# Design and predictive modeling of a veterinary drug detection sensor in paddy field water based on artificial neural networks

**Authors:** Junshi Huang, Bolin Huang, Shuanggen Huang, Xiaobin Wang, Jinhui Zhao

PMC · DOI: 10.1038/s41598-026-38752-9 · 2026-02-13

## TL;DR

A new sensor system using artificial neural networks detects veterinary drugs in paddy field water quickly and in real time.

## Contribution

A novel sensor system with a multi-input multi-output model for rapid detection of multiple veterinary drugs in paddy field water.

## Key findings

- The sensor system effectively detects sulfamethazine, doxycycline hydrochloride, ofloxacin, and tetracycline hydrochloride in paddy field water.
- Using phase difference data as input improved model performance with R2 values between 0.7831 and 0.8713.
- The system enables real-time monitoring of veterinary drug residues across a broad frequency range.

## Abstract

For rapid real-time detection of veterinary drug residues in paddy field water, we developed a novel sensor system using interdigitated electrodes as detection probes and the STM32F405RGT6 microcontroller as the core processing unit. The hardware architecture integrates multiple functional modules including excitation signal generation, signal detection, signal processing, LoRa coupled with 4G wireless communication, voltage regulation, and lithium battery charging. The system acquires three types of measurement data (amplitude ratio, phase difference, and their combination) from water samples containing sulfamethazine, ofloxacin, doxycycline hydrochloride and tetracycline hydrochloride across a broad frequency spectrum from 200 Hz to 100 MHz. Through Competitive Adaptive Reweighted Sampling (CARS) for feature selection and artificial neural network modeling, we established a multi-input multi-output concentration prediction model. Comparative analysis demonstrated superior performance when using phase difference data as model input, achieving prediction coefficients of determination (R2) between 0.7831 and 0.8713 with root mean square errors of prediction (RMSEP) ranging from 22.0759 to 28.1526 mg/L. Studies showed that this sensor device could effectively detect the contents of four veterinary drugs, namely sulfamethazine, doxycycline hydrochloride, ofloxacin, and tetracycline hydrochloride, in paddy field water, thus realizing the rapid and real-time monitoring of veterinary drugs in paddy field water.

## Linked entities

- **Chemicals:** sulfamethazine (PubChem CID 5327), ofloxacin (PubChem CID 4583), doxycycline hydrochloride (PubChem CID 54681535), tetracycline hydrochloride (PubChem CID 54704426)

## Full-text entities

- **Chemicals:** lithium (MESH:D008094), tetracycline hydrochloride (MESH:D013752), sulfamethazine (MESH:D013418), doxycycline hydrochloride (-), water (MESH:D014867), ofloxacin (MESH:D015242)

## Figures

11 figures with captions in the complete paper: https://tomesphere.com/paper/PMC12982488/full.md

---
Source: https://tomesphere.com/paper/PMC12982488