• International Journal of Advanced Culture Technology
• /
• v.7 no.1
• /
• pp.8-13
• /
• 2019

Despite technical advances in healthcare, the rates of hospital-acquired pressure injury (HAPI) are still high although many are potentially preventable. The purpose of this study was to determine whether tree-based prediction modeling is suitable for assessing the risk of HAPI in ICU patients. Retrospective cohort study has been carried out. A decision tree model was constructed with Age, Weight, eTube, diabetes, Braden score, Isolation, and Number of comorbid conditions as decision nodes. We used RStudio for model training and testing. Correct prediction rate of the final prediction model was 92.4 and the Area Under the ROC curve (AUC) was 0.699, which means there is about 70% chance that the model is able to distinguish between HAPI and non-HAPI. The results of this study has limited generalizability as the data were from a single academic institution. Our research finding shows that the data-driven tree-based prediction modeling may potentially support ICU sensitive risk assessment for HAPI prevention.

• Geomechanics and Engineering
• /
• v.7 no.4
• /
• pp.403-430
• /
• 2014

Shale gas formations exhibit strong mechanical and strength anisotropies. Thus, it is necessary to study the effect of anisotropy on the hydraulic fracture initiation pressure. The calculation model for the in-situ stress of the bedding formation is improved according to the effective stress theory. An analytical model of the stresses around wellbore in shale gas reservoirs, in consideration of stratum dip direction, dip angle, and in-situ stress azimuth, has been built. Besides, this work established a calculation model for the stress around the perforation holes. In combination with the tensile failure criterion, a prediction model for the hydraulic fracture initiation pressure in the shale gas reservoirs is put forward. The error between the prediction result and the measured value for the shale gas reservoir in the southern Sichuan Province is only 3.5%. Specifically, effects of factors including elasticity modulus, Poisson's ratio, in-situ stress ratio, tensile strength, perforation angle (the angle between perforation direction and the maximum principal stress) of anisotropic formations on hydraulic fracture initiation pressure have been investigated. The perforation angle has the largest effect on the fracture initiation pressure, followed by the in-situ stress ratio, ratio of tensile strength to pore pressure, and the anisotropy ratio of elasticity moduli as the last. The effect of the anisotropy ratio of the Poisson's ratio on the fracture initiation pressure can be ignored. This study provides a reference for the hydraulic fracturing design in shale gas wells.

• Journal of Biosystems Engineering
• /
• v.20 no.4
• /
• pp.343-350
• /
• 1995

In order to design efficient and effective pressure cooling system for fruits and vegetables, a numerical model for temperature prediction of fruits was developed. This model was extended to study the various factors affecting product cooling time, such as product depth, approach air temperature, entering air velocity and initial product temperature. Also, selection of these factors were examined with respect to the efficiency of the pressure cooling system, the overall precooling cost and the final quality of the product. When designing a pressure cooling system for a particular product, the range of the factors must be selected carefully according to the thermal and physiological properties.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.17 no.5
• /
• pp.116-122
• /
• 2008

In order to establish automation or optimization of the machining process, predictions of the forces in machining are often needed. A new model fur farces in milling with the experimental model based on the specific cutting pressure and the Oxley's predictive machining theory has been developed and is presented in this paper. The specific cutting pressure is calculated according to the definition of the 3 dimensional cutting forces suggested by Oxley and some preliminary milling experiments. Using the model, the average cutting forces and force variation against cutter rotation in milling can be predicted. Milling experimental tests are conducted to verify the model and the predictive results agree well with the experimental results.

• Journal of Mechanical Science and Technology
• /
• v.16 no.8
• /
• pp.1144-1153
• /
• 2002

A hybrid performance prediction method is proposed in the present study. A channel diffuser is divided into four subregions: vaneless space, semi-vaneless space, channel, and channel exit region. One-dimensional compressible core flow and boundary layer calculation of each region with an incidence loss model and empirical correlation of residuary pressure recovery coefficient of a channel predict the performance of diffusers. Three channel diffusers are designed and tested for validating the developed prediction method. The pressure distributions from an impeller exit to the channel diffuser exit are measured and discussed for various operating conditions from choke to nearly surge conditions. The strong non-uniform pressure distribution which is caused by impeller-diffuser interaction is obtained over the vaneless and semi-vaneless spaces. The predicted performance shows good agreement with the measured performance of diffusers at a design condition as well as at off-design conditions.

• The Journal of Society for e-Business Studies
• /
• v.23 no.2
• /
• pp.33-47
• /
• 2018

City gas pipelines are buried underground. Because of this, pipeline is hard to manage, and can be easily damaged. This research proposes a real time prediction system that helps experts can make decision about pressure anomalies. The gas pipline pressure data of Jungbu City Gas Company, which is one of the domestic city gas suppliers, time variables and environment variables are analysed. In this research, regression models that predicts pipeline pressure in minutes are proposed. Random forest, support vector regression (SVR), long-short term memory (LSTM) algorithms are used to build pressure prediction models. A comparison of pressure prediction models' preformances shows that the LSTM model was the best. LSTM model for Asan-si have root mean square error (RMSE) 0.011, mean absolute percentage error (MAPE) 0.494. LSTM model for Cheonan-si have RMSE 0.015, MAPE 0.668.

• Atmosphere
• /
• v.27 no.2
• /
• pp.235-249
• /
• 2017

This paper describes methodology verifying near-surface predictability of numerical weather prediction models against the surface synoptic weather station network (SYNOP) observation. As verification variables, temperature, wind, humidity-related variables, total cloud cover, and surface pressure are included in this tool. Quality controlled SYNOP observation through the pre-processing for data assimilation is used. To consider the difference of topographic height between observation and model grid points, vertical inter/extrapolation is applied for temperature, humidity, and surface pressure verification. This verification algorithm is applied for verifying medium-range forecasts by a global forecasting model developed by Korea Institute of Atmospheric Prediction Systems to measure the near-surface predictability of the model and to evaluate the capability of the developed verification tool. It is found that the verification of near-surface prediction against SYNOP observation shows consistency with verification of upper atmosphere against global radiosonde observation, suggesting reliability of those data and demonstrating importance of verification against in-situ measurement as well. Although verifying modeled total cloud cover with observation might have limitation due to the different definition between the model and observation, it is also capable to diagnose the relative bias of model predictability such as a regional reliability and diurnal evolution of the bias.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.26 no.11
• /
• pp.2399-2408
• /
• 2002

A prediction procedure has been developed to evaluate the microtructures and material properties of heat affected zone (HAZ) in pressure vessel steel weld, based on temperature analysis, thermodynamics calculation and reaction kinetics model. Temperature distributions in HAE are calculated by finite element method. The microstructures in HAZ are predicted by combining the temperature analysis results with the reaction kinetics model for austenite grain growth and austenite decomposition. Substituting the microstructure prediction results into the previous experimental relations, the mechanical material properties such as hardness, yielding strength and tensile strength are calculated. The prediction procedure is modified and verified by the comparison between the present results and the previous study results for the simulated HAZ in reactor pressure vessel (RPV) circurnferential weld. Finally, the microstructures and mechanical material properties are determined by applying the final procedure to real RPV circumferential weld and the local weak zone in HAZ is evaluated based on the application results.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.15 no.2
• /
• pp.596-603
• /
• 1991

Fatigue life prediction of pressure vessel is studied analytically using cumulative damage models and linear elastic fracture mechanics method. The stresses are analyzed by finite element method. During operation, the maximum stress occurs at the outside of neck region while fatigue analysis indicates that the bottom of nozzle part has the shortest fatigue life. Previously proposed fatigue life prediction equation and cumulative damage model are modified successfully by introducing reference fatigue modulus. It is found that the modified life prediction equation and damage model are useful for lower stress level application.

• Proceedings of the Korea Concrete Institute Conference
• /
• 2009.05a
• /
• pp.217-218
• /
• 2009

This experimental work is to verify the previously developed prediction model for self-consolidating concrete (SCC) formwork pressure. A new apparatus was devised to simulate formwork pressure in laboratory, and experiments were performed for one SCC mix. The predicted pressure with the calibrated parameters were compared with the pressure measured under continuous and discrete pouring. The calibrated parameters have a specific trend over loading time, and the calculated pressure accurately simulates the real pressure varying over time.