Predicting sleep and lying time of calves with a support vector machine classifier using accelerometer data
Autor: | Johannes Tiusanen, Matti Pastell, Ann-Helena Hokkanen, Laura Hänninen |
---|---|
Rok vydání: | 2011 |
Předmět: |
2. Zero hunger
Sleeping time Development environment medicine.medical_specialty 040301 veterinary sciences 0402 animal and dairy science 04 agricultural and veterinary sciences Audiology 040201 dairy & animal science Non-rapid eye movement sleep Sleep in non-human animals Surgery 0403 veterinary science Food Animals Ambulatory EEG Support vector machine classifier medicine Animal Science and Zoology Accelerometer data Psychology Lying |
Zdroj: | University of Helsinki |
ISSN: | 0168-1591 |
Popis: | Sleep is essential to calves, but to date the only possibilities for measuring sleep in cattle production systems use ambulatory EEG or validated sleeping behavior assessments. We developed a small, neck-based, wireless accelerometer system for measuring the sleep and lying time of calves. We collected data from 10 dairy calves and developed a model based on wavelet analysis with a support vector machine classifier for measuring sleep and lying time and were able to record sleep and lying time accurately. For total sleeping time the model was able to distinguish (mean ± SE) 90 ± 3% and 85 ± 4% of the sleeping bouts, and 82 ± 2% of the occurrence of sleep. Correspondingly, the model distinguished 66 ± 8% and 70 ± 6% of the total time for NREM and REM sleep. 70 ± 6% of the NREM sleep bout lengths and 80 ± 5% of the REM sleep bouts were predicted. The numbers for NREM and REM bouts were 77 ± 5% and 79 ± 4%, respectively. The model correctly predicted 96 ± 1% of total lying time, 79 ± 6% of lying bout durations, and 77 ± 7% of the occurrence of lying bouts. The device provides a method to measure sleep and lying time in calves continuously in a production environment without disturbing the animals. |
Databáze: | OpenAIRE |
Externí odkaz: |