Researchers have developed an intelligent detection method for quaternary blended oil using near-infrared spectroscopy (NIRS) technology.
A new detection method for quaternary blended oil was recently used in a new study published in the Journal of Chemometrics (1). This study attempts to solve a critical problem in the oil industry, which is how to accurately detect quaternary blended oil (1).The researchers used near-infrared spectroscopy (NIRS) in this study, comparing the prediction performance of different models and their preprocessing combinations (1).
Oil pumps. | Image Credit: © Ded Pixto - stock.adobe.com
Establishing a workable prediction performance required implementing several preprocessing steps to the NIRS data (1). As an example, the researchers used the random forest (RF) model for soybean oil content. The RF model proved to be effective after second derivative optimization (1).
The researchers also had to worry about feature selection. Establishing an effective method to realize this was integral in extracting the most informative wavelengths (1). In the study, the researchers used a two-step feature selection method, using an elastic net (EN) to examine the wavelengths (1).
Based on the 20 effective wavelengths selected by EN + CARS, the researchers established a quantitative detection model (1). A test set was used to evaluate model performance, and it produced encouraging results (1). According to the results the researchers published in their paper, the correlation coefficient of determination (R2), root-mean-square error of prediction (RMSEP), and relative percent difference (RPD) values for the 2D + EN + CARS + RF model were 0.97953, 1.34306, and 7.08875, respectively (1).
As a result of this study, a two-step feature selection method in extracting the most informative wavelengths for quaternary blended oil detection proved to be effective (1). The researchers also showed in this study how NIRS technology can have great detection capabilities and accurately determine the components of blended oil (1).
The food and chemical sectors would benefit from the application of this detection method. By utilizing NIRS technology and advanced data analysis techniques, manufacturers can ensure the quality and integrity of their products, streamline production processes, and enhance overall efficiency (1).
The research conducted by the team at Heilongjiang University opens new avenues for detecting quaternary blended oil and its analysis, which should positively affect quality control (QC) and product authentication in various important industries (1).
(1) Zhao, Z.; Sun, L.; Bai, H.; Zhang, H.; Tian, Y. Intelligent component detection of quaternary blended oil based on near infrared spectroscopy technology. J. Chemom. 2023, ASAP. DOI: 10.1002/cem.3476
How Satellite-Based Spectroscopy is Transforming Inland Water Quality Monitoring
Published: April 29th 2025 | Updated: April 29th 2025New research highlights how remote satellite sensing technologies are changing the way scientists monitor inland water quality, offering powerful tools for tracking pollutants, analyzing ecological health, and supporting environmental policies across the globe.
NIR Spectroscopy Explored as Sustainable Approach to Detecting Bovine Mastitis
April 23rd 2025A new study published in Applied Food Research demonstrates that near-infrared spectroscopy (NIRS) can effectively detect subclinical bovine mastitis in milk, offering a fast, non-invasive method to guide targeted antibiotic treatment and support sustainable dairy practices.
Smarter Sensors, Cleaner Earth Using AI and IoT for Pollution Monitoring
April 22nd 2025A global research team has detailed how smart sensors, artificial intelligence (AI), machine learning, and Internet of Things (IoT) technologies are transforming the detection and management of environmental pollutants. Their comprehensive review highlights how spectroscopy and sensor networks are now key tools in real-time pollution tracking.
New AI Strategy for Mycotoxin Detection in Cereal Grains
April 21st 2025Researchers from Jiangsu University and Zhejiang University of Water Resources and Electric Power have developed a transfer learning approach that significantly enhances the accuracy and adaptability of NIR spectroscopy models for detecting mycotoxins in cereals.