References of "Andriamandroso, Andriamasinoro"
     in
Bookmark and Share    
Full Text
Peer Reviewed
See detailInfluences of feeding behaviour and forage quality on diurnal methane emission dynamics of grazing cows
Blaise, Yannick ULiege; Andriamandroso, Andriamasinoro ULiege; Heinesch, Bernard ULiege et al

in Berckmans, Daniel; Keita, Keita (Eds.) Precision Livestock Farming ‘17 (2017, September 12)

This study aimed to evaluate diurnal methane (CH4) emission dynamics of grazing cattle and highlight their relationships with biotic factors such as the feeding behaviour as well as seasonal changes in ... [more ▼]

This study aimed to evaluate diurnal methane (CH4) emission dynamics of grazing cattle and highlight their relationships with biotic factors such as the feeding behaviour as well as seasonal changes in pasture characteristics. Existing methods to assess grazing ruminants’ daily CH4 emissions provide useful insights to investigate mitigation strategies relying on feeding and genetic selection. Nonetheless such methods based on tracer gases (SF6) or feeding bins equipped with sniffers (e.g. GreenFeed) can hardly cover diurnal CH4 emission fluctuations which can influence the accuracy of total CH4 production estimations. Previous studies in barns showed that emission dynamics strongly vary during post feeding time, leading to a possible bias in estimates of daily CH4 emissions as high as 100%. To investigate whether such fluctuations are also taking place on pasture, a portable device was designed with infrared CH4 and CO2 sensors measuring concentrations in the exhaled air at a high sampling rate (4 Hz). Six grazing dry red-pied cows were equipped with the device and motion sensors during runs of 24h to monitor CH4 and CO2 emissions and detect their feeding behaviours (grazing, rumination and other behaviours), respectively. This experiment was performed in summer and fall in order to cover seasonal changes in pasture forage quality. Methane emission was estimated from the CH4:CO2 concentration ratio and the metabolic CO2 production of the cows. As for barn studies, variations were observed in total daily CH4 emission due to the seasons and diurnal variations were also observed due to animal behaviours. Relationships between animal feeding behaviour and CH4 emissions patterns on pasture were also unravelled. [less ▲]

Detailed reference viewed: 84 (12 ULiège)
Full Text
Peer Reviewed
See detailDifferentiating pre- and post-grazing pasture heights using a 3D camera: a prospective approach
Andriamandroso, Andriamasinoro ULiege; Castro Muñoz, Eloy ULiege; Blaise, Yannick ULiege et al

in Berckmans, Daniel; Keita, Alassane (Eds.) Precision Livestock Farming ‘17 (2017, September)

Grasslands management involves the monitoring of both animal and plant components. Recent precision livestock farming developments have focused on high-rate monitoring of grazing animals to enhance ... [more ▼]

Grasslands management involves the monitoring of both animal and plant components. Recent precision livestock farming developments have focused on high-rate monitoring of grazing animals to enhance livestock productivity and welfare. The evolution of grass resource during the grazing process is not being overlooked by graziers and researchers, but grass characteristics, such as height, dry matter content, productivity or density, are still measured using low frequency and sometimes destructive and time-consuming methods; such as quadrat, sward-sticks, rising plate meters. This study investigated the potential of using 3D cameras to assess sward physical characteristics. Main objectives were: (1) to define the correct way to capture images, particularly the camera position above the ground and, (2) to assess if differences in sward height were detectable. Couples of images differing in grass height were captured on the same spot with a 3D camera at different above-ground heights (30, 40, 50 cm) on a ryegrass-white clover pasture. Pregrazing height was 15cm and post-grazing sward was simulated by cutting at 2 cm. Histograms of intensity performed on greyscale images showed differences between pre- and post-grazing sward. As expected, overall darker pixels were observed for pre-grazing images (p<0.01) and whiter pixels for post-grazing images (p<0.01), indicating longer distances consistent with lower forage biomass. Images taken at a distance of 30 and 40 cm could identify these differences. Further developments require improving the calibration of the camera and developing image analysis method to estimate more plant characteristics such as density or dry matter content. [less ▲]

Detailed reference viewed: 18 (4 ULiège)
Full Text
Peer Reviewed
See detailDevelopment of an open-source algorithm based on inertial measurement units (IMU) of a smartphone to detect cattle grass intake and ruminating behaviors
Andriamandroso, Andriamasinoro ULiege; Lebeau, Frédéric ULiege; Beckers, Yves ULiege et al

in Computers & Electronics in Agriculture (2017), 139

In this paper, an open algorithm was developed for the detection of cattle’s grass intake and rumination activities. This was done using the widely available inertial measurement unit (IMU) from a ... [more ▼]

In this paper, an open algorithm was developed for the detection of cattle’s grass intake and rumination activities. This was done using the widely available inertial measurement unit (IMU) from a smartphone, which contains an accelerometer, a gyroscope, a magnetometer and location sensors signals sampled at 100 Hz. This equipment was mounted on 19 grazing cows of different breeds and daily video sequences were recorded on pasture of different forage allowances. After visually analyzing the cows’ movements on a calibration database, signal combinations were selected and thresholds were determined based on 1-s time windows, since increasing the time window did not increase the accuracy of detection. The final algorithm uses the average value and standard deviation of two signals in a two-step discrimination tree: the gravitational acceleration on x-axis (Gx) expressing the cows’ head movements and the rotation rate on the same x-axis (Rx) expressing jaw movements. Threshold values encompassing 95% of the normalized calibrated data gave the best results. Validation on an independent database resulted in an average detection accuracy of 92% with a better detection for rumination (95%) than for grass intake (91%). The detection algorithm also allows for characterization of the diurnal feeding activities of cattle at pasture. Any user can make further improvements, for data collected at the same way as the iPhone’s IMU has done, since the algorithm codes are open and provided as supplementary data. [less ▲]

Detailed reference viewed: 54 (15 ULiège)
Full Text
See detailCattle grazing dynamics under contrasted pasture characteristics at temporal and spatial scales
Andriamandroso, Andriamasinoro ULiege

Doctoral thesis (2017)

Grassland constitutes an important and a low-cost food source for grazing livestock. Optimal management should consider both forage resource productivity and animal needs. For cattle, grazing is a normal ... [more ▼]

Grassland constitutes an important and a low-cost food source for grazing livestock. Optimal management should consider both forage resource productivity and animal needs. For cattle, grazing is a normal behavior displayed in an attempt to eat the amount of forage to fulfill their nutritive requirements for maintenance and production. It is the most time-consumed activity of cows reared in pasture-based systems. With the increase of herd size, on one hand, farmers have been constrained to integrate innovative tools and techniques, such as milking robot, to improve the production system in particular to reduce the labor cost. On the other hand, such change might reduce time allocated for grazing on pasture. However pasture-based systems constitute a real pillar for sustainability as they are socially acceptable and environmentally profitable as they play an important role on ecosystem services and biodiversity provision. Studying grazing processes at individual level, which finally is the key point of animal-plant interactions, is a valuable research domain to enhance the knowledge about this mechanism and to feed decision support tools. This thesis aimed to link the changes in pasture characteristics to the grazing behavior of cattle in order to better understand the grazing strategy under different pasture characteristics and forage allowances. To allow an individual monitoring, sensor technology has integrated within farms and livestock researches to monitor many physical variables, inducing the emergence of precision livestock farming approach. Different types of sensors were designed, and already commercialized for some, primarily for physiological status detections such as heat, parturition or diseases. Grazing behaviors could be monitored using pressure, electromyography, acoustic or accelerometric sensors by classifying posture and movements of the animal into unitary behaviors (grazing, ruminating, resting, walking, etc.) and finer behavior such as chews and bites through jaw movements’ detection. When compared to real observation, detection accuracies of these behaviors were variable according to the type of sensor, its position on the animal during data acquisition on pasture, the data recording frequency, the time-window and the method dedicated to the post-recording data analysis. State-of-the-art analysis demonstrated a great performance of accelerometers for unitary behaviors and bites detection. An inertial measurement unit, integrating accelerometer, gyroscope and location sensors, was used for recording cattle movements during grazing at high sampling rate (100Hz). It allows a correct detection of grass intake and rumination behaviors with an average accuracy of 91% using 1-second time-window when calibrating and validating the detection algorithm. Deeper analysis of accelerometric signal allowed us to detect bites and chews performed during grazing and ruminating. Effects of pasture heights on grazing bites characteristics were differentiated by a higher frequency when pasture is at a lower height. Finally when combined to geographical information, a similar pattern was observed for cattle grazing on the same spot confirming their herd movement during grazing in terms of bites location. Differences were visible under different pasture heights but not significant. Such bites location, combined with continuous monitoring of cattle behaviors, through use of sensors, should be furtherly linked with more pasture characteristics, if possible with the same accuracy, and monitored on longer period in order to obtain a complete coverage of cattle grazing strategy and the effect of contrasted environment in order to purpose valuable tool for a better grazing management. [less ▲]

Detailed reference viewed: 102 (18 ULiège)
Full Text
See detailActivités et production de méthane des bovins au pâturage
Blaise, Yannick ULiege; Andriamandroso, Andriamasinoro ULiege; Castro Muñoz, Eloy ULiege et al

Conference given outside the academic context (2017)

Quels sont les liens entre les comportements des bovins et les caractéristiques de la prairie sur la dynamique de production de méthane (CH4)?

Detailed reference viewed: 25 (8 ULiège)
Full Text
Peer Reviewed
See detailWeb-based cattle behavior service for researchers based on the smartphone inertial central
Debauche, Olivier ULiege; Mahmoudi, Saïd; Andriamandroso, Andriamasinoro ULiege et al

in Procedia Computer Science (2017), 110(C), 110-116

Smartphones, particularly iPhones, 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 ... [more ▼]

Smartphones, particularly iPhones, 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 and a scientific sharing platform used to archive and process highfrequency data are proposed. An application to the study of cattle behavior on pasture on the basis of the data recorded with the IMU of iPhones 4S is exemplified. 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 fog computing on the iPhone reduced by 42% on average the size of the raw data by eliminating redundancies. [less ▲]

Detailed reference viewed: 45 (14 ULiège)
Full Text
See detailI-cows exploring plant-animal interface by precision grazing
Bindelle, Jérôme ULiege; Andriamandroso, Andriamasinoro ULiege; Blaise, Yannick ULiege et al

Conference (2016, August 02)

Detailed reference viewed: 88 (37 ULiège)
Full Text
Peer Reviewed
See detailA review on the use of sensors to monitor cattle jaw movements and behavior when grazing
Andriamandroso, Andriamasinoro ULiege; Bindelle, Jérôme ULiege; Mercatoris, Benoît ULiege et al

in Biotechnologie, Agronomie, Société et Environnement = Biotechnology, Agronomy, Society and Environment (2016), 20

Precision Livestock Farming (PLF) is spreading rapidly in intensive cattle farms. It is based on the monitoring of individuals using different kinds of sensors. Applied to grazing animals, PLF is mainly ... [more ▼]

Precision Livestock Farming (PLF) is spreading rapidly in intensive cattle farms. It is based on the monitoring of individuals using different kinds of sensors. Applied to grazing animals, PLF is mainly based on the recording of three parameters: the location, the posture and the movements of the animal. Until now, several techniques have been used to discriminate grazing and ruminating behaviors with accuracies over 90% on average, when compared to observations, providing valuable tools to improve the management of pasture and grazing animals. However, bites and jaw movements are still overlooked, even though they are of utmost importance to assess the animal grazing strategies for various pasture types and develop future techniques allowing better estimation of their intake. The goal of this review is to explore the possibility of monitoring the individual jaw movements and the differentiation of bites in grazing animals. For this purpose, (1) the mechanisms of forage intake in cattle are explained briefly in order to understand the movements performed by the cow, especially during grazing, (2) the various sensors that have been proposed to monitor jaw movements of ruminants such as mechanical sensors (pressure sensors), acoustic sensors (microphone) and electromyography sensors are compared and (3) finally the relationship between jaw movements, biting behavior and forage intake is discussed. The review clearly demonstrated the abilities of mechanical, acoustic and electromyography sensors to classify the difference types of jaw movements. However, it also indicated a wide range of accuracies and different observation windows required to reach these accuracies when compared to the observed movement. This classification purpose could lead to a better detection of more specific behavior, e.g. bite detection, and their exact location on pasture. [less ▲]

Detailed reference viewed: 255 (39 ULiège)
Full Text
See detailLINKING CATTLE GRAZING BEHAVIOR TO METHANE AND CARBON DIOXIDE DYNAMICS
Blaise, Yannick ULiege; Lebeau, Frédéric ULiege; Andriamandroso, Andriamasinoro ULiege et al

in Communications in Agricultural and Applied Biological Sciences (2016, February), 81(1), 107-112

Various methods are presently used to measure methane (CH4) emissions of ruminants on pasture. Those measurements are essential to evaluate nutritional strategies to mitigate enteric CH4 emissions as well ... [more ▼]

Various methods are presently used to measure methane (CH4) emissions of ruminants on pasture. Those measurements are essential to evaluate nutritional strategies to mitigate enteric CH4 emissions as well as addressing the selection of low producing individuals. On pasture and in the barn, variations in CH4 emissions are observed depending on the time of the day. However, no studies have been made to link these diurnal fluctuations to behavioural phases, especially on pasture. The aim of this study was to understand the individual dynamics of CH4 production and their links to the grazing behaviour. For this purpose, a new tool was specifically developed. Five red-pied dry cows were equipped with infrared CH4 and carbon dioxide (CO2) sensors measuring concentrations in the exhaled air at 4 Hz. The animals were equipped with a heart rate belt (HR) and motion sensors to detect their feeding behaviours (grazing vs. rumination) for periods of 8 h/d. Wind speed (WS) was also monitor to verify interference with sampled gas concentrations. Results showed that using the CH4:CO2 ratio reduced the interference with WS that was observed on raw CH4 and CO2 concentration signals. CH4:CO2 ratio average over 5 min periods indicated that CH4 emissions were lower during grazing than rumination (P<0.01). The eructation frequency during grazing (0.48 eructation/min, P<0.01) was also lower than during rumination (0.65 eructation/min). HR was higher during grazing that rumination. Because HR is usually linked to metabolic CO2 production intensity, hence influencing the denominator of the CH4:CO2 ratio, further investigation should focus on the quantification of changes in fermentative and metabolic CO2 emissions along the day to estimate total CH4 production more accurately and the relationship between CH4 emissions patterns and post-feeding times. [less ▲]

Detailed reference viewed: 345 (58 ULiège)
Full Text
See detailOUTDOOR MEASUREMENT OF CATTLE METHANE EMISSIONS USING THE EDDY-COVARIANCE TECHNIQUE IN COMBINATION WITH GEOLOCALIZATION DEVICES
Dumortier, Pierre ULiege; Andriamandroso, Andriamasinoro ULiege; Aubinet, Marc ULiege et al

Poster (2016, February)

Methane emissions account for 8% of the EU-15 GHG emissions and livestock generates approximately half of these emissions [1]. In order to improve emissions reporting and properly test mitigation options ... [more ▼]

Methane emissions account for 8% of the EU-15 GHG emissions and livestock generates approximately half of these emissions [1]. In order to improve emissions reporting and properly test mitigation options, techniques for measuring methane emissions from cattle must be developed and adapted to each management system. Among available micrometeorological methods, the use of eddy-covariance is still in its infancy [2] and its relevance and robustness for cattle flux estimation has still to be proved. On one hand, it is well adapted to seasonal grazing systems, is non-invasive, needs little animal handling and allows detection of daily emission patterns. On the other hand, it has the drawback of requiring cattle geo-localization and long periods of measurements (typically one month). In this study, we combined measured CH4 fluxes with a footprint model [3] and cattle positions (GPS devices) over several one-month campaigns at key periods in the grazing season in order to obtain CH4 emissions per cow at herd scale. Accelerometers were also added to the system for behaviour detection, opening the possibility of linking emissions to feeding behaviour. Measurements were performed and are still ongoing at the Dorinne Terrestrial Observatory in 2014/2015. The first campaign provided a mean emission per cow of 65±6 kg CH4.LSU-1.year-1. Cattle emission pattern was tightly linked with behaviour pattern, emissions being higher during and shortly after grazing (i.e. at dawn and dusk). Uncertainties linked to the method will be discussed and quantified (footprint model validity, geo-localization precision, eddy covariance corrections and filtering specificities linked to CH4 measurements). Compilation of data from multiple campaigns will allow quantification of the effects of forage quality, animal weight and lactating state on emissions per cow. [less ▲]

Detailed reference viewed: 107 (24 ULiège)
Full Text
See detailHigh rate monitoring CH4 production dynamics and their link with behavioral phases in cattle
Blaise, Yannick ULiege; Lebeau, Frédéric ULiege; Andriamandroso, Andriamasinoro ULiege et al

in EAAP – 67 th Annual Meeting, Belfast 2016 (2016)

Microbial fermentation in the rumen produces methane (CH4) which is a loss of energy for ruminants and also contributes to global warming. While the respiration chamber is the standard reference for CH4 ... [more ▼]

Microbial fermentation in the rumen produces methane (CH4) which is a loss of energy for ruminants and also contributes to global warming. While the respiration chamber is the standard reference for CH4 emissions quantification, daily CH4 production dynamics can be measured only by steps of 30 min and measurements on pasture are impossible. The alternative method using SF6 as tracer gas can be applied for grazing animals but provides average CH4 production values over at least several hours, making it impossible to measure short term dynamics of rumen CH4 production with changing animal behavior along the day. Newly developed methods using CO2 as internal tracer gas extrapolate CH4 emissions from few short measurements. However, both CO2 and CH4 emissions fluctuate during the day depending on the behavior and the post-feeding times questioning the validity of this method. Therefore, an innovative device was developed to monitor at a high rate CH4 and CO2 emission dynamics in order to investigate the link between CH4 dynamics and the animal behavior on pasture. Preliminary results showed the ability of the device to record differences in CH4:CO2 ratios and eructation frequencies according to the individual and the behavior. Results from complementary experiments in barn with animals fed contrasting diets regarding CH4 production (with and without linseed) and on pasture with different forage allowance will be presented in order to highlight how post-feeding time and grazing behavior impact CO2 and CH4 emission dynamics along the day. [less ▲]

Detailed reference viewed: 72 (26 ULiège)
Full Text
Peer Reviewed
See detailChanges in biting characteristics recorded using the inertial measurement unit of a smartphone reflect differences in sward attributes
Andriamandroso, Andriamasinoro ULiege; Lebeau, Frédéric ULiege; Bindelle, Jérôme ULiege

in Guarino, Marcella; Berckmans, Daniel (Eds.) Precision Livestock Farming '15 (2015, September)

Accurate monitoring of grazing activity at individual cow level would provide useful information to farmers to improve the management of their animals and pastures in intensive dairy systems. Pasture ... [more ▼]

Accurate monitoring of grazing activity at individual cow level would provide useful information to farmers to improve the management of their animals and pastures in intensive dairy systems. Pasture attributes, starting with sward height, influence grazing behaviour and bites characteristics. In an attempt to link sward height to an individual automated detection of biting behaviour, a series of recording sessions of 4×3 days were realized on a ryegrass pasture with two contrasting heights (5 and 15 cm) over the grazing season (from July to October) with 4 dry red-pied cows equipped with the inertial measurement unit (IMU) of a smartphone on a halter, recording acceleration data at 100Hz. The behaviours were video-recorded. The number of grazing bouts performed during grazing trends to increase when the grass is highest. Fourier transforms of acceleration data showed that grazing bouts were characterized by a distinctive acceleration peak which frequency ranged between 1.02Hz and 1.46Hz whatever the sward height. It corresponded to the uprooting of grass frequency in the biting movement when compared with the observation in the video recordings and it could be used to improve automated grazing behaviour detection and to remotely characterize bites. These results show that some bite characteristics are influenced by sward height and automated individual monitoring of grazing behaviour is possible. An extension of this methodology should allow analysing more deeply the grazing behaviour of cattle in order to determine number of bites and possibly to link it to biomass intake. [less ▲]

Detailed reference viewed: 143 (55 ULiège)
Full Text
Peer Reviewed
See detailAccurate monitoring of the rumination behaviour of cattle using IMU signals from a mobile device
Andriamandroso, Andriamasinoro ULiege; Lebeau, Frédéric ULiege; Bindelle, Jérôme ULiege

in Hopkins, A; Collins, R.P.; Fraser, M.D. (Eds.) et al Grassland Science in Europe, 19 (EGF at 50: the Future of European Grasslands) (2014, September)

Improving the monitoring of rumination in cattle could help in assessing of the welfare status and their risk of acidosis. In this work, the monitoring of cattle’s behaviour was performed using the ... [more ▼]

Improving the monitoring of rumination in cattle could help in assessing of the welfare status and their risk of acidosis. In this work, the monitoring of cattle’s behaviour was performed using the inertial measurement unit (IMU) present in smartphones mounted on the neck of cows. The processing of both time and frequency domains of the IMU signals was capable to detect accurately the main behaviours (grazing, rumination and other) and highlight the characteristics of the rumination process. The algorithm for analysis of rumination was more accurate for grazing cattle than for silage-fed cattle in stables. [less ▲]

Detailed reference viewed: 217 (59 ULiège)
Full Text
See detailUse of Inertial Measurement Unit of a Mobile Device to Discriminate Cattle Grazing and Ruminating Behaviours on Pasture
Andriamandroso, Andriamasinoro ULiege; Bindelle, Jérôme ULiege; Lebeau, Frédéric ULiege

in Animal Production in Australia (2014, September)

Precision livestock farming is emerging in the wake of the technological developments in remote sensing and motion monitoring. Tools are developed to allow accurate real time monitoring of the individual ... [more ▼]

Precision livestock farming is emerging in the wake of the technological developments in remote sensing and motion monitoring. Tools are developed to allow accurate real time monitoring of the individual cattle behaviour in a quest to improve the management of pastures. Studies have shown the relevancy of accelerometers in the analysis of behaviour using dedicated devices. Accelerometers are located either close to the mouth or jaw of the animal or on its forehead or neck. Records are usually performed at low frequency (<1Hz) and most studies classify behaviours using neuronal networks or multivariate statistical approaches, with little consideration to the animals’ actual movements. Inertial measurement units (IMU) in consumer mobile devices are specifically developed to record accurately user movements. Besides 3D-accelerometer, they can include 3-D rotational speed sensors, 3-D magnetometers and GPS. Optimised power consumption offers significant autonomy. Data directly acquired from the sensors and IMU signals from build-in proprietary algorithms can be recovered using user-friendly low-cost applications. Moreover, mobile devices can store or communicate information by wireless in real time at high frequency. As movements of cattle are in the same range as humans, this study investigates the relevancy of mobile devices IMU signals to discriminate main behaviours of cattle on pasture. [less ▲]

Detailed reference viewed: 166 (46 ULiège)
Full Text
See detailThe performance of mobile devices' inertial measurement unit for the detection of cattle's behaviors on pasture
Andriamandroso, Andriamasinoro ULiege; Dumont, Benjamin ULiege; Lebeau, Frédéric ULiege et al

Conference (2014, July 21)

Over the past decade, the Precision Livestock Farming (PLF) concept has taken a considerable place in the development of accurate methods for a better management of farm animals, as Precision Agriculture ... [more ▼]

Over the past decade, the Precision Livestock Farming (PLF) concept has taken a considerable place in the development of accurate methods for a better management of farm animals, as Precision Agriculture has done for crop production. Mass consumption mobile devices have nowadays the possibility to record accurately user movements with their Inertial Measurement Unit (IMU). We used iPhone 4S to detect accurately cattle behaviors such as grazing and ruminating with the aim of performing a precision grazing management on the near future. Results showed accuracies ranging between 84% and 100% when detecting these two major behaviors by analyzing recorded raw signals in the time-domain. Ongoing research tries to link these behaviors to different pasture characteristics and performs a refined signal processing analysis for a better monitoring of some possible behavioral changes. [less ▲]

Detailed reference viewed: 114 (40 ULiège)
Full Text
See detailAnalyzing relationships between cattle grazing behavior and pasture attributes using the inertial measurement unit of a mobile phone.
Andriamandroso, Andriamasinoro ULiege; Lebeau, Frédéric ULiege; Bindelle, Jérôme ULiege

Poster (2014, February 07)

The recent technological developments are boosting the opportunities of accurate method to monitor resource use efficiency in agriculture and in their wake, precision livestock farming (PLF) has ... [more ▼]

The recent technological developments are boosting the opportunities of accurate method to monitor resource use efficiency in agriculture and in their wake, precision livestock farming (PLF) has experienced huge developments over the past decade. These developments focus on the optimization of individual performances of farm animals as opposed to herd management. The aim of this paper is to explore a method to detect accurately and to analyze changes in cattle's behaviors on pasture during grazing time using signals from the inertial measurement unit (IMU) of mobile devices as a possible tool to manage individual grazing behavior. Commercial iPhones or iPods, which include a 3-axis accelerometer, a gyroscope and a GPS sensor, are fitted on a halter and placed on the neck of grazing cows. The acquired IMU data are recovered using an open source application (Sensor Data, Wavefrontlabs) and analyzed in a “white-box” model of the cows’ movements. First results using time-domain analysis allowed the detection of grazing behaviors showed accuracies ranging between 84% and 96%, attesting the relevancy of the method. Refined signal processing method will improve the detection but will also inform more about the relative link between the behaviors and the pasture attributes such as sward height, composition and nutritive value. [less ▲]

Detailed reference viewed: 129 (35 ULiège)