic triples, namely pipeline and joint models and compares their performances in depth. The pipeline model consists of an entity recognition sub-system based on bidirectional GRU-CRFs and a relation extraction module using multiple encoding scheme, whereas the joint model was implemented with a single bidirectional GRU-CRFs equipped with multi-head labeling method. In the experiments using i2b2/VA 2010, the performance of the pipeline model was 5.5% (F-measure) higher. In addition, through a comparative experiment with existing state-of-the-art systems using large-scale neural language models and manually constructed features, the objective performance level of the end-to-end models implemented in this paper could be identified properly.

• Geophysics and Geophysical Exploration
• /
• v.26 no.2
• /
• pp.37-51
• /
• 2023

The ground roll is the most common coherent noise in land seismic data and has an amplitude much larger than the reflection event we usually want to obtain. Therefore, ground roll suppression is a crucial step in seismic data processing. Several techniques, such as f-k filtering and curvelet transform, have been developed to suppress the ground roll. However, the existing methods still require improvements in suppression performance and efficiency. Various studies on the suppression of ground roll in seismic data have recently been conducted using deep learning methods developed for image processing. In this paper, we introduce three models (DnCNN (De-noiseCNN), pix2pix, and CycleGAN), based on convolutional neural network (CNN) or conditional generative adversarial network (cGAN), for ground roll suppression and explain them in detail through numerical examples. Common shot gathers from the same field were divided into training and test datasets to compare the algorithms. We trained the models using the training data and evaluated their performances using the test data. When training these models with field data, ground roll removed data are required; therefore, the ground roll is suppressed by f-k filtering and used as the ground-truth data. To evaluate the performance of the deep learning models and compare the training results, we utilized quantitative indicators such as the correlation coefficient and structural similarity index measure (SSIM) based on the similarity to the ground-truth data. The DnCNN model exhibited the best performance, and we confirmed that other models could also be applied to suppress the ground roll.

• The Journal of Korean Academic Society of Nursing Education
• /
• v.9 no.1
• /
• pp.17-29
• /
• 2003

This study investigated the degree of self-care practice to maintain the stable respiratory function and the required respiratory nursing needs upon the elderly with chronic obstructive pulmonary diseases. The research subjects were 115 elderly people over 60 years old, who were diagnosed to have chronic obstructive pulmonary diseases (the mixed type, chronic bronchitis, bronchial asthma, emphysema) and were hospitalized in 3 university hospitals in Busan or treated as outpatient, and the data was collected over the period between June 1, 2002 and September 30, 2002. In order to measure the respiratory self-care practice degree and nursing needs of the subjects, the instrument on the self-care practice and the instrument on nursing needs were developed by the researcher. The research results are as follows: 1. The mean of respiratory self-care practice degree by the subjects was 2.41 out of 4 for each clause, and the degree of practicing general management was the highest(2.70), and nutrition control(2.66), respiratory exercise(2.65), expectoration of sputum (2.63), oxygen therapy(2.60), environment control(2.50), and medication control(2.36) succeeded. 2. The degree of self-care practice had a significant difference depending on age(F=2.82, P=0.02), frequency of hospitalization(F=3.11, P=0.01), and diagnosed disease(F=15.66, P=0.00). 3. The subjects nursing needs of respiratory system were 3.07 on the average out of 4.00, and 'I want to know how to prevent the infection of respiratory system such as cold scored the highest 3.83, while the clauses like 'want to know how to face the respiratory disorder properly'(3.77) and 'want the specific explanation of the symptoms of my disease'(3.66) also had scored high points. 4. The nursing needs of the respiratory system had a significant difference depending on diagnosed disease such as mixed type of chronic obstructive pulmonary diseases, emphysema, bronchitis, and asthma (F=6.70, P=0.00). The research showed that the subjects degree of self-care practice of respiratory system was low on the whole, while the nursing needs for managing respiratory organ were relatively high. Therefore, specific education concerning the nursing of the disease and self-care upon the elderly having chronic obstructive pulmonary disease is necessary.