• Home
  • Search
  • Prediction Model for Tea Polyphenol Content with Deep Features Extracted Using 1D and 2D Convolutional Neural Network
  • Cite Icon26
  • https://doi.org/10.3390/agriculture12091299Copy DOI Icon

Prediction Model for Tea Polyphenol Content with Deep Features Extracted Using 1D and 2D Convolutional Neural Network

Show More
  • Abstract
  • PDF
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

The content of tea polyphenols (TP) is one of the important indicators for judging the quality of tea. Accurate and non-destructive estimation technology for tea polyphenol content has attracted more and more attention, which has become a key technology for tea production, quality identification, grading and so on. Hyperspectral imaging technology is a fusion of spectral analysis and image processing technology, which has been proven to be an efficient technology for predicting tea polyphenol content. To make full use of spectral and spatial features, a prediction model of tea polyphenols based on spectral-spatial deep features extracted using convolutional neural network (CNN) was proposed, which not only broke the limitations of traditional shallow features, but also innovated the technical path of integrated deep learning in non-destructive detection for tea. Firstly, one-dimensional convolutional neural network (1D-CNN) and two-dimensional convolutional neural network (2D-CNN) models were constructed to extract the spectral deep features and spatial deep features of tea hyperspectral images, respectively. Secondly, spectral deep features, spatial deep features, and spectral-spatial deep features are used as input variables of machine learning models, including Partial Least Squares Regression (PLSR), Support Vector Regression (SVR) and Random Forest (RF). Finally, the training, testing and evaluation were realized using the self-built hyperspectral dataset of green tea from different grades and different manufacturers. The results showed that the model based on spectral-spatial deep features had the best prediction performance among the three machine learning models (R2 = 0.949, MAE = 0.533 for training sets, R2 = 0.938, MAE = 0.799 for test sets). Moreover, the visualization of estimation results of tea polyphenol content further demonstrated that the model proposed in this study had strong estimation ability. Therefore, the deep features extracted using CNN can provide new ideas for estimation of the main components of tea, which will provide technical support for the estimation tea quality estimation.

Loading PDF

Similar Papers
  • Conference Article
  • Citations4

Improving Gravitational Wave Detection with 2D Convolutional Neural Networks

  • Jan 10, 2021
  • Siyu Fan +4
  • Video Transcripts

Improving Gravitational Wave Detection with 2D Convolutional Neural Networks

  • Jan 07, 2021
  • Underline Science Inc.
  • Siyu Fan
  • Research Article
  • Citations17

V3O2: hybrid deep learning model for hyperspectral image classification using vanilla-3D and octave-2D convolution

  • Apr 25, 2020
  • Journal of Real-Time Image Processing
  • Alkha Mohan +1
  • PDF
  • Research Article
  • Citations17

Traffic State Prediction Using One-Dimensional Convolution Neural Networks and Long Short-Term Memory

  • May 19, 2022
  • Applied Sciences
  • Selim Reza +3
  • PDF
  • Research Article
  • Citations8

HYPERSPECTRAL IMAGE CLASSIFICATION USING RESIDUAL 2D AND 3D CONVOLUTIONAL NEURAL NETWORK JOINT ATTENTION MODEL

  • Aug 10, 2021
  • The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
  • Q Yuan +2
  • Research Article
  • Citations63

Comparative study of hyperspectral image classification by multidimensional Convolutional Neural Network approaches to improve accuracy

  • May 29, 2021
  • Expert Systems with Applications
  • Gizem Ortac +1
  • PDF
  • Research Article
  • Citations4

Mountain Forest Type Classification Based on One-Dimensional Convolutional Neural Network

  • Sep 06, 2023
  • Forests
  • Maoyang Bai +6
  • PDF
  • Research Article
  • Citations49

A Multi-Scale and Multi-Level Spectral-Spatial Feature Fusion Network for Hyperspectral Image Classification

  • Jan 01, 2020
  • Remote Sensing
  • Caihong Mu +2
  • Conference Article
  • Citations1

Lightweight Multilevel Feature Fusion Network for Hyperspectral Image Classification

  • Nov 26, 2022
  • Quanyu Huang +3
  • PDF
  • Research Article
  • Citations14

Using Convolutional Neural Networks for Blocking Prediction in Elastic Optical Networks

  • Feb 28, 2024
  • Applied Sciences
  • Farzaneh Nourmohammadi +3
  • Research Article
  • Citations22

Hyperspectral imaging combined with dual-channel deep learning feature fusion model for fast and non-destructive recognition of brew wheat varieties

  • Oct 23, 2023
  • Journal of Food Composition and Analysis
  • Lipeng Han +8
  • Research Article

Contents of fluoride and tea polyphenols in brick tea at fluorosis regions in Inner Mongolia

  • May 20, 2014
  • Chin J Endemiol
  • 梁丽娜 +2
  • PDF
  • Research Article
  • Citations39

Estimation of Leaf Nitrogen Content in Wheat Based on Fusion of Spectral Features and Deep Features from Near Infrared Hyperspectral Imagery.

  • Jan 17, 2021
  • Sensors (Basel, Switzerland)
  • Baohua Yang +4
  • Research Article
  • Citations16

Ultrasonic Assessment of Liver Fibrosis Using One-Dimensional Convolutional Neural Networks Based on Frequency Spectra of Radiofrequency Signals with Deep Learning Segmentation of Liver Regions in B-Mode Images: A Feasibility Study

  • Aug 26, 2024
  • Sensors (Basel, Switzerland)
  • Haiming Ai +4
  • Research Article
  • Citations176

Deep learning approaches for automatic detection of sleep apnea events from an electrocardiogram

  • Jul 30, 2019
  • Computer Methods and Programs in Biomedicine
  • Urtnasan Erdenebayar +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.