• Journal of the Korea Computer Graphics Society
• /
• v.27 no.1
• /
• pp.9-17
• /
• 2021

In this paper, we present a simple and fast supervised learning framework based on model predictive control so as to learn motion controllers for a physic-based character to track given example motions. The proposed framework is composed of two components: training data generation and offline learning. Given an example motion, the former component stochastically controls the character motion with an optimal controller while repeatedly updating the controller for tracking the example motion through model predictive control over a time window from the current state of the character to a near future state. The repeated update of the optimal controller and the stochastic control make it possible to effectively explore various states that the character may have while mimicking the example motion and collect useful training data for supervised learning. Once all the training data is generated, the latter component normalizes the data to remove the disparity for magnitude and units inherent in the data and trains an artificial neural network with a simple architecture for a controller. The experimental results for walking and running motions demonstrate how effectively and fast the proposed framework produces physics-based motion controllers.

• The Journal of Internal Korean Medicine
• /
• v.23 no.1
• /
• pp.1-4
• /
• 2002

Objective : Hyperhomocysteinemia has been proven to be an independent risk factor for stroke. The genetic mutation of methylenetetrahydrofolate reductase(MTHFR) elevates serum homocysteine level, but it still remains controversial whether the MTHFR gene mutation could be a predictor of ischemic stroke. Therefore, we studied if this genetic defect could cause ischemic stroke independently. Methods : We gathered ischemic stroke subjects and age, sex-matched controls. Age, gender, past medical history, smoking habit, serum homocysteine level, and the MTHFR genotype were recorded. General characteristics of ischemic stroke subjects were compared to the controls. We classified the stroke according to the related vessels(small and large artery infarction) and single lesion and multiple infraction. Relevant risk of the MTHFR genotype was evaluated in each stroke subtype with multiple logistic regression analysis. Results : When the controls were compared to the whole ischemic stroke, there was no specific difference except some medical histories. However, further analysis based on stroke subtypes showed important results. The small artery infarction group, multiple infraction group had significant odds ratio of the MTHFR TT genotype adjusted for age, gender, medical history and smoking habit. Conclusions : The MTHFR TT genotype is an independent risk factor for certain types of ischemic stroke, small artery infarction and multiple infarction.

• Health Policy and Management
• /
• v.22 no.2
• /
• pp.263-274
• /
• 2012

This study describes the hypertensive patients characteristics associated with the health incentive point program, and develops and analyzes a simple predictive model of participation in the program. Based on the Incheon Chronic Disease Management System(iCDMS), a model program of community partnership for hypertensive or diabetic patients detection and follow-up since 2005 in Incheon metropolitan city, a cross-sectional design was used in this study. An effective 10.844 adults sample was divided into groups according to participation in the health incentive point program and continuing treatment, and individual and health characteristics among groups were compared. Furthermore, the predictors associated with participation in the program were identified by the logistic regression analysis. After the health incentive point program in iCDMS was introduced, the number of hypertensive patients participation in the program increased 23.9 times which is vastly high given the various programs were provided. There were statistically significant differences among the groups: age(p=0.000), treatment compliance(p=0.000), and blood pressure control at the last measurement(p=0.000), in particular, between participation group(GroupI, n=246) and non-participation group(GroupIII, n=10,408). Furthermore, age over 60 years(OR: 0.33), treatment compliance(OR: 3.49~3.78) and blood pressure controls(OR: 2.13~2.30) were statistically significant predictors associated with participation in the program, based on the logistic regression analysis with GroupI and GroupIII. To increase participation in the health incentive point program, variables such as age, treatment compliance and blood pressure controls are more concerned. And, high-risk patients and family members need targeted health incentive programs.

• YAKHAK HOEJI
• /
• v.49 no.1
• /
• pp.44-50
• /
• 2005

The purpose of this study was to investigate the relationship between Trp64Arg polymorphism in the ${\beta}_3$-adrenergic receptor gene and complex phenotypes such as blood pressure, body compositions and bone parameters in young men about 20 years, and to collect the fundamental data in designing the exercise program. Eighty healthy young men including 41 controls and 39 athletes were recruited, Trp64Arg polymorphism in the ${\beta}_3$-adrenergic receptor gene was genotyped by PCR-RFLP method. By association study, there were no significance in genotype and allele frequencies of Trp64Arg polymorphism in the ${\beta}_3$-adrenergic receptor gene between controls and athletes, respectively (p>0.05). When the relationship between physiological parameters and Trp64Arg polymorphism in the ${\beta}_3$-adrenergic receptor gene was tested, this polymorphism was significantly associated with 3th lumber and left femoral neck Z-score values in controls (p<0.05), but these associations were not detected in athletic groups (p>0.05). It is likely that Trp64Arg polymorphism in the ${\beta}_3$-adrenergic receptor gene is a genetic marker for the bone mineral density index in young men, but environmental factors such as exercise modify the significant effect of this polymorphism. Thus, our results suggest that Trp64Arg polymorphism in the ${\beta}_3$-adrenergic receptor gene may be applicable as a predictive marker for osteoporosis in Korean young men, and regular exercise may prevent the disadventageous effect of this polymorphism for bone mineral density in male athletic group.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.36 no.2
• /
• pp.79-87
• /
• 1994

A real-time flood forecasting system(FLOFS) was developed for the real-time and predictive determination of flood discharges and stages, and to aid in flood management decisions in the Keum River Estuary Dam. The system consists of three subsystems : data subsystem, model subsystem, and user subsystem. The data subsystem controls and manages data transmitted from telemetering systems and simulated by models. The model subsystem combines various techniques for rainfall-runoff modeling, tidal-level forecasting modeling, one-dimensional unsteady flood routing, Kalman filtering, and autoregressivemovingaverage(ARMA) modeling. The user subsystem in a menu-driven and man-machine interface system.

• Proceedings of the KIEE Conference
• /
• 1996.07b
• /
• pp.1031-1033
• /
• 1996

Now is an automation age. Therefore it is required that machine can do work which was done by men. Artificial Neural Network was developed by the necessity of this purpose. This paper shows a Predictive Control with a Neural Network. The Neural Network learns an Inverted Pendulum in various situations. Then, it has a power to predict the next state after accept the current state. And the Neural Network directs the Bang-Bang Controller to give input to a plant. It seems like that a human expert looks the state of a plant and then controls the plant. It is used a Feedforward Neural Network and shown control state according to the learning. We could get a satisfactory results after complete learning.

• Journal of Food Hygiene and Safety
• /
• v.35 no.5
• /
• pp.495-502
• /
• 2020

Processing fresh produce into fresh-cut products increases the risk of bacterial growth and contamination by breaking the exterior barrier of produce. Our objective in this study was to develop predictive models of Listeria monocytogenes in the fresh-cut salad, fresh-cut pineapple, and frozen mango. Predictive growth and survival models were developed to predict the change of L. monocytogenes populations in the fresh-cut salad (4, 10, 12, 13, 17, 25, and 36℃), fresh-cut pineapple (4, 10, 17, 25, 30, and 36℃), and frozen mango (-2, -10 and -18℃) as a function of temperature. The growth of L. monocytogenes in fresh-cut salad and pineapple was observed at above 13℃ and 10℃, respectively. The growth of L. monocytogenes in pineapple was faster than in salad. The delta value of L. monocytogenes in frozen mango increased as the storage temperature decreased. The results indicate that L. monocytogenes behave differently according to the physicochemical properties of fresh-cut fruits and vegetables. Since L. monocytogenes grow and survive well in refrigerated and frozen conditions, management programs and preventive controls for the processing of fresh-cut produce should be effectively implemented to enhance the safety of fresh-cut fruits and vegetables at retail markets.

• Journal of Internet Computing and Services
• /
• v.1 no.2
• /
• pp.29-37
• /
• 2000

Asynchronous transfer mode is flexible to support multimedia communication services using asynchronous time-sharing and statistical multimedia techniques to the existing data communication area, ATM ABR service controls network traffic using feedback information on the network congestion situation in order to guarantee the demanded service qualities and the available cell rates, In this paper we apply the control method using queue length prediction to the formation of feedback information for more efficient ABR traffic control. If backward node receive the longer delayed feedback information on the impending congestion, the switch can be already congested from the uncontrolled arriving traffic and the fluctuation of queue length can be inefficiently high in the continuing time intervals, The feedback control method proposed in this paper predicts the queue length in the switch using the slope of queue length prediction function and queue length changes in time-series, The predicted congestion information is backward to the node, NLMS and neural network are used as the predictive control functions, and they are compared from performance on the queue length prediction. Simulation results show the efficiency of the proposed method compared to the feedback control method without the prediction, Therefore, we conclude that the efficient congestion and stability of the queue length controls are possible using the prediction scheme that can resolve the problems caused from the longer delays of the feedback information.

• Korean Journal of Psychosomatic Medicine
• /
• v.15 no.1
• /
• pp.44-50
• /
• 2007

Objectives: previous studies have suggested the possible predisposing personality in fibromyalgia(FM). The aim of this study is to investigate the personality traits in female patients with FM compared to healthy female controls using the Temperament and Character Inventory(TCI) and furthermore, to evaluate the personality traits affecting the severity of the symptoms of FM. Methods Forty female patients with FM and 40 healthy female controls were examined using the TCI and the Hamilton depression rating scale. The FM patients were also evaluated the severity of the symptoms of FM using the fibromyalgia impact questionnaire(FIQ). Results : ANCOVA with age and depression levels as covariates showed that the FM patients scored significantly higher on the harm avoidance(F=2.187, p=0.047) and lower on the self-directedness(F=4.551, p=0.036) than the healthy controls. The FIQ scores showed positive correlation with the harm avoidance scores in the FM patients when adjusting for age and depression level(R=0.399, p=0.013) Multiple linear regression models revealed that the harm avoidance scores would affect the FIQ scores in FM patients(95% Cl=0.004-1.942, p=0.049). Conclusions : These results suggest that the female FM patients have distinctive temperament and character dimensions compared to the healthy female controls. Moreover, the harm avoidance may be the predictive personality to affect the severity of the symptoms of female FM patients.

• Asian Pacific Journal of Cancer Prevention
• /
• v.14 no.12
• /
• pp.7433-7438
• /
• 2013

Aim: To identify new biomarkers for NPC diagnosis with an anti-EBV Western blot test kit. Methods: Serum samples from 64 NPC patients and healthy subjects with four specific VCA-IgA/EA-IgA profiles were tested with an anti-EBV Western blot test kit from EUROIMMUN AG. Proteins were quantified with scores of intensity visually assigned to the protein bands. The markers which showed statistical differences between the NPC and non-NPC subjects were further evaluated in another 32 NPC patients and 32 controls in comparison with established biomarkers including VCA-IgA, EA-IgA, EBV-related protein IgG, and EBV DNA. Results: Among the markers screened, EA-D p45-IgG showed a statistically significant difference (p < 0.05) between NPC and non-NPC subjects with VCA-IgA positivy. In 32 VCA-IgA positive NPC patients and 32 control subjects, the diagnostic accuracy of EA-D p45-IgG was 78.1% with a positive predictive value of 77.8% and a negative predictive value of 78.6%. In the verification experiment, the specificity and sensitivity of EA-D p45-IgG were 75.0% and 90.6 %, respectively. Conclusions: EA-D p45-IgG might be a potential biomarker for NPC diagnosis, especially among VCA-IgA positive subjects.