skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


  • NSF Public Access
  • Search Results
  • Development of a Novel Classification Approach for Cow Behavior Analysis Using Tracking Data and Unsupervised Machine Learning Techniques
Title: Development of a Novel Classification Approach for Cow Behavior Analysis Using Tracking Data and Unsupervised Machine Learning Techniques
Global Positioning Systems (GPSs) can collect tracking data to remotely monitor livestock well-being and pasture use. Supervised machine learning requires behavioral observations of monitored animals to identify changes in behavior, which is labor-intensive. Our goal was to identify animal behaviors automatically without using human observations. We designed a novel framework using unsupervised learning techniques. The framework contains two steps. The first step segments cattle tracking data using state-of-the-art time series segmentation algorithms, and the second step groups segments into clusters and then labels the clusters. To evaluate the applicability of our proposed framework, we utilized GPS tracking data collected from five cows in a 1096 ha rangeland pasture. Cow movement pathways were grouped into six behavior clusters based on velocity (m/min) and distance from water. Again, using velocity, these six clusters were classified into walking, grazing, and resting behaviors. The mean velocity for predicted walking and grazing and resting behavior was 44, 13 and 2 min/min, respectively, which is similar to other research. Predicted diurnal behavior patterns showed two primary grazing bouts during early morning and evening, like in other studies. Our study demonstrates that the proposed two-step framework can use unlabeled GPS tracking data to predict cattle behavior without human observations.  more » « less
Award ID(s):
1914635
PAR ID:
10616166
Author(s) / Creator(s):
; ; ; ;
Publisher / Repository:
MDPI
Date Published:
Journal Name:
Sensors
Volume:
24
Issue:
13
ISSN:
1424-8220
Page Range / eLocation ID:
4067
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; ; ; ; ; (, Environmental Data Initiative)
    Circular management of beef supply chains holds great promise for improving sustainability from grazing agroecosystem to dinner plate. In the United States and Canada, one approach to circularity entails transporting manure nutrients from cattle produced in feedlots back to the grazing agroecosystems where they originated to enrich haylands for further grazing cattle production. We provide data to assess this strategy centered around three grazing agroecosystems: Florida, New Mexico, and the provincial assemblage of Manitoba, Saskatchewan, Alberta, British Columbia. We describe four datasets that can be used to estimate the potential nutrient utilization of hay fed to grazing cattle in the three grazing agroecosystems and the magnitudes of feedlot manure nutrients available for transport back to them. We found that although biogeography and management differ among the three grazing agroecosystems, the hay allocated for grazing cattle represented approximately 65% of the total harvested hay produced per agroecosystem after accounting for harvest losses, and that on average all three areas exported about 450,000 cattle annually for feedlot, pasture, and slaughter to states across the US. Although we highlight only three grazingland settings, our approach relies on methods that could ultimately be scaled nationally and internationally, with applicability to other animal industries for which circular management is an aspiration for sustainability outcomes. 
    more » « less
  2. ; ; ; ; ; ; ; ; (, Scientific Data)
    Abstract Monitoring livestock feeding behavior may help assess animal welfare and nutritional status, and to optimize pasture management. The need for continuous and sustained monitoring requires the use of automatic techniques based on the acquisition and analysis of sensor data. This work describes an open dataset of acoustic recordings of the foraging behavior of dairy cows. The dataset includes 708 h of daily records obtained using unobtrusive and non-invasive instrumentation mounted on five lactating multiparous Holstein cows continuously monitored for six non-consecutive days in pasture and barn. Labeled recordings precisely delimiting grazing and rumination bouts are provided for a total of 392 h and for over 6,200 ingestive and rumination jaw movements. Companion information on the audio recording quality and expert-generated labels is also provided to facilitate data interpretation and analysis. This comprehensive dataset is a useful resource for studies aimed at exploring new tools and solutions for precision livestock farming. 
    more » « less
  3. ; ; ; (, Environmental Data Initiative)
    This data package contains two types of data for the Jornada Experimental Range (JER) from 1915 to 1952: 1) shape files containing polygons and attribute tables that represent the pasture configurations on the Jornada Experimental Range and 2) monthly stocking data from these pastures. The livestock represented in the stocking data comprise cattle, horse, sheep, and goats. Grazing goats were infrequent and are grouped with sheep in the source data. As such for this data set, they are included in the sheep category. Stocking data are expressed in animal unit months (AUM), which is based on metabolic weight. This data package provides finer resolution AUM data than knb-lter-jrn.210412001, which presents the annual stocking data for the entire JER from 1916 to 2001. The stocking data in this package begins in June of 1915 and continues through December of 1952, the last year for which the researchers on this project have verified and digitized historical pasture configurations on the JER. https://portal.edirepository.org/nis/mapbrowse?scope=knb-lter-jrn&identifier=210412001 
    more » « less
  4. (, IEEE International Conference on Robotics and Automation)
    For humanoids to be deployed in demanding situations, such as search and rescue, highly intelligent decision making and proficient sensorimotor skill is expected. A promising solution is to leverage human prowess by interconnecting robot and human via teleoperation. Towards creating seamless operation, this paper presents a dynamic telelocomotion framework that synchronizes the gait of a human pilot with the walking of a bipedal robot. First, we introduce a method to generate a virtual human walking model from the stepping behavior of a human pilot which serves as a reference for the robot to walk. Second, the dynamics of the walking reference and robot walking are synchronized by applying forces to the human pilot and the robot to achieve dynamic similarity between the two systems. This enables the human pilot to continuously perceive and cancel any asynchrony between the walking reference and robot. A consistent step placement strategy for the robot is derived to maintain dynamic similarity through step transitions. Using our human-machine-interface, we demonstrate that the human pilot can achieve stable and synchronous teleoperation of a simulated robot through stepping-in-place, walking, and disturbance rejection experiments. This work provides a fundamental step towards transferring human intelligence and reflexes to humanoid robots. 
    more » « less
  5. ; ; ; ; ; ; ; ; (, Ornithological Applications)
    Abstract Intensification of livestock production has reduced heterogeneity in vegetative structure in managed grasslands, which has been linked to widespread declines in grassland songbird populations throughout North America. Patch-burn grazing management aims to restore some of that heterogeneity in vegetative structure by burning discrete pasture sections, so that cattle preferentially graze in recently burned areas. Although patch-burn grazing can increase reproductive success of grassland songbirds, we know little about possible interactions with regional variation in predator communities or brood parasite abundance, or annual variation in weather conditions. Using six years of data from two tallgrass prairie sites in eastern Kansas, USA, we tested effects of patch-burn grazing on the rates of brood parasitism, clutch size, nest survival, and fledging success of three common grassland songbirds, Dickcissels (Spiza americana), Eastern Meadowlarks (Sturnella magna), and Grasshopper Sparrows (Ammodramus savannarum), among pastures managed with patch-burn grazing versus pastures that were annually burned and either grazed or ungrazed. Dickcissel nests experienced lower parasitism (72.8 ± 4.6% SE vs. 89.1 ± 2.2%) and Eastern Meadowlarks had higher nest survival (63.2 ± 20.5% vs. 16.5 ± 3.5%) in annually burned and ungrazed pastures than pastures managed with patch-burn grazing. However, average number of host fledglings per nesting attempt did not differ among management treatments for any species. Annual variation in weather conditions had a large effect on vegetation structure, but not on reproductive success. Probability of brood parasitism was consistently high (25.5‒84.7%) and nest survival was consistently low (9.9–16.9%) for all species pooled across treatments, sites, and years, indicating that combined effects of predation, parasitism and drought can offset potential benefits of patch-burn grazing management previously found in tallgrass prairies. Although differences in reproductive success among management treatments were minimal, patch-burn grazing management could still benefit population dynamics of grassland songbirds in areas where nest predators and brood parasites are locally abundant by providing suitable nesting habitat for bird species that require greater amounts of vegetation cover and litter, generally not present in burned pastures. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email