Towards biological plausibility of electronic noses: A spiking neural network based approach for tea odour classification

Sarkar, Siddhartha; Bhondekar, Amol P.; Macaš, Martin; Kumar, Ritesh; Kaur, Ramneek; Sharma, Anupma; Gulati, Ashu; Kumar, Amod

doi:10.1016/j.neunet.2015.07.014

Cited by 29 publications

(16 citation statements)

References 38 publications

(54 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…With the rapid development of sensors, the wide application of electronic nose (E-nose), electronic tongue, and near-infrared technology [15][16][17][18][19][20][21][22] has made tea quality estimation easier. Especially, electronic nose technology has the convenience and objectivity of detecting food taste, which has been successfully applied to many aspects of tea research by simulating the human olfactory system, including in the tea fermentation process [23,24], tea classification [25][26][27][28], tea storage [29], and tea components [30].…”

Section: Introductionmentioning

confidence: 99%

Cross-Category Tea Polyphenols Evaluation Model Based on Feature Fusion of Electronic Nose and Hyperspectral Imagery

Yang

Wang

et al. 2019

Sensors

View full text Add to dashboard Cite

Tea polyphenols are important ingredients for evaluating tea quality. The rapid development of sensors provides an efficient method for nondestructive detection of tea polyphenols. Previous studies have shown that features obtained from single or multiple sensors yield better results in detecting interior tea quality. However, due to their lack of external features, it is difficult to meet the general evaluation model for the quality of the interior and exterior of tea. In addition, some features do not fully reflect the sensor signals of tea for several categories. Therefore, a feature fusion method based on time and frequency domains from electronic nose (E-nose) and hyperspectral imagery (HSI) is proposed to estimate the polyphenol content of tea for cross-category evaluation. The random forest and the gradient boosting decision tree (GBDT) are used to evaluate the feature importance to obtain the optimized features. Three models based on different features for cross-category tea (black tea, green tea, and yellow tea) were compared, including grid support vector regression (Grid-SVR), random forest (RF), and extreme gradient boosting (XGBoost). The results show that the accuracy of fusion features based on the time and frequency domain from the electronic nose and hyperspectral image system is higher than that of the features from single sensor. Whether based on all original features or optimized features, the performance of XGBoost is the best among the three regression algorithms (R2 = 0.998, RMSE = 0.434). Results indicate that the proposed method in this study can improve the estimation accuracy of tea polyphenol content for cross-category evaluation, which provides a technical basis for predicting other components of tea.

show abstract

Section: Introductionmentioning

confidence: 99%

Cross-Category Tea Polyphenols Evaluation Model Based on Feature Fusion of Electronic Nose and Hyperspectral Imagery

Yang

Wang

et al. 2019

Sensors

View full text Add to dashboard Cite

show abstract

“…By presenting many different odorants to the sensor array, a database is built up. This database of odorants with each odorant unique characteristics is used to train an intelligent classification system, such as Neural Networks [11][12][13][14][15][16][17][18][19][20].…”

Section: Introductionmentioning

confidence: 99%

Two Dimensional Electronic Nose for Vehicular Central Locking System (E-Nose-V)

Iskandarani¹

2019

IJACSA

View full text Add to dashboard Cite

A new approach to vehicle security is proposed, tried, tested. The designed and tested system comprises an odor detection system (E-Nose) that sends signals corresponding to selected odors to the smart vehicle Electronic Control Unit (ECU), which is interfaced to a smart system with neural networks. The signal is interpreted in time and space, whereby a certain ordered number of samples should be obtained before the vehicle functions are unlocked. Correlation of rise and decay times and amplitudes of the signal is carried out to ensure security. The proposed system is highly secured and could be further developed to become a vital and integrated part of Intelligent Transportation Systems (ITS) through the addition of driver's body odor smell as an extra measure of security and in cases of accidents to auto call emergency services with driver identification and some diagnostics. Such system can be utilized in smart cities.

show abstract

“…The learning method of artificial neural networks (ANN) has a good effect applied to detection of cigarettes and tea quality and freshness of chicken [15][16][17]. The electronic nose (EN) system was also used in the diagnosis of respiratory diseases [18] and rapid identification of Chinese herbal medicines [19], and the machine olfactory joint robot is applied to the collection of local odor source positioning [20].…”

Section: Introductionmentioning

confidence: 99%

Detecting and Identifying Industrial Gases by a Method Based on Olfactory Machine at Different Concentrations

Sun

Luo

et al. 2018

Journal of Electrical and Computer Engineering

View full text Add to dashboard Cite

Gas sensors have been widely reported for industrial gas detection and monitoring. However, the rapid detection and identification of industrial gases are still a challenge. In this work, we measure four typical industrial gases including CO 2 , CH 4 , NH 3 , and volatile organic compounds (VOCs) based on electronic nose (EN) at different concentrations. To solve the problem of effective classification and identification of different industrial gases, we propose an algorithm based on the selective local linear embedding (SLLE) to reduce the dimensionality and extract the features of high-dimensional data. Combining the Euclidean distance (ED) formula with the proposed algorithm, we can achieve better classification and identification of four kinds of gases. We compared the classification and recognition results of classical principal component analysis (PCA), linear discriminate analysis (LDA), and PCA + LDA algorithms with the proposed SLLE algorithm after selecting the original data and performing feature extraction. The experimental results show that the recognition accuracy rate of the SLLE reaches 91.36%, which is better than the other three algorithms. In addition, the SLLE algorithm provides more efficient and accurate responses to high-dimensional industrial gas data. It can be used in real-time industrial gas detection and monitoring combined with gas sensor networks.

show abstract

Towards biological plausibility of electronic noses: A spiking neural network based approach for tea odour classification

Cited by 29 publications

References 38 publications

Cross-Category Tea Polyphenols Evaluation Model Based on Feature Fusion of Electronic Nose and Hyperspectral Imagery

Cross-Category Tea Polyphenols Evaluation Model Based on Feature Fusion of Electronic Nose and Hyperspectral Imagery

Two Dimensional Electronic Nose for Vehicular Central Locking System (E-Nose-V)

Detecting and Identifying Industrial Gases by a Method Based on Olfactory Machine at Different Concentrations

Contact Info

Product

Resources

About