Development of an open-source algorithm based on inertial measurement units (IMU) of a smartphone to detect cattle grass intake and ruminating behaviors

Andriamandroso, Andriamasinoro; Lebeau, Frédéric; Beckers, Yves; Froidmont, Éric; Dufrasne, Isabelle; Heinesch, Bernard; Dumortier, Pierre; Blanchy, Guillaume; Blaise, Yannick; Bindelle, Jérôme

doi:10.1016/j.compag.2017.05.020

Cited by 72 publications

(41 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In terms of grazing behavior research, our approach could be combined with information provided by motion capture collars, such as those described by Andriamandroso et al [45]. Regarding the very fine spatial scale of the UAS products, attention must be paid to the quality of the positioning associated with the information to which it is compared.…”

Section: Discussionmentioning

confidence: 99%

Mapping and Monitoring of Biomass and Grazing in Pasture with an Unmanned Aerial System

et al. 2019

Self Cite

View full text Add to dashboard Cite

The tools available to farmers to manage grazed pastures and adjust forage demand to grass growth are generally rather static. Unmanned aerial systems (UASs) are interesting versatile tools that can provide relevant 3D information, such as sward height (3D structure), or even describe the physical condition of pastures through the use of spectral information. This study aimed to evaluate the potential of UAS to characterize a pasture’s sward height and above-ground biomass at a very fine spatial scale. The pasture height provided by UAS products showed good agreement (R2 = 0.62) with a reference terrestrial light detection and ranging (LiDAR) dataset. We tested the ability of UAS imagery to model pasture biomass based on three different combinations: UAS sward height, UAS sward multispectral reflectance/vegetation indices, and a combination of both UAS data types. The mixed approach combining the UAS sward height and spectral data performed the best (adj. R2 = 0.49). This approach reached a quality comparable to that of more conventional non-destructive on-field pasture biomass monitoring tools. As all of the UAS variables used in the model fitting process were extracted from spatial information (raster data), a high spatial resolution map of pasture biomass was derived based on the best fitted model. A sward height differences map was also derived from UAS-based sward height maps before and after grazing. Our results demonstrate the potential of UAS imagery as a tool for precision grazing study applications. The UAS approach to height and biomass monitoring was revealed to be a potential alternative to the widely used but time-consuming field approaches. While reaching a similar level of accuracy to the conventional field sampling approach, the UAS approach provides wall-to-wall pasture characterization through very high spatial resolution maps, opening up a new area of research for precision grazing.

show abstract

Section: Discussionmentioning

confidence: 99%

Mapping and Monitoring of Biomass and Grazing in Pasture with an Unmanned Aerial System

et al. 2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…Similarly, using a GPS and an accelerometer implanted on the neck of a cow allowed to reach 90% accuracy in behavior classification (González et al 2015). As stated before, smartphones are generally equipped with an Inertial Measurement Units (IMU) which contains motion and location sensors able to record signals at high rate (Andriamandroso et al 2017). They are widely available, easy to use and they save long hardware developments.…”

Section: Optimizing Smartphones As Behavior Sensorsmentioning

confidence: 99%

“…In this paper, we present a chain of tools fulfilling the above-mentioned criteria for data related to cattle behavior measured by means of the IMU signals of iPhone worn by the animals on halters (Andriamandroso et al 2017). We propose and describe a new infrastructure allowing to collect, store, treat and share information between scientists.…”

Section: Introductionmentioning

confidence: 99%

Cloud services integration for farm animals’ behavior studies based on smartphones as activity sensors

Debauche

Mahmoudi

Andriamandroso

et al. 2018

J Ambient Intell Human Comput

Self Cite

View full text Add to dashboard Cite

Smartphones, particularly iPhone, can be relevant instruments for researchers in animal behavior because they are readily available on the planet, contain many sensors and require no hardware development. They are equipped with high performance Inertial Measurement Units (IMU) and absolute positioning systems analyzing users' movements, but they can easily be diverted to analyze likewise the behaviors of domestic animals such as cattle. The study of animal behavior using smartphones requires the storage of many high frequency variables from a large number of individuals and their processing through various relevant variables combinations for modeling and decision-making. Transferring, storing, treating and sharing such an amount of data is a big challenge. In this paper, a lambda cloud architecture innovatively coupled to a scientific sharing platform used to archive, and process high-frequency data are proposed to integrate future developments of the Internet of Things applied to the monitoring of domestic animals. An application to the study of cattle behavior on pasture based on the data recorded with the IMU of iPhone 4s is exemplified. Performances comparison between iPhone 4s and iPhone 5s is also achieved. The package comes also with a web interface to encode the actual behavior observed on videos and to synchronize observations with the sensor signals. Finally, the use of Edge computing on the iPhone reduced by 43.5% on average the size of the raw data by eliminating redundancies. The limitation of the number of digits on individual variable can reduce data redundancy up to 98.5%.

show abstract

“…Today, there are readily-available sensors and Precision Livestock Farming (PLF) tools that offer the possibility to continuously monitor animal behaviour. Accelerometers can record gross activities such as walking, eating, lying down, positioning systems can connect an animal positions to specific resources and thus infer its putative activity, and image analysis can provide further input (González et al, 2015;Andriamandroso et al, 2017;Barwick et al, 2018). As argued by Dawkins et al (2012), the issue is not about collecting data but how to process it.…”

Section: Introductionmentioning

confidence: 99%

Machine learning to detect behavioural anomalies in dairy cows under subacute ruminal acidosis

Wagner

Antoine

Mialon

et al. 2020

Computers and Electronics in Agriculture

View full text Add to dashboard Cite

et al.. Machine learning to detect behavioural anomalies in dairy cows under subacute ruminal acidosis. A B S T R A C TSickness behaviour is characterised by a lethargic state during which the animal reduces its activity, sleeps more and at times when normally awake, reduces its feed and water intake, and interacts less with its environment. Subtle modifications in behaviour can materialise just before clinical signs of a disease. Recent sensor developments enable continuous monitoring of animal behaviour, but the shift to abnormal animal activity remains difficult to detect. We explored the use of Machine Learning (ML) to detect abnormal behaviour from continuous monitoring. We submitted 14 cows (Bos taurus) to Sub-Acute Ruminal Acidosis (SARA), a disease known to induce changes in behaviour. Another 14 control cows were not submitted to SARA. We used a ruminal bolus to monitor pH and detect when a cow experienced SARA. We used a positioning system to infer an animal's activity based on its position in relation to specific elements in the barn (feeder, resting area, and alleys). We tested several ML algorithms: K Nearest Neighbours for Regression (KNNR); Decision Tree for Regression (DTR); MultiLayer Perceptron (MLP); Long Short-Term Memory (LSTM); and an algorithm where activity is assumed to be similar from one day to the next. First, we developed ML models to predict activity on a given day from the previous 24 h, considering all cows together. Then, we calculated the error between observed and predicted values for a given cow. Finally, we compared the error to a threshold chosen to optimise the distinction between normal and abnormal values. KNNR performed best, detecting 83% of SARA cases (true-positives), but it also produced 66% of false-positives, which limits its use in practice. In conclusion, ML can help detect anomalies in behaviour. Further improvements could probably be obtained by applying ML on very large datasets at animal rather than group level.

show abstract

Development of an open-source algorithm based on inertial measurement units (IMU) of a smartphone to detect cattle grass intake and ruminating behaviors

Cited by 72 publications

References 35 publications

Mapping and Monitoring of Biomass and Grazing in Pasture with an Unmanned Aerial System

Mapping and Monitoring of Biomass and Grazing in Pasture with an Unmanned Aerial System

Cloud services integration for farm animals’ behavior studies based on smartphones as activity sensors

Machine learning to detect behavioural anomalies in dairy cows under subacute ruminal acidosis

Contact Info

Product

Resources

About