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

The Evidence for Evolution02:55

The Evidence for Evolution

48.1K
Genetic variations accumulating within populations over generations give rise to biological evolution. Evolutionary changes can result in the formation of novel varieties and entire new species. These changes are responsible for the diverse forms of life inhabiting the planet. The evidence for evolution suggests that all living organisms descended from common ancestors.
48.1K
Convergent Evolution01:54

Convergent Evolution

32.9K
Evolution shapes the features of organisms over time, ensuring that they are suited for the environments in which they live. Sometimes, selection pressure leads to the rise of similar but unrelated adaptations in organisms with no recent common ancestors, a process known as convergent evolution.
32.9K
Eukaryotic Evolution01:24

Eukaryotic Evolution

41.4K
The endosymbiont theory is the most widely accepted theory of eukaryotic evolution; however, its progression is still somewhat debated. According to the nucleus-first hypothesis, the ancestral prokaryote first evolved a membrane to enclose DNA and form the nucleus. Conversely, the mitochondria-first hypothesis suggests that the nucleus was formed after endosymbiosis of mitochondria.
Contrary to the endosymbiont theory, the eukaryote-first hypothesis proposes that the simpler prokaryotic and...
41.4K
Synteny and Evolution02:31

Synteny and Evolution

3.8K
John H. Renwick first coined the term “synteny” in 1971, which refers to the genes present on the same chromosomes, even if they are not genetically linked. The species with common ancestry tend to show conserved syntenic regions. Therefore, the concept of synteny is nowadays used to describe the evolutionary relationship between species.
Around 80 million years ago, the human and mice lineages diverged from the common ancestor. During the course of evolution, the ancestral...
3.8K
Fixed Action Patterns01:06

Fixed Action Patterns

17.6K
A fixed action pattern (FAP) is a specific, hard-wired sequence of behaviors that occurs in response to an external stimulus, called a sign stimulus. The behavior is “fixed” because it is essentially unchangeable—proceeding similarly across individuals of a species every time it occurs.
17.6K
Gene Evolution - Fast or Slow?02:05

Gene Evolution - Fast or Slow?

3.7K
3.7K

You might also read

Related Articles

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

Sort by
Same author

A hybrid deep learning framework for epileptic seizure prediction using scalp and intracranial EEG data.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2026
Same author

Large language models in healthcare: a systematic evaluation on medical Q/A datasets.

Health information science and systems·2025
Same author

Potential of AI-based diagnostic grading system for knee osteoarthritis.

Frontiers in medicine·2025
Same author

Psychiatric disorders from EEG signals through deep learning models.

IBRO neuroscience reports·2024
Same author

Computational imaging for rapid detection of grade-I cerebral small vessel disease (cSVD).

Heliyon·2024
Same author

Applying an adaptive Otsu-based initialization algorithm to optimize active contour models for skin lesion segmentation.

Journal of X-ray science and technology·2022

Related Experiment Video

Updated: Feb 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

8.2K

m-CALP - Yet another way of generating handwritten data through evolution for pattern recognition.

Aamir Wali1, Mehreen Saeed1

  • 1Department of Computer Science, FAST-NUCES, Faisal Town, Lahore, Pakistan.

Bio Systems
|December 12, 2018
PubMed
Summary

A new method, m-CALP, improves handwritten data generation for pattern recognition by considering image deformation during evolution. This approach enhances data quality and classifier performance, especially for small datasets.

Keywords:
CALPCellular automataData evolutionData generationDynamic generation of pool of ensemblesEnsemblesHandwritten pattern recognition

More Related Videos

Monitoring Activation of the Antiviral Pattern Recognition Receptors RIG-I And PKR By Limited Protease Digestion and Native PAGE
12:43

Monitoring Activation of the Antiviral Pattern Recognition Receptors RIG-I And PKR By Limited Protease Digestion and Native PAGE

Published on: July 29, 2014

12.7K
Generating Strictly Controlled Stimuli for Figure Recognition Experiments
05:39

Generating Strictly Controlled Stimuli for Figure Recognition Experiments

Published on: March 18, 2019

5.6K

Related Experiment Videos

Last Updated: Feb 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

8.2K
Monitoring Activation of the Antiviral Pattern Recognition Receptors RIG-I And PKR By Limited Protease Digestion and Native PAGE
12:43

Monitoring Activation of the Antiviral Pattern Recognition Receptors RIG-I And PKR By Limited Protease Digestion and Native PAGE

Published on: July 29, 2014

12.7K
Generating Strictly Controlled Stimuli for Figure Recognition Experiments
05:39

Generating Strictly Controlled Stimuli for Figure Recognition Experiments

Published on: March 18, 2019

5.6K

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Machine Learning

Background:

  • Existing Cellular Automata Learning and Prediction (CALP) models generate handwritten data for pattern recognition through evolution.
  • The CALP method lacks intuitiveness by not accounting for image deformation during evolution, leading to distorted shapes.
  • This deformation can negatively impact the effectiveness of the generated data for pattern recognition tasks.

Purpose of the Study:

  • To introduce m-CALP, a novel evolutionary data generation method that incorporates image deformation into its objective function.
  • To evaluate the performance of m-CALP against the original CALP model and other synthetic oversampling techniques.
  • To demonstrate the efficacy of m-CALP in improving pattern recognition, particularly with small training datasets.

Main Methods:

  • Implemented m-CALP, an evolutionary algorithm that evolves handwritten shapes while considering image deformation.
  • Replicated the experimental setup of the CALP model using the same 5 handwritten datasets and classifiers.
  • Compared the performance of data evolved by m-CALP against CALP and state-of-the-art methods like SMOTE and BORDERLINE-SMOTE.

Main Results:

  • Data evolved using m-CALP preserves essential pattern properties, unlike the distorted shapes produced by CALP.
  • m-CALP demonstrates superior performance compared to CALP in most experimental scenarios.
  • Evolving small-sized training data with m-CALP yields better results than both CALP and larger datasets.

Conclusions:

  • m-CALP offers a more intuitive and effective approach to evolutionary data generation for pattern recognition.
  • The method significantly improves upon existing CALP techniques by managing image deformation.
  • m-CALP presents a promising solution for developing robust classifiers, especially when dealing with limited training data.