Effective and accurate discrimination of individual dairy cattle through acoustic sensing

Acoustic sensing seems to be one of the best methods for monitoring of dairy animals at an organized farm for their better care and management. The main aim of present investigation was to establish the existence of significant differences for various acoustic features of vocal signals uttered from different individuals of a herd of crossbred cows. The mean call duration, mean pitch, 1st formant, periodicity and degree of voice breaks of adult lactating Karan Fries crossbred cattle were observed to be 2.37 ± 0.03 s, 191.57 ± 2.40 Hz, 790.71 ± 5.54 Hz, 97.76% (371.71 periodic pulses out of 380.20 pulses) and 7.64 ± 0.44% respectively. Analysis of bioacoustics features extracted from 300 voice samples of ten adult lactating Karan Fries crossbred cows revealed that differences for amplitudes (minimum, maximum and mean), total energy, mean power, pitch (median, minimum, maximum, range and mean), pitch spreading (84–50, 50–16 and 90–10%), intensities (minimum, maximum and mean (P < 0.01)), formants (F1, F2, F3, F4 and F5), bandwidths (B1, B3 and B4), number of pulse, number of period, mean period, unvoiced frames, degree of voice breaks, jitter, shimmer, mean noise to harmonic ratio (%) and mean harmonic to noise ratio (dB) were highly significant (P < 0.001). Out of these only few acoustic features viz. Pitch (mean and range), formants (F1, F2, F3, F4 and F5), number of pulse, degree of voice breaks, shimmer and mean noise to harmonic ratio (%) were observed to have significant difference for each and every individual cow, therefore only these features could be suggested as the best suited acoustic features for discrimination of individual dairy cattle from their herd. Acoustic features of voice signals uttered from different cows proved to be a passive indicator in discrimination of individual cow.