Investigation of Clustering-Heuristic-based Approach for Interval Fuzzy Type-2 Triangular and Trapezoidal Membership Functions Construction
Virtual Hajj (Hajj Guide Interactive Simulator)
Projects Details
Name of Project:Investigation of Clustering-Heuristic-based Approach for Interval Fuzzy Type-2 Triangular and Trapezoidal Membership Functions Construction
Funding Agency: Ministry of Higher Education Malaysia in collaboration with Universiti Teknologi PETRONAS, Malaysia.
Total Funding Amount: RM 133,237.74 (USD 29,941.08)
Status: Completed
Sub-Project Title: A Novel Fuzzy Type-1 Approach for generating Multiple Membership Function Types through Fuzzy C-Means
Novel Algorithms designed in the project and their implemented form in MATLAB are displayed below:
List of Problems Solved in the Project:
Australian Energy Marketing Operator (AEMO) electricity price forecasting.[Published]
Regression Problems [In Process of Publication]
Alabama University Enrollment
Daily Minimum Temperatures in Melbourne, Australia
Blood Transfusion Service Center, Hsin-Chu, Taiwan
Haberman's Breast Cancer Survival Data from Chicago
Each problem is explained in detail below:
Australian Energy Marketing Operator (AEMO) electricity price forecasting.
Australian Energy Market Operator (AEMO) data for the state of Queensland, Australia, is chosen for forecasting. The data is real-time data that is recorded between 01-01-2002 and 31-01-2002, there are around 1670 instances of data recorded for demand, price, and temperature attributes. Price is forecasted based on historical data.
Data Representation:
Data Preparation:
Dataset is prepared and divided into training and testing data after which the outliners are removed.
Forecasting Results:
Price Forecasting is performed on the dataset and results are presented below:
Regression Problem:
Alabama University Enrollment
Fuzzy Inference System is evaluated against Alabama University Enrollment dataset to validate the accuracy of prediction.Data is taken from the Alabama University Student Enrolment cell for the year 1971 to 1992 and contains 22 instances of data.
Minimum Daily Temperature
Fuzzy Inference System is evaluated against minimum daily temperature record dataset to validate the accuracy of prediction.Data is taken from Melbourne city, Australia from the year 1981 to 1990 and contains 3650 records.
Daily Female Birth Data
Fuzzy Inference System is evaluated against a daily female birth dataset to validate the accuracy of prediction.Data is taken from California, USA during the year 1959 and contains 365 data values.
Monthly Shampoo Sales
Fuzzy Inference System is evaluated against a monthly shampoo sales dataset to validate the accuracy of prediction.It consists of 36 data observation for over 3 years taken from 01-01-2001 to 31-12-2003 and is credited to Makridakis, who recorded the observations from New York.
Classification Problem:
Iris Dataset
Fuzzy Inference System is evaluated against Iris dataset to validate the accuracy of prediction.The data set contains 3 classes of 50 instances each, where each class refers to a type of iris plant.
Banknote Authentication Dataset
Fuzzy Inference System is evaluated against Banknote Authentication dataset to validate the accuracy of prediction.Data were extracted from images that were taken from genuine and forged banknote-like specimens. For digitization, an industrial camera usually used for print inspection was used. Dataset has 4 attributes.
Blood Transfusion Service Center Dataset
Fuzzy Inference System is evaluated against Blood Transfusion dataset to validate the accuracy of prediction.To demonstrate the RFMTC marketing model (a modified version of RFM), this study adopted the donor database of Blood Transfusion Service Center in Hsin-Chu City in Taiwan. The dataset has 4 attributes.
Haberman Breast Cancer Detection Dataset
Fuzzy Inference System is evaluated against the Haberman Breast Cancer Detection dataset to validate the accuracy of prediction.The dataset contains cases from a study that was conducted between 1958 and 1970 at the University of Chicago's Billings Hospital on the survival of patients who had undergone surgery for breast cancer. The dataset has 4 attributes.
2. Name of Project:Virtual Hajj (Hajj Guide Interactive Simulator)
Type of Project: Final Year Project (BS)
Game Engine Used: Unity3D Game Engine
Coding Language: C#.Net
Modelling Software: Blender
Platform: Cross Platform (Android, IOS, VR, Windows Application)
Snippets below show the Interface and Models of the Application