Figure 1 - available via license: Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International
Content may be subject to copyright.
Screenshot of Adobe ® Audition TM CS6 software. Spectrograms and frequency analysis of an extracted sound.
Source publication
In this study, we describe the monitoring of young broiler chicken vocalisation, with sound recorded and assessed at regular intervals throughout the life of the birds from day 1 to day 38, with a focus on the first week of life. We assess whether there are recognisable, and even predictable, vocalisation patterns based on frequency and sound spect...
Contexts in source publication
Context 1
... Adobe ® Audition TM CS6, a number of discrete sound 'groups' were identified and analysed using time (x-axis) and frequency (y-axis) for further statistical comparisons. A fast fourier transform (FFT) was used to perform the frequency analyses using a Hamming window with a FFT dimension of 256 (Figure 1). Figure 1 shows the spectrogram of a labelled vocalisation. ...
Context 2
... fast fourier transform (FFT) was used to perform the frequency analyses using a Hamming window with a FFT dimension of 256 (Figure 1). Figure 1 shows the spectrogram of a labelled vocalisation. The time is reported on the x-axis and the frequency on the y-axis. ...
Context 3
... results in capturing sounds within the broiler house where the chicks tended to cluster ‘ in groups ’ classi fi ed as house sounds (HS). At the same time as the sound recordings were being made, video recordings were acquired by placing a digital video camera on a low-level tripod focussed on the area where the birds were most active and in the locality of the microphones. After each period of continuous recording, three chicks, chosen at random, were moved into an enclosed ‘ shielded recording area ’ (30 cm high box with an area of 0.8 m 2 ), in order to collect individual bird sounds of ‘ isolated ’ chicks by shielding the microphone from background environmental noise. The chicks were individually placed into the separation box at times 0 (chick 1), 1 min later (chick 2) and 2 min later (chick 3); 5 min of recording box sounds (BS) were initiated when the fi rst chick was placed in the box. Simultaneously with the BS audio recordings video recordings were made, positioning the video of the chicks inside the box, and also of chicks in the area just outside the box. After 5 min of recording, the barrier was removed and the chicks were returned to the fl ock. The fi nal sound ‘ library ’ consisted of 27 h 24 min of sound recordings for trial 1 and 27 h 56 min of sound recordings for trial 2. It was decided to analyse and manually label the vocalisations recorded with MIC 1 (bird focussed) due to the higher quality of the sounds compared with the ones recorded with MIC 2 (background focussed). In this study, the sounds (HS and BS) recorded during Day 1 and Day 5 in both trials have been analysed. Day 1 and Day 5 were chosen in order to provide a time interval appropriate to examine the difference of the sounds emitted within the fi rst week of the birds life. Sound recordings were manually analysed of fl ine and labelled using sound analysis software: Adobe ® Audition TM CS6. Sound labelling involved the extraction and classi fi cation of both individual ‘ isolated ’ animal sounds (BS) and general sounds coming from the whole fl ock (HS). Analysis examined amplitude and frequency of the sound signals in audio fi les, each fi le being manually labelled using a procedure based on acoustic analysis combined with visual spectral analysis, used to extract recognisably distinct and characteristic sound patterns from the entire recording fi le. Every hour long digital recording was cut in shorter labelled fi les of 10 min duration in order to facilitate the sound analysis and the labelling procedure. The sound analysis was divided into two different phases. First, the fi le was examined (lis- tened to with high frequency response headphones) in its entirety in order to recognise the regions of the recording with the clearest sounds. During the ‘ listen through ’ , the regions of the recording with the clearest sounds were then digitally marked ( fl agged) in order to classify different types of sound. The methodology for the labelling procedure and the sound analysis is that described by (Marx et al., 2001). The labelling procedure was carried out of fl ine, identifying those sounds that the operator classi fi ed as signi fi cant vocalisation sounds through the combination of auditive analysis (listening with headphones) and the visual observation of the spectrogram of the sounds corresponding to each sound ‘ group ’ (Ferrari et al., 2008). Through Adobe ® Audition TM CS6, a number of discrete sound ‘ groups ’ were identi fi ed and analysed using time (x-axis) and frequency (y-axis) for further statistical comparisons. A fast fourier transform (FFT) was used to perform the frequency analyses using a Hamming window with a FFT dimension of 256 (Figure 1). Figure 1 shows the spectrogram of a labelled vocalisation. The time is reported on the x-axis and the frequency on the y-axis. Bright areas indicate sounds with high energy. The small box on the right shows the frequency analysis of the marked sound on the left. The mean duration, the mean interval and the number of repetitions of each kind of vocalisation were collected. For both HS and BS, the peak frequency (PF = representing the frequency of maximum power) was manually extracted. The frequency range was band pass fi ltered between 1000 and 13 000 Hz. The lower frequency limit was set at 1000 Hz to remove the low frequency background noise and the upper limit was set at 13 000 Hz to cut off high frequency noise and also because broilers are sensitive to a frequency range of about 60 to 11 950 (Appleby et al., 1992; Tefera, 2012). Video and sound recordings were synchronised during the labelling procedure in order to link the behaviours to the sounds emitted by the animals. Statistical analysis was performed using statistical software SAS 9.3. The difference in PF of HS and BS recorded during Day 1 and Day 5 were tested using a paired t-test in order to evaluate whether there were statistically signi fi cant changes in vocalisation PF related to different days and situations (isolated/in group). Paired sample t-tests were made to compare the PF of vocalisations emitted by the chicks in six speci fi c situations: a) BS collected in Day 1 and in Day 5 (BS1-BS5). b) HS collected in Day 1 and in Day 5 (HS1-HS5). c) BS and HS collected in Day 1 (BS1-HS1). d) BS and HS collected in Day 5 (BS5-HS5). e) BS collected in Day 1 and HS collected in Day 5 (BS1-HS5). f) BS collected in Day 5 and HS collected in Day 1 (BS5-HS1). Statistical analysis of sounds was performed using the clearest vocalisations (the loudest, the ‘ clearest ’ and with the highest energy) found during the labelling procedure of recordings made on Day 1 and Day 5. The fi nal dataset consisted of 60 BS (isolated chicks) sound fi les, and 136 sound fi les from HS. The correlations between BS and HS were evaluated to identify whether chicks emitted speci fi c sounds on a speci fi c day (1 or 5) or speci fi c sounds during a stress situation (isolated or in group). A further comparison among the different BS sounds was fi rst performed analysing the spectrogram of each sounds (visual analysis) and then using the PDIFF (differences between least squares means) option in the GLM procedure of SAS to verify their similarity/ dissimilarity (SAS User ’ s Guide, ...
Context 4
... results in capturing sounds within the broiler house where the chicks tended to cluster ‘ in groups ’ classi fi ed as house sounds (HS). At the same time as the sound recordings were being made, video recordings were acquired by placing a digital video camera on a low-level tripod focussed on the area where the birds were most active and in the locality of the microphones. After each period of continuous recording, three chicks, chosen at random, were moved into an enclosed ‘ shielded recording area ’ (30 cm high box with an area of 0.8 m 2 ), in order to collect individual bird sounds of ‘ isolated ’ chicks by shielding the microphone from background environmental noise. The chicks were individually placed into the separation box at times 0 (chick 1), 1 min later (chick 2) and 2 min later (chick 3); 5 min of recording box sounds (BS) were initiated when the fi rst chick was placed in the box. Simultaneously with the BS audio recordings video recordings were made, positioning the video of the chicks inside the box, and also of chicks in the area just outside the box. After 5 min of recording, the barrier was removed and the chicks were returned to the fl ock. The fi nal sound ‘ library ’ consisted of 27 h 24 min of sound recordings for trial 1 and 27 h 56 min of sound recordings for trial 2. It was decided to analyse and manually label the vocalisations recorded with MIC 1 (bird focussed) due to the higher quality of the sounds compared with the ones recorded with MIC 2 (background focussed). In this study, the sounds (HS and BS) recorded during Day 1 and Day 5 in both trials have been analysed. Day 1 and Day 5 were chosen in order to provide a time interval appropriate to examine the difference of the sounds emitted within the fi rst week of the birds life. Sound recordings were manually analysed of fl ine and labelled using sound analysis software: Adobe ® Audition TM CS6. Sound labelling involved the extraction and classi fi cation of both individual ‘ isolated ’ animal sounds (BS) and general sounds coming from the whole fl ock (HS). Analysis examined amplitude and frequency of the sound signals in audio fi les, each fi le being manually labelled using a procedure based on acoustic analysis combined with visual spectral analysis, used to extract recognisably distinct and characteristic sound patterns from the entire recording fi le. Every hour long digital recording was cut in shorter labelled fi les of 10 min duration in order to facilitate the sound analysis and the labelling procedure. The sound analysis was divided into two different phases. First, the fi le was examined (lis- tened to with high frequency response headphones) in its entirety in order to recognise the regions of the recording with the clearest sounds. During the ‘ listen through ’ , the regions of the recording with the clearest sounds were then digitally marked ( fl agged) in order to classify different types of sound. The methodology for the labelling procedure and the sound analysis is that described by (Marx et al., 2001). The labelling procedure was carried out of fl ine, identifying those sounds that the operator classi fi ed as signi fi cant vocalisation sounds through the combination of auditive analysis (listening with headphones) and the visual observation of the spectrogram of the sounds corresponding to each sound ‘ group ’ (Ferrari et al., 2008). Through Adobe ® Audition TM CS6, a number of discrete sound ‘ groups ’ were identi fi ed and analysed using time (x-axis) and frequency (y-axis) for further statistical comparisons. A fast fourier transform (FFT) was used to perform the frequency analyses using a Hamming window with a FFT dimension of 256 (Figure 1). Figure 1 shows the spectrogram of a labelled vocalisation. The time is reported on the x-axis and the frequency on the y-axis. Bright areas indicate sounds with high energy. The small box on the right shows the frequency analysis of the marked sound on the left. The mean duration, the mean interval and the number of repetitions of each kind of vocalisation were collected. For both HS and BS, the peak frequency (PF = representing the frequency of maximum power) was manually extracted. The frequency range was band pass fi ltered between 1000 and 13 000 Hz. The lower frequency limit was set at 1000 Hz to remove the low frequency background noise and the upper limit was set at 13 000 Hz to cut off high frequency noise and also because broilers are sensitive to a frequency range of about 60 to 11 950 (Appleby et al., 1992; Tefera, 2012). Video and sound recordings were synchronised during the labelling procedure in order to link the behaviours to the sounds emitted by the animals. Statistical analysis was performed using statistical software SAS 9.3. The difference in PF of HS and BS recorded during Day 1 and Day 5 were tested using a paired t-test in order to evaluate whether there were statistically signi fi cant changes in vocalisation PF related to different days and situations (isolated/in group). Paired sample t-tests were made to compare the PF of vocalisations emitted by the chicks in six speci fi c situations: a) BS collected in Day 1 and in Day 5 (BS1-BS5). b) HS collected in Day 1 and in Day 5 (HS1-HS5). c) BS and HS collected in Day 1 (BS1-HS1). d) BS and HS collected in Day 5 (BS5-HS5). e) BS collected in Day 1 and HS collected in Day 5 (BS1-HS5). f) BS collected in Day 5 and HS collected in Day 1 (BS5-HS1). Statistical analysis of sounds was performed using the clearest vocalisations (the loudest, the ‘ clearest ’ and with the highest energy) found during the labelling procedure of recordings made on Day 1 and Day 5. The fi nal dataset consisted of 60 BS (isolated chicks) sound fi les, and 136 sound fi les from HS. The correlations between BS and HS were evaluated to identify whether chicks emitted speci fi c sounds on a speci fi c day (1 or 5) or speci fi c sounds during a stress situation (isolated or in group). A further comparison among the different BS sounds was fi rst performed analysing the spectrogram of each sounds (visual analysis) and then using the PDIFF (differences between least squares means) option in the GLM procedure of SAS to verify their similarity/ dissimilarity (SAS User ’ s Guide, ...
Similar publications
Natural Animal Sound Spectrum Characterization based on Fourier analysis is a undamental scientific study of the spectrum of natural animal sounds that can be used as a stimulator of growth and productivity in food intensification. The results of characterization are very useful for adding scientific treasures in the field of biophysics, especially...
Citations
... In contrast to the controlled settings of closed environments in previous studies, real-world conditions in commercial farms introduce various ambient noises 41) . Recognizing sneezing as a clinical indicator of respiratory diseases, an algorithm was devised and implemented to identify sneezing sounds amidst multiple noise sources. ...
... Nevertheless, calves also vocalise to communicate in neutral stress environments, intra-and interspecies. In farm animals: cattle [144], sheep [145], goats [146], horses [147], pigs [148], and chickens [149], the sound vocalisation pattern, waveform, or fundamental frequencies have been evaluated with microphones, video cameras, sound analysis software, and specific algorithms. Green et al. [150] used spectrographic analysis of dairy cows' vocalisations upon cow-calf separation to assess emotional stress. ...
Precision livestock farming (PLF) research is rapidly increasing and has improved farmers’ quality of life, animal welfare, and production efficiency. PLF research in dairy calves is still relatively recent but has grown in the last few years. Automatic milk feeding systems (AMFS) and 3D accelerometers have been the most extensively used technologies in dairy calves. However, other technologies have been emerging in dairy calves’ research, such as infrared thermography (IRT), 3D cameras, ruminal bolus, and sound analysis systems, which have not been properly validated and reviewed in the scientific literature. Thus, with this review, we aimed to analyse the state-of-the-art of technological applications in calves, focusing on dairy calves. Most of the research is focused on technology to detect and predict calves’ health problems and monitor pain indicators. Feeding and lying behaviours have sometimes been associated with health and welfare levels. However, a consensus opinion is still unclear since other factors, such as milk allowance, can affect these behaviours differently. Research that employed a multi-technology approach showed better results than research focusing on only a single technique. Integrating and automating different technologies with machine learning algorithms can offer more scientific knowledge and potentially help the farmers improve calves’ health, performance, and welfare, if commercial applications are available, which, from the authors’ knowledge, are not at the moment.
... Also, the chicks, as hatched were reared in three consecutive batches of flock age 28, 29 and 31 weeks. Vocalization (emitting of calling sounds) by higher percentage of birds at 4 d compared to 35 d was linked to increased motivation to seek social reinstatement in early life (Heiblum et al. 1998;Fontana et al. 2016). The longer TI durations observed at 35 d were associated with the fact that a sharp increase in duration of TI has been reported from 5 d (Heiblum et al. 1998). ...
Development of quality welfare assessment protocols is a necessary step towards achieving high broiler welfare standards. Rapid growth rate and highly intensive commercial production systems have been highly associated with poor welfare indicated by mainly leg deformities, high stress levels and increased fear responses. Stress response in broilers is characterised by increased corticosterone and heterophil-to-lymphocyte ratio especially under heat stress, high light intensity, high stocking density, and an unenriched environment. Rearing environment, genotypes, high light intensity and human handling highly influence fear responses as proved during tonic immobility, open field, novel enrichment, and avoidance distance tests. Lameness which is usually visually assessed by a gait score scale remains an undisputable indicator of poor welfare in broiler production due to its effects on mobility and association with pain. Other leg problems including footpad dermatitis and hock burn also remain significant and they are highly associated with fast growth, high stocking density, poor litter quality, and poor or non-enriched production systems. Litter management and good ventilation are necessary to ensure good plumage conditions, reduction in ammonia emissions thereby promoting the well-being of broilers. Generally, broilers should be motivated and able to exhibit natural behaviours without straining including feeding, drinking, walking, and stretching thereby enhancing bird health, performance, production, and consumer satisfaction. Using a systematic approach, the important welfare parameters including stress, fear response, leg problems, plumage condition, environment, and behaviour are intensively discussed to explore the latest insights of broiler chickens’ welfare.
... A research on an intense broiler farm revealed that the peak frequency of the noises produced by broiler chickens reduced significantly throughout the course of the birds' whole lives as they grew (Fontana et al. 2015 and [21][22] . Additionally, a broiler weight prediction model was developed and verified using a peak frequency analysis of the birds' vocalisations [23] . Thus, vocalisations might be used to help with the autonomous monitoring of broiler chicken development. ...
... In [12], there is a wide state of the art about vocalisations of different farm-raised animals. Vocalisations, such as screams, should be identified since they are usually due to pain or stressful situations [17], but the general structure and behaviour of farm-raised animals should also be known (e.g., cattle [18], chickens [19], among others). Recently, several research groups have started working on the development of vocalisation identification algorithms, which integrate feature extraction together with machine learning algorithms [20], in order to identify in real-time the vocalisations in a real operating environment, such as a farm. ...
... This study is focused on the acoustic analysis and feature identification in the framework of poultry farms. Several studies have been conducted in this area, as the one in [19], where mean duration, number of call repetitions and range peak frequency describe chicken vocalisations to find some patterns depending on the age of the birds, and also considering whether the birds are alone or in a group. Other researchers have worked with the distinction of healthy from infected chickens using sparse decomposition of audio spectrograms [21], and ref [22] have analysed the following features: root mean square, power, energy, absolute extremum, intensity, shimmer, jiter, harmonic to noise ratio, pitch, formant F1-F4 and power spectral density 1-39 to automatically detect stress in laying hens. ...
The concentration of CO2 is relatively large in poultry farms and high accumulations of this gas reduce animal welfare. Good control of its concentration is crucial for the health of the animals. The vocalizations of the chickens can show their level of well-being linked to the presence of carbon dioxide. An audio recording system was implemented and audio raw data was processed to extract acoustical features from four cycles of forty days, three of them from the same farm. This research aims to find the most relevant acoustic features extracted from the broiler’s calls that are related to the CO2 concentration and that could help to automate procedures. The results are encouraging since MFCC 6, 9, 4 and 3 are the most important features that relate the vocalizations of the chickens to the gas concentration, furthermore there is a clear and more similar representativeness trend during birds’ life period from day 15 to day 40.
... This is confirmed by the lower frequency of vocalizations on day 11 as compared to day 1. Furthermore, it has been suggested that at a very young age, vocalizations are mainly performed to seek social contact (68). Thus, our results indicate a higher social reinstatement in EE than in NE chickens rather than fear of a predator (68). ...
... Furthermore, it has been suggested that at a very young age, vocalizations are mainly performed to seek social contact (68). Thus, our results indicate a higher social reinstatement in EE than in NE chickens rather than fear of a predator (68). Interestingly, this response is already present on day 1 when the chickens had a relatively short-term experience with the dark brooder. ...
... A higher frequency of vocalizations was observed for HH as compared to OH chickens in the novel environment. As explained above, it has been suggested that at a very young age, vocalizations are mainly performed to seek social contact (68). Thus, on day 1, the higher frequency of vocalizations in HH chickens may indicate a higher motivation for social reinstatement in HH as compared to OH chickens, which is in line with a previous study comparing on-farm with hatchery hatched broiler chickens (44), but was not verified in a later study by the same group (45). ...
This study aimed to identify whether early-life conditions in broiler chickens could affect their behavior and welfare, and whether or not this was associated with an altered gut microbiome composition or diversity. Broilers were tested in a 2 x 2 factorial design with hatching conditions [home pen (OH) or at the hatchery (HH)] and enrichment (dark brooder (EE) or no brooder (NE) until 14 days of age) as factors (N = 6 per treatment combination). Microbiota composition was measured in the jejunum on days (d) 7, 14, and 35 and in pooled fecal samples on day 14. A novel environment test (NET) was performed on days 1 and 11, and the behavior was observed on days 6, 13, and 33. On day 35, composite asymmetry was determined and footpad dermatitis and hock burn were scored. In their home pen, HH showed more locomotion than OH (P = 0.05), and NE were sitting more and showed more comfort behavior than EE at all ages (P <0.001 and P = 0.001, respectively). On days 6 and 13 NE showed more eating and litter pecking while sitting, but on day 33 the opposite was found (age*enrichment: P = 0.05 and P <0.01, respectively). On days 1 and 11, HH showed more social reinstatement in the NET than OH, and EE showed more social reinstatement than NE (P <0.05). Composite asymmetry scores were lower for EE than NE (P <0.05). EE also had less footpad dermatitis and hock burn than NE (P <0.001). Within OH, NE had a more diverse fecal and jejunal microbiome compared to EE on day 14 (feces: observed richness: P = 0.052; jejunum: observed richness and Shannon: P <0.05); the principal component analysis (PCA) showed differences between NE and EE within both HH and OH in fecal samples on day 14, as well as significant differences in bacterial genera such as Lactobacillus and Lachnospiraceae (P <0.05). On day 35, PCA in jejunal samples only showed a trend (P = 0.068) for differences between NE vs. EE within the OH. In conclusion, these results suggest that especially the dark brooder affected the behavior and had a positive effect on welfare as well as affected the composition and diversity of the microbiome. Whether or not the behavior was modulated by the microbiome or vice versa remains to be investigated.
... Vocalization is an important indicator to evaluate poultry welfare, and it can reflect the feeding, growth and health of poultry, among other information (Fontana et al., 2016;Du et al., 2020;Zong et al., 2021). For example, Lee et al. (2015) used three binary-classifier support vector machines (SVMs) to detect the stress from the changes in the sounds of poultry and classified the changes into subsidiary sound types. ...
Newcastle disease (ND) is a common disease in poultry that has a great impact on poultry health and production. ND has destructive effects on the respiratory system, such as altering the acoustic features of bird vocalizations. For this reason, this research proposed a new method, the deep poultry vocalization network (DPVN), for the early detection of ND based on poultry vocalization. The method combined multiwindow spectral subtraction and high-pass filtering to reduce the influence of noise. In order to detect poultry vocalizations automatically, a multiple subband poultry vocalization endpoint detection method was proposed in this paper. The performance of the detection method was evaluated using the intersection-over-union (IOU) between the detected vocalizations and ground truth vocalizations. The recall of the detection method was 95.11%, and the precision was 96.54%. The audio features of poultry vocalizations are extracted by sound technology and used as the input of a deep learning network to recognize the vocalizations of poultry with Newcastle disease. Five different models were compared in the experiments. The method used in this paper achieves the best performance and the highest accuracy, recall and F1-score of 98.50%, 96.60% and 97.33%, respectively. The accuracies within the first, second, third and fourth days after infection were 82.15%, 90.00%, 93.60% and 98.50%, respectively. The experimental results show that the method proposed in this paper can be used to detect Newcastle disease in the early stage. It will be significant for improving animal welfare and the automated monitoring of poultry production.
... To name a few, such solutions are RFID sensors, internal sensors for temperature monitoring, behaviour monitoring, and control. There are multiple researchers working towards sound [40,41] and video [42] analysis in the poultry sector. Future technology also tends to develop towards prediction [43,44] rather than reactive response., this mostly includes health status and respiratory problems. ...
Internet of things provides ways to obtain information about farm production; however, the more data there is, the harder it is to determine the correct way to process these data. The solutions on the market are aimed specifically at gathering data, rather than processing and analyzing them. Poultry farming is one of the fields, where the application of Industry 4.0 principles is becoming a necessity, especially in the case of greenhouse gas control. Minimum standards and rules in the poultry management are regulated by EU Directives and required parameters must be ensured at all times, therefore, real-time environmental monitoring must be performed. The only practically viable approach is to automate data gathering using appropriate sensors, which is only possible if a standardized data structure model is defined.
In this research the Cyber-Physical Model is the proposed as a basis to development of smart poultry farm management system that is adjustable to particular production needs. Three main data groups are defined – necessary data to ensure requirements of EU Directives, farm monitoring data for business analysis and optimization, and additional data that can influence overall poultry farm management. The proposed data set was implemented into the existing infrastructure of a Baltic poultry farm. Multiple CO2 (carbon dioxide) and NH3 (ammonia) sensors were installed in order to gather data, measurements of which previously were taken manually by the farm’s staff. The solution was developed on centralized cloud-based data processing system, where MQTT Broker was used for security measures. The processed data is used by the decision support system with the aim to define optimal feeding and housing.
... The growth of the poultry chickens is also analyzed by observing the peak frequencies made by the chicken. The peak frequency decreased with the increase in the growth of the poultry chicken [22,23] and hence provides the detection of the growth rate of the poultry chicken. Disease diagnoses can also be analyzed through sound analysis. ...
The poultry industry contributes majorly to the food industry. The demand for poultry
chickens raises across the world quality concerns of the poultry chickens. The quality measures in
the poultry industry contribute towards the production and supply of their eggs and their meat.
With the increasing demand for poultry meat, the precautionary measures towards the well-being
of the chickens raises the concerns of the industry stakeholders. The modern technological advancements
help the poultry industry in monitoring and tracking the health of poultry chicken.
These advancements include the identification of the chickens’ sickness and well-being using video
surveillance, voice observations, ans feces examinations by using IoT-based wearable sensing devices
such as accelerometers and gyro devices. These motion-sensing devices are placed over a chicken
and transmit the chicken’s movement data to the cloud for further analysis. Analyzing such data
and providing more accurate predictions about chicken health is a challenging issue. In this paper,
an IoT based predictive service framework for the early detection of diseases in poultry chicken is
proposed. The proposed study contributes by extending the dataset through generating the synthetic
data using Generative Adversarial Networks (GAN). The experimental results classify the sick and
healthy chicken in a poultry farms using machine learning classification modeling on the synthetic
data and the real dataset. Theoretical analysis and experimental results show that the proposed
system has achieved an accuracy of 97%. Moreover, the accuracy of the different classification models
are compared in the proposed study to provide more accurate and best performing classification
technique. The proposed study is mainly focused on proposing an Industrial IoT-based predictive
service framework that can classify poultry chickens more accurately in real time.
... The growth of the poultry chickens is also analyzed by observing the peak frequencies made by the chicken. The peak frequency decreased with the increase in the growth of the poultry chicken [22,23] and hence provides the detection of the growth rate of the poultry chicken. Disease diagnoses can also be analyzed through sound analysis. ...
The poultry industry contributes majorly to the food industry. The demand for poultry chickens raises across the world quality concerns of the poultry chickens. The quality measures in the poultry industry contribute towards the production and supply of their eggs and their meat. With the increasing demand for poultry meat, the precautionary measures towards the well-being of the chickens raises the concerns of the industry stakeholders. The modern technological advancements help the poultry industry in monitoring and tracking the health of poultry chicken. These advancements include the identification of the chickens’ sickness and well-being using video surveillance, voice observations, ans feces examinations by using IoT-based wearable sensing devices such as accelerometers and gyro devices. These motion-sensing devices are placed over a chicken and transmit the chicken’s movement data to the cloud for further analysis. Analyzing such data and providing more accurate predictions about chicken health is a challenging issue. In this paper, an IoT based predictive service framework for the early detection of diseases in poultry chicken is proposed. The proposed study contributes by extending the dataset through generating the synthetic data using Generative Adversarial Networks (GAN). The experimental results classify the sick and healthy chicken in a poultry farms using machine learning classification modeling on the synthetic data and the real dataset. Theoretical analysis and experimental results show that the proposed system has achieved an accuracy of 97%. Moreover, the accuracy of the different classification models are compared in the proposed study to provide more accurate and best performing classification technique. The proposed study is mainly focused on proposing an Industrial IoT-based predictive service framework that can classify poultry chickens more accurately in real time.
