Mohd Zuli Jaafar

A novel computer-aided multivariate water quality index

A computer-aided multivariate water quality index is developed based on partial least squares (PLS) regression. The index is termed as the partial least squares water quality index (PLS-WQI). Briefly, a training set was computationally generated based on the guideline of National Water Quality Standards for Malaysia (NWQS) to predict the water quality. The index is benchmarked with the well-established index developed by the Department of Environment, Malaysia (DOE-WQI). The PLS-WQI is a continuous variable with the value closer to I indicating good water quality and closer to V indicating poor water quality. Unlike other conventional indexing methods, the algorithm calculates the index in a multivariate manner. The algorithm allows rapid processing of a large dataset without tedious calculation; it can be an efficient tool for spatial and temporal routine monitoring of water quality. Although the algorithm is designed based on the guideline of NWQS, it can be easily adapted to accommodate other guidelines. The algorithm was evaluated and demonstrated on the simulated and real datasets. Results indicate that the algorithm is robust and reliable. Based on six parameters, the overall ratings derived are inversely correlated to DOE-WQI. When the number of parameter is increased, the overall ratings appear to provide better insights into the water quality.

Noninvasive glucose level determination using diffuse reflectance near infrared spectroscopy and chemometrics analysis based on in vitro sample and human skin

Fourier Transform Near Infrared Spectroscopy (FT-NIRS) is a bright method to estimate glucose concentration level by detecting glucose molecular properties in tissue and blood. NIRS technique consists of many method measurements including diffuse reflection method. It capable to predict blood glucose level in human blood noninvasively without pain. However the main weakness of FT-NIRS is the low absorption spectrum of glucose and not a straight forward signal for quantification analysis. Therefore, preprocessing data and chemometrics analysis is required to enhance the spectrum performance and identified certain chemical information present in the sample. The main objective in this paper is to evaluate the potential of low level detection using FT-NIRS towards glucose spectrum in water and intralipid. This study also observed the relationship between human skin spectrums with its blood glucose level value. Utilizing a few preprocessing method and PLS regression technique, Root Mean Square Error Cross Validation (RMSECV) and Coefficient of determination Cross validation (R2CV) were observed to validate the model. RMSECV obtained for glucose in water and intralipid were 47.05 mg/dl (2.6 mmol) and 31.17 mg/dl (1.7 mmol) respectively. Meanwhile R2CV achieved for glucose in water and intralipid were at 0.94 and 0.97 respectively. The Clarke Error Grid shows 97% of the measurement fell within zone A and B. This study has shown that, glucose detection was possible to be monitored in human blood by using FT-NIRS and PLS regression analysis.

Comparison of PLS Discriminant Analysis and supervised SOMs for Blood Brain Barrier activity

In the development of drugs compounds suitable for human being, many experiments have to be conducted to ensure drugs safe consumption and generally takes almost 10 to 12 years for a particular drugs to enter the market from laboratory. Therefore, the pattern recognition in QSAR is significant for analyzing the data and developing several necessary models, so that only novel drugs candidate will be synthesized. There are three important aspects for the classification of BBB activity in this work, (1) variable reduction by PCA (2) variable selection and class separation with comparison of three methods such as T-Statistics, Partial Least Squares Regression Coefficient (PLSRC) and newly invented Self Organising Maps Discriminatory Index (SOMDI). and (3) classification, a comparison of linear (PLSDA) and non linear (SuSOMs) methods. The number of PCA component determined by LOO cross-validations is seven. Based on PCA score, the variables selected by T-Statistics and SOMDI are more selective and can provide better separation for BBB activity than PLSRC. Models performances and validations, built through PLSDA and SOMs show that the consensually selected 7 descriptors in this work by using SOMDI, T-statistics and PLSRC were able to classify BBB penetration and non-penetration compounds.

Signal processing strategies in FT-NIR and FTIR spectra of palm oils

In the palm oil industry, iodine value (IV) has become an important parameter in quality control that measures the degree of unsaturation of the oils. However, it is difficult to obtain the IV chemically. In other hand, the use of instrumental analysis in IV determination accurately needs suitable data pre-processing. In this study, we proposed the strategy for pre-processing the FT-NIR and FTIR spectra data in analyzing the IV of non-fried and fried palm oils. The utility and effectiveness of four data pre-processing which are column standardization, mean centre and combination of row scaling with column standardization and mean centre were applied. The effect of data splitting methods which are duplex and kenstone was also investigated in the Partial Least Squares (PLS) regression model of palm oils. From the result, the use of different data pre-processing provides different quality of prediction model. Either the application of the row scaling and column scaling individually or combination of both methods may improve the quality of the model. It is concluded that the data pre-processing is context dependent which is depend on the nature of the dataset and there can be no single method for general use.

Data preprocessing methods of FT-NIR spectral data for the classification cooking oil

This recent work describes the data pre-processing method of FT-NIR spectroscopy datasets of cooking oil and its quality parameters with chemometrics method. Pre-processing of near-infrared (NIR) spectral data has become an integral part of chemometrics modelling. Hence, this work is dedicated to investigate the utility and effectiveness of pre-processing algorithms namely row scaling, column scaling and single scaling process with Standard Normal Variate (SNV). The combinations of these scaling methods have impact on exploratory analysis and classification via Principle Component Analysis plot (PCA). The samples were divided into palm oil and non-palm cooking oil. The classification model was build using FT-NIR cooking oil spectra datasets in absorbance mode at the range of 4000cm−1-14000cm−1. Savitzky Golay derivative was applied before developing the classification model. Then, the data was separated into two sets which were training set and test set by using Duplex method. The number of each class was...

Quantitative structure-activity relationship (QSAR) modelling of N-aryl derivatives as cholinesterase inhibitors

A QSAR study on a series of N-aryl derivatives was performed to explore the important molecular descriptor which is responsible for their inhibitory activity towards choli nest erase enzyme, the common target for the treatment of Alzheimers disease. Molecular descriptors were calculated using DRAGON version 5.2 software Two methods of descriptor selection, stepwise regression and forward selection procedure, were performed and compared. Multiple Linear Regression (MLR) analysis was carried out to derive QSAR models, which were further evaluated for statistical significance and predictive power by leave-one-out (LOO) cross validation test. The best QSAR models against acetylcholinesterase and butylcholinesterase inhibitory activity were selected, having squared correlation coefficient R2=945% and 98.4%, and cross-validated squared correlation coefficient R2cv = 91.9% and 97.2%, respectively. The statistical outcomes derived from the present study demonstrate good predictability and may be useful in the design of more potent substituted N-aryl derivatives as cholinesterase inhibitor.