In order to reduce the uncertainty of the genetic algorithm (GA) in optimizing the near-infrared spectral calibration model and avoid the loss of spectral information of the unselected variables, a strategy of fusing consensus models is proposed to measure the soluble solids content (SSC) in peaches. A total of 266 peach samples were collected at four arrivals, and their interactance spectra were scanned by an integrated analyzer prototype, and then an internal index of SSC was destructively measured by the standard refractometry method. The near-infrared spectra were pre-processed with mean centering and were selected successively with a genetic algorithm (GA) to construct the consensus model, which was integrated with two member models with optimized weightings. One was the conventional partial least square (PLS) optimized with GA selected variables (PLS_GA), and the other one was the derived PLS developed with residual variables after GA selections (PLS_RV). The performance of PLS_RV models showed some useful spectral information related to peaches’ SSC and someone performed close to the full-spectral-based PLS model. Among these 10 runs, consensus models obtained a lower root mean squared errors of prediction (RMSEP), with an average of 1.106% and standard deviation (SD) of 0.0068, and performed better than that of the optimized PLS_GA models, which achieved a RMSEP of average 1.116% with SD of 0.0097. It can be concluded that the application of fusion strategy can reduce the fluctuation uncertainty of a model optimized by genetic algorithm, fulfill the utilization of the spectral information amount, and realize the rapid detection of the internal quality of the peach.

Egg freshness is of great importance to daily nutrition and food consumption. In this work, visible near-infrared (vis-NIR) spectroscopy combined with the sparsity of interval partial least square regression (iPLS) were carried out to measure the egg’s freshness by semi-transmittance spectral acquisition. A fiber spectrometer with a spectral range of 550-985 nm was embedded in the developed spectral scanner, which was designed with rich light irradiation mode from another two reflective surfaces. The semi-transmittance spectra were collected from the waist of eggs and monitored every two days. Haugh unit (HU) is a key indicator of egg’s freshness, and ranged 56–91 in 14 days after delivery. The profile of spectra was analyzed the relation to the changes of egg’s freshness. A series of iPLS models were constructed on the basis of spectral intervals at different divisions of the spectral region to predict the egg’s HU, and then the least absolute shrinkage and selection operator (Lasso) was used to sparse the number of iPLS member models acting as a role of model selection and fusion regression. By optimization of the number of spectral intervals in the range of 1 to 40, the 26^th fusion model obtained the best performance with the minimum root mean of squared error of prediction (RMSEP) of 5.161, and performed the best among the general PLS model and other intervals-combined PLS models. This study provided a new, rapid, and reliable method for the non-destructive and in-site determination of egg’s freshness.

A novel multi-classification method, which integrates the elastic net and probabilistic support vector machine, was proposed to solve this problem in cancer detection with gene expression profile data of platelets, whose problems mainly are a kind of multi-class classification problem with high dimension, small samples, and collinear data. The strategy of one-against-all (OVA) was employed to decompose the multi-classification problem into a series of binary classification problems. The elastic net was used to select class-specific features for the binary classification problems, and the probabilistic support vector machine was used to make the outputs of the binary classifiers with class-specific features comparable. Simulation data and gene expression profile data were intended to verify the effectiveness of the proposed method. Results indicate that the proposed method can automatically select class-specific features and obtain better performance of classification than that of the conventional multi-class classification methods, which are mainly based on global feature selection methods. This study indicates the proposed method is suitable for general multi-classification problems featured with high-dimension, small samples, and collinear data.

Detection of fruit traits by using near-infrared (NIR) spectroscopy may encounter out-of-distribution samples that exceed the generalization ability of a constructed calibration model. Therefore, confidence analysis for a given prediction is required, but this cannot be done using common calibration models of NIR spectroscopy. To address this issue, this paper studied the Gaussian process regression (GPR) for fruit traits detection using NIR spectroscopy. The mean and variance of the GPR were used as the predicted value and confidence, respectively. To show this, a real NIR data set related to dry matter content measurements in mango was used. Compared to partial least squares regression (PLSR), GPR showed approximately 14% lower root mean squared error (RMSE) for the in-distribution test set. Compared with no confidence analysis, using the variance of GPR to remove abnormal samples made GPR and PLSR showed approximately 58% and 10% lower RMSE on the mixed distribution test set, respectively (when the type 1 error rate was set to 0.1). Compared with traditional one-class classification methods, the variance of the GPR can be used to effectively eliminate poorly predicted samples.

In some cases, near-infrared spectra (NIRS) make the prediction of quantitative models unreliable, and the choice of a suitable number of latent variables (LVs) for partial least square (PLS) is difficult. In this case, a strategy of fusing member models with important information is gradually becoming valued in recent research. In this work, a series of PLS regression models were developed with an increasing number of LVs as member models. Then, the least absolute shrinkage and selection operator (Lasso) was employed as the model’s selection access to sparse uninformative ones among these PLS member models. Deviation weighted fusion (DW-F), partial least squares regression coefficient fusion (PLS-F), and ridge regression coefficient fusion (RR-F) were comparatively used further to fuse the above sparsed member models, respectively. Three spectral datasets, including six attributes in NIR data of corn, apple, and marzipan, respectively, were applied in order to validate the feasibility of this fusion algorithm. Six fusion models of the above attributes performed better than the general optimal PLS model, with a noticeable enhancement of root mean errors squared of prediction (RMSEP) arriving at its highest at 80%. It also reduced more than half of the spectral bands; the DW-F especially showed its excellent fusing capacity and obtained the best performance. Results show that the preferred strategy of DW-F model combined with Lasso selection can make full use of spectral information, and significantly improve the prediction accuracy of fusion models.

Methanol gasoline blends are a more economical, and environmentally friendly fuels than gasoline alone, and are widely used in the transportation industry. The content of methanol in methanol gasoline plays an important role in ensuring the quality of gasoline. In some solutions, due to the shortage of energy and illegal profits, the problem of gasoline adulteration and its fineness, has received more and more attention, which would seriously affect the operating condition and service life of internal combustion engines. Therefore, it is very important to identify the correct level of gasoline. However, the traditional detection method is complex and time-consuming. To this end, the feasibility of using attenuated total reflectance Fourier transform infrared (ATR-FTIR) methods coupled with chemometrics methods were investigated to quantitatively and qualitatively analyze methanol gasoline. The qualitative analysis result of partial least squares discriminant analysis (PLS-DA) obtained 100% and 98.66% accuracy in the calibration set and the prediction set, respectively. As for quantitative analysis; two regression algorithms of partial least squares regression (PLSR) and the least square support vector machine (LS-SVM), as well as two variables selection methods of the successive projections algorithm (UVE) competitive adaptive reweighted sampling (CARS) and uninformative variable elimination (UVE) were combined to establish the quantitative model. By comparing the performance of the optimal models; the UVE-PLSR model performed best with a residual predictive deviation (RPD) value of 6.420. The qualitative and quantitative analysis results demonstrate the feasibility of using ATR-FTIR spectra to detect the methanol in methanol gasoline. It is believed that the promising IR spectra will be widely used in gasoline energy quality control in the further.