Information Extraction From Sound for Medical Telemonitoring

Abstract

Abstract-Today, the growth of the aging population in Europe needs an increasing number of health care professionals and facilities for aged persons. Medical telemonitoring at home (and, more generally, telemedicine) improves the patient's comfort and reduces hospitalization costs. Using sound surveillance as an alternative solution to video telemonitoring, this paper deals with the detection and classification of alarming sounds in a noisy environment. The proposed sound analysis system can detect distress or everyday sounds everywhere in the monitored apartment, and is connected to classical medical telemonitoring sensors through a data fusion process. The sound analysis system is divided in two stages: sound detection and classification. The first analysis stage (sound detection) must extract significant sounds from a continuous signal flow. A new detection algorithm based on discrete wavelet transform is proposed in this paper, which leads to accurate results when applied to nonstationary signals (such as impulsive sounds). The algorithm presented in this paper was evaluated in a noisy environment and is favorably compared to the state of the art algorithms in the field. The second stage of the system is sound classification, which uses a statistical approach to identify unknown sounds. A statistical study was done to find out the most discriminant acoustical parameters in the input of the classification module. New wavelet based parameters, better adapted to noise, are proposed in this paper. The telemonitoring system validation is presented through various real and simulated test sets. The global sound based system leads to a 3% missed alarm rate and could be fused with other medical sensors to improve performance.

One Class Support Vector Machines for audio abnormal events detection

“…Evaluation consisted of applying our decision function 1-frame by frame, 2-after median filtering over 1 second and 3-using adaptive segmentation. Obtained results are presented in Figure 7 [10]. Each curve corresponds to a given SNR and illustrates the trade-off between miss and false-alarm probabilities.…”

“…Classical approaches consist of setting up detectors dedicated to few identified abnormal events [17], or strongly related to the a priori ambience [10]. These are not suitable in the context of surveillance as: 1-we have no prior information relative to events to detect; 2-in noisy environments (e.g.…”

Pervasive Homecare Monitoring Technologies and Applications

“…Most of the related work in this context focuses on collecting and analyzing sound data captured from the patient's close environment. Authors in [36] present a sound analysis system enabling the detection of special sounds and their association with events related to specific activities or situations where first aid is needed (e.g., falls, glass breaking, call for help, etc). The examined sounds are categorized into classes according to their corresponding average magnitude levels in order to detect a variety of sound signatures of both distressful and normal events.…”

Heterogeneous Multi-sensor Fusion Based on an Evidential Network for Fall Detection

“…Such a remote monitoring platform exists at Telecom SudParis elaborated with the close collaboration of Esigetel [8] and U558-INSERM (F. Steenkeste [6]). This Alarm management platform is composed of three detection sub-systems or modalities: GARDIEN [6,5], RFPAT [7,5] and ANASON [8]. In this new application work on Evidential Network, we first focused on two of these modalities: GARDIEN and RFPAT.…”