• The Journal of the Korea institute of electronic communication sciences
• /
• v.13 no.6
• /
• pp.1333-1342
• /
• 2018

Until now, Electroencephalography(: EEG) has been the most important and convenient method for the diagnosis and treatment of epilepsy. However, it is difficult to identify the wave characteristics of an epileptic EEG signals because it is very weak, non-stationary and has strong background noise. In this paper, we analyse the effect of dimensionality reduction methods on Epileptic EEG feature selection and classification. Three dimensionality reduction methods: Pincipal Component Analysis(: PCA), Kernel Principal Component Analysis(: KPCA) and Linear Discriminant Analysis(: LDA） were investigated. The performance of each method was evaluated by using Support Vector Machine SVM, Logistic Regression(: LR), K-Nearestneighbor(: K-NN), Decision Tree(: DR) and Random Forest(: RF). From the experimental result, PCA recorded 75% of highest accuracy in SVM, LR and K-NN. KPCA recorded 85% of best performance in SVM and K-KNN while LDA achieved 100% accuracy in K-NN. Thus, LDA dimensionality reduction is found to provide the best classification result for epileptic EEG signal.

• Research in Community and Public Health Nursing
• /
• v.32 no.4
• /
• pp.457-466
• /
• 2021

Purpose: The purpose of this study was to examine the correlations among emotional perception clarity, emotion regulation, family relationship, non-suicidal self-injury, and depression, and to determine associated factors of non-suicidal self-injury and depression for senior elementary school students. Methods: Data were collected from 150 early adolescences in K region, Korea. A self-report questionnaire consisted of Trait Meta-Mood Scale, Cognitive Emotion Regulation Questionnaire, Family Relationship Assessment Scale, Functional Assessment of Self-Mutilation, and Children's Depression Inventory. The data were analyzed using t-test, Pearson's correlation coefficient, logistic regression, and multiple regression analysis. Results: Non-suicidal self-injury and depression were positively associated with maladaptive emotion regulation strategy and family conflict, but negatively related to emotional perception clarity and family support. Adaptive emotion regulation strategy and family togetherness were only significantly correlated with depression. In logistic regression analysis, significant predictors of non-suicidal self-injury were emotional perception clarity, maladaptive emotion regulation strategy, and family support. Multiple regression analysis found that significant factors of depression were adaptive and maladaptive emotion regulation strategies, which explained 38.0% of the variance. Conclusion: Our study findings suggest that targeted intervention to reinforce the adaptive emotion regulation strategy and family relationship may prevent non-suicidal self-injury, and depression for senior elementary school students.

• Journal of Korea Society of Industrial Information Systems
• /
• v.14 no.3
• /
• pp.106-113
• /
• 2009

Various statistical classification methods have been used to establish prediction model of underground cultural assets in our country. Among them, linear discriminant analysis, logistic regression, decision tree, neural network, and support vector machines are used in this paper. We introduced the basic concepts of above-mentioned classification methods and applied these to the analyses of real data of I city. As a results, five different prediction models are suggested. And also model comparisons are executed by suggesting correct classification rates of the fitted models. To see the applicability of the suggested models for a new data set, simulations are carried out. R packages and programs are used in real data analyses and simulations. Especially, the detailed executing processes by R are provided for the other analyser of related area.

• International Journal of Computer Science & Network Security
• /
• v.23 no.3
• /
• pp.49-56
• /
• 2023

Machine learning methods diversely applied to the Internet of Things (IoT) field have been successful due to the enhancement of computer processing power. They offer an effective way of detecting malicious intrusions in IoT because of their high-level feature extraction capabilities. In this paper, we proposed a novel feature selection method for malicious intrusion detection in IoT by using an evolutionary technique - Genetic Algorithm (GA) and Machine Learning (ML) algorithms. The proposed model is performing the classification of BoT-IoT dataset to evaluate its quality through the training and testing with classifiers. The data is reduced and several preprocessing steps are applied such as: unnecessary information removal, null value checking, label encoding, standard scaling and data balancing. GA has applied over the preprocessed data, to select the most relevant features and maintain model optimization. The selected features from GA are given to ML classifiers such as Logistic Regression (LR) and Support Vector Machine (SVM) and the results are evaluated using performance evaluation measures including recall, precision and f1-score. Two sets of experiments are conducted, and it is concluded that hyperparameter tuning has a significant consequence on the performance of both ML classifiers. Overall, SVM still remained the best model in both cases and overall results increased.

• Journal of Korean Academy of Nursing
• /
• v.54 no.1
• /
• pp.59-72
• /
• 2024

Purpose: This cross-sectional study aimed to identify factors influencing the intention for continual fertility treatments among women undergoing assisted reproductive technology (ART). Methods: A total of 197 women were recruited through convenience sample from fertility hospitals in Gyeonggi-do and Busan, South Korea. Data were collected using a self-report questionnaire incorporating measures of uncertainty; Depression Anxiety Stress Scales; Fatigue Severity Scale; Coping Scale for Infertility-Women; spousal support; treatment environment; and intention for continual fertility treatment. Descriptive statistics, chi-square tests, t-tests, and logistic regression analysis were conducted using IBM SPSS 26.0. Results: As many as 70.6% of the participants expressed an intention for continual fertility treatments. Logistic regression analysis revealed that factors such as uncertainty (odds ratio [OR] = 0.44, 95% confidence interval [CI] 0.20~0.95), active coping (OR = 4.04, 95% CI 1.11~14.71), treatment environment (OR = 2.77, 95% CI 1.26~6.07), and the duration of marriage (OR = 2.61, 95% CI 1.24~5.49) were significantly related with this intention. Conclusion: These findings underscore the significance of uncertainty management, having proactive coping strategies, having supportive treatment environments, and considering the duration of marriage concerning women's intention for continual fertility treatment in the context of ART. The implications of these results extend to the development of nursing intervention programs aimed at providing crucial support for women undergoing ART and seeking to continue their infertility treatment.

• Journal of The Korean Society of Integrative Medicine
• /
• v.12 no.2
• /
• pp.155-166
• /
• 2024

Purpose : This study aims to identify key factors for predicting dropout risk at the university level and to provide a foundation for policy development aimed at dropout prevention. This study explores the optimal machine learning algorithm by comparing the performance of various algorithms using data on college students' dropout risks. Methods : We collected data on factors influencing dropout risk and propensity were collected from N University. The collected data were applied to several machine learning algorithms, including random forest, decision tree, artificial neural network, logistic regression, support vector machine (SVM), k-nearest neighbor (k-NN) classification, and Naive Bayes. The performance of these models was compared and evaluated, with a focus on predictive validity and the identification of significant dropout factors through the information gain index of machine learning. Results : The binary logistic regression analysis showed that the year of the program, department, grades, and year of entry had a statistically significant effect on the dropout risk. The performance of each machine learning algorithm showed that random forest performed the best. The results showed that the relative importance of the predictor variables was highest for department, age, grade, and residence, in the order of whether or not they matched the school location. Conclusion : Machine learning-based prediction of dropout risk focuses on the early identification of students at risk. The types and causes of dropout crises vary significantly among students. It is important to identify the types and causes of dropout crises so that appropriate actions and support can be taken to remove risk factors and increase protective factors. The relative importance of the factors affecting dropout risk found in this study will help guide educational prescriptions for preventing college student dropout.

• Research in Community and Public Health Nursing
• /
• v.26 no.2
• /
• pp.140-149
• /
• 2015

Purpose: This study was conducted to identify activities of daily living, depression and self-rated health and related factors for Korean Elderly. Methods: Data from the survey for the Korean Longitudinal Study of Aging in 2010 were used. The data were analyzed using frequencies, weighted proportions, and hierarchical multiple logistic regression. Results: Significant difference was observed in health status induced by socioeconomic status between men and women, but not among age groups. Socioeconomic status was strongly associated with self-rated health among male and female elders. Being unschooled and low net family asset were significantly related with dependency in activities of daily living and depressive symptoms among men. Only low net family asset was significantly related with depressive symptoms among women. Family support provides a slight decrease to the negative relationship between socioeconomic status and health status, especially depressive symptoms. Conclusion: This study suggests that interventions to reduce health inequalities should target elderly with lower socioeconomic status and with poor family support, using a gender-specific approach.

• Environmental Analysis Health and Toxicology
• /
• v.31
• /
• pp.18.1-18.8
• /
• 2016

Objectives This study aimed to evaluate the risk factors associated with depression and suicidal ideation in a rural population. Methods A survey was conducted with 543 farmers from Chungcheongnam-do Province using the Center for Epidemiologic Studies Depression Scale (CES-D) for depression, Lubben Social Network Scale (LSNS) for social support, Swedish Q16 for neurotoxicity symptoms and a survey tool for farmer's syndrome. Results After adjusting for socioeconomic factors using logistic regression analysis, poor self-rated health, low social support and neurotoxicity were positively associated with the risk of depression (odds ratio [OR], 15.96; 95% confidence interval [CI], 3.11 to 81.97; OR, 3.14; 95% CI, 1.26 to 7.82; and OR, 3.68; 95% CI, 1.08 to 12.57, respectively). The risk of suicidal ideation significantly increased with low social support, neurotoxicity and farmer's syndrome (OR, 2.28; 95% CI, 1.18 to 4.40; OR, 6.17; 95% CI, 2.85 to 13.34; and OR, 3.70; 95% CI, 1.51 to 9.07, respectively). Conclusions Given the overall results of this study, there is a need to establish programs which can improve the health and social relationships of farmers. Also, when farmers have neurological symptoms from pesticide exposure and characteristic symptoms of farmer's syndrome, a monitoring system for depression and suicide must be made available.

• Korean Journal of Health Education and Promotion
• /
• v.28 no.4
• /
• pp.39-49
• /
• 2011

Objectives: This study was to examine the association between structural and functional characteristics of social network and self-rated health in middle-aged Korea population. We also explored gender difference in the relationship between social network and health. Methods: Data were collected from individuals aged 40-69 years old participating in the 2005 survey for the Korean Genome & Epidemiology Study. We examined the association between social network, social support, social conflict and self-rated health using multiple logistic regression analysis stratified by gender. Results: The extent and contact frequency of close people, and social participations were associated by not only the positive function but also the negative function of social network. Both the positive and negative functions of social network affected self-rated health. The relationship between the function of social network and health showed a gender difference: only positive function was significantly associated with health in men while only negative function had significant relationship with health in women. Conclusions: Social support and social conflict affected the health in both genders through different ways. The ambivalent effect of social network on health should be explored further.

• Journal of Korean Public Health Nursing
• /
• v.28 no.2
• /
• pp.333-346
• /
• 2014

Purpose: This study was conducted in order to identify factors that influence depression for low-income elderly who live at home from the International Classification of Functioning model (ICF). Methods: The subjects were 205 elderly people living at home in two public health centers located in metropolitan cities. Subjects were divided according to their depression scores, which were measured using the GDS-short form, including normal, risk, and depression groups. Each variable was consistent with factors of the ICF model, including health condition, individual factors, environmental factors, body function, activities, and participation. Data were collected using structured questionnaires. ANOVA, $x^2$, Pearson's correlation coefficient, and Multinomial logistic regression with IBM SPSS 21.0 were used for analysis of the data. Results: Statistically significant differences were observed among normal, risk, and depression groups regarding personal factors. Gender, education level, numbers of diseases, perceived health, life satisfaction, and social support were identified as the variables that had a significant impact on depression of low-income elderly living at home. Conclusion: Results of this study indicate that there is a need for construction and implementation of strategies that strengthen life satisfaction and social support in order to lower depression of low-income elderly.