• 생물환경조절학회지
• /
• 제1권1호
• /
• pp.52-60
• /
• 1992

The optimum management of nutrient solution needs the effective combination of fertilizers as well as the accurate control of nutrient solution. This study was attempt to make a supporting system for effective fertilizer combination by using computer and also to develop a EC predicting equation for keeping the EC of solution within the allowable range after application of combined fertilizers. The supporting system consists of three parts : (1) data bases, (2) rules for deciding the kinds and amounts of fertilizers and (3) main control. With input data, the main control automatically constructs the network connecting the related data bases and subsequently executes the operation of searching proper fertilizers through it. For more effective searching, fertilizers are classified into two levels(level 1 and level 2) in consideration of solubility, price, and frequency in use, and searched in that order. The EC prediction equation, a extended form of the Robinson and Stroke's theoretical equation only available for a binary electrolyte, is suggested for predicting the EC of the nutrient solution containing many kinds of inorganic compounds. The comparison of predicted and measured ECs showed good agreements with the high correlation between the predicted EC decrement by ion interaction and the actual one(limiting EC minus measured EC).

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2022년도 추계학술발표대회
• /
• pp.55-56
• /
• 2022

Hypertension is a severe health problem and increases the risk of other health issues, such as heart disease, heart attack, and stroke. In this research, we propose a machine learning-based prediction method for the risk of chronic hypertension. The proposed method consists of four main modules. In the first module, the linear interpolation method fills missing values of the integration of gas and meteorological datasets. In the second module, the OrdinalEncoder-based normalization is followed by the Decision tree algorithm to select important features. The prediction analysis module builds three models based on k-Nearest Neighbors, Decision Tree, and Random Forest to predict hypertension levels. Finally, the features used in the prediction model are explained by the DeepSHAP approach. The proposed method is evaluated by integrating the Korean meteorological agency dataset, natural gas leakage dataset, and Korean National Health and Nutrition Examination Survey dataset. The experimental results showed important global features for the hypertension of the entire population and local components for particular patients. Based on the local explanation results for a randomly selected 65-year-old male, the effect of hypertension increased from 0.694 to 1.249 when age increased by 0.37 and gas loss increased by 0.17. Therefore, it is concluded that gas loss is the cause of high blood pressure.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2023년도 춘계학술발표대회
• /
• pp.417-419
• /
• 2023

Hypertension is one of the leading causes of mortality worldwide. In recent years, the incidence of hypertension has increased dramatically, not only among the elderly but also among young people. In this regard, the use of machine-learning methods to diagnose the causes of hypertension has increased in recent years. In this study, we improved the prediction of hypertension detection using Mahalanobis distance-based multivariate outlier removal using the KNHANES database from the Korean national health data and the COVID-19 dataset from Kaggle. This study was divided into two modules. Initially, the data preprocessing step used merged datasets and decision-tree classifier-based feature selection. The next module applies a predictive analysis step to remove multivariate outliers using the Mahalanobis distance from the experimental dataset and makes a prediction of hypertension. In this study, we compared the accuracy of each classification model. The best results showed that the proposed MAH_RF algorithm had an accuracy of 82.66%. The proposed method can be used not only for hypertension but also for the detection of various diseases such as stroke and cardiovascular disease.

• 디지털융복합연구
• /
• 제19권9호
• /
• pp.257-269
• /
• 2021

논문은 심탄도(BCG, Ballistocardiogram) 센서를 이용하여 생체신호 데이터를 비침습, 무구속적인 방식으로 수집하고, ICT 기술과 고성능 컴퓨팅 환경에서 인공지능 기계학습 알고리즘을 활용하여 데이터 기반 혈당 예측 알고리즘 모델 개발 및 검증하는 방법을 제시하고 연구하는 것이다. 혈당수치 예측모델은 MLP 아키텍처에 입력노드는 심박수, 호흡수, 심박출량, 심박변이도, SDNN, RMSSD, PNN50, 나이, 성별이며, 은닉층 7개를 사용하였다. 실험 결과는 5회 실험한 학습데이터의 평균 MSE, MAE 및 RMSE 값은 각각 0.5226, 0.6328 및 0.7692이며 검증데이터 평균 값은 각각 0.5408, 0.6776, 0.7968이었으며, 결정계수(R2) 수치는 0.9997의 결과를 보였다. 데이터를 기반으로 한 혈당수치를 예측하는 모델을 표준화하고 데이터셋 수집과 예측 정확성을 검증하는 연구가 계속적으로 진행된다면 비침습 방식의 혈당 수준 관리에 활용될 수 있을 것으로 사료된다.

• Journal of Chest Surgery
• /
• 제21권6호
• /
• pp.979-983
• /
• 1988

Calcium channel blockers may prevent myocardial injury during cardioplegia and reperfusion. This study was done to evaluate the effects of diltiazem cardioplegia on myocardial protection during ischemic arrest and recovery of myocardial function after reperfusion. Four formulations of crystalloid cardioplegic solutions, GIK solution[group I, n=12], diltiazem[lug/ml GIK] in GIK solution[group II, n=7], ],diltiazem[2ug/ml GIK] in GIK solution[group III, n=6] and diltiazem[4ug/ml GIK] in GIK solution[group IV, n=6] were compared in isolated working rat heart subjected to a long period [2 hours] of hypothermic arrest with multi-dose infusion. Diltiazem cardioplegia[group II, III and IV]was found to be superior in nearly all aspects. Diltiazem cardioplegia showed faster recovery of regular rhythm and lower incidence of ventricular fibrillation than group I did. In comparing mechanical function in all experimental hearts, the mean postischemic recoveries of aortic flow, cardiac output, peak aortic pressure, stroke volume and stroke work[expressed as a percentage of its preischemic control] were significantly greater in group II, III and IV[diltiazem cardioplegia] than in group I. The infused amount of cardioplegic solution was more increased by the addition of diltiazem to GI K solution. [p < 0.01] Creatine kinase leakage tended to be lower in hearts receiving diltiazem cardioplegia, especially in group III and IV[p<0.05] than in those receiving GIK solution only[group I]. Diltiazem cardioplegia results in the increased flow of cardioplegic solution and the decreased ischemic injury of myocardium during ischemic arrest and the improved recovery of myocardial function after reperfusion, and a dose-response relation must be established before clinical use.

• 대한기계학회논문집
• /
• 제18권2호
• /
• pp.467-478
• /
• 1994

This paper deals with dynamic behaviors of a free-piston Vuilleumier heat pump system, which are characterized by stroke of each diplacer/stroke ratio, operating frequency and phase angle. Based on the Isothermal Model, basic equations of motion are derived and linearized. In particular, dependence of damping coefficients of the dynamic parameters are taken into account in the formulation, which does not bring additional difficulties in the analysis. In order to investigate effects of design conditions on the dynamic parameters are taken into account in the formulation, which does not bring additional difficulties in the analysis. In order to investigate effects of design conditions on the dynamic characteristics, calculations are performed for the prototype made by Schulz and Thomas and results are qualitatively compared with their data obtained from the analysis as well as the experiment. It appears that they made a mistake in evaluating the hysteresis loss of the gas spring in their analysis. And, the present results show a better agreement with their experimental data than those by their own analysis. Although there are some unresolved aspects such as frequency variations with respect to the mean pressure and the hot space temperature, it is expected that the present analysis may be an effective tool for prediction of dynamics of a free- pistion VM machine at the preliminary design stage.

• 오토저널
• /
• 제13권2호
• /
• pp.67-87
• /
• 1991

The computer program which predicts the gas exchange process of multi-cylinder 4-Stroke cycle spark-ignition engine, can be great assistance for the design and development of new engine. In this study, the computer program was developed to predict the gas exchange process of multi-cylinder four stroke cycle spark ignition engine including intake and exhaust systems. When gas exchange process is to be calculated, the evaluation of the variation of the thermo-dynamic properties with time and position in the intake and exhaust systems is required. For the purpose, the application of the generalized method of characteristics to the gas exchange process is known as one of the method. The simulation model developed was investigated to the analysis of the branch system of multi-cylinder. The models used were the 2-zone expansion model and single zone model for in cylinder calculation and the generalized method of characteristic including area change, friction, heat transfer and entropy gradients for pipe flow calculation. The empirical constants reduced to least number as possible were determined through the comparison with the experimented indicator diagram of one particular operation condition and these constants were applied to other operating condition. The predicted pressures in cylinder were compared with the experimental results over the wide range of equivalence ratio and ignition timing. The predicted values have shown good agreement with the experimental results. The thermodynamic properties in the intake and exhaust system were predicted over the wide range of equivalence ratio and ignition timing. The obtained results can be summarized as follows. 1. Pressures in the exhaust manifold have a little influence on the equivalence ratio, a great influence on the ignition timing. 2. Pressures in the inlet manifold are nearly unchanged by the equivalence ratio and the ignition timing. 3. In this study, the behaviors of the exhaust temperature, gas in the exhaust manifold were ascertained.

• 한국한의학연구원논문집
• /
• 제13권2호통권20호
• /
• pp.59-63
• /
• 2007

The purpose of this study was to diagnosis that what patterns identification using the statistical method. Discriminant analysis using the medical specialist and resident pattern identification agree case in stroke patients within 1 month of onset. The agreement rate of dificiency of Gi(75%), heat-transformation(74%), dampphlegm syndrome(69%), deficiency of Eum(51%) and syndrome of blood stagnation(43%) are respectively 0.75, 0.74, 0.69, 0.51 and 0.43 in medical specialist and using linear discriminant function pattern identification are same. The study of inspection, pulse feeling and palpitation will be continued to evaluate concordance rate. Discrimination model will be make to get higher Accuracy and prediction, it means becomes the help in pattern identification diagnosis objectivity and scientific.

• 한국건설순환자원학회논문집
• /
• 제4권2호
• /
• pp.195-202
• /
• 2016

콘크리트의 펌핑에는 일반적으로 피스톤 펌프를 많이 사용한다. 충진율은 피스톤 펌프의 실린더 부피와 실린더 내에 채워지는 콘크리트의 부피비를 의미한다. 따라서 콘크리트 펌핑에서 토출량과 펌핑 효율에 직접적으로 영향을 미치는 인자라고 할 수 있다. 하지만 아직까지 이에 대한 정확한 분석은 이루어지지 않고 있다. 이 연구에서는 기존에 수행된 350m와 548m 수평배관 펌핑 실험 데이터를 바탕으로 콘크리트의 유동특성, 토출량, 그리고 스트로크 시간과 콘크리트펌프 충진율과의 관계를 파악하였다. 또한 콘크리트의 유동특성과 스트로크 시간으로부터 충진율을 계산할 수 있는 모델을 제안하였다.

• Physical Therapy Rehabilitation Science
• /
• 제7권2호
• /
• pp.54-60
• /
• 2018

Objective: Persons with chronic stroke fall more often than healthy elderly individuals. The Timed Up and Go test (TUG) is used as a fall prediction tool, but only provides a result for the total measurement time. This study aimed to determine the optimal cut-off values for each of the 6 components of the TUG. Design: Retrospective study. Methods: Thirty persons with chronic stroke participated in the study. TUG evaluation was performed using a wearable miniaturized inertial sensor. Sensitivity, specificity, and predictive values were calculated using the Receiver Operating Characteristic (ROC) curve analysis for the measured values in each section. Optimal values for fall risk classification were determined. Logistic regression analysis was used to investigate the risk of future falls based on TUG. Results: The cut-off values of the 6 sections of the TUG were determined, as follows: sit-to-stand >2.00 seconds (p<0.05), forward gait >4.68 seconds (p<0.05), mid-turn >3.82 seconds (p<0.05), return gait >4.81 seconds (p<0.05), end-turn >2.95 seconds (p<0.05), and stand-to-sit >2.13 seconds (p<0.05). The risk of falling increased by 2.278 times when the mid-turn value was >3.82 seconds (p<0.05). Conclusions: The risk of falls increased by 2.28 times when the value of the mid-turn interval exceeded 3.82 seconds. Therefore, when interpreting TUG results, the predictive accuracy for falls will be higher when the measurement time for each section is analyzed, together with the total time for TUG.