Fuzzy Rule-building Expert System Research Articles

Pipeline for High-Throughput Modeling of Marijuana and Hemp Extracts.

Authentication of Cannabis products is important for assuring the quality of manufacturing, with the increasing consumption and regulation. In this report, a two-stage pipeline was developed for high-throughput screening and chemotyping the spectra from two sets of botanical extracts from the Cannabis genus. The first set contains different marijuana samples with higher concentrations of tetrahydrocannabinol (THC). The other set includes samples from hemp, a variety of Cannabis sativa with the THC concentration below 0.3%. The first stage applies the technique of class modeling to determine whether spectra belong to marijuana or hemp and reject novel spectra that may be neither marijuana nor hemp. An automatic soft independent modeling of class analogy (aSIMCA) that self-optimizes the number of principal components and the decision threshold is utilized in the first pipeline process to achieve excellent efficiency and efficacy. Once these spectra are recognized by aSIMCA as marijuana or hemp, they are then routed to the appropriate classifiers in the second stage for chemotyping the spectra, i.e., identifying these spectra into different chemotypes so that the pharmacological properties and cultivars of the spectra can be recognized. Three multivariate classifiers, a fuzzy rule building expert system (FuRES), super partial least-squares-discriminant analysis (sPLS-DA), and support vector machine tree type entropy (SVMtreeH), are employed for chemotyping. The discriminant ability of the pipeline was evaluated with different spectral data sets of these two groups of botanical samples, including proton nuclear magnetic resonance, mass, and ultraviolet spectra. All evaluations gave good results with accuracies greater than 95%, which demonstrated promising application of the pipeline for automated high-throughput screening and chemotyping marijuana and hemp, as well as other botanical products.

High-Throughput Chemotyping of Cannabis and Hemp Extracts Using an Ultraviolet Microplate Reader and Multivariate Classifiers

As the use of Cannabis products as natural medicines burgeons, it is also appearing as a food ingredient. It is important to screen Cannabis samples as ingredients by profiling their chemical compositions, which is referred to as chemotyping. Two sets of botanical extracts were studied. The first set is referred to as Cannabis contained plant materials from 15 samples of the sativa, indica, and hybrids of the two species. The second set contained 20 extracts from the variety of Cannabis sativa with low tetrahydrocannabinol (THC) concentrations, i.e., below 0.3%, and, henceforth, will be referred to as hemp. An ultraviolet (UV) microplate reader provides a cost-effective and high-throughput method for identifying chemotypes of plant extracts by their spectra. The microplate reader affords rapid measurements of small volumes, e.g., 50 µL, which demonstrates a potential to significantly reduce the analysis time and cost for Cannabis and hemp chemotyping or chemical profiling. Replicate samples were measured on different days to demonstrate the robustness of the method. Projected difference resolution (PDR) maps were used to visualize the separations among the classes. Five multivariate classifiers, fuzzy rule-building expert system (FuRES), super partial least squares-discriminant analysis (sPLS-DA), support vector machine (SVM), and two tree-based support vector machines (SVMtreeG and SVMtreeH) were evaluated. The classifiers were validated with ten bootstrapped Latin partitions (BLPs). For the Cannabis extracts, the SVMtreeG yielded the best performance and the classification accuracy was 99.1 ± 0.4% for spectra collected in the nonlinear absorbance range. For the hemp extracts, the SVM classifier performed the best with a 97.4 ± 0.6% classification accuracy. These results demonstrate that the UV microplate reader coupled with multivariate classifiers can be used as a high-throughput and cost-effective approach for chemotyping Cannabis.

Differentiating Rice Varieties by Inductively Coupled Plasma Mass Spectrometry Chemical Profiling with Singular Value Decomposition Background Correction

As a global staple, rice has an increasing demand for differentiation and authentication, considering both fraud and health aspects for consumers. The complexity of rice urges a rapid, labor-saving, effective, and economical rice differentiation method. A semi-quantitative method using inductively coupled plasma mass spectrometry (ICP–MS) for fast and high-throughput analysis of rice entire elements with singular value decomposition (SVD) background correction (BC) was developed. The SVD BC method is the first time that it has been used with ICP–MS to minimize the effect of instrumental drift. Other data preprocessing methods, normalization (NM), error scaling (ES), and standard normal variate (SNV) were evaluated by principal component analysis (PCA) and projected difference resolution (PDR). A fuzzy rule-building expert system (FuRES), super partial least squares discriminant analysis (sPLS-DA), support vector machine (SVM), and SVM classification tree (SVMTreeG) classifiers gave 98.1 ± 0.0, 99.8 ± 0.4, 99.8 ± 0.4, and 100.0 ± 0.0% prediction rates with all of the data preprocessing methods (NM, SVD BC with one component to reconstruct the background, ES, and SNV) for the differentiation of the nine rice-digested samples, respectively.

Differentiation of Bovine, Porcine, and Fish Gelatins by Attenuated Total Reflectance Fourier Transform Infrared Spectroscopy (ATR-FTIRS) Coupled with Pattern Recognition.

Bovine, porcine, and fish gelatins have been differentiated based on their spectra collected by attenuated total reflectance FTIR spectroscopy (ATR-FTIRS) coupled with pattern recognition. Three tree-based classification methods, a fuzzy rule-building expert system (FuRES), support vector machine classification trees (SVMTreeG and SVMTreeH), and one reference model, super partial least-squares discriminant analysis (sPLS-DA), were evaluated with and without two preprocessing techniques, namely standard normal variate (SNV) and principal component orthogonal signal correction (PC-OSC). Validation of these methods was obtained with 95% confidence intervals with 10 bootstraps and 4 Latin partitions (10:4). The ATR-FTIR spectra were used with four different ranges: full spectra (4000-650 cm-1), fingerprint region (1731-650 cm-1), specified spectra (4000-800 cm-1), and narrow fingerprint region (1731-800 cm-1). Classification rates for the methods were improved with SNV and PC-OSC when they were used separately or together. The highest classification rates were obtained from the narrow fingerprint region with SNV and PC-OSC at 97.4 ± 1.6% for FuRES, 100 ± 0% for sPLS-DA, and 99.3 ± 0.5% for both SVMTreeG and SVMTreeH. ATR-FTIRS combined with pattern recognition is a potential analytical technique for differentiating the sources of bovine, porcine, and fish gelatins with fast and reliable results.

Effect of preprocessing high-resolution mass spectra on the pattern recognition of Cannabis, hemp, and liquor

High-resolution mass spectrometry (HRMS) combined with pattern recognition was used to discriminate among twenty-five Cannabis samples, twenty hemp samples, and eight liquor samples. The effects of preprocessing on multivariate data analysis were evaluated for Orbitrap high-resolution mass spectra. Different root transformations were evaluated with respect to the bin width and the average classification rates. In addition, linear binning and proportional binning with various resolving powers were studied with respect to the average classification rates. The proportional binning with the square root transformation gave the best overall performance for chemical profiling or spectral fingerprinting. Six classification methods, fuzzy rule-building expert system (FuRES), linear discriminant analysis (LDA), super partial least squares discriminant analysis (sPLS-DA), support vector machine (SVM), SVM classification tree type gap (SVMTreeG), and SVM classification tree type entropy (SVMTreeH) had similar trends in prediction rate with respect to the resolving power. The optimal proportional mass bin width may depend on the data set, i.e., for the Cannabis samples is resolving power 10−4, for the hemp samples and the liquor samples are resolving power 10−3. Hence, data preprocessing methods such as different transformations, binning strategies, and resolving powers are important factors to be optimized for HRMS direct infusion measurements combined with pattern recognition to be an authentication and characterization tool for various products.

Chemical profiling of floral and chestnut honey using high-performance liquid chromatography-ultraviolet detection

Using the two-way images of phenolic compounds from high-performance liquid chromatography-ultraviolet diode array detection (HPLC-DAD), floral and chestnut honey from Turkey were successfully differentiated. A fuzzy rule-building expert system (FuRES), support vector machine classification tree (SVMTreeG), and super partial least-square discriminant analysis (sPLS-DA) were used to develop classification models. Normalization, retention time alignment, square root transform, and dissimilarity kernel were evaluated as data preprocessing methods. The bootstrapped Latin partition was used with 100 bootstraps and 4 partitions. Classification rates of FuRES and SVMTreeG with a square root transform were 97.6±0.4% and 97.6±0.4% for classifying the type of honey, respectively. The measures of precision are 95% confidence intervals. HPLC-DAD was demonstrated as a reliable analytical method for authentication of honey.

Spectral Representation of Proton NMR Spectroscopy for the Pattern Recognition of Complex Materials

Proton nuclear magnetic resonance (NMR) spectroscopy provides a powerful tool for chemical profiling, also known as spectral fingerprinting, because of its inherent reproducibility. NMR is now increasing in use for authentication of complex materials. Typically, the absorbance spectrum is used that is obtained as the phase-corrected real component of the Fourier transform (FT) of the free induction decay (FID). However, the practice discards half the information that is available in the dispersion spectrum obtained as the imaginary component from the FT. For qualitative analysis or quantitative analysis of small sets of absorbance peaks, the symmetric and sharp peaks of the real spectra work well. However, for pattern recognition of entire spectra, trading peak resolution for peak reproducibility is beneficial. The absolute value of the complex spectrum gives the length or magnitude of magnetization vector in the complex plane; therefore, the magnitude relates directly to the signal (i.e., induced magnetization). The magnitude spectrum is obtained as the absolute value from the real and imaginary spectral components after the FT of the FID. By breaking with tradition and using the magnitude spectrum the reproducibility of the spectra and consequent recognition rates can be improved. This study used a 500-MHz 1H NMR instrument to obtain spectra from 4 diverse datasets; 12 tea extracts, 8 liquor samples, 9 hops extracts, and 25 Cannabis extracts. Six classifiers were statistically evaluated using 100 bootstrapped Latin partitions. The classifiers were a fuzzy rule-building expert system (FuRES) tree, support vector machine trees (SVMTreeG and SVMTreeH), a regularized linear discriminant analysis (LDA), super partial least squares discriminant analysis (sPLS-DA), and a one against all support vector machine (SVM). All classifiers gave better or equivalent results for the magnitude spectral representation than for the real spectra, except for one case of the 24 evaluations. In addition, the enhanced reproducibility of the absolute value spectra is demonstrated by comparisons of the pooled within sample standard deviations. For pattern recognition of NMR spectra, the magnitude spectrum is advocated.

Strain-level Staphylococcus differentiation by CeO2-metal oxide laser ionization mass spectrometry fatty acid profiling

BackgroundThe Staphylococcus genus is composed of 44 species, with S. aureus being the most pathogenic. Isolates of S. aureus are generally susceptible to β-lactam antibiotics, but extensive use of this class of drugs has led to increasing emergence of resistant strains. Increased occurrence of coagulase-negative staphylococci as well as S. aureus infections, some with resistance to multiple classes of antibiotics, has driven the necessity for innovative options for treatment and infection control. Despite these increasing needs, current methods still only possess species-level capabilities and require secondary testing to determine antibiotic resistance. This study describes the use of metal oxide laser ionization mass spectrometry fatty acid (FA) profiling as a rapid, simultaneous Staphylococcus identification and antibiotic resistance determination method.ResultsPrincipal component analysis was used to classify 50 Staphyloccocus isolates. Leave-one-spectrum-out cross-validation indicated 100 % correct assignment at the species and strain level. Fuzzy rule building expert system classification and self-optimizing partial least squares discriminant analysis, with more rigorous evaluations, also consistently achieved greater than 94 and 84 % accuracy, respectively. Preliminary analysis differentiating MRSA from MSSA demonstrated the feasibility of simultaneous determination of strain identification and antibiotic resistance.ConclusionThe utility of CeO2-MOLI MS FA profiling coupled with multivariate statistical analysis for performing strain-level differentiation of various Staphylococcus species proved to be a fast and reliable tool for identification. The simultaneous strain-level detection and antibiotic resistance determination achieved with this method should greatly improve outcomes and reduce clinical costs for therapeutic management and infection control.

Diagnosis of patients with chronic kidney disease by using two fuzzy classifiers

The feasibility of two in-house fuzzy classifiers, fuzzy rule-building expert system (FuRES) and fuzzy optimal associative memory (FOAM), for diagnosis of patients with chronic kidney disease (CKD) was investigated. A linear classifier, partial least squares discriminant analysis (PLS-DA), was used for comparison. The CKD data used in this work were taken from the UCI Machine Learning Repository. Composite datasets were created by adding different levels of proportional noise to evaluate the robustness of the two fuzzy approaches. Firstly, 11 levels of proportional noises were added to each numeric attribute of the training and prediction sets one after another, and then these simulated training and prediction sets were combined in pairs. Thus, a grid with 121 groups of simulated data was generated, and classification rates for these 121 pairs were compared. Secondly, the performances of two fuzzy classifiers using the simulated datasets, in which 11 levels of noise were randomly distributed to each numeric attribute, were compared and the average prediction rates of FuRES and FOAM were 98.1±0.5% and 97.2±1.2%, respectively, with 200 bootstrap Latin partitions. The PLS-DA can give 94.3±0.8% with the identical evaluation. Confluent datasets comprised of the original and modified datasets were also used to evaluate FuRES, FOAM, and PLS-DA classification models. The average prediction rates of FuRES and FOAM obtained from 200 bootstrapped evaluations were 99.2±0.3% and 99.0±0.3%. PLS-DA yields slightly worse accuracy with 95.9±0.6%. The results demonstrate that both FuRES and FOAM perform well on the identification of CKD patients, while FuRES is more robust than FOAM. These two fuzzy classifiers are useful tools for the diagnosis of CKD patients with satisfactory robustness, and can also be used for other kinds of patients.

Support Vector Machine Classification Trees

Proteomic and metabolomic studies based on chemical profiling require powerful classifiers to model accurately complex collections of data. Support vector machines (SVMs) are advantageous in that they provide a maximum margin of separation for the classification hyperplane. A new method for constructing classification trees, for which the branches comprise SVMs, has been devised. The novel feature is that the distribution of the data objects is used to determine the SVM encoding. The variance and covariance of the data objects are used for determining the bipolar encoding required for the SVM. The SVM that yields the lowest entropy of classification becomes the branch of the tree. The SVM-tree classifier has the added advantage that nonlinearly separable data may be accurately classified without optimization of the cost parameter C or searching for a correct higher dimensional kernel transform. It compares favorably to a regularized linear discriminant analysis, SVMs in a one against all multiple classifier, and a fuzzy rule-building expert system, a tree classifier with a fuzzy margin of separation. SVMs offer a speed advantage, especially for data sets that have more measurements than objects.

Profiling Amino Acids of Jordanian Scalp Hair as a Tool for Diabetes Mellitus Diagnosis: A Pilot Study.

Hair analysis is an area of increasing interest in the fields of medical and forensic sciences. Human scalp hair has attractive features in clinical studies because hair can be sampled easily and noninvasively from human subjects, and unlike blood and urine samples, it contains a chronological record of medication use. Keratin protein is the major component of scalp hair shaft material and it is composed of 21 amino acids. The method used herein for the amino acid determination in hair included keratin protein acid hydrolysis using 6 M hydrochloric acid (HCl), followed by amino acids derivatization using N,O-bis(trimethylsilyl)trifluoroacetamide (BSTFA), and the determination of derivatized amino acids by gas chromatography/mass spectrometry (GC/MS). Amino acid profiles of scalp hair of 27 Jordanian subjects (15 diabetes mellitus (DM) type 2 patients and 12 control subjects) were analyzed. A fuzzy rule-building expert system (FuRES) classified the amino acid profiles into diabetic and control groups based on multivariate analyses of the abundance of 14 amino acids. The sensitivity and specificity were 100% for diabetes detection using leave-one-individual-out cross-validation. The areas under the receiver operative characteristics (ROC) curves were 1.0, which represents a highly sensitive and specific diabetes test. The nonessential amino acids Gly and Glu, and the essential amino acid Ile were more abundant in the scalp hair of diabetic patients compared to the hair of control subjects. The associations between the abundance of amino acids of human hair and health status may have clinical applications in providing diagnostic indicator or predicting other chronic or acute diseases.

Terahertz time-domain spectroscopy combined with fuzzy rule-building expert system and fuzzy optimal associative memory applied to diagnosis of cervical carcinoma.

Combined with terahertz time-domain spectroscopy, the feasibility of fast and reliable diagnosis of cervical carcinoma by a fuzzy rule-building expert system (FuRES) and a fuzzy optimal associative memory (FOAM) had been studied. The terahertz spectra of 52 specimens of cervix were collected in the work. The original data of samples were preprocessed by Savitzky-Golay first derivative (χderivative), principal component orthogonal signal correction (PC-OSC) and emphatic orthogonal signal correction to improve the performance of FuRES and FOAM models. The effect of the different pretreating methods to improve prediction accuracy was evaluated. The FuRES and FOAM models were validated using bootstrapped Latin-partition method. The obtained results showed that the FuRES and FOAM model optimized with the combination S-G first derivative and PC-OSC method had the better predictive ability with classification rates of 92.9±0.4 and 92.5±0.4%, respectively. The proposed procedure proved that terahertz spectroscopy combined with fuzzy classifiers could supply a technology which has potential for diagnosis of cancerous tissue.

Comparison of metal oxide catalysts for pyrolytic MOLI–MS bacterial identification

Six metal oxide catalysts were investigated for effective cleavage and laser ionization of bacterial cell wall phospholipid extracts. Calcium oxide has been utilized in the past for this application, but suffered from degradation of catalytic activity. Following evaluation of the six catalysts, CeO2 was found to be the most stable over time and produced fatty acid profiles of bacterial pathogens similar to freshly activated CaO. A suite of ten bacteria previously studied using CaO catalysis provided cross validation results of analysis of 97% correct correlation for negative-ion data. Cerium oxide catalysis studies yielded cross validation results of 100%. Using analysis of variance–principal component analysis (ANOVA–PCA), four sample sets collected with stored catalyst at 0, 8, 24, and 504h showed no effect based on long-term catalyst degradation. Supervised learning by a fuzzy rule-building expert system (FuRES) that was validated with training and prediction set partitions independent of CeO2 age and unsupervised data analysis using a dendrogram of Euclidean distance confirmed that the CeO2 catalyst age had no effect on the fatty acid mass spectral profiles.

Comparison of three algorithms for the baseline correction of hyphenated data objects.

Three novel two-way baseline correction algorithms, that is, orthogonal basis (OB), fuzzy optimal associative memory (FOAM), and polynomial fitting (PF), were evaluated with high performance liquid chromatography-mass spectrometry (HPLC-MS) and gas chromatography/mass spectrometry (GC/MS) data objects. Among these algorithms, both OB and FOAM are two-way baseline correction algorithms, which reconstruct the entire two-way backgrounds from blank data objects, while the PF algorithm is a pseudo-two-way method, which models each ion chromatogram baseline with a third-order polynomial. The performance of baseline correction methods was first evaluated with respect to the signal-to-noise ratios (SNRs) of 4 major peaks of the HPLC-MS total ion current (TIC) chromatograms of celery seed extracts. Then, the effect of baseline correction on pattern recognition was evaluated by using 42 two-way headspace (HS) solid phase microextraction (SPME) GC/MS data objects of 7 polychlorinated biphenyl (PCB) mixture standard solutions. Two types of classifiers, that is, a fuzzy rule-building expert system (FuRES) and partial least-squares-discriminant analysis (PLS-DA) were evaluated in parallel. Bootstrapped Latin partitions (BLPs) were used to give an unbiased and generalized evaluation of the classification accuracy. Results indicate that SNRs of major peaks of the TIC chromatogram representative of two-way HPLC-MS data objects are increased by baseline correction. In addition, higher prediction accuracies can be obtained by performing baseline correction on the entire GC/MS data set prior to pattern recognition. It is also found that proper data transformation is able to improve the performance of baseline correction. This report is the first of two-way baseline correction methods for hyphenated chromatography/mass spectrometry data objects. Both the orthogonal basis and FOAM baseline correction methods are novel in-house algorithms and proved to be generally effective for two-way baseline correction in the present study. Polynomial fitting is a conventional baseline correction method for one-way data objects and is applied to two-way data objects for the first time. It is applicable when blank data objects are unavailable.

THz-TDS combined with a fuzzy rule-building expert system applied to the identification of official rhubarb samples

Terahertz time domain spectroscopy (THz-TDS) combined with fuzzy rule-building expert systems was used for the identification of rhubarb samples.

Probability of Identification: Adulteration of American Ginseng with Asian Ginseng

The AOAC INTERNATIONAL guidelines for validation of botanical identification methods were applied to the detection of Asian Ginseng [Panax ginseng (PG)] as an adulterant for American Ginseng [P. quinquefolius (PQ)] using spectral fingerprints obtained by flow injection mass spectrometry (FIMS). Samples of 100% PQ and 100% PG were physically mixed to provide 90, 80, and 50% PQ. The multivariate FIMS fingerprint data were analyzed using soft independent modeling of class analogy (SIMCA) based on 100% PQ. The Q statistic, a measure of the degree of non-fit of the test samples with the calibration model, was used as the analytical parameter. FIMS was able to discriminate between 100% PQ and 100% PG, and between 100% PQ and 90, 80, and 50% PQ. The probability of identification (POI) curve was estimated based on the SD of 90% PQ. A digital model of adulteration, obtained by mathematically summing the experimentally acquired spectra of 100% PQ and 100% PG in the desired ratios, agreed well with the physical data and provided an easy and more accurate method for constructing the POI curve. Two chemometric modeling methods, SIMCA and fuzzy optimal associative memories, and two classification methods, partial least squares-discriminant analysis and fuzzy rule-building expert systems, were applied to the data. The modeling methods correctly identified the adulterated samples; the classification methods did not.

Automated pipeline for classifying Aroclors in soil by gas chromatography/mass spectrometry using modulo compressed two-way data objects

Seven polychlorinated biphenyls (PCBs) commercial mixtures, Aroclor 1016, 1221, 1232, 1242, 1248, 1254, and 1260, were analyzed by gas chromatography/mass spectrometry (GC/MS) combined with solid phase microextraction (SPME). Three pattern recognition methods: a fuzzy rule-building expert system (FuRES), partial least-squares discriminant analysis (PLS-DA), and a fuzzy optimal associative memory (FOAM) were used to build classification models. Modulo compression was introduced for data preprocessing to extract the characteristic features and compress the data size. Baseline correction and data normalization were also applied prior to data processing. Four GC/MS data set configurations were constructed and used to evaluate the classifiers and data pretreatments including two-way modulo compressed, two-way data, one-way total ion current and one-way total mass spectrum. The results indicate that modulo compression and baseline correction methods significantly improved the performance of the classifiers which resulted in improved classification rates for FuRES, PLS-DA, and FOAM classifiers. By using two-way modulo compressed data sets, the average classification rates with FuRES, PLS-DA, and FOAM were 100±0%, 94.6±0.7%, and 96.1±0.6% for 100 bootstrapped Latin partitions of the Aroclor standards. The classifiers were validated by application to Aroclor samples extracted from soil with no parametric changes except that the calibration set of standards and validation set of soil samples were individually mean centered. The classification rates for the GC/MS modulo 35 compressed data obtained from the Aroclor soil samples with FOAM, FuRES, and PLS-DA were 100%, 96.4%, and 78.6%, respectively. Therefore, a chemometric pipeline for SPME-GC/MS data coupled with chemometric analysis was devised as a fast authentication method for different Aroclors in soil.

Feature selection of gas chromatography/mass spectrometry chemical profiles of basil plants using a bootstrapped fuzzy rule-building expert system

A bootstrapped fuzzy rule-building expert system (FuRES) and a bootstrapped t-statistical weight feature selection method were individually used to select informative features from gas chromatography/mass spectrometry (GC/MS) chemical profiles of basil plants cultivated by organic and conventional farming practices. Feature subsets were selected from two-way GC/MS data objects, total ion chromatograms, and total mass spectra, separately. Four economic classifiers based on the bootstrapped FuRES approach, i.e., fuzzy optimal associative memory (e-FOAM), e-FuRES, partial least-squares-discriminant analysis (e-PLS-DA), and soft independent modeling by class analogy (e-SIMCA), and four economic classifiers based on the bootstrapped t-weight approach, i.e., e-PLS-DA-t, e-FOAM-t, e-FuRES-t, and e-SIMCA-t, were constructed thereafter to be compared with full-size classifiers obtained from the entire GC/MS data objects (i.e., FOAM, FuRES, PLS-DA, and SIMCA). By using three features selected from two-way data objects, the average classification rates with e-FOAM, e-FuRES, e-PLS-DA, and e-SIMCA were 95.3 ± 0.5%, 100%, 100%, and 91.8 ± 0.2%, respectively. The established economic classifiers were used to classify a new validation set collected 2.5 months later with no parametric change to experimental procedure. Classification rates with e-FOAM, e-FuRES, e-PLS-DA, and e-SIMCA were 96.7%, 100%, 100%, and 96.7%, respectively. Characteristic components in basil extracts corresponding to highest-ranked useful features were putatively identified. The feature subset may prove valuable as a rapid approach for organic basil authentication.

Authentication of organically and conventionally grown basils by gas chromatography/mass spectrometry chemical profiles.

Basil plants cultivated by organic and conventional farming practices were accurately classified by pattern recognition of gas chromatography/mass spectrometry (GC/MS) data. A novel extraction procedure was devised to extract characteristic compounds from ground basil powders. Two in-house fuzzy classifiers, i.e., the fuzzy rule-building expert system (FuRES) and the fuzzy optimal associative memory (FOAM) for the first time, were used to build classification models. Two crisp classifiers, i.e., soft independent modeling by class analogy (SIMCA) and the partial least-squares discriminant analysis (PLS-DA), were used as control methods. Prior to data processing, baseline correction and retention time alignment were performed. Classifiers were built with the two-way data sets, the total ion chromatogram representation of data sets, and the total mass spectrum representation of data sets, separately. Bootstrapped Latin partition (BLP) was used as an unbiased evaluation of the classifiers. By using two-way data sets, average classification rates with FuRES, FOAM, SIMCA, and PLS-DA were 100 ± 0%, 94.4 ± 0.4%, 93.3 ± 0.4%, and 100 ± 0%, respectively, for 100 independent evaluations. The established classifiers were used to classify a new validation set collected 2.5 months later with no parametric changes except that the training set and validation set were individually mean-centered. For the new two-way validation set, classification rates with FuRES, FOAM, SIMCA, and PLS-DA were 100%, 93%, 97%, and 100%, respectively. Thereby, the GC/MS analysis was demonstrated as a viable approach for organic basil authentication. It is the first time that a FOAM has been applied to classification. A novel baseline correction method was used also for the first time. The FuRES and the FOAM are demonstrated as powerful tools for modeling and classifying GC/MS data of complex samples, and the data pretreatments are demonstrated to be useful to improve the performance of classifiers.

Classification of cultivation locations of Panax quinquefolius L samples using high performance liquid chromatography-electrospray ionization mass spectrometry and chemometric analysis.

Panax quinquefolius L ( P. quinquefolius L) samples grown in the United States and China were analyzed with high performance liquid chromatography-mass spectrometry (HPLC-MS). Prior to classification, the two-way data sets were subjected to pretreatment including baseline correction and retention time (RT) alignment. Principal component analysis (PCA) and projected difference resolution (PDR) metrics were used to evaluate the data quality and the pretreatment effects. A fuzzy rule-building expert system (FuRES) classifier was used to classify the P. quinquefolius L samples grown in the United States and China with the optimized partial least-squares (o-PLS) classifier as the positively biased control method. A classification rate as high as 98 ± 3% with FuRES was obtained after baseline correction and RT alignment, which is equivalent to the result obtained by using the positively biased o-PLS control method (98 ± 3%). RT alignment improved the classification rates for both FuRES and o-PLS classifiers (18% improvement for the FuRES classification rate and 10% improvement for the o-PLS classification rate with baseline correction). From the rule obtained to classify the P. quinquefolius L samples grown in the United States and China, peaks were identified that can be prospective biomarkers for differentiating samples from different growth regions. HPLC-MS with chemometric analysis has the potential to be used as an authentication method for P. quinquefolius L grown in China and the United States.