Transactions of the ASABE Vol. 51(3): 1051-1055 E 2008 American Society of Agricultural and Biological Engineers ISSN 0001-2351 1051 ANALYSIS OF COUGH SOUNDS FOR DIAGNOSIS OF RESPIRATORY INFECTIONS IN INTENSIVE PIG F ARMING S. Ferrari, M. Silva, M. Guarino, D. Berckmans ABSTRACT. Respiratory diseases are widespread causes of mortality and loss of productivity in intensive pig farming. Cough is one of the symptoms and a central element in screening and diagnosis of common illnesses caused, for example, by Pasteurella multocida or Actinobacillus pleuropneumoniae ( App). The aim of this research is to compare the acoustic features of cough sounds originating from the mentioned infections and non‐infectious cough sounds provoked by inhalation of citric acid by means of labeling and sound analysis. The acoustic parameters investigated are peak frequency and duration of the cough signals. The differences resulting from the sound analysis confirm the variability in acoustical parameters according to health status or disease in the animals. In infections, there is a change in the status of the respiratory system; consequently, infectious coughs are different from non‐infectious coughs. The duration of single infectious coughs is considerably different among the types of cough analyzed, which are: non‐infectious coughs, App coughs, and P. multocida coughs. Frequency analysis of single coughs allows a more general classification between non‐infectious and infectious coughs. Acoustics parameters can be used in an algorithm‐based alarm system to automatically identify cough sounds and provide farmers an early warning about the health status of their herds. Keywords. Cough sounds, Infections, Pigs, Sound analysis. espiratory pathologies are frequent in pig husband‐ ry, and cough is their principal symptom. Due to their numerousness and incidence on farms, it is crucial to find an objective and non‐invasive meth‐ od to investigate cough sounds, with the aim of understanding the spread and evolution of respiratory diseases. It has been shown that pig vocalization is directly related to pain, and classification of such sounds has been attempted (Marx et al., 2003). It is also common practice by veterinarians to assess cough sounds in pig houses for diagnostic purposes. In this regard, there have been attempts to identify the characteris‐ tics of coughing in animals (Van Hirtum and Berckmans, 2002a, 2002b) and automatically identify cough sounds in field recordings (Aerts et al., 2005; Van Hirtum and Berck‐ mans, 2001, 2003a, 2003b). The analysis in this work considers three databases of coughs collected under field and laboratory conditions. Two Submitted for review in September 2007 as manuscript number SE 7190; approved for publication by the Structures & Environment Division of ASABE in May 2008. The authors are Sara Ferrari, Doctoral Student, Faculty of Veterinary Medicine, Department of Veterinarian Sciences and Technologies for Food Safety, University of Milan, Milan, Italy; Mitchell Silva, Doctoral Student, Department of Biosystems, Division M3‐BIORES: Measure, Model and Manage Bioresponses, Katholieke Universiteit Leuven, Leuven, Belgium; Marcella Guarino, Researcher, Faculty of Veterinary Medicine, Department of Veterinarian Sciences and Technologies for Food Safety, University of Milan, Milan, Italy; and Daniel Berckmans, ASABE Member Engineer, Full Professor, Department of Biosystems, Division M3‐BIORES: Measure, Model and Manage Bioresponses, Katholieke Universiteit Leuven, Leuven, Belgium. Corresponding author: Marcella Guarino, Department of Veterinarian Sciences and Technologies for Food Safety, Faculty of Veterinary Medicine, University of Milan Via Celoria 10, 20133 Milan, Italy; phone/fax: 0039‐02‐50317909; e‐mail: marcella. guarino@unimi.it. databases were recorded from infections by multifactorial respiratory diseases mainly caused by Actinobacillus pleuropneumoniae (App) and Pasteurella multocida, and the third database of coughs was induced under laboratory condi‐ tions by inhalation of citric acid. The two most important primary bacterial agents involved in respiratory disease are considered to be Mycoplasma hyop‐ neumoniae , which causes enzootic pneumonia (Ross, 1992), and App, which causes pleuropneumonia (Sebunya and Saunders, 1983). The most important secondary agent, which becomes involved in respiratory disease only after impair‐ ment of the lungs' defense mechanisms, is considered to be Pasteurella multocida (Ciprian et al., 1988; Pijoan, 1992). App is currently a widespread problem in intensive pig breed‐ ing and fattening farming in the EU, Asia, and North Ameri‐ ca. It can affect pigs at all ages, and the severity of the disease depends on the pig's immune system, the virulence of the ba‐ cillus strain, and the possibility of concomitant infections with viruses and Mycoplasma. In both the acute and chronic manifestation of these dis‐ eases, the animals are affected by cough and dyspnoea, hy‐ perthermia in the first phase, lack of appetite, and reduction of weight. The evolution of the disease depends on environ‐ mental conditions, population density, and thermal excur‐ sions. The change from acute to chronic form may occur months after acute phase clinical recovery. Relapses are fre‐ quent. In field conditions, App may interact with other micro‐ organisms like Mycoplasma PRRSV or PCV‐2. Sick animals are treated by parenteral antibiotic (Christensen and Bis‐ gaard, 2004). P. multocida is an opportunist bacteria that causes pulmo‐ nary pasteurellosis and is often associated with and compli‐ cates infections from herpesvirus (PRV), arterivirus (PRRSV), and especially M. hyopneumoniae. It is also the cause of progressive atrophic rhinitis (RAP), a significant R