Sweetener identification using transfer learning and attention mechanism

Accurate identification of the taste of compounds has helped in the screening and development of new sweeteners. This study proposes a deep learning model for sweetener identification based on transfer learning and attention mechanism. The Squeeze-and-Excitation (SE) attention mechanism is incorpora...

Full description

Saved in:
Bibliographic Details
Main Authors: Fanchao Lin, Yuan Ji, Shoujiang Xu
Format: Article
Language:English
Published: Taylor & Francis Group 2024-12-01
Series:CyTA - Journal of Food
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/19476337.2024.2341812
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850052994730557440
author Fanchao Lin
Yuan Ji
Shoujiang Xu
author_facet Fanchao Lin
Yuan Ji
Shoujiang Xu
author_sort Fanchao Lin
collection DOAJ
description Accurate identification of the taste of compounds has helped in the screening and development of new sweeteners. This study proposes a deep learning model for sweetener identification based on transfer learning and attention mechanism. The Squeeze-and-Excitation (SE) attention mechanism is incorporated into the pre-trained Residual Network-50 (ResNet-50) model, resulting in SE-ResNet-50. Additionally, the Convolutional Block Attention Module (CBAM) is integrated to generate the CBAM-SEResNet-50 model for sweetener identification. This study divided the taste molecule dataset into two parts: Cross-Validation (CV) dataset and Hold-out test dataset. The effectiveness of the algorithm was verified using both the 5-fold CV and the Hold-out test methods. The experimental results demonstrate that the CBAM-SEResNet-50 model achieves an accuracy of 0.956 and an Area Under the Receiver Operating Characteristic Curve (AUROC) of 0.972 on the Hold-out test dataset. In the case of the 5-fold CV, the accuracy is 0.944 and the AUROC is 0.969.
format Article
id doaj-art-b8e5fa0bd721413fb66829596c2096a4
institution DOAJ
issn 1947-6337
1947-6345
language English
publishDate 2024-12-01
publisher Taylor & Francis Group
record_format Article
series CyTA - Journal of Food
spelling doaj-art-b8e5fa0bd721413fb66829596c2096a42025-08-20T02:52:41ZengTaylor & Francis GroupCyTA - Journal of Food1947-63371947-63452024-12-0122110.1080/19476337.2024.2341812Sweetener identification using transfer learning and attention mechanismFanchao Lin0Yuan Ji1Shoujiang Xu2School of Artificial Intelligence, Jiangsu Food and Pharmaceutical Science College, Huaian, ChinaSchool of Artificial Intelligence, Jiangsu Food and Pharmaceutical Science College, Huaian, ChinaSchool of Artificial Intelligence, Jiangsu Food and Pharmaceutical Science College, Huaian, ChinaAccurate identification of the taste of compounds has helped in the screening and development of new sweeteners. This study proposes a deep learning model for sweetener identification based on transfer learning and attention mechanism. The Squeeze-and-Excitation (SE) attention mechanism is incorporated into the pre-trained Residual Network-50 (ResNet-50) model, resulting in SE-ResNet-50. Additionally, the Convolutional Block Attention Module (CBAM) is integrated to generate the CBAM-SEResNet-50 model for sweetener identification. This study divided the taste molecule dataset into two parts: Cross-Validation (CV) dataset and Hold-out test dataset. The effectiveness of the algorithm was verified using both the 5-fold CV and the Hold-out test methods. The experimental results demonstrate that the CBAM-SEResNet-50 model achieves an accuracy of 0.956 and an Area Under the Receiver Operating Characteristic Curve (AUROC) of 0.972 on the Hold-out test dataset. In the case of the 5-fold CV, the accuracy is 0.944 and the AUROC is 0.969.https://www.tandfonline.com/doi/10.1080/19476337.2024.2341812Sweetener identificationtransfer learningattention mechanism
spellingShingle Fanchao Lin
Yuan Ji
Shoujiang Xu
Sweetener identification using transfer learning and attention mechanism
CyTA - Journal of Food
Sweetener identification
transfer learning
attention mechanism
title Sweetener identification using transfer learning and attention mechanism
title_full Sweetener identification using transfer learning and attention mechanism
title_fullStr Sweetener identification using transfer learning and attention mechanism
title_full_unstemmed Sweetener identification using transfer learning and attention mechanism
title_short Sweetener identification using transfer learning and attention mechanism
title_sort sweetener identification using transfer learning and attention mechanism
topic Sweetener identification
transfer learning
attention mechanism
url https://www.tandfonline.com/doi/10.1080/19476337.2024.2341812
work_keys_str_mv AT fanchaolin sweeteneridentificationusingtransferlearningandattentionmechanism
AT yuanji sweeteneridentificationusingtransferlearningandattentionmechanism
AT shoujiangxu sweeteneridentificationusingtransferlearningandattentionmechanism