An electronic nose (e-nose) is a measuring instrument that mimics human olfaction and outputs ‘fingerprint’ information of mixed gases or odors. Generally speaking, an e-nose is mainly composed of two parts: a gas sensing system (gas sensor arrays, gas transmission paths) and an information processing system (microprocessor and related hardware, pattern recognition algorithms). It has been more than 30 years since the e-nose concept was introduced in the 1980s. Since then, e-noses have evolved from being large in size, expensive, and power-hungry instruments to portable, low cost devices with low power consumption. This paper reviews the development of compact e-nose design and calculation over the last few decades, and discusses possible future trends. Regarding the compact e-nose design, which is related to its size and weight, this paper mainly summarizes the development of sensor array design, hardware circuit design, gas path (i.e. the path through which the mixed gases to be measured flow inside the e-nose system) and sampling design, as well as portable design. For the compact e-nose calculation, which is directly related to its rapidity of detection, this review focuses on the development of on-chip calculation and wireless computing. The future trends of compact e-noses include the integration with the internet of things, wearable e-noses, and mobile e-nose systems.

A novel bioinspired neural network is proposed as a replacement for traditional data processing methods in the electronic nose (e-nose) that we designed. This neural network mimics the main structures of the mammalian olfactory system. It contains olfactory sensing neurons, mitral cells, and granule cells. The proposed method can directly use the raw data collected from sensors in the e-nose without any signal preprocessing, feature selection, or reduction. The output neurons of the network can change the sensors' responses into two new time series, of which we only use the variances to perform classification. This significantly simplifies the data processing procedure in e-noses. In order to test the performance of the proposed bioinspired neural network in the e-nose, two sampling methods, three classification methods, and seven kinds of Chinese liquors were employed. The highest classification rates of the proposed method and traditional method are 100% and 93%, respectively.

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.

An electronic nose (e-nose) was designed to classify Chinese liquors of the same aroma style. A new method of feature reduction which combined feature selection with feature extraction was proposed. Feature selection method used 8 feature-selection algorithms based on information theory and reduced the dimension of the feature space to 41. Kernel entropy component analysis was introduced into the e-nose system as a feature extraction method and the dimension of feature space was reduced to 12. Classification of Chinese liquors was performed by using back propagation artificial neural network (BP-ANN), linear discrimination analysis (LDA), and a multi-linear classifier. The classification rate of the multi-linear classifier was 97.22%, which was higher than LDA and BP-ANN. Finally the classification of Chinese liquors according to their raw materials and geographical origins was performed using the proposed multi-linear classifier and classification rate was 98.75% and 100%, respectively.

Traditional data processing methods for electronic noses (e-noses) need to use the whole response curves (including rise, steady and recovery phases) of sensor array, which leads to a long sampling time. The traditional methods also perform many steps such as signal pre-processing, feature generation/reduction, and classification, which increase the difficulty of selecting a suitable method for each step. In view of the above problems, we present a simplified method based on convolutional neural network (CNN) for e-noses. CNN not only uses fewer sampling points to perform classification, but also can automatically implement feature generation without signal pre-processing step. This significantly improves detection efficiency and simplifies data processing procedures of e-noses. The performance of CNN was tested using a portable e-nose designed by us. The results showed that CNN not only took shorter sampling time (15 seconds), but also obtained higher classification accuracy (95.7%) than traditional methods (92.9%).

We proposed a hybrid algorithm by combining kernel entropy component analysis (KECA) with linear discriminant analysis (LDA), namely, KECA-LDA for feature reduction in electronic-nose systems. It combined the advantages of KECA and LDA. Then, the data extracted by KECA-LDA were inputted to extreme learning machine (ELM) for classification. In order to examine the performance of the proposed method, eight types of strong-flavor Chinese liquors were tested using an electronic nose (e-nose) system designed by ourselves, and the results after cross validation showed that features extracted by KECA-LDA were more beneficial to classification than KECA, and the performance of ELM was better than that of backpropagation neural network. The highest classification rate by KECA-LDA-ELM was 100%. In conclusion, an e-nose combined with KECA-LDA and ELM is a feasible method to classify Chinese liquors.