• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.2
• /
• pp.313-316
• /
• 2022

In this paper, we implement a system that detects abnormalities in the charging data transmitted from the charger during the charging process of electric vehicles and controls them remotely. Using classification algorithms such as logistic regression, KNN, SVM, and decision trees, to do this, an analysis model is created that judges the data received from the charger as normal and abnormal. In addition, a model is created to determine the cause of the abnormality using the existing charging data based on the analysis of the type of charger abnormality. Finally, it is solved using unsupervised learning method to find new patterns of abnormal data.

• Journal of Sensor Science and Technology
• /
• v.32 no.6
• /
• pp.378-385
• /
• 2023

Human biosignals provide essential information for diagnosing diseases such as dementia and Parkinson's disease. Owing to the shortcomings of current clinical assessments, noninvasive solutions are required. Machine learning (ML) on wearable sensor data is a promising method for the real-time monitoring and early detection of abnormalities. ML facilitates disease identification, severity measurement, and remote rehabilitation by providing continuous feedback. In the context of wearable sensor technology, ML involves training on observed data for tasks such as classification and regression with applications in clinical metrics. Although supervised ML presents challenges in clinical settings, unsupervised learning, which focuses on tasks such as cluster identification and anomaly detection, has emerged as a useful alternative. This review examines and discusses a variety of ML algorithms such as Support Vector Machines (SVM), Random Forests (RF), Decision Trees (DT), Neural Networks (NN), and Deep Learning for the analysis of complex clinical data.

• Journal of the Korean Data and Information Science Society
• /
• v.26 no.1
• /
• pp.187-196
• /
• 2015

The team's performances were analyzed by evaluating the scores gained by their offense and the scores allowed by their defense. To evaluate the team's attacking and defending abilities, we also considered the factors that contributed the team's gained points or the opposing team's gained points? In order to analyze the outcome of the games, three prediction models were used such as decision trees, logistic regression, and discriminant analysis. As a result, the factors associated with the defense showed a decisive influence in determining the game results. We analyzed the offense and defense by using the response variable. This showed that the major factors predicting the offense were non-stop pass and attack speed and the major factor predicting the defense were the distance between right and left players and the distance between front line attackers and rearmost defenders during the game.

• Journal of Korean Academy of Nursing
• /
• v.50 no.2
• /
• pp.191-199
• /
• 2020

Purpose: The purpose of this study was to compare sociodemographic characteristics of a normal cognitive group and mild cognitive impairment group, and establish prediction models of Mild Cognitive Impairment (MCI). Methods: This study was a secondary data analysis research using data from "the 4th Korea Longitudinal Study of Ageing" of the Korea Employment Information Service. A total of 6,405 individuals, including 1,329 individuals with MCI and 5,076 individuals with normal cognitive abilities, were part of the study. Based on the panel survey items, the research used 28 variables. The methods of analysis included a χ²-test, logistic regression analysis, decision tree analysis, predicted error rate, and an ROC curve calculated using SPSS 23.0 and SAS 13.2. Results: In the MCI group, the mean age was 71.4 and 65.8% of the participants was women. There were statistically significant differences in gender, age, and education in both groups. Predictors of MCI determined by using a logistic regression analysis were gender, age, education, instrumental activity of daily living (IADL), perceived health status, participation group, cultural activities, and life satisfaction. Decision tree analysis of predictors of MCI identified education, age, life satisfaction, and IADL as predictors. Conclusion: The accuracy of logistic regression model for MCI is slightly higher than that of decision tree model. The implementation of the prediction model for MCI established in this study may be utilized to identify middle-aged and elderly people with risks of MCI. Therefore, this study may contribute to the prevention and reduction of dementia.

• Korean Journal of Plant Resources
• /
• v.18 no.2
• /
• pp.279-284
• /
• 2005

The study was conducted to investigate the correlation and regression analysis between the factors - diameter, hight and crown width - and collection amount of Rhus lacquer by the sex of Rhus verniciflua. The relationship between the diameter and the collection amount of the lacquer by the sex of the lacquer tree indicated that, for both of the male and the female, the lacquer amount was likely to increase as the diameter got larger. In general, the male trees tended towards the higher amount of the lacquer than the female. The relationship between the crown width and the collection amount of the lacquer by the sex showed little difference. As the crown became wider, however, the lacquer amount showed the increasing trend. The regression analysis by the sex of the tree indicated that the major factors of the female had larger influence on the lacquer amount than those of the male. The no differences of statistical significance were found among the diameter, the height, the crown width, and the lacquer amount.

• Journal of the Korean Data and Information Science Society
• /
• v.25 no.3
• /
• pp.513-522
• /
• 2014

Using the assumption that the price of a stock follows a geometric Brownian motion with constant volatility, Black and Scholes (BS) derived a formula that gives the price of a European call option on the stock as a function of the stock price, the strike price, the time to maturity, the risk-free interest rate, the dividend rate paid by the stock, and the volatility of the stock's return. However, implied volatilities of BS method tend to depend on the stock prices and the time to maturity in practice. To address this shortcoming, we estimate the implied volatility function as a function of the strike priceand the time to maturity for data consisting of the daily prices for KOSPI200 call options from January 2007 to May 2009 using support vector regression (SVR), the multiple additive regression trees (MART) algorithm, and ordinary least squaress (OLS) regression. In conclusion, use of MART or SVR in the BS pricing model reduced both RMSE and MAE, compared to the OLS-based BS pricing model.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.11 no.6
• /
• pp.49-60
• /
• 2008

In this study, the green zone patterns of sidewalks are classified 'one street-tree row + building,' 'one street-tree row + green zone,' 'two street-tree rows + building,' and 'two street-tree rows + green zone' and assessed their visual characteristic in order to provide desirable measures for scenery design. As a result of the analysis of visual images of sidewalk, the scenery in which street trees are planted in one row was generally assessed to be negative, while roads where green zones rather than buildings are adjacent were revealed to seem stable and pleasant. The scenery in which street trees are planted in two rows was assessed highly in an image of 'extensionality' indicating street circumstances, and especially the pattern 'two street-tree rows + green zone' was shown to be the most beautiful scenery. According to the results of factor analysis of sidewalks, three factors were identified : 'extensionality' showing sidewalk circumstances; 'peculiarity' including unique personality, and 'pliability' showing the organic flow of the scenery. The results of the analysis of visual preference of the scenery according to green zone patterns showed that the 'two street-tree rows + green zone' was measured to be highest. When buildings are adjacent to a sidewalk, two street-tree rows rather than one street-tree row were assessed to increase preference. As for the correlation between visual factors and preference analyzed through multiple regression analysis, all 'extensionality,' 'peculiarity,' and 'pliability' were revealed to show positive correlation for visual preference.

• International Journal of Highway Engineering
• /
• v.18 no.6
• /
• pp.173-180
• /
• 2016

OBJECTIVES : Fixed roadside objects are a threat to drivers when their vehicles deviate from the road. Therefore, such roadside objects need to be suitably dealt with to decrease accidents. This study determines the factors affecting the severity of accidents because of fixed roadside objects. METHODS : This study analyzed the crash severity impact of fixed roadside objects by using ordered probit regression as the analysis methodology. In this research, data from 896 traffic accidents reported in the last three years were used. These accidents consisted of sole-car accidents, fixed roadside object accidents, and lane-departure accidents on the national highway of Korea. The accident severity was classified as light injury, severe injury, and death. The factors relating to the road and the driver were collected as independent variables. RESULTS : The result of the analysis showed that the variables of the crash severity impact are the collision location (left side), gender of the driver (female), alcohol use, collision facility (roadside trees, traffic signals, telephone poles), and type of road (rural segments). Additionally, the collision location (left side), gender of the driver (female), alcohol use, collision facility (street trees, traffic signals, telephone poles), and type of road (rural segments), in order of influence, were found to be the factors affecting the crash severity in accidents due to fixed roadside objects. CONCLUSIONS : An alternative solution is urgently required to reduce the crash severity in accidents due to fixed roadside objects. Such a solution can consider the appropriate places to install breakaway devices and energy-absorbing systems.

• Journal of Forest and Environmental Science
• /
• v.30 no.4
• /
• pp.351-361
• /
• 2014

Leaf area ($A_0$) and leaf biomass ($M_0$) estimation are significant prerequisites to studying tree physiological processes and modeling in the forest ecosystem. The objective of this study was to develop allometric models for estimating $A_0$ and $M_0$ of Swietenia mahagoni L. from different tree parameters such as DBH and tree height of mahogany plantations in the northeastern region of Bangladesh. A total of 850 healthy and well formed trees were selected randomly for sampling in the five study sites. Then, twenty two models were developed based on different statistical criteria that propose reliable and accurate models for estimating the $A_0$ and $M_0$ using non-destructive measurements. The results exposed that model iv and xv were selected on a single predictor of DBH and showed more statistically accuracy than other models. The selected models were also validated with an additional test data set on the basis of linear regression and t-test for mean difference between observed and predicted values. After that, a comparison between the best logarithmic and non-linear allometric model shows that the non-linear model produces systematic biases and underestimates $A_0$ and $M_0$ for larger trees. As a result, it showed that the bias-corrected logarithmic model iv and xv can be used to help quantify forest structure and functions, particularly valuable in future research for estimating $A_0$ and $M_0$ of S. mahagoni in this region.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.17 no.2
• /
• pp.131-140
• /
• 2004

It really needs fuzzy decision making of integrity assessment considering about both durability and load carrying capacity for maintenance and administration, such as repairing and reinforcing. This thesis shows efficient models about reinforced concrete structure using CART-ANFIS. It compares and analyzes decision trees parts of expert system, using the theory of fuzzy, and applying damage & diagnosis at reinforced concrete structure and decision trees of integrity assessment using established artificial neural. Decided the theory of reinforcement design for recovery of durability at damaged concrete ＆ the theory of reinforcement design for increasing load carrying capacity keep stability of damage and detection. It is more efficient maintenance and administration at reinforced concrete for using integrity assessment model of this study and can carry out predicting cost of life cycle.