UUM Electronic Theses and Dissertation
UUM ETD | Universiti Utara Malaysian Electronic Theses and Dissertation
FAQs | Feedback | Search Tips | Sitemap

Predicting Production of Crude Palm Oil Based on Weather Attributes

Ong, Ei Lin (2009) Predicting Production of Crude Palm Oil Based on Weather Attributes. Masters thesis, Universiti Utara Malaysia.

[thumbnail of Ong_Ei_Lin.pdf] PDF
Restricted to Registered users only

Download (2MB) | Request a copy
[thumbnail of 1.Ong_Ei_Lin.pdf]

Download (97kB) | Preview


In hydrological cycle, water is the important source for rainfall forecasting. Hence,rainfall forecasting becomes a critical issue in equatorial country like Malaysia. Rainfall
can affect environment and plantation activities and agriculture in Malaysia.In Malaysia,Meteorological Department collects weather information for each state in Malaysia.Rainfall prediction is important because it can produces the useful information to the palm oil production and recommending appropriate prevention climate change such as floods warning advise as well as managing water resource operations. For instances,Malaysian Palm Oil Board (MPOB) has given a lot of information about the palm oil production and its effect due to the climate changes. In this study, the analysis on weather data from the year 1996-2005 for five states such as Kedah, Kelantan, Malacca, Penang and Perak was carried out. In the initial study, regression analysis has been conducted to determine the relationship of the weather attributes and palm oil variable such as Fresh Fruit Bunches, Oil Extraction Rate and Crude Palm Oil production. However, the results
were not so encouraging, therefore CBR approach has been attempted to solve the current problem then reuse the information and knowledge based that have been stored in the
cases. The similarity measurement can be determined effectively between cases.Therefore, similarity measurement between cases in the rainfall and palm oil case base is
the important element in CBR. The performance of each similarity measure is evaluated based on attribute’s weight, and classification accuracy, In general, the similarity values achieved at most is 99.33%.

Item Type: Thesis (Masters)
Supervisor : UNSPECIFIED
Item ID: 1576
Uncontrolled Keywords: Artificial Intelligence, Case-Based Reasoning, Palm Oil Production, Rainfall Forecasting
Subjects: Q Science > QA Mathematics > QA299.6-433 Analysis
Divisions: College of Arts and Sciences (CAS)
Date Deposited: 23 Feb 2010 06:44
Last Modified: 24 Jul 2013 12:12
Department: College of Art and Sciences
URI: https://etd.uum.edu.my/id/eprint/1576

Actions (login required)

View Item
View Item