Combined Linear Discriminant Analysis Research Articles

Rapid method for identifying diacylglycerol edible oils using Raman spectroscopy combined with the “oil microscopy” method

This study aims to identify diacylglycerol (DAG) edible oils using Raman spectroscopy to protect consumers. Raman spectral data from 28 samples were collected, including DAG (1,3-diolein), triacylglycerol (triolein), DAG edible oils, adulterated oils, and ordinary edible oils. These samples were analyzed using a combined linear discriminant analysis–k nearest neighbors algorithm, characteristic band ratios, peak area ratios, and oil microscopy. The results of Raman spectroscopy analysis demonstrated DAG edible oils, adulterated oil, and ordinary cooking oil at 1746 cm−1 with Iordinary edible oil >Iadulterated oil >IDAG edible oil. Further analyses revealed differences in esterification between DAG edible oils and triacylglycerol. Moreover, the results demonstrated that the combination of Raman spectroscopy and oil microscopy can quickly and accurately detect DAG edible oil adulteration, which is expected to be an effective tool for food safety regulation to protect consumers’ rights.

Detection of aflatoxins in ground maize using a compact and automated Raman spectroscopy system with machine learning

Consumption of aflatoxin-contaminated food can cause severe illness when consumed by humans or livestock. Because the mycotoxin frequently occurs in cereal grains and other agricultural crops, it is crucial to develop portable devices that can be used non-destructively and in real-time to identify aflatoxin-contaminated food materials during early stages of harvesting or processing. In this study, an aflatoxin detection method was developed using a compact Raman device that can be used in the field. Data were obtained using maize samples naturally contaminated with aflatoxin, and the data were analyzed using a machine learning method. Of the multiple classification models evaluated, such as linear discriminant analysis (LDA), linear support vector machines (LSVM), quadratic discriminant analysis (QDA), and quadratic support vector machines and spectral preprocessing methods, the best classification accuracy was achieved at 95.7% using LDA in combination with Savitzky-Golay 2nd derivative (SG2) preprocessing. Partial least squares regression (PLSR) models demonstrated a close-range accuracy within the scope of standard normal variate (SNV) and multiplicative scatter correction (MSC) preprocessing methods, with determination of coefficient values of R2C and R2V of 0.9998 and 0.8322 respectively for SNV, and 0.9916 and 0.8387 respectively for MSC. This study demonstrates the potential use of compact and automated Raman spectroscopy, coupled with chemometrics and machine learning methods, as a tool for rapidly screening food and feed for hazardous substances at on-site field processing locations.

Habitat Mapping and Quality Assessment of NATURA 2000 Heathland Using Airborne Imaging Spectroscopy

Appropriate management of (semi-)natural areas requires detailed knowledge of the ecosystems present and their status. Remote sensing can provide a systematic, synoptic view at regular time intervals, and is therefore often suggested as a powerful tool to assist with the mapping and monitoring of protected habitats and vegetation. In this study, we present a multi-step mapping framework that enables detailed NATURA 2000 (N2000) heathland habitat patch mapping and the assessment of their conservation status at patch level. The method comprises three consecutive steps: (1) a hierarchical land/vegetation type (LVT) classification using airborne AHS imaging spectroscopy and field reference data; (2) a spatial re-classification to convert the LVT map to a patch map based on life forms; and (3) identification of the N2000 habitat type and conservation status parameters for each of the patches. Based on a multivariate analysis of 1325 vegetation reference plots acquired in 2006–2007, 24 LVT classes were identified that were considered relevant for the assessment of heathland conservation status. These labelled data were then used as ground reference for the supervised classification of the AHS image data to an LVT classification map, using Linear Discriminant Analysis in combination with Sequential-Floating-Forward-Search feature selection. Overall classification accuracies for the LVT mapping varied from 83% to 92% (Kappa ≈ 0.82–0.91), depending on the level of detail in the hierarchical classification. After converting the LVT map to a N2000 habitat type patch map, an overall accuracy of 89% was obtained. By combining the N2000 habitat type patch map with the LVT map, two important conservation status parameters were directly deduced per patch: tree and shrub cover, and grass cover, showing a strong similarity to an independent dataset with estimates made in the field in 2009. The results of this study indicate the potential of imaging spectroscopy for detailed heathland habitat characterization of N2000 sites in a way that matches the current field-based workflows of the user.

Expression-robust 3D face recognition based on feature-level fusion and feature-region fusion

3D face shape is essentially a non-rigid free-form surface, which will produce non-rigid deformation under expression variations. In terms of that problem, a promising solution named Coherent Point Drift (CPD) non-rigid registration for the non-rigid region is applied to eliminate the influence from the facial expression while guarantees 3D surface topology. In order to take full advantage of the extracted discriminative feature of the whole face under facial expression variations, the novel expression-robust 3D face recognition method using feature-level fusion and feature-region fusion is proposed. Furthermore, the Principal Component Analysis and Linear Discriminant Analysis in combination with Rotated Sparse Regression (PL-RSR) dimensionality reduction method is presented to promote the computational efficiency and provide a solution to the curse of dimensionality problem, which benefit the performance optimization. The experimental evaluation indicates that the proposed strategy has achieved the rank-1 recognition rate of 97.91 % and 96.71 % based on Face Recognition Grand Challenge (FRGC) v2.0 and Bosphorus respectively, which means the proposed approach outperforms state-of-the-art approach.

Hepatitis C related chronic liver cirrhosis: feasibility of texture analysis of MR images for classification of fibrosis stage and necroinflammatory activity grade.

PurposeTo assess the feasibility of texture analysis for classifying fibrosis stage and necroinflammatory activity grade in patients with chronic hepatitis C on T2-weighted (T2W), T1-weighted (T1W) and Gd-EOB-DTPA-enhanced hepatocyte-phase (EOB-HP) imaging.Materials and methodsFrom April 2008 to June 2012, MR images from 123 patients with pathologically proven chronic hepatitis C were retrospectively analyzed. Texture parameters derived from histogram, gradient, run-length matrix, co-occurrence matrix, autoregressive model and wavelet transform methods were estimated with imaging software. Fisher, probability of classification error and average correlation, and mutual information coefficients were used to extract subsets of optimized texture features. Linear discriminant analysis in combination with 1-nearest neighbor classifier (LDA/1-NN) was used for lesion classification. In compliance with the software requirement, classification was performed based on datasets from all patients, the patient group with necroinflammatory activity grade 1, and that with fibrosis stage 4, respectively.ResultsBased on all patient dataset, LDA/1-NN produced misclassification rates of 28.46%, 35.77% and 20.33% for fibrosis staging and 34.15%, 25.20% and 28.46% for necroinflammatory activity grading in T2W, T1W and EOB-HP images. In the patient group with necroinflammatory activity grade 1, LDA/1-NN yielded misclassification rates of 5.00%, 0% and 12.50% for fibrosis staging in T2W, T1W and EOB-HP images respectively. In the patient group with fibrosis stage 4, LDA/1-NN yielded misclassification rates of 5.88%, 12.94% and 11.76% for necroinflammatory activity grading in T2W, T1W and EOB-HP images respectively.ConclusionTexture quantitative parameters of MR images facilitate classification of the fibrosis stage as well as necroinflammatory activity grade in chronic hepatitis C, especially after categorizing the input dataset according to the activity or fibrosis degree in order to remove the interference between the fibrosis stage and necroinflammatory activity grade on texture features.

Texture-based classification of different gastric tumors at contrast-enhanced CT

PurposeTo determine the feasibility of texture analysis for the classification of gastric adenocarcinoma, lymphoma, and gastrointestinal stromal tumors on contrast-enhanced hydrodynamic-MDCT images. Materials and methodsThe arterial phase scans of 47 patients with adenocarcinoma (AC) and a histologic tumor grade of [AC-G1, n=4, G1, n=4; AC-G2, n=7; AC-G3, n=16]; GIST, n=15; and lymphoma, n=5, and the venous phase scans of 48 patients with AC-G1, n=3; AC-G2, n=6; AC-G3, n=14; GIST, n=17; lymphoma, n=8, were retrospectively reviewed. Based on regions of interest, texture analysis was performed, and features derived from the gray-level histogram, run-length and co-occurrence matrix, absolute gradient, autoregressive model, and wavelet transform were calculated. Fisher coefficients, probability of classification error, average correlation coefficients, and mutual information coefficients were used to create combinations of texture features that were optimized for tumor differentiation. Linear discriminant analysis in combination with a k-nearest neighbor classifier was used for tumor classification. ResultsOn arterial-phase scans, texture-based lesion classification was highly successful in differentiating between AC and lymphoma, and GIST and lymphoma, with misclassification rates of 3.1% and 0%, respectively. On venous-phase scans, texture-based classification was slightly less successful for AC vs. lymphoma (9.7% misclassification) and GIST vs. lymphoma (8% misclassification), but enabled the differentiation between AC and GIST (10% misclassification), and between the different grades of AC (4.4% misclassification). No texture feature combination was able to adequately distinguish between all three tumor types. ConclusionClassification of different gastric tumors based on textural information may aid radiologists in establishing the correct diagnosis, at least in cases where the differential diagnosis can be narrowed down to two histological subtypes.

Chemometric techniques on inorganic elements composition for the determination of the geographic origin of Welsh onions.

Techniques to determine the producing country of Welsh onions (Allium fistulosum L.) were developed by using 216 samples from Japan and from Anchu Shandgon, Shanghai and Amoy Fjian in China. Twelve elements (Na, P, K, Ca, Mg. Mn, Fe, Cu, Zn, Sr, Ba, Al, Co, Ni, Rb, Mo, Cd, Cs, La, Ce, Tl and Pb) contained in Welsh onions were determined. In order to determining whether Welsh onions originate in Japan or in China, linear discriminant analysis (LDA) and soft independent modeling of class analogy (SIMCA) were performed, using concentrations of 20 elements excluding Al and Pb in 22 elements. In LDA for two-group discrimination modeled on Welsh onions from Japan and China, 103 samples used for modeling were classified 95% correctly, and 89 other samples were predicted 94% correctly. As the average of predictions by SIMCA modeled on samples selected by 10 times of random selections, 192 samples, including the 103 samples used for modeling, were predicted 96% correctly. In discriminations by combined LDA and SIMCA, all 81 samples produced in Japan were correctly judged to be Japanese ones, and only 8 samples out of 111 samples produced in China were not correctly judged to be Chinese ones.