TDDF: HFMD Outpatients Prediction Based on Time Series Decomposition and Heterogenous Data Fusion in Xiamen, China

Cai

2021

Appl Intell

Self Cite

Predicting the number of COVID-19 cases in a geographical area is important for the management of health resources and decision making. Several methods have been proposed for COVID-19 case predictions but they have important limitations in terms of model interpretability, related to COVID-19's incubation period and major trends of disease transmission. To be able to explain prediction results in terms of incubation period and transmission trends, this paper presents the Multivariate Shapelet Learning (MSL) model to learn shapelets from historical observations in multiple areas. An experimental evaluation was done to compare the prediction performance of eleven algorithms, using the data collected from 50 US provinces/states. Results show that the proposed method is effective and efficient. The learned shapelets explain increasing and decreasing trends of new confirmed cases, and reveal that the COVID-19 incubation period in the USA is around 28 days.

Section: Effects On C and Tmentioning

confidence: 99%

COVID-19 cases prediction in multiple areas via shapelet learning

Cai

2021

Appl Intell

Self Cite

“…As an important entrance for users to obtain digital information resources on the Internet, the search engine provides lots of useful information. e search index of specific keywords directly reflects the social attention on infectious diseases [28][29][30]. Hence, MF data and BSI data are considered as exogenous inputs to models.…”

Section: Study Materialsmentioning

confidence: 99%

Short-Term Infectious Diarrhea Prediction Using Weather and Search Data in Xiamen, China

Huang

et al. 2020

Scientific Programming

Self Cite

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.

“…This section introduces existing time series prediction techniques with respect to univariate input 14‐34 and multivariate input 35‐51 . Table 2 lists related studies on disease time series prediction.…”

Section: Literature Reviewmentioning

confidence: 99%

“…To alleviate the problem of data uncertainty, multiple exogenous data sources are collected and fused into the above stochastic methods 35‐41 and learning methods 42‐51 …”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

Dual‐grained representation for hand, foot, and mouth disease prediction within public health cyber‐physical systems

Huang

2020

Softw Pract Exp

Self Cite

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.