Nondestructive detection of S-ovalbumin content in eggs using portable NIR spectrometer and MPA-CARS

Article Food Science & Technology

Fast online estimation of quail eggs freshness using portable NIR spectrometer and machine learning

Yasmin Lima Brasil et al.

Summary: This study demonstrated that Egg Quality Index (EQI) is the best way to express the freshness of quail eggs, and portable NIR spectrometer shows potential for monitoring quail eggs freshness with good predictive capacity.

FOOD CONTROL (2022)

添加到收藏夹

Article Spectroscopy

A variable selection method based on mutual information and variance inflation factor

Jiehong Cheng et al.

Summary: Feature selection plays a vital role in reducing dimensionality in the quantitative analysis of high-dimensional data. This paper proposes a variable selection method called Mutual Information-Variance Inflation Factor (MI-VIF) that combines mutual information (MI) and the variance inflation factor (VIF). By maximizing the correlation between the independent variable and the response variable and minimizing multicollinearity, MI-VIF achieves effective feature selection.

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

添加到收藏夹

Article Engineering, Chemical

Non-destructive detection of egg qualities based on hyperspectral imaging

Kunshan Yao et al.

Summary: This study successfully detects egg freshness, scattered yolk, and eggshell cracks using hyperspectral imaging, multivariate analysis, and image processing. The study also proposes models and algorithms for analyzing and extracting the features of eggs, achieving quantitative assessment and identification of egg quality.

JOURNAL OF FOOD ENGINEERING (2022)

添加到收藏夹

Article Energy & Fuels

Probabilistic solar irradiance forecasting based on XGBoost

Xianglong Li et al.

Summary: The paper presents a probabilistic prediction model of solar irradiance based on XGBoost, which utilizes historical data to train a point prediction model and generates probability prediction intervals under different confidence levels using kernel density estimation. Experimental results demonstrate that this method has better accuracy and is suitable for engineering practice.

ENERGY REPORTS (2022)

添加到收藏夹

Article Chemistry, Applied

Portable NIR spectrometer for quick identification of fat bloom in chocolates

Rafaela F. Gatti et al.

Summary: This study utilized a portable NIR spectrometer combined with chemometric tools to differentiate milk chocolate, white chocolate, 40% cocoa chocolate, and 70% cocoa chocolate samples under temperature abuse conditions. PCA separated the samples into different temperature groups for each chocolate type, while PLS-DA models showed high sensitivity, specificity, and accuracy values and identified the wavelengths most impacting the model construction.

FOOD CHEMISTRY (2021)

添加到收藏夹

Article Automation & Control Systems

Near Infrared feature waveband selection for fishmeal quality assessment by frequency adaptive binary differential evolution

Youyou Zhang et al.

Summary: This study utilizes NIR spectroscopy for rapid detection of ash content in fishmeal, proposing the adaptive binary differential evolution (ABDE) algorithm for feature selection and improving model performance by introducing frequency into the ABDE algorithm.

CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS (2021)

添加到收藏夹

Article Construction & Building Technology

Feasibility of portable NIR spectrometer for quality assurance in glue-laminated timber production

Jakub Sandak et al.

Summary: The study confirmed the feasibility of a portable NIR sensor for off-line determination of various wood quality aspects in glue-laminated timber production, with a focus on assessing wood moisture content. Additionally, successful demonstration was made in traceability of raw resources, automatic classification of diverse wood defects, and prediction of total delamination using a developed chemometric model. Recommendations for further system development were provided to integrate NIR measurement into glue-laminated timber production plants.

CONSTRUCTION AND BUILDING MATERIALS (2021)

添加到收藏夹

Article Engineering, Chemical

On-line monitoring of egg freshness using a portable NIR spectrometer in tandem with machine learning

J. P. Cruz-Tirado et al.

Summary: The study evaluated the performance of a small and cost-effective portable NIR spectrometer for estimating the freshness of eggs online. SVM-R model in the spectral region of 1300-1690 nm showed the best results with a relative error of 7.32% and RPD of 2.56. PLS-DA presented better results than SVM-C for the classification of fresh and stale eggs, with an accuracy of 87.0%.

JOURNAL OF FOOD ENGINEERING (2021)

添加到收藏夹

Article Agriculture, Multidisciplinary

Prediction performance of portable near infrared reflectance instruments using preprocessed dried, ground forage samples

P. Berzaghi et al.

Summary: Near infrared reflectance (NIR) spectroscopy has made significant advancements since the 1970s, becoming the most commonly used technique for forage analysis. A study comparing different portable instruments to a laboratory NIR instrument found that alfalfa had better calibration and test-set statistics than grasses. The laboratory instrument performed best, while the SCiO portable instrument had higher error rates, offering potential for on-farm analysis in the future.

COMPUTERS AND ELECTRONICS IN AGRICULTURE (2021)

添加到收藏夹

Article Chemistry, Analytical

Non-invasive identification of commercial green tea blends using NIR spectroscopy and support vector machine

Victor Gustavo Kelis Cardoso et al.

Summary: This study aimed to differentiate four commercial blends of green tea using NIR spectroscopy and SVM, with Bayesian optimization providing accurate models. The results indicated that the proposed methodology has the potential to be applied in automatic quality control.

MICROCHEMICAL JOURNAL (2021)

添加到收藏夹

Article Computer Science, Hardware & Architecture

Deep pre-trained networks as a feature extractor with XGBoost to detect tuberculosis from chest X-ray

Muhammad Rahman et al.

Summary: This study utilizes deep learning and X-ray image data to identify tuberculosis, and the proposed method shows high accuracy and sensitivity in tuberculosis classification, providing hope for medical facilities in developing countries to tackle the issue of early diagnosis.

COMPUTERS & ELECTRICAL ENGINEERING (2021)

添加到收藏夹

Article Biochemistry & Molecular Biology

MutTMPredictor: Robust and accurate cascade XGBoost classifier for prediction of mutations in transmembrane proteins

Fang Ge et al.

Summary: A new transmembrane protein mutation predictor, MutTMPredictor, was developed in this study and demonstrated to be effective through experiments on multiple datasets. The performance of MutTMPredictor surpassed existing predictors, showcasing its potential as a valuable tool for predicting and prioritizing missense mutations in transmembrane proteins. The MutTMPredictor webserver is freely accessible for academic use.

COMPUTATIONAL AND STRUCTURAL BIOTECHNOLOGY JOURNAL (2021)

添加到收藏夹

Proceedings Paper Materials Science, Multidisciplinary

Development of a low-cost portable spectrophotometer for milk quality analysis

P. Prasanth et al.

Summary: This paper introduces a low-cost portable spectrometer for analyzing fat and water content in milk. The spectrophotometer is developed from open source components with single chip sensors, providing reliable and affordable solution for small-scale farmers and milk societies.

MATERIALS TODAY-PROCEEDINGS (2021)

添加到收藏夹

Article Instruments & Instrumentation