Basics of artificial neural networks

Zupan, Jure

doi:10.1016/s0922-3487(03)23007-0

Cited by 6 publications

(5 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Artificial neural network (ANN) algorithms are used for a variety of applications where the goal is to discern a pattern in a large quantity of imperfect data. [31][32][33][34][35][36][37][38][39] For example, ANNs have been used in concert with ''electronic noses'' to identify nitrohydrocarbons in air, 40 lung cancer patients from their 1 for sensor element composition listings. b FA -floating all terms during the fit.…”

Section: Artificial Neural Network To Improve Overall Sensor Performancementioning

confidence: 99%

Tailored xerogel-based sensor arrays and artificial neural networks yield improved O2 detection accuracy and precision

Tang

Tao

Bukowski

et al. 2006

Analyst

View full text Add to dashboard Cite

The objective of this research is to develop arrays of tuned chemical sensors wherein each sensor element responds to a particular target analyte in a unique manner. By creating sol-gel-derived xerogels that are co-doped with two luminophores at a range of molar ratios, we can form suites of sensor elements that can exhibit a continuum of response profiles. We trained an artificial neural network (ANN) to "learn" to identify the optical outputs from these xerogel-based sensor arrays. By using the ANN in concert with our tailored sensor arrays we obtained a 5-10 fold improvement in accuracy and precision for quantifying O2 in unknown samples. We also explored the response characteristics of these types of sensor elements after they had been contacted with rat plasma/blood. Contact with plasma/blood caused approximately 15% of the luminophore molecules within the xerogels to become non-responsive to O2. This behavior is consistent with rat albumin blocking certain pore sub-populations within the mesoporous xerogel matrix thereby limiting O2 access to the luminophores.

show abstract

Section: Artificial Neural Network To Improve Overall Sensor Performancementioning

confidence: 99%

Tailored xerogel-based sensor arrays and artificial neural networks yield improved O2 detection accuracy and precision

Tang

Tao

Bukowski

et al. 2006

Analyst

View full text Add to dashboard Cite

show abstract

“…Artificial neural network (ANN) algorithms are employed for a range of applications where the objective is to detect a pattern in a large quantity of imperfect data. [3][4][5][6][7][8][9][10][11] For instance,…”

Section: Resultsmentioning

confidence: 99%

A novel, selective, and extremely responsive thienyl-based dual fluorogenic probe for tandem superoxide and Hg²⁺chemosensing

Singh

Murale

et al. 2013

Dalton Trans.

View full text Add to dashboard Cite

show abstract

“…ANN are sophisticated computational tools capable of handling non-linearity in explorative analysis, discriminant classification, and regression tasks. The use of ANNs for data processing has constantly been increasing (Zupan 2003;Marini et al 2008); regarding food analysis, ANN are often employed in modeling data obtained by devices known as electronic senses, that is, instrumental techniques or sensors imitating the human senses such as electronic noses, electronic tongues, and computer vision, widely applied today in food analysis for process monitoring and determining the quality and authenticity of foods (Marini 2009;Sĺiwinśka et al 2014).…”

Section: Ann-based Methodologymentioning

confidence: 99%

“…Here we only give a brief introduction to the methodology; the interested reader is referred to literature for the basics of ANN in chemometrics context (Zupan 2003) and a review of ANN applications in food science (Marini 2009). We do not describe the related methodology, support vector machine (SVM), which has also become very popular recently, but we refer to a tutorial review on this subject (Brereton and Lloyd 2010).…”

Section: Ann-based Methodologymentioning

confidence: 99%

Chemometrics – Bioinformatics

Cocchi

Vigni

Durante

2017

Food Authentication

View full text Add to dashboard Cite

Quality and authenticity are integrated measures of several characteristics either deliberately produced (sophistication, adulteration, counterfeit, color, appearance, etc.) or not (purity, contamination, degradation, etc.), as well as of the ensemble of features capable of linking the product to its origin, provenance, and typicality. In order to overcome the subjectivity which is inherent in some of the definitions reported above and in the procedures adopted to control them, mainly based on paper documentation, there is a need to introduce chemical, physico-chemical, and organoleptic determinations which can be related to the different aspects of quality, in other words, an exhaustive characterization of foodstuff. The analytical methodology actually evolved from the analysis of a subsets of properties on the basis of some a priori knowledge of possible constituents/contaminants, to broad sample characterization by using instrumental techniques, going from chromatographic-spectrometric series, through hyper-spectral imaging and higher dimensional spectroscopic techniques, to batteries of sensors/ microarray devices.In terms of data analysis, this implies a change of paradigm from the analysis of mainly univariate data (i.e., a limited number of determined analytes) to multivariate data analysis of the collected instrumental responses in order to capture the required information. This approach relies on data-driven discovery, that is, information is achieved from an understanding of the underlying inner relationships among variables as highlighted by data analysis a posteriori

show abstract

Basics of artificial neural networks

Cited by 6 publications

References 55 publications

Tailored xerogel-based sensor arrays and artificial neural networks yield improved O2 detection accuracy and precision

Tailored xerogel-based sensor arrays and artificial neural networks yield improved O2 detection accuracy and precision

A novel, selective, and extremely responsive thienyl-based dual fluorogenic probe for tandem superoxide and Hg²⁺chemosensing

Chemometrics – Bioinformatics

Contact Info

Product

Resources

About

Basics of artificial neural networks

Cited by 6 publications

References 55 publications

Tailored xerogel-based sensor arrays and artificial neural networks yield improved O2 detection accuracy and precision

Tailored xerogel-based sensor arrays and artificial neural networks yield improved O2 detection accuracy and precision

A novel, selective, and extremely responsive thienyl-based dual fluorogenic probe for tandem superoxide and Hg2+chemosensing

Chemometrics – Bioinformatics

Contact Info

Product

Resources

About

A novel, selective, and extremely responsive thienyl-based dual fluorogenic probe for tandem superoxide and Hg²⁺chemosensing