Cover Image

Development of capacitance based rubber tree latex system for white root disease detection / Ahmad Faiz Mohd Sampian

White root infection to rubber tree is a very common problem faced in rubber industry. Once the tree is infected, it will affect latex productivity and eventually died because of nutrient loss taken by the fungus. Detection method of this infection are usually done by expertise evaluation and a lab...

Full description

Saved in:
Bibliographic Details
Main Author: Mohd Sampian, Ahmad Faiz
Format: Thesis
Language:English
Published: 2017
Online Access:https://ir.uitm.edu.my/id/eprint/37576/1/37576.pdf
https://ir.uitm.edu.my/id/eprint/37576/
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.uitm.ir.37576
record_format eprints
spelling my.uitm.ir.375762023-01-26T08:00:11Z https://ir.uitm.edu.my/id/eprint/37576/ Development of capacitance based rubber tree latex system for white root disease detection / Ahmad Faiz Mohd Sampian Mohd Sampian, Ahmad Faiz White root infection to rubber tree is a very common problem faced in rubber industry. Once the tree is infected, it will affect latex productivity and eventually died because of nutrient loss taken by the fungus. Detection method of this infection are usually done by expertise evaluation and a lab test which is not accessible to every rubber tree planters. Thus, due to this fact, this work is done to investigate the detection of white root infection to a rubber tree via rubber latex by measuring its capacitance value with prototype console unit (PCU) developed. Based on the statistical analysis done to 100 normally distributed measurements for healthy and infected samples, there are discrimination between both samples. Discrimination can be seen visually in comparison between error bars and this finding is enforced with the value of paired samples test (p-value) equal to 0.000. An optimized classification model by using ANN is developed and neuron with hidden layer size of 2 is chosen as the best based on accuracy of 82.5% and 5 numbers of connections with threshold of 0.5. Completing this research, a visual interaction system based on optimized model is developed and tested. Based on the 30 samples for each group tested during validation, the system perform considerably good with 78.34% accuracy. 2017 Thesis NonPeerReviewed text en https://ir.uitm.edu.my/id/eprint/37576/1/37576.pdf Development of capacitance based rubber tree latex system for white root disease detection / Ahmad Faiz Mohd Sampian. (2017) Masters thesis, thesis, Universiti Teknologi MARA (UiTM).
institution Universiti Teknologi Mara
building Tun Abdul Razak Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknologi Mara
content_source UiTM Institutional Repository
url_provider http://ir.uitm.edu.my/
language English
description White root infection to rubber tree is a very common problem faced in rubber industry. Once the tree is infected, it will affect latex productivity and eventually died because of nutrient loss taken by the fungus. Detection method of this infection are usually done by expertise evaluation and a lab test which is not accessible to every rubber tree planters. Thus, due to this fact, this work is done to investigate the detection of white root infection to a rubber tree via rubber latex by measuring its capacitance value with prototype console unit (PCU) developed. Based on the statistical analysis done to 100 normally distributed measurements for healthy and infected samples, there are discrimination between both samples. Discrimination can be seen visually in comparison between error bars and this finding is enforced with the value of paired samples test (p-value) equal to 0.000. An optimized classification model by using ANN is developed and neuron with hidden layer size of 2 is chosen as the best based on accuracy of 82.5% and 5 numbers of connections with threshold of 0.5. Completing this research, a visual interaction system based on optimized model is developed and tested. Based on the 30 samples for each group tested during validation, the system perform considerably good with 78.34% accuracy.
format Thesis
author Mohd Sampian, Ahmad Faiz
spellingShingle Mohd Sampian, Ahmad Faiz
Development of capacitance based rubber tree latex system for white root disease detection / Ahmad Faiz Mohd Sampian
author_facet Mohd Sampian, Ahmad Faiz
author_sort Mohd Sampian, Ahmad Faiz
title Development of capacitance based rubber tree latex system for white root disease detection / Ahmad Faiz Mohd Sampian
title_short Development of capacitance based rubber tree latex system for white root disease detection / Ahmad Faiz Mohd Sampian
title_full Development of capacitance based rubber tree latex system for white root disease detection / Ahmad Faiz Mohd Sampian
title_fullStr Development of capacitance based rubber tree latex system for white root disease detection / Ahmad Faiz Mohd Sampian
title_full_unstemmed Development of capacitance based rubber tree latex system for white root disease detection / Ahmad Faiz Mohd Sampian
title_sort development of capacitance based rubber tree latex system for white root disease detection / ahmad faiz mohd sampian
publishDate 2017
url https://ir.uitm.edu.my/id/eprint/37576/1/37576.pdf
https://ir.uitm.edu.my/id/eprint/37576/
_version_ 1756687544987156480
score 13.211869

Similar Items