Introduction: How IoT Became an Early Warning Weapon Against African Swine Fever
For animal disease, the earlier you know, the better. African swine fever (ASF), one of the most devastating swine infectious diseases in the world: Vietnam has approved domestically produced live attenuated vaccines since 2022, but there are still international concerns about their safety and Taiwan has not approved their use, so disease prevention can still only rely on biosecurity. The Internet of Things (IoT) used on livestock farms is also known as "Precision Livestock Farming" (PLF), and can help detect outbreaks earlier.
Precision livestock farming uses sensors, cameras, and algorithms to build a round-the-clock health observation system for pigs. According to a systematic review by Gómez et al. (2021) published in Frontiers in Veterinary Science, IoT technology can continuously collect behavioral, physiological, and environmental data and has great potential for improving pig welfare and disease management. The following are three main areas where this technology can be applied to early warning of ASF:
1. Detecting Abnormal Behavior: Activity Patterns as the First Early Warning Line
A pig's daily behavior can show its health. According to a study by Huang et al. (2024) published in Computers and Electronics in Agriculture, healthy pigs show clear activity peaks from about 5 a.m. to 10 a.m. and from 2 p.m. to 6 p.m. each day, and abnormal activity (such as excessive stillness or reduced activity) is often an early sign of disease.
ASF causes behavior changes in pigs early on, such as lethargy and reduced movement. With cameras and accelerometers (mostly embedded in ear tags), each pig's movement patterns and posture can be tracked in real time, and algorithms compare them against the "normal daily pattern" to quickly identify potentially abnormal individuals.
In addition, according to Arulmozhi et al. (2021) in the journal Animals, this kind of image-based behavior monitoring is low in cost and especially suited to small and medium-sized pig farms.
2. Body Temperature Tracking: Digital Ear Tags as the Pig's "Temperature-Sensing Skin"
Elevated body temperature is the most direct indicator of inflammation and infection. Gómez et al. (2021) point out that IoT devices such as thermal imagers, infrared thermometers, and embedded sensors can continuously monitor body surface temperatures without contact, significantly improving the efficiency of early detection.
Huang et al. (2024) also discovered that although temperature data from ear tags is affected by the environment and behavior, hidden anomalies can still be found by comparing the "overall herd trend." For example, if a pig repeatedly shows a "drop in body temperature" trend during the day, it may be the result of the pig trying to find lower-temperature areas to rest after a fever; this negative change is considered a latent symptom of the disease.
3. Data Integration: From Single-Point Detection to Comprehensive Early Warning
A single sensor can find abnormalities, but if behavioral, physiological, feeding, and drinking data are cross-checked together, early warning is more accurate.
According to a literature review by Trabachini et al. (2025) in the journal Animals, feeding multi-sensor data into AI models such as Random Forest and deep learning systems can effectively distinguish normal from abnormal pigs and turn the results into judgments that managers can act on.
In addition, combining RFID technology with load sensors can also monitor each pig's feeding and drinking behavior. Slight changes in eating patterns are often among the earliest abnormalities before illness.
Conclusion: Let Pig House Data Give an Early Warning
Precision livestock farming builds a detection system from "digital eyes" (cameras) and "digital skin" (sensors), compares large amounts of data in real time, and gives warnings proactively before an outbreak breaks out.
YenProtek's Pig Herd Management System can start with record integration: ear tag numbers link breeding, medication, environment and biosecurity records, and the house environment is measured by FarmerPack, with a reminder when it exceeds the threshold for that house.
References:
- Gómez, Y., et al. (2021). A Systematic Review on Validated Precision Livestock Farming Technologies for Pig Production and Its Potential to Assess Animal Welfare. Frontiers in Veterinary Science, 8:660565. https://doi.org/10.3389/fvets.2021.660565
- Huang, Y., et al. (2024). Analysis of pig activity level and body temperature variation based on ear tag data. Computers and Electronics in Agriculture, 219, 108768. https://doi.org/10.1016/j.compag.2024.108768
- Arulmozhi, E., et al. (2021). The Application of Cameras in Precision Pig Farming: An Overview for Swine-Keeping Professionals. Animals, 11(8), 2343. https://doi.org/10.3390/ani11082343
- Trabachini, A., et al. (2025). Precision Livestock Farming Applied to Swine Farms—A Systematic Literature Review. Animals, 15, 2138. https://doi.org/10.3390/ani15142138
- Benjamin, M., & Yik, S. (2019). Precision Livestock Farming in Swine Welfare: A Review for Swine Practitioners. Animals, 9(4), 133. https://doi.org/10.3390/ani9040133