Identification of Chinese Herbal Medicines with Electronic Nose Technology: Applications and Challenges

Zhou, Hua-Ying; Luo, Dehan; GholamHosseini, Hamid; Zhong, Li; He, Junfeng

doi:10.3390/s17051073

Cited by 42 publications

(34 citation statements)

References 98 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Each Chinese medicinal material has its own special odor, and some even have a strong pungent odor. After using the E-nose technology to obtain the odor information of Chinese herbal medicines, the method of machine learning can achieve the objective, accurate identification of Chinese herbal medicines for authenticity and quality assessment [24].…”

Section: Machine Learning Methods For E-nosementioning

confidence: 99%

POP-CNN: Predicting Odor Pleasantness With Convolutional Neural Network

Luo

Wong

et al. 2019

IEEE Sensors J.

Self Cite

View full text Add to dashboard Cite

Predicting odor's pleasantness simplifies the evaluation of odors and has the potential to be applied in perfumes and environmental monitoring industry. Classical algorithms for predicting odor's pleasantness generally use a manual feature extractor and an independent classifier. Manual designing a good feature extractor depend on expert knowledge and experience is the key to the accuracy of the algorithms. In order to circumvent this difficulty, we proposed a model for predicting odor's pleasantness by using convolutional neural network. In our model, the convolutional neural layers replace manual feature extractor and show better performance. The experiments show that the correlation between our model and human is over 90% on pleasantness rating. And our model has 99.9% accuracy in distinguishing between absolutely pleasant or unpleasant odors. Index Terms-predicting pleasantness, convolutional neural network, electronic nose.

show abstract

Section: Machine Learning Methods For E-nosementioning

confidence: 99%

POP-CNN: Predicting Odor Pleasantness With Convolutional Neural Network

Luo

Wong

et al. 2019

IEEE Sensors J.

Self Cite

View full text Add to dashboard Cite

show abstract

“…First of all, they can be used in medicine as markers for determination of the presence of different diseases like cancer (Turner, 2013). As markers of the presence of some substances, VOCs can also be a useful tool for verification in industry (James, Scott, Zulfiqur, & O'Hare, 2005), environmental research (Bieganowski et al, 2018;Guz et al, 2015), medicine (Zhou, Luo, GholamHosseini, Li, & He, 2017), and even in military applications (Patel, 2014). Analyses of VOCs have been widely used to determine the quality of biomaterials (Ayari, Mirzaee-Ghaleh, Rabbani, & Heidarbeigi, 2018;Zhang, Cheng, Ma, & Li, 2017).…”

Section: Introductionmentioning

confidence: 99%

Identification of Volatile Organic Compounds and Their Concentrations Using a Novel Method Analysis of MOS Sensors Signal

Gancarz

Nawrocka

Rusinek

2019

Journal of Food Science

View full text Add to dashboard Cite

Volatile organic compounds (VOCs) are natural markers useful in rapid assessment of adverse changes occurring in biological material. The use of an electronic nose seems to be a good, fast, and cheap method to determine particular VOCs. This paper presents a new method determination for VOCs and their concentration based on three sensorgram parameters: maximum of normalized sensor response, reaction time, and cleaning time measured from the end of the test to the half value of the maximum of normalized sensor response. The novelty of the method consists in the use for the first time of two parameters: reaction time and cleaning time measured from the end of the test to the half value of the maximum of normalized sensor response. The VOC sensorgrams at different VOC concentrations (26 to 3,842 ppm) were measured by an electronic nose Food Volatile Compound Analyzer (Agrinose) equipped with eight metal oxide semiconductor sensors dedicated to detect different gases. In the present studies, only six sensors that best respond to the VOCs were used. The highest responses to VOCs were obtained for two sensors—TGS2602 and AS‐MLV‐P2. The results showed that the dependence between the sensorgram parameters on VOC concentration was well described by a logarithmic curve in the whole range of concentrations. Detailed analysis revealed that the cleaning time increases with an increase in the number of carbon atoms in aliphatic molecules. The principal component analysis (PCA) was used to verify the utility of the new three parameters method in VOCs differentiation. The PCA analysis of these parameters showed that maximum of the normalized sensor response alone, which has been used for identification of particular VOCs so far, could not be regarded as a good parameter used for this purpose. Application of all the three parameters gave the best results in VOC identification. The research indicates that the use of three parameters of a volatile compound instead of only one parameter can allow precise determination of substances. Moreover, the results indicate that the analyzed parameters depend on the chemical structure of VOCs.

show abstract

“…Electronic nose (e-nose) is a portable and rapid instrument inspired by olfactory systems of mammals, which has been widely used in food safety, environmental monitoring and disease diagnosis [ 2 , 3 , 4 ]. Data processing procedure of a traditional e-nose mainly consists of several steps: pre-processing, feature extraction (generation and reduction) and classification.…”

Section: Introductionmentioning

confidence: 99%

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

Zhao

Meng

Zeng

et al. 2017

Sensors

View full text Add to dashboard Cite

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.

show abstract

Identification of Chinese Herbal Medicines with Electronic Nose Technology: Applications and Challenges

Cited by 42 publications

References 98 publications

POP-CNN: Predicting Odor Pleasantness With Convolutional Neural Network

POP-CNN: Predicting Odor Pleasantness With Convolutional Neural Network

Identification of Volatile Organic Compounds and Their Concentrations Using a Novel Method Analysis of MOS Sensors Signal

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

Contact Info

Product

Resources

About