Optimizing starch content prediction in kudzu: Integrating hyperspectral imaging and deep learning with WGAN-GP

Hu, Huiqiang; Mei, Yunlong; Zhou, Yiming; Zhao, Yuping; Fu, Ling; Xu, Huaxing; Mao, Xiaobo; Huang, Luqi

doi:10.1016/j.foodcont.2024.110762

Food Control

2024

DOI: 10.1016/j.foodcont.2024.110762

|View full text |Cite

Optimizing starch content prediction in kudzu: Integrating hyperspectral imaging and deep learning with WGAN-GP

Huiqiang Hu,

Yunlong Mei,

Yiming Zhou

et al.

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2024

2025

Publication Types

Select...

Article4

Relationship

Self Cite0

Independent4

Authors

Journals

Cited by 4 publications

References 69 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Geographical origin traceability of chrysanthemum using hyperspectral imaging with class information-guided evolutionary multitasking wavelength selection and spatial feature extraction

Wei,

Hu,

Yuan

et al. 2025

Journal of Food Composition and Analysis

View full text Add to dashboard Cite

Geographical origin traceability of chrysanthemum using hyperspectral imaging with class information-guided evolutionary multitasking wavelength selection and spatial feature extraction

Wei,

Hu,

Yuan

et al. 2025

Journal of Food Composition and Analysis

View full text Add to dashboard Cite

Exploring deep learning frameworks for multi-track music synthesis

Liu

2024

Applied Mathematics and Nonlinear Sciences

View full text Add to dashboard Cite

It has been found that the existing methods for generating multi-track music fail to meet the market requirements in terms of melody, rhythm and harmony, and most of the generated music does not conform to the basic music theory knowledge. This paper proposes a multi-track music synthesis model that uses the improved WGAN-GP and is guided by music theory rules to generate music works with high musicality to solve the problems mentioned above. Through the improvement of the adversarial loss function and the introduction of the self-attention mechanism, the improved WGANGP is obtained, which is applied to multi-track music synthesis, and both subjective and objective aspects evaluate the performance of the model. The score of multi-track music synthesized by this paper’s model is 8.22, higher than that of real human works, which is 8.04, and the average scores of the four indexes of rhythm, melody, emotion, and harmony are 8.15, 8.27, 7.61, and 8.22, respectively, which are higher than that of the three models of MuseGAN, MTMG, and HRNN, except for the emotion index. The data processing accuracy and error rate of this paper’s model, as well as the training loss value and track matching, are 94.47%, 0.15%, 0.91, and 0.84, respectively, which are better than WGANGP and MuseGAN. The gap between synthesized multi-track music and the music theory rules of real music using the model in this paper is very small, which can fully meet practical needs. The deep learning model constructed in this paper provides a new path for the generation of multi-track music.

show abstract

Hyperspectral Imaging Aiding Artificial Intelligence: A Reliable Approach for Food Qualification and Safety

Nikzadfar,

Rashvand,

Zhang

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

Hyperspectral imaging (HSI) is one of the non-destructive quality assessment methods providing both spatial and spectral information. HSI in food quality and safety can detect the presence of contaminants, adulterants, and quality attributes, such as moisture, ripeness, and microbial spoilage, in a non-destructive manner by analyzing spectral signatures of food components in a wide range of wavelengths with speed and accuracy. However, analyzing HSI data can be quite complicated and time consuming, in addition to needing some special expertise. Artificial intelligence (AI) has shown immense promise in HSI for the assessment of food quality because it is so powerful at coping with irrelevant information, extracting key features, and building calibration models. This review has shown various machine learning (ML) approaches applied to HSI for quality and safety control of foods. It covers the basic concepts of HSI, advanced preprocessing methods, and strategies for wavelength selection and machine learning methods. The application of HSI to AI increases the speed with which food safety and quality can be inspected. This happens through automation in contaminant detection, classification, and prediction of food quality attributes. So, it can enable decisions in real-time by reducing human error at food inspection. This paper outlines their benefits, challenges, and potential improvements while again assessing the validity and practical usability of HSI technologies in developing reliable calibration models for food quality and safety monitoring. The review concludes that HSI integrated with state-of-the-art AI techniques has good potential to significantly improve the assessment of food quality and safety, and that various ML algorithms have their strengths, and contexts in which they are best applied.

show abstract

scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.

Contact Info

customersupport@researchsolutions.com

10624 S. Eastern Ave., Ste. A-614

Henderson, NV 89052, USA

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

Blog Terms and Conditions API Terms Privacy Policy Contact Cookie Preferences Do Not Sell or Share My Personal Information

Made with 💙 for researchers

Part of the Research Solutions Family.

Optimizing starch content prediction in kudzu: Integrating hyperspectral imaging and deep learning with WGAN-GP

Cited by 4 publications

References 69 publications

Geographical origin traceability of chrysanthemum using hyperspectral imaging with class information-guided evolutionary multitasking wavelength selection and spatial feature extraction

Geographical origin traceability of chrysanthemum using hyperspectral imaging with class information-guided evolutionary multitasking wavelength selection and spatial feature extraction

Exploring deep learning frameworks for multi-track music synthesis

Hyperspectral Imaging Aiding Artificial Intelligence: A Reliable Approach for Food Qualification and Safety

Contact Info

Product

Resources

About