Acoustic Sensors for Biomedical Applications, Lima Junior , I. Queiroz , N. Oliveira , A. Lopes , P. International Journal of Advances in Intelligent Informatics 4 :3, Online publication date: Nov Artificial Intelligence in Medicine 88 , Online publication date: 1-Jun Journal of Sensors , Online publication date: 1-Jan Sensor Systems and Software, Nitin S.
NEWS & VIDEOS
Ambatkar , S. ETRI Journal 37 :4, Online publication date: 1-Aug Wireless Mobile Communication and Healthcare, Quick search:. This issue This series All series. PDF KB. Quick Links. Purchase print or personal eBook. Alert me when: New articles cite this article. Typically, it is made up of the following elements [ 3 ]:. Sound capturing: the positioning of the microphone is important; actually the chest acts like a reducer and a low-pass filter.
- Phantom Stallion #10: Red Feather Filly!
- Handbook of Justice Research in Law!
- A Novel Method for Automatic Identification of Breathing State.
- Customer Reviews.
- Elementary Geometry for College Students;
- Hollywood Blockbusters: The Anthropology of Popular Movies.
Kraman and coll. Cheetham and coll. Using a unique microphone: It is the more frequently used method. Others make use of an accelerometer; it is less sensitive to background noise [ 17 ], but performance is must less than an electret microphone. Utilisation of several microphones and three dimensional representations. This technique makes it possible to identify the location of the origin of the sounds; it is a dynamic method at shows structural and functional properties for diagnosis [ 18 ][ 19 ].
Emission of a sound and analysis of its propagation. The analysed parameters are energy ratios, signal time delays, and dominant frequency. Measurement in closed loop controlled ventilation [ 21 ][ 22 ]. Heart sounds can introduce perturbations during the analysis of lung sounds. Most of the spectrum of heart sounds is located between 20 and Hz. According to Elphick and coll. Nevertheless, a high-pass filter at Hz is not a good solution in so far as the main components of lung sounds are also located in this frequency range. The filter proposed by Bahoura and coll. This filter provides more accurate and effective results than its rivals; experimental tests demonstrate very good performances.
Moreover, the proposed technique allows better care of the characteristics of stationary signals normal sounds or wheezes. Yadollahi and coll. The more recent techniques use simultaneous usage of several sensors. The spectrum of heart sounds is defined between 20 and Hz for basic signals and higher frequency upper than Hz for breaths. Abnormal sounds can be divided into two sub-classes [ 25 ]:.
- Fundamentals of Respiratory System and Sounds Analysis : Zahra Moussavi : .
- Acoustic Wave Problems.
- English Merchant Shipping 1460-1540;
- Services on Demand;
Now, we are going to detail the characteristics of the two more studied noises: wheezes and crackles [ 28 ]. Then, he proposes a Fourier transform with points and two types of representation of respiratory sound: the waterfall method with a representation of the spectrum in three dimensions amplitude, frequency, time , and the spectrogram method that was mentioned above in this article.
These representations generally allow to have a good visualization of respiratory cycles. The identification of continuous adventitious breath sounds, such as wheeze in the respiratory cycle, is of great importance in the diagnosis of obstructive airways pathologies [ 29 ] Fig. In fact, Sovijarvi and coll. Wheezes, that Laennec calls dry wheezing groan, or wheezing, are sounds that have a duration according to articles greater than 50 ms [ 30 ] or ms and lower than ms [ 29 ]. The frequency of wheezes lies within and Hz, with a fundamental frequency between or [ 25 ] and Hz [ 29 ] or Hz [ 30 ].
On the other hand, [ 25 ] indicates that wheezes have a dominant frequency greater than Hz, contrary to rhonchus whose dominant frequency lies within Hz and below. Finally, asthmatic subjects show wheezes during expiration phase; the latter have a duration range between 80 and ms [ 17 ]. Fiz [ 31 ] and Albers [ 32 ] are able to identify objectively the presence of an obstructive pathology. Likewise, Meslier and Charbonneau [ 33 ] associate wheezes to the following pathologies:.
Infections such as croup infection that generally affects infants from less than three years , whooping cough, laryngitis, acute tracheobronchilis. Asthma: wheeze detection in asthma [ 34 ], identification of nocturnal asthma [ 35 ],.. They are generally generated during the airways opening that were abnormally closed during the inspiration phase, or during the closing in end-expiration. Crackles detection is important in so far as their number is a possible indicator of the severity of a pulmonary affection [ 36 ], airways disorders [ 39 ].
Nevertheless, all the more as their number, their positioning in the respiratory cycle and the waveform of their signal are characteristics of the lung pathologic case [ 1 ].
Evaluation of features for classification of wheezes and normal respiratory sounds
Crackles generally begin with a width deflection, followed by a long and damped sinusoidal wave [ 40 ] [ 41 ] such as represented below Fig. IDW or initial deflection width represents the duration between the beginning of the crackle and the first deflection. It is accepted [ 25 ] that the duration of a crackle is lower than 20 ms and the frequency range is between and Hz. They are exclusively inspiratory. Puerile and coll.
Known markers are crackles and wheezes. The principal algorithm families of detection of these markers are summarised in Table 1. Different analysis methods are described. We can quote temporal analysis of the waveform for crackles searching, and frequency analysis Fourier transform, spectrogram in 2D or 3D [ 16 ], sonogram [ 48 ] used for wheeze detection. In techniques of spectral analysis, the main parameters are the average frequency of the spectrum, the frequency of maximal power, the number of dominant peaks, the factor of exponential decreasing.
Finally, time-amplitude and time-frequency analysis are classically implemented thanks to a wavelet transform. Among the complex solution, we can quote the use of a multi-layer perception in a neuronal network, genetic algorithms and a hybrid solution between both. The search of the parameters is performed through a learning method. Guler and coll. Finally, Murphy and coll. As we explained before, reference [ 3 ] describes a spectral analysis technique for wheeze detection.
In fact, the main characteristic of sounds stands in peaks of energy that can be visualized in the spectrum.
Analysis of Respiratory Sounds: State of the Art
The limits of this method stand in the existence, in normal pulmonary sounds, of peaks similar to those charactering wheezes. Consequently, an important rate of erroneous detections of generated. The difficulties found during the automatic wheeze detection tools can be overcome thanks to a joint time-frequency analysis.
As follows, the principle is: the detection in frequency domain of a peak that could correspond to a wheeze, will be followed by a second test in time domain in order to confirm true wheezes and reject erroneous ones. According to Homs-Cobrera and coll. They use parameters: number of wheezes, mean wheeze frequency with highest power peak, mean wheeze frequency with highest mean power, mean frequency, percentile of manoeuvre occupied by wheezes. The parameters are defined after dividing the frequency range into bands of 50 Hz from to Hz.
Moreover, the present algorithm indicates that there is a significant correlation between the number of wheezes detected and the signal amplitude due to a simultaneous dependence between normalisation factor and fuzzy rules thresholds. Nevertheless, this is not sufficient to objectively characterize sounds. Another process of automatic wheeze detection was proposed [ 3 ][ 51 ]; it is based on wavelet packets decomposition, in two stages.
First, it consists in frequency detection with wheeze extraction. Then, an inverse transform and a reconstruction of the useful signal; a time detection, here also makes it possible to eliminate false detection, generated by a superposition of spectral domains of some normal sounds and wheezes. From spectrograms generated with recorded sounds, Lin and coll. Similarly, a method of continuous wavelet transform is described in[ 29 ], combined with a scale-dependent threshold.
This method seems to provide a higher good detection rate.