Food Computing: AI-Powered Innovations and Applications in the Food Industry

A special issue of Foods (ISSN 2304-8158). This special issue belongs to the section "Food Engineering and Technology".

Deadline for manuscript submissions: 31 October 2025 | Viewed by 7578

Special Issue Editors


E-Mail Website
Guest Editor
School of Cyber Science & Engineering, Wuhan University, Wuhan, China
Interests: big data; food safety; deep learning; blockchain
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor Assistant
Science Center for Future Foods, Jiangnan University, Wuxi, China
Interests: artificial intelligence; food engineering; image processing; milk powder

Special Issue Information

Dear Colleagues,

The integration of Artificial Intelligence (AI) into the food industry is transforming how we approach food production, safety, nutrition, and sustainability. This Special Issue delves into the growing field of food computing, where AI-driven technologies—such as machine learning, computer vision, and big data analytics—are applied to tackle critical challenges in the food sector. From optimizing supply chains and reducing food waste to enhancing food quality and enabling personalized nutrition plans, AI has the potential to revolutionize every aspect of the food ecosystem. This Special Issue welcomes the latest interdisciplinary research and application advancements at the intersection of food science and AI technology, fostering innovative solutions.

Prof. Dr. Xiaohui Cui
Guest Editor

Dr. Haohan Ding
Guest Editor Assistant

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Foods is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2900 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • food computing
  • food industry
  • machine learning
  • computer vision
  • big data analytics
  • deep learning
  • food safety
  • food quality
  • nutrition
  • sustainable food

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.

Further information on MDPI's Special Issue policies can be found here.

Published Papers (5 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

Jump to: Review

23 pages, 6947 KiB  
Article
Lightweight DeepLabv3+ for Semantic Food Segmentation
by Bastián Muñoz, Angela Martínez-Arroyo, Constanza Acevedo and Eduardo Aguilar
Foods 2025, 14(8), 1306; https://doi.org/10.3390/foods14081306 - 9 Apr 2025
Viewed by 689
Abstract
Advancements in artificial intelligence, particularly in computer vision, have driven the research and development of visual food analysis systems focused primarily on enhancing people’s well-being. Food analysis can be performed at various levels of granularity, with food segmentation being a major component of [...] Read more.
Advancements in artificial intelligence, particularly in computer vision, have driven the research and development of visual food analysis systems focused primarily on enhancing people’s well-being. Food analysis can be performed at various levels of granularity, with food segmentation being a major component of numerous real-world applications. Deep learning-based methodologies have demonstrated promising results in food segmentation; however, many of these approaches demand high computational resources, making them impractical for low-performance devices. In this research, a novel, lightweight, deep learning-based method for semantic food segmentation is proposed. To achieve this, the state-of-the-art DeepLabv3+ model was adapted by optimizing the backbone with the lightweight network EfficientNet-B1, replacing the Atrous Spatial Pyramid Pooling (ASPP) in the neck with Cascade Waterfall ASPP (CWASPP), and refining the encoder output using the squeeze-and-excitation attention mechanism. To validate the method, four publicly available food datasets were selected. Additionally, a new food segmentation dataset consisting of self-acquired food images was introduced and included in the validation. The results demonstrate that high performance can be achieved at a significantly lower cost. The proposed method yields results that are either better than or comparable to those of state-of-the-art techniques while requiring significantly lower computational costs. In conclusion, this research demonstrates the potential of deep learning to perform food image segmentation on low-performance stand-alone devices, paving the way for more efficient, cost-effective, and scalable food analysis applications. Full article
Show Figures

Figure 1

25 pages, 8231 KiB  
Article
Quality Changes in Live Ruditapes philippinarum During “Last Mile” Cold Chain Breakage: Effect of Packaging
by Yiming Huang, Xinrui Xie, Shoaib Younas, Caiyun Liu and Xin Wang
Foods 2025, 14(6), 1011; https://doi.org/10.3390/foods14061011 - 17 Mar 2025
Cited by 1 | Viewed by 520
Abstract
The reliability of the “last mile” of cold-chain logistics is crucial for food safety. This study investigated the effect of different packaging treatments on the quality of anhydrously preserved live Ruditapes philippinarum (R. philippinarum) in “last mile” cold chain disruption. The temperature [...] Read more.
The reliability of the “last mile” of cold-chain logistics is crucial for food safety. This study investigated the effect of different packaging treatments on the quality of anhydrously preserved live Ruditapes philippinarum (R. philippinarum) in “last mile” cold chain disruption. The temperature profiles of three packaging treatments at ambient temperature (25 °C) were monitored. Quality assessment was conducted based on sensory scoring, survival rate, total viable count (TVC), water-holding capacity (WHC), pH, total volatile basic nitrogen (TVB-N), thiobarbituric acid-reactive substances (TBA), color, and texture. Low-frequency nuclear magnetic resonance (LF-NMR) and magnetic resonance imaging (MRI) were utilized to characterize the water state profile. The findings demonstrated a progressive increase in internal package temperature throughout the “last mile”, with packages containing additional ice packs more effectively maintaining lower temperature and restricting the migration of “hot spots” towards the center. Specifically, the package with three ice packs maintained a markedly lower temperature, which effectively inhibited microbial activity, lipid oxidation, and the production of alkaline substances, resulting in higher survival rates, water-holding capacity, texture, sensory acceptability, and immobilized water fraction. Furthermore, LF-NMR relaxation parameters showed strong correlations with various physicochemical indices, suggesting a potential approach for real-time quality monitoring. This study provides insights for maintaining live R. philippinarum quality during the “last mile”. Full article
Show Figures

Figure 1

14 pages, 4848 KiB  
Article
The Electrochemical Detection of Bisphenol A and Catechol in Red Wine
by Chao Wang, Xiangchuan Wu, Xinhe Lin, Xueting Zhu, Wei Ma and Jian Chen
Foods 2025, 14(1), 133; https://doi.org/10.3390/foods14010133 - 6 Jan 2025
Viewed by 1258
Abstract
The use of nanozymes for electrochemical detection in the food industry is an intriguing area of research. In this study, we synthesized a laccase mimicking the MnO2@CeO2 nanozyme using a simple hydrothermal method, which was characterized by modern analytical methods, [...] Read more.
The use of nanozymes for electrochemical detection in the food industry is an intriguing area of research. In this study, we synthesized a laccase mimicking the MnO2@CeO2 nanozyme using a simple hydrothermal method, which was characterized by modern analytical methods, such as transmission electron microscope (TEM), X-ray diffraction (XRD), and energy dispersive X-ray spectroscopy (EDX), etc. We found that the addition of MnO2 significantly increased the laccase-like activity by 300% compared to CeO2 nanorods. Due to the excellent laccase-like activity of the MnO2@CeO2 nanozyme, we developed an electrochemical sensor for the detection of hazardous phenolic compounds such as bisphenol A and catechol in red wines by cyclic voltammetry (CV) and differential pulse voltammetry (DPV). We used the MnO2@CeO2 nanozyme to develop an electrochemical sensor for detecting harmful phenolic compounds like bisphenol A and catechol in red wine due to its excellent laccase-like activity. The MnO2@CeO2 nanorods could be dispersion-modified glassy carbon electrodes (GCEs) by polyethyleneimine (PEI) to achieve a rapid detection of bisphenol A and catechol, with limits of detection as low as 1.2 × 10−8 M and 7.3 × 10−8 M, respectively. This approach provides a new way to accurately determine phenolic compounds with high sensitivity, low cost, and stability. Full article
Show Figures

Figure 1

Review

Jump to: Research

18 pages, 2236 KiB  
Review
IoT-Enabled Biosensors in Food Packaging: A Breakthrough in Food Safety for Monitoring Risks in Real Time
by Abdus Sobhan, Abul Hossain, Lin Wei, Kasiviswanathan Muthukumarappan and Maruf Ahmed
Foods 2025, 14(8), 1403; https://doi.org/10.3390/foods14081403 - 18 Apr 2025
Viewed by 1114
Abstract
The integration of biosensors and the Internet of Things (IoT) in food packaging is gaining significant interest in rapidly enhancing food safety and traceability worldwide. Currently, the IoT is one of the most intriguing topics in the digital and virtual world. Biosensors can [...] Read more.
The integration of biosensors and the Internet of Things (IoT) in food packaging is gaining significant interest in rapidly enhancing food safety and traceability worldwide. Currently, the IoT is one of the most intriguing topics in the digital and virtual world. Biosensors can be integrated into food packaging to monitor, sense, and identify early signs of food spoilage or freshness. When coupled with the IoT, these biosensors can contribute to data transmission via IoT networks, providing real-time insights into food storage and transportation conditions for stakeholders across each stage of the food supply chain, facilitating proactive decision-making practices. The technologies of combining biosensors with IoT could leverage artificial intelligence (AI) to enhance food safety, quality, and security in food industries, compared to conventional existing food inspection technologies, which are limited to assessing weight, volume, color, and physical appearance. This review focused on highlighting the latest and existing advancements, identifying the knowledge gaps in the applications of biosensors and the IoT, and exploring their opportunities to shape future food packaging, particularly in the context of 21st-century food safety. The review also aims to investigate the role of the IoT in creating smart food ecosystems and examines how data transmitted from biosensors to IoT systems can be stored in cloud-based platforms, in addition to addressing upcoming research challenges. Concerns of data privacy, security, and regulatory compliance in implementing the IoT and biosensors for food packaging are also addressed, along with potential solutions to overcome these barriers. Full article
Show Figures

Figure 1

37 pages, 2498 KiB  
Review
Application of Convolutional Neural Networks and Recurrent Neural Networks in Food Safety
by Haohan Ding, Haoke Hou, Long Wang, Xiaohui Cui, Wei Yu and David I. Wilson
Foods 2025, 14(2), 247; https://doi.org/10.3390/foods14020247 - 14 Jan 2025
Cited by 1 | Viewed by 3336
Abstract
This review explores the application of convolutional neural networks (CNNs) and recurrent neural networks (RNNs) in food safety detection and risk prediction. This paper highlights the advantages of CNNs in image processing and feature recognition, as well as the powerful capabilities of RNNs [...] Read more.
This review explores the application of convolutional neural networks (CNNs) and recurrent neural networks (RNNs) in food safety detection and risk prediction. This paper highlights the advantages of CNNs in image processing and feature recognition, as well as the powerful capabilities of RNNs (especially their variant LSTM) in time series data modeling. This paper also makes a comparative analysis in many aspects: Firstly, the advantages and disadvantages of traditional food safety detection and risk prediction methods are compared with deep learning technologies such as CNNs and RNNs. Secondly, the similarities and differences between CNNs and fully connected neural networks in processing image data are analyzed. Furthermore, the advantages and disadvantages of RNNs and traditional statistical modeling methods in processing time series data are discussed. Finally, the application directions of CNNs in food safety detection and RNNs in food safety risk prediction are compared. This paper also discusses combining these deep learning models with technologies such as the Internet of Things (IoT), blockchain, and federated learning to improve the accuracy and efficiency of food safety detection and risk warning. Finally, this paper mentions the limitations of RNNs and CNNs in the field of food safety, as well as the challenges in the interpretability of the model, and suggests the use of interpretable artificial intelligence (XAI) technology to improve the transparency of the model. Full article
Show Figures

Figure 1

Back to TopTop