Evaluation of Mutton Adulteration under the Effect of Mutton Flavour Essence Using Hyperspectral Imaging Combined with Machine Learning and Sparrow Search Algorithm

Article Chemistry, Applied

Soluble solid content and firmness index assessment and maturity discrimination of Malus micromalus Makino based on near-infrared hyperspectral imaging

Qiang Gao et al.

Summary: The study utilized NIR-HSI combined with chemometrics to establish effective wavelength extraction and prediction models for accurately evaluating the quality of Malus micromalus Makino.

FOOD CHEMISTRY (2022)

Add to Collection

Article Food Science & Technology

Rapid and nondestructive quantification of deoxynivalenol in individual wheat kernels using near-infrared hyperspectral imaging and chemometrics

Guanghui Shen et al.

Summary: This study evaluated the feasibility of using NIR-HSI and chemometrics for quantifying DON in individual wheat kernels, finding that different types of kernels contained varying levels of DON, with LPLS-S algorithm showing the best performance in model construction.

FOOD CONTROL (2022)

Add to Collection

Article Food Science & Technology

Identification of coumarin-based food additives using terahertz spectroscopy combined with manifold learning and improved support vector machine

Tao Chen et al.

Summary: This study successfully identified coumarin-based food additives with high accuracy by combining THz spectroscopy, manifold learning, and improved SVM model. The improved model showed excellent performance in identification and can be applied in the field of food safety to enhance efficiency in detection.

JOURNAL OF FOOD SCIENCE (2022)

Add to Collection

Article Food Science & Technology

Quantitative Detection of Myoglobin Content in Tan Mutton During Cold Storage by Near-infrared Hyperspectral Imaging

Yourui Sun et al.

Summary: This study utilized near-infrared hyperspectral imaging system to rapidly detect myoglobin content in Tan mutton and built predictive models. The results provide a theoretical reference for rapid evaluation of myoglobin content in other animal products.

FOOD ANALYTICAL METHODS (2022)

Add to Collection

Article Chemistry, Applied

Identification and quantification of fox meat in meat products by liquid chromatography-tandem mass spectrometry

Yingying Zhang et al.

Summary: Food adulteration is a global problem that threatens public health safety and the healthy development of the food industry. This study established an LC-MS/MS method for accurate identification and quantitative analysis of fox meat products, successfully screening fox-specific peptides for precise quantification.

FOOD CHEMISTRY (2022)

Add to Collection

Article Spectroscopy

Rapid in measurements of brown tide algae cell concentrations using fluorescence spectrometry and generalized regression neural network

Ying Chen et al.

Summary: This paper presents a method that combines three-dimensional fluorescence spectroscopy and generalized regression neural network for accurately and efficiently detecting the concentration of Aureococcus anophagefferens (A. anophagefferens). The fluorescence spectrometer is used to collect spectra of A. anophagefferens with different growth cycles and concentrations. The importance of spectral features is ranked using the gradient boosting decision tree algorithm, and the input features with high importance and the concentration of algal cells are used to establish a generalized regression neural network model optimized by the improved sparrow search algorithm (FASSA-GRNN). The predicted results of the FASSA-GRNN model show high accuracy, and the FASSA algorithm allows for faster convergence to the global optimum during the training process. This research provides a new method for predicting the concentration of algae cells.

SPECTROCHIMICA ACTA PART A-MOLECULAR AND BIOMOLECULAR SPECTROSCOPY (2022)

Add to Collection

Article Spectroscopy

Prediction of milk protein content based on improved sparrow search algorithm and optimized back propagation neural network

Jiangping Liu et al.

Summary: This study proposed a model based on an improved sparrow search algorithm and optimized back propagation neural network for predicting milk protein content. Experimental results demonstrated that the BP model optimized by the improved sparrow search algorithm had better prediction accuracy for milk protein content.

SPECTROSCOPY LETTERS (2022)

Add to Collection

Article Food Science & Technology

Double-layer indicator films aided by BP-ANN-enabled freshness detection on packaged meat products

Yanan Sun et al.

Summary: This study proposed the use of raspberry anthocyanins as a freshness indicator for packaged meat products. The stability of the indicator was improved by incorporating it into low-acyl gellan and forming an outer layer with chitosan. The double-layer indicator film showed strong mechanical properties, low water vapor permeability, and good structural compatibility. The neural network model accurately predicted the freshness of the meat products based on the color change of the films.

FOOD PACKAGING AND SHELF LIFE (2022)

Add to Collection

Article Food Science & Technology

The Use of Electronic Nose in the Quality Evaluation and Adulteration Identification of Beijing-You Chicken

Jingru Chen et al.

Summary: This study aimed to uncover the unique meat characteristics of Beijing-you chicken (BJY) and compare its quality and flavor with Luhua chicken (LH) and Arbor Acres broiler (AA) at their typical market ages. The results revealed that BJY meat had higher content of essential amino acids, arachidonic acid, inosine monophosphate (IMP), and guanosine monophosphate (GMP). The study also identified significant differences among these three chickens using electronic nose and SPME-GC/MS analysis, with aldehydes contributing to the richer flavor of BJY chicken.

FOODS (2022)

Add to Collection

Article Agriculture, Multidisciplinary

Paddy moisture on-line detection based on ensemble preprocessing and modeling for combine harvester

Jinshan Yan et al.

Summary: In this study, a comprehensive consideration of paddy varieties, paddy flow, feeding types, and algorithms led to the optimization of paddy moisture content (MC) detection method. The use of Extreme Learning Machine (ELM) coupled with ensemble preprocessing of orthogonal signal correction with Savitzky-Golay (OSC + SG) showed robustness under complex detecting conditions. This method achieved a low root mean standard error of prediction (RMSEPV) and demonstrated sufficient stability for online MC measurement of paddy.

COMPUTERS AND ELECTRONICS IN AGRICULTURE (2022)

Add to Collection

Article Chemistry, Applied

Fusion of electronic nose and hyperspectral imaging for mutton freshness detection using input-modified convolution neural network

Cunchuan Liu et al.

Summary: The combination of electronic nose and hyperspectral image was used to evaluate mutton freshness. The proposed method provides an approach for accurately analyzing mutton freshness and can be used as a technical basis for investigating other meat qualities.

FOOD CHEMISTRY (2022)

Add to Collection

Article Geosciences, Multidisciplinary

Rock burst mechanism induced by stress anomaly in roof thickness variation zone: a case study

Xianxi Bai et al.

Summary: This study investigated the impact of roof thickness variation on rock bursts during longwall mining. The results revealed that a thicker roof led to higher initial stress and increased risk of rock bursts. Additionally, the thin roof zone had a higher likelihood of roof breakage, resulting in significant dynamic load and microseismic energy.

GEOMATICS NATURAL HAZARDS & RISK (2022)

Add to Collection

Article Food Science & Technology

Detection of porcine DNA in food using direct asymmetric PCR and catalyzed hairpin assembly fluorescent biosensor: A novel assay for halal food analysis

Apinya Prachugsorn et al.

Summary: A novel direct asymmetric PCR and catalyzed hairpin assembly fluorescent biosensor was developed for naked eye detection of porcine DNA in food. The method showed high sensitivity and specificity, and demonstrated reproducibility. It can be utilized by law enforcement agencies and small-scale laboratories to investigate contamination and adulteration of halal foods.

FOOD CONTROL (2022)

Add to Collection

Article Spectroscopy

Rapid and accurate determination of diesel multiple properties through NIR data analysis assisted by machine learning

Shiyu Liu et al.

Summary: This paper developed a new machine learning model using near-infrared spectroscopy to rapidly and accurately detect multiple properties of diesel. Experimental results indicated that the model outperformed existing methods in diesel quality detection, making it a promising tool for routine monitoring of diesel.

SPECTROCHIMICA ACTA PART A-MOLECULAR AND BIOMOLECULAR SPECTROSCOPY (2022)

Add to Collection

Article Food Science & Technology

Detection of chocolate powder adulteration with peanut using near-infrared hyperspectral imaging and Multivariate Curve Resolution

Antoine Laborde et al.

Summary: This study successfully detected peanut flour adulteration in chocolate powder using NIR hyperspectral imaging and chemometrics, with adulterated pixel detection rates ranging from 0% to 17% in mixed samples.

FOOD CONTROL (2021)

Add to Collection

Review Chemistry, Applied

Mass spectrometry-based protein and peptide profiling for food frauds, traceability and authenticity assessment

Mariangela Valletta et al.

Summary: Mass spectrometry (MS) methodologies are increasingly used in food authentication and traceability due to their unparalleled specificity, accuracy, and sensitivity. Protein and peptide profiling using MS has become more consolidated and is being utilized to assess food traceability and authenticity. Recent applications of MS in protein/peptide analyses in food matrices show potential in ensuring the quality of agro-food products.

FOOD CHEMISTRY (2021)

Add to Collection

Article Engineering, Multidisciplinary

Detection of gear fault severity based on parameter-optimized deep belief network using sparrow search algorithm

Jingbo Gai et al.

Summary: A parameter-optimized deep belief network (DBN) based on sparrow search algorithm (SSA) is proposed for gear fault severity detection, improving sensitivity, stability, and accuracy. By avoiding interference caused by subjective parameter selection, the method showed over 96% average detection accuracy with a standard deviation of 1.46%, proving better feature extraction ability, stability, and accuracy compared to other methods.

MEASUREMENT (2021)

Add to Collection

Article Engineering, Multidisciplinary

Semi-Supervised Ensemble Classifier with Improved Sparrow Search Algorithm and Its Application in Pulmonary Nodule Detection

Jiangnan Zhang et al.

Summary: The Adaptive Boosting (AdaBoost) classifier is widely used in ensemble learning for classification tasks. In order to address the issue of labeled and unlabeled data classification, a semi-supervised AdaBoost classifier was developed using an improved sparrow search algorithm (AdaBoost-ISSA-S4VM). The classifier shows good performance on lung CT images.

MATHEMATICAL PROBLEMS IN ENGINEERING (2021)

Add to Collection

Article Spectroscopy

Near-infrared hyperspectral imaging for detection and visualization of offal adulteration in ground pork

Hongzhe Jiang et al.

Summary: This study utilized hyperspectral imaging technology to detect lung adulteration in ground pork, employing PLSR models and methods like principal component loadings to process data, ultimately establishing a simplified PLSR model for effective visualization of the adulteration situation.

SPECTROCHIMICA ACTA PART A-MOLECULAR AND BIOMOLECULAR SPECTROSCOPY (2021)

Add to Collection

Article Food Science & Technology

Utilizing near infrared hyperspectral imaging for quantitatively predicting adulteration in tapioca starch

Duangkamolrat Khamsopha et al.

Summary: This study tested a non-destructive method using reflectance near infrared hyperspectral imaging to detect adulterants in tapioca starch. By establishing a calibration model, the concentration of adulterant was accurately predicted. The potential of NIR-HSI for rapidly detecting adulterant concentration in tapioca starch was demonstrated through the predictive model and visualization.

FOOD CONTROL (2021)

Add to Collection

Article Food Science & Technology

Multivariate Analysis Coupled with M-SVM Classification for Lard Adulteration Detection in Meat Mixtures of Beef, Lamb, and Chicken Using FTIR Spectroscopy

Muhammad Aadil Siddiqui et al.

Summary: The study focused on the issue of adulteration of meat products and conducted a comprehensive spectral analysis to identify functional groups and difference regions in pure and adulterated samples. By utilizing PCA and M-SVM techniques, the study achieved high classification accuracy for various samples, demonstrating the potential for accurate detection of lard adulteration in different meat samples.

FOODS (2021)

Add to Collection

Article Agronomy

Detection of Fusarium Head Blight in Wheat Ears Using Continuous Wavelet Analysis and PSO-SVM

Linsheng Huang et al.

Summary: A method using continuous wavelet analysis and PSO-SVM algorithm for detecting fusarium head blight was proposed. The results showed that under the same feature variables, the PSO-SVM detection method outperformed the BPNN detection method, while the RF detection model had the lowest overall accuracy.

AGRICULTURE-BASEL (2021)

Add to Collection

Article Chemistry, Analytical

Determination of Fatty Acid Content of Rice during Storage Based on Feature Fusion of Olfactory Visualization Sensor Data and Near-Infrared Spectra

Hongping Lu et al.

Summary: This study introduces a feature fusion technique for rapid measurement of fatty acid content during rice storage. Experimental results show that the best BPNN model based on the fusion feature performs well, improving detection accuracy and generalization performance.

SENSORS (2021)

Add to Collection

Article Food Science & Technology

Detection of Meat Adulteration Using Spectroscopy-Based Sensors

Lemonia-Christina Fengou et al.

Summary: The potential of spectroscopy-based sensors in detecting fraudulent minced meat substitution was assessed in this study, with MSI-based models outperforming Vis and Fluo-based models. Overall, spectroscopic data show considerable potential for the detection and quantification of minced meat adulteration, albeit being sensor-specific.

FOODS (2021)

Add to Collection

Article Food Science & Technology

Classification and quantification of minced mutton adulteration with pork using thermal imaging and convolutional neural network

Minchong Zheng et al.

Summary: A novel method using thermal imaging and CNN for classifying and quantifying adulterated minced mutton was proposed in this study, achieving good results in qualitative classification and quantitative prediction. The method was found to have great potential for application in the detection and supervision of adulterated food due to its economic and convenient characteristics.

FOOD CONTROL (2021)

Add to Collection

Article Food Science & Technology

Artificial bionic taste sensors coupled with chemometrics for rapid detection of beef adulteration

Biao Lu et al.

Summary: The study demonstrated that taste sensors coupled with ELM technology can be used for the rapid detection of beef adulteration, with the ELM models proving more accurate than PLS models.

FOOD SCIENCE & NUTRITION (2021)

Add to Collection

Article Computer Science, Information Systems

An Online Network Intrusion Detection Model Based on Improved Regularized Extreme Learning Machine

Yanqiang Tang et al.

Summary: An improved intrusion detection algorithm model based on extreme learning machine was proposed, featuring online learning with dynamic adaptation of new data, enhanced particle swarm optimization algorithm, and initial weight and deviation optimization using IPSO to improve classification ability.

IEEE ACCESS (2021)

Add to Collection

Article Food Science & Technology