• The Journal of Korea Robotics Society
• /
• v.15 no.3
• /
• pp.269-276
• /
• 2020

As we become an aging society, the number of elderly patients continues to increase. Pressure sores that can easily occur in patients with trauma cause serious socio-economic problems. In general, prevention of bedsores through predicting the patient's posture is being developed. Developed method usually use artificial intelligence techniques to estimate the patient's posture by measured pressure images in the mattress. In this method, it has a problem the reduction of estimation accuracy when posture of patient is changed. Therefore, it is necessary to use the filter of pressure images in the position transition of patient. In this paper, we propose an algorithm to predict the patient's posture, and an algorithm to reduce the ambiguity that can occur in the patient's posture transition section. By obtaining stable data through this algorithm, learning/prediction stability of the neural network can be expected, and prediction performance is improved accordingly. Through experiments, the effectiveness of the algorithm was verified.

• 한국전산유체공학회:학술대회논문집
• /
• 2004.03a
• /
• pp.220-223
• /
• 2004

The initial conditions such as the film thickness and the void fraction at the onset of annular flow are required for the analytical dryout model. The Disturbance Wave Instability model(DWI model) is one of the model describing the Annular-to-Intermittent Flow regime Transition(AIFT). The experimental CHF conditions for the uniformly heated tube were compared with the predictions by the modified Levy model, for which the initial conditions at AIFT were estimated by the DWI model. For the flow through long tubes with small inlet subcooling, the effect of AIFT model on the dryout prediction was little. However, the use of DWI model gave better prediction of CHF in a short tube.

• Proceedings of the KOSOMBE Conference
• /
• v.1992 no.05
• /
• pp.163-166
• /
• 1992

In this study, the extractions of formant and articulately motion trajectorles from Korean diphthongs are performed by using the RISL adaptive linear prediction filter. This enables us to extract spectrum transition of speech signal accurately. This study showes that the RISL algorithm is superior to the Levinson algorithm, specially in transition part of speech.

• Proceedings of the Korea Database Society Conference
• /
• 2010.06a
• /
• pp.187-199
• /
• 2010

Recently, Internet Telephony has become increasingly popular in telecommunication industry. However, previous research on Internet Telephony has focused on analyzing specific Internet Telephony solutions, identifying the Internet Telephony movement itself. The research on prediction models about Internet Telephony adoption has been minimal. The main propose of this study is to develop models for predicting transition intention from using traditional telephones to using Internet Telephony. To do so, this study uses data mining methods to analyze demands in the IT communications market and to provide management strategies for Internet telephony providers. Especially this study uses discriminant analysis, logistic regression, classification tree, and neural nets to develop the prediction models for the Internet Telephony adoption. The models are compared with each other and a superior model is chosen.

• Korean Journal of Remote Sensing
• /
• v.1 no.1
• /
• pp.53-61
• /
• 1985

The purpose of the study is to establish models of land use prediction system for development and management of land resources using remotely sensed data as well as ancillary data in the context of multi-disciplinary approach in the application to CheJoo Island. The model adopts multi-date processing techniques and is a spatial/temporal land-use projection strategy emerged as a synthesis of the probability transition model and the discriminant-annlysis model. A discriminant model is applied to all pixels in CheJoo landscape plane to predict the most likely change in land use. The probability transition model provides the number of these pixels that will convert to different land use in a gives future time increment. The synthetic model predicts the future change in land use and its volume of pixels in the landscape plane.

• Journal of computational fluids engineering
• /
• v.20 no.4
• /
• pp.36-43
• /
• 2015

Accurate prediction of supersonic transition is required for the heat transfer estimation over supersonic double compression ramp flows. Correlation-based transition models were assessed for a supersonic double ramp problem. Numerical results were compared with experimental data from RWTH Aachen University. A parametric study on the nose bluntness was performed using a selected transition model. As the nose bluntness increases, the boundary layer thickness is increased and the triple point of shock interactions moves downstream. The peak magnitude of the heat transfer is consequently decreased with the nose bluntness.

• Journal of Soil and Groundwater Environment
• /
• v.21 no.3
• /
• pp.21-34
• /
• 2016

In the present study, we applied various machine learning techniques comparatively for prediction of subsurface structures based on multiple secondary information (i.e., well-logging data). The machine learning techniques employed in this study are Naive Bayes classification (NB), artificial neural network (ANN), support vector machine (SVM) and logistic regression classification (LR). As an alternative model, conventional hidden Markov model (HMM) and modified hidden Markov model (mHMM) are used where additional information of transition probability between primary properties is incorporated in the predictions. In the comparisons, 16 boreholes consisted with four different materials are synthesized, which show directional non-stationarity in upward and downward directions. Futhermore, two types of the secondary information that is statistically related to each material are generated. From the comparative analysis with various case studies, the accuracies of the techniques become degenerated with inclusion of additive errors and small amount of the training data. For HMM predictions, the conventional HMM shows the similar accuracies with the models that does not relies on transition probability. However, the mHMM consistently shows the highest prediction accuracy among the test cases, which can be attributed to the consideration of geological nature in the training of the model.

• Proceedings of the KIEE Conference
• /
• 1991.07a
• /
• pp.896-899
• /
• 1991

This paper presents the neural network method to predict the Korea composition stock price index. The error back-propagation method is used to train the multi-layer perceptron network. Ten of the various economic indices of the past 7 Nears are used as train data and the monthly transition of the composition stock price index is represented by five output neurons. Test results of this method using the data of the last 18 months are very encouraging.

• Journal of the Korean Crystal Growth and Crystal Technology
• /
• v.7 no.1
• /
• pp.108-116
• /
• 1997

A laboratory experiment was made of critical transition flow modes in Czocllralski convection. Numerical computation was also made to delineate the dynamic transition. The period of temperature oscillation ($t_p$) and the interval of temperature oscillation ($\Delta\theta$) were scrutinized to capture the critical transition regime. The mixed convection parameter was varied in the range of $0.134\le Ra/PrRe^2 \le3.804$. The data from calculation were in good agreement with ones from experiment. The influence of the Prandtl number on the transition was examined for Pr ＝ 910, 4445 and 8889. To understand the transition mechanism, the detailed temperature oscillation modes, the isolines of meridional temperature and the axial velocity profiles were investigated.

• Proceedings of the SAREK Conference
• /
• 2007.11a
• /
• pp.382-386
• /
• 2007

In this study, the qualitative prediction and evaluation of clean room being utilized for mass production of electrronic components have been performed with the help of flow simulation. Compared to the experimental analysis based on measurements of the number of particles, concentration of contaminants and flow characteristics, the numerical analysis used in this study is much cost-effective.