1 April 2023 in International Journal of Electrical and Computer Engineering (IJECE)
Water pollution is one of the most serious environmental problems in Malaysia. The most notable occurrence of pollution happened in Selangor. Currently, there are various water quality monitoring (WQM) methods to observe the quality of water. One of the methods used is the internet of things (IoT) for wireless sensor network technology to obtain real-time data measurement. In this study, the developed WQM system is equipped with a sensor that can measure total dissolved solid (TDS) and electrical conductivity (EC). Arduino UNO was used in this system as a microcontroller to interact with the sensor. The Wi-Fi module, ESP8266, was used to transfer the collected data to ThingSpeak, which acts as a cloud to store all the data. The results showed that both sample populations can be discriminated since the p-value is greater than 0.05 in the normality test, while in the paired sample t-test, the p-value is less than 0.05. In conclusion, this research provides an easier way to monitor water quality by taking up less time at less cost, as well as being reliable in giving real-time data reading.
19 November 2015 in IOP Conference Series: Materials Science and Engineering
Dry rubber content (DRC) is one of main material existing inside latex. It is usually in ranged of 25% - 45% of rubber latex. Statistical analysis are done to determine the discrimination of dry rubber content of latex between healthy and white root infected rubber tree. Based on 150 rubber trees and 10 clones tested, parametric test which include normality test, error-bar plot, and paired samples test are done. The result outcomes have shown that both data of dry rubber content of latex for healthy and white root infected rubber tree are normally distributed. Error-bar plot test is clearly indicated that there is visible discrimination between both cases. Paired samples test are done to reinforce this findings in terms of numerical p- value which is found to be less than 0.05. Thus, this indicate overwhelming evidence that healthy group can be discriminated from white root. Conclusively, changes in DRC content in latex can be correlated with white root disease infections of rubber tree.
1 January 2013 in International Journal on Smart Sensing and Intelligent Systems
This paper presents a study in an efficient methodology for analysis and characterization of digital images psoriasis lesions using Daubechies D8 wavelet technique. The methodology is based on the transformation of 2D Discrete Wavelet Transform (DWT) algorithm for Daubechies D8 at first level to obtain the coefficients of the approximations and details sub-images. For classification method, statistical approach analysis is applied to identify significance difference between each groups of psoriasis in terms of mean and standard deviation parameter. Results performances are concluded by observing the error plots with 95% confidence interval and applied independent T-test. The test outcomes have shown that approximate mean and standard deviation parameter can be used to distinctively classify erythroderma from the other groups in consistent with visual observations of the error plots. Whilst, in order to discriminate guttate from the other groups, standard deviation parameters for horizontal, vertical and diagonal can be utilized. Based on the results, plaque is distinguishable with guttate and erythroderma by using standard deviation vertical sub-images parameter. Results of Daubechies D8 is compared with study done previously by using Daubechies D4 and Daubechies D12 in order to observe the reliability of the results in Daubechies families. The resultant parameters can be used to design computer-aided system in diagnosis the skin lesion of psoriasis.
19 November 2015 in IOP Conference Series: Materials Science and Engineering
ASAhmad Faiz Mohd Sampian
NKNoor Aishah Khairuzzaman
+1
The most serious disease known in rubber industry is root disease and among the major root diseases, white root is the most destructive agent of trees and agricultural crops. Since, it is too difficult and expensive to treat root disease infection on trees; prevention is important whereby one must rely on symptoms appearing on roots themselves in order to recognize the disease. Infection symptom on the tree is detected when leaves became discolored yellowish and dying. The main objective of this work is to investigate empirically an infected rubber trees infected by white root disease where its symptom could be detected visually from leaves gradual discolouration. Visible spectrum of optical measurements is taken on four different regions of interest (ROI) locations of the top side leaf sample features such as petiolule, main vein/midrib, vein and leaf cell of rubber trees. Statistical techniques is used to analyse for conclusive scientific findings of which ROIs above has shown clear discrimination between the healthy, medium and worst condition. The scope of work involves raw data inclusion of leaf samples belong only to 2025 rubber tree clone. This clone is recommended by Rubber Research Institute of Malaysia (RRIM) management due to its popularity and commercially used by small scale planters. Outcomes of this work has suggested that only main vein/midrib and leaf cell ROIs produced convincing significant discrimination between healthy, medium and worst case. Thus, their measurements can be recommended for developing on the shelf technology engineering sensor instrument using non-invasive advanced signal processing techniques and intelligent system for early detection of white root disease.
1 July 2020 in Indonesian Journal of Electrical Engineering and Computer Science
White root disease is one of the most serious diseases in rubber plantation in Malaysia that originally infects on the root surface of the rubber tree. So, prevention is important compared to treatment. The classification system proposed in the research had the ability of detecting the disease by classifying between healthy rubber trees and white root disease infected rubber trees. 600 samples of latex from healthy rubber trees and white root disease infected rubber trees were taken from the RRIM station in Kota Tinggi, Johor. These samples were measured based on its relative permittivity and capacitance. All of the measurement inputs from the experiment were tested using statistical analysis. These measurement input were then went through the process of classification in ANN to generate the optimized models by using LM and SCG algorithm. There were four optimized models selected from the classification process. The accuracy from the selected most optimized models were greater than 70%. The selected most optimized models were then used to classify between healthy trees and white root infected trees based on single input categories.