Optimization of sand casting performance parameters and missing data prediction

Due to a wide range of applications, sand casting occupies an important position in modern casting practice. The main purpose of this study was to optimize the performance parameters of sand casting based on grey relational analysis and predict the missing data using back propagation (BP) neural network. First, the influence of human factors was eliminated by adopting the objective entropy weight method, which also saved manpower. The larger variation degree in the evaluation indicators, indicating that the evaluated projects had good discrimination in this regard, the larger weight should be given to these evaluation indicators. Second, the performance parameters of sand casting were optimized based on grey relational analysis, providing a reference for sand milling. The larger the grey relational degree, the closer the evaluated project was to the ideal project. Third, this paper provided a new method for determining the number of hidden neurons in a network according to the mean square error of training samples, and venting quality was predicted based on BP neural network. The relevant theory was deduced before predicting missing data, such that there will be a general understanding regarding the prediction principle of BP neural network. Fourth, to demonstrate the validity of BP neural network adopted in the process of missing data prediction, grey system theory was applied to compare the result of missing data prediction.

CDL4CDRP: A Collaborative Deep Learning Approach for Clinical Decision and Risk Prediction

(1) Background: Recommendation algorithms have played a vital role in the prediction of personalized recommendation for clinical decision support systems (CDSSs). Machine learning methods are powerful tools for disease diagnosis. Unfortunately, they must deal with missing data, as this will result in data error and limit the potential patterns and features associated with obtaining a clinical decision; (2) Methods: Recent years, collaborative filtering (CF) have proven to be a valuable means of coping with missing data prediction. In order to address the challenge of missing data prediction and latent feature extraction, neighbor-based and latent features-based CF methods are presented for clinical disease diagnosis. The novel discriminative restricted Boltzmann machine (DRBM) model is proposed to extract the latent features, where the deep learning technique is adopted to analyze the clinical data; (3) Results: Proposed methods were compared to machine learning models, using two different publicly available clinical datasets, which has various types of inputs and different quantity of missing. We also evaluated the performance of our algorithm, using clinical datasets that were missing at random (MAR), which were missing at various degrees; and (4) Conclusions: The experimental results demonstrate that DRBM can effectively capture the latent features of real clinical data and exhibits excellent performance for predicting missing values and result classification.

Development of missing data prediction model for carbon monoxide

Carbon monoxide (CO) is one of the most important pollutants since it is selected for API calculation. Therefore, it is paramount to ensure that there is no missing data of CO during the analysis. There are numbers of occurrences that may contribute to the missing data problems such as inability of the instrument to record certain parameters. In view of this fact, a CO prediction model needs to be developed to address this problem. A dataset of meteorological and air pollutants value was obtained from the Air Quality Division, Department of Environment Malaysia (DOE). A total of 113112 datasets were used to develop the model using sensitivity analysis (SA) through artificial neural network (ANN). SA showed particulate matter (PM10) and ozone (O3) were the most significant input variables for missing data prediction model of CO. Three hidden nodes were the optimum number to develop the ANN model with the value of R2 equal to 0.5311. Both models (artificial neural network-carbon monoxide-all parameters (ANN-CO-AP) and artificial neural network-carbon monoxide-leave out (ANN-CO-LO)) showed high value of R2 (0.7639 and 0.5311) and low value of RMSE (0.2482 and 0.3506), respectively. These values indicated that the models might only employ the most significant input variables to represent the CO rather than using all input variables.