Infectious diarrhea has high morbidity and mortality around the world. For this reason, diarrhea prediction has emerged as an important problem to prevent and control outbreaks. Numerous studies have built disease prediction models using large-scale data. However, these methods perform poorly on diarrhea data. To address this issue, this paper proposes a parsimonious model (PM), which takes historical outpatient visit counts, meteorological factors (MFs) and Baidu search indices (BSIs) as inputs to perform prediction. An experimental evaluation was done to compare the short-term prediction performance of ten algorithms for four groups of inputs, using data collected in Xiamen, China. Results show that the proposed method is effective in improving the prediction accuracy.

No abstract

No abstract

The prediction model is a major component within public health cyber‐physical systems, which supports decisions on prevention and control of diseases. Hand, foot, and mouth disease (HFMD) is one of the most common global infectious diseases with the highest incidence rate. Previous HFMD prediction models are mainly based on the time series that counted in equal‐grained time intervals. However, there are details in the time series counted in fine‐grained time intervals. To benefit from both equal‐grained and fine‐grained data, we proposed a dual‐grained representation (DGR) model. The DGR first represents inputted data to temporal patterns. Then, the represented patterns are consolidated to generate predictions. Experimental comparisons of the short‐term prediction performance are figured out by using real outpatient collections in Xiamen, China.

No abstract