Toward a Sound Analysis System for Telemedicine

Nguyen, Cong Phuong; Pham, Thi Ngoc Yen; Castelli, Eric

doi:10.1007/11540007_44

Cited by 5 publications

(3 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sound event detection and feature extraction is performed through Discrete Wavelet Transformation (DWT), whereas classification to predefined events or vocal expressions is performed through a Gaussian Mixture Model (GMM) technique. In [27], Mel Frequency Cepstral Coefficients (MFCC) are used in order to detect a variety of sound signatures of both distressful and normal events. The examined sounds are categorized into classes according to their corresponding average magnitude levels that emerge from the application of Fourier Transform on the sound signal.…”

Section: Discussion Of Related Workmentioning

confidence: 99%

“…Head tracking is used in [17] in order to follow patient's movement trajectory with a success rate of fall detection at 66.67%. Environmental sound processing is used in [22][23][24][25][26][27] for monitoring the overall behavior of patients and detection of alarm incidents.…”

Section: Discussion Of Related Workmentioning

confidence: 99%

“…The capture sound signal from the sensors microphones is transmitted to the monitoring module for further processing. Related work within literature [23][24][25][26][27]29] uses Discrete Wavelet Transformation (DWT) for signal denoising and detection of special sounds that can be associated with a patient's state. However, in this work, the use of DWT has been avoided, because this transformation has high complexity and the results can be biased from the decomposition level of the wavelet coefficients.…”

Section: Data Processing and Classificationmentioning

confidence: 99%

See 2 more Smart Citations

An assistive environment for improving human safety utilizing advanced sound and motion data classification

Doukas

2010

Univ Access Inf Soc

View full text Add to dashboard Cite

This paper presents the concept and an initial implementation of an assistive awareness system that may be used for human activity interpretation and emergency recognition in cases such as elder or patient falls and distress speech expressions, thus improving their safety. Awareness is achieved through collecting, analyzing and classifying motion and sound data. The latter are collected through sensors equipped with accelerometers and microphones that are attached to the human body and transmit movement and sound data wirelessly to the monitoring unit. The detection of fall incidents has been proven to be feasible by applying Short Time Fourier Transform (STFT) and spectrogram analysis on sounds. The classification of the sound and movement data is performed using a variety of advanced classification techniques. Evaluation results provide a performance comparison between the evaluated classifiers and indicate the high accuracy and the effectiveness of the proposed implementation. The system architecture is open and can be easily enhanced to include patient awareness based on additional context (e.g., physiological data).

show abstract

Section: Discussion Of Related Workmentioning

confidence: 99%