Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Light Acquisition

Light Acquisition

In order to produce glucose, plants need to capture sufficient light energy. Many modern plants have evolved leaves specialized for light acquisition. Leaves can be only millimeters in width or tens of meters wide, depending on the environment. Due to competition for sunlight, evolution has driven the evolution of increasingly larger leaves and taller plants, to avoid shading by their neighbors with contaminant elaboration of root architecture and mechanisms to transport water and nutrients.

You might also read

Related Articles

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

Sort by

Same author

Mechano-biological mechanisms of femoral head collapse in osteonecrosis: a multiscale zonal analysis.

Hip international : the journal of clinical and experimental research on hip pathology and therapy·2026

Same author

Multiscale mechano-biological characterization of necrotic, sclerotic, and healthy zones in femoral head osteonecrosis: linking viscoelastic heterogeneity to mechanical failure.

Calcified tissue international·2026

Same author

Absolute Quantification of microRNA Copies in Exosomes Using Real-Time PCR.

Current protocols·2026

Same author

Stress-induced alteration of small extracellular vesicles drives amyloid-beta sequestration and exacerbates Alzheimer's disease pathogenesis.

Alzheimer's research & therapy·2026

Same author

Infrared spectral signatures of plasma-derived small extracellular vesicles reveal diagnostic potential of idiopathic Parkinson's disease detection.

Biochimica et biophysica acta. Biomembranes·2026

Same author

Constructed wetlands as sustainable solutions for textile effluent treatment: a review.

Physiology and molecular biology of plants : an international journal of functional plant biology·2026

Search research articles

Related Experiment Video

Updated: Jun 17, 2025

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Published on: February 9, 2024

Fruit-In-Sight: A deep learning-based framework for secondary metabolite class prediction using fruit and leaf

Neeraja M Krishnan¹, Saroj Kumar¹, Binay Panda^1,2

¹School of Biotechnology, Jawaharlal Nehru University, New Delhi, India.

|August 8, 2024

Summary

This summary is machine-generated.

Deep learning models predict metabolite concentration in neem fruits using only images. This simplifies selecting trees for valuable secondary metabolite collection without lab analysis.

More Related Videos

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning

Published on: March 3, 2023

Related Experiment Videos

Last Updated: Jun 17, 2025

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Published on: February 9, 2024

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning

Published on: March 3, 2023

Area of Science:

Agricultural Science
Computer Science
Biotechnology

Background:

Fruits contain valuable secondary metabolites, but their analysis is costly and time-consuming.
Metabolite concentration varies significantly between trees, complicating efficient fruit collection.
Existing analytical methods are not practical for field-based selection of trees.

Purpose of the Study:

To develop deep learning models for predicting secondary metabolite concentration classes (high or low) using only fruit and leaf images.
To assess the feasibility of image-based prediction for simplifying tree selection in the field.
To create a mobile application for real-time decision-making on fruit collection.

Main Methods:

Collected 1045 fruit and leaf images from wild neem trees.
Measured concentrations of five key metabolites (azadirachtin, deacetyl-salannin, salannin, nimbin, nimbolide) using HPLC.
Trained and evaluated seven deep learning models (YOLOv5, GoogLeNet, InceptionNet, EfficientNet_B0, Resnext_50, Resnet18, SqueezeNet) for metabolite class prediction.
Developed a multi-analyte framework and integrated it into an Android mobile app (Fruit-In-Sight).

Main Results:

The best deep learning model achieved a test F1 score of 0.88.
The multi-analyte framework significantly improved prediction accuracy, reaching 100% specificity for both high and low metabolite classes.
The Fruit-In-Sight app provides 'pick' or 'not pick' recommendations based on image analysis.

Conclusions:

Image-based deep learning models can accurately predict secondary metabolite concentration classes in fruits.
This approach eliminates the need for expensive laboratory equipment and complex analytical procedures.
The developed mobile application offers a practical solution for efficient and targeted fruit collection from selected trees.