Foodborne Disease DetectionUsing Machine Learning

EasyChair Preprint 4204

Abstract

Foodborne disease outbreak, arises when number of people affected with the same type of illness from the use of the same type of infected food or drinks. Almost 48 million people in the US get ill with Foodborne diseases by using the infected food and drinks per year. Foodborne is not part of well known outbreak disease as outbreaks diseases provides the detailed information of the disease.

In this paper I a used the dataset of Foodborne disease outbreaks containing the data from year 1998 to 2015. It contains the different attributes of the data like year, month, state, location, food, illness etc. Rapid Miner tool of data science is used for the analysis of this dataset, which is one of the best visualizing tool. Three types of algorithms are applied on the dataset. Two types of clustering algorithms are also applied on this dataset.

Keywords---  Data mining, Foodborne disease outbreaks, RapiMiner, Prediction, K-means Clustering, X-means Clustering, Generalized Linear Model, Random Forest, Gradient boosted tree.

Keyphrases: Clustering, Generalized Linear Model, Gradient Boosted Tree, Random Forest

@booklet{EasyChair:4204,
  author    = {Salma Yousaf and Shakeel Khan},
  title     = {Foodborne Disease DetectionUsing Machine Learning},
  howpublished = {EasyChair Preprint 4204},
  year      = {EasyChair, 2020}}