80
M. C. Ben Nasr et al.
is associated with a huge economic burden. In fact, numbers published by the
Global initiative for Chronic Obstructive Lung Disease [4] shows that the direct
costs of respiratory disease in the European Union are estimated to be about
6% of the total annual healthcare budget with COPD accounting for 56% (38.6
billion Euros) of the cost of respiratory disease. These numbers are further amplified by the ever-growing healthcare costs, the aging of the population and the
widespread of such diseases. The monitoring of respiratory activities plays an
important role in the current management of patients with acute respiratory
failure [5]. As a consequence, it is recommended to have continuous monitoring
of the vital signs to ensure an optimal diagnosis of a patient’s state [6]. Moreover,
monitoring of respiratory activity is useful for detecting respiratory disorders,
such as the sleep apnea, cessation of breathing in infants, shortness of breath in
patients with heart failure, and so on. Hence, it is important to monitor respiratory activities such as normal breathing, cough, hold breath expiration.
A new generation of sensor-based mattress is able to unobtrusively monitor
vital signs such as the Heart rate Beat Rate (HBR) and the Respiratory Rate
(RR). Indeed, this study considered an Optical Fiber based Sensor (FOS) [7]
for the unobstructed monitoring of the Ballistocardiogram (BCG) signal. Due
to the ejection of the blood during the systole, the body’s mechanical reaction
is measured hence the BCG signal. Our aim is to investigate a classification
method to distinguish between several types of respiratory activities such as
normal breathing, cough and hold breath using the BCG signal.
This paper is organized as follows. Section 2 is dedicated to describe the
material and method. It describes the data collection, BCG signal analysis and
feature extraction and classification. Section 3 provides information about the
experimental results mainly feature illustration and classifier evaluation. Finally,
Sect. 4 concludes the study and gives perspectives.
2 Material and Method
2.1 Data Collection
The system used for collecting data includes a small FOS mattress and a module
to gather optical data coming from the mattress [8,9]. The FOS mattress was
fixed on the back of a regular office chair. The raw data is sampled at 50 Hz by
the module.
The BCG signals were acquired on 6 healthy participants: 3 male and 3
female aged between 21 and 32 years. The participants were asked to perform a
certain experimental protocol. A part of normal breathing, other human body
activities that commonly occur are introduced in this protocol. It is composed of
the following steps by following activities: normal breathing (C1), cough (C2),
Normal breathing after cough (C3), hold breath (C4), expiration (C5), movement
(C6). We also consider a class other to regroup all other activities (C7). Figure 1
illustrates an example of the BCG signal. The different human body activities
are plotted in different colors. The objective is to highlight the differences in the
BCG signal according to the activity.
M. C. Ben Nasr et al.
is associated with a huge economic burden. In fact, numbers published by the
Global initiative for Chronic Obstructive Lung Disease [4] shows that the direct
costs of respiratory disease in the European Union are estimated to be about
6% of the total annual healthcare budget with COPD accounting for 56% (38.6
billion Euros) of the cost of respiratory disease. These numbers are further amplified by the ever-growing healthcare costs, the aging of the population and the
widespread of such diseases. The monitoring of respiratory activities plays an
important role in the current management of patients with acute respiratory
failure [5]. As a consequence, it is recommended to have continuous monitoring
of the vital signs to ensure an optimal diagnosis of a patient’s state [6]. Moreover,
monitoring of respiratory activity is useful for detecting respiratory disorders,
such as the sleep apnea, cessation of breathing in infants, shortness of breath in
patients with heart failure, and so on. Hence, it is important to monitor respiratory activities such as normal breathing, cough, hold breath expiration.
A new generation of sensor-based mattress is able to unobtrusively monitor
vital signs such as the Heart rate Beat Rate (HBR) and the Respiratory Rate
(RR). Indeed, this study considered an Optical Fiber based Sensor (FOS) [7]
for the unobstructed monitoring of the Ballistocardiogram (BCG) signal. Due
to the ejection of the blood during the systole, the body’s mechanical reaction
is measured hence the BCG signal. Our aim is to investigate a classification
method to distinguish between several types of respiratory activities such as
normal breathing, cough and hold breath using the BCG signal.
This paper is organized as follows. Section 2 is dedicated to describe the
material and method. It describes the data collection, BCG signal analysis and
feature extraction and classification. Section 3 provides information about the
experimental results mainly feature illustration and classifier evaluation. Finally,
Sect. 4 concludes the study and gives perspectives.
2 Material and Method
2.1 Data Collection
The system used for collecting data includes a small FOS mattress and a module
to gather optical data coming from the mattress [8,9]. The FOS mattress was
fixed on the back of a regular office chair. The raw data is sampled at 50 Hz by
the module.
The BCG signals were acquired on 6 healthy participants: 3 male and 3
female aged between 21 and 32 years. The participants were asked to perform a
certain experimental protocol. A part of normal breathing, other human body
activities that commonly occur are introduced in this protocol. It is composed of
the following steps by following activities: normal breathing (C1), cough (C2),
Normal breathing after cough (C3), hold breath (C4), expiration (C5), movement
(C6). We also consider a class other to regroup all other activities (C7). Figure 1
illustrates an example of the BCG signal. The different human body activities
are plotted in different colors. The objective is to highlight the differences in the
BCG signal according to the activity.