• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.33 no.6
• /
• pp.265-274
• /
• 2021

Outlier detection research in ocean data has traditionally been performed using statistical and distance-based machine learning algorithms. Recently, AI-based methods have received a lot of attention and so-called supervised learning methods that require classification information for data are mainly used. This supervised learning method requires a lot of time and costs because classification information (label) must be manually designated for all data required for learning. In this study, an autoencoder based on unsupervised learning was applied as an outlier detection to overcome this problem. For the experiment, two experiments were designed: one is univariate learning, in which only SST data was used among the observation data of Deokjeok Island and the other is multivariate learning, in which SST, air temperature, wind direction, wind speed, air pressure, and humidity were used. Period of data is 25 years from 1996 to 2020, and a pre-processing considering the characteristics of ocean data was applied to the data. An outlier detection of actual SST data was tried with a learned univariate and multivariate autoencoder. We tried to detect outliers in real SST data using trained univariate and multivariate autoencoders. To compare model performance, various outlier detection methods were applied to synthetic data with artificially inserted errors. As a result of quantitatively evaluating the performance of these methods, the multivariate/univariate accuracy was about 96%/91%, respectively, indicating that the multivariate autoencoder had better outlier detection performance. Outlier detection using an unsupervised learning-based autoencoder is expected to be used in various ways in that it can reduce subjective classification errors and cost and time required for data labeling.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.5
• /
• pp.271-278
• /
• 2022

This study attempted to prepare basic data for international students with Vietnamese nationality in Korea to identify positive psychological capital, social support, social presence, and quality of life and to prepare support measures to improve their quality of life. Data collection is from May 1, 2021 to June 30, 2021, and was conducted through an online survey for anonymity and convenience. For data analysis, the IBM SPSS/25 statistical program was used, and the significance level for the results was measured as .05, and the reliability of each measurement tool was calculated. The results of this study are summarized as follows. First, the age of the subjects was '24 years old-27 years old', and women accounted for the majority. In the fourth grade, the fourth grade was the most, with "outgoing" personality, "sometimes" experiences of interpersonal conflict, "more than four years and less than five years" in the period of residence in Korea, and the level of Korean proficiency was "grade three." Second, the average quality of life of Vietnamese international students was 3.52 points (out of 5 points), positive psychological capital was 3.98 points (out of 6 points), social support was 2.96 points (out of 4 points), and social presence was 3.59 points (out of 5 points). Third, in the case of the quality of life of Vietnamese international students, there was a significant difference according to their personality, and as a result of post-verification, the quality of life of the 'extroverted' group was higher than the 'mixed' group. There was a significant difference according to interpersonal conflict), and as a result of post-examination, the "no conflict" group had a higher quality of life than the "conflict frequent" group. Fourth, the factors that most affected the subject's quality of life were social support, positive psychological capital, and personality (extroverted). The explanatory power of the model was 33.2%.