A batch variable learning rate gradient descent algorithm is proposed to efficiently train a neuro-fuzzy network of zero-order Takagi-Sugeno inference systems. By using the advantages of regularization, the smoothing L1/2 regularization is utilized to find more appropriate sparse network. Combining the second-order information of the smoothing error function, a variable learning rate is chosen along the steep descent direction, which avoids line search procedure and may reduce the cost of computation. In order to appropriately adjust the Lipschitz constant of the smoothing error function in the learning rate, a new scheme is proposed by introducing a hyper-parameter. Also the article applies the modified secant equation for estimating the Lipschitz constant, which makes the algorithm greatly reduce the oscillating phenomenon and improve the robustness. Under appropriate assumptions, a convergent result of the proposed algorithm is also given. Simulation results for two identification and classification problems show that the proposed algorithm has better numerical performance and promotes the sparsity capability of the network, compared with the common batch gradient descent algorithm and a variable learning rate gradient-based algorithm.

Objectives To analyze the possible factors causing fatty liver in children based on ultrasound data of children in south Texas, and to establish machine learning models of fatty liver in children to provide ideas for the prevention and treatment of fatty liver in children. Methods The binary classification model of fatty liver problem in obese children in Texas was established under the multiple model. First, we selected important features using the CatBoost algorithm. Second, the best parameters of the algorithm were selected on the training set and the validation set by using the grid search method, and all six models were tested on the test set. The six models then were compared by area under the curve value, precision, accuracy, recall rate, and F1 score in a model evaluation. Then, two algorithms, logic regression and CatBoost, were selected to establish prediction models of fatty liver disease in children. Results We selected body mass index, height, liver size, kidney volume, glomerular filtration rate, and liver diameter as the features used in the machine learning model. The prediction models we chose showed that children with higher body mass index at the same age tended to have a greater probability of fatty liver. Conclusions Based on the analysis of the results of the two prediction models established by logistic regression and CatBoost, we determined that the mean probability of fatty liver in severely obese children was between 74.47% and 92.22%, 73.45% and 85.41% in obese children, and slightly higher in boys than in girls, with a mean difference of 3.00% to 3.95%.

With the emergence and development of application requirements such as data analysis and publishing, it is particularly important to use differential privacy protection technology to provide more reliable, secure, and compliant datasets for research in the field of children’s health. This paper focuses on the differential privacy protection of the ultrasound examination health dataset of adolescents in southern Texas from three aspects: differential privacy protection with output perturbation on basic statistics, publication of differential privacy marginal histogram and synthesized data, and a machine learning differential privacy learning algorithm. Firstly, differential privacy protection results with output perturbation show that Laplace and Gaussian mechanisms for numerical data, as well as the exponential mechanism for non-numerical data, can achieve the goal of protecting privacy. The exponential mechanism provides higher privacy protection. Secondly, a differential privacy marginal histogram with four attributes can be obtained with an appropriate privacy budget that approximates the marginal histogram of the original data. In order to publish synthetic data, we construct a synthetic query to obtain the corresponding differential privacy histogram for two attributes. Further, a synthetic dataset can be constructed by following the data distribution of the original dataset and the quality of the synthetic data publication can also be evaluated by the mean square error and error rate. Finally, consider a differential privacy logistic regression model under machine learning to predict whether children have fatty liver in binary classification tasks. The experimental results show that the model combined with quadratic perturbation has better accuracy and privacy protection. This paper can provide differential privacy protection models under different demands, which provides important data release and analysis options for data managers and research organizations, in addition to enriching the research on child health data releasing and mining.

A comprehensive attribute assessment model is proposed for evaluating teaching quality of all teaching units in a university. By establishing the Index System of undergraduate teaching level of Ordinary colleges and Universities in China and using the attribute assessment system and the objective weight, the teaching quality of all teaching units is evaluated. The ranking and the evaluation grade for units are presented. It shows that the model is feasible and reliable for evaluating teaching quality. Furthermore, the assessment presented could give references for related teaching administers.