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

Multiple Regression

Multiple Regression

Multiple regression assesses a linear relationship between one response or dependent variable and two or more independent variables. It has many practical applications.
Farmers can use multiple regression to determine the crop yield based on more than one factor, such as water availability, fertilizer, soil properties, etc. Here, the crop yield is the response or dependent variable as it depends on the other independent variables. The analysis requires the construction of a scatter plot...

You might also read

Related Articles

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

Sort by

Same author

Discontinuous 3D Printing of Amorphous Photonic Crystal Hydrogels for Multifunctional Applications.

Small (Weinheim an der Bergstrasse, Germany)·2026

Same author

Fast Iodine Conversion Kinetics Enabled by Highly Electrocatalytic Molybdenum Carbide Nanocrystal-Embedded Ordered Carbon Nanocages.

Nano letters·2026

Same author

Intercalation of bismuth nanoparticles into Ti<sub>3</sub>C<sub>2</sub> MXene as an anode material for lithium-ion batteries.

Nanoscale·2025

Same author

Stabilizing zinc metal anodes with MXene-derived electrospun titanium dioxide/carbon nanofiber protective layers.

Journal of colloid and interface science·2025

Same author

Ionic Diodes: Pioneering the Future of Ionotronics in Electronics and Beyond.

ACS applied materials & interfaces·2025

Same author

Nucleation and Growth Mechanisms of Micro/Nano Structural Manganese-Trimesic Acid Coordinations for Aqueous Zinc-Ion Batteries.

Angewandte Chemie (International ed. in English)·2025

Search research articles

Related Experiment Video

Updated: Jun 26, 2025

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Published on: August 16, 2024

A deep learning-based quantitative prediction model for the processing potentials of soybeans as soymilk raw

Guoyin Zhu¹, Xin Huang¹, Xingyun Peng¹

¹Beijing Key Laboratory of Plant Protein and Cereal Processing, College of Food Science and Nutritional Engineering, China Agricultural University, Beijing 100083, China.

|May 18, 2024

Summary

A new deep-learning model accurately predicts soymilk quality and profit using soybean physicochemical properties. This approach overcomes limitations of traditional methods, enabling a more efficient and profitable soymilk industry.

Keywords:

Deep-learning model Processing potential Quantitative prediction Soybean Soymilk

More Related Videos

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

Imaging and Analysis for Quantifying Maize (Zea mays) Abiotic Stress Phenotypes

Imaging and Analysis for Quantifying Maize (Zea mays) Abiotic Stress Phenotypes

Published on: March 28, 2025

Related Experiment Videos

Last Updated: Jun 26, 2025

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Published on: August 16, 2024

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

Imaging and Analysis for Quantifying Maize (Zea mays) Abiotic Stress Phenotypes

Imaging and Analysis for Quantifying Maize (Zea mays) Abiotic Stress Phenotypes

Published on: March 28, 2025

Area of Science:

Agricultural Science
Food Science and Technology
Data Science and Machine Learning

Background:

Traditional methods for evaluating soybean potential (correlation, regression, classification) offer limited, vague assessments and fail quantitative prediction.
These limitations hinder efficiency and profitability within the soymilk industry.
A need exists for advanced analytical tools to precisely evaluate soybean physicochemical nature (PN) and soymilk profit and quality attributes (PQA).

Purpose of the Study:

To develop a deep-learning based model for quantitative prediction of soymilk PQA using PN data.
To overcome the limitations of existing analytical technologies in soybean potential evaluation.
To enhance the efficiency and profitability of the soymilk industry through improved predictive capabilities.

Main Methods:

Collected data from 54 soybean cultivars and their soymilks, including chemical, textural, and sensory analyses.
Established datasets for soybean physicochemical nature (PN) and soymilk profit and quality attributes (PQA).
Developed and trained a deep-learning model using stochastic gradient descent optimization over 45 rounds, with validation on 9 PN/PQA data pairs.

Main Results:

The deep-learning model demonstrated significant improvements in prediction performance with iterative training.
The trained model achieved satisfying predictions (|relative error| ≤ 20%, standard deviation of relative error ≤ 40%) for 78% of key soymilk PQAs.
The model provides a quantitative and accurate method for predicting soymilk quality and profit.

Conclusions:

The developed deep-learning model effectively predicts soymilk PQAs from PN data, surpassing traditional methods.
This quantitative approach offers substantial improvements for the soymilk industry, enhancing profitability and efficiency.
Future research incorporating big data could further refine predictions, particularly for soymilk odor qualities.