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 Videos

Don't care values in induction

N Diamantidis1, E A Giakoumakis

  • 1Informatics Department, Athens University of Economics and Business, Greece. mgia@aueb.gr

Artificial Intelligence in Medicine
|October 1, 1996
PubMed
Summary

This study introduces efficient techniques for handling "don

Related Concept Videos

You might also read

Related Articles

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

Sort by
Same journal

GLF-Net: A quasi-periodic prior-guided waveform segmentation network for ECG delineation.

Artificial intelligence in medicine·2026
Same journal

Real-time EEG-based epileptic seizure prediction using artificial intelligence: A systematic review.

Artificial intelligence in medicine·2026
Same journal

R-peak detection and ECG data compression scheme based on empirical mode decomposition and wavelet transform.

Artificial intelligence in medicine·2026
Same journal

CastNet: A three-channel EEG-based deep learning model for cross-subject depression detection.

Artificial intelligence in medicine·2026
Same journal

State-of-the-art TinyML approaches for colorectal cancer detection: Current advances, challenges, and future directions.

Artificial intelligence in medicine·2026
Same journal

JRadiEvo: A Japanese radiology report generation model enhanced by evolutionary optimization of model merging.

Artificial intelligence in medicine·2026

Area of Science:

  • Machine Learning
  • Data Mining
  • Medical Informatics

Background:

  • Inductive learning algorithms excel at knowledge extraction from data, particularly in medical domains.
  • Real-world applications, including medical diagnosis, often involve unknown attribute values.
  • A critical distinction exists between missing values (due to lack of measurement) and don't care values (irrelevant to the class).

Purpose of the Study:

  • To address the challenge of 'don't care' values in inductive learning algorithms.
  • To highlight the importance of distinguishing between missing and don't care values in medical domains.
  • To present efficient techniques for handling don't care values during decision tree induction.

Main Methods:

  • Development of novel techniques for efficient processing of don't care values in decision tree induction.
  • Comparative analysis of datasets to investigate the prevalence of don't care versus missing values.
  • Examination of the impact of distinguishing these value types on expert-driven diagnosis.

Main Results:

  • The proposed techniques enable efficient handling of don't care values in decision tree induction.
  • Demonstrated the significant impact of distinguishing don't care from missing values in medical diagnosis.
  • Identified the presence of don't care values in both medical and non-medical real-world datasets.

Conclusions:

  • Distinguishing don't care values from missing values is crucial for accurate knowledge extraction in inductive learning, especially in medicine.
  • Efficient algorithms for handling don't care values improve decision tree induction.
  • The study underscores the practical relevance of this distinction in real-world data analysis.

Related Experiment Videos