Data mining is multidisciplinary process involving computer science, artificial intelli- gence, and machine learning. The aim of data mining is discovering knowledge from a vast amount of data. This process consists of a set of stages forming a pipeline. This pipeline process consists of multiple steps: 1) Finding the right data source and collecting a substantial amount of data, 2) extracting features from the collected data to be fed into training models, 3) train different machine learning algorithms and fine tune hyperparam- eters, 4) and finally measure model performances based on specific metrics. This pipeline process is well-defined and is being applied to a wide range of disciplines from computer vision, voice recognition, text mining, and more. Healthcare informatics is an important discipline where machine learning applications aim to improve decision making, and quality of life. With preliminary work focusing on solving problems of different types including predictive modeling, feature extraction, and sentiment analysis with regards to various forms of data. This thesis demonstrates advancements in other disciplines that could be deployed to the healthcare informatics field, and adapted for possibly for better training and performance.

Creator

• Al-Bahrani, Reda

DOI

• https://doi.org/10.21985/n2-bdvx-ny16

Subject

• Computer science

Language

• en

Alternate Identifier

• etdadmin_upload_631418
• http://dissertations.umi.com/northwestern:14485

Date created

• 2018-01-01

Resource type

• Dissertation

Rights statement

• In Copyright