Skip to main content
ARS Home » Plains Area » Clay Center, Nebraska » U.S. Meat Animal Research Center » Genetics and Animal Breeding » Research » Publications at this Location » Publication #423780
Research Project: Multi-Dimension Phenotyping to Enhance Prediction of Performance in Swine

Location: Genetics and Animal Breeding

Title: Multiscale vibration sensing for activity and vital signs monitoring in pig pens

Author
item CODLING, JESSE - University Of Michigan
item SHULKIN, JEFFREY - University Of Michigan
item VIBHATASILPIN, ABHIPOL - University Of Michigan
item ADHANA, VEDANT - University Of Michigan
item Rohrer, Gary
item Miles, Jeremy
item SHARMA, SUDHENDU RAJ - University Of Lincoln
item BROWN-BRANDL, TAMI - University Of Lincoln
item NOH, HAE YOUNG - Stanford University
item ZHANG, PEI - University Of Michigan

Submitted to: Proceedings
Publication Type: Proceedings
Publication Acceptance Date: 3/1/2025
Publication Date: 6/5/2025
Citation: Codling, J.R., Shulkin, J.D., Vibhatasilpin, A., Adhana, V., Rohrer, G.A., Miles, J.R., Sharma, S., Brown-Brandl, T.M., Noh, H., Zhang, P. 2025. Multiscale vibration sensing for activity and vital signs monitoring in pig pens. In: Proceedings of Association for Computing Machinery. 23rd Association for Computing Machinery Networked Sensor Systems, May 6-9, 2025, Irvine, California. p. 650-651. https://doi.org/10.1145/3715014.3724052.
DOI: https://doi.org/10.1145/3715014.3724052

Interpretive Summary: An innovative approach using vibration sensing to monitor vital signs and activities in pig pens was developed, aiming to reduce pre-weaning piglet mortality during the farrowing period. This technology is implemented by mounting sensors to the underside of flooring material in standard commercial farrowing pens. The proposed method predicts future amplification values necessary based on past sensor data, allowing for automatic adaptation to changes in pig behavior and environmental conditions. This approach avoids shortfalls of traditional methods, such as too much data or lack of visibility, offering a solution suitable for remote farm locations.

Technical Abstract: Monitoring vital signs and activities in pig pens during the farrowing period is crucial for reducing pre-weaning piglet mortality and enhancing farm productivity. Traditional methods focus on either vital signs or activities separately, falling short in the dynamically changing farm environment. This paper introduces a multiscale vibration sensing method which dynamically adjusts sensor amplifier gain to detect both vital signs (e.g. heartbeats and respirations) and larger-scale activities (e.g. walking, eating, nursing, etc.). Preliminary trials demonstrate the system's potential to adapt to rapidly changing conditions by switching between high sensitivity for vital signs and reduced sensitivity for activity sensing depending on the detected vibration signal.