Blueberry Remaining Shelf-Life Prediction Based on the PSO-CNN-BiLSTM-MHA Model

Remaining shelf-life prediction of blueberries is crucial in reducing economic losses and enhancing market competitiveness. To meet the demand for high accuracy in predicting the remaining shelf-life of blueberries, this paper proposes a fusion model (PSO-CNN-BiLSTM-MHA) that combines Particle Swarm...

Full description

Saved in:
Bibliographic Details
Main Authors: Mengya Liu, Xu Cheng, Yu Cao, Qian Zhou
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10915596/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850038198421422080
author Mengya Liu
Xu Cheng
Yu Cao
Qian Zhou
author_facet Mengya Liu
Xu Cheng
Yu Cao
Qian Zhou
author_sort Mengya Liu
collection DOAJ
description Remaining shelf-life prediction of blueberries is crucial in reducing economic losses and enhancing market competitiveness. To meet the demand for high accuracy in predicting the remaining shelf-life of blueberries, this paper proposes a fusion model (PSO-CNN-BiLSTM-MHA) that combines Particle Swarm Optimization (PSO), Convolutional Neural Network (CNN), Bidirectional Long Short-Term Memory network (BiLSTM), and Multi-Head Attention (MHA) mechanisms for predicting the remaining shelf-life of &#x2018;Emerald&#x2019; blueberries under two temperature conditions, <inline-formula> <tex-math notation="LaTeX">$4^{\circ } \text {C}$ </tex-math></inline-formula> and <inline-formula> <tex-math notation="LaTeX">$25^{\circ } \text {C}$ </tex-math></inline-formula>. In this study, seven key features were selected from fifteen quality indicators of blueberries using the embedded method, and the PSO algorithm was used to determine the optimal hyperparameter combination of the model, which effectively improved its prediction performance. The experimental results show that our model outperforms other models in all evaluation metrics under both temperature conditions and demonstrates excellent prediction ability and stability. This study provides an effective technical approach for the accurate prediction of the remaining shelf-life of blueberries and other fruits.
format Article
id doaj-art-15c150e1136646a3bc624f51f987d478
institution DOAJ
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-15c150e1136646a3bc624f51f987d4782025-08-20T02:56:39ZengIEEEIEEE Access2169-35362025-01-0113432384324810.1109/ACCESS.2025.354872010915596Blueberry Remaining Shelf-Life Prediction Based on the PSO-CNN-BiLSTM-MHA ModelMengya Liu0https://orcid.org/0009-0008-7268-5834Xu Cheng1https://orcid.org/0000-0002-9559-7721Yu Cao2https://orcid.org/0009-0006-7562-5680Qian Zhou3School of Information Science and Control Engineering, Liaoning Petrochemical University, Fushun, ChinaCollege of Economics and Management, Shenyang Agricultural University, Shenyang, ChinaSchool of Information Science and Control Engineering, Liaoning Petrochemical University, Fushun, ChinaFood Science College, Shenyang Agricultural University, Shenyang, ChinaRemaining shelf-life prediction of blueberries is crucial in reducing economic losses and enhancing market competitiveness. To meet the demand for high accuracy in predicting the remaining shelf-life of blueberries, this paper proposes a fusion model (PSO-CNN-BiLSTM-MHA) that combines Particle Swarm Optimization (PSO), Convolutional Neural Network (CNN), Bidirectional Long Short-Term Memory network (BiLSTM), and Multi-Head Attention (MHA) mechanisms for predicting the remaining shelf-life of &#x2018;Emerald&#x2019; blueberries under two temperature conditions, <inline-formula> <tex-math notation="LaTeX">$4^{\circ } \text {C}$ </tex-math></inline-formula> and <inline-formula> <tex-math notation="LaTeX">$25^{\circ } \text {C}$ </tex-math></inline-formula>. In this study, seven key features were selected from fifteen quality indicators of blueberries using the embedded method, and the PSO algorithm was used to determine the optimal hyperparameter combination of the model, which effectively improved its prediction performance. The experimental results show that our model outperforms other models in all evaluation metrics under both temperature conditions and demonstrates excellent prediction ability and stability. This study provides an effective technical approach for the accurate prediction of the remaining shelf-life of blueberries and other fruits.https://ieeexplore.ieee.org/document/10915596/Bidirectional long short-term memory networkconvolutional neural networkmulti-head attention mechanismsparticle swarm optimizationremaining shelf-life prediction
spellingShingle Mengya Liu
Xu Cheng
Yu Cao
Qian Zhou
Blueberry Remaining Shelf-Life Prediction Based on the PSO-CNN-BiLSTM-MHA Model
IEEE Access
Bidirectional long short-term memory network
convolutional neural network
multi-head attention mechanisms
particle swarm optimization
remaining shelf-life prediction
title Blueberry Remaining Shelf-Life Prediction Based on the PSO-CNN-BiLSTM-MHA Model
title_full Blueberry Remaining Shelf-Life Prediction Based on the PSO-CNN-BiLSTM-MHA Model
title_fullStr Blueberry Remaining Shelf-Life Prediction Based on the PSO-CNN-BiLSTM-MHA Model
title_full_unstemmed Blueberry Remaining Shelf-Life Prediction Based on the PSO-CNN-BiLSTM-MHA Model
title_short Blueberry Remaining Shelf-Life Prediction Based on the PSO-CNN-BiLSTM-MHA Model
title_sort blueberry remaining shelf life prediction based on the pso cnn bilstm mha model
topic Bidirectional long short-term memory network
convolutional neural network
multi-head attention mechanisms
particle swarm optimization
remaining shelf-life prediction
url https://ieeexplore.ieee.org/document/10915596/
work_keys_str_mv AT mengyaliu blueberryremainingshelflifepredictionbasedonthepsocnnbilstmmhamodel
AT xucheng blueberryremainingshelflifepredictionbasedonthepsocnnbilstmmhamodel
AT yucao blueberryremainingshelflifepredictionbasedonthepsocnnbilstmmhamodel
AT qianzhou blueberryremainingshelflifepredictionbasedonthepsocnnbilstmmhamodel