Rudi Heryanto

Curcuminoid’s Content and Fingerprint Analysis for Authentication and Discrimination of Curcuma xanthorrhiza from Curcuma longa by High-Performance Liquid Chromatography-Diode Array Detector

An accurate and reliable method for authentication and discrimination of Curcuma xanthorrhiza (CX) from Curcuma longa (CL) by determining the curcuminoid’s content and analyzing the HPLC fingerprint combined with discriminant analysis (DA) was developed. By using the proposed method, it was found that CL had higher amount of all curcuminoid compounds compared to CX. Therefore, these two closely related species could be authenticated and discriminated by the amount of curcuminoids present in the samples. Authentication and discrimination of the two species were also achieved by comparing their HPLC fingerprint chromatograms using their typical marker peaks. To be more convincing, an aid from DA was also used. Combination of HPLC fingerprint analysis and DA gave excellent result that the two species were separated clearly, including CX samples adulterated with CL. The developed method was successfully used for quality control of the two plants.

Fourier transform infrared spectroscopy combined with chemometrics for discrimination of Curcuma longa, Curcuma xanthorrhiza and Zingiber cassumunar

Turmeric (Curcuma longa), java turmeric (Curcuma xanthorrhiza) and cassumunar ginger (Zingiber cassumunar) are widely used in traditional Indonesian medicines (jamu). They have similar color for their rhizome and possess some similar uses, so it is possible to substitute one for the other. The identification and discrimination of these closely-related plants is a crucial task to ensure the quality of the raw materials. Therefore, an analytical method which is rapid, simple and accurate for discriminating these species using Fourier transform infrared spectroscopy (FTIR) combined with some chemometrics methods was developed. FTIR spectra were acquired in the mid-IR region (4000-400 cm(-1)). Standard normal variate, first and second order derivative spectra were compared for the spectral data. Principal component analysis (PCA) and canonical variate analysis (CVA) were used for the classification of the three species. Samples could be discriminated by visual analysis of the FTIR spectra by using their marker bands. Discrimination of the three species was also possible through the combination of the pre-processed FTIR spectra with PCA and CVA, in which CVA gave clearer discrimination. Subsequently, the developed method could be used for the identification and discrimination of the three closely-related plant species.

Learning similarity functions for binary strings via genetic programming

Data that encode the presence of some characteristics typically can be represented as binary strings. We need similarity functions for binary strings in order to classify or cluster them. Existing similarity functions, however, do not take advantage of training data, which are often available. We believe that similarity functions should be data-specific. To this end, we use genetic programming (GP) to learn similarity functions from training data. We propose a novel fitness function that considers five aspects of good similarity functions, i.e. recall, magnitude, zero-division, identity and symmetry. We also report mostly-used math operators from extensive literature review. Experiment results show that GP-based similarity functions outperform the well-known Tanimoto function in most datasets in terms of classification accuracy using SVMs. In addition, those GP-based similarity functions are simpler: using fewer numbers of operators and operands. This suggests that our proposed fitness function for GP is justifiable for learning similarity functions.

Quality Control of Jati Belanda Leaves (Guazuma ulmifolia) using Image Analysis and Chemometrics

The quality of medicinal plants, such as Guazuma ulmifolia (jati belanda, JB), affects the quality of the herbal material derived from them, and can be determined using image analysis. The objective of this study is to investigate the possibility of using an image-generated spectrum and chemometrics as a method for quality control of Jati belanda leaves. Three different quality levels of JB leaves were determined, based on their harvesting time, and confirmed by total flavonoid content analysis. The images of JB samples were collected and reconstructed as a reflection spectrum using the Wiener estimation. The reconstructed spectrum had a goodness-of-fit coefficient of 0.9576 and a root-mean-square-error (RMSE) of 36.65%, compared to the experimental spectrum. Principal Component Analysis (PCA) was used to classify the JB reconstructed spectrum based on its quality. A score plot of two PCs that represented 98% variance was able to group the JB spectrum. Further analysis using Partial Least Squares-Discriminant Analysis (PLSDA) showed that the method can result in around 90% prediction success rate with external validation. This study indicates that image analysis and chemometrics could be used as quality control methods for herbal material.

A classification system for jamu efficacy based on formula using support vector machine and k-means algorithm as a feature selection

Jamu is an Indonesia herbal medicine made from natural materials such as roots, leaves, fruits, and animals. The purpose of this research is to develop a classification system for jamu efficacy based on the composition of plants using Support Vector Machine (SVM) and to implement the k-means clustering algorithm as a feature selection method. The result of this study was compared to the previous research that using SVM method without feature selection. This study used variances to evaluate the results of clustering. The total of 3138 data herbs and 465 plant species were grouped into 100 clusters with the variance of 0.0094. The managed group succesfully reduced the data dimension into 3047 of jamu sample and 236 species of herbs and plants as features. The result of SVM classification using feature selection yielded the accuracy of 71.5%.

A classification system for Jamu efficacy based on formula using Support Vector Machine

Jamu is made from natural materials such as roots, leaves, timber and fruits. Jamu has many variations of formula. The composition of Jamu formula is usually based on empirical data or personal experiences. Thus, the classification for the efficacy of Jamu based on its compositions of plants still remains an interesting task. The purpose of this research is to develop a classification system for Jamu effects based on the composition of plants using Support Vector Machine (SVM). This method is compared to those of previous research using Partial Least Squares Discriminant Analysis (PLS-DA). The result shows that the SVM method with Radial Basis Function (RBF) kernel obtains higher accuracy than those that used PLS-DA.