Related Experiment Video
Updated: Jul 28, 2026
14:04
Biosensor for Detection of Antibiotic Resistant Staphylococcus Bacteria
Published on: May 8, 2013
25.1K
AI-Powered Embedded System for Rapid Detection of Veterinary Antibiotic Residues in Food-Producing Animals
Ximing Li1, Lanqi Chen1, Qianchao Wang1
1College of Mathematics and Informatics, South China Agricultural University, Guangzhou 510642, China.
Antibiotics (Basel, Switzerland)
|September 27, 2025
Summary
An AI system automates veterinary antibiotic residue detection using colloidal gold test cards, enhancing food safety. This rapid, cost-effective screening supports regulatory compliance and public health.
Area of Science:
- Artificial Intelligence in Food Safety
- Veterinary Drug Residue Detection
- Embedded Systems for Diagnostics
Background:
- Widespread veterinary antibiotic use in food animals raises concerns about drug residues and antimicrobial resistance.
- Colloidal gold immunoassay (CGIA) test cards are used for rapid screening but manual interpretation is inconsistent.
- Need for automated, efficient systems for veterinary antibiotic residue detection to ensure food safety and regulatory compliance.
Purpose of the Study:
- To develop a complete AI-based detection system for automated interpretation of CGIA test cards for veterinary antibiotic residues.
- To create a lightweight, high-performance AI model (VetStar) suitable for resource-constrained embedded devices.
- To enable high-throughput, automated reporting for regulatory documentation and quality control in food safety.
Main Methods:
- Developed an AI system on the Rockchip RK3568 platform with an OV5640 camera and LED illumination.
- Proposed VetStar, a lightweight detection algorithm featuring StarBlock and a Depthwise Separable-Reparameterization Detection Head (DR-head).
- Employed Bridging Cross-task Protocol Inconsistency Knowledge Distillation (BCKD) for model optimization and performance enhancement.
Main Results:
- The VetStar model, with 0.04 M parameters and 0.3 GFLOPs, achieved high accuracy (mAP50: 97.4, mAP50-95: 89.5) on the VDR-RTC dataset.
- The integrated system demonstrated rapid inference, delivering results in 5.4 seconds on the RK3568 device.
- VetStar significantly outperformed comparable models in terms of speed while maintaining accuracy.
Conclusions:
- The AI-based system offers a high-throughput, cost-effective solution for rapid veterinary antibiotic residue screening.
- VetStar provides an accurate and efficient algorithm for automated interpretation of CGIA test cards on embedded systems.
- The system has strong potential to enhance food safety surveillance and regulatory compliance.
Keywords:
embedded systemfood safetyhigh-throughputlightweight modelobject detectionveterinary antibiotic residueMore Related Videos
Related Concept Videos
01:24iChip
The cultivation of environmental microorganisms has long been hindered by the inability to replicate complex native conditions in vitro. The isolation chip (iChip) addresses this limitation by facilitating the growth of previously uncultivable microorganisms through in situ incubation. Designed for high-throughput microbial cultivation, the iChip comprises hundreds of microchambers, each capable of housing a single microbial cell. These microchambers are loaded with a mixture of molten agar and...
01:17Microbial Biosensors
Microbial biosensors are analytical devices that utilize living microbes to detect specific substances through measurable signals. These devices consist of two main components: biosensing organisms and signal-transducing elements. Biosensing organisms, such as Escherichia coli or Saccharomyces cerevisiae, are typically housed in multiwell plates connected to transducers, enabling rapid, real-time detection of target analytes.Signal Generation MechanismWhen a target analyte—such as...
01:25Rapid Identification of Pathogens
MALDI-TOF MS has transformed clinical microbiology by offering a rapid and reliable method for pathogen identification. The traditional approach to microbial identification typically involves time-consuming culture techniques and biochemical tests, which can delay the initiation of appropriate antimicrobial therapy. MALDI-TOF MS avoids these delays by using characteristic ribosomal protein mass patterns of microbial cells, enabling accurate species-level identification within minutes.Principle...
01:24Automated Microbial Diagnostics
Automated diagnostic analyzers have transformed clinical microbiology by providing rapid and reliable methods for pathogen identification and antibiotic susceptibility testing. Among these systems, the Vitek 2 is widely used because it automates the traditionally labor-intensive processes of microbial identification (ID) and antibiotic susceptibility testing (AST), delivering standardized and timely results that are essential for effective patient care.Microbial Identification with ID CardsThe...