[State Recognition of Solid Fermentation Process Based on Near Infrared Spectroscopy with Adaboost and Spectral Regression Discriminant Analysis].

In order to achieve the rapid monitoring of process state of solid state fermentation (SSF), this study attempted to qualitative identification of process state of SSF of feed protein by use of Fourier transform near infrared (FT-NIR) spectroscopy analysis technique. Even more specifically, the FT-NIR spectroscopy combined with Adaboost-SRDA-NN integrated learning algorithm as an ideal analysis tool was used to accurately and rapidly monitor chemical and physical changes in SSF of feed protein without the need for chemical analysis. Firstly, the raw spectra of all the 140 fermentation samples obtained were collected by use of Fourier transform near infrared spectrometer (Antaris II), and the raw spectra obtained were preprocessed by use of standard normal variate transformation (SNV) spectral preprocessing algorithm. Thereafter, the characteristic information of the preprocessed spectra was extracted by use of spectral regression discriminant analysis (SRDA). Finally, nearest neighbors (NN) algorithm as a basic classifier was selected and building state recognition model to identify different fermentation samples in the validation set. Experimental results showed as follows: the SRDA-NN model revealed its superior performance by compared with other two different NN models, which were developed by use of the feature information form principal component analysis (PCA) and linear discriminant analysis (LDA), and the correct recognition rate of SRDA-NN model achieved 94.28% in the validation set. In this work, in order to further improve the recognition accuracy of the final model, Adaboost-SRDA-NN ensemble learning algorithm was proposed by integrated the Adaboost and SRDA-NN methods, and the presented algorithm was used to construct the online monitoring model of process state of SSF of feed protein. Experimental results showed as follows: the prediction performance of SRDA-NN model has been further enhanced by use of Adaboost lifting algorithm, and the correct recognition rate of the Adaboost-SRDA-NN model achieved 100% in the validation set. The overall results demonstrate that SRDA algorithm can effectively achieve the spectral feature information extraction to the spectral dimension reduction in model calibration process of qualitative analysis of NIR spectroscopy. In addition, the Adaboost lifting algorithm can improve the classification accuracy of the final model. The results obtained in this work can provide research foundation for developing online monitoring instruments for the monitoring of SSF process.

[Study on Quality Identification of Olive Oil Based on Near Infrared Spectra].

Currently on the market, the sale of olive oil is mainly divided into extra virgin olive oil and common virgin olive oil. In order to identify the qualities of two different olive oils, a new method to identify the quality of olive oil with siPLS-IRIV-PCA algorithm is developed. Based on the near infrared spectral data of olive oil, the efficient spectral subintervals are selected with a synergy interval partial least squares (siPLS). The performance of the model is evaluated by using the root mean square error of cross-validation (RMSECV). The characteristic wavelengths are selected from the efficient spectral subintervals by iteratively retains informative variables (IRIV) algorithm. Principal component analysis (PCA) model is constructed based on the selected characteristic wavelengths. The samples of 90 groups of extra virgin olive oil and 90 groups of common olive oil are identified. PCA uses 1 427 wavelength variables as input variables and the contribution rates of the first two principal components are 51.891 8% and 26.473 2% respectively. siPLS-PCA uses 408 wavelength variables as input variables and the contribution rates of the first two principal components are 56.039 1% and 36.2355%. siPLS-IRIV-PCA uses 6 wavelength variables as input variables and the contribution rates of the first two principal components are 66.347 6% and 32.3043%. The result shows that, compared with PCA and siPLS-PCA, siPLS-IRIV-PCA has the best identification performance. The method is simple and convenient and has a high identification degree which offers a new approach to identify the quality of olive oil.

[A wavelength selection approach of near infrared spectra Based on SCARS strategy and its application].

According to the characteristics of near infrared spectral(NIR)data, a new tactic called stability competitive adaptive reweighted sampling (SCARS) is employed to select characteristic wavelength variables of NIR data to build PLS model. This method is based on the stability of variables in PLS model. SCARS algorithm consists of a number of loops. In each loop, the stability of each corresponding variable is computed at first. Then enforced wavelength selection and adaptive reweighted sampling (ARS) is used to select important variables according to the stability of variables. The selected variables are kept as a variable subset and further used in the next loop. After the running of all loops, a number of subsets of variables are obtained and root mean squared error of cross validation (RMSECV) of PLS models is computed. The subset of variables with the lowest RMSECV is considered as the optimal variable subset. Validated by NIR data set of protein fodder solid-state fermentation process, the SCARS-PLS prediction model is better than PLS models based on wavelengths selected by competitive adaptive reweighted sampling (CARS) and Monte Carlo uninformative variable elimination (MC-UVE) methods. As a result, twenty one wavelength variables are selected by SCARS method to build the PLS prediction model with the predicted root mean square error (RMSEP) valued at 0.0543 and correlation coefficient (Rp) 0.9908. The results show that SCARS tactic can efficiently improve the accuracy and stability of NIR wavelength variables selection and optimize the precision of prediction model in solid-state fermentation process. The SCARS method has a certain application value.

[Determination of process variable pH in solid-state fermentation by FT-NIR spectroscopy and extreme learning machine (ELM)].

Fourier transform near-infrared (FT-NIR) spectroscopy was attempted to determine pH, which is one of the key process parameters in solid-state fermentation of crop straws. First, near infrared spectra of 140 solid-state fermented product samples were obtained by near infrared spectroscopy system in the wavelength range of 10 000-4 000 cm(-1), and then the reference measurement results of pH were achieved by pH meter. Thereafter, the extreme learning machine (ELM) was employed to calibrate model. In the calibration model, the optimal number of PCs and the optimal number of hidden-layer nodes of ELM network were determined by the cross-validation. Experimental results showed that the optimal ELM model was achieved with 1040-1 topology construction as follows: R(p) = 0.961 8 and RMSEP = 0.104 4 in the prediction set. The research achievement could provide technological basis for the on-line measurement of the process parameters in solid-state fermentation.

Long-living lotus: germination and soil {gamma}-irradiation of centuries-old fruits, and cultivation, growth, and phenotypic abnormalities of offspring.

Sacred lotus (Nelumbo nucifera) has been cultivated as a crop in Asia for thousands of years. An ∼1300-yr-old lotus fruit, recovered from an originally cultivated but now dry lakebed in northeastern China, is the oldest germinated and directly (14)C-dated fruit known. In 1996, we traveled to the dry lake at Xipaozi Village, China, the source of the old viable fruits. We identified all of the landmarks recorded by botanist Ichiro Ohga some 80 yr ago when he first studied the deposit, but found that the fruits are now rare. We (1) cataloged a total of 60 lotus fruits; (2) germinated four fruits having physical ages of 200-500 yr by (14)C dating; (3) measured the rapid germination of the old fruits and the initially fast growth and short dormancy of their seedlings; (4) recorded abnormal phenotypes in their leaves, stalks, roots, and rhizomes; (5) determined γ-radiation of ∼2.0 mGy/yr in the lotus-bearing beds; and (6) measured stratigraphic sequences of the lakebed strata. The total γ-irradiation of the old fruits of 0.1-3 Gy (gray, the unit of absorbed dosage defined as 1 joule/kg; 1 Gy = 100 rad), evidently resulting in certain of the abnormal phenotypes noted in their seedlings, represents the longest natural radiobiology experiment yet recorded. Most of the lotus abnormalities resemble those of chronically irradiated plants exposed to much higher irradiances. Though the chronic exposure of the old fruits to low-dose γ-radiation may be responsible in part for the notably weak growth and mutant phenotypes of the seedlings, it has not affected seed viability. All seeds presumably repair cellular damage before germination. Understanding of repair mechanisms in the old lotus seeds may provide insight to the aging process applicable also to other organisms.