Search research articles

Search research articles

Related Experiment Videos

Bacteria classification using Cyranose 320 electronic nose.

Ritaban Dutta¹, Evor L Hines, Julian W Gardner

¹Division of Electrical and Electronic Engineering, School of Engineering, University of Warwick, Coventry, CV4 7AL, United Kingdom. r.dutta@warwick.ac.uk

Biomedical Engineering Online

|November 20, 2002

Summary

This summary is machine-generated.

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

Single and Dual Mode SMR Sensors for Pest Detection in Plant Health Monitoring.

Sensors (Basel, Switzerland)·2026

Same author

Micromachined Thermal Gas Sensors-A Review.

Sensors (Basel, Switzerland)·2023

Same author

Artificial intelligence automates the characterization of reversibly actuating planar-flow-casted NiTi shape memory alloy foil.

PloS one·2022

Same author

Development of a physiological-based model that uses standard polysomnography and clinical data to predict oral appliance treatment outcomes in obstructive sleep apnea.

Journal of clinical sleep medicine : JCSM : official publication of the American Academy of Sleep Medicine·2021

Same author

Vision based supervised restricted Boltzmann machine helps to actuate novel shape memory alloy accurately.

Scientific reports·2021

Same author

Optimising Deep Learning at the Edge for Accurate Hourly Air Quality Prediction.

Sensors (Basel, Switzerland)·2021

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

An electronic nose accurately identified six bacteria species causing eye infections. Combining advanced data clustering and machine learning achieved up to 98% classification accuracy, improving detection of complex bacterial mixtures.

Area of Science:

Biotechnology
Analytical Chemistry
Machine Learning

Background:

An electronic nose (e-nose), the Cyrano Sciences' Cyranose 320, equipped with 32 polymer carbon black composite sensors, was employed to detect six bacterial species responsible for eye infections.
Bacterial samples were analyzed in saline solutions at various concentrations by measuring the headspace volatiles using the portable e-nose system.
The complex mixture of chemical compounds generated by the bacteria presented a significant analytical challenge.

Purpose of the Study:

To evaluate the effectiveness of an electronic nose for identifying specific bacteria linked to ocular infections.
To explore advanced data analysis techniques for improving the classification accuracy of complex bacterial samples.
To determine the optimal machine learning models for accurate bacteria identification from e-nose data.

Related Experiment Videos

Main Methods:

Principal Component Analysis (PCA) was initially used, achieving 74% accuracy in classifying four out of six bacterial species.
An innovative approach combined 3D scatter plots, Fuzzy C Means (FCM), and Self-Organizing Map (SOM) for enhanced bacteria data clustering.
Supervised classifiers, including Multi-Layer Perceptron (MLP), Probabilistic Neural Network (PNN), and Radial Basis Function (RBF) networks, were applied for classification.

Main Results:

A 6x1 SOM network demonstrated a high classification accuracy of 96% for the six bacteria classes.
Comparative evaluation of classifiers revealed that the RBF network achieved the highest accuracy, predicting six bacteria classes with up to 98% accuracy.
The study successfully demonstrated the capability to differentiate and identify six distinct bacterial species with high precision.

Conclusions:

The analysis and feature extraction of complex bacterial data from e-nose measurements are challenging.
The combined application of nonlinear data clustering methods effectively addresses feature extraction challenges with complex datasets.
This integrated approach significantly enhances the performance of the Cyrano Sciences' Cyranose 320 e-nose for bacteria identification.