Rapid Identification of Asteraceae Plants with Improved RBF‐ANN Classification Models Based on MOS Sensor E‐Nose

Abstract

Plants from Asteraceae family are widely used as herbal medicines and food ingredients, especially in Asian area. Therefore, authentication and quality control of these different Asteraceae plants are important for ensuring consumers' safety and efficacy. In recent decades, electronic nose (E-nose) has been studied as an alternative approach. In this paper, we aim to develop a novel discriminative model by improving radial basis function artificial neural network (RBF-ANN) classification model. Feature selection algorithms, including principal component analysis (PCA) and BestFirst + CfsSubsetEval (BC), were applied in the improvement of RBF-ANN models. Results illustrate that in the improved RBF-ANN models with lower dimension data classification accuracies (100%) remained the same as in the original model with higher-dimension data. It is the first time to introduce feature selection methods to get valuable information on how to attribute more relevant MOS sensors; namely, in this case, S1, S3, S4, S6, and S7 show better capability to distinguish these Asteraceae plants. This paper also gives insights to further research in this area, for instance, sensor array optimization and performance improvement of classification model.

An original approach for the quantitative characterization of saffron aroma strength using electronic nose

“…[18][19][20] One of the main problems of RBF and MLP network modelling is that more redundant or uncorrelated information in the input data set may decrease model accuracy or may result in over-fitting in the output layer. [21] Owing to these problems, redundant data were eliminated from the data set in two times based on the PCA results (data sets were: total aroma features, total aroma features excluding the less-effective features, and only the more-effective aroma features). PCA analysis was performed using Unscrambler 10.4 software while MLP and RBF network analyses were performed using the MATLAB 7.14.0 software package.…”

Organoleptic Evaluation of Amomi Fructus and Its Further Background Verified via Morphological Measurement and GC Coupled with E‐Nose

“…This E-nose instrument contains three main parts: an automatic sampling system, namely, HS-100 sampler, two chambers with six MOG sensors in each, and a data acquisition unit connected to a computer, which allows data storage and processing. The materials and properties of these 12 MOG sensors have been reported in our previous researches as well as the optimization method [ 21 ]. The whole 12 MOG sensors consist of (i) six LY-type sensors including LY2/LG, LY2/G, LY2/GH, LY2/AA, LY2/gCT, and LY2/gCTL (majorly sensitive to short chain volatile fatty acids and aldehydes); (ii) four P-type sensors including P10/1, P10/2, P40/1, and PA/2 (majorly sensitive to methane, propane, and other aliphatic nonpolar molecules), and (iii) two T-type sensors including T30/1 and T70/2 (majorly sensitive to polar alcoholic and chlorinated compounds), which allows E-nose perceived responses of most volatile compounds [ 22 ].…”

“…However, searching the optimum strategy becomes an inevitable problem. Our team figured out two solutions to improve the discriminative model and increase the distinguishing positive rate, concerning BestFirst + CfsSubsetEval (BC) feature extraction, and cascade classifier [ 21 , 25 , 26 ]. Therefore, as proven to be an efficient feature extraction method, BC was used to optimize the sensor with greater contributions and eliminate the tedious information of high-dimensional data from E-nose.…”

Plant Pest Detection Using an Artificial Nose System: A Review

“…MOS sensors are some of the most commonly used gas sensors for constructing sensor arrays due to their cost-effectiveness, reliability, and availability. They have been widely applied in agriculture and forestry industries for diagnosis of plant infection caused by fungus, bacteria, and viruses; insect damage; or mechanical damage [ 42 , 43 , 44 , 45 , 46 , 47 ]. The main advantages of MOS sensors are the fast response and recovery times, which mainly depend on the temperatures and the level of interaction between the sensors and gases [ 48 ].…”