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 a ffecting the airways and the lungs of humans and animals. The aim of this r esearch is to build an intelligent alarm system that can be used for the ea rly detection of cough sounds in pig houses, Registration of coughs from di fferent pigs in a metallic chamber was done in order to analyze the acousti cal signal. A new approach is presented to distinguish cough sounds from ot her sounds like grunts, metal clanging, and noise using neural network clas sification methods. Other signals (grunts, metal clanging, etc.) could also be detected A hybrid classifier is proposed that achieves the highest clas sification accuracy in both the off-line and the on-line detection of cough s and other sounds. The best correct classification performance was obtaine d with a hybrid classifier that classified coughs and metal clanging separa ted from other sounds, giving better results compared to a multi-layer perc eptron alone. The hybrid classifier which consisted of a 2-class probabilis tic neural network and a 4-class multi-layer perceptron, gave high discrimi nation performance in the case of grunts and noise (91.3% and 91.3% respect ively) 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 infec tion so that early treatment can be implemented.