Search

Lonicerae japonicae flos (Jinyinhua, JYH) and Lonicerae flos (Shanyinhua, SYH) have high medical and economical value. Due to their similar appearance, the more expensive JYH is often adulterated with the cheaper SYH for economic gain. In this study, near-infrared hyperspectral imaging (HSI) was used to identify the geographical origins of JYH and SYH and differentiate JYH from SYH. Support vector classification (SVC) models using linear kernel function were established to achieve the research goals. For the identification of geographical origin, we explored the impact of different sample batches on classification performance. The overall testing sets classification accuracy of JYH and SYH was in the range of 60.10–85.59% and 63.35–91.67%, respectively. For species classification, the impact of sample geographical origins and sample batches on model performances was explored. The overall testing sets classification accuracy for distinguishing JYH and SYH was 98.46–100%. These results demonstrated the significant impact of sample sources on the performance of the models. Using SVC models, the important wavelengths contributing more to the classification were identified by recursive feature elimination (RFE). The results showed that HSI holds great potential for the identification of JYH and SYH, as well as their geographical origins. This technique can provide crucial technical support for the development and standardization of the Traditional Chinese Medicine industry. • Origin identification and species classification of Jinyinhua and Shanyinhua were studied by hyperspectral imaging. • Impact of sample batches on origin identification models were investigated. • Impact of sample origins and batches on species classification models were investigated. • Important wavelengths for origin identification and species classification were analyzed. [ABSTRACT FROM AUTHOR]

Using the zone fire model CFAST as the simulation engine, time series data for building sensors, such as heat detectors, smoke detectors, and other targets at any arbitrary locations in multi-room compartments with different geometric configurations, can be obtained. An automated process for creating inputs files and summarizing model results, CData, is being developed as a companion to CFAST. An example case is presented to demonstrate the use of CData where synthetic data is generated for a wide range of fire scenarios. Three machine learning algorithms: support vector machine (SVM), decision tree (DT), and random forest (RF), are used to develop classification models that can predict the location of a fire based on temperature data within a compartment. Results show that DT and RF have excellent performance on the prediction of fire location and achieve model accuracy in between 93% and 96%. For SVM, model performance is sensitive to the size of training data. Additional study shows that results obtained from DT and RT can be used to examine the importance of each input feature. This paper contributes a learning-by-synthesis approach to facilitate the utilization of a machine learning paradigm to enhance situational awareness for fire fighting in buildings. [ABSTRACT FROM AUTHOR]

A novel transfer support vector machine called TSVM-GP with group probabilities is proposed for the scenarios where plenty of labeled data in the source domain and the group probabilities of unlabeled data in the target domain are available. TSVM-GP integrates a transfer term and group probabilities into the support vector machine (SVM) to improve the classification accuracy. In order to reduce the high computational complexity of TSVM-GP, the scalable version of TSVM-GP called scalable transfer support vector machine with group probabilities (STSVM-GP) is further developed by selecting the representative set of the training samples as the training data in the source domain. Experimental results on synthetic datasets as well as several real-world datasets show the effectiveness of the proposed classifiers, and especially STSVM-GP is very feasible for large scale transfer datasets. [ABSTRACT FROM AUTHOR]

An electronic nose (E-nose) has been used to characterize five types of strawberry juices based on different processing approaches (i.e., Microwave Pasteurization, Steam Blanching, High Temperature Short Time Pasteurization, Frozen–Thawed, and Freshly Squeezed). Juice quality parameters (vitamin C and total acid) were detected by traditional measuring methods. Multivariate statistical methods (Principle Component Analysis, Linear Discriminant Analysis, Multiple Linear Regression, and Partial Least Squares Regression) and neural networks (Extreme Learning Machine (ELM), Learning Vector Quantization and Library Support Vector Machines) were employed for qualitative classification and quantitative regression. ELM showed best performances on classification and regression, indicating that ELM would be a good choice for E-nose data treatment. Results provide promising principles for the elaboration of E-nose which could be used to discriminate processed juices and to predict juice quality parameters based on appropriate algorithms for the beverage industry. [ABSTRACT FROM AUTHOR]

Abstract: Random forest (RF) has been proposed on the basis of classification and regression trees (CART) with “ensemble learning” strategy by Breiman in 2001. In this paper, RF is introduced and investigated for electronic tongue (E-tongue) data processing. The experiments were designed for type and brand recognition of orange beverage and Chinese vinegar by an E-tongue with seven potentiometric sensors and an Ag/AgCl reference electrode. Principal component analysis (PCA) was used to visualize the distribution of total samples of each data set. Back propagation neural network (BPNN) and support vector machine (SVM), as comparative methods, were also employed to deal with four data sets. Five-fold cross-validation (CV) with twenty replications was applied during modeling and an external testing set was employed to validate the prediction performance of models. The average correct rates (CR) on CV sets of the four data sets performed by BPNN, SVM and RF were 86.68%, 66.45% and 99.07%, respectively. RF has been proved to outperform BPNN and SVM, and has some advantages in such cases, because it can deal with classification problems of unbalanced, multiclass and small sample data without data preprocessing procedures. These results suggest that RF may be a promising pattern recognition method for E-tongues. [Copyright &y& Elsevier]

Sesame oil (SO) is a high-quality oil that is more expensive than other edible oils, and therefore becomes a target of economically motivated adulteration. An approach based on excitation-emission matrix (EEM) fluorescence and chemometric methods was applied for the rapid classification and determination of the authenticity of SO. First, a five-factor alternating trilinear decomposition (ATLD) model roughly completed the characterization of the fluorescent components in the edible oil samples, providing meaningful chemical information. Then, four chemometric methods, including linear discriminant analysis (LDA), partial least squares–discriminant analysis (PLS-DA), support vector machine (SVM) and unfolded partial least-squares discriminant analysis (UPLS-DA), were used to establish the models for the classification of SO and other edible oils (Model 1), and determine the authenticity of SO and adulterated SOs (Model 2). All models achieved good classification results. The combination of the second-order calibration algorithm (ATLD) and the pattern recognition algorithm (LDA, PLS-DA, or SVM) not only achieved the characterization of the components in edible oils but also realized the rapid detection of adulterated SOs. The proposed method is rapid, accurate, requires a simple sample pre-treatment and can be used to determine the authenticity and adulteration of high-quality edible oils. • A simple and rapid EEMs fluorescence was developed for adulteration of sesame oil for the first time. • ATLD decomposed the meaningful chemical composition of edible oils. • Discriminant model for detection was built by ATLD-LDA, ATLD-PLS-DA, ATLD-SVM and UPLS-DA. • All methods successfully identified various pure edible oils and adulterated sesame oils. [ABSTRACT FROM AUTHOR]

The ecological environment is gravely threatened by the buildup of microplastics (MPs) in soil. Currently, there are no established techniques for detecting MPs in soil. Some of the standard chemical detection methods now in use are time-consuming and cumbersome. This research suggested a method for identifying soil microplastic polymers (MPPs) based on convolutional neural networks (CNN) and hyperspectral imaging (HSI) technologies to address this issue. The categorization model for MPPs on the soil surface was first established by simulating the natural soil environment in the lab. While decision tree (DT) and support vector machine (SVM) models' classification accuracy was 87.9 % and 85.6 %, respectively, that of CNN was 92.6 %. The HIS and CNN model combination produced the best classification results out of all of these models. Secondly, farmland in Guangzhou's Tianhe, Panyu, and Zengcheng districts was sampled for surface soil samples measuring 0–20 cm in order to confirm the model's accuracy in the actual environment. Before data analysis, the physicochemical properties of soil samples were determined by a standardization scheme. MPs in soil samples were extracted by traditional chemical detection method and their chemical properties were obtained as the results of the control group. Then, CNN was applied to hyperspectral data from soil samples collected for MPs detection. Finally, it was demonstrated that the physical and chemical properties of the soil have an impact on the accuracy of the model through the investigation of the physical and chemical characteristics of soil samples from three distinct areas. On the other hand, the results indicated that the suggested technique offers quick and non-destructive results for MPPs detection when comparing the detection results of hyperspectral and conventional chemical methods. [Display omitted] • This research suggests a new method for identifying soil microplastic polymers (MPPs). • The HIS and CNN model combination produces the best classification results out of all of these models. • CNN is applied to hyperspectral data from soil samples collected for MPs detection. • The technique offers quick and non-destructive results for MPPs detection for soil microplastics. [ABSTRACT FROM AUTHOR]