Simple Search:

Developing an Expert System to Predict the Effect of Selective Logging on Large Mammals


Citation

Eldin Ismail, Moutasim Gammar (2001) Developing an Expert System to Predict the Effect of Selective Logging on Large Mammals. Masters thesis, Universiti Putra Malaysia.

Abstract / Synopsis

Expert systems have started to play an important role in this era of knowledge. As we move from information age to knowledge age, management and organization of human expertise will have a great impact in all aspects of life in terms of time saving and money. An expert system (ES) to predict the effect of selective logging on large mammals was developed through a combination of results from field survey, interviews with domain experts and data from Department of Wildlife and National Parks, Malaysia. The field survey was carried out for track identification of four large mammals (barking deer, sambar deer, tapir and wild boar), vegetation and microclimate measurements. ANOVA analysis of variance, regression and sensitivity analysis were used to test the data. The problems related to selective logging and the various aspects of its effects on large mammals were translated into specific rules and incorporated into the ES. The data and information were stored in databases, which can be updated and referred to in the ES . The program provides information for courses and teaching purposes as well as acting as advisor to draw conclusions. In addition to this it helps wildlifers and foresters on decision making on the effect of selective logging on large mammals.


Download File

[img] PDF
FK_2001_32_A.pdf

Download (1MB)

Additional Metadata

Item Type: Thesis (Masters)
Subject: Expert systems (Computer science)
Call Number: FK 2001 32
Chairman Supervisor: Mohamed Bin Daud, PhD, MBA.
Divisions: Faculty of Engineering
Depositing User: Nur Kamila Ramli
Date Deposited: 09 Jun 2011 01:40
Last Modified: 09 Jun 2011 01:40
URI: http://psasir.upm.edu.my/id/eprint/11008
Statistic Details: View Download Statistic

Actions (login required)

View Item View Item