Search

The excessive content of additives in food is a radical problem that affects human health. However, traditional chemical methods are limited by a long cycle, low accuracy, and strong destructiveness, so a fast and accurate alternative is urgently needed. This paper proposes a prediction model introducing near-infrared spectroscopy and deep learning to perform fast and accurate non-destructive detection of artificial bright blue pigment in cream. The model results show that R

133 camelina samples were used to build the Fourier transform infrared (FT-IR) prediction model. Several methods have been used for the establishment of the predicting model, but support vector machine was rarely used in FT-IR area to build the prediction model. The aim of this study was to develop a new model for predicting protein with higher accuracy. In the spectra region 690–1700 cm$$^{-1}$$, the SVM method was better than that of PLS and PCR. In the development of SVM, the $$\hbox {R}_{\mathrm{RMSEC}}^{2}$$ and $$\hbox {R}_{\mathrm{RMSEP}}^{2}$$ of the model were 0.83963 and 0.96578 respectively, and the RPD was 5.5016. The RPD was greater than that of PLS and PCR. The FT-IR was effective in predicting the content of camelina protein and SVM was a better method to build prediction model.

Camelina is a promising feedstock as a result of its ability to provide high-quality edible oil and jet fuel. However, predicting its oil content currently requires time- and labor-intensive analyses. Near-infrared (NIR) spectroscopy provides a rapid, low-cost determination approach for oil seed characterization. The objective of this study was to develop a NIR model to predict the camelina oil content using 200 camelina seed simples. Partial least squares (PLS) regression and principal component regression (PCR) were used to compare the performance of calibration models to the full spectra range (4000–1000 cm–1). PLS regression showed better prediction performance than PCR. The optimal model provided excellent fitness, with a R2 of 0.94 and root mean square of prediction error of 0.495%, making the model useful in various applications, including quality assurance and screening. This study confirmed that the NIR method significantly reduces time (from 60 to 1 min) and cost [from 20 to 1 United States doll...

Artificial pigment is a common food additive in cream products. If added in excess, it will do harm to human body. At present, there is no research on the detection of cream pigment by Near Infrared (NIR) spectroscopy. In this paper, a method based on random forest was applied to determine the indigotine in cream. Weighting in the experiments was accomplished using analytical balances with precision as low as 0.0001 g. The NIR spectra data of cream with different concentration of indigotine were recorded. The original spectra was pretreated by SG smoothing, mean centering and second derivative. Random forest was applied to establish a quantitative analysis model for cream pigment content, and multiple evaluation criteria were selected to comprehensively evaluate the model. The R 2 was 0.9402, R M S E P was 0.2509 and R P D was 4.0893. Consequently, NIR spectroscopy, combined with data pretreatments and random forest model, was confirmed to be an interesting tool for non-destructive evaluation of pigment content in cream.

Microbial cells cultivation is not only the origin, but also the foundation of microbiology. Researches in microbiology can only be carried out when the microbial cells can be cultured. However, conventional microbial cell cultivation is not only time consuming and labour intensive, but human error is also inevitable. Recent years, automated, modularised microbial cells micro-cultivation systems with small volume, good controllability, and equipped with real-time monitoring system have attracted great attention in microbiology. This review presents the state-of-the-art micro-cultivation systems which are implemented in microbial cells cultivation. The key development, applications of various system classified based on their construction, and the prospects of micro-cultivation system are discussed and insights into them are also provided.微生物培养是微生物学的起源和根本，成功的微生物培养是进行后续研究的重要前提与基础。但是，微生物培养操作不仅耗费了科研人员大量的精力和时间，还存在着极大的人为误差。近年来，容量小、高通量、模块化、可操作性良好并可进行在线检测的微生物微培养系统得到了微生物学领域的广泛关注。文中介绍了应用于微生物学领域的微培养系统，并按系统构成分类讨论了微生物微培养系统的发展、应用和展望。.

Based on near-infrared spectrum and interval random forest, a fast quantitative analysis method for the content of sunset yellow content was established. The spectra of 132 cream pigment samples were obtained by FT-NIR spectrometer, and various preprocessing methods such as standard normal variable (SNV), wavelet transform (WT), and SG (Savitzky-Golay) were used to smooth and denoise the original spectrum. In this paper, WT and first-order differentiation were used as pretreatment and the Kennard-Stone algorithm was used to divide the data set. Finally interval partial least squares, partial least squares, interval random forest and random forest were used to construct an optimal quantitative analysis model. The experimental results show that the interval random forest can find the best sub-interval to achieve the prediction ability of the model. The R2 (the coefficient of determination) and RMSEP (root mean square error of the prediction) of the prediction set are 0.8965 and 0.2454, respectively. The research results show that near-infrared spectroscopy combined with interval random forest algorithm is a fast and non-destructive method to detect the content of sunset yellow in cream.

The VLAD (vector of locally aggregated descriptors) representation, derived from BoF and Fisher kernel, has shown its efficiency in the field of image search. However, assigning local descriptors to a codeword is a hard voting process, which does not consider the uncertainty and the plausibility for single codeword. In this paper, we propose an approach to combine VLAD with locality-constrained linear coding, as opposed to the original one, considering several nearest neighbors when assigning local descriptors and computing weights. In order to evaluate our proposed method, experiments are conducted on several image classification benchmarks, using VLAD for comparison. The experimental results show that our method stably outperforms VLAD in terms of classification accuracy, while producing feature representation of the same dimension without much additional computational cost.