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

He, Anzhi; Wei, Guangsheng; Yu, Jun; Li, Meihua; Li, Zhongzhou; Tang, Zhenan

doi:10.3390/s19092173

Cited by 6 publications

(4 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

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%

“…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%

See 1 more Smart Citation

Application of a Low-Cost Electronic Nose to Detect of Forest Tree Pathogens: Fusarium oxysporum and Phytophthora plurivora

et al. 2022

View full text Add to dashboard Cite

The presence of forest tree pathogens may lead to substantial problems and their early detection in the stage of seeds storage or nurseries may be critical for the choice of appropriate management strategy. A new construction of a low-cost electronic nose was tested on the samples of pathogenic fungi and oomycetes of Fusarium oxysporum and Phytopthora plurivora. The electronic nose uses Figaro Inc. TGS series sensors with applied heater voltage modulation. Such a mode of electronic nose operation may be more appropriate for application for constant monitoring of seeds storage, when we compare it to the the method applying modulation of the gas concentration. A rectangular shape of the sensors' heater voltage modulation pattern, with a shallow drop of the heater voltage from the nominal voltage, was proposed. Data visualization using the principal component analysis method and the random forest machine learning technique used to build classification models. The classification accuracy of 97% was obtained by a fusion of data collected by TGS 2610 and TGS 2602 sensors.

show abstract

Section: Comparison With Other Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Application of a Low-Cost Electronic Nose to Detect of Forest Tree Pathogens: Fusarium oxysporum and Phytophthora plurivora

et al. 2022

View full text Add to dashboard Cite

show abstract

“…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%

Analysis of Wheat Grain Infection by Fusarium Mycotoxin-Producing Fungi Using an Electronic Nose, GC-MS, and qPCR

Borowik,

Dyshko,

Tkaczyk

et al. 2024

Sensors

View full text Add to dashboard Cite

Fusarium graminearum and F. culmorum are considered some of the most dangerous pathogens of plant diseases. They are also considerably dangerous to humans as they contaminate stored grain, causing a reduction in yield and deterioration in grain quality by producing mycotoxins. Detecting Fusarium fungi is possible using various diagnostic methods. In the manuscript, qPCR tests were used to determine the level of wheat grain spoilage by estimating the amount of DNA present. High-performance liquid chromatography was performed to determine the concentration of DON and ZEA mycotoxins produced by the fungi. GC-MS analysis was used to identify volatile organic components produced by two studied species of Fusarium. A custom-made, low-cost, electronic nose was used for measurements of three categories of samples, and Random Forests machine learning models were trained for classification between healthy and infected samples. A detection performance with recall in the range of 88–94%, precision in the range of 90–96%, and accuracy in the range of 85–93% was achieved for various models. Two methods of data collection during electronic nose measurements were tested and compared: sensor response to immersion in the odor and response to sensor temperature modulation. An improvement in the detection performance was achieved when the temperature modulation profile with short rectangular steps of heater voltage change was applied.

show abstract

“…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%

Cross-sparse representation based on dispersion dictionary for ultrasonic guided wave to messenger cable damage detection in cladding zone

Jian-xi

Lin

Hong

et al. 2023

Structural Health Monitoring

View full text Add to dashboard Cite

The damage detection of messenger cable is an important guarantee to ensure the safety of electrified railways. The traditional nondestructive testing methods have difficulty in accurately detecting the damage of messenger cable in cladding zone. In this paper, a novel cross-sparse representation (CSR) method based on dispersion dictionary for ultrasonic guided wave (UGW) is proposed for the outer stranded wire of messenger cable in cladding zone. Firstly, the dispersion curves of UGW in multilayer spiral structure are solved by semi-analytical finite element method, to select an appropriate excitation signal. Secondly, the stationary phase approximation method is used to construct dispersion dictionary according to the dispersion curve which can characterize the modes and propagation distance of UGWs, and the CSR is proposed to separate and identify the damage signal. Thirdly, the simulation models of different damages in the outer stranded wire of messenger cable in the cladding zone are established to analyze the correlation between the damage rate and damage index in the cross-sections. Finally, the damage recognition effect based on CSR is analyzed and compared by experiments. The experimental results show that compared with the sparse representation (SR) method using traditional dictionary, the proposed method can improve the average accuracy of damage signal recognition from about 20% to 99.4% within a wide threshold range.

show abstract

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

Cited by 6 publications

References 31 publications

Application of a Low-Cost Electronic Nose to Detect of Forest Tree Pathogens: Fusarium oxysporum and Phytophthora plurivora

Application of a Low-Cost Electronic Nose to Detect of Forest Tree Pathogens: Fusarium oxysporum and Phytophthora plurivora

Analysis of Wheat Grain Infection by Fusarium Mycotoxin-Producing Fungi Using an Electronic Nose, GC-MS, and qPCR

Cross-sparse representation based on dispersion dictionary for ultrasonic guided wave to messenger cable damage detection in cladding zone

Contact Info

Product

Resources

About