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

Quantifying and Rejecting Outliers: The Grubbs Test01:02

Quantifying and Rejecting Outliers: The Grubbs Test

1.6K
Sometimes, a data set can have a recorded numerical observation that greatly  deviates from the rest of the data. Assuming that the data is normally distributed, a statistical method called the Grubbs test can be used to determine whether the observation is truly an outlier.  To perform a two-tailed Grubbs test, first, calculate the absolute difference between the outlier and the mean. Then, calculate the ratio between this difference and the standard deviation of the sample. This...
1.6K
What Are Outliers?01:12

What Are Outliers?

3.8K
Outliers are observed data points that are far from the least squares line. They have unusual values and need to be examined carefully. Though an outlier may result from erroneous data, at other times, it may hold valuable information about the population under study and should be included in the data. Hence, it is crucial to examine what causes a data point to be an outlier.
The z score is used to find outliers or unusual values. It should be noted that any values beyond -2 and +2 are...
3.8K
Outliers and Influential Points01:08

Outliers and Influential Points

4.0K
An outlier is an observation of data that does not fit the rest of the data. It is sometimes called an extreme value. When you graph an outlier, it will appear not to fit the pattern of the graph. Some outliers are due to mistakes (for example, writing down 50 instead of 500), while others may indicate that something unusual is happening. Outliers are present far from the least squares line in the vertical direction. They have large "errors," where the "error" or residual is the...
4.0K
Detection of Gross Error: The Q Test01:00

Detection of Gross Error: The Q Test

6.1K
When one or more data points appear far from the rest of the data, there is a need to determine whether they are outliers and whether they should be eliminated from the data set to ensure an accurate representation of the measured value. In many cases, outliers arise from gross errors (or human errors) and do not accurately reflect the underlying phenomenon. In some cases, however, these apparent outliers reflect true phenomenological differences. In these cases, we can use statistical methods...
6.1K

You might also read

Related Articles

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

Sort by
Same author

Gender discrimination, marital attitude, and perceived choice and awareness as explanatory factors of flourishing among young Indian unmarried women.

Discover mental health·2026
Same author

Modeling Particle Transport In Biomedical Flows Using Implicit Geometry Representations.

bioRxiv : the preprint server for biology·2026
Same author

In-context adaptation of VLMs for few-shot cell detection in optical microscopy.

Frontiers in artificial intelligence·2026
Same author

Steroid-responsive delayed multifocal encephalopathy following vasculotoxic snakebite with serial MRI evolution: a case report.

Toxicon : official journal of the International Society on Toxinology·2026
Same author

Association between household fuel use and cardiometabolic risk factors in sub-Saharan Africa: A systematic review.

Environmental pollution (Barking, Essex : 1987)·2026
Same author

Single-Center Experience with the Optiblock Coil: An Efficient and Thrombogenic Solution for Targeted Vessel Takedown.

World neurosurgery·2026
Same journal

UAV-based temporal synergistic estimation of multiple alfalfa qualities integrating physics-informed network and 3D allometric operator.

Plant phenomics (Washington, D.C.)·2026
Same journal

Machine learning to predict genotypes and genotype-environment interaction associated with complex traits for genomic selection.

Plant phenomics (Washington, D.C.)·2026
Same journal

FQGR-net: Morphology-based litchi flower quantification and gender recognition.

Plant phenomics (Washington, D.C.)·2026
Same journal

Thermal image segmentation in weedy fields via synthetic RGB-trained models and GAN-based cross-modality alignment.

Plant phenomics (Washington, D.C.)·2026
Same journal

Unlocking almond breeding for nutritional composition with hyperspectral imaging.

Plant phenomics (Washington, D.C.)·2026
Same journal

From plots to commercial fields: scalable, transferable cotton morphology and productivity estimation using functional growth proxies from UAV and PlanetScope time series.

Plant phenomics (Washington, D.C.)·2026
See all related articles

Related Experiment Video

Updated: Jun 27, 2025

Flying Insect Detection and Classification with Inexpensive Sensors
05:16

Flying Insect Detection and Classification with Inexpensive Sensors

Published on: October 15, 2014

25.2K

Out-of-Distribution Detection Algorithms for Robust Insect Classification.

Mojdeh Saadati1, Aditya Balu2, Shivani Chiranjeevi2

  • 1Department of Computer Science, Iowa State University, Ames, IA, USA.

Plant Phenomics (Washington, D.C.)
|May 3, 2024
PubMed
Summary
This summary is machine-generated.

Out-of-distribution (OOD) detection algorithms enhance insect classification in agriculture by identifying unknown or irrelevant images. This study evaluates OOD methods, recommending the best approach to improve model reliability and user trust in pest identification systems.

More Related Videos

A Rapid Method to Confine and Safely Handle Bees in the Field
03:45

A Rapid Method to Confine and Safely Handle Bees in the Field

Published on: August 23, 2024

750
A Precise and Autonomous System for the Detection of Insect Emergence Patterns
06:22

A Precise and Autonomous System for the Detection of Insect Emergence Patterns

Published on: January 9, 2019

5.7K

Related Experiment Videos

Last Updated: Jun 27, 2025

Flying Insect Detection and Classification with Inexpensive Sensors
05:16

Flying Insect Detection and Classification with Inexpensive Sensors

Published on: October 15, 2014

25.2K
A Rapid Method to Confine and Safely Handle Bees in the Field
03:45

A Rapid Method to Confine and Safely Handle Bees in the Field

Published on: August 23, 2024

750
A Precise and Autonomous System for the Detection of Insect Emergence Patterns
06:22

A Precise and Autonomous System for the Detection of Insect Emergence Patterns

Published on: January 9, 2019

5.7K

Area of Science:

  • Agricultural Science
  • Computer Vision
  • Machine Learning

Background:

  • Accurate insect identification and classification are crucial for effective agricultural pest management, with significant economic and environmental implications.
  • Deep learning models show promise for insect classification but struggle with out-of-distribution (OOD) data, such as non-insect images or novel insect classes.
  • Out-of-distribution (OOD) detection algorithms can prevent misclassification by identifying data that deviates from the training distribution.

Purpose of the Study:

  • To explore the application and performance of state-of-the-art OOD detection algorithms for insect classification in agricultural contexts.
  • To evaluate extrusive OOD algorithms (maximum softmax probability, Mahalanobis distance, energy-based) that integrate with pre-trained classifiers.
  • To provide practical guidelines for robust OOD performance in agricultural AI applications by analyzing algorithm sensitivity to base model accuracy, domain dissimilarity, and data imbalance.

Main Methods:

  • Comparison of three extrusive OOD detection algorithms: maximum softmax probability, Mahalanobis distance (MAH), and energy-based methods.
  • Evaluation of OOD algorithm performance across varying base model accuracies, levels of domain dissimilarity, and data imbalance scenarios.
  • Identification of the most effective OOD algorithm for enhancing an accurate insect classifier.

Main Results:

  • The study systematically evaluated the performance of different OOD detection algorithms on insect classification tasks.
  • Analysis revealed how factors like classifier accuracy, data dissimilarity, and class imbalance influence OOD detection effectiveness.
  • The most effective OOD algorithm was identified and its performance demonstrated for robust pest classification.

Conclusions:

  • Out-of-distribution detection algorithms significantly improve the reliability of insect pest classification systems in agriculture.
  • These algorithms enhance user trust by enabling models to abstain from predictions on uncertain or irrelevant inputs.
  • The findings offer practical insights for deploying dependable AI solutions in real-world agricultural settings.