• Journal of Korean Academy of Nursing
• /
• v.41 no.3
• /
• pp.423-431
• /
• 2011

Purpose: The study was designed to determine the discriminating ability of a Bayesian network (BN) for predicting risk for pressure ulcers. Methods: Analysis was done using a retrospective cohort, nursing records representing 21,114 hospital days, 3,348 patients at risk for ulcers, admitted to the intensive care unit of a tertiary teaching hospital between January 2004 and January 2007. A BN model and two logistic regression (LR) versions, model-I and .II, were compared, varying the nature, number and quality of input variables. Classification competence and case coverage of the models were tested and compared using a threefold cross validation method. Results: Average incidence of ulcers was 6.12%. Of the two LR models, model-I demonstrated better indexes of statistical model fits. The BN model had a sensitivity of 81.95%, specificity of 75.63%, positive and negative predictive values of 35.62% and 96.22% respectively. The area under the receiver operating characteristic (AUROC) was 85.01% implying moderate to good overall performance, which was similar to LR model-I. However, regarding case coverage, the BN model was 100% compared to 15.88% of LR. Conclusion: Discriminating ability of the BN model was found to be acceptable and case coverage proved to be excellent for clinical use.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.30 no.6_2
• /
• pp.623-629
• /
• 2012

During the construction of crossing engineering one of the important measures to ensure the safety of subway operation is the implementation of deformation surveying to the existing subway tunnel. Guangzhou new subway line 2 engineering which crosses the existing tunnel is taken as the background. How to achieve intelligent and automatic deformation surveying forecast during the subway tunnel construction process is studied. Because large amount of surveying data exists in the subway construction, deformation analysis is difficult and prediction has low accuracy, a subway intelligent deformation prediction model based on the PBIL and support vector machine is proposed. The PBIL algorithm is used to optimize the exact key parameters combination of support vector machine though probability analysis and thereby the predictive ability of the model deformation is greatly improved. Through applications on the Guangzhou subway across deformation surveying deformation engineering the prediction method's predictive ability has high accuracy and the method has high practicality. It can support effective solution to the implementation of the comprehensive and accurate surveying and early warning under subway operation conditions with the environmental interference and complex deformation.

• Journal of the Korean Chemical Society
• /
• v.60 no.4
• /
• pp.225-234
• /
• 2016

The activity of 34 sulfonamide derivatives has been estimated by means of multiple linear regression (MLR), artificial neural network (ANN), simulated annealing (SA) and genetic algorithm (GA) techniques. These models were also utilized to select the most efficient subsets of descriptors in a cross-validation procedure for non-linear -log (IC50) prediction. The results obtained using GA-ANN were compared with MLR-MLR, MLR-ANN, SA-ANN and GA-ANN approaches. A high predictive ability was observed for the MLR-MLR, MLR-ANN, SA-ANN and MLR-GA models, with root mean sum square errors (RMSE) of 0.3958, 0.1006, 0.0359, 0.0326 and 0.0282 in gas phase and 0.2871, 0.0475, 0.0268, 0.0376 and 0.0097 in solvent, respectively (N=34). The results obtained using the GA-ANN method indicated that the activity of derivatives of sulfonamides depends on different parameters including DP03, BID, AAC, RDF035v, JGI9, TIE, R7e+, BELM6 descriptors in gas phase and Mor 32u, ESpm03d, RDF070v, ATS8m, MATS2e and R4p, L1u and R3m in solvent. In conclusion, the comparison of the quality of the ANN with different MLR models showed that ANN has a better predictive ability.

• The Korean Journal of Financial Management
• /
• v.16 no.2
• /
• pp.243-261
• /
• 1999

본 논문은 순이익의 시계열 속성을 조사하고, 순이익의 시계열이 랜덤워크 모형과 일치하는지를 단위근 검증방식을 사용하여 조사하며, 시계열 속성에 근거하여 도출된 예측모형과 흔히 사용되어 온 랜덤워크 모형의 예측능력을 비교하여 선행연구에서 사용되고 있는 랜덤워크 모형에 실증적 타당성을 제시하는 것을 주목적으로 하고 있다. 본 연구는 한국신용평가주식회사의 데이터 베이스에 1980년부터 1996년까지 17년간 자료가 연속적으로 포함되어 있는 금융기업을 제외한 모든 기업(272개)을 표본으로 사용하고 있다. 표본기업의 순이익 시계열에 가장 적합한 과정은 랜덤워크나 AR(1) 또는 AR(2) 모형이다. 또한 본 논문은 대부분의 기업에 때해 순이익이 랜덤워크 과정을 따른다는 가설을 기각할 수 없음을 보였다. 이들 상이한 모형의 표본외 예측력(out-of-sample predictive ability)을 비교한 결과 상수항을 포함한 랜덤워크 모형이 가장 작은 평균 절대 예측오차(mean absolute forecast error)를 갖는 것으로 나타나고 있다. 본 연구는 기존의 연구가 순이익 시계열의 불안정성(nonstationarity) 문제를 무시하거나 명시적으로 다루고 있지 않은 것과는 달리 단위근 검증(unit root test)을 통해 연간 순이익이 대체로 불안정하다는 것을 보였으며, 또한 상이한 모형의 표본외 예측능력을 비교한 결과 선행연구에서 사용하여 온 랜덤워크 모형의 우월성에 대한 실증적 증거를 제공하였다는 데 의의가 있다.

• Proceedings of the KIEE Conference
• /
• 2001.07d
• /
• pp.2699-2701
• /
• 2001

The study is concerned with an approach to the design of a new category of fuzzy neural networks. The proposed Fuzzy Polynomial Neural Networks(FPNN) with hybrid multi-layer inference architecture is based on fuzzy neural networks(FNN) and polynomial neural networks(PNN) for model identification of complex and nonlinear systems. The one and the other are considered as premise and consequence part of FPNN respectively. We introduce two kinds of FPNN architectures, namely the generic and advanced types depending on the connection points (nodes) of the layer of FNN. Owing to the specific features of two combined architectures, it is possible to consider the nonlinear characteristics of process and to get output performance with superb predictive ability. The availability and feasibility of the FPNN is discussed and illustrated with the aid of two representative numerical examples. The results show that the proposed FPNN can produce the model with higher accuracy and predictive ability than any other method presented previously.

• 한국노년학
• /
• v.41 no.3
• /
• pp.295-308
• /
• 2021

This study is a descriptive study conducted to find out the predictive factors according to the level of the frailty of the communitydwelling older adult in a rural area. Data were collected from 400 older adults aged 65 years or older living in rural areas of Gyeongsangnam-do from October 2019 to March 2020. Data were analyzed using logistic regression to examine the predictive factors according to the level of frailty. The results showed that 27.8% for robust older adults, 30.9% for pre-frailty older adults, and 41.3% for frailty older adults. As a result of analyzing the predictive factors according to the level of frailty, the predictors from the robust stage to the pre-frailty stage were grip strength, nutritional status, and depression. The predictive factors for entering the pre-frailty stage into the frailty stage were gender, nutritional status, physical performance ability, and depression. Also, it was found that the predictive factors for entering from the robust stage to the frailty stage were sex, occupation, nutritional status, physical performance ability, and depression. Through this study, it was possible to understand the level of the frailty of the older adults living in rural communities and the effects of multidimensional variables. These results can be used as basic data necessary to find a way to prevent and manage the progression of frailty among older adults in rural areas.

• Journal of dental hygiene science
• /
• v.19 no.4
• /
• pp.220-227
• /
• 2019

Background: This descriptive study aimed to examine the relationship between the 4C core competencies and work ability among dental hygienists. Methods: From November 2018 to January 2019, data were collected-from 190 dental hygienists workong in dental clinics in Busan, Ulsan, and Gyeongsangnam province using structured questionnaires. For the general characteristics of the dental hygienists, frequency and percentage were calculated, and the level of the 4C core competencies and work ability of dental hygienists was calculated using means and standard deviations. A multiple regression analysis was conducted to analyze the effects of the 4C core competencies on work ability. Results: The mean scores for the 4C core competency levels of the dental hygienists were as follows: communication ability 3.34, critical thinking ability 3.41, creative problem-solving 3.40, and collaborative self-efficacy 3.27. Meanwhile the mean score for work ability level was 3.65. The predictive factors influencing work ability were communication ability and cooperative self-efficacy (p<0.001), and the sub-factors of critical thinking ability that affect work ability were sound conferences (p<0.01), intellectual fairness (p<0.05), intellectual enthusiasm (p<0.05), and self-confidence (p<0.001). Finally, the sub-factors of creative problem-solving ability that affect work ability were planning and execution (p<0.01) and performance evaluation (p<0.05). Conclusion: The current study showed that education programs covering the core competencies of dental hygienists, rather than the existing theoretical education program, should be developed and implemented to enhance 4C core competencies that affect work ability.

• Journal of Electrical Engineering and Technology
• /
• v.11 no.6
• /
• pp.1674-1683
• /
• 2016

In this paper, a Finite Control Set Model Predictive Control (FCS-MPC) for a five level cascaded multilevel inverter (CMLI) with reduced switch topology is proposed. Five switches are used here instead of conventionally used eight switches. The main contribution of this paper is to make the MPC controller work for the reduced switch topology using only 19 voltage vectors in place of conventional 61 voltage vectors for a five level CMLI. This simplifies the execution of the MPC algorithm, paving a way for the significant reduction in the computational time. The controller makes use of the excellent ability of MPC to multitask, by adding one more objective which is to reduce the average switching frequency in addition to controlling the load current. This is especially important, since switching losses and therefore switching frequency is significant for high-power applications. The trade-off of this MPC is that the current is not as smooth as the 61 vector scheme, but well within the limits of IEEE standards. The results shown prove that this MPC works well in steady state and dynamic conditions too.

• Molecular & Cellular Toxicology
• /
• v.1 no.3
• /
• pp.157-163
• /
• 2005

Because of their widespread occurrence and substantial biological activity, halogenated aromatic hydrocarbons are one of the important classes of contaminants in the environment. We have performed comparative molecular field analysis (CoMFA) on structurally diverse ligands of Ah (dioxin) receptor to explore the physico-chemical requirements for binding. All CoMFA models have given $q^{2}$ value of more than 0.5 and $r^{2}$ value of more than 0.83. The predictive ability of the models was validated by an external test set, which gave satisfactory predictive $r^{2}$ values. Best predictions were obtained with CoMFA model of combined modified training set ($q^{2}=0.631,\;r^{2}=0.900$), giving predictive residual value = 0.002 log unit for the test compound. We have suggested a model comprises of four structurally different compounds, which offers a good predictability for various ligands. Our QSAR model is consistent with all previously established QSAR models with less structurally diverse ligands. The implications of the CoMFA/QSAR model presented herein are explored with respect to quantitative hazard identification of potential toxicants.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.599-602
• /
• 2003

A new technique is presented to construct predictive models of plasma etch processes. This was accomplished by combining a backpropagation neural network (BPNN) and a random generator (RC). The RG played a critical role to control neuron gradients in the hidden layer, The predictive model constructed in this way is referred to as a randomized BPNN (RG-BPNN). The proposed scheme was evaluated with a set of experimental plasma etch process data. The etch process was characterized by a 2$^3$ full factorial experiment. The etch responses modeled are 4, including aluminum (Al) etch rate, profile angle, Al selectivity, and do bias. Additional test data were prepared to evaluate model appropriateness. The performance of RC-BPNN was evaluated as a function of the number of hidden neurons and the range of gradient. for given range and hidden neurons, 100 sets of random neuron gradients were generated and among them one best set was selected for evaluation. Compared to the conventional BPNN, the proposed RC-BPNN demonstrated about 50％ improvements in all comparisons. This illustrates that the RG-BPNN of multi-valued gradients is an effective way to considerably improve the predictive ability of current BPNN of single-valued gradient.