Jove
Visualize
Contact Us

Related Concept Videos

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
  1. Home
  3. Integrating Weight And Imaging Features: A Machine Learning Framework For Larval Instar Identification In Mythimna Separata (walker).
  1. Home
  3. Integrating Weight And Imaging Features: A Machine Learning Framework For Larval Instar Identification In Mythimna Separata (walker).

Related Experiment Video

FIM Imaging and FIMtrack: Two New Tools Allowing High-throughput and Cost Effective Locomotion Analysis
10:02

FIM Imaging and FIMtrack: Two New Tools Allowing High-throughput and Cost Effective Locomotion Analysis

Published on: December 24, 2014

11.7K

Integrating weight and imaging features: A machine learning framework for larval instar identification in Mythimna

Xiao Feng1, Jingyu Wang1, Yunliang Ji1

  • 1College of Plant Protection, Jilin Agricultural University, Changchun, PR China.

Bulletin of Entomological Research
|April 23, 2025

View abstract on PubMed

Summary
This summary is machine-generated.

Machine learning accurately identifies oriental armyworm (Mythimna separata) larval instars using image features and predicted weight. This automated approach enhances pest monitoring and management strategies.

Keywords:
Shapley additive explanationsinstar identificationlarval weightmachine learningpermutation feature importance

More Related Videos

Imaging and Analysis of Tissue Orientation and Growth Dynamics in the Developing Drosophila Epithelia During Pupal Stages
08:25

Imaging and Analysis of Tissue Orientation and Growth Dynamics in the Developing Drosophila Epithelia During Pupal Stages

Published on: June 2, 2020

9.2K
Flying Insect Detection and Classification with Inexpensive Sensors
05:16

Flying Insect Detection and Classification with Inexpensive Sensors

Published on: October 15, 2014

25.1K

Related Experiment Videos

FIM Imaging and FIMtrack: Two New Tools Allowing High-throughput and Cost Effective Locomotion Analysis
10:02

FIM Imaging and FIMtrack: Two New Tools Allowing High-throughput and Cost Effective Locomotion Analysis

Published on: December 24, 2014

11.7K
Imaging and Analysis of Tissue Orientation and Growth Dynamics in the Developing Drosophila Epithelia During Pupal Stages
08:25

Imaging and Analysis of Tissue Orientation and Growth Dynamics in the Developing Drosophila Epithelia During Pupal Stages

Published on: June 2, 2020

9.2K
Flying Insect Detection and Classification with Inexpensive Sensors
05:16

Flying Insect Detection and Classification with Inexpensive Sensors

Published on: October 15, 2014

25.1K

Area of Science:

  • Agricultural Entomology
  • Computational Biology
  • Machine Learning Applications

Background:

  • Oriental armyworm (Mythimna separata) outbreaks cause significant crop losses.
  • Conventional pest monitoring methods are labor-intensive and error-prone.
  • Accurate identification of larval instars is crucial for effective pest management.

Purpose of the Study:

  • To develop an automated system for precise identification of Mythimna separata larval instars using machine learning.
  • To evaluate the contribution of image-derived features and predicted larval weight for instar classification.
  • To compare the performance of different machine learning models for pest identification and weight prediction.

Main Methods:

  • Analysis of 1577 larval images for geometric, color, and texture features.
  • Prediction of larval weight using 13 regression models.
  • Instar identification using Support Vector Classifier (SVC), Random Forest, and Multi-Layer Perceptron.
  • Feature importance analysis to identify key classification drivers.

    • Main Results:

    • Machine learning models achieved high efficiency and accuracy in automated instar identification.
    • Predicted larval weight was a significant feature, enhancing all identification models.
    • SVC achieved the highest instar identification accuracy (94%).
    • BaggingRegressor showed the best performance for larval weight prediction (R² = 98.20%).

    Conclusions:

    • Integrating predicted larval weight with image features is a highly effective strategy for pest identification.
    • Machine learning offers a scalable and reliable framework for precise pest management.
    • The proposed methodology improves accuracy and efficiency in larval instar identification, aiding targeted control strategies.