Electronic nose with a new feature reduction method and a multi-linear classifier for Chinese liquor classification

High-Resolution Mass Spectrometry-Based Chemical Fingerprinting of Baijiu, a Traditional Chinese Liquor

Fourier transform ion cyclotron resonance (FT-ICR) mass spectrometry, coupled with electrospray ionization (ESI) or atmospheric-pressure photoionization (APPI), was employed for chemical fingerprinting of baijiu, a traditional Chinese liquor. Baijiu is the most consumed distilled alcoholic beverage globally, with over 10 billion liters sold annually. It is a white (transparent) spirit that exhibits similarities to dark spirits such as whisky or rum in terms of aroma and mouthfeel. In this study, direct-infusion FT-ICR mass spectrometry was used to analyze 10 commercially available baijiu liquors, enabling the examination of both volatile and nonvolatile constituents without the need for tedious sample extractions or compound derivatizations. The chemical fingerprints obtained by FT-ICR MS revealed substantial compositional diversity among different baijiu liquors, reflecting variations in the raw materials and production methods. The main compounds identified included a variety of acids, esters, aldehydes, lactones, terpenes, and phenolic compounds. The use of ESI and APPI provided complementary compositional information; while ESI demonstrated greater selectivity toward polar, aliphatic sample constituents, APPI also ionized semipolar and nonpolar (aromatic) ones.

A Machine Learning Method for the Quality Detection of Base Liquor and Commercial Liquor Using Multidimensional Signals from an Electronic Nose

Chinese liquor is a world-famous beverage with a long history. Base liquor, a product of liquor brewing, significantly affects the flavor and quality of commercial liquor. In this study, a machine learning method consisting of a deep residual network (ResNet)18 backbone with a light gradient boosting machine (LightGBM) classifier (ResNet-GBM) is proposed for the quality identification of base liquor and commercial liquor using multidimensional signals from an electronic nose (E-Nose). Ablation experiments are conducted to analyze the contribution of the framework’s components. Five evaluation metrics (accuracy, sensitivity, precision, F1 score, and kappa score) are used to verify the performance of the proposed method, and six other frameworks (support vector machine (SVM), random forest (RF), k-nearest neighbor (KNN), extreme gradient boosting (XGBoost), multidimensional scaling-support vector machine (MDS-SVM), and back-propagation neural network (BPNN)) on three datasets (base liquor, commercial liquor, and mixed base and commercial liquor datasets). The experimental results demonstrate that the proposed ResNet-GBM model achieves the best performance for identifying base liquor and commercial liquors with different qualities. The proposed framework has the highest F1 score for the identification of commercial liquor in the mixed dataset due to the contribution of similar microconstituents from the base liquor. The proposed method can be used for the quality control of Chinese liquor and promotes the practical application of E-nose devices.

Marker-Independent Food Identification Enabled by Combing Machine Learning Algorithms with Comprehensive GC × GC/TOF-MS

Reliable methods are always greatly desired for the practice of food inspection. Currently, most food inspection techniques are mainly dependent on the identification of special components, which neglect the combination effects of different components and often lead to biased results. By using Chinese liquors as an example, we developed a new food identification method based on the combination of machine learning with GC × GC/TOF-MS. The sample preparation methods SPME and LLE were compared and optimized for producing repeatable and high-quality data. Then, two machine learning algorithms were tried, and the support vector machine (SVM) algorithm was finally chosen for its better performance. It is shown that the method performs well in identifying both the geographical origins and flavor types of Chinese liquors, with high accuracies of 91.86% and 97.67%, respectively. It is also reasonable to propose that combining machine learning with advanced chromatography could be used for other foods with complex components.

Discrimination of Chinese Baijiu grades based on colorimetric sensor arrays

In this study, a novel colorimetric sensor array based on chemo dyes including porphyrins and pH indicators were developed to analyse the volatile organic compounds of Chinese Baijiu with different grades. Ethyl acetate, ethyl butyrate and ethyl caproate appeared by significantly different concentration in different Baijiu grades measuring by gas chromatography and mass spectrometry and they were chosen as characteristic volatile organic components. The olfactory visualization system based on colorimetric sensor arrays was used to identify different Baijiu grades. The data were processed by building the principle components analysis, linear discriminant analysis and K-nearest neighbor classification models with the results of sensory evaluation and olfactory visualization system. This work presents a new-style colorimetric sensor using sensitive chemo dyes which has significant potential in quantitative analysis of volatile organic compounds, afterwards identifying different grades of Baijiu.

Electronic nose using a bio-inspired neural network modeled on mammalian olfactory system for Chinese liquor classification

The simplification of data processing is the frontier domain for electronic nose (e-nose) applications, whereas there are a lot of manual operations in a traditional processing procedure. To solve this problem, we propose a novel data processing method using the bio-inspired neural network modeled on the mammalian olfactory system. Through a neural coding scheme with multiple squared cosine receptive fields, continuous sensor data are simplified as the spike pattern in virtual receptor units. The biologically plausible olfactory bulb, which mimics the structure and function of main olfactory pathways, is designed to refine the olfactory information embedded in the encoded spikes. As a simplified presentation of cortical function, the bionic olfactory cortex is established to further analyze olfactory bulb's outputs and perform classification. The proposed method can automatically learn features without tedious steps such as denoising, feature extraction and reduction, which significantly simplifies the processing procedure for e-noses. To validate algorithm performance, comparison studies were performed for seven kinds of Chinese liquors using the proposed method and traditional data processing methods. The experimental results show that squared cosine receptive fields and the olfactory bulb model are crucial for improving classification performance, and the proposed method has higher classification rates than traditional methods when the sensor quantity and type are changed.

Stacked Sparse Auto-Encoders (SSAE) Based Electronic Nose for Chinese Liquors Classification

This paper presents a stacked sparse auto-encoder (SSAE) based deep learning method for an electronic nose (e-nose) system to classify different brands of Chinese liquors. It is well known that preprocessing; feature extraction (generation and reduction) are necessary steps in traditional data-processing methods for e-noses. However, these steps are complicated and empirical because there is no uniform rule for choosing appropriate methods from many different options. The main advantage of SSAE is that it can automatically learn features from the original sensor data without the steps of preprocessing and feature extraction; which can greatly simplify data processing procedures for e-noses. To identify different brands of Chinese liquors; an SSAE based multi-layer back propagation neural network (BPNN) is constructed. Seven kinds of strong-flavor Chinese liquors were selected for a self-designed e-nose to test the performance of the proposed method. Experimental results show that the proposed method outperforms the traditional methods.

Design of a portable electronic nose for real-fake detection of liquors

Portability is a major issue that influences the practical application of electronic noses (e-noses). For liquors detection, an e-nose must preprocess the liquid samples (e.g., using evaporation and thermal desorption), which makes the portable design even more difficult. To realize convenient and rapid detection of liquors, we designed a portable e-nose platform that consists of hardware and software systems. The hardware system contains an evaporation/sampling module, a reaction module, a control/data acquisition and analysis module, and a power module. The software system provides a user-friendly interface and can achieve automatic sampling and data processing. This e-nose platform has been applied to the real-fake recognition of Chinese liquors. Through parameter optimization of a one-class support vector machine classifier, the error rate of the negative samples is greatly reduced, and the overall recognition accuracy is improved. The results validated the feasibility of the designed portable e-nose platform.

Quality assessment of Chinese liquor with different ages and prediction analysis based on gas chromatography and electronic nose

The economic value of Chinese liquor is closely related with its age. Results from gas chromatograph (GC) analysis indicated that 8 dominant compounds were decreased with the increase of liquor age (0 to 5 years) while ethyl lactate was found to be the most stable dominant compound as no significant change was observed in it during the aging process. Liquor groups with different ages were well-discriminated by principal component analysis (PCA) based on electronic nose signals. High-accurate identification of liquor ages was realized using linear discriminant analysis (LDA) with the accuracy of 98.3% of the total 120 samples from six age groups. Partial least squares regression (PLSR) exhibited satisfying ability for liquor age prediction (R²: 0.9732 in calibration set and 0.9101 in validation set). The feasibility of volatile compounds prediction using PLSR combined with electronic nose was also verified by this research. However, the accuracies of PLSR models can be further promoted in future researches, perhaps by using more suitable sensors or modeling approaches.

Classification of Multiple Chinese Liquors by Means of a QCM-based E-Nose and MDS-SVM Classifier

Chinese liquors are internationally well-known fermentative alcoholic beverages. They have unique flavors attributable to the use of various bacteria and fungi, raw materials, and production processes. Developing a novel, rapid, and reliable method to identify multiple Chinese liquors is of positive significance. This paper presents a pattern recognition system for classifying ten brands of Chinese liquors based on multidimensional scaling (MDS) and support vector machine (SVM) algorithms in a quartz crystal microbalance (QCM)-based electronic nose (e-nose) we designed. We evaluated the comprehensive performance of the MDS-SVM classifier that predicted all ten brands of Chinese liquors individually. The prediction accuracy (98.3%) showed superior performance of the MDS-SVM classifier over the back-propagation artificial neural network (BP-ANN) classifier (93.3%) and moving average-linear discriminant analysis (MA-LDA) classifier (87.6%). The MDS-SVM classifier has reasonable reliability, good fitting and prediction (generalization) performance in classification of the Chinese liquors. Taking both application of the e-nose and validation of the MDS-SVM classifier into account, we have thus created a useful method for the classification of multiple Chinese liquors.

Development of a colorimetric sensor array for the discrimination of Chinese liquors based on selected volatile markers determined by GC-MS

A new colorimetric sensor array was developed for the discrimination of 12 high-alcoholic Chinese base liquors from Luzhou Co., Ltd., and 15 commercial Chinese liquor of different brands as well as flavor types. Seventeen volatile compounds within four chemical groups were determined as markers in the base liquor by GC-MS analysis and factor analysis method (FAM). A specialized colorimetric sensor array composed of 20 sensitive dots was fabricated accordingly to obtain sensitive interaction with different types of volatile markers. Discrimination of the liquor samples was subsequently performed using chemometric and statistical methods, including principal component analysis (PCA) and hierarchical clustering analysis (HCA). The results suggested that facile identification of either base liquors with high-alcoholic volume or commercial liquors of the same flavor types could be achieved by analysis of the color change profiles. The response of the sensor improved significantly in comparison with those that rely on nonspecific interactions, and no misclassification was observed for both liquor samples using two chemometric methods. Besides, it was also found that the discrimination is closely related to the characteristic flavor compounds (esters, aldehydes, and acids) and alcoholic strength in liquors, and its performance was even comparable with that of GC-MS.