Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/17200
Title: Breast cancer prediction and stock portfolio management using fuzzy neural network
Authors: Hu, ZeXiong.
Keywords: DRNTU::Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
Issue Date: 2009
Abstract: Neural Networks have become increasingly popular in areas of prediction. Typical application in area of financial sector includes prediction of future stock market price. In the area of medical sector, Neural Networks prediction also gains its popularity by proving its accuracy in prediction making. A hybrid intelligent system called Takagi-Sugeno-Kang Type-2 Fuzzy Cerebellar Model Articulation Controller (T2FCMAC-TSK) is introduced in this paper. The Cerebellar Model Articulation Controller (CMAC) [Albus75] is one kind of neural network that provides local generalization and rapid algorithmic computational capabilities. Fuzzy Logic System incorporates into CMAC provides a better interpretation to the network, making the new system a better choice for engineer. Type-2 fuzzy logic concept implemented in the system even better enhance the system in term of uncertainty management, making the system more tolerable to noise and provide more reliable and accurate prediction. In this project, two methods of neural networks are used, the T2FCMAC-TSK and Adaptive Neural Fuzzy Inference System (ANFIS). The main focus of this project is to compare and use these two fuzzy neural network systems as a tool for prediction applications, such as breast cancer prediction and stock price prediction.
URI: http://hdl.handle.net/10356/17200
Rights: Nanyang Technological University
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
HuZeXiong09.pdf
  Restricted Access
1.09 MBAdobe PDFView/Open

Page view(s)

265
checked on Sep 28, 2020

Download(s)

26
checked on Sep 28, 2020

Google ScholarTM

Check

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.