• Journal of Convergence for Information Technology
• /
• v.12 no.4
• /
• pp.260-269
• /
• 2022

In this paper, We propose an anomaly detection model using deep neural network to automate the identification of outliers of the national air pollution measurement network data that is previously performed by experts. We generated training data by analyzing missing values and outliers of weather data provided by the Institute of Environmental Research and based on the BeatGAN model of the unsupervised learning method, we propose a new model by changing the kernel structure, adding the convolutional filter layer and the transposed convolutional filter layer to improve anomaly detection performance. In addition, by utilizing the generative features of the proposed model to implement and apply a retraining algorithm that generates new data and uses it for training, it was confirmed that the proposed model had the highest performance compared to the original BeatGAN models and other unsupervised learning model like Iforest and One Class SVM. Through this study, it was possible to suggest a method to improve the anomaly detection performance of proposed model while avoiding overfitting without additional cost in situations where training data are insufficient due to various factors such as sensor abnormalities and inspections in actual industrial sites.

• The Journal of the Korea Contents Association
• /
• v.21 no.11
• /
• pp.135-144
• /
• 2021

Recently, data-driven decision-making technology has become a key technology leading the data industry, and machine learning technology for this requires high-quality training datasets. However, real-world data contains missing values for various reasons, which degrades the performance of prediction models learned from the poor training data. Therefore, in order to build a high-performance model from real-world datasets, many studies on automatically imputing missing values in initial training data have been actively conducted. Many of conventional machine learning-based imputation techniques for handling missing data involve very time-consuming and cumbersome work because they are applied only to numeric type of columns or create individual predictive models for each columns. Therefore, this paper proposes a new data imputation technique called 'Denoising Self-Attention Network (DSAN)', which can be applied to mixed-type dataset containing both numerical and categorical columns. DSAN can learn robust feature expression vectors by combining self-attention and denoising techniques, and can automatically interpolate multiple missing variables in parallel through multi-task learning. To verify the validity of the proposed technique, data imputation experiments has been performed after arbitrarily generating missing values for several mixed-type training data. Then we show the validity of the proposed technique by comparing the performance of the binary classification models trained on imputed data together with the errors between the original and imputed values.

• The Journal of Society for e-Business Studies
• /
• v.26 no.4
• /
• pp.133-154
• /
• 2021

Today smart phone is the most common media with a vehicle called 'application'. In order to understand how media users select applications and build their repertoire, this study conducted two-step approach using big data from smart phone log for 4 weeks in November 2019, and finally classified 8 media repertoire groups. Each of the eight media repertoire groups showed differences in time spent of mobile application category compared to other groups, and also showed differences between groups in demographic distribution. In addition to the academic contribution of identifying the mobile application repertoire with large scale behavioral data, this study also has significance in proposing a two-step approach that overcomes 'outlier issue' in behavioral data by extracting prototype vectors using SOM (Sefl-Organized Map) and applying it to k-means clustering for optimization of the classification. The study is also meaningful in that it categorizes customers using e-commerce services, identifies customer structure based on behavioral data, and provides practical guides to e-commerce communities that execute appropriate services or marketing decisions for each customer group.

• 한국노년학
• /
• v.31 no.3
• /
• pp.653-672
• /
• 2011

The present study empirically confirmed Korean elder's four major pains consisted of poverty, disease, role loss, loneliness and investigated the mediating role of depression between the four major pains and the elder's suicidal thought. To investigate the cause and effect of factors, we conveniently collected 309 samples from 16 Gyungrodangs evenly located in Jeonju and 291 samples, survived the data cleaning such as missing values, outliers, normality and covariance conditions, were analyzed by frequency, factor analysis, reliability, confirmatory factor analysis and structural model analysis. Followed were the selected contributions of the present study. First, the constructs of four major pains such as poverty, disease, role loss, loneliness were predictors of suicidal thought mediated by depression. Second, the elder's poverty, that was the heaviest factor of the four major pain constructs, was a predictor of role loss leading to loneliness. Third, four major pains were predictors of the elder's depression. Note that poverty were not direct but indirect predictor of depression. The present study confirmed the concept of four major pains. Also those who practice in the area of the elderly care should consider the four major pains as well as depression while intervening in the elderly's suicidal thought.

• 한국노년학
• /
• v.32 no.2
• /
• pp.359-376
• /
• 2012

The present study empirically confirmed knowledge of ageing and quality of contact were predictors affecting middle-aged Korean's ageism against the elderly and verified mediating role of intergroup anxiety between not only knowledge of ageing but also quality of contact and ageism. To investigate causalities of factors, we purposively collected 400 samples from 20 Dongs evenly located in Jeonju and 393 samples, survived the data cleaning such as missing values, outliers, normality and covariance conditions, were analyzed by frequency, factor analysis, reliability, confirmatory factor analysis and structural model analysis. Followed were the selected contributions of the present study. First, the knowledge of ageing and quality of contact were predictors of ageism mediated by intergroup anxiety. Second, the knowledge of ageing and quality of contact did not directly affect middle-aged Korean's ageism against the elderly. Third, intergroup anxiety had strong effect on ageism. The contributions suggested increasing knowledge of ageing and providing contact experience to middle-aged Korean as combating strategy against ageism.

• Journal of Korea Water Resources Association
• /
• v.54 no.spc1
• /
• pp.1107-1118
• /
• 2021

Climate change brought on by global warming increased the frequency of flood and drought on the Korean Peninsula, along with the casualties and physical damage resulting therefrom. Preparation and response to these water disasters requires national-level planning for water resource management. In addition, watershed-level management of water resources requires flow duration curves (FDC) derived from continuous data based on long-term observations. Traditionally, in water resource studies, physical rainfall-runoff models are widely used to generate duration curves. However, a number of recent studies explored the use of data-based deep learning techniques for runoff prediction. Physical models produce hydraulically and hydrologically reliable results. However, these models require a high level of understanding and may also take longer to operate. On the other hand, data-based deep-learning techniques offer the benefit if less input data requirement and shorter operation time. However, the relationship between input and output data is processed in a black box, making it impossible to consider hydraulic and hydrological characteristics. This study chose one from each category. For the physical model, this study calculated long-term data without missing data using parameter calibration of the Soil Water Assessment Tool (SWAT), a physical model tested for its applicability in Korea and other countries. The data was used as training data for the Long Short-Term Memory (LSTM) data-based deep learning technique. An anlysis of the time-series data fond that, during the calibration period (2017-18), the Nash-Sutcliffe Efficiency (NSE) and the determinanation coefficient for fit comparison were high at 0.04 and 0.03, respectively, indicating that the SWAT results are superior to the LSTM results. In addition, the annual time-series data from the models were sorted in the descending order, and the resulting flow duration curves were compared with the duration curves based on the observed flow, and the NSE for the SWAT and the LSTM models were 0.95 and 0.91, respectively, and the determination coefficients were 0.96 and 0.92, respectively. The findings indicate that both models yield good performance. Even though the LSTM requires improved simulation accuracy in the low flow sections, the LSTM appears to be widely applicable to calculating flow duration curves for large basins that require longer time for model development and operation due to vast data input, and non-measured basins with insufficient input data.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.18 no.3
• /
• pp.45-60
• /
• 2023

In this study, we analyzed the influence of middle-aged office workers' entrepreneurial competency and entrepreneurial opportunity recognition on entrepreneurial intention by mediating entrepreneurial opportunity evaluation. Sub-variables of entrepreneurial competency were classified into prior knowledge, positive attitude, and social network. For the empirical analysis of this study, an online survey using Naver Office was conducted for about 15 days (February 6, 2023 - February 20, 2023) targeting office workers across the country who are interested in starting a business, and a total of 262 copies were collected and missing values. For 250 copies excluding 12 copies, SPSS Ver.24.0 and PROCESS MACRO Model 4.0 were used for empirical analysis. The results of the analysis are as follows: First, the higher the prior knowledge of the founder's individual competency, social network, and entrepreneurial opportunity recognition, the higher the entrepreneurial opportunity evaluation and entrepreneurial intention. On the other hand, it was found that the positive attitude among entrepreneurs' individual competencies did not affect entrepreneurship opportunity evaluation and entrepreneurial intention. In addition, the magnitude of the influence on entrepreneurial opportunity evaluation and entrepreneurial intention was in the order of entrepreneurial opportunity recognition, prior knowledge, and social network. This is because the positive attitude of middle-aged office workers towards start-up has a negative image of start-up due to the shrinking start-up environment due to COVID-19, fear of failure due to lack of preparation for start-up, and successive cases of start-up failure due to cognitive bias errors due to overconfidence. implying that there is Second, it was found that the evaluation of entrepreneurship opportunities had a significant positive (+) effect on entrepreneurial intention in a situation where the entrepreneur's individual competency and entrepreneurial opportunity recognition were controlled. Third, the startup opportunity evaluation was shown to mediate between the prior knowledge of the entrepreneur's individual competency, social network and entrepreneurial opportunity recognition, and entrepreneurial intention, but it did not mediate between positive attitude and entrepreneurial intention. Fourth, among the factors influencing entrepreneurial opportunity evaluation and entrepreneurial intention, entrepreneurial opportunity recognition was found to be larger than founder's individual competency, confirming the importance of entrepreneurial opportunity recognition. Fifth, it was found that prior knowledge and network, which are individual capabilities of the founder, affect the evaluation of entrepreneurial opportunities and entrepreneurial intention, so that strengthening entrepreneurship education to recognize the importance of cultivating prior entrepreneurial knowledge and experience can revitalize middle-aged office workers' entrepreneurship. confirmed.

• The Journal of Korean Society for School & Community Health Education
• /
• v.25 no.2
• /
• pp.45-57
• /
• 2024

Objectives: The purpose of this study is to determine the impact of artificial menopause on the diagnosis of thyroid cancer, breast cancer, and cervical cancer, and to provide basic data for cancer prevention and early diagnosis in women. Methods: Analysis was conducted using raw data from the 2011-2020 National Health and Nutrition Examination Survey. Among the 79,262 people surveyed in the 2011-2020 National Health and Nutrition Examination Survey, 10,207 people were selected as the final research subjects, excluding men, those under 18 years old, those over 80 years old, those who did not participate in the health survey, those with missing data, and those who were not in menopause. Among them, 248 people were diagnosed with thyroid cancer (2.7%), 225 people were diagnosed with breast cancer (2.5%), and 143 people were diagnosed with cervical cancer (21.5%). Results: First, there appeared to be differences between the thyroid cancer diagnosed group and the non-diagnosed group depending on educational level, childbirth experience, and menopause type. Second, there appeared to be differences between the breast cancer diagnosis group and the non-diagnosis group depending on educational level, menopause age, pregnancy experience, childbirth experience, subjective health status, and menopause type. Third, there appeared to be differences between the cervical cancer diagnosis group and the non-diagnosis group depending on menopause age, subjective health status, and menopause type. Fourth, compared to natural menopause, in the case of artificial menopause, the diagnosis probability of women increased by 2.010 times for thyroid cancer, 3.872 times for breast cancer, and 14.902 times for cervical cancer. Conclusion: For thyroid cancer, breast cancer, and cervical cancer, the probability of cancer diagnosis increases in the case of artificial menopause compared to natural menopause, so it is considered important to avoid experiencing artificial menopause to prevent cancer.