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 Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Mechanochemical Preparation of Superabsorbent Materials from Okara and Itaconic Acid.

Molecules (Basel, Switzerland)·2026
Same author

Overexpression of the <i>FTSH</i> gene <i>GH_DO1G0225.1</i> enhances resistance against heat stress in cotton (<i>Gossypium hirsutum</i> L.).

Frontiers in genetics·2026
Same author

Solid Lipid Nanoparticle Mediated Intranasal Drug Delivery for Brain Targeting: A Comprehensive Review.

CNS & neurological disorders drug targets·2026
Same author

Traumatic infantile unicystic ameloblastoma of posterior maxilla- A case report.

National journal of maxillofacial surgery·2026
Same author

Dual Modification of Guar Meal via Fermentation and Enzyme Treatment Enhances Growth Performance, Nutrient Digestibility and Gut Morphology in Broilers.

Veterinary medicine and science·2026
Same author

Effects of Betaine on Performance, Blood Biochemistry, Nutrient Utilization and Gut Health in Coccidia-Infected Broilers.

Veterinary medicine and science·2026

Related Experiment Video

Updated: Mar 17, 2026

Fine-tuning the Size and Minimizing the Noise of Solid-state Nanopores
09:43

Fine-tuning the Size and Minimizing the Noise of Solid-state Nanopores

Published on: October 31, 2013

14.3K

An accelerated framework for the classification of biological targets from solid-state micropore data.

Madiha Hanif1, Abdul Hafeez2, Yusuf Suleman3

  • 1Nano-Bio Lab, University of Texas at Arlington, Arlington, TX 76019; Department of Bioengineering, University of Texas at Arlington, Arlington, TX 76019; Nanotechnology Research Center, University of Texas at Arlington, Arlington, TX 76019.

Computer Methods and Programs in Biomedicine
|August 3, 2016
PubMed
Summary

This study introduces a machine learning method for real-time analysis of biological data from micro- and nanoscale systems. The approach enhances cell detection and classification accuracy, significantly speeding up data processing using graphics processing units (GPUs).

Keywords:
Cancer detectionHuman cellsPattern detection and classificationRun-time systemsSolid-state micropores/nanopores

More Related Videos

Monitoring Protein Adsorption with Solid-state Nanopores
08:51

Monitoring Protein Adsorption with Solid-state Nanopores

Published on: December 2, 2011

14.1K
Membrane Transport Processes Analyzed by a Highly Parallel Nanopore Chip System at Single Protein Resolution
11:55

Membrane Transport Processes Analyzed by a Highly Parallel Nanopore Chip System at Single Protein Resolution

Published on: August 16, 2016

12.2K

Related Experiment Videos

Last Updated: Mar 17, 2026

Fine-tuning the Size and Minimizing the Noise of Solid-state Nanopores
09:43

Fine-tuning the Size and Minimizing the Noise of Solid-state Nanopores

Published on: October 31, 2013

14.3K
Monitoring Protein Adsorption with Solid-state Nanopores
08:51

Monitoring Protein Adsorption with Solid-state Nanopores

Published on: December 2, 2011

14.1K
Membrane Transport Processes Analyzed by a Highly Parallel Nanopore Chip System at Single Protein Resolution
11:55

Membrane Transport Processes Analyzed by a Highly Parallel Nanopore Chip System at Single Protein Resolution

Published on: August 16, 2016

12.2K

Area of Science:

  • Biotechnology and Biomedical Engineering
  • Computational Biology and Bioinformatics
  • Machine Learning Applications in Life Sciences

Background:

  • Micro- and nanoscale systems offer ultrahigh sensitivity for detecting biological targets like DNA, proteins, and cells.
  • Significant noise in raw data from sensitive devices complicates analysis and hinders real-time feedback.
  • Efficient data processing and real-time analysis are critical for advancing biological target detection systems.

Purpose of the Study:

  • To develop and validate a supervised machine learning algorithm for real-time detection and classification of biological targets.
  • To improve the speed and accuracy of analyzing pulse data generated by micro- and nanoscale sensing devices.
  • To implement a non-commercial, GPU-accelerated system for streamlined biological data analysis in academic research.

Main Methods:

  • A supervised machine learning approach was employed to record single cell events (pulses) and compute relevant features.
  • The algorithm classifies cellular patterns, distinguishing between types such as cancerous and non-cancerous cells using training data.
  • A parallel implementation on a graphics processing unit (GPU) was developed to accelerate the computational analysis.

Main Results:

  • The developed algorithm achieved 70% accuracy in cell detection from raw data, with improved classification accuracy using larger training sets.
  • GPU parallelization demonstrated a three-to-four-fold speedup in data processing compared to serial implementation on a CPU.
  • The study presents the first non-commercial GPU-based technique for real-time analysis coupled with biological cluster targeting.

Conclusions:

  • The supervised machine learning approach effectively processes and classifies biological target data in real-time.
  • GPU acceleration significantly enhances the efficiency of data analysis, addressing a key limitation in sensitive biosensing systems.
  • This GPU-based system offers a viable, non-commercial solution for real-time analysis, advancing capabilities in biological research.