Validation of sensor-based technology for measuring interaction with organic enrichment materials in fattening pigs

• Organic enrichment material (EM) improves animal welfare in pig farming. • Validation of Passive Infrared Detectors and tri-axial accelerometers to measure interaction with EM in fattening pigs. • The influence of different material types on pigs’ interaction with EM. • Passive Infrared Detectors achieved a sensitivity of 80.6% and a specificity of 80.5%. • The x-, y-, and z-axes of the accelerometer showed varying values, with specificity ranging from 64.5% to 74.9% and sensitivity ranging from 52.7% to 69.7%. Monitoring pig interactions with enrichment materials (EM) is essential for assessing animal welfare, yet automated detection remains underdeveloped. This study aimed to validate Passive Infrared Detectors and tri-axial accelerometers to monitor such interactions and compare activity levels when different organic materials were provided. Both sensor types were attached to a material dispenser. Animal behavior was documented via video recording and analyzed using scan sampling. Interactions with EM were recorded over a 12-week fattening period in a control group with chopped straw and a treatment group exposed to weekly changes in material (chopped straw, straw pellets, chopped hay, hay pellets). Sensor performance parameters such as sensitivity, specificity, precision, and accuracy were calculated. Activity levels were compared between the control and treatment group, and the influence of different material types on pig activity was analyzed. Passive Infrared Detectors showed strong correlations with video analysis ( r = 0.59 - 0.70; P < 0.001) throughout all fattening phases and achieved 80.6% sensitivity and 80.5% specificity. Accelerometers showed lower accuracy and variable sensor performance parameters across different axes. In the starter and grower phases, pigs in the treatment group were more active than those in the control group, with overall activity decreasing toward the end of the fattening period. Within the treatment group, the highest activity was observed with straw pellets and the lowest with chopped hay. This study demonstrated that Passive Infrared Detectors had the potential to detect interaction with enrichment material and should be further developed for practical use in pig farming.

Authors

Institutions

Publication Details

Journal
Smart Agricultural Technology
Published
2025-07-16
DOI
https://doi.org/10.1016/j.atech.2025.101210
Citations
1
Primary Topic
Meat and Animal Product Quality
Type
article
Field-Weighted Citation Impact
1.19

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Validation of sensor-based technology for measuring interaction with organic enrichment materials in fattening pigs

Wolfgang Büscher, Senta Becker, Inga Tiemann, Esther Wurm et al.
1 citations
Smart Agricultural Technology
Meat and Animal Product Quality
1.19
article

Validation of sensor-based technology for measuring interaction with organic enrichment materials in fattening pigs

Wolfgang Büscher, Senta Becker, Inga Tiemann, Esther Wurm, Simon Andert, Anna Rathke
article en
1 citations

Abstract

• Organic enrichment material (EM) improves animal welfare in pig farming. • Validation of Passive Infrared Detectors and tri-axial accelerometers to measure interaction with EM in fattening pigs. • The influence of different material types on pigs’ interaction with EM. • Passive Infrared Detectors achieved a sensitivity of 80.6% and a specificity of 80.5%. • The x-, y-, and z-axes of the accelerometer showed varying values, with specificity ranging from 64.5% to 74.9% and sensitivity ranging from 52.7% to 69.7%. Monitoring pig interactions with enrichment materials (EM) is essential for assessing animal welfare, yet automated detection remains underdeveloped. This study aimed to validate Passive Infrared Detectors and tri-axial accelerometers to monitor such interactions and compare activity levels when different organic materials were provided. Both sensor types were attached to a material dispenser. Animal behavior was documented via video recording and analyzed using scan sampling. Interactions with EM were recorded over a 12-week fattening period in a control group with chopped straw and a treatment group exposed to weekly changes in material (chopped straw, straw pellets, chopped hay, hay pellets). Sensor performance parameters such as sensitivity, specificity, precision, and accuracy were calculated. Activity levels were compared between the control and treatment group, and the influence of different material types on pig activity was analyzed. Passive Infrared Detectors showed strong correlations with video analysis ( r = 0.59 - 0.70; P < 0.001) throughout all fattening phases and achieved 80.6% sensitivity and 80.5% specificity. Accelerometers showed lower accuracy and variable sensor performance parameters across different axes. In the starter and grower phases, pigs in the treatment group were more active than those in the control group, with overall activity decreasing toward the end of the fattening period. Within the treatment group, the highest activity was observed with straw pellets and the lowest with chopped hay. This study demonstrated that Passive Infrared Detectors had the potential to detect interaction with enrichment material and should be further developed for practical use in pig farming.

Smart Agricultural TechnologyVol. 12
University of Bonn (DE), Animal Husbandry and Veterinary Department (IN), Hochschule Osnabrück (DE)
Rheinische Friedrich-Wilhelms-Universität Bonn
Openalex Percentile: Top 22%
Meat and Animal Product Quality
1.19
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.