A Data Mining Approach for Forecasting Cancer Threats

Kiage, Benard Nyangena (2015) A Data Mining Approach for Forecasting Cancer Threats. Masters thesis, Jomo Kenyatta University of Agriculture and Technology.

[img] PDF (A Data Mining Approach for Forecasting Cancer Threats)
Nyangena kiage , MSc. 2015.pdf - Accepted Version
Restricted to Repository staff only

Download (1MB) | Request a copy

Abstract

Healthcare facilities have at their disposal vast amounts of cancer patients’ data. The analysis of available data can lead to more efficient decision-making. The challenge is how to extract relevant knowledge from this data and act upon it in a timely manner. To turn into knowledge, efficient computing and data mining tools must be used. This data can aid in developing expert systems for decision support that can assist physicians in diagnosing and predicting some debilitating life threatening diseases such as cancer. Expert systems for decision support can reduce the cost, the waiting time, liberate medical practitioners for more research and reduce errors and mistakes that can be made by humans due to fatigue and tiredness. The process of utilizing health data effectively however, involves many challenges such as the problem of missing feature values, data dimensionality due to a large number of attributes, and the course of actions to determine features that can lead to more accurate diagnosis. Effective data mining tools can assist in early detection of diseases such as cancer. This research proposes a new approach called Information Gain Artificial Neuro-network Fussy Inference System (IG-ANFIS). This approach optimally minimizing the number of features using the information gain (IG) algorithm, then applies the new reduced features dataset to the Adaptive Neuro Fuzzy Inference system (ANFIS). The research also proposes a new approach for constructing missing feature values based on iterative k-nearest neighbours and the distance functions.

Item Type: Thesis (Masters)
Uncontrolled Keywords: Data Mining, Clustering, Classification, Neural networks, Fuzzy Inference system Information gain
Subjects: R Medicine > RA Public aspects of medicine
R Medicine > RA Public aspects of medicine > RA0421 Public health. Hygiene. Preventive Medicine
T Technology > T Technology (General)
Divisions: Africana
Depositing User: Geoffrey Obatsa
Date Deposited: 13 Sep 2017 06:31
Last Modified: 13 Sep 2017 06:31
URI: http://thesisbank.jhia.ac.ke/id/eprint/2070

Actions (login required)

View Item View Item