Emanuela Tullo

An innovative approach to predict the growth in intensive poultry farming

Chicken weight provides information about growth and feed conversion of the flock.We record and analyse broiler vocalisations under normal farm conditions.We find a significant correlation between frequency of sounds and weight of the birds.The more the birds grow, the lower the frequency of the sounds emitted by the animals.Young chicks vocalise at high frequency under non-stress condition. Chicken weight provides information about growth and feed conversion of the flock in order to identify deviations from the expected homogeneous growth trend of the birds. This paper proposes a novel method to automatically measure the growth rate of broiler chickens by sound analysis.Through the application of process engineering, Precision Livestock Farming (PLF) can combine audio and video information into on-line automated tools that can be used to control, monitor and model the behaviour, health and production of animals and their biological response.The aim of this study was to record and analyse broiler vocalisations under normal farm conditions, to identify the relation between animal sounds and their weight. Recordings were made at regular intervals, during the entire life of birds, in order to evaluate the variation of frequency and bandwidth of the sounds emitted by the animals.Two experimental trials were carried out in an indoor reared broiler farm; the audio recording procedures lasted for 38days. The recordings were made, in an automated, non-invasive and non-intrusive way and without disturbing the animals in to the broiler house. Once a week, 50 birds were selected at random and their weight recorded in order to follow the growth trend in the birds.Sound recordings were manually analysed and labelled using the Adobe� Audition� CS6 software.Analysing the sounds recorded, it was possible to find a significant correlation (P<0.001) between the frequencies of the vocalisations recorded and the weight of the broilers.The results explained how the frequency of the sounds emitted by the animals was inversely proportional to the age and to the weight of the broilers; the more they grow, the lower the frequency of the sounds emitted by the animals.This preliminary study, conducted in an indoor reared broiler farm, shows how this method based on the identification of specific frequencies of the sounds, linked to the age and to the weight of the birds, might be used as an early warning method/system to evaluate the health and welfare status of the animals at farm level. This is the basis for a further development of an automated growth monitoring tool.

Discerning Pig Screams in Production Environments

Pig vocalisations convey information about their current state of health and welfare. Continuously monitoring these vocalisations can provide useful information for the farmer. For instance, pig screams can indicate stressful situations. When monitoring screams, other sounds can interfere with scream detection. Therefore, identifying screams from other sounds is essential. The objective of this study was to understand which sound features define a scream. Therefore, a method to detect screams based on sound features with physical meaning and explicit rules was developed. To achieve this, 7 hours of labelled data from 24 pigs was used. The developed detection method attained 72% sensitivity, 91% specificity and 83% precision. As a result, the detection method showed that screams contain the following features discerning them from other sounds: a formant structure, adequate power, high frequency content, sufficient variability and duration.

Early recognition of bovine respiratory disease in calves using automated continuous monitoring of cough sounds

Abstract Bovine respiratory disease (BRD) complex in calves impairs health and welfare and causes severe economic losses for the Stockperson. Early recognition of BRD should lead to earlier veterinary (antibiotic/anti-inflammatory) treatment interventions thereby reducing the severity of the disease and associated costs. Coughing is one of the clinical manifestations of BRD. It is believed that by automatically and continuously monitoring the sounds within calf houses, and analysing the coughing frequency, early recognition of BRD in calves is possible. Therefore, the objective of the present study was to develop an automated calf cough monitor and examine its potential as an early warning system for BRD in artificially reared dairy calves. The coughing sounds of 62 calves were continuously recorded by a microphone over a three-month period. A sound analysis algorithm was developed to distinguish calf coughs from other sounds (e.g. mechanical sounds). During the sound recording period the health of the calves was assessed and scored periodically per week by a trained human observer. Calves presenting with BRD received antibiotic and/or anti-inflammatory treatment and the dates of treatment were recorded. This treatment date reference served as a comparison for the investigation of whether an increase in coughing frequency could be related to calves developing BRD. The calf cough detection algorithm achieved 50.3% sensitivity, 99.2% specificity and 87.5% precision. Four out of five periods, where coughing frequency was observed to be increased, coincided with the development of BRD in more than one calf. This period of increased coughing frequency was always observed before the calves were treated. Therefore, the calf cough monitor has the potential to identify early onset of BRD in calves.

Application note: Labelling, a methodology to develop reliable algorithm in PLF

Abstract Automatic animal monitoring through Precision Livestock Farming (PLF) tools is a method to support farmers in achieving farm sustainability. The development of PLF systems requires close interdisciplinary collaboration between sector experts, farmers, animal scientists and bio-engineers. Labelling is a key activity in the development of reliable algorithm to be included in PLF tools. It is a set of procedures that animal experts must embark to precisely define and interpret detailed variations in measured field signals. This application note will describe the fundamental aspects of sound and image labelling and how this has enabled the engineering of useful automated PLF systems.

Sound analysis to model weight of broiler chickens

ABSTRACT The pattern of body weight gain during the commercial growing of broiler chickens is important to understand growth and feed conversion ratio of each flock. The application of sound analysis techniques has been widely studied to measure and analyze the amplitude and frequency of animal sounds. Previous studies have shown a significant correlation (P ≤ 0.001) between the frequency of vocalization and the age and weight of broilers. Therefore, the aim of this study was to identify and validate a model that describes the growth rate of broiler chickens based on the peak frequency of their vocalizations and to explore the possibility to develop a tool capable of automatically detecting the growth of the chickens based on the frequency of their vocalizations during the production cycle. It is part of an overall goal to develop a Precision Livestock Farming tool that assists farmers in monitoring the growth of broiler chickens during the production cycle. In the present study, sounds and body weight were continuously recorded in an intensive broiler farm during 5 production cycles. For each cycle the peak frequencies of the chicken vocalizations were used to estimate the weight and then they were compared with the observed weight of the birds automatically measured using on farm automated weighing devices. No significant difference is shown between expected and observed weights along the entire production cycles; this trend was confirmed by the correlation coefficient between expected and observed weights (r = 96%, P value ≤ 0.001). The identified model used to predict the weight as a function of the peak frequency confirmed that bird weight might be predicted by the frequency analysis of the sounds emitted at farm level. Even if the precision of the weighing method based on sounds investigated in this study has to be improved, it gives a reasonable indication regarding the growth of broilers opening a new scenario in monitoring systems in broiler houses.

The influence of microclimate on the development of foot pad dermatitis in broilers

Footpad dermatitis and lameness are a major welfare concern in broiler chicken farming. In general, footpad lesions are linked to poor environmental conditions. Ulcers that arise from advanced lesions can negatively affect the gait of the birds, with effects on the animal welfare, including, in the worst cases, inability to reach the feed or water. In this study, the degree of footpad dermatitis and lameness was manually scored on four broiler farms across Europe, as part of an EU-wide welfare assessment programme (Welfare Quality® protocol). Assessment of animal welfare is typically based on manual scoring, which requires a lot of trained manpower/labour. Precision Livestock Farming (PLF) can combine information technologies into on-line automated tools that can be used to control, monitor and model the behavior of animals and their biological response without stressing, disturbing or handling the animals. The association between the PLF and the Welfare Quality® protocol was investigated to assess whether animal welfare could be better ensured if they were closely monitored with state of the art technology that gives rapid feedback to the farmer. Thus, the aim of this study was to find the association between environmental predisposing factors, measured continuously (such as the indoor temperature and humidity) and leg problems, scored manually during the welfare assessment procedure, in order to find an automated prediction system to detect those lesions. Even if genetics is a heavy predisposing factor for leg disorders, environmental condition could trigger the presence of lesions. Indeed, immobility on litter of poor quality might cause footpad dermatitis affecting the gait of birds. The association between automated control of the environmental conditions and the welfare assessments could be the basis for the development of models and algorithms capable to automatically detect thresholds above which lesions are mostly probable.

Pedigree-based analysis of genetic variability in the registered Normande cattle breed in Colombia

Genetic variability and structure of the population were studied in 7949 registered Normande cattle in Colombia. The pedigree was deep with 18 traced generations, but there were some incomplete genealogical information for the cattle born in the more distant past. The average number of complete and equivalent complete generations was 2.42 and 5.21, respectively. The average pedigree completeness index for five generations was 0.62, which increased over time, and a significant difference between sexes was found (males: 0.82 ± 0.11; females: 0.62 ± 0.38). The average generation interval was 7.57 years. The number of founders, effective founders, ancestors, and founder genomes were 575, 115, 47, and 22.22, respectively, which suggests that an unequal use of founders and a random loss of alleles from founders occurred over time. The level of inbreeding was 0.019 and increased to 0.023, when the inbreeding coefficient was calculated by assigning inbreeding of contemporaries to founders. These levels of inbreeding lead to an effective population size of 138.5 and 117.9 and to a 0.36% and 0.42% rate of inbreeding, respectively. Out of 267 herds with more than five registered breeding animals, only one nucleus herd was present, whereas 117 and 119 were classified as multiplier and commercial herds, respectively. About 92% of calves were sired by French bulls; but the use of Colombian bulls for breeding is increasing. The Colombian Normande breed is at an acceptable level of genetic variability, although some losses of founder alleles have occurred. As the level of inbreeding has been increasing, inbreeding and mating strategies should be monitored in order to maintain the genetic diversity of the breed.

Acoustic Analysis of Some Characteristics of Red Deer Roaring

Different strategies have been adopted to track and monitor red deer (Cervus elaphus) populations according to different habitats and ecosystems. The population census techniques usually carried out are time consuming and involve lot of manpower. A method that relies on individual animal signs like acoustic indices could be useful to support the wildlife management, since vocalisations can encode and transmit a variety of biologically significant information. The present study considered 460 roars recorded from 14 adult deers, from five to eight years old. Recordings were performed in five different locations of northern-central Italy. The acoustic spectrum of each roar was analysed in order to extract its main features, namely: the fundamental frequency (F0), the peak frequency (PF), the sound length (SL) and 24 frequency bins of 174.3 Hz, representing the sound distribution between 50 and 4233.2 Hz (F1 to F24). Statistical analyses showed that individuality and age of animals were significant on F0 (P<0.001), PF (P<0.001) and SL (P<0.001). Results also showed a correlation among the 24 F-variables of roars emitted by deer of similar age (r>0.90; P<0.001), indicating that age could influence the spectral features of roaring. The roaring frequency variables appear to be indicators of the individuality of male deer, even if the strong influence of age on the emitted sounds could compromise the reliability of the method over long periods of time.

Genetic Parameters for Milk Yield and Persistency in Carora Dairy Cattle Breed Using Random Regression Model

In tropical environments, lactation curves with lower peaks and higher persistency (PS) might be desirable from both an economical and a physiological point of view. The objective of this study was to obtain genetic parameters for test day (TD) yields, and PS for the tropical breed Carora and to compare these with results from a standard 305-d-milk yield animal model. Four random regression models (RRM) were used on a dataset composed of 95,606 TD records collected in Venezuela and tested to find the best fitting the data. Estimated daily heritabilities for milk yields ranged from 0.21 to 0.30, with the lowest values around the peak of lactation. Lactation repeatabilities ranged from 0.50 to 0.56. Correlations between the breeding values obtained with the RRM and the lactation model currently used in Venezuela [single trait Animal Model (stAM)] are quite high and positive (Pearson correlation=0.71 and Spearman correlation=0.72). Correlations between PS and 305-d-milk yield estimated breeding values (EBV) ranged from -0.18 (PS as the deviation of daily productions in the interval 50-279 days in milk from a point at the end of lactation) to 0.52 (PS as EBV difference between the second and the first stage of lactation). The use of PS indexes accounting for milk yield may allow the selection of individuals able to express their potential genetic values in tropical environment, without incurring in excessive heat stress losses.