Abstract
According to the World Health Organisation, three to five million individuals are infected by influenza, and around 250,000 to 500,000 people die of this infectious disease worldwide. Influenza epidemics pose a serious public health threat. Moreover, graver dangers are encountered with influenza subtypes against which there is little or no preexisting human immunity. Such subtypes of influenza have the potential to cause devastating epidemics. Thus, enhancing surveillance systems for the purpose of detecting influenza epidemics in an early stage can quicken response times and save millions of lives. This paper presents three adapting intelligence models: support vector machine regression (SVMR), artificial neural network using particle swarm optimisation (ANNPSO), and our intelligent time series (INTS) to predict influenza epidemics. The novelty of the current study is that it proposes a new intelligent model to predict influenza outbreaks. The INTS model combines clustering with a time series model to enhance the prediction of influenza outbreaks. The innovation of our proposed model integrates the results obtained from the existing weighted exponential smoothing model with centroids obtained from clustering. We developed a surveillance system for influenza epidemics using Google search queries. The current research is based on a weighted version of the Center for Disease Control and Prevention influenza-like illness activity level obtained from the Center for Disease Control and Prevention data, as well as query data obtained from the Goggle search engine in the USA. The influenza-like illness data was collected from January 4, 2009 (week 1), to December 27, 2015 (week 52), stretching across a total time span of 312 weeks. Google Correlate was used to select search queries related to influenza epidemics. In total, 100 search queries were obtained from Google Correlate, 10 of which were better and more relevant search queries selected in this study. The model was evaluated using online Google search queries collected from Google Correlate. Standard measure performance MSE, RMSE, and MAE were employed to estimate the results of the proposed model. The empirical results of the INTS model showed MSE = 0.003, RMSE = 0.036, and MAE = 0.0185, indicating that the errors of the proposed model are very limited. A comparative model of predicting results between the INTS model, alternative Google Flu Trend (GFT), and autoregression with Google search data is also presented. The proposed model outperformed the existing models.
Highlights
With the rapid development of societies and economies worldwide, health technologies have been enhanced, and health facilities have been promoted as well. e flu infection faces societies with a number of health problems.influenza diseases have still posed a great threat to human health, and controlling influenza diseases has become a very important challenge globally
Our analyses used the data from January 4, 2009 to December 27, 2015 across a total period of 312 weeks, covering 7 years of the Center for Disease Control (CDC) data. e CDC data are uploaded to Google Correlate, obtaining 100 search query terms that are related to the influenza epidemic
Analysis of the INtelligent Time Series (INTS) Model. e Weighted Exponential Smoothing algorithm was applied to search terms obtained from Google correlate. e weighted exponential smoothing model depends on the α smoothing constant; it was tested with values from 0.1 to 0.9. e MSE performance measure was scrutinized through the use of these parameters. e α 0.9 parameter was selected as a
Summary
With the rapid development of societies and economies worldwide, health technologies have been enhanced, and health facilities have been promoted as well. e flu infection faces societies with a number of health problems.influenza diseases have still posed a great threat to human health, and controlling influenza diseases has become a very important challenge globally. Many researchers have used huge amounts of data on the Internet and social media platforms such as Twitter or Facebook to discover novel methods to diagnose diseases. Understanding population behaviour and trends of noncommunication diseases is directed by using web search activity data. Noncommunicable diseases have been detected by using web search activity data and examination data that has been submitted to the concerned health officials. In November 2008, Google launched the Google Flu service, which uses a computational search term model to predict influenza activity. In 2009, Google offered Google Flu Trends (GFT), a digital method used to detect public health surveillance [8]. E novelty of the GFT model is that it is used by the Center for Disease Control (CDC) to find specific search terms from digital data for predicting influenza epidemics. Various subsequent studies have modelled their approaches after the GFT model to enhance the GFT model [9,10,11,12]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
