Agent Identification Using a Sparse Bayesian Model

Huang, Duan; Li, Hongbin; Jing, Xie; Panikov, N. S.; Cui, Hong‐Liang

doi:10.1109/jsen.2011.2130521

Cited by 2 publications

(3 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Measuring bacterial odor in cow manure isolates indicates good reproducibility. Bit-based direct fingerprinting methods like this one are less intelligent than machine learning tools [42][43][44][45], but they have reduced energy dissipation and can be important in specific FES applications. Funding: X.Y.…”

Section: Discussionmentioning

confidence: 99%

“…In principle, the generated patterns, such as the power density spectra (PDS), bispectra, etc., can directly be fed into a classifier (neural network and other machine learning/artificial intelligence tools [42][43][44][45]), to identify the chemical composition related to this pattern. However, machine learning tools require intensive data processing which implies a large energy dissipation.…”

Section: Binary Fingerprintsmentioning

confidence: 99%

“…It is important to note that the pattern generation/recognition aspects are the subject of intensive research that goes beyond the scope of our papers-see for example [42][43][44][45]. Obviously, such research can incorporate artificial intelligence-related technologies, too.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Ternary Fingerprints with Reference Odor for Fluctuation-Enhanced Sensing

2020

View full text Add to dashboard Cite

An improved method for fluctuation-enhanced sensing (FES) is introduced. We enhanced the old binary fingerprinting method, where the fingerprint bit values were ±1, by introducing ternary fingerprint bits utilizing a reference odor. In the ternary method, the fingerprint bit values are −1, 0, and +1, where the 0 value stands for the situation where the slope of the spectrum is identical to that of the reference odor. The application of the reference odor spectrum makes the fingerprint relative to the reference. The ternary nature and the reference feature increase the information entropy of the fingerprints. The method is briefly illustrated by sensing bacterial odor in cow manure isolates.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Binary Fingerprintsmentioning

confidence: 99%

See 1 more Smart Citation

Ternary Fingerprints with Reference Odor for Fluctuation-Enhanced Sensing

2020

View full text Add to dashboard Cite

show abstract

Component spectra extraction from terahertz measurements of unknown mixtures

Hou

Huang

et al. 2015

Appl. Opt.

View full text Add to dashboard Cite

The aim of this work is to extract component spectra from unknown mixtures in the terahertz region. To that end, a method, hard modeling factor analysis (HMFA), was applied to resolve terahertz spectral matrices collected from the unknown mixtures. This method does not require any expertise of the user and allows the consideration of nonlinear effects such as peak variations or peak shifts. It describes the spectra using a peak-based nonlinear mathematic model and builds the component spectra automatically by recombination of the resolved peaks through correlation analysis. Meanwhile, modifications on the method were made to take the features of terahertz spectra into account and to deal with the artificial baseline problem that troubles the extraction process of some terahertz spectra. In order to validate the proposed method, simulated wideband terahertz spectra of binary and ternary systems and experimental terahertz absorption spectra of amino acids mixtures were tested. In each test, not only the number of pure components could be correctly predicted but also the identified pure spectra had a good similarity with the true spectra. Moreover, the proposed method associated the molecular motions with the component extraction, making the identification process more physically meaningful and interpretable compared to other methods. The results indicate that the HMFA method with the modifications can be a practical tool for identifying component terahertz spectra in completely unknown mixtures. This work reports the solution to this kind of problem in the terahertz region for the first time, to the best of the authors' knowledge, and represents a significant advance toward exploring physical or chemical mechanisms of unknown complex systems by terahertz spectroscopy.

show abstract

Agent Identification Using a Sparse Bayesian Model

Cited by 2 publications

References 19 publications

Ternary Fingerprints with Reference Odor for Fluctuation-Enhanced Sensing

Ternary Fingerprints with Reference Odor for Fluctuation-Enhanced Sensing

Component spectra extraction from terahertz measurements of unknown mixtures

Contact Info

Product

Resources

About