An optimized deep convolutional neural network for dendrobium classification based on electronic nose

Wang, You; Diao, Junwei; Zhan, Wang; Zhan, Xianghao; Zhang, Bixuan; Li, Nan; Li, Guang

doi:10.1016/j.sna.2020.111874

Cited by 58 publications

(20 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this study, CPSC and CPKNN were applied to the classification of 12 categories of alternative herbal medicines based on a self-assembled e-nose system. This e-nose system has been shown effective in the classification of herbal medicines in our previous publications [19,[28][29][30][31]. The system includes 16 TGS (Taguchi Gas Sensors) type metal-oxide semi-conductive (MOS) sensors by Figaro Engineering Inc, Osaka, Japan.…”

Section: Experiments and Datasetmentioning

confidence: 99%

CPSC: Conformal prediction with shrunken centroids for efficient prediction reliability quantification and data augmentation, a case in alternative herbal medicine classification with electronic nose

Liu¹,

Zhan²,

Yang³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

In machine learning applications, the reliability of predictions is significant for assisted decision and risk control. As an effective framework to quantify the prediction reliability, conformal prediction (CP) was developed with the CPKNN (CP with kNN). However, the conventional CPKNN suffers from high variance and bias and long computational time as the feature dimensionality increases. To address these limitations, a new CP frameworkconformal prediction with shrunken centroids (CPSC) is proposed. It regularizes the class centroids to attenuate the irrelevant features and shrink the sample space for predictions and reliability quantification. To compare CPKNN and CPSC, we employed them in the classification of 12 categories of alternative herbal medicine with electronic nose as a case and assessed them in two tasks: 1) offline prediction: the training set was fixed and the accuracy on the testing set was evaluated; 2) online prediction with data augmentation: they filtered unlabeled data to augment the training data based on the prediction reliability and the final accuracy of testing set was compared. The result shows that CPSC significantly outperformed CPKNN in both two tasks: 1) CPSC reached a significantly higher accuracy with lower computation cost, and with the same credibility output, CPSC generally achieves a higher accuracy; 2) the data augmentation process with CPSC robustly manifested a statistically significant improvement in prediction accuracy with different reliability thresholds, and the augmented data were more balanced in classes. This novel CPSC provides higher prediction accuracy and better reliability quantification, which can be a reliable assistance in decision support.

show abstract

Section: Experiments and Datasetmentioning

confidence: 99%

CPSC: Conformal prediction with shrunken centroids for efficient prediction reliability quantification and data augmentation, a case in alternative herbal medicine classification with electronic nose

Liu¹,

Zhan²,

Yang³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…To be consistent with TDACNN, some CNNs with a large number of convolutional layers far beyond the number of convolutional layers in the proposed method are not considered. For CNNs in the E-nose field, several CNN-based methods utilized in artificial olfaction are also involved, including SniffMultinose [41], SniffConv [41], optimized deep CNN (ODCNN) [27], and GasNet [31]. In terms of methods based on general concepts except for CNN, we choose several methods, including PCA, linear discriminant analysis (LDA), locality preserving projections (LPP), (component correction based on PCA) CC-PCA [42], orthogonal signal correction (OSC) [43], generalized least squares weighting (GLSW) [44], and direct standardization (DS) [45].…”

Section: Implementation Detailsmentioning

confidence: 99%

“…To better adapt CNNs to the data characteristics of E-noses (usually a one-dimensional time series), many studies have begun to focus on the customized modification of CNNs. Wang et al proposed a CNN with a one-dimensional band convolution kernel for electronic nose data recognition and classification, achieving better results than traditional methods [27]. For mixture gas classification, a multilabel method based on a 1D CNN was proposed by Zhao et al to identify multiple gas elements simultaneously in a complex odor mixture [28].…”

Section: Introductionmentioning

confidence: 99%

TDACNN: Target-domain-free Domain Adaptation Convolutional Neural Network for Drift Compensation in Gas Sensors

Zhang,

Xiang,

Wang

et al. 2021

Preprint

View full text Add to dashboard Cite

Sensor drift is a long-existing unpredictable problem that deteriorates the performance of gaseous substance recognition, calling for an antidrift domain adaptation algorithm. However, the prerequisite for traditional methods to achieve fine results is to have data from both nondrift distributions (source domain) and drift distributions (target domain) for domain alignment, which is usually unrealistic and unachievable in real-life scenarios. To compensate for this, in this paper, deep learning based on a target-domain-free domain adaptation convolutional neural network (TDACNN) is proposed. The main concept is that CNNs extract not only the domain-specific features of samples but also the domain-invariant features underlying both the source and target domains. Making full use of these various levels of embedding features can lead to comprehensive utilization of different levels of characteristics, thus achieving drift compensation by the extracted intermediate features between two domains. In the TDACNN, a flexible multibranch backbone with a multiclassifier structure is proposed under the guidance of bionics, which utilizes multiple embedding features comprehensively without involving target domain data during training. A classifier ensemble method based on maximum mean discrepancy (MMD) is proposed to evaluate all the classifiers jointly based on the credibility of the pseudolabel. To optimize network training, an additive angular margin softmax loss with parameter dynamic adjustment is utilized. Experiments on two drift datasets under different settings demonstrate the superiority of TDACNN compared with several state-of-the-art methods.

show abstract

“…In [36], the authors made the comprehensive research on principles and recent advances in electronic nose for quality inspection of agricultural and food products. In [37], an optimized deep CNN for dendrobium classification based on electronic nose was proposed. In [38], on-line assessment of oil quality during deep frying was addressed by using an electronic nose and proton transfer reaction mass spectrometry.…”

Section: The Related Applicationsmentioning

confidence: 99%

Using Recurrent Neural Network to Optimize Electronic Nose System with Dimensionality Reduction

Zou

2020

Electronics

View full text Add to dashboard Cite

Electronic nose is an electronic olfactory system that simulates the biological olfactory mechanism, which mainly includes gas sensor, data pre-processing, and pattern recognition. In recent years, the proposals of electronic nose have been widely developed, which proves that electronic nose is a considerably important tool. However, the most recent studies concentrate on the applications of electronic nose, which gradually neglects the inherent technique improvement of electronic nose. Although there are some proposals on the technique improvement, they usually pay attention to the modification of gas sensor module and barely consider the improvement of the last two modules. Therefore, this paper optimizes the electronic nose system from the perspective of data pre-processing and pattern recognition. Recurrent neural network (RNN) is used to do pattern recognition and guarantee accuracy rate and stability. Regarding the high-dimensional data pre-processing, the method of locally linear embedding (LLE) is used to do dimensionality reduction. The experiments are made based on the real sensor drift dataset, and the results show that the proposed optimization mechanism not only has higher accuracy rate and stability, but also has lower response time than the three baselines. In addition, regarding the usage of RNN model, the experimental results also show its efficiency in terms of recall ratio, precision ratio, and F1 value.

show abstract

An optimized deep convolutional neural network for dendrobium classification based on electronic nose

Cited by 58 publications

References 28 publications

CPSC: Conformal prediction with shrunken centroids for efficient prediction reliability quantification and data augmentation, a case in alternative herbal medicine classification with electronic nose

CPSC: Conformal prediction with shrunken centroids for efficient prediction reliability quantification and data augmentation, a case in alternative herbal medicine classification with electronic nose

TDACNN: Target-domain-free Domain Adaptation Convolutional Neural Network for Drift Compensation in Gas Sensors

Using Recurrent Neural Network to Optimize Electronic Nose System with Dimensionality Reduction

Contact Info

Product

Resources

About