Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Jun 1, 2026

Electronic Tongue Generating Continuous Recognition Patterns for Protein Analysis
08:46

Electronic Tongue Generating Continuous Recognition Patterns for Protein Analysis

Published on: September 16, 2014

Improved probabilistic neural network algorithm for chemical sensor array pattern recognition.

R E Shaffer1, S L Rose-Pehrsson

  • 1Chemistry Division, Naval Research Laboratory, Code 6116, 4555 Overlook Avenue, SW, Washington, D.C. 20375.

Analytical Chemistry
|June 14, 2011
PubMed
Summary
This summary is machine-generated.

An improved probabilistic neural network (IPNN) enhances chemical sensor array pattern recognition. This algorithm reduces computational needs, speeds training, and lowers false alarms for surface acoustic wave sensors.

Related Experiment Videos

Last Updated: Jun 1, 2026

Electronic Tongue Generating Continuous Recognition Patterns for Protein Analysis
08:46

Electronic Tongue Generating Continuous Recognition Patterns for Protein Analysis

Published on: September 16, 2014

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

MS2 Coliphage as a Surrogate for 2009 Pandemic Influenza A (H1N1) Virus (pH1N1) in Surface Survival Studies on N95 Filtering Facepiece Respirators.

Journal of the International Society for Respiratory Protection·2015
Same author

Note: pneumatically modulated liquid delivery with feedback control.

The Review of scientific instruments·2012
Same author

Selective metals determination with a photoreversible spirobenzopyran.

Analytical chemistry·2011
Same author

A method to determine the available UV-C dose for the decontamination of filtering facepiece respirators.

Journal of applied microbiology·2010
Same author

Application of quantitative chemometric analysis techniques to direct sampling mass spectrometry.

Analytical chemistry·2001
Same author

Genetic algorithm-based method for selecting wavelengths and model size for use with partial least-squares regression: application to near-infrared spectroscopy.

Analytical chemistry·1996
Same journal

Strain-Level Food Surveillance of <i>Escherichia coli</i> Using a Specific-Nonspecific Hybrid Sensor Array Strategy.

Analytical chemistry·2026
Same journal

A Field-Portable Fe(IV)-Mediated Competitive Quenching Chemiluminescence Platform with a Synchronous Y-Shaped Flow-through Cell for Broad-Spectrum Quantification of Volatile Phenols.

Analytical chemistry·2026
Same journal

Single-Molecule Characterization of CRISPR-Cas12a for Amplification-Free Genetic Testing.

Analytical chemistry·2026
Same journal

Integrated Acoustofluidic Manipulation and Oscillation-Stabilized Magnetic Relaxation Biosensing for <i>Salmonella</i> Detection.

Analytical chemistry·2026
Same journal

A Self-Powered Sensing Platform Based on the Janus Heterostructure for Machine Learning-Assisted Dual-Mode Detection of 17β-Estradiol.

Analytical chemistry·2026
Same journal

Large Language Model-Generated Dietary Metabolite Biomarker Database Drives Deep Annotation of the Human Diet Metabolome.

Analytical chemistry·2026
See all related articles

Area of Science:

  • Artificial Intelligence
  • Chemical Sensing
  • Signal Processing

Background:

  • Probabilistic neural networks (PNNs) are effective for pattern recognition in chemical sensor arrays.
  • Conventional PNNs can be computationally intensive and require significant memory.
  • Optimizing PNN parameters like kernel width and rejection threshold is crucial for performance.

Purpose of the Study:

  • To introduce an improved probabilistic neural network (IPNN) algorithm for chemical sensor array pattern recognition.
  • To enhance the efficiency and accuracy of PNNs by reducing computational and memory demands.
  • To decrease the false alarm rate in sensor array data analysis.

Main Methods:

  • Developed an IPNN based on a modified PNN incorporating three key innovations.
  • Implemented a competitive learning strategy from learning vector quantization (LVQ) neural networks to reduce storage and computation.
  • Utilized a distance-based calculation for approximating optimal PNN kernel width, reducing training time and user input.
  • Applied Monte Carlo simulations to establish an optimal rejection threshold for outlier rejection.

Main Results:

  • The IPNN's hidden layer requires significantly less storage space compared to conventional PNNs.
  • The distance-based kernel width approximation decreased training time without user intervention.
  • The Monte Carlo-derived rejection threshold effectively identified and rejected ambiguous patterns.
  • Demonstrated IPNN utility on simulated and laboratory surface acoustic wave sensor array data sets.

Conclusions:

  • The IPNN algorithm offers a more efficient and effective solution for chemical sensor array pattern recognition.
  • Innovations in the IPNN lead to reduced computational load, faster training, and improved accuracy.
  • The IPNN successfully minimizes false alarms through optimized parameter selection and outlier rejection.