신경망과 의사결정 나무를 이용한 충수돌기염 환자의 재원일수 예측모형 개발

At present, patients whose have suffered from stroke in Thailand are increasing every year. Stroke impairments relate to many functions such as sensory, motor function, communication, visual and emotional function which depend on brain's lesion. Physical examinations and assessments are important for planning the rehabilitation programs. For this reason, there are several information for medical decision making. Missing some data for treatment planning may occur. To solve this problem, the proposed study used two algorithms to determine the proper rehabilitation treatment program. Artificial Neural Networks and Decision Trees models were considered. Sensitivity, specificity and accuracy values were computed to define the performance of both algorithms. The results of this study indicated that both techniques can apply for data classification and define the proper treatment programs. However, the results were shown that the specificity and accuracy of decision trees model were higher than neural network model.

Global warming and climate change have become universal issues recently. One of the leading sources of climate change is automobiles. Automobiles are the prime source of air pollution in urban areas globally. This has resulted in a problematic and chaotic state in the development of an automatic traffic management system for capturing and monitoring vehicles’ hourly and daily passage. With the significant advancement of sensor technology, atmospheric information such as air pollu-tion, meteorological, and motor vehicle data can be harvested and stored in databases. However, due to the complexity and non-linear associations between air quality, meteorological, and traffic variables, it is difficult for the traditional statistical and mathematical models to analyze them. Recently, machine learning algorithms in the field of traffic emissions prediction have become a popular tool. Meteorological and traffic variables influence the variation and the trend of the traffic pollutants. In this paper, an optimized artificial neural network (OANN) was developed to enhance the existing artificial neural network (ANN) model by updating the initial weights in the network using a Genetic Algorithm (GA). The OANN model was implemented to predict the concentration of CO, NO, NO2, and NOx pollutants produced by motor vehicles in Kuala Lumpur, Malaysia. OANN was compared with Artificial Neural Network (ANN), Random Forest (RF), and Decision Tree (DT) models. The results show that the developed OANN model performed better than the ANN, RF, and DT models with the lowest MSE values of 0.0247 for CO, 0.0365 for NO, 0.0542 NO2, and 0.1128 for NOx. It can be concluded that the developed OANN model is a better choice in predicting traffic emission concentrations. The developed OANN model can help environmental agencies monitor traffic-related air pollution levels efficiently and take necessary measures to ensure the effectiveness of traffic management policy. The OANN model can also help decision-makers mitigate traffic emissions to protect citizens living in the neighborhood of highways.

The bank telemarketing dataset was collected by a Portuguese retail bank when selling a bank long-term deposits product. In order to predict the success of bank telemarketing, an more accurate approach was proposed. Firstly, the dataset was analyzed and processed. The features value of the dataset could be divided into two kinds: continuous variable and categorical variable. The two kinds of variable had been processed with different methods. The continuous variables were transformed to discrete features and then were normalized. The categorical variables were coded with two different methods according to whether they were belong to the ordered categories. The missing value of features had to been processed with two different methods depending on the examples number of the missing value. Secondly, the three data mining models which were support vector machine, neural network and decision trees were adopted to predict the result of the processed bank telemarketing dataset. The classification and regression trees algorithm was adopted in the decision trees model. The BFGS algorithm had been used when the neural network model was programming. The simple sequential minimal optimization (SMO) algorithm was adopted in the support vector machine model. All the three models were executed using python 2.7 and conducted in a Windows7 PC, with an Intel Cerelon G1630 2.80 GHz processor. The results of three models were analyzed and compared. The decision trees presented the best results and cost the least time, and its accuracy, precision, recall value and AUC area of the were all equal to 1.0. It showed that decision trees could predict 100% correct rate. The accuracy, recall value and AUC area of the neural network were better than those obtained by the support vector machine (improvement of 1.5 pp, 2.7 pp and 5 pp respectively), but the neural network cost almost 4.4 times more time than the support vector machine. It showed that not only choosing the data mining models but also processing datasets in advance played a key role in obtaining better prediction results when datasets needed classifying.

1. In this study, neural network (NN) and response surface (RS) models were developed to investigate the response [average daily gain (ADG) and feed efficiency (FE)] of young broiler chickens to dietary protein and lysine. For this purpose, data on their responses to dietary protein and lysine were extracted from the literature and separate NN and RS models were constructed. 2. Comparison between the NN and RS models revealed higher accuracy of prediction with the NN models compared to the RS models. In terms of R 2 values, the NN models developed for both ADG (R 2 = 0.923) and FE (R 2 = 0.904) were far superior to the RS models (R 2 for ADG = 0.511; R 2 for FE = 0.67). This suggests that the NN models can serve as an alternative option to conventional regression approaches including use of RS models. 3. Optimisation of the NN models developed for response to protein and lysine showed that diets containing 220.7 (g/kg of diet) protein and 12.85 (g/kg of diet) lysine maximise ADG, whereas maximum FE is achieved with diets containing 241.3 and 13.12 (g/kg) protein and lysine, respectively. Based on the optimisation results, optimal dietary protein and lysine concentrations for maximum FE in broiler chickens during the starting period are higher than for ADG.

A comparison of 4 predictive models of calving assistance and difficulty in dairy heifers and cows

Comparison of artificial neural network and decision tree models in estimating spatial distribution of snow depth in a semi-arid region of Iran

Background: Data mining (DM) is an approach used in extracting valuable information from environmental processes. This research depicts a DM approach used in extracting some information from influent and effluent wastewater characteristic data of a waste stabilization pond (WSP) in Birjand, a city in Eastern Iran. Methods: Multiple regression (MR) and neural network (NN) models were examined using influent characteristics (pH, Biochemical oxygen demand [BOD 5 ], temperature, chemical oxygen demand [COD], total suspended solids [TSS], total dissolved solid [TDS], electrical conductivity [EC] and turbidity) as the regression input vectors. Models were adjusted to input attributes, effluent BOD 5 (BODout) and COD (CODout). The models performances were estimated by 10-fold external cross-validation. An internal 5-fold cross-validation was also used for the training data set in NN model. The models were compared using regression error characteristic (REC) plot and other statistical measures such as relative absolute error (RAE). Sensitivity analysis was also applied to extract useful knowledge from NN model. Results: NN models (with RAE = 78.71 ± 1.16 for BODout and 83.67 ± 1.35 for CODout) and MR models (with RAE = 84.40% ± 1.07 for BODout and 88.07 ± 0.80 for CODout) indicate different performances and the former was better (P < 0.05) for the prediction of both effluent BOD 5 and COD parameters. For the prediction of CODout the NN model with hidden layer size (H) = 4 and decay factor = 0.75 ± 0.03 presented the best predictive results. For BODout the H and decay factor were found to be 4 and 0.73 ± 0.03, respectively. TDS was found as the most descriptive influent wastewater characteristics for the prediction of the WSP performance. The REC plots confirmed the NN model performance superiority for both BOD and COD effluent prediction. Conclusion: Modeling the performance of WSP systems using NN models along with sensitivity analysis can offer better understanding on exploring the most significant parameters for the prediction of system performance. The findings of this study could build the foundation for prospective work on the characterization of WSP operations and optimization of their performances with a view to conducting statistical approaches.

To develop a logistic regression model, artificial neural network (ANN) model and decision tree (DT) model for the progression of mild cognitive impairment (MCI) to Alzheimer's disease (AD) to compare the performance of the three models. A total of 425 patients with MCI were screened from the original cohort. The actual follow up included 361 patients, with AD as the outcome variable. Three kinds of prediction models were developed: a logistic regression model, ANN model and DT model. The performance of all three models was measured with accuracy, sensitivity, positive predictive value and area under the receiver operating characteristic curve. A total of 121 patients with MCI developed AD, and the average conversion rate was 9.49% per year. The ANN model had higher accuracy (89.52 ± 0.36%), area under the receiver operating characteristic curve (92.08 ± 0.12), sensitivity (82.11 ± 0.42%) and positive predictive value (75.26 ± 0.86%) than the other two models. The first five important predictors of the ANN model were, in order, ADL score, age, urine AD-associated neuronal thread protein, alcohol consumption and smoking. For the DT model, they were age, activities of daily living score, family history of dementia, urine AD-associated neuronal thread protein and alcohol consumption. For the logistic regression model, they were age, sex, activities of daily living score, alcohol consumption and smoking. The logistic regression, ANN and DT models performed well at predicting the transition from MCI to AD with ideal stability. However, the ANN model had the best predictive value. Increased age, activities of daily living score, urine AD-associated neuronal thread protein, alcohol consumption, smoking and sex were important factors. Geriatr Gerontol Int 2021; 21: 43-47.

Accurate, real-time models to predict hospital adverse events could facilitate timely and targeted interventions to improve patient outcomes. Advances in computing enable the use of supervised machine learning (SML) techniques to predict hospital-onset infections. The purpose of this study was to trial SML methods to predict urinary tract infections (UTIs) during inpatient hospitalization at the time of admission. In a large cohort of adult hospitalizations in three New York City acute care facilities (N = 897,344), we used two SML methods-neural networks and decision trees-to predict having a hospital-onset UTI using data available and accessible on the first day of admission at healthcare facilities in the United States. Performance for both neural network and decision tree models were superior compared to logistic regression methods. The decision tree model had a higher sensitivity compared to neural network, but a lower specificity. SML methods show potential for automated accurate UTI risk stratification using electronic data routinely available at admission; this could relieve nurses from the burden of having to complete and document additional risk assessment forms in the electronic medical record. Future studies should pilot and test interventions linked to the risk stratification results, such as short nursing educational modules or alerts triggered for high-risk patients.

The molecular regulatory network (MRN) within a cell determines cellular states and transitions between them. Thus, modeling of MRNs is crucial, but this usually requires extensive analysis of time-series measurements, which is extremely difficult to obtain from biological experiments. However, single-cell measurement data such as single-cell RNA-sequencing databases have recently provided a new insight into resolving this problem by ordering thousands of cells in pseudo-time according to their differential gene expressions. Neural network modeling can be employed by using temporal data as learning data. In contrast, Boolean network modeling of MRNs has a growing interest, as it is a parameter-free logical modeling and thereby robust to noisy data while still capturing essential dynamics of biological networks. In this study, we propose a Boolean feedforward neural network (FFN) modeling by combining neural network and Boolean network modeling approach to reconstruct a practical and useful MRN model from large temporal data. Furthermore, analyzing the reconstructed MRN model can enable us to identify control targets for potential cellular state conversion. Here, we show the usefulness of Boolean FFN modeling by demonstrating its applicability through a toy model and biological networks.

Computer-aided Prediction of the ZrO2 Nanoparticles' Effects on Tensile Strength and Percentage of Water Absorption of Concrete Specimens

Background: Nowadays, forecasting models based on nonparametric models have been developed in many branches of science such as mathematics and economics. However, the relatively complicated structure of these models has made them less practical in medical sciences. Objectives: In this study, we investigated the application of a nonparametric regression model to predict the psychological symptoms appearing six months after mild traumatic brain injury. We also made a comparison between the performance of nonparametric regression and artificial neural network models in predicting the psychological symptoms. Methods: In a six-month period during 2015 - 2017, information of 100 mild traumatic patients was included in a prospective cohort study. The data were then divided randomly into two groups of training (n = 50) and testing (n = 50) for 100 times. In the training group, the focus was on 100 artificial neural network and nonparametric regression models. However, in the testing group, a comparison was made between the values obtained using the two final models. To compare the models, the ROC curve and the accuracy rate were finally applied. Results: According to the obtained results, the nonparametric regression model showed an accuracy rate of 91.25% while the neural network model had an accuracy rate of 85.34%. In the experimental set for both neural network and nonparametric regression models, the area under the ROC curve appeared to be 81.51% and 85.73 %, respectively. Conclusions: The nonparametric regression model appeared to be more powerful than the neural network model in predicting psychological symptoms.

IntroductionAs one of the most prevalent chronic diseases in the United States, diabetes, especially type 2 diabetes, affects the health of millions of people and puts an enormous financial burden on the US economy. We aimed to develop predictive models to identify risk factors for type 2 diabetes, which could help facilitate early diagnosis and intervention and also reduce medical costs.MethodsWe analyzed cross-sectional data on 138,146 participants, including 20,467 with type 2 diabetes, from the 2014 Behavioral Risk Factor Surveillance System. We built several machine learning models for predicting type 2 diabetes, including support vector machine, decision tree, logistic regression, random forest, neural network, and Gaussian Naive Bayes classifiers. We used univariable and multivariable weighted logistic regression models to investigate the associations of potential risk factors with type 2 diabetes.ResultsAll predictive models for type 2 diabetes achieved a high area under the curve (AUC), ranging from 0.7182 to 0.7949. Although the neural network model had the highest accuracy (82.4%), specificity (90.2%), and AUC (0.7949), the decision tree model had the highest sensitivity (51.6%) for type 2 diabetes. We found that people who slept 9 or more hours per day (adjusted odds ratio [aOR] = 1.13, 95% confidence interval [CI], 1.03–1.25) or had checkup frequency of less than 1 year (aOR = 2.31, 95% CI, 1.86–2.85) had higher risk for type 2 diabetes.ConclusionOf the 8 predictive models, the neural network model gave the best model performance with the highest AUC value; however, the decision tree model is preferred for initial screening for type 2 diabetes because it had the highest sensitivity and, therefore, detection rate. We confirmed previously reported risk factors and also identified sleeping time and frequency of checkup as 2 new potential risk factors related to type 2 diabetes.

Predicting electricity energy consumption: A comparison of regression analysis, decision tree and neural networks

This study aims to develop the severity-adjusted length of stay(LOS) model for acute stroke patients using data from the hospital discharge survey and propose management of length of stay(LOS) for acute stroke patients and using for Hospital management. The dataset was taken from 23,134 database of the hospital discharge survey from 2004 to 2009. The severity-adjusted LOS model for the acute stroke patients was developed by data mining analysis. From decision making tree model, the main reasons for LOS of acute stroke patients were acute stroke type. The difference between severity-adjusted LOS from the decision making tree model and real LOS was compared and it was confirmed that insurance type and bed number of hospital, location of hospital were statistically associated with LOS. And to conclude, hospitals should manage the LOS of acute stroke patients applying it into the medical information system. Key Words : Acute stroke, Length of stay(LOS), Hospital discharge survey, Datamining, Severity-adjusted