A Van Hirtum

Fuzzy approach for improved recognition of citric acid induced piglet coughing from continuous registration

Abstract A natural acoustic indicator of animal welfare is the appearance (or absence) of coughing in the animal habitat. A sound-database of 5319 individual sounds including 2034 coughs was collected on six healthy piglets containing both animal vocalizations and background noises. Each of the test animals was repeatedly placed in a laboratory installation where coughing was induced by nebulization of citric acid. A two-class classification into ‘cough’ or ‘other’ was performed by the application of a distance function to a fast Fourier spectral sound analysis. This resulted in a positive cough recognition of 92%. For the whole sound-database however there was a misclassification of 21%. As spectral information up to 10000 Hz is available, an improved overall classification on the same database is obtained by applying the distance function to nine frequency ranges and combining the achieved distance-values in fuzzy rules. For each frequency range clustering threshold is determined by fuzzy c-means clustering.

Assessing the sound of cough towards vocality.

The presented research positively evaluates the vocality of the cough sound by estimating the global cough fundamental frequency or pitch. The fundamental frequency was determined by autocorrelation analysis on both the original time-signal and the linear predicted time-signal. The experimental cough database was registered in the free acoustical field on respectively three pathological and nine healthy non-smoking human subjects and on two pathological and two healthy Belgian Landrace piglets. For both species differences between pitch values for cough-sounds originating from subjects suffering from a respiratory infection and healthy subjects are put forward. The retrieved pitch-difference between respectively healthy and infected subjects indicates the existence of acoustically different cough-classes in accordance with a different cause or physical condition of the respiratory system.

Neural recognition systems for swine cough

Coughing is one of the most frequent presenting symptoms of many diseases affecting the airways and the lungs of humans and animals. The aim of this paper is to build up an intelligent alarm system that can be used for the early detection of cough sounds in piggeries. Registration of coughs from different pigs in a metallic chamber was done in order to analyse the acoustical signal. A new approach is presented to distinguish cough sounds from other sounds like grunts, metal clanging and noise using neural networks (NN) as classification method. Other signals (grunts, metal clanging, etc.) could also be detected. Self-organising maps are used for visualisation of data relationships. Several types of NN are compared with statistical methods for the classification of the cough sounds. The early detection of coughs can be used for the construction of an intelligent alarm that can inform about the presence of a possible viral infection.

Considering the influence of artificial environmental noise to study cough time–frequency features

Abstract In general the study of the cough mechanism and sound in both animal and human is performed by eliciting coughing in a reproducible way by nebulization of an irritating substance. Due to ventilation the controlled evaporation-protocol causes artificial noises from a mechanical origin. The resulting environmental low-frequency noises complicate cough time–frequency features. In order to optimize the study of the cough-sound the research described in this paper attempts on the one hand to characterize and model the environmental noises and on the other hand to evaluate the influence of the noise on the time–frequency representation for the intended cough sounds by comparing different de-noising approaches. Free field acoustic sound is continuously registered during 30 min citric acid cough-challenges on individual Belgian Landrace piglets and during respiratory infection experiments, with a duration of about 10 days, where room-ventilation was present.

An intelligent alarm for early detection of swine epidemics based on neural networks

Coughing is one of the most frequent presenting symptoms of many diseases affecting the airways and the lungs of humans and animals. The aim of this research is to build an intelligent alarm system that can be used for the early detection of cough sounds in pig houses. Registration of coughs from different pigs in a metallic chamber was done in order to analyze the acoustical signal. A new approach is presented to distinguish cough sounds from other sounds like grunts, metal clanging, and noise using neural network classification methods. Other signals (grunts, metal clanging, etc.) could also be detected. A hybrid classifier is proposed that achieves the highest classification accuracy in both the off-line and the on-line detection of coughs and other sounds. The best correct classification performance was obtained with a hybrid classifier that classified coughs and metal clanging separately from other sounds, giving better results compared to a multi-layer perceptron alone. The hybrid classifier, which consisted of a 2-class probabilistic neural network and a 4-class multi-layer perceptron, gave high discrimination performance in the case of grunts and noise (91.3% and 91.3% respectively) and a performance of 94.8% for correct classification in the case of coughs. The early detection of coughs can be used for the construction of an intelligent alarm that can signal the presence of a possible viral infection so that early treatment can be implemented.

Autoregressive acoustical modelling of free field cough sound

In this paper the performance and assumptions of linear prediction acoustical modelling are assessed on the free field cough sound. Four distinct free field cough classes originating from animal and human species in different health conditions are considered. Firstly based on the prediction signal-to-noise ratio the model order for each cough class was chosen to 14. Secondly for each cough class the vocal tract formants are estimated from the linear prediction parameters. Finally the occurrence of subglottal resonances in the cough-sound is investigated.

Model-based PIP control of the spatial temperature distribution in cars.

An on-line mathematical approach was used to model the spatio-temporal temperature distribution in the imperfectly mixed air inside a car. A second-order model proved to be a sufficiently good description of the temperature dynamics (R 2 = 0.985) of the system. Furthermore, it was possible to fully understand the physical meaning of the second-order model structure. Using this model, a proportional integral plus (PIP) climate controller was developed for a single input single output (SISO) system. The controller was able to follow a temperature level of 18–23–21°C at any desirable point, and to robustly react to a random local disturbance.

Objective cough-sound recognition as a biomarker for aerial factors

The relation between air quality and respiratory health and comfort in humans and animals has been widely shown. In general, a state of respiratory discomfort in everyday indoor and outdoor life results in an increase in audible acoustic symptoms. The general concept of sound analysis as an objective, contactless, and non-invasive biomarker for aerial stressors was studied on free-field registered cough sounds of 12 Belgian Landrace piglets. A citric acid-induced cough sound-recognition algorithm with a recognition percentage of 95% was applied to cough sounds registered in the presence of distinct types of aerial factors: irritating gas (ammonia), respirable particles (dust), and climate (temperature). The recognition percentage for all aerial factors exceeded 90% and averaged 94%. Therefore, it was concluded that sound analysis could provide an effective biomarker for all three types of aerial factors. The generality of the biomarker is speculated to arise from the common mechanism involved in protective cough, which will stand as long as no physical changes (e.g., growth, disease) to the state of the respiratory system occur. The results suggest that sound analysis as a biomarker of the respiratory state may be integrated into room or personalized air ventilation control to improve respiratory comfort of animals.

Model-based temperature measurement technique to quantify the dynamic three-dimensional air freshness flow in the interior of a car

A data-based mechanistic (DBM) approach was used to model the spatio-temporal temperature distribution in the imperfectly mixed fluid in a car. The first phase of DBM involves the identification of a mathematical model from experimental data. A second order model proves to deliver a sufficiently good description of the temperature dynamics of the system (R² = 0.985). Furthermore, the physical interpretation of this second order model provides a useful variable. The physical meaning of one of the model parameters is what is called the local volumetric concentration of fresh air flow inside the car. It thus becomes possible to quantify the local air freshness in a complex geometric space as the interior of a car, only using simple temperature measurements. This technique could become a valuable tool in evaluating the performance of for instance climate controllers in interior spaces.

Influence of aerial pollutants on objective cough-sound-recognition

The relation of air quality and respiratory health and comfort in man and animal is widely shown. In general a state of respiratory discomfort in every day indoor and outdoor life is prevailed by an increase in acoustic audible symptoms. The general concept of sound-analysis as objective non-invasive biomarker for aerial pollution is studied on free field cough-sound of 12 Belgian Landrace piglets. A citric acid induced cough-sound recognition-algorithm with recognition rate of 95% is applied to cough-sounds registered in presence of distinct types of aerial pollutants: irritating gas (ammonia), respirable particulars (dust) and climate factors (temperature). The recognition-performance for all aerial pollutants obtained > 90% and maintained 94% on average. Therefore it is concluded that sound-analysis allows an effective biomarker for all 3 types of aerial pollution. The generality of the biomarker is hypothesized to be due to the common mechanism involved in protective coughing which will stand as long as no physical changes to the state of the respiratory system occur. As a consequence it is suggested to imply sound-analysis as a biomarker for the respiratory state into ventilation-control to improve respiratory comfort affected by aerial pollutants.