The study of raw water based on quality parameter using smell-print sensing device

Water is a renewable natural resource and comprises about 70% of earth whilst the balance is land. Cleanliness and purity of drinking water is important for human health worldwide, thus it is important to know the water body source content so that consumption of it does not give any risk to human bo...

Full description

Saved in:
Bibliographic Details
Main Authors: Suziyanti, Zaib, Muhammad Sharfi, Najib, Suhaimi, Mohd Daud, Nurdiyana, Zahed, Muhamad Faruqi, Zahari, Nur Farina, Hamidon Majid, Mujahid, Mohamad, Hadi, Manap
Format: Conference or Workshop Item
Language:English
English
Published: Springer, Singapore 2020
Subjects:
Online Access:http://umpir.ump.edu.my/id/eprint/32772/1/The%20study%20of%20raw%20water%20based%20on%20quality%20parameter.pdf
http://umpir.ump.edu.my/id/eprint/32772/2/The%20study%20of%20raw%20water%20based%20on%20quality%20parameter%20.pdf
http://umpir.ump.edu.my/id/eprint/32772/
https://doi.org/10.1007/978-981-15-2317-5_17
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Water is a renewable natural resource and comprises about 70% of earth whilst the balance is land. Cleanliness and purity of drinking water is important for human health worldwide, thus it is important to know the water body source content so that consumption of it does not give any risk to human body’s health. This study focuses on establishing a case library profile and classification of water based on recommended by Ministry of Health (MOH). This study water quality parameters such as iron (Fe) and pH is obtained using Electronic nose (E-nose). E-nose is an instrument that mimics human nose that has the ability to sniff in advance for volatile odor. However, colourless and odourless chemical usually undetectable by normal eyes or noses. Case Based Reasoning (CBR) is used in performing the intelligent classification that involved CBR computation, voting and performance measure. The similarity result shows that the technique accomplished to classify with 97.5% accuracy, 88.0% specificity and 92.2% accuracy.