Prevalence of anxiety symptom anddepressive symptom among college students during COVID-19 pandemic: A meta-analysis

Huiwen Jiang, Linghui Li, Hongzhong Si

Abstract: The global pandemic of COVID-19 has brought huge changes to people’s lifestyles, postgraduates have also been affected seriously. Evidence about these significant changes indicated that graduate students were more prone to feel anxious and depressed due to the pressure of scientific research. To derive a precise assessment of the prevalence of anxiety symptom and depressive symptom among graduate students worldwide, we conducted this meta-analysis. Based on the guidance of PRISMA, literature was searched in Pubmed, Web of Science, CNKI, and Wanfang database (last search February 23, 2022). These articles after the screening were analyzed by a random-effects model to estimate the pooled prevalence of anxiety symptom and depressive symptom. Also, subgroup analysis, sensitivity analysis, and publication bias were performed in this meta-analysis.

: Download (free)  CSE-PDF

A PINN-based method for solving the convective diffusion equation

Rujia Liu, Yin Huang, Jieyu Ding

Abstract: Convective diffusion equations are a special class of partial differential equations, and the study of their numerical solution methods has been a hot issue. PINNs (Physics-informed Neural Networks) based on physical information are introduced and applied to solve two-dimensional convective diffusion equations. In contrast to traditional neural network models, PINNs introduce automatic differentiation techniques in the model building process, and compile the physical information, i.e., partial differential equation information, to obtain the optimization objectives of the neural network parameters, i.e., weights and biases, in the model by defining loss functions, which are then solved using existing optimization

: Download (free)  CSE-PDF

Multi-objective prediction of carrier-based aircraft aviation materials based on combinatorial optimization

Aiqing Niu, Jieyu Ding, Feng Guo

Abstract: A single prediction model may have some deviations or even inaccuracies in predicting multiple data. In order to obtain more accurate prediction data of carrier-based aircraft aviation materials, multi-objective genetic algorithm, nsga2 algorithm, multi-objective particle swarm optimization algorithm are used to combinatorial optimization the three prediction models of gray prediction, quadratic exponential smoothing method, and time series three prediction models, and use the optimized model to predict the annual average flight hours, oil pumps, sensors, and seal ring data to obtain more accurate prediction data.

: Download (free)  CSE-PDF