2019
DOI: 10.3390/s19092173
|View full text |Cite
|
Sign up to set email alerts
|

A Novel Sparse Representation Classification Method for Gas Identification Using Self-Adapted Temperature Modulated Gas Sensors

Abstract: A novel sparse representation classification method (SRC), namly SRC based on Method of Optimal Directions (SRC_MOD), is proposed for electronic nose system in this paper. By finding both a synthesis dictionary and a corresponding coefficient vector, the i-th class training samples are approximated as a linear combination of a few of the dictionary atoms. The optimal solutions of the synthesis dictionary and coefficient vector are found by MOD. Finally, testing samples are identified by evaluating which class … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
4
0

Year Published

2019
2019
2024
2024

Publication Types

Select...
6

Relationship

0
6

Authors

Journals

citations
Cited by 6 publications
(4 citation statements)
references
References 31 publications
0
4
0
Order By: Relevance
“…Another application [26] of a similar device allowed to reach accuracy up to 94.43% for differentiation between various foodstuffs. He et al [27] applied sensors temperature modulation with varying frequency to recognize gases like hydrogen, methane, carbon monoxide, and benzene and obtained an accuracy of 84.5-98.5% depending on the machine learning model. Amini et al [21] investigated recognition of various concentrations of methanol using rectangular modulation of various heights, starting from a relatively low voltage of 2 V and reaching an accuracy of 92%.…”
Section: Comparison With Other Resultsmentioning
confidence: 99%
See 1 more Smart Citation
“…Another application [26] of a similar device allowed to reach accuracy up to 94.43% for differentiation between various foodstuffs. He et al [27] applied sensors temperature modulation with varying frequency to recognize gases like hydrogen, methane, carbon monoxide, and benzene and obtained an accuracy of 84.5-98.5% depending on the machine learning model. Amini et al [21] investigated recognition of various concentrations of methanol using rectangular modulation of various heights, starting from a relatively low voltage of 2 V and reaching an accuracy of 92%.…”
Section: Comparison With Other Resultsmentioning
confidence: 99%
“…Oates et al [25] presented a low-cost electronic nose with sinusoidally heated standard commercially available sensors for the classification of oil types, and recently [26] demonstrated application to basic detection of different foodstuffs. He et al [27] applied a spike-like pattern with a modulated frequency of spikes during the measurement procedure. A triangular modulation profile was used by Krivetskiy et al [28].…”
Section: Introductionmentioning
confidence: 99%
“…Yuan et al [ 59 ] proposed a triangular in combination with rectangular profiles, starting from a base level with low sensor temperature conditions. He et al [ 60 ] used a spike-like modulation protocol with a variable frequency of spikes during the measurement process. Iwata et al [ 61 ] proposed the use of a protocol with a modulation profile for the sensor heater voltage in which amplitude and frequency changed periodically.…”
Section: Discussionmentioning
confidence: 99%
“…Xu et al 24 compared the effect of Gaussian dictionaries and Chirp dictionaries on Lamb waves decomposition based on matching pursuit. The dictionary learning methods, such as optimal direction method, 25 K-singular value decomposition, 26 and online dictionary learning, 27,28 iterates and updates dictionaries according to the signal characteristics to optimize the dictionaries, which are computationally intensive but have a better decomposition effect to original signal. The UGW signal has sparsity in both time domain and frequency domain, which can be used to construct overcomplete dictionaries based on the characteristics of the UGW signal.…”
Section: Introductionmentioning
confidence: 99%