Effect of Importance Sampling on Robust Segmentation of Audio-cough Events in Noisy Environments
| Autor: | Keshav Dahal, Carlos Hoyos-Barcelo, Paul Lesso, Pablo Casaseca-de-la-Higuera, Jesus Monge-Alvarez, Javier Escudero |
|---|---|
| Předmět: |
Engineering
Databases Factual Speech recognition Signal-To-Noise Ratio Sensitivity and Specificity Sneezing Background noise 03 medical and health sciences 0302 clinical medicine Humans Oversampling Segmentation Audio signal Noise measurement business.industry Signal Processing Computer-Assisted Ranging Cough 030228 respiratory system Area Under Curve Smartphone Noise business Classifier (UML) 030217 neurology & neurosurgery Importance sampling |
| Zdroj: | Javier Escudero ResearcherID EMBC University of Edinburgh-PURE Monge-Álvarez, J, Hoyos-Barcelo, C, Escudero, J, Lesso, P, Dahal, K & Casaseca-de-la-Higuera, P 2016, Effect of Importance Sampling on Robust Segmentation of Audio-cough events in Noisy Environments . in Proceedings of the 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society . pp. 3740-3744, 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Orlando, United States, 16/08/16 . |
| Popis: | This paper proposes a new cough detection system based on audio signals acquired from conventional smartphones. The system relies on local Hu moments to characterize cough events and a k-NN classifier to distinguish cough events from non-cough ones (speech, laugh, sneeze, etc.) and noisy sounds. To deal with the unbalance between classes, we employ Distinct-Borderline2 Synthetic Minority Oversampling Technique and a bespoke cost matrix. The system additionally features a post-processing module to avoid isolated false negatives and, this way, increases sensitivity. Evaluation has been carried out using a database comprising a variety of cough and non-cough events and different types of background noise. In this study, we specifically focused on noise likely to appear when the user is carrying the smartphone in daily activities. Different Signal to Noise Ratio values were tested ranging between -15 and 0 dB. Our experiments confirm that local Hu moments are suitable not only for characterizing cough events but also for coping with noisy environments. Results show a sensitivity of 94.17% and a specificity of 92.16% at -15 dB. Thus, our system shows potential as a reliable and place-ubiquitous monitoring device that helps patients self-manage their own respiratory diseases and avoids unreported or fabricated symptoms. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|