Frequency modulated continuous wave radar-based system for monitoring dairy cow respiration rate

Heat stress is one of the major challenges in livestock production and management. Due to heat stress, dairy cows experience health and fertility problems as well as lower milk production, resulting in great economic losses to dairy farmers. One of the approaches to assessing heat stress in dairy cows is by monitoring their respiration rate (RR). Many studies show that the RR of dairy cows is highly correlated to heat stress. The measurement of RR is most commonly taken by counting flank movements via human observation, which is labor-intensive and may vary across observers. This paper presents a non-contact system for RR monitoring of dairy cows using millimeter-wave frequency modulated continuous wave (FMCW) radar. The system utilizes an integrated sensor node that collects the data from a FMCW radar and a temperature-humidity sensor. The sensor node was installed in the milking parlor of an experimental dairy farm to continuously measure the displacements from cows' flank movements. The radar data was converted by the sensor node into RR measurements and sent together with the environmental data to a remote server for post-processing. A dairy cow RR measurement algorithm was developed to process the radar data; it can be divided into three parts: cow presence state determination, timestamp labelling, and individual dairy cow RR matching. A model trained to automatically determine the presence of cows from the collected radar data had an F1-score of 0.95, as verified by manual observation. The timestamp labelling sub-routine was used to merge the predicted states and perform gap and chunk analyses for removing outliers and merging consecutive chunks. Finally, the RR measurements were matched to each time-stamp in order to identify the RR of each cow in specific time periods. The algorithm had an R2 of 0.995 and root mean square error (RMSE) of 1.582 breaths/min, also verified by manual observation. The system was operated for a year to investigate the relationship between the RR and temperature-humidity index (THI); this relationship was described using a piecewise linear-exponential regression model, which revealed the effect of THI on the level of heat stress among dairy cows in a subtropical region. The proposed system herein proved the feasibility of employing a novel dairy cow RR monitoring system using FMCW radar, and demonstrated its potential ap-plications for automated assessment of dairy cow heat stress and health monitoring.