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

You might also read

Related Articles

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

Sort by

Same author

Dynamic Charge Redistribution as the Key Mechanism for NO<sub>2</sub> Detection in MoS<sub>2</sub> Revealed by <i>In Operando</i> Scanning Photoelectron Microscopy.

ACS applied materials & interfaces·2026

Same author

Chemical, colour, and sensory evolution of Schiava wines: Impact of grape freezing and co-inoculum of yeast and malolactic Bacteria.

Food chemistry·2026

Same author

Exploring hemodynamic measurements from the Tromsø Study for prediction of cardiovascular disease using traditional statistical models and machine learning approaches.

Scientific reports·2026

Same author

Rosy Discolouration in an Alpine Chapel: Beyond Salt Dependence.

Microbial ecology·2026

Same author

Polyacrylamide ZrOH Hydrogels for Spatially Resolved Sampling of Carboxylates Exuded from Roots Growing in Soil.

Journal of visualized experiments : JoVE·2026

Same author

Nanoparticle-rhizosphere crosstalk: Insights into transformation, microbial interaction, plant uptake and translocation.

Chemosphere·2026

Search research articles

Related Experiment Video

Updated: Nov 4, 2025

Construction of Models for Nondestructive Prediction of Ingredient Contents in Blueberries by Near-infrared Spectroscopy Based on HPLC Measurements

Construction of Models for Nondestructive Prediction of Ingredient Contents in Blueberries by Near-infrared Spectroscopy Based on HPLC Measurements

Published on: June 28, 2016

Supervised binary classification methods for strawberry ripeness discrimination from bioimpedance data.

Pietro Ibba¹, Christian Tronstad², Roberto Moscetti³

¹Faculty of Science and Technology, Free University of Bolzano-Bozen, 39100, Bolzano-Bozen, Italy. pibba@unibz.it.

Scientific Reports

|May 28, 2021

Summary

Researchers developed a new method using bioimpedance data and machine learning to accurately determine strawberry ripeness on-site. Multi-layer perceptron (MLP) networks showed the best performance, offering a promising tool for harvest management.

More Related Videos

Fruit Volatile Analysis Using an Electronic Nose

Fruit Volatile Analysis Using an Electronic Nose

Published on: March 30, 2012

The Terroir Concept Interpreted through Grape Berry Metabolomics and Transcriptomics

The Terroir Concept Interpreted through Grape Berry Metabolomics and Transcriptomics

Published on: October 5, 2016

Related Experiment Videos

Last Updated: Nov 4, 2025

Construction of Models for Nondestructive Prediction of Ingredient Contents in Blueberries by Near-infrared Spectroscopy Based on HPLC Measurements

Construction of Models for Nondestructive Prediction of Ingredient Contents in Blueberries by Near-infrared Spectroscopy Based on HPLC Measurements

Published on: June 28, 2016

Fruit Volatile Analysis Using an Electronic Nose

Fruit Volatile Analysis Using an Electronic Nose

Published on: March 30, 2012

The Terroir Concept Interpreted through Grape Berry Metabolomics and Transcriptomics

The Terroir Concept Interpreted through Grape Berry Metabolomics and Transcriptomics

Published on: October 5, 2016

Area of Science:

Agricultural Science
Electrical Engineering
Computer Science

Background:

Consumer demand for high-quality strawberries necessitates accurate on-site ripeness assessment during harvest.
Traditional methods for determining ripeness can be subjective and time-consuming, impacting quality control.

Purpose of the Study:

To develop and evaluate machine learning models for predicting strawberry ripeness using bioimpedance data.
To establish a feature selection and optimization pipeline for bioimpedance analysis in fruit grading.
To compare the performance of six supervised machine learning techniques for ripeness classification.

Main Methods:

Collected bioimpedance data from 923 strawberries across various ripening stages (20 Hz to 300 kHz).
Classified strawberries into ripe and unripe categories based on surface color.
Trained, optimized, and tested six machine learning models: Logistic Regression, Decision Trees, Naive Bayes, K-Nearest Neighbors, Support Vector Machine, and Multi-Layer Perceptron Networks.

Main Results:

Multi-layer Perceptron (MLP) networks achieved the highest classification performance on the test set.
MLP models demonstrated strong generalization capabilities, accurately predicting ripeness on unseen data.
Achieved F-scores of 0.72, 0.82, and 0.73 for MLP models, indicating robust performance.

Conclusions:

MLP models trained with bioimpedance data offer a promising, non-destructive method for real-time strawberry ripeness estimation.
This technology can significantly aid farmers and producers in optimizing harvest time management.
The developed feature selection and optimization pipeline advances bioimpedance data analysis for agricultural applications.