检索结果-内蒙古大学图书馆

Preparation and physicochemical/antimicrobial characteristics of asparagus cellulose􀂿􀀃􀁏􀁐􀁖􀀃􀁆􀁒􀁑􀁗􀁄􀁌􀁑􀁌􀁑􀁊􀀃􀁔􀁘􀁈􀁕􀁆􀁈􀁗􀁌􀁑

学校读者我要写书评

暂无评论

Food Science and Human Wellness 2021年第2期10卷 251-257页

作者： Tao Jin Ling Yan Wei Liu Shuai Liu Changhong Liu Lei Zheng School of Food and Biological Engineering Hefei University of TechnologyHefei 230009China Intelligent Control and Compute Vision Lab Hefei UniversityHefei 230601China Research Laboratory of Agricultural Environment and Food Safety Anhui Modern Agricultural Industry Technology SystemHefei230009China

Due to the increased potential for application of natural biopolymers in the food industry,the goal of this study was to prospectively produce antimicrobial films using asparagus *** this study,cellulose was extracted from asparagus residue,and then 3 cellulose solutions of 0.008,0.01 and 0.025 g/mL were applied to prepare films using a phase inversion *** were characterized by Fourier transform infrared spectroscopy(FTIR),X-ray diffraction(XRD),thermal gravimetric analysis(TGA)and scanning electron microscopy(SEM).The film produced by 0.01 g/mL asparagus cellulose solution exhibited a swelling ratio of 125.4%and excellent antimicrobial activity against Escherichia coli and Staphylococcus aureus using the disk agar diffusion *** study presents a promising method for producing antimicrobial films with asparagus residue.

关键词： Asparagus Cellulose films Quercetin Antimicrobial properties

Determination of benzo(a)pyrene in peanut oil based on Raman spectroscopy and machine learning methods

学校读者我要写书评

暂无评论

SPECTROCHIMICA ACTA PART A-MOLECULAR AND BIOMOLECULAR SPECTROSCOPY 2023年第1期299卷 122806页

作者： Liu, Wei Sun, Shengai Liu, Yang Deng, Haiyang Hong, Fei Liu, Changhong Zheng, Lei Hefei Univ Intelligent Control & Compute Vision Lab Hefei 230601 Peoples R China Hefei Univ Technol Sch Food & Biol Engn Hefei 230009 Peoples R China Anhui Modern Agr Ind Technol Syst Res Lab Agr Environm & Food Safety Hefei 230009 Peoples R China

Benzo(a)pyrene (BaP) generated in the production process of oil is harmful to human severely as a kind of carcinogenic substance. In this study, the qualitative and quantitative detection of BaP concentration in peanut oil was investigated based on Raman spectroscopy combined with machine learning methods. The glass substrates and magnetron sputtered gold substrates for the Raman spectra were compared and the data preprocessing methods of principal component analysis (PCA) and t-distributed stochastic neighbor embedding (tSNE) were used to process Raman signal. Back propagation neural network (BPNN), partial least squares regression (PLSR), support vector machine (SVM) and random forest (RF) algorithms were developed to obtain the qualitative and quantitative detection model of BaP concentration in peanut oil. The results showed that the Raman spectra with the glass substrate was more suitable for the BaP detection than magnetron sputtered gold substrates. RF combined with t-SNE could achieve an accuracy of 97.5% in the qualitative detection of BaP concentration levels in model validation experiment, and the correlation coefficient of the prediction set (Rp) in the quantitative detection was 0.9932, the root mean square error (RMSEP) was 0.8323 & mu;g/kg and the bias was 0.1316 & mu;g/kg. It can be concluded that Raman spectroscopy combined with machine learning methods could provide an effective method for the rapid determination of BaP concentration in peanut oil.

关键词： Peanut oil Benzo(a)pyrene Raman spectroscopy Machine learning methods

Identification of varieties of wheat seeds based on multispectral imaging combined with improved YOLOv5

学校读者我要写书评

暂无评论

Food Physics

Food Physics 2025年 2卷

作者： Liu, Wei Liu, Yang Hong, Fei Li, Jiaming Jiang, Quan Kong, Lingfei Liu, Changhong Zheng, Lei Intelligent Control and Compute Vision Lab Hefei University Hefei 230601 China School of Food and Biological Engineering Hefei University of Technology Hefei 230009 China Research Laboratory of Agricultural Environment and Food Safety Anhui Modern Agricultural Industry Technology System Hefei 230009 China

The identification of seed variety is important in wheat production because the growth and yield are highly related with its variety. Traditional identification methods for wheat seed varieties were suffered with time consuming and contamination. This study proposed a method for convenient identification of wheat seed varieties by using improved YOLOv5 combined with multispectral images. Three optimal spectral bands images including 405 nm, 570 nm and 890 nm were selected to fuse new image from all 19 bands using Genetic algorithm and confusion matrix. The YOLOv5s model for wheat seed variety identification was improved by adding a convolutional block attention module (CBAM) and the identification model was developed with the fusion images. The identification performance of proposed method achieved an accuracy of 99.38 % in testing set, which was better than traditional VOLOv5 with RGB images or with the multispectral images. Meanwhile, the evaluation indexes of the model such as P/%, R/%, F1/% and mAP/% were all higher than 90 %, which showed that the method was suitable for identification of wheat seeds variety rapidly and non-destructively. © 2024 KeAi Communications Co., Ltd

关键词： Attention mechanism Deep learning Image fusion Multispectral image Variety identification

Rapid Detection of Peanut Oil Oxidation by Data Fusion Strategy Based on Sers and Electronic Nose Technology

学校读者我要写书评

暂无评论

SSRN 2023年

作者： Liu, Wei Hong, Fei Sun, Shengai Liu, Yang Deng, Haiyang Liu, Changhong Zheng, Lei Intelligent Control and Compute Vision Lab Hefei University Hefei230601 China School of Food and Biological Engineering Hefei University of Technology Hefei230009 China Research Laboratory of Agricultural Environment and Food Safety Anhui Modern Agricultural Industry Technology System Hefei230009 China

The oxidation of edible vegetable oils generates many toxic by-products that will result in poor flavor and threaten to human health. In this study, surface-enhanced Raman spectroscopy (SERS) and electronic nose technology (E-nose) were combined to detect peanut oil oxidation rapidly and accurately. The best characteristic spectral region associated with the oxidation of peanut oil were found from799-1073 cm-1 using Raman spectroscopy with surface-enhanced gold substrate. Three different data fusion strategies with different machine learning methods were compared to obtain the best qualitative and quantitative prediction model. The results showed that the data fusion strategy could effectively improve the model prediction performance. BPNN and RF in low-level fusion could identify the peanut oil peroxide levels well with Ac and Ap reaching 100%. The best quantitative prediction model for peroxide value was obtained by t-SNE-RF model in the intermediate fusion strategy. It can be concluded that the combination of surface-enhanced Raman spectroscopy and electron nose technique is an effective method for rapid determination of the oxidation status of peanut oil. © 2023, The Authors. All rights reserved.

关键词： Oxidation

Determination of Benzo(A)Pyrene in Peanut Oil Based on Raman Spectroscopy and Machine Learning Methods

学校读者我要写书评

暂无评论

SSRN 2023年

作者： Liu, Wei Sun, Shengai Liu, Yang Deng, Haiyang Hong, Fei Liu, Changhong Zheng, Lei Intelligent Control and Compute Vision Lab Hefei University Hefei230601 China School of Food and Biological Engineering Hefei University of Technology Hefei230009 China Research Laboratory of Agricultural Environment and Food Safety Anhui Modern Agricultural Industry Technology System Hefei230009 China

Benzo(a)pyrene (BaP) generated in the production process of oi is harmful to human severely as a kind of carcinogenic substance. In this paper, the qualitative and quantitative detection of BaP content in peanut oil was investigated based on Raman spectroscopy combined with machine learning methods. The glass substrates and magnetron sputtered gold substrates for the Raman spectra of peanut oil were compared and the data preprocessing methods of principal component analysis (PCA) and t-distributed stochastic neighbor embedding (t-SNE) were used to process Raman data. Back propagation neural network (BPNN), partial least squares regression (PLSR), support vector machine (SVM) and random forest (RF) algorithms were developed to obtain the qualitative and quantitative detection model of BaP content in peanut oil. The results showed that the Raman spectral with the glass substrate was more suitable for the BaP detection than magnetron sputtered gold substrates. RF combined with PCA, t-SNE could achieve an accuracy of 100% in the qualitative detection of BaP concentration levels, and the correlation coefficient (R) of the prediction set in the quantitative detection was 0.9996, the root mean square error (RMSE) was 0.1853 ug/kg and the bias was 0.0121 ug/kg. It can be concluded that Raman spectroscopy combined with machine learning methods can provide an effective method for the rapid determination of benzo(a)pyrene concentration in peanut oils. © 2023, The Authors. All rights reserved.

关键词： Principal component analysis

Identification of Wheat Varieties Based on Multispectral Imaging Combined with Improved Yolov5

学校读者我要写书评

暂无评论

SSRN 2023年

作者： Liu, Wei Liu, Yang Hong, Fei Li, Jiaming Jiang, Quan Kong, Lingfei Liu, Changhong Zheng, Lei Intelligent Control and Compute Vision Lab Hefei University Hefei230601 China School of Food and Biological Engineering Hefei University of Technology Hefei230009 China Research Laboratory of Agricultural Environment and Food Safety Anhui Modern Agricultural Industry Technology System Hefei230009 China

The wheat seed variety detection is important in wheat production because the growth and yield is highly related with its variety. Traditional discrimination methods for wheat seed varieties were suffered with time consuming and contamination. In this study, multispectral imaging technology combined with improved YOLOv5s was proposed. Three optimal spectral bands images were selected from all 19 bands using Genetic algorithm and confusion matrix and then the new images were fused with the three band images. The improved YOLOv5s with CBAM module was developed to train the identification model of wheat varieties using fusion images. The experimental results showed that the average precision of the model from proposed method in test set reached 99.38% that were better than the traditional YOLOSv5s model. Meanwhile, the evaluation indexes of the model such as P/%, R/%, F1/% and mAP/% were all higher than 90%. The results showed that the method could be used for wheat variety identification rapidly and non-destructively. © 2023, The Authors. All rights reserved.

关键词： Image fusion

Non-Destructive Detection of Inner Mildewed Sunflower Seeds Based on Multimodal Fusion Method

学校读者我要写书评

暂无评论

SSRN 2024年

作者： Liu, Wei Deng, Haiyang Chen, Jianglin Zuo, Bowei Liu, Changhong Zheng, Lei Intelligent Control and Compute Vision Lab Hefei University Hefei230601 China Qiaqia Food Co. Ltd Hefei Anhui230009 China School of Food and Biological Engineering Hefei University of Technology Hefei230009 China Research Laboratory of Agricultural Environment and Food Safety Anhui Modern Agricultural Industry Technology System Hefei230009 China

Inner mildew is the most harmful factors that impact the quality of sunflower seeds. In this study, multispectral imaging technology including 19 wavelengths was combined with deep learning methods to discriminate the inner mildewed sunflower seeds. Support vector machines-Sequential Minimal Optimization (SVM-SMO) and ResNet50 containing Shuffle Attention (SA) was developed to obtain the disclination model with spectral features and spectral images features, respectively. The distribution function was constructed for the output results of SVM-SMO model and ResNet50 network. Then a multimodal fusion deep learning method based on joint probability distribution was established. The results showed that the fusion model was the most efficient method that could achieve the precision with 88.0%, accuracy with 90.0%, recall with 91.7%, F1 score with 89.8% and balance accuracy with 90.1%. It could be concluded the multispectral image combined with proposed multimodal fusion method was efficiency to discriminate inner mildew of sunflower seeds. © 2024, The Authors. All rights reserved.

关键词： Support vector machines

Application of Multispectral Imaging Combined with Machine Learning for Rapid and Non-Destructive Detection of Zearalenone (Zen) in Maize

学校读者我要写书评

暂无评论

SSRN 2022年

作者： Liu, Wei Deng, Haiyang Shi, Yule Liu, Changhong Zheng, Lei Xia, Yiming Intelligent Control and Compute Vision Lab Hefei University Hefei230601 China School of Food and Biological Engineering Hefei University of Technology Hefei230009 China Research Laboratory of Agricultural Environment and Food Safety Anhui Modern Agricultural Industry Technology System Hefei230009 China

Maiz e is inevitably contaminated by zearalenone (ZEN) that will cause serious harm to human beings. In this study, multispectral imaging (MSI) technology combined with different machine learning were used to detect ZEN content in maize. The wavelengths that were most related to ZEN concentration in maize could be selected by genetic algorithm with a back-propagation neural network (GA-BPNN). Our results showed that ZEN contamination level could be detected with the accuracy of 93.33% by GA-BPNN method. In addition, for quantitative prediction of ZEN contamination content GA-BPNN algorithm was the best method with the correlation coefficient ( Rp ), the root means square error (RMSEP), residual predictive deviation (RPD) and bias achieved to 0.95, 3.66 μg/kg, 5.39 and 1.55 μg/kg, respectively in prediction set. It can be concluded that multispectral imaging combined with machine learning was applicable for rapid measurement of ZEN content in maize. © 2022, The Authors. All rights reserved.

关键词： Genetic algorithms

Corrigendum to "Rapid determination of aflatoxin B1 concentration in soybean oil using terahertz spectroscopy with chemometric methods" [Food Chemistry 293 (2019) 213-219]

学校读者我要写书评

暂无评论

Food chemistry 2020年 316卷 126131页

作者： Wei Liu Pengguang Zhao Chaosheng Wu Changhong Liu Jianbo Yang Lei Zheng School of Food and Biological Engineering Hefei University of Technology Hefei 230009 China Intelligent Control and Compute Vision Lab Hefei University Hefei 230601 China. School of Food and Biological Engineering Hefei University of Technology Hefei 230009 China. Rice Research Institute Anhui Academy of Agricultural Sciences Hefei 230031 China. Research Laboratory of Agricultural Environment and Food Safety Anhui Modern Agricultural Industry Technology System Hefei 230009 China. Electronic address: lzheng@***.