**4. Signal processing methods for respiratory signals**

#### **4.1 Amplification**

Some sensor signals have very low amplitude and need to be processed. The sensitivity of the EMFit, for example, is about 2.2–7 mV/mmHg. For signals so small, high-impedance voltage amplifiers must be used [24].

### **4.2 Filtering**

Depending on the signal, filtering is advantageous for processing [40]. Filters are quite common in biomedical engineering applications to emphasize the spectral contents of electrophysiological signals [41]. There are signals with a well-known spectrum that researchers have extensively investigated. Once the frequency range of the signal is determined, an electronic circuit prevents unwanted energy from contributing to the processing and decision-making [42]. As an example, if the acoustic signal band frequency of interest of a solution is between 500 and 900 Hz, then a band-pass filter encompassing this spectrum is inserted into the circuit [43]. For each sensor, one filter should be placed.

Filters can be applied to minimize high-frequency noise, preserving the shape of the respiratory signal [29]. A band-pass filter with cutoff frequencies of 0.1 and 1.5 Hz was applied to compensate for possible drifts and to reduce the total noise level in the signals [10]. **Table 1** shows some types of filters used by the researchers in this area.

#### **4.3 Analog to digital processing**

Despite the advances in digital technologies, we still live in a world full of analog phenomena and human physiology is no exception. Almost all electronic biomedical devices use some kind of quantity conversion, from analog to digital. The exceptions are those devices that work entirely in analog mode.

Key factors of analog to digital conversion need to be considered in order to understand the operation of mobile wearable devices. One factor relates to Claude Shannon's [46] and Harry Nyquist's theories [47]. The sampling theory helps to determine the acquisition frequency (or sampling frequency *fs* ) of analog signals. To digitize a pure sinusoidal wave properly, an acquisition frequency of at least twice the maximum frequency of the analog signal must be used. Knowledge of the spectral range is therefore crucial for determining *fs* .

Human electrophysiological signals are not purely sinusoidal so that the developers of biomedical systems should be far more conservative in determining *fs* . Knowing the maximum frequency of the bandwidth (*fmax*) is useful, because the theory indicates to set *fs* at least twice that value (*fs* <sup>≥</sup> <sup>2</sup> <sup>×</sup> *fmax*). In some cases, however, *fs* must be high enough to keep the signal's significant energy depending on the frequencies of interest. Acoustic sounds, for instance, revealed that signal power was mainly distributed below 5000 Hz [25]. The


**63**

*Breathing Monitoring and Pattern Recognition with Wearable Sensors*

researchers, therefore, set *fs* = 22,050 Hz, which covers up to 11,025 Hz, because the range was considered enough for their application. **Table 2** shows some of

**Reference Sensor Objective Sample rate**

Talking detection 100 Hz

Sleep apnea detection 44.1 kHz

Wheeze detection 2048 Hz

22,050 Hz

4 kHz

Activity detection of deep breath, eating, drinking, speaking, whispering, whistling, laughing, sighing, and coughing.

Measurement of acoustic sounds from the thorax, including the lung sounds

Other equally important factors affect the quality of the acquisition, operation,

Fast Fourier Transform (FFT) is an algorithm that converts the signal from the time domain to the frequency domain and vice versa [40, 48]. This algorithm is important because it is the first step to extract spectral features, which can be used by machine learning algorithms and other algorithms for signal

Machine Learning is the result of pattern recognition and the assumption that computers can learn to execute a task. As a field of artificial intelligence, machine learning is the ability of a machine to learn, identify, and classify from being exposed to specific data in an interactive way, and to not only learn and make reli-

This technique can be useful for automatic pattern recognition in respiratory signals such as sleep apnea, respiratory patterns, and talking detection [10, 49, 50]. The steps to implement a machine learning algorithm are introduced in the follow-

First, for machine learning classification, some features must be given to the classification algorithm. These features must be extracted from the original signal,

and energy efficiency of wearable devices, such as the duration of acquisition, signal conditioning, conversion resolution, etc. However, these are not explored in

**5. Machine learning for respiratory signal pattern detection**

able decisions but also to adapt when exposed to new data.

and they must be well chosen for better results.

*DOI: http://dx.doi.org/10.5772/intechopen.85460*

[10] Chest or abdominal belt with

[25] Acoustic sensor configured

[3] Acoustic sensor fixed with

[44] Acoustic sensor fixed with

[23] Acoustic sensor embedded

a resistive sensor

as a headset over the throat

tape near the nose

tape on the thoracic region

in a wearable mechanical design over the right chest

the sampling rates used.

*Examples of sampling rates.*

**4.4 Fast Fourier transform (FFT)**

this chapter.

**Table 2.**

processing.

ing sections.

**5.1 Feature extraction**

#### **Table 1.**

*Synthesis of the use of filters in respiratory signals.*


*Breathing Monitoring and Pattern Recognition with Wearable Sensors DOI: http://dx.doi.org/10.5772/intechopen.85460*

#### **Table 2.**

*Wearable Devices - The Big Wave of Innovation*

For each sensor, one filter should be placed.

**4.3 Analog to digital processing**

**4.2 Filtering**

in this area.

mining *fs*

**Reference Sensor Type of filter Cutoff frequencies (Hz)**

Depending on the signal, filtering is advantageous for processing [40]. Filters are quite common in biomedical engineering applications to emphasize the spectral contents of electrophysiological signals [41]. There are signals with a well-known spectrum that researchers have extensively investigated. Once the frequency range of the signal is determined, an electronic circuit prevents unwanted energy from contributing to the processing and decision-making [42]. As an example, if the acoustic signal band frequency of interest of a solution is between 500 and 900 Hz, then a band-pass filter encompassing this spectrum is inserted into the circuit [43].

Filters can be applied to minimize high-frequency noise, preserving the shape of the respiratory signal [29]. A band-pass filter with cutoff frequencies of 0.1 and 1.5 Hz was applied to compensate for possible drifts and to reduce the total noise level in the signals [10]. **Table 1** shows some types of filters used by the researchers

Despite the advances in digital technologies, we still live in a world full of analog phenomena and human physiology is no exception. Almost all electronic biomedical devices use some kind of quantity conversion, from analog to digital. The

Key factors of analog to digital conversion need to be considered in order to understand the operation of mobile wearable devices. One factor relates to Claude Shannon's [46] and Harry Nyquist's theories [47]. The sampling theory helps to

To digitize a pure sinusoidal wave properly, an acquisition frequency of at least twice the maximum frequency of the analog signal must be used. Knowledge of the

Human electrophysiological signals are not purely sinusoidal so that the developers of biomedical systems should be far more conservative in deter-

energy depending on the frequencies of interest. Acoustic sounds, for instance, revealed that signal power was mainly distributed below 5000 Hz [25]. The

. Knowing the maximum frequency of the bandwidth (*fmax*) is useful,

[23] Acoustic Band-pass filter 150–1000 [10] Resistive Band-pass filter 0.1–1.5 [5] Piezoresistive Band-pass filter 0.05–2 [45] Accelerometer Low-pass filter 1

low-pass filters in series

2nd order Butterworth low-pass filter 0.2

at least twice that value (*fs* <sup>≥</sup> <sup>2</sup> <sup>×</sup> *fmax*). In

.

must be high enough to keep the signal's significant

20–2000

) of analog signals.

**62**

**Table 1.**

[24] Pressure and

some cases, however, *fs*

accelerometer

because the theory indicates to set *fs*

*Synthesis of the use of filters in respiratory signals.*

[44] Acoustic 2nd order Butterworth high-pass and

exceptions are those devices that work entirely in analog mode.

determine the acquisition frequency (or sampling frequency *fs*

spectral range is therefore crucial for determining *fs*

*Examples of sampling rates.*

researchers, therefore, set *fs* = 22,050 Hz, which covers up to 11,025 Hz, because the range was considered enough for their application. **Table 2** shows some of the sampling rates used.

Other equally important factors affect the quality of the acquisition, operation, and energy efficiency of wearable devices, such as the duration of acquisition, signal conditioning, conversion resolution, etc. However, these are not explored in this chapter.

#### **4.4 Fast Fourier transform (FFT)**

Fast Fourier Transform (FFT) is an algorithm that converts the signal from the time domain to the frequency domain and vice versa [40, 48]. This algorithm is important because it is the first step to extract spectral features, which can be used by machine learning algorithms and other algorithms for signal processing.
