In this study, we analyze how vitamin D (VD) serum levels flow with latitude and throughout seasons of the year within a population sample over three years, taking into account that VD is mainly photosynthesized in th...In this study, we analyze how vitamin D (VD) serum levels flow with latitude and throughout seasons of the year within a population sample over three years, taking into account that VD is mainly photosynthesized in the skin from sun exposure. Vitamin D levels have been measured in 80,763 patients during 2013, 2014, and 2015. To accomplish the objectives, we first perform some inference tests like two-way Analysis of Variance (ANOVA) followed by post-hoc tests. Secondly, we develop time series techniques including cross correlation calculations. Least than 10% of the sample had healthy VD levels, which should be a fact of public health major concern. The effect of the interaction between the two factors, zones and seasons, was proved by ANOVA. The mean values which are significantly different were determined by post hoc test. Furthermore, we find that mean serum VD levels, measured as 25-hydroxy-VD, follow a seasonal lag pattern of 9 weeks, a delay for minimum and maximum values after the respective equinoxes and daily sunlight duration. Reliable estimates of the population are provided in the present study, since one of the strengths is its huge sample size. We have quantitatively characterized the seasonality of serum vitamin D levels in the Argentine and the seasonal lag pattern has been determined for the study region.展开更多
Correlated multivariate time series prediction is an effective tool for discovering the chang rules of temporal data,but it is challenging tofind these rules.Recently,deep learning methods have made it possible to pred...Correlated multivariate time series prediction is an effective tool for discovering the chang rules of temporal data,but it is challenging tofind these rules.Recently,deep learning methods have made it possible to predict high-dimensional and complex multivariate time series data.However,these methods cannot capture or predict potential mutation signals of time series,leading to a lag in data prediction trends and large errors.Moreover,it is difficult to capture dependencies of the data,especially when the data is sparse and the time intervals are large.In this paper,we proposed a prediction approach that leverages both propagation dynamics and deep learning,called Rolling Iterative Prediction(RIP).In RIP method,the Time-Delay Moving Average(TDMA)is used to carry out maximum likelihood reduction on the raw data,and the propagation dynamics model is applied to obtain the potential propagation parameters data,and dynamic properties of the correlated multivariate time series are clearly established.Long Short-Term Memory(LSTM)is applied to capture the time dependencies of data,and the medium and long-term Rolling Iterative Prediction method is established by alternately estimating parameters and predicting time series.Experiments are performed on the data of the Corona Virus Disease 2019(COVID-19)in China,France,and South Korea.Experimental results show that the real distribution of the epidemic data is well restored,the prediction accuracy is better than baseline methods.展开更多
文摘In this study, we analyze how vitamin D (VD) serum levels flow with latitude and throughout seasons of the year within a population sample over three years, taking into account that VD is mainly photosynthesized in the skin from sun exposure. Vitamin D levels have been measured in 80,763 patients during 2013, 2014, and 2015. To accomplish the objectives, we first perform some inference tests like two-way Analysis of Variance (ANOVA) followed by post-hoc tests. Secondly, we develop time series techniques including cross correlation calculations. Least than 10% of the sample had healthy VD levels, which should be a fact of public health major concern. The effect of the interaction between the two factors, zones and seasons, was proved by ANOVA. The mean values which are significantly different were determined by post hoc test. Furthermore, we find that mean serum VD levels, measured as 25-hydroxy-VD, follow a seasonal lag pattern of 9 weeks, a delay for minimum and maximum values after the respective equinoxes and daily sunlight duration. Reliable estimates of the population are provided in the present study, since one of the strengths is its huge sample size. We have quantitatively characterized the seasonality of serum vitamin D levels in the Argentine and the seasonal lag pattern has been determined for the study region.
基金This work was supported by the National Key R&D Program of China under Grant No.2020YFB1710200.
文摘Correlated multivariate time series prediction is an effective tool for discovering the chang rules of temporal data,but it is challenging tofind these rules.Recently,deep learning methods have made it possible to predict high-dimensional and complex multivariate time series data.However,these methods cannot capture or predict potential mutation signals of time series,leading to a lag in data prediction trends and large errors.Moreover,it is difficult to capture dependencies of the data,especially when the data is sparse and the time intervals are large.In this paper,we proposed a prediction approach that leverages both propagation dynamics and deep learning,called Rolling Iterative Prediction(RIP).In RIP method,the Time-Delay Moving Average(TDMA)is used to carry out maximum likelihood reduction on the raw data,and the propagation dynamics model is applied to obtain the potential propagation parameters data,and dynamic properties of the correlated multivariate time series are clearly established.Long Short-Term Memory(LSTM)is applied to capture the time dependencies of data,and the medium and long-term Rolling Iterative Prediction method is established by alternately estimating parameters and predicting time series.Experiments are performed on the data of the Corona Virus Disease 2019(COVID-19)in China,France,and South Korea.Experimental results show that the real distribution of the epidemic data is well restored,the prediction accuracy is better than baseline methods.
