Modeling Time Series for Prediction of Thalassemia in Nineveh Governorate

Abstract

The aim of this research is to analyze the time series of Thalassemia cancer cases by making assumptions on the number of cases to formulate the problem to find the best model for predicting the number of patients in Nineveh governorate using (Box and Jenkins) method of analysis based on the monthly data provided by Al Salam Hospital in Nineveh for the period (2014-2018). The results of the analysis showed that the appropriate model of analysis is the Auto-Regressive Integrated Moving Average (ARIMA) (2,1,0) and based on this model the number of people with this disease was predicted for the next two years where the results showed values ​​consistent with the original values which indicates the good quality of the model.

Study Estimating hourly traffic flow using Artificial Neural Network: A M25 motorway case

“…In [3], the author categorizes the various methods of short-term traffic prediction into the categories of time series analysis, function approximation, optimization, pattern recognition, and clustering. Popular parametric approaches include the ARIMA model [4,5], non-ARIMA time series models [6,7], support vector regression [8,9], and neural networks [10,11]. As examples of non-parametric approaches, we can look at graphical models [4,12] and Bayesian inference [12,13].…”

“…Popular parametric approaches include the ARIMA model [4,5], non-ARIMA time series models [6,7], support vector regression [8,9], and neural networks [10,11]. As examples of non-parametric approaches, we can look at graphical models [4,12] and Bayesian inference [12,13]. Recent nonparametric studies in this field have made use of deep learning (see [9][10] for examples).…”