Analyzing Cattle Activity Patterns with Ear Tag Accelerometer Data

Area of Science:

• Animal Science
• Biotechnology
• Agricultural Engineering

Background:

• Monitoring cattle activity is crucial for assessing health and welfare.
• Smart ear tags offer a non-invasive method for continuous data collection.
• Understanding activity patterns can reveal physiological or environmental stressors.

Purpose of the Study:

• To develop and validate a method for characterizing cattle activity using smart ear tag accelerometers.
• To identify the most effective statistical features and data processing techniques for activity profiling.
• To assess the utility of daily differential activity (DDA) for quantifying activity variations.

Main Methods:

• Equipped cattle in tropical and temperate climates with smart ear tags containing triaxial accelerometers.
• Collected accelerometer data and processed it using statistical features (mean, median, standard deviation, median absolute deviation) over five-minute windows.
• Aggregated data into hourly/daily totals and calculated daily differential activity (DDA) across various interval divisions.

Main Results:

• High-pass filtering of accelerometer readings significantly improved the visualization of activity patterns.
• The median of the acceleration vector norm was identified as the most reliable feature for activity characterization and DDA calculation.
• Activity profiles derived from standard deviation showed higher inter-animal variability and overall value variation.

Conclusions:

• Smart ear tag accelerometers are a promising tool for monitoring cattle activity, health, and welfare.
• High-pass filtering and using the median feature enhance the accuracy of activity profiling.
• Accounting for diurnal patterns is essential for optimal results in animal activity assessment.