See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/268370059

Designing Intelligent Mechanical Ventilator and User Interface Using

LabVIEW®

Article  in  ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING · January 2013

DOI: 10.1007/s13369-014-1090-y

CITATIONS READS

10 91

3 authors, including:

Hasan Guler Ibrahim Turkoglu

Firat University Firat University
34 PUBLICATIONS   109 CITATIONS    73 PUBLICATIONS   1,571 CITATIONS   

SEE PROFILE SEE PROFILE

Some of the authors of this publication are also working on these related projects:

Weaning system View project

A hybrid genetic algorithm for analog active filter component selection View project

All content following this page was uploaded by Hasan Guler on 25 March 2020.

The user has requested enhancement of the downloaded file.

Designing Intelligent Mechanical
Ventilator and User Interface Using
LabVIEW®

Hasan Guler, Ibrahim Turkoglu & Fikret

Ata

Arabian Journal for Science and

Engineering

ISSN 1319-8025
Volume 39
Number 6

Arab J Sci Eng (2014) 39:4805-4813

DOI 10.1007/s13369-014-1090-y

1 23
Your article is protected by copyright and
all rights are held exclusively by King Fahd
University of Petroleum and Minerals. This e-
offprint is for personal use only and shall not
be self-archived in electronic repositories. If
you wish to self-archive your article, please
use the accepted manuscript version for
posting on your own website. You may
further deposit the accepted manuscript
version in any repository, provided it is only
made publicly available 12 months after
official publication or later and provided
acknowledgement is given to the original
source of publication and a link is inserted
to the published article on Springer's
website. The link must be accompanied by
the following text: "The final publication is
available at link.springer.com”.

1 23
 Author's personal copy
Arab J Sci Eng (2014) 39:4805–4813
DOI 10.1007/s13369-014-1090-y

RESEARCH ARTICLE - ELECTRICAL ENGINEERING

Designing Intelligent Mechanical Ventilator and User Interface

Using LabVIEW®
Hasan Guler · Ibrahim Turkoglu · Fikret Ata

Received: 23 October 2012 / Accepted: 31 May 2013 / Published online: 10 April 2014
© King Fahd University of Petroleum and Minerals 2014

Abstract The main purpose of this paper is to design

mechanical ventilator and to develop user interface. Mechan-
ical ventilators have been generally controlled by open-loop
controller. Thus, workload of clinicians in intensive care
unit is too much. In this study, an intelligent mechanical
ventilator was designed as a closed loop to reduce work-
load of clinicians. The device is called intelligent ventilator
because of using an intelligent control technique, fuzzy logic.
A software-based interface was developed in LabVIEW® to
monitor and adjust respiratory variables. In this work, fuzzy
controlled the inspiration/expiration valves and pressure reg-
ulator in ventilator. Fuzzy has two inputs and two outputs for
inspiration/expiration times and it has one input and one out-
put for pressure regulator. The performance of device was
tested with eight female Wistar albino rats using pressure-
controlled ventilation. Student t test for p < 0.05 was applied
to the calculated rats’ lung parameters to determine statisti-
cal discrepancy. The results show that there is no statistical
discrepancy in rats’ lung parameters for before and after the
experiments. It can be said that the designed ventilator sup-
ports rats’ artificial respiration, successfully and does not
alter the lung parameters of rats.
1 Introduction
Keywords Fuzzy logic · Medical control system ·
Respiration · LabVIEW Mechanical ventilator is a device that supports enough oxy-
gen for patients with respiratory distress in intensive care
unit (ICU). Oxygen is important for human being since it
provides energy. Respiration can be defined as transporta-
H. Guler (B) · F. Ata
tion of oxygen and carbon dioxide. It has two phases: inspi-
Electrical-Electronics Engineering Department, ration and expiration [1]. Inhalation or inspiration is defined
Firat University, 23119 Elazig, Turkey as taking air into the lungs, and exhalation or expiration is
e-mail: hasanguler23@gmail.com; hasanguler@firat.edu.tr called the process of breathing it out. Ventilation can be done
in three different types. These are negative pressure ventila-
I. Turkoglu
Software Engineering Department, Firat University, tion, positive-pressure ventilation and high-frequency venti-
23119 Elazig, Turkey lation.

123
 Author's personal copy
4806 Arab J Sci Eng (2014) 39:4805–4813

Many engineers and scientists have tried to improve 2 Material and Methods
features of mechanical ventilator since 1980s. They have
firstly focused on monitoring patients’ respiration physi- In the designing of intelligent mechanical ventilator proto-
ology. Afterwards, microprocessor-driven ventilators have type and user interface, LabVIEW® software produced by
been used instead of the mechanically controlled ventilators national instrument (NI) was used to control all system and
[2]. create software-based user interface. The reason why we
After mid-1990s, the scientists focused mainly on three choose LabVIEW® is that it has fuzzy controller tool and
different systems. These are algorithmic programs, model- also the user interface can be created easily because of being
based system and knowledge-based system. Algorithmic graphical programming language.
program method is not suitable for ventilation because of The schematic diagram of intelligent mechanical ventila-
patients’ complex cardiovascular and respiration physiology. tor prototype was designed as shown in Fig. 1.
However, the other two systems can produce solution by tak- The prototype was created as modular structures. The pro-
ing into account the disadvantage of algorithmic programs. totype has eight electronic circuits. These are power unit, pro-
All respiration system must be modeled in model-based sys- portional valves circuit, pressure regulator circuit, solenoid
tem. Nevertheless, it is not easy to model respirations system valves circuit, pressure sensors circuit, inspiration and expi-
of patients with different lung pathologies. Modeling respira- ration flow sensor circuits and finally main board circuit. The
tion system is not necessary in the knowledge-based system. main controller unit of the prototype is NI-cRIO 9073 chas-
Experts’ opinion plays an important role in this system. Most sis. Analog input and output modules and digital input and
researchers have tried to control respiration parameters via output modules were added to the chassis.
open- and closed-loop controller in these systems. The power unit circuit was specially designed and has
After artificial intelligence techniques have been success- three power units such as 24 V and 90 mA, 12 V and 65 mA
fully applied to many systems, these techniques have begun and −12 V and 65 mA. The proportional valves were used
to be widely used in biomedical applications in recent years. to adjust oxygen percent of the air by mixing pure oxygen
There have been several attempts to design and control venti- and air. The pressure regulator was used to adjust pressure of
lator and ventilation via using classical control methods and the oxygen. The operating range of the regulator is between
artificial control techniques. Many researchers have gener- 0.001 and 0.1 MPa. The aim of using solenoid valves is to
ally developed open-loop systems to control patients’ respi- provide inspiration and expiration processes. The operating
ration parameters in model- and knowledge-based systems frequency of valves is 20 Hz. In the pressure sensors circuits,
[3–15]. There have been a few studies to design or develop two different sensors were used to measure oxygen pressures
closed-loop controller for mechanical ventilation [16–21]. during inspiration/expiration phases. The measuring ranges
However, these studies have been mainly focused on weaning of sensors are 1 and 5 PSI. The goal of using 1 PSI sensor
process in model- and knowledge-based systems. Commer- is to detect small pressure changes. Inspiration and expira-
cial ventilators have generally been used in these studies. In tion flow sensors measured to oxygen flow in the inspiration
[22–28] studies, respiration parameters such as FiO2 , SaO2 , and expiration phases. The measuring range of flow sensor
tidal volume and respiration rate have been controlled by the is 0–10 l/min. The main board circuit is designed to pro-
intelligent control techniques. vide commutations between the other seven circuits and NI
In the literature, although there are many studies about chassis. The figure of the circuit is shown in Fig. 2.
controlling ventilator, only a few studies about designing The prototype mechanical ventilator is shown in Fig. 3.
open- or closed-loop controlled ventilator exist. Recently, In modern ventilator used in ICU, ventilators provide
some researchers have tried to make intelligent ventilators many ventilation modes such as pressure-controlled ventila-
via using artificial intelligent techniques. However, in these tion (PCV), pressure support ventilation (PSV) and volume-
studies, researchers have used expensive commercial ventila- controlled ventilation. In this study, NI LabVIEW® 2010
tors. Thus, in this study, the low-cost LabVIEW-based intel- academic premium suite program was used. The two differ-
ligent mechanical ventilator and user interface were designed ent programs were implemented in LabVIEW® to provide
to reduce workload of clinicians. Eight female Wistar albino various ventilation modes. In addition, these programs offer
rats were used to test the designed ventilator. During the manual or automatic control for users. In the programs, fuzzy
experiments, the clinician did not adjust any parameters on logic controlled inspiration and expiration valves and pres-
ventilator prototype. According to the obtained results, it is sure regulator according to the measured pressure on rats.
seen that the designed intelligent ventilator supports rats’ res- The implemented software-based user interfaces are shown
piration successfully and the ventilator does not alter the lung in Figs. 4 and 5.
parameters of rats. In addition, it is obvious that this study In setting interface section for Fig. 4, respiration rate, the
may be the first step for future intelligent ventilator used in first inspiration time, PEEP, oxygen percentage and the first
ICU. value of pressure regulator are determined by clinician. In

123
 Author's personal copy
Arab J Sci Eng (2014) 39:4805–4813 4807

Fig. 1 Schematic diagram of V1

mechanical ventilator prototype O2 Tube

V3 V4
PR

Atmosphere

Air Tube
P2
P1

P3
V2

F1
P1,2,3:Pressure Sensor
PR :Pressure Regulator
V1,2 :Proportional Valve F2
V3,4 :Selenoid Valve
F1,2 :Flowsensor
Rat

The constructed fuzzy logic controlled solenoid valves

and pressure regulator in the system, separately. When mem-
bership functions for fuzzy systems were being created, real
values of rats’ lung pressure were used just like in [19,29].
Thus, the scaling of membership functions was not normal-
ized to [−1,1]. The membership functions of fuzzy input
and output for solenoid valves are shown in Figs. 6 and 7,
respectively.
Fig. 2 The designed main board circuit Where NB is negative big, NS is negative small, Z is zero,
PS is positive small, PB is positive big. The triangle shapes in
membership functions of fuzzy inputs and outputs were cho-
sen in accordance with those stated in the relevant literature
[19,23,25,26].
The constructed fuzzy system for inspiration/expiration
valves has two inputs and two outputs to determine inspira-
tion and expiration times in this system. The inputs are error
and the changes in error. The outputs are inspiration and expi-
ration times. These membership functions determined inspi-
ration and expiration time according to pressure changes on
rats. Solenoid valves were opened or closed with respect to
the estimated time via fuzzy logic. Twenty-five rules were
separately created for inspiration and expiration time. These
rules were created by taking the opinions of clinicians. Rule
tables for inspiration and expiration time are shown in Tables
1 and 2.
The other equipment controlled via fuzzy logic is the pres-
Fig. 3 The designed intelligent mechanical ventilator prototype sure regulator. The input and output membership functions
are shown in Figs. 8 and 9, respectively.
Where P is the measured peak inspiration pressure and
monitorization interface section for Fig. 5, inspiration pres- Reg is the output value of pressure regulator. The triangle
sure, inspiration and expiration time, inspiration and expira- shape was chosen for the input and the trapeze shape was
tion valve’s status, flow, the new value of pressure regulator chosen for the output.
and pressure waveform are monitored. The three LEDs were Five rules were created for the output value of pressure
used to show which valve is open. In addition, clinician can regulator as below:
control ventilator prototype as open loop when to press key If peak pressure is P1 then regulator values is Reg1.
button on the screen.

123
 Author's personal copy
4808 Arab J Sci Eng (2014) 39:4805–4813

Fig. 4 The implemented

software-based user interface
for setting

Fig. 5 The implemented

software-based user interface
for monitorization

µpe(k) µins

INS1 INS2 INS3 INS4 INS5 INS6 INS7

NB NS Z PS PB

0 0.2 0.4 0.6 0.8 1 1.2 sec

-40 -20 0 20 40 cmH2O

µexp
µ pe(k)
EXP1 EXP2 EXP3 EXP4 EXP5 EXP6 EXP7
NB NS Z PS PB

0 0.2 0.4 0.6 0.8 1 1.2 sec

-10 -5 0 5 10 cmH2O Fig. 7 The membership functions of the outputs

Fig. 6 The membership functions of inputs

123
 Author's personal copy
Arab J Sci Eng (2014) 39:4805–4813 4809

Table 1 Rule tables for inspiration time

e(k)/δe(k) NB NS Z PS PB

NB INS1 INS1 INS2 INS3 INS4

NS INS1 INS2 INS3 INS4 INS5
Z INS2 INS3 INS4 INS5 INS6
PS INS3 INS4 INS5 INS6 INS7
PB INS4 INS5 INS6 INS7 INS7

Table 2 Rule tables for expiration time

e(k)/δe(k) NB NS Z PS PB

NB EXP7 EXP7 EXP6 EXP5 EXP4

NS EXP7 EXP6 EXP5 EXP4 EXP3
Z EXP6 EXP5 EXP4 EXP3 EXP2
Fig. 10 The ventilated rat in the experiment
PS EXP5 EXP4 EXP3 EXP2 EXP1
PB EXP4 EXP3 EXP2 EXP1 EXP1
weights of rats used in the experiment were 225 ± 25 g.
Respiratory parameters of rats were chosen in accordance
µ Pik with those stated in relevant literature [30,31]. Thus, FiO2 : 1
P1 P2 P3 P4 P5
(fraction of inspired oxygen), PEEP: 0 cmH2 O (positive end-
1 expiratory pressure), tidal volume: 6 ml/kg were used in the
experiments. Pressure regulator was first set to 30 cmH2 O.
The test procedure for each rat is as below.

• Application of anesthesia for rats.

0 10 20 30 40 cmH2O • The tracheotomy operation on rats
• Determine ventilation parameters on setting screen.
Fig. 8 The membership function of the input • Provide artificial respiration during 1 min.
• Inject Blok-L agent to paralyze respiration system of rats.
µ Reg • After 40 min, start weaning process from ventilator and
then euthanasia.
Reg1 Reg2 Reg3
1
During experiments, PCV mode was used for rat’s ventila-
tion. Rats were firstly anesthetized with 0.3 ml ketamine and
tracheotomy operation was carried out to provide artificial
respiration. Afterwards, 0.3 ml Blok-L was injected to para-
lyze respiratory system of rats. Thus, respiration of rats was
0 10 15 25 30 40 cmH2O
carried out by the device.
Fig. 9 The membership function of the output The picture of ventilated rat during experiment is shown
in Fig. 10.
The flow chart of the implemented program is shown in
If peak pressure is P2 then regulator values is Reg1. Fig. 11.
If peak pressure is P3 then regulator values is Reg2.
If peak pressure is P4 then regulator values is Reg2.
If peak pressure is P5 then regulator values is Reg3. 4 Results

After the experiments on rats, lung resistance and capacitance

3 Experimental Setup of rats were calculated. Equations 1, 2 and 3 were used to
calculate these values [27].
Eight female Wistar albino rats were used to investigate Ppeak − Pplato
the success of the designed ventilator prototype. The mean R= (1)
V̇

123
 Author's personal copy
4810 Arab J Sci Eng (2014) 39:4805–4813

Fig. 11 The flow chart of the

implemented PCV mode

Vt Table 3 The calculated resistance and capacitance values before Block-

Cdynamic = (2)
Ppeak − PEEP L agent was not applied for rats
R (mmHg/ml/s) Cdynamic (ml/mmHg) Cstatic (ml/mmHg)
Vt
Cstatic = (3) Rat-1 0.164 0.172 0.194
Pplato − PEEP
Rat-2 0.173 0.189 0.214
where R is the resistance, Cdynamic and Cstatic are the capaci- Rat-3 0.178 0.201 0.233
tance, Ppeak is peak inspiration pressure, Pplato is the pressure Rat-4 0.159 0.153 0.170
applied to small airways and alveoli during positive-pressure Rat-5 0.163 0.176 0.199
mechanical ventilation, V̇ is flow, Vt is tidal volume and Rat-6 0.160 0.154 0.171
PEEP is the positive end-expiratory pressure. Rat-7 0.166 0.162 0.179
The calculated resistance and capacitance values before Rat-8 0.161 0.167 0.188
Block-L agent was not injected to rats are shown in Table 3
and the calculated resistance and capacitance values after the
experiments are shown in Table 4.
The changes of lung resistance and capacitance of rats are The maximum and minimum discrepancies in lung resistance
shown in Figs. 12, 13 and 14, respectively. were in rat 7 and rat 4, respectively. The maximum and mini-
It can be seen from Figs. 12, 13, 14 that there is no big mum discrepancies in lung capacitances were in rat 6 and rat
discrepancy in the rats’ lung dynamics for before and after 4, respectively. Respiratory speed of rats was selected as 80
the experiment. The clinicians confirmed that the increases breaths per minute. Thus, rats’ respiration period was 0.75 s.
in the lung dynamics were resulted from the injected agents. The shortest inspiration time and the smallest peak pressure

123
 Author's personal copy
Arab J Sci Eng (2014) 39:4805–4813 4811

Table 4 The calculated resistance and capacitance values after exper-

iments on rats
R (mmHg/ml/s) Cdynamic (ml/mmHg) Cstatic (ml/mmHg)

Rat-1 0.169 0.179 0.204

Rat-2 0.180 0.202 0.233
Rat-3 0.182 0.212 0.247
Rat-4 0.163 0.157 0.175
Rat-5 0.169 0.185 0.210
Rat-6 0.166 0.181 0.205
Rat-7 0.175 0.174 0.197
Rat-8 0.165 0.171 0.193

Fig. 14 The changes of rats’ static lung capacitance for before and
after experiments


x
X= (4)
n

(x − x)2
S =
2
(5)
n−1

(x1 − x2 )
t= (6)
S12 S22
n 1 −1 + n 2 −1

Fig. 12 The changes of rats’ lung resistance for before and after exper- where x is the arithmetic mean, S 2 is variance, t is the test
iments
formula, x is the investigated group and n is the number of
data in group.
According to the results from student t test, it can be seen
that there is no statistical discrepancy for 98.7 % reliability
between the values of the rats’ lung resistance and capaci-
tance. It means that the designed intelligent ventilator does
not disturb lung parameters of rats and provides artificial res-
piration, successfully.

5 Conclusion and Discussion

Mechanical ventilator is widely used to treat patients with

respiratory distress. According to patients’ physiological sta-
Fig. 13 The changes of rats’ dynamic lung capacitance for before and tus, clinicians determine the settings of ventilator in ICU
after experiments manually, but this increases the workload of them. Thus,
many researchers have focused on automatic ventilator con-
were obtained in rat 4, whose lung resistance was the low- trol to decrease it. In literature, the open-loop or closed-loop
est; while the longest inspiration time and the highest peak systems were designed or developed by researchers. They
pressure were obtained in rat 6, whose lung resistance was have generally developed open-loop controller to control
the highest. patients’ respiration parameters. There have also been studies
The student t test was used to determine statistical dis- about designing the closed-loop systems for mechanical ven-
crepancy in rats’ lung parameters. The student t test for tilation. In these studies, commercial ventilators have been
p < 0.05 was applied to the obtained results from rats’ exper- converted to closed-loop ventilators. Thus, the researchers
iments. The Eqs. 4, 5 and 6 were used to calculate statistical were unable to intervene in the software and hardware of
discrepancy. ventilator.

123
 Author's personal copy
4812 Arab J Sci Eng (2014) 39:4805–4813

In this study, instead of buying commercial ventilator, concept and prototype. Comput. Methods Progr. Biomed. 30(1),
the intelligent mechanical ventilator prototype was designed 59–70 (1989)
9. Tong, D.A.: Weaning patients from mechanical ventilation. A
and the software-based user interface was implemented with knowledge-based system approach. Comput. Methods Progr. Bio-
LabVIEW® to monitor and adjust respiratory variables. The med. 35(4), 267–278 (1991)
designed device was controlled as closed loop. However, ven- 10. Arroe, M.A.: A computerized aid in ventilating neonates. Comput.
tilator can be also controlled as open loop when to press key Biol. Med. 21(1–2), 15–21 (1991)
11. Henderson, S.; Crapo, R.O.; Wallace, C.J.; East, T.D.; Morris,
button on the interface screen. A.H.; Gardner, R.M.: Performance of computerized protocols for
The performance of device was tested with eight female the management of arterial oxygenation in an intensive care unit.
Wistar albino rats by using PCV mode. During the experi- Int. J. Clin. Monit. Comput. 8(4), 271–280 (1992)
ments, the clinician did not adjust any parameters on ventila- 12. Rutledge, G.W.; Thomsen, G.E.; Farr, B.R.; Tovar, M.A.;
Polaschek, J.X.; Beinlich, I.A.; et al.: The design and implemen-
tor prototype. Fuzzy logic controller made decisions accord- tation of a ventilator-management advisor. Artif. Intell. Med. 5(1),
ing to rat’s physiological status. After the experiments, stu- 67–82 (1993)
dent t test was used to determine statistical discrepancy in 13. Shahsavar, N.; Ludwigs, U.; Blomqvist, H.; Gill, H.; Wigertz, O.;
rats’ lung parameters. These lung parameters are lung resis- Matell, G.: Evaluation of a knowledge-based decision-support sys-
tem for ventilator therapy management. Artif. Intell. Med. 7(1),
tance, dynamic and static capacitances. In the light of the 37–52 (1995)
obtained results from the student t test, it is obvious that 14. Miksch, S.; Horn, W.; Popow, C.; Paky, F.: Utilizing temporal data
the designed prototype supports artificial respiration of rats abstraction for data validation and therapy planning for artificially
successfully and do not alter the lung parameters of rats. In ventilated newborn infants. Artif. Intell. Med. 8(6), 543–576 (1996)
15. Rees, S.E.; Allerod, C.; Murley, D.; Zhao, Y.; Smith, B.W.; Kjar-
addition, this study shows that the designed intelligent ven- gaard, S.; et al.: Using physiological models and decision theory for
tilator minimizes the workload of clinicians and so it can be selecting appropriate ventilator settings. J. Clin. Monit. Comput.
said that this study may be the first step for future’s intelligent 20(6), 421–429 (2006)
ventilator used in ICU. 16. Strickland, Jr. J.H.; Hassan, J.H.: A computer controlled ventilator
weaning system. Chest 100(4), 1096–1099 (1991)
In the future studies, artificial neural network, neural fuzy 17. Dojat, M.; Harf, A.; Touchard, D.; Lemaire, F.; Brochard, L.: Clin-
hybrid system or decision support systems will be added to ical evaluation of a computer-controlled pressure support mode.
the designed ventilator to investigate the effects of these sys- Am. J. Respir. Crit. Care Med. 161(4), 1161–1166 (2000)
tems in the respiration of living being. These studies may 18. Bouadma, L.; Lellouche, F.; Cabello, B.; Taille, S.; Mancebo,
J.; Dojat, M.; et al.: Computer-driven management of prolonged
create future research-driven protocols. mechanical ventilation and weaning: a pilot study. Int. Care Med.
31(10), 1446–1450 (2005)
Acknowledgments This work was supported in part by the FUBAP- 19. Nemoto, T.; Hatzakis, G.E.; Thorpe, C.W.; Olivenstein, R.; Dial,
1911 and TGSD-0595 projects. The authors would like to thank Prof. S.; Bates, J.H.T.: Automatic control of pressure support mechanical
Servet KILINÇ and Asst.Prof. Kadri KULUALP for tracheotomy oper- ventilation using fuzzy logic. Am. J. Respir. Crit. Care Med. 160(2),
ation. 550–556 (1999)
20. Tehrani, F.T.: A new decision support system for mechanical venti-
lation. In: Proceedings of the 29th Annual International Conference
References of IEEE Engineering in Medicine and Biology Society, pp. 3569–
3572 (2007)
1. Perel, A.; Stock M.C.: Handbook of Mechanical Ventilatory Sup- 21. Tehrani, F.T.; Roum, J.H.: FLEX: A new computerized system for
port. 1st edn. Williams and Wilkins, Philadelphia (1992) mechanical ventilation. J. Clin. Monit. Comput. 22(2), 121–130
2. Clemmer, T.P.: Computers in ICU: where we started and where we (2008)
are now. J. Crit. Care 19(4), 201–207 (2004) 22. Rees, S.E.; Kjaergaard, S.; Thorgaard, P.; Egon, T.; Andreassen, S.:
3. Fagan, L.M.; Kunz, J.C.; Feingenbaum, E.A.; Osborn, J.J.: Exten- A physiological model based approach to medical decision support
sions to the rule-based formalism for a monitoring task. In: Buch- in the intensive care unit. In: Proceedings of the 25th Annual Inter-
canan B.G.; Shorthlife, E.H., (eds.) Rule-Based Expert Systems: national Conference of IEEE Engineering in Medicine and Biology
The MYCIN Experiments of The Stanford Heuristic Programming Society, pp. 432–433 (2003)
Project. Addision-Wesley, Reading (1985) 23. Stegmaier, P.A.; Brunner, J.X.; Tschichold, N.N.; Laubscher, T.P.;
4. Miller, P.: Goal-directed critiquing by computer: ventilator man- Liebert, W.: Fuzzy Logic Cough Detection: A First Step Towards
agement. Comput. Biomed. Res. 4, 422–438 (1985) Clinical Application. Fuzz Sys, IEEE W Cong on Comp Int., Pro
5. Carlo, W.A.; Pacifico, L.; Chatburn, R.L.; Fanaroff, A.A.: Effi- of the 3th IEEE Conf, pp. 1000–1005 (1994)
cacy of computer-assisted management of respiratory failure in 24. Kwok, H.F.; Linkens, D.A.; Mahfouf, M.; Mills, G.H.: SIVA:
neonates. Pediatrics 78, 139–143 (1986) hybrid knowledge and model based advisory system for intensive
6. Hernandez, C.; Moret-Bonillo, V.; Alonso-Betanzos, A.: ESTER: care ventilators. IEEE Trans. Inf. Tech. Biomed. 8(2), 161–171
an expert system for management of respiratory weaning therapy. (2004)
IEEE Trans. Biomed. Eng. 559–564 (1989) 25. Zhu, H.; Möller, K.: Ventilator control based on fuzzy-neural net-
7. Sittig, D.F.; Pace, N.L.; Gardner, R.M.; Morris, A.H.: Implemen- work approach. Bioinf. Biomed. Eng. ICBBE 747–750 (2008)
tation of a computerized patient advice system using the HELP 26. Tzavaras, A.; Weller, P.R.; Spyropoulos, B.: A neuro-fuzzy con-
clinical information system. Comput. Biomed. Res. 22(5), 474– troller for the estimation of tidal volume and respiration frequency
487 (1989) ventilator settings for copd patients ventilated in control mode. In:
8. Rudowski, R.; Frostell, C.; Gill, H.A.: A knowledge-based support Proceedings of the Annual International Conference of the IEEE-
system for mechanical ventilation of the lungs. The KUSIVAR EMBS, pp. 3765–3768 (2007)

123
 Author's personal copy
Arab J Sci Eng (2014) 39:4805–4813 4813

27. Wang, S.; Shaw, D.; Jih, K.S.: An intelligent control system for 30. Eroglu, F.; Eroglu, H.E.: Analgesia and anesthesia in rats. J. Clin.
ventilators. Med. Eng. Phys. 20, 534–542 (1998) Anal. Med. 1–5 (2011)
28. Nelson, D.S.; Strickland, J.H.; Jannet, T.C.: Simulation of fuzzy 31. Tanju, S.: Solunum Sistemi Hastalıklarında Deneysel Hayvan
control for management of respiratory rate in assist control mechan- Modelleri-Deney Hayvanı Kullanım Teknikleri. Türk Toraks
ical ventilation. In: Proceedings of 19th International Conference Derneği 13.yıllık Kongresi pp. 1–4 (2010)
on IEEE/EMBS, pp. 1104–1107 (1997)
29. Karakaya, A.; Karakas, E.: Performance analysis of PM synchro-
nous motors using fuzzy logic and self tuning fuzzy PI speed con-
trols. Arab. J. Sci. Eng. 33, 153–177 (2008)

123

View publication stats