• Korean Journal of Artificial Intelligence
• /
• 제12권2호
• /
• pp.1-7
• /
• 2024

In this paper, we compare three models (logistic regression, Random Forest, and XGBoost) for predicting stroke occurrence using data from the Korea National Health and Nutrition Examination Survey (KNHANES). We evaluated these models using various metrics, focusing mainly on recall and F1 score to assess their performance. Initially, the logistic regression model showed a satisfactory recall score among the three models; however, it was excluded from further consideration because it did not meet the F1 score threshold, which was set at a minimum of 0.5. The F1 score is crucial as it considers both precision and recall, providing a balanced measure of a model's accuracy. Among the models that met the criteria, XGBoost showed the highest recall rate and showed excellent performance in stroke prediction. In particular, XGBoost shows strong performance not only in recall, but also in F1 score and AUC, so it should be considered the optimal algorithm for predicting stroke occurrence. This study determines that the performance of XGBoost is optimal in the field of stroke prediction.

• The Journal of Korean Physical Therapy
• /
• 제36권1호
• /
• pp.21-26
• /
• 2024

Purpose: The study was undertaken to investigate the electromyographic activities of the gluteus maximus (GM), hamstring (HAM), and multifidus (MF) in three different sling locations during bridge exercise in the supine position. Methods: Twenty healthy male subjects participated. An electromyography device was used to measure the muscle activities of the GM, HAM, and MF muscles. Subjects were asked to perform bridge exercises with three different sling locations as follows: 1) Bridge exercise with an ankle sling; BEAS, 2) Bridge exercise with a calf sling; BECS, and 3) Bridge exercise with a knee sling; BEKS in random order. The analysis was conducted using one-way repeated ANOVA and the Bonferroni post hoc. Significance was set at α=0.01. Results: HAM muscle activity was significantly different in the three conditions (BEAS, BECS, BEKS) (adjusted p-value [p_adj]<0.01), and HAM muscle activity was significantly smaller during BEKS than during BEAS or BECS (p_adj<0.01). Muscle activity ratio (GM/HAM) during BEKS was significantly greater than muscle activity ratios during BEAS or BECS (p_adj<0.01). Conclusion: BEKS is recommended to inhibit HAM muscle activity and improve the GM/HAM muscle activity ratio.

• Journal of the Institute of Electronics and Information Engineers
• /
• 제52권2호
• /
• pp.141-147
• /
• 2015

The contrast of a display is generally evaluated by using the ratio of the minimum luminance to the maximum luminance of the display. However, this contrast ratio is not matched with perceived contrast because it uses only physical characteristic of display without considering human perceptual characteristics. In this paper, the proposed contrast measure that considers perceptually discriminable brightness within the range of display brightness is suggested. First, the range between the minimum and maximum brightness of display in CIECAM02 color space is calculated to measure the length of perceived brightness for the display. Next, brightness ranges which are perceptually same at each brightness level are determined by applying Weber-Fechner ratio and then, the number of brightness values within each brightness range is counted. Finally, perceptually discriminable brightness is defined as the sum of ratio between the number of brightness values in each brightness range and the perceptual contrast length of the display. In the experiments, preference test using various displays with random brightness patches is performed to evaluate perceived contrast. As a result, the proposed measure is more consistent with human perception than the previous contrast measures.

• Korean Journal of Remote Sensing
• /
• 제34권6_2호
• /
• pp.1229-1238
• /
• 2018

We examined if a state of sea-ice in Bering Sea acts as a prelude of variation in that of Chukchi Sea by using satellites-based Arctic sea-ice concentration time series. Datasets consist of monthly values of sea-ice concentration during 36 years (1982-2017). Time series analysis armed with Transfer entropy is performed to describe how sea-ice data in Chukchi Sea is affected by that in Bering Sea, and to explain the relationship. The transfer entropy is a measure which identifies a nonlinear coupling between two random variables or signals and estimates causality using modification of time delay. We verified this measure checked a nonlinear coupling for simulated signals. With sea-ice concentration datasets, we found that sea-ice in Bering Sea is influenced by that in Chukchi Sea 3, 5, 6 months ago through the transfer entropy measure suitable for nonlinear system. Particularly, when a sea-ice concentration of Bering Sea has a local minimum, sea ice concentration around Chukchi Sea tends to decline 5 months later with about 70% chance. This finding is considered to be a process that inflow of Pacific water through Bering strait reduces sea-ice in Chukchi Sea after lowering the concentration of sea-ice in Bering Sea. This approach based on information theory will continue to investigate a timing and time scale of interesting patterns, and thus, a coupling inherent in sea-ice concentration of two remote areas will be verified by studying ocean-atmosphere patterns or events in the period.

• Proceedings of the Technology Innovation Conference
• /
• 기술경영경제학회 1996년도 제10회 동계학술발표회 논문집
• /
• pp.265-295
• /
• 1996

This paper investigates empirically the relationship between various business portfolio properties (particularly technological properties) and chaebol′s performance using data on the 50 largest chaebols in Korea. In addition to the traditional indexes to measure diversification such as entropy index we calculated inter-industry technological similarity using R&D expenditure data by industry and 1990 Input-output Table in Korea, and obtained chaebol-level technological relatedness and internal transaction proportion from chaebols′business profile, inter-industry technological similarity and 1990 input-output table. We applied factor analysis on 13 business portfolio property indexes and showed that they could be grouped into 3 dimensions, diversification scope, inter-business relatedness and degree of vertical integration. In this paper, using 50 largest chaebols′financial data (1989-1994), we analyzed empirically the effect of business portfolio properties on ROS (Return On Sales) which is conventional index for firm performance and on TFP(Total Factor Productivity) growth which is a pure measure of firm performance. To utilize the advantage of panel data, FEM(Fixed Effect Model) and REM(Random Effect Model) were used. The empirical result shows that the entropy index as a measurement of inter-business relatedness is not significant but technological relatedness index is significant. OLS estimates on pooled data were considerably different from FEM or REM estimates on panel data. By introducing interaction effect among the three variables for business portfolio properties, we obtained three findings. First, only VI (Vertical integration) has a significant positive correlation with ROS. Second, when using TFP growth as an dependent variable, both TR(Technological Relatedness) and f[ are significant and positively related to the deepened variable. Third, the interaction term between TR and VI is significant and negatively affects TFP growth, meaning that TR and VI are substitutes. These results suggest strategic directions on restructuring business portfolio. As VI is increased, chaebols will get more profit. A higher level of either TR or W will increase TFP growth rate. but increase in both TR and VI will have a negative effect on TFP growth. To summarize, certain business portfolio properties such as VI and TR can be considered "resources" themselves since they can affect profit rate and productivity growth. VI and TR have a synergy effect of change in profit rate and productivity growth. VI increases ROS and productivity growth, while TR increases productivity growth representing a technological synergy effect.

• Journal of Digital Convergence
• /
• 제15권11호
• /
• pp.245-250
• /
• 2017

Flash floods is defined as the flooding of intense rainfall over a relatively small area that flows through river and valley rapidly in short time with no advance warning. So that it can cause damage property and casuality. This study is to establish the flash-flood warning system using 38 accident data, reported from the National Disaster Information Center and Land Surface Model(TOPLATS) between 2009 and 2012. Three variables were used in the Land Surface Model: precipitation, soil moisture, and surface runoff. The three variables of 6 hours preceding flash flood were reduced to 3 factors through factor analysis. Decision tree, random forest, Naive Bayes, Support Vector Machine, and logistic regression model are considered as big data methods. The prediction performance was evaluated by comparison of Accuracy, Kappa, TP Rate, FP Rate and F-Measure. The best method was suggested based on reproducibility evaluation at the each points of flash flood occurrence and predicted count versus actual count using 4 years data.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• 제13권9호
• /
• pp.4098-4106
• /
• 2012

This study aims to investigate the effect of trunk muscle strengthening exercises on balance performance of sitting posture and muscle tone, targeting the children with spastic diplegic cerebral palsy. 16 children with spastic diplegic cerebral palsy in IV phase of GMFCS were sampled at random and the tests were conducted for 6 weeks, 3 times per week. For experimental groups, only trunk muscle strengthening exercises were conducted and for control groups, only basic physical therapy was conducted. The trunk muscle strengthening exercise consisted of 2 exercises to strengthen abdominal muscles and back muscles. BPM(Balance Performance Monitor) was used to measure balance performance and MMAS(Modified Modified Ashworth Scale) was used to measure muscle tone. As a result, the changes of sitting balance performance in experimental groups and control groups show significant difference in the changes of sway path and sway velocity(p<.05), the comparison of changes in sitting balance performance in between experimental groups and control groups show significant difference in the changes of sway path and sway velocity(p<.05). Knee flexor muscles and hip adductor muscles in both groups show no significant difference in changes of the muscle tone(p>.05). Therefore, the balance performance in both experimental groups and control groups was improved. However, the experimental group had more significant improvement in balance performance and no change in muscle tone was detected in both groups. Thus, these findings show trunk muscle strengthening exercises are effective in improving the balance performance of sitting posture for the children with spastic diplegic cerebral palsy without changing muscle tone.

• Journal of the Korea Convergence Society
• /
• 제9권5호
• /
• 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.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• 제19권4호
• /
• pp.81-99
• /
• 2020

Origin-destination data have been collected and utilized for demand analysis and service design in various fields such as public transportation and traffic operation. As the utilization of big data becomes important, there are increasing needs to store raw origin-destination data for big data analysis. However, it is not practical to store and analyze the raw data for a long period of time since the size of the data increases by the power of the number of the collection points. To overcome this storage limitation and long-period pattern analysis, this study proposes a methodology for compression and origin-destination data analysis with the compressed data. The proposed methodology is applied to public transit data of Sejong and Seoul. We first measure the reconstruction error and the data size for each truncated matrix. Then, to determine a range of principal components for removing random data, we measure the level of the regularity based on covariance coefficients of the demand data reconstructed with each range of principal components. Based on the distribution of the covariance coefficients, we found the range of principal components that covers the regular demand. The ranges are determined as 1~60 and 1~80 for Sejong and Seoul respectively.

• Journal of Home Health Care Nursing
• /
• 제13권1호
• /
• pp.54-60
• /
• 2006

This study, a quasi-experimental study using a nonequivalent control group pretest-posttest design. conducted a survey on 30 patients test group and control group of IS patients sampling an adjacent population at random - who are operated on the breast cancer and are in the A University Hospital located in Suwon, to examine into the effects of foot reflex zone massage on their pain and sleep satisfaction through the nursing interventions. It gave them a foot reflex zone massage for the total 30 minutes-basic massage 10 minutes and reflex massage 20 minutes required to alleviate their pain day in day out covering a two-month period from the first of July to the first of September 2004. for the purpose of collecting data. It launched into a two-round foot reflex zone massage at 6 and 24 hours since mastectomy through a direct visit at the hospital room to measure pain intensity, physiological index(pulse and blood pressure) and sleep satisfaction of them. The results are as follows. First, it showed that there is all the difference between pain intensity of test group and that of control group. In result, the first hypothesis, pain of test group. which measure at 6(p=.000) and 24 hours(p=.001) since mastectomies, will be bigger than that of control group, was established. Second, it showed that there is all the difference between physiological index of test group and that of control group. In result. the second hypothesis, pulse(p= .025, p= .002), systolic blood pressure(p= .004, p=.012) and diastolic blood pressure(p=.004. p= .003) of test group, which investigate at 6 and 24 hours since mastectomies, will be bigger than that of control group, was established. Third, it showed that there is a significant difference between sleep satisfaction of test group and that of control group(p=.000). In result, the fourth hypothesis, sleep satisfaction of test group. which examine in the morning after mastectomies, will be bigger than that of control group, was established. In the result. a foot reflex zone massage is seen to be effective in the pain reduction and sleep promotion of patients who are operated on breast cancer, and in providing them with more qualitative care by improving confidence between them and nurses through a physical touch. Also, it can be applied to a clinical examination through an independent nursing intervention.