Action recognition using Partial Least Squares and Support Vector Machines

From a wide range of techniques appropriate to relate spectra measurements with soil properties, partial least squares (PLS) regression and support vector machines (SVM) are most commonly used. This is due to their predictive power and the availability of software tools. Both represent exclusively statistically based approaches and, as such, benefit from multiple responses of soil material in the spectrum. However, physical-based approaches that focus only on a single spectral feature, such as simple linear regression using selected continuum-removed spectra values as a predictor variable, often provide accurate estimates. Furthermore, if this approach extends to multiple cases by taking into account three basic absorption feature parameters (area, width, and depth) of all occurring features as predictors and subjecting them to best subset selection, one can achieve even higher prediction accuracy compared with PLS regression. Here, we attempt to further extend this approach by adding two additional absorption feature parameters (left and right side area), as they can be important diagnostic markers, too. As a result, we achieved higher prediction accuracy compared with PLS regression and SVM for exchangeable soil pH, slightly higher or comparable for dithionite-citrate and ammonium oxalate extractable Fe and Mn forms, but slightly worse for oxidizable carbon content. Therefore, we suggest incorporating the multiple linear regression approach based on absorption feature parameters into existing working practices.

As a laboratory proximal sensing technique, the capability of visible and near-infrared (Vis-NIR) diffused reflectance spectroscopy with partial least squares (PLS) regression to determine soil properties has previously been demonstrated. However, the evaluation of the soil phosphorus (P) content—a major nutrient constraint for crop production in the tropics—is still a challenging task. PLS regression with waveband selection can improve the predictive ability of a calibration model, and a genetic algorithm (GA) has been widely applied as a suitable method for selecting wavebands in laboratory calibrations. To develop a laboratory-based proximal sensing method, this study investigated the potential to use GA-PLS regression analyses to estimate oxalate-extractable P in upland and lowland soils from laboratory Vis-NIR reflectance data. In terms of predictive ability, GA-PLS regression was compared with iterative stepwise elimination PLS (ISE-PLS) regression and standard full-spectrum PLS (FS-PLS) regression using soil samples collected in 2015 and 2016 from the surface of upland and lowland rice fields in Madagascar (n = 103). Overall, the GA-PLS model using first derivative reflectance (FDR) had the best predictive accuracy (R2 = 0.796) with a good prediction ability (residual predictive deviation (RPD) = 2.211). Selected wavebands in the GA-PLS model did not perfectly match wavelengths of previously known absorption features of soil nutrients, but in most cases, the selected wavebands were within 20 nm of previously known wavelength regions. Bootstrap procedures (N = 10,000 times) using selected wavebands also confirmed the improvements in accuracy and robustness of the GA-PLS model compared to those of the ISE-PLS and FS-PLS models. These results suggest that soil oxalate-extractable P can be predicted from Vis-NIR spectroscopy and that GA-PLS regression has the advantage of tuning optimum bands for PLS regression, contributing to a better predictive ability.

An optical method recently proposed for non-invasive in vivo blood glucose concentration (BGL) measurement, named pulse glucometry, was implemented with three multivariate regression methods, Principal Component Regression (PCR), Partial Least Squares Regression (PLS) and Support Vector Machines Regression (SVMsR), as well as with a classification method, Support Vector Machines Classification (SVMsC), for carrying out calibration. A very fast spectrophotometer provided instantaneously and simultaneously the total transmitted radiation spectrum (I � ) and the cardiac-related pulsatile component (� I � ) superimposed on Iin human fingertips over a wavelength range from 900 to 1700 nm with resolution of 8 nm in 100 Hz sampling. From a family of Is including information relating to various BGL values, differential optical densities (� ODs (=log(1+� I � /I � )) were calculated and normalized by theODvalues at 1100 nm. Finally, the 2nd derivatives of the normalizedODs served as regressors. Subsequently, calibration models from regressors and regressands (the corresponding measured BGL or classified BGL values) were constructed with PCR, PLS, SVMsR and SVMsC. Each regression model showed a relatively good result by evaluating a 5-fold cross validation using total 100 data-sets: Clarke error grid analysis indicated a good correlation in each model compared with the measured BGL values, and the SVMsR calibration provided the best plot distributions. Good regression models were obtained by these three methods. This study suggests that pulse glucometry can produce clinically acceptable results when implemented with regression and classification type calibrations, and, through rapid BGL assessment, promises to offer a more practical, easier and more convenient way for diabetes screening and health care in normal subjects than is possible with existing methods.

The application of near infrared spectroscopy for quantitative analysis of cotton-polyester textile was investigated in the present work. A total of 214 cotton-polyester fabric samples, covering the range from 0% to 100% cotton were measured and analyzed. Partial least squares and least-squares support vector machine models with all variables as input data were established. Furthermore, successive projection algorithm was used to select effective wavelengths and establish the successive projection algorithm-least-squares support vector machine models, with the comparison of two other effective wavelength selection methods: loading weights analysis and regression coefficient analysis. The calibration and validation results show that the successive projection algorithm-least-squares support vector machine model outperformed not only the partial least squares and least-squares support vector machine models with all variables as inputs, but also the least-squares support vector machine models with loading weights analysis and regression coefficient analysis effective wavelength selection. The root mean squared error of calibration and root mean squared error of prediction values of the successive projection algorithm-least-squares support vector machine regression model with the optimal performance were 0.77% and 1.17%, respectively. The overall results demonstrated that near infrared spectroscopy combined with least-squares support vector machine and successive projection algorithm could provide a simple, rapid, economical and non-destructive method for determining the composition of cotton-polyester textiles.

Partial least square (PLS) methods (also sometimes called projection to latent structures) relate the information present in two data tables that collect measurements on the same set of observations. PLS methods proceed by deriving latent variables which are (optimal) linear combinations of the variables of a data table. When the goal is to find the shared information between two tables, the approach is equivalent to a correlation problem and the technique is then called partial least square correlation (PLSC) (also sometimes called PLS-SVD). In this case there are two sets of latent variables (one set per table), and these latent variables are required to have maximal covariance. When the goal is to predict one data table the other one, the technique is then called partial least square regression. In this case there is one set of latent variables (derived from the predictor table) and these latent variables are required to give the best possible prediction. In this paper we present and illustrate PLSC and PLSR and show how these descriptive multivariate analysis techniques can be extended to deal with inferential questions by using cross-validation techniques such as the bootstrap and permutation tests.

In semiconductor wafer fabrication, etching is one of the most critical processes, by which a material layer is selectively removed. Because of difficulty to correct a mistake caused by over etching, it is critical that etch should be performed correctly. This paper proposes a new approach for etch endpoint detection of small open area wafers. The traditional endpoint detection technique uses a few manually selected wavelengths, which are adequate for large open areas. As the integrated circuit devices continue to shrink in geometry and increase in device density, detecting the endpoint for small open areas presents a serious challenge to process engineers. In this work, a high-resolution optical emission spectroscopy (OES) sensor is used to provide the necessary sensitivity for detecting subtle endpoint signal. Partial Least Squares (PLS) method is used to analyze the OES data which reduces dimension of the data and increases gap between classes. Support Vector Machine (SVM) is employed to detect endpoint using the data after PLS. SVM classifies normal etching state and after endpoint state. Two data sets from OES are used in training PLS and SVM. The other data sets are used to test the performance of the model. The results show that the trained PLS and SVM hybrid algorithm model detects endpoint accurately.

Comparison of PLS and SVM models for soil organic matter and particle size using vis-NIR spectral libraries

We aimed to identify the browning of white adipocytes using partial least squares regression (PLSR), infrared spectral biomarkers, and partial least squares discriminant analysis (PLS-DA) with FTIR spectroscopy instead of molecular biology. PLSR helps distinguish human beige adipocytes treated with norepinephrine and rosiglitazone. When PLSR was based on the selected regions of 3997–3656 and 1618–938 cm−1, PLSR achieved an R2 of cross-validation of 88.95, a root mean square error of cross validation (RMSECV) of 2.13, and a ratio performance deviation (RPD) of 3.01. Infrared spectral biomarkers [1635 cm−1 (β-sheet amide I), 879–882, 860–3 cm−1 (A-form helix), and 629–38 cm−1 (OH out-of-plane bending)] were identified in human beige adipocytes based on spectral differences between human beige adipocytes and human white adipocytes, principal component analysis-linear discriminant analysis (PCA-LDA) cluster vector, U-test, and Fisher’s score per wavenumber. PLS-DA yielded a useful classification of adipocytes and expression distribution of adipogenesis genes in adipocytes. PLSR, infrared spectral biomarkers, and PLS-DA using FTIR spectroscopy are proposed as effective tools for identifying specific biological activities in a limited environment through features that do not require labeling and are relatively inexpensive in terms of time and labor.

ABSTRACTTextile products must be marked by fabric type and composition on the label and cotton is by far the most important fiber in the industry and often needs fast quantitative analysis. The corresponding standard methods are very time-consuming and labor-intensive. The work focuses on exploring the feasibility of combining near-infrared (NIR) spectroscopy and interval-based partial least squares (iPLS) for determining cotton content in textiles. Three types of partial least square (PLS)-based algorithms were used for experimental measurements. A total of 91 cloth samples with cotton content ranging from 0 to 100% (w/w) were collected and all compositions are commercially available on the market in China. In all cases, the original spectrum axis was split into 20 subintervals. As a result, three final models, i.e., the iPLS model on a single subinterval, the backward interval partial least squares (biPLS) model on the region remaining six subintervals, and the moving window partial least squares (mwPLS) model with a window of 75 variables, achieved better results than the full-spectrum PLS model. Also, no obvious differences in performance were observed for the three models. Thus, either iPLS or mwPLS was preferred considering their simplicity, which suggested that iPLS and mwPLS combined with NIR technique may have potential for the rapid determination of the cotton content of textile products with comparable accuracy to standard procedures. In addition, this approach may have commercial and regulatory advantages that avoid labor-intensive and time-consuming chemical analysis.

we propose a regression method using partial least square (PLS) technique and kernel method, which we refer to as kernel partial least square regression II to distinguish the conventional kernel PLS regression. The motivation of the conventional kernel PLS regression is to establish a coordinator system where the independent and dependent variables have a stronger correlation, and which models a regression model using the coordinator system. However, it projects independent variables into a reproducing kernel Hilbert space (RKHS) alone. The proposal extends the basic framework of conventional kernel PLS regression. The proposed method does not only project independent variables into the RKHS, but also dependent variables, and establishes a coordinator system where the independent and dependent variables have a stronger correlation. We use two function regression cases to evaluate the proposed method compared with the conventional kernel PLS regression. The regression performance of the proposed method has almost the same regression accuracy arising from the evaluation result, and this depends on the regression tasks. We explain the correlation calculations of our proposed method, conventional kernel PLS regression, and PLS regression. The meaning of correlation depends on the application in question. We also analyse and discuss the algorithm implementation, correlation meaning, and other issues for further development of the proposal.

Calibration of UV/Vis spectrophotometers: A review and comparison of different methods to estimate TSS and total and dissolved COD concentrations in sewers, WWTPs and rivers

The potential hazard of heavy metals in reclaimed mine soil has been attracted more and more attention. Hyperspectral inversion can be applied to predict the heavy metal content of the soil effectively. Three machine learning methods, Support Vector Machine (SVM), Random Forest (RF) and Extreme Learning Machine (ELM), are introduced in this paper, and then are compared with the Partial Least Squares (PLS) method. With the correlation analysis of heavy metal content and pretreatment spectral band, the models are constructed to predict the content of heavy metal in soil. The results show that the prediction results of machine learning methods are better than PLS, and ELM and RF are better than SVM. Analyzing the stability of the model, it can be found that the concentration of heavy metal samples will affect the prediction of ELM. Meanwhile, the stability of RF is the best than the other three models. RF algorithm has also the highest accuracy in the inversion of soil heavy metal research.

Detection of saffron adulteration with Crocus sativus style using NIR-hyperspectral imaging and chemometrics

It is very important for human health to supervise the use of food additives, because excessive use of food additives will cause harm to the human body, especially lead to organ failures and even cancers. Therefore, it is important to realize high-sensibility detection of benzoic acid, a widely used food additive. Based on the theory of electromagnetism, this research attempts to design a terahertz-enhanced metamaterial resonator, using a metamaterial resonator to achieve enhanced detection of benzoic acid additives by using terahertz technology. The absorption peak of the metamaterial resonator is designed to be 1.95 THz, and the effectiveness of the metamaterial resonator is verified. Firstly, the original THz spectra of benzoic acid aqueous solution samples based on metamaterial are collected. Secondly, smoothing, multivariate scattering correction (MSC), and smoothing combined with first derivative (SG + 1 D) methods are used to preprocess the spectra to study the better spectral pretreatment methods. Then, Uninformative Variable Elimination (UVE) and Competitive Adaptive Reweighted Sampling (CARS) are used to explore the optimal terahertz band selection method. Finally, Partial Least Squares (PLS) and Least square support vector machine (LS-SVM) models are established, respectively, to realize the enhanced detection of benzoic acid additives. The LS-SVM model combined with CARS has the best effect, with the correlation coefficient of prediction set (Rp) is 0.9953, the root mean square error of prediction set (RMSEP) is 7.3 × 10−6, and the limit of detection (LOD) is 2.3610 × 10−5 g/mL. The research results lay a foundation for THz spectral analysis of benzoic acid additives, so that THz technology-based detection of benzoic acid additives in food can reach requirements stipulated in the national standard. This research is of great significance for promoting the detection and analysis of trace additives in food, whose results can also serve as a reference to the detection of antibiotic residues, banned additives, and other trace substances.

Objective. Partial Least Squares (PLS) regression is a suitable linear decoder model for correlated and high dimensional neural data. This algorithm has been widely used in the application of brain–computer interface (BCI) for the decoding of motor parameters. PLS does not consider nonlinear relations between brain signal features. The nonlinear version of PLS that considers a nonlinear relationship between the latent variables has not been proposed for the decoding of intracranial data. This nonlinear model may cause overfitting in some cases due to a larger number of free parameters. In this paper, we develop a new version of nonlinear PLS, namely nonlinear sparse PLS (NLS PLS) and test it in BCI applications. Approach. In motor related BCI systems, improving the decoding accuracy of both kinetic and kinematic parameters of movement is crucial. To do this, two BCI datasets were chosen to decode the force amplitude and position of hand trajectory using the nonlinear and sparse versions of PLS algorithm. In our new NLS PLS method, we considered a polynomial relationship between the latent variables and used the lasso penalization in the latent space to avoid overfitting and to improve the decoding accuracy. Main results. Some linear and nonlinear based PLS models and our new proposed method, NLS PLS, were applied to the two datasets. According to our results, significant improvement from the NLS PLS method is confirmed over other methods. Our results show that nonlinear PLS outperforms generic PLS in the force decoding but it has lower accuracy in the hand trajectory decoding because of high dimensional feature space. By using lasso penalization, we presented a sparse nonlinear PLS-based model that outperforms generic PLS in both datasets and improves the coefficient of determination, 34% in the force decoding and 10% in the hand trajectory decoding. Significance. We constructed a simple PLS-based model that considers a nonlinear relationship between features and it is also robust to overfitting because of using the lasso penalty in the latent space. This model is suitable for a high dimensional and correlated datasets, like intracranial data and can improve the accuracy of estimation.