Publications
NIBIOs employees contribute to several hundred scientific articles and research reports every year. You can browse or search in our collection which contains references and links to these publications as well as other research and dissemination activities. The collection is continously updated with new and historical material.
2023
Authors
Andres Perea Lara Macon Sajidur Rahman Huiying Chen Andrew Cox Shelemia Nyamuryekung'e Sara Campa Madrid Huiping Cao Andres F. Cibils Richard Estell Glenn Duff Santiago A. UtsumiAbstract
Monitoring cattle on rangelands is a daunting task that can be improved by using wearable sensors that are capable of transmitting motion and position data in real time and at low cost. This study tested the performance of machine learning (ML) classifiers to discriminate among foraging activities of cows based on triaxial accelerometer data collected in real-time by LoRa WAN networks. Trials were conducted at the New Mexico State University Chihuahuan Desert Rangeland Research Center and the USDA Jornada Experimental Range in Doña Ana County, NM. A total of 24 Brangus, Brahman, Raramuri Criollo and Angus x Hereford mature cows fitted with LoRa WAN tracking collars housing GPS and triaxial accelerometers were monitored across four periods during the 2022 summer and fall seasons on desert rangeland pastures. Trackers integrated and transmitted activity count (Ac) data from accelerometers at one-minute intervals. Video recording of focal cows (n = 24) was undertaken during daylight hours (0630 to 2000 h) from a distance of ~30 m to minimize interference with natural behaviors. A total of 168 hours of video were recorded and inspected by an experienced observer to label video files according to a classification tree of four main activities: grazing (GR), walking (WA), resting (RE) and ruminating (RU), and two states: active (AC) or static (ST). Individualized activities and states were considered when cows performed the same predefined activity or state for more than 30 secs. Retrieved sensor data from collar trackers were labeled by state and activity according to labels collected from video records. This classification resulted in a dataset containing 9,222 events, including 3,928 for GR, 2,286 for WA, 2,032 for RE, and 976 for RU, as well as 6,214 labels for AC and 3,008 labels for ST. Deep learning through Multilayer Perceptron Classifiers (MLPC) were coded and implemented using a split configuration of 70% of the data for training and 30% for testing, respectively. In preliminary runs, models had reduced ability to properly discriminate among RE (F1 = 0.42) and RU (F1 = 0.43) Thus, RE and RU were merged on subsequent tests, resulting in 3,928 labels for GR, 2,286 labels for WA, and 3,008 labels for merged RE. Deep learning models successfully classified between AC vs. ST behavior with an overall F1 performance score of 0.96. Further use of the same deep learning models successfully classified among GR, WA, and RE activities with an overall F1 performance score of 0.91, suggesting satisfactory application of the trained models to monitor cattle grazing activities on desert rangeland.
Authors
Santiago A. Utsumi Shelemia Nyamuryekung'e Andres Perea Maximiliano Spetter Andrew Cox Lara Macon Richard Estell Glenn DuffAbstract
Virtual fencing is a promising alternative to contain livestock dispersal without using physical barriers. This technology uses smart-wearable collars that deliver predictable warning tones to animals when they approach virtual boundaries paired with mild electric pulses. Virtual fencing allows for dynamic management of livestock grazing, based on site-specific variations in the quality and quantity of forages. However, several factors can affect the efficacy of virtual fencing, including the length of prior experience with virtual fencing, climatic conditions, forage availability inside and outside virtual fencing paddocks and collar configuration schedules. Lactation requirements and social interactions between collared cows and uncollared calves can also influence the efficacy of the technology. Virtual fencing trials were conducted at the New Mexico State University’s Chihuahuan Desert Rangeland Research Center from August 27 to December 21 of 2022 to evaluate the efficacy of virtual fencing to manage rangeland cows during late lactation and following weaning. Twenty-six Brangus cows previously trained to use NoFence C2 collars (NoFence, Batnfjordsøra, Norway), were monitored for 30 days during late lactation and 28 days after weaning. Collared cows and uncollared calf pairs were allocated to four virtual fence pastures in late lactation and after weaning, with pasture duration (4.2 ± 0.6 d), size (72 ± 19 ha) and perimeter (4,523 ± 352 m) varying according to forage availability and access to fresh drinking water. Audio cues, electric pulses and ratio of electric pulses to audio cues before and after weaning were compared by ANOVA in a Completely Randomized Design replicated across pre-weaning and post-weaning pastures (n = 8). The average number of electric pulses per cow was greater (P < 0.0004) for pre-weaning (3.7 ± 0.2) than for post-weaning post-weaning (1.6 ± 0.3) pastures. The number of audio warnings per cow was also greater (P < 0.0001) for pre-weaning (52 ± 3.3) than post-weaning (34 ± 3.3) pastures. Conversely, cows had decreased (P < 0.0001) ratios of electric pulses relative to audio tones on post-weaning (4.8 ± 0.5%) than pre-weaning (7.0 ± 0.8%) pastures. These results suggest that cows responded better to virtual fencing after weaning, likely because weaned cows were no longer affected by social interactions with uncollared calves. Furthermore, cows after weaning apparently relied on warning tones and fewer electric pulses to interact safely with virtual fences. However, it is important to note that sources of variation not accounted for or controlled by the present experimental design may have also affected the recorded interactions with virtual fences in the present study.
Authors
Tony Waterhouse Ann McLaren Aimee Walker John P. Holland Claire Morgan-Davies Shelemia Nyamuryekung'e Andrew Cox Santiago A. UtsumiAbstract
No abstract has been registered
Authors
Shelemia Nyamuryekung'e Glenn Duff Santiago A. Utsumi Richard Estell Matthew M. McIntosh Micah Funk Andrew Cox Huiping Cao Huiying Chen Sheri Spiegal Andres Perea Sajidur Rahman Andres F. CibilsAbstract
LoRa-WAN sensors were used to compare methods for determining walking distances by grazing cattle in near real-time. The accuracy of relying on a global positioning system (GPS) alone or in combination with motion data derived from triaxial accelerometers was compared using stationary control trackers (Control) placed in fixed field locations (n=6) or vs. trackers (Animal) mounted on cows (n=6) grazing on pasture at the New Mexico State University’s Clayton Livestock Research Center. Trackers communicated motion data at 1-minute intervals and GPS positions at 15-minute intervals for seven days. Daily distance walked was determined using: 1) raw GPS data (RawDist), 2) data with erroneous GPS locations removed (CorrectedDist), or 3) data with erroneous GPS locations removed and with GPS data associated with the static state excluded (CorrectedDist_Act). Distances were analyzed via one-way ANOVA to compare Control vs. Animal deployment effects. No difference (P=0.43) in walking distance was detected between Control vs. Animal for RawDist. However, distances calculated for CorrectedDist differed (P<0.01) between the two tracker deployments. Due to the random error of GPS measurements, CorrectedDist for stationary devices differed (P=0.01) from zero. The walking distance calculated by CorrectedDist_Act differed (P<0.01) between Control vs. Animal trackers, with distances for Control trackers not differing (P=0.44) from zero. The fusion of GPS and accelerometer data was a more suitable method for calculating walking distance by grazing cattle. This result may highlight the value of combining more than one source of independent sensor data in Precision Livestock Farming applications.
Authors
Shelemia Nyamuryekung'e Andrew Cox Andres Perea Richard Estell Andres F. Cibils John P. Holland Tony Waterhouse Glenn Duff Micah Funk Skye Aney Matthew M. McIntosh Sheri Spiegal Brandon Bestelmeyer Santiago A. UtsumiAbstract
Virtual fencing (VF) is an alternative method to control livestock dispersal. This method consists of the use of animal wearable collars that employ auditory-electric pulse cues to deter animals from exiting their predefined containment zones. The study aimed to document skin defense (SkinM) and association learning mechanism (AssocM) in describing the conditioning behavior of the VF application. Nursing Brangus cows at the New Mexico State University’s Chihuahuan Desert Rangeland Research Center were allotted three days of free access to feeding areas (0.19ha) with VF-deactivated (VF-Off) or VF-Activated (VF-On) collars restricting one-third of the penned area. This training sequence was repeated twice (6-day/Period) with two replications (n=11 and 17cows). The VF collars communicated real-time animal positions at 15-minute intervals. ANOVA was used to compare daily-derived variables per cattle on the percentage of time spent within the containment and restricted zones (SkinM) and the number of auditory and electric pulses emitted during the VF-On configurations (AssocM). The VF-On treatment increased the percentage of time collared animals spent within the containment zone (98.4 vs.72.0 ±1.0 %Time;P<0.01) and reduced the percentage of time within the restricted zone (1.6 vs.28.0 ±1.0 %Time;P<0.01) compared to the VF-Off treatment. Exposure to VF-On in Period 1 triggered a greater frequency of auditory (1.8 vs.0.6 ±0.4;P<0.01) and electrical pulses (0.7 vs.0.2 ±0.2;P<0.01) than in Period 2. Results indicate that groups of cows learn rapidly to respond to VF boundaries by reducing the time spent within the restricted areas (SkinM) and relying increasingly on auditory cues to alter behavior (AssocM).
Authors
Andres F. Cibils Richard Estell Sheri Spiegal Shelemia Nyamuryekung'e Matthew M. McIntosh Danielle M. Duni Oscar A. Herrera Conegliano Felipe A. Rodriguez Almeida Octavio Roacho Estrada Lisandro J. Blanco Michael C. Duniway Santiago A. Utsumi Alfredo L. GonzalezAbstract
No abstract has been registered
Authors
Danielle M. Duni Matthew M. McIntosh Shelemia Nyamuryekung'e Andres F. Cibils Michael C. Duniway Richard Estell Sheri Spiegal Alfredo L. Gonzalez Melakeneh G. Gedefaw Matthew Redd Robert Paulin Caitriana M. Steele Santiago A. Utsumi Andres PereaAbstract
No abstract has been registered
Authors
Matthew M. McIntosh Andres F. Cibils Shelemia Nyamuryekung'e Richard Estell Andrew Cox Danielle M. Duni Qixu Gong Tony Waterhouse John P. Holland Huiping Cao Laura Boucheron Huiying Chen Sheri Spiegal Glenn Duff Santiago A. UtsumiAbstract
No abstract has been registered
Abstract
No abstract has been registered
Authors
Odd Arne Rognli Trygve S. Aamlid Muath K Alsheikh Helga Amdahl Sigridur Dalmannsdottir Kristoffer Herland Hellton Marit Jørgensen Mallikarjuna Rao Kovi Therese Mæland Akhil Reddy Pashapu Ievina Sturite Thordis Linda Thorarinsdottir Susanne Skinnehaugen WindjuAbstract
No abstract has been registered