Biomedical subjects

J C Pesquet

Publications and source records attributed to J C Pesquet.

3 recordsLinked to original sources

PubMed1998

Wheezing Lung Sounds Analysis with adaptive local trigonometric transform.

Wheezes are abnormal sounds which are known to be relevant to Chronic Obstructive Pulmonary Diseases (COPD). The analysis of such signals is especially useful in patient monitoring or pharmacology. Respiratory sounds are dependent on the flow and the volume. Furthermore, they can be the result of a complex mixture of events. The analysis of lung sounds can be greatly improved with time-frequency techniques because these methods highlight the evolution of the spectra of events. In this paper, we present the application of the Adaptive Local Trigonometric Decomposition (ALTD) to lung sound analysis. This analysis provides an optimal representation of the signal in the time-frequency domain with a lattice which is adapted in time. In our work, the parameterization of the ALTD is studied for the detection of wheezing phenomena.

Algorithms↗

PubMed1998

Time-scale segmentation of respiratory sounds.

Respiratory sounds are composed of various events: normal and so-called adventitious sounds. These phenomena present a wide range of characteristics which make difficult their analysis with a single technique. Adapted time-frequency and time-scale techniques allow to fit best, under constraints, the accuracy of analysis of a time segmentation and, by the way, make feasible the study of complex signals. We present here new approaches based only on the wavelet packet decomposition to segment respiratory sounds.

Algorithms↗

PubMed1998

Classification of respiratory sounds based on wavelet packet decomposition and learning vector quantization.

In this paper, a wavelet packet-based method is used for detection of abnormal respiratory sounds. The sound signal is divided into segments, and a feature vector for classification is formed using the results of the search for the best wavelet packet decomposition. The segments are classified as containing crackles, wheezes or normal lung sounds, using Learning Vector Quantization. The method is tested using a small set of real patient data which was also analysed by an expert observer. The preliminary results are promising, although not yet good enough for clinical use.

Algorithms↗