www.ijecs.

in
International Journal Of Engineering And Computer Science ISSN:2319-7242
Volume 3 Issue 6 June, 2014 Page No. 6432-6437

Design and fabrication of low cost intelligent

wheelchair
Pradeep Kumar Rattewal, Parteek Kumar
M.Tech dept. of ECE Hindu College of Engineering
Sonipat, Haryana, India
[email protected]
[email protected]
Abstract A novel approach is proposed in this paper to

impart intelligence to a low cost smart wheelchair based on

embedded system. The sensors give the perceiving power to
the wheelchair and scientific inference engine in the
microcontroller gives the intelligent power of decision making
and its implementation to the wheelchair. This approach is
very effective as it does not involve the wastage of the
computational and working power of PC/Laptop, rather by
using the microcontroller based specific system we have saved
the operating power as well as the cost involved in designing.
This paper constitutes the circuit diagram of the proposed
prototype of the intelligent wheelchair with the algorithms for
decision making, table of comparison of features and the cost
of the final product.
Keywords- scientific inference engine; embedded system;
intelligent wheelchair.

I.

INTRODUCTION

Throughout the world, a number of persons lost their limbs in

accidents, wars and injuries of spinal cord. These people have
to rely on the aid of wheelchairs. There are many wheelchairs
available in the market with automatic power supply in the
wheels and touchpad/joysticks for the control of navigation.
Most of these wheelchairs require manual operation and an
extra person to look after the safeguard of the amputee. In
most of the cases persons suffering from such disabilities are
likely to go under emotional distress state and may take the
abnormal decisions which may result fatal. Further the
commercially available wheelchairs are expensive and devoid
of distinguishing between the user normal psychological states
and mentally disturb psychological state as well as between
the normal environment and the continuously changing
ambient environment. With advancement of technology the
persons can control the wheelchair simply by their voice
action, joystick and touchpad. The Voice controlled
wheelchair is determined by creating a speech recognition
system utilizing a speech recognition board and a
microcontroller [1]. Likewise touchpad [2] and joystick [3]
can be implemented but the guardian help is still required for
the safeguard of the patient. Moreover the amputees or aged
persons may or may not be effectively use these systems [4].
There is another big issue of distress state which make the
implementation of unusual decisions. Thus, to find out a way

to control the wheelchair without involving the hands and

imparting a decision making power, could be of a great help to
such persons. Here the most perfect solution comes out to be
the voice control, physiological state analyzing and
environmental state analyzing, self decision making
wheelchair. This motivates us to work in the direction of
design and implementation of prototype of low cost intelligent
wheelchair by distinguishing emotion, illness and environment
for elderly and physically challenged. Following are the
situation where traditional wheelchairs fail:
Handling Joystick/Touchpad: For the persons who suffer
from spasms and paralysis of extremities, the joystick or
touchpad is a useless. So, the voice command system may be
the good information transmission means to control the
navigation of the wheelchair by such users.
Emotional Distress/Disease State: Except the normal
wheelchair control, the morbidity and the exceptional emotion
also need to be considered fully. The wheelchairs operation
depends upon the instruction provided by the user. Under the
influence of Emotional Distress/Disease state the instruction
may result fatal. Thus users need to be continuously monitored
for such bad emotions or states.
Sudden change in Ambient Environment: The outside
environment and the risk cannot be decided completely by the
old and the disabled. A sudden introduction of any moving
object in path of wheelchair causes sudden decision reaction of
the user which in general case is a disable, old person with
slow response. In such case Wheelchair's intelligence can
lighten user's burden, to provide the safe movement safeguard.
Physiological Change in the User Health: While ambulate if
any physiological change happens, it could not easily be
detected until the user report the problem and doctor diagnose.
This may take a long time which may be crucial for the user.
Traditional wheelchairs lack such monitoring system.
II.

LITERATURE SURVEY

In early nineties PSUBOT (Portland State University ROBOT)

- a computerized electric wheelchair commanded by voice was
purposed. In this wheelchair control algorithms, navigation,
and human interface were described using 8086 based personal
computer [5]. Ronald H. Rockland purposed the Voice
Activated Wheelchair Controller (VAWC) to develop a
feasibility model for activating a wheelchair using a low-cost

Pradeep Kumar Rattewal, IJECS Volume 3 Issue 6 June, 2014 Page No.6432-6437

Page 6432

speech recognition system HM2007. A microcontroller was

programmed to provide user control over each command for
navigation [6]. Kayoko KOMIYA realized that for the people
who suffer from spasms and paralysis of extremities, the
joystick is useless device as a manipulating tool. They cannot
operate the joystick smoothly at all. So, he purposed voice
command system [7]. G. Pacnik et al purposed the
development of the intelligent wheelchair lab prototype
VOIC. VOIC was designed for physically disabled person,
who cannot control their movements and control the wheelchair
with the joystick [8]. Masato Nishimori et al developed a voice
controlled wheelchair. The user could control the wheelchair by
voice commands. A grammar-based recognition parser named
Julian was used in their system [9]. T. Z. Qi, T. J. Moir
presented a novel in-car design to recognize the driver's voice
and control in-car devices with non-stationary noise car
environment, a speech recognition kit with speech recognition
chip HM2007 [10] was used and With an adaptive Wiener
filter [11]. Akira Murai et al. proposed a functional voice
activated wheelchair with the solution of collision avoidance
function CAF by which wheelchair avoids the wall or obstacle
without voice command by using the information from two
kinds of sensor [12]. H.Uchiyama developed a semiautonomous
wheelchair
prototype,
which
increases
independent mobility for individuals with multiple disabilities,
specifically those who are wheelchair-bound and severely
vision impaired, by providing perceptual and navigational
capabilities [13]. Yuhong Zhu proposed in his paper, a novel
approach of designing a wheelchair by using simple voice
commands to control operations. A health diagnosis function
was used in his method to find the disease paroxysm of users,
to distinguish psychological and physical state, and to avoid
abnormal operation risk by disease and emotion [4]. Rajesh
Kannan Megalingam in his work proposed an Intelligent Home
Navigation System (IHNS) which comprises of a wheelchair,
voice module and navigation module [14]. Mohammed Faeik
Ruzaij et al succeed in developing an intelligent wheelchair to
help patients using speech recognition system to control the
movement of wheelchair in different directions by using voice
commands and also the simple movement of the patient's
fingers with keypad control. Automatic obstacle detection is
done using an ultrasound system [1].
Different parameters cause different effect on the vital statistics
of human body. People suffering from various physiological
and psychological disorders have body condition differ from
normal healthy people [15]. Different Sensors [16] and their
fusion help in driving Scientific Inference [17] which results in
control of the navigation of the proposed model of the
wheelchair.
III.

PROPOSED MODEL

The proposed model (Fig.1)consists of four modules viz. the

Sensing module, the User Control module, the Scientific
Inference module and the Navigation and Alert module.

Figure 1. Block diagram of Proposed Intelligent wheelchair

A. Sensing and Measuring module:

The purposed Sensing and Measuring module consists of three
sub module viz. Environment sensing, Physiology sensing, and
Voice sensing sub modules. The Sensing part helps to
determine the different input data which are analyzed in
Scientific Inference part to determine the disease or mental
distress state i.e. physiological state to psychological state as
well as the environmental conditions to take the final decision
for navigation and generation of alert signal.
Environment sensing Sub module: The Environment sensing
sub module consists of four types of sensors. These sensors
perceive the surrounding information for the intelligent
wheelchair which is analyzed to assist the navigation.
1. Obstacle sensing: Obstacles can be sensed by IR
Proximity sensor. The output of this sensor is fed to
Scientific Inference part to take further step [18].
2. Fast moving objects sensing: Ultrasonic Object
Detecting & Ranging sensor can be used for sensing
the sudden introduction of fast moving objects [19].
3. Sharp edge sensing: Sharp edges can be detected by
using Sharp IR Rangefinder [20]. The output is analog
signal which is converted in digital form for further
processing.
4. Fences and walls sensing: IR proximity sensors [18]
can be used to monitor the vicinity of the walls or
fences by mounting them at the sides of the
wheelchair .
Physiology sensing Sub module: Physiological parameters are
sensed and measured by different sensors as given below:
1. Breath rate measurement: An elastic neck clip with an
air bag can feel carotid directly and a thermister probe
is fixed on this clip by a holder. The number of pulses
is counted in microcontroller [21]. The normal range
is 15 breaths per minute. If the number of pulses
increase beyond 18 it is infer to disease state and
alarm is raised if the rate is higher than 20
breaths/minutes with an alert signal to the guardian.
2. Pulse rate measuring: Pulse rate can be measured by
Heart beat sensor of Sunrom Technologies, Isanpur,

Pradeep Kumar Rattewal, IJECS Volume 3 Issue 6 June, 2014 Page No.6432-6437

Page 6433

Gujarat, India [22]. Normal range is 72 beats/ minute.

The alarming range is 80 beats per minute.
3. Blood pressure measuring: Blood pressure can be
measured by modified Oximeter [21]. Normal Blood
pressure range is 120/80 systolic/diastolic. The
alarming range is 160/120.
4. Temperature measurement: Temperature can be
measured by thermopile sensor, which can be accurate
to a tenth of a degree. The thermopile sees the
eardrum and measures its infrared emissions. The
emission is converted into digital form [21]. Normal
body temperature is 37 the high temperature
considered in the proposed intelligent wheelchair is
beyond 40 .
5. Tremor sensing: For detecting Tremors, fits, epilepsy
etc special sensors can be incorporated in the elastic
neck clip [23]. If tremors are detected both alarm and
alert signal are raised.
6. Voice: To recognize the voice, HM2007 voice
recognition module [10] of Sunrom technologies,
Isanpur, Gujarat, India is used. The voice is an
important parameter to determine the physiological
state of the user by careful analysis.
These physiological parameters can be used to infer about the
psychological state of the user and to take the final decision for
the movement of the intelligent wheelchair.
B. User Command module:
The user can direct/command the intelligent wheelchair for
navigation by Joystick, Touchpad or by Voice commands.
Here Voice command module is used for command purpose.
The voice commands given by user can be recognized by the
HM2007 speech recognition module [10].
It is to be noted that voice is used here in two modules. First
to determine the psychological state of the user under
physiological parameter, and Second to command the
wheelchair for navigation.

heart beats (pulse rate), breathing rate, blood pressure

etc. along with abnormality in usual voice commands
[15]. There is a significant role of voice in detection of
emotional anomalies like length, strength, quality and
clarity of the spoken words.
3. Infer abnormal environmental situations: The sensors
sensing and measuring the environmental parameters
directly report the abnormal environmental situation in
initial as well as during the navigation state to take the
necessary control steps, alarm and alerts by the
Scientific Inference engine and the microcontroller.
Scientific Inference is derived at each point of time of the
operation of the intelligent wheelchair. With every
navigation command given by the user, the environmental
and the physiological parameters are sensed and infer to
oblige or to deny the command. Here it should be note that
it is not at all necessary to predict the actual disease but to
detect only the anomaly which could be reported to
microcontroller for taking the decision of further
navigation of the wheelchair. Fig. 2 shows the flowchart of
Scientific Inference engine implemented using Assembly
Language Program (ALP) on 89S52 microcontroller. This
flow chart of Scientific Inference engine shows the
elimination of the need of an extra person (attendant) who
assist the disable person for navigation. The data from
various sensing and measuring sub modules as well as
from the user control module serve as the input to the
Scientific Inference engine (Fig.2).
FLOW CHART OF THE SCIENTIFIC INFERENCE ENGINE
START

DATA

YES
YES

SHARP
EDGE
PRESENT

PULSE
RATE
HIGH
NO

SPEECH
NORMAL

YES

NO

NO

YES

BREATH
RATE
HIGH

SAFE
DISTANCE
FROM
OTHERS

START
NAVIGTION

NO

C. Scientific Inference Engine module:

It is the most significant module that imparts actual
intelligence to the wheelchair. Scientific inference is an
approach by which theories are constructed and logically
tested against the available facts. Scientific Inference starts
with theoretical statements and tested against the
observations to derive the final conclusion [17]. At every
measured and sensed value a limit of minimum or maximum
is set; if the limit is crossed then navigation as well as alert
and alarm decision is taken by infer in if-then-else conditions
of particular situation. It may be important to indicate here
that the single parameter alone cannot be able to infer
correctly the psychological state of the user; so it necessary
to consider a combination of physiological states to derive a
final psychological state and to take the final decision.
1. Infer disease state: Abnormality of breath, quicker
pulse, higher temperature, high/low blood pressure
may be disease precursors. These physiological
situations from the physiology sensing sub module
can infer the psychological state of the user. Likewise
different physiological parameters taken together
along with the knowledge of patient history can be
used to predict the most likely state of the disease.
2. Infer emotional anomalies: During emotional state
there are significant physiological changes in the body
of a person. These may include sudden rise or fall in

FROM SENSORS

NO

NO
YES

YES

YES

BLOOD
PRESSURE
HIGH

OBSTACLE
DETECTED
YES

NO

NO
YES

TREMORS
PRESENT

YES

HIGH
TEMPER
ATURE

NO

ABNORMAL
HEART
BEAT

VICINITY
OF FENCES
YES

NO

STOP NAVIGATION

NO
ALARM AND ALERT

END

Figure2: FLOW CHART OF SCIENTIFIC INFERENCE ENGINE IMPLEMENTED USING ALP

Figure
2. Flow chart of Scientific Inference Engine

The Scientific Inference engine at each step of input, compare

the data with the prefixed value and decides to go for further
steps following the same routine of comparison. First all the
physiological parameters are checked and then with the
beginning of the navigation all environmental parameters are
monitored. If any of the parameter violates the prefixed value
then navigation is stopped and alarm and alert signal is raised.
If all the parameters are up to the safe limits then the navigation
command of the user is followed to guide the intelligent
wheelchair.
D. Navigation and Alert Module:
Navigation and Alert module consists of two sub modules viz.
Navigation sub module and Alert sub module.
Navigation Sub module: It has Motor driver L293D IC which
finally execute the decision of the intelligent wheelchair by
controlling the direction of rotation of the motors attached with

Pradeep Kumar Rattewal, IJECS Volume 3 Issue 6 June, 2014 Page No.6432-6437

Page 6434

the wheels. L293D IC is actually an H-bridge circuit controlled

directly by the microcontroller [25].
Alert Sub module: Alert sub module has GSM module [26] to
inform the guardian by sending an SMS on his mobile on
behalf of the user when alert is evoked. It has an alarming
signal too in the form of a Buzzer. Buzzer is raised when there
is violation of the prefixed parameter infer by the Scientific
Inference engine. Buzzer is raised for few seconds but if the
situation is not changed it automatically evoke the alert sub
module which send SMS to the guardian for immediate help.
IV.

RESULTS AND DISCUSSIONS

temperature and voice of the user. If all parameters reported to

have deviation from the normal pre-stored values then
Inference, user is suffering from Anxiety is derived and
navigation is not carried out else Inference, user is mentally
Sound is derived and command from the user is followed for
navigation of the wheelchair. Program is written in Assembly
language and Inference is derived for each possible situation.
Here the Simulation and results of Inference Anxiety and
Normal situation are shown Fig. 5 to Fig.7. The breath rate
sensor and heart beat rate sensor are connected to Port1 with
pinP1.5 and P1.6 respectively.

This section discusses the results obtained after designing and

fabrication of the intelligent wheelchair prototype. It includes
circuit diagrams, software implementation and the performance
analysis in detail along with the table of cost of the proposed
work. The Scientific Inference Engine which gives capabilities
of intelligence to the wheelchair system is implemented on the
IDE Keil Software Version3. The program codes are written in
Assembly Language Programming and the circuit diagrams are
designed using the Express PCB Electronics Design Software.
Circuit Diagram and Working: The purposed intelligent
wheelchair consists of 9 sensors including the speech
recognition sensor module, connected at different ports and

Figure 4.Flow chart of Inference Anxiety

For normal condition:

Port0: Forward command ; Port1: Pulse rate, Brearh rate,
Motor ; Port2: Temperature normal; Port3: B.P sensor

Figure 3. Circuit diagram of Intelligent Wheelchair

pins of 89S52 microcontroller as shown in the circuit diagram

of the purposed intelligent wheelchair (Fig.3)., The peripherals
execute navigation are connected at Port1.0, Port1.1, Port1.2
and Port1.3. To execute stop all bits are set include 8255PPI,
ADC0804, L293D motor driver IC, crystal oscillator of
11.0592MHZ etc. The data from the sensor and the command
from the user is converted into digital coded form(where
necessary) and fed to microcontroller where these get stored at
different memory locations and scientific inference module take
the final decision based on the received data. The data is
continuously updated by the sensors while in navigation or at
rest. The decision is implemented by the motor driver by
performing navigation. If any anomaly appears whether in
physiological, environmental or user command and last for
more than the predefined time then alarm and alert signals are
evoked. HM2007 is attached to Port0. The body temperature is
measured in analog form and converted in digital form using
ADC is connected at Port2. The motors to to move in forward
direction all positive polarity are high, to move in reverse all
negative polarity are high and so on.
Inference Anxiety Results: Inference Anxiety results are shown
in flow chart form and implemented using ALP (Fig.4). The
Inference Anxiety is derived from the combination of
parameters of pulse rate, breath rate, blood pressure, body

Figure 5. Software Result of Inference Normal

For Normal Condition with different command:

Port0:Stop command; Port1: Pulse rate, Breath rate, Motor
control; Port2: Temperature normal; Port3: B.P sensor

Pradeep Kumar Rattewal, IJECS Volume 3 Issue 6 June, 2014 Page No.6432-6437

Page 6435

COST OF PRODUCT: THE COST OF THE PROTOTYPE INTELLIGENT

WHEELCHAIR EXCLUDING THE CHASSIS AND POWER UNIT COMES
TO BE TABLE I. NICHE OF INTELLIGENT WHEELCHAIR

Situations
with user
and
environment

Figure 6. Software Result of Inference Normal with different command

Abnormal Condition: Anxiety

Port0: Mismatch Speech; Port1: Pulse rate, Breath rate,
Motor control; Port2: Temperature is slightly high; Port3:
B.P sensor

Wheelchair
with
joystick
[3]

Wheelchairs Responses
Wheelchair
Wheelchair
with voice
with
control
environment
[1]
sensors
[27]
Yes
Yes

Wheelchair
with
touchpad
[2]

Only lower
limb affected

Yes

Yes

Upper limb is
also affected

No

No

Yes

Speech is
affected

Yes

Yes

Abnormal
mental
condition
Handling in
Tremors

No

Computer
based
wheelchair
[28]

Proposed
Intelligent
wheelchair

Yes

Yes

No

Yes

Yes

No

Yes

Yes

No

No

No

No

Yes

Yes

No

No

No

No

Yes

Yes

Avoid
Pits/Obstacles

Hard

Hard

Hard

Easy

Easy

Easy

Safe distance
from others

No

No

No

Yes

Yes

Yes

Speed control

Yes

Yes

No

Yes

Yes

No

Evoke
alarm/alert

No

No

No

No

Yes

Yes

Self navigate

No

No

No

No

Yes

Yes

Monitor
health

No

No

No

No

Yes

Yes

Processing
speed

High

Slow

Slow

Figure 7. Software Result of Inference Anxiety

V. PERFORMANCE EVALUATION
Performance evaluation can be done on the basis of the
following four categories each. These are:
Ease of operation: With the incorporation of various sensors to
recognize the user commands, mental state and the
environmental situations, it become easy to operate the
intelligent wheelchair without the support of others hence it is
user friendly. Voice commands simply avoid the use of
Touchpad/Joystick and ambient environment sensors keep the
safeguard of the user.
Size of extra hardware: Purposed intelligent wheelchair extra
hardware is reduced by the use of microcontroller as compared
with the smart PC incorporated wheelchairs. The weight of
smart PC ranges in 2.0 kilograms to 3.5 kilograms while
intelligent PCB weighs less than 0.5 kilograms.
The computational power of PC: The designing of the specific
embedded system saves the computational as well as the
working power of the PC that are used in smart wheelchairs for
controlling the navigation.
Niche of the intelligent wheelchair: Here are few possible
situations and the working reactions of different wheelchairs
are compared in tabulate form (Table I) to show the niche of
the proposed intelligent wheelchair.

Slow

Very High

Slow

INR 9,940 in july 2013 (TABLE II).

S.
N
O
.
1.
2
3
4
5

6
7
8
9
1
0
1
1
1
2
1
3

ITEMS AND COST

TOTAL
ITEM NAME

T
A
IR PROXIMITY
SENSOR
B
BREATHE RATE
L
SENSOR
E
DISTANCE
SENSOR
TEMPERATURE
I
SENSOR
I
BLOOD
.
PRESSURE
SENSOR
TREMOR
T SENSOR
PULSE
A RATE
SENSOR
B
SHARP EDGE
L
SENSOR
E
SPEECH
PROCESSOR
BUZZER
O
GSMFMODULE
MICROCONTROL
C
LER
O
ALLIED
S
CIRCUITRY
T
SUM(INR)

Pradeep Kumar Rattewal, IJECS Volume 3 Issue 6 June, 2014 Page No.6432-6437

QUANTITY

COST/ITEM

100

300

40

40

800

800

60

60

250

250

40

40

900

900

600

600

5000

5000

30

30

1500

1500

70

70

350

350
9,940

Page 6436

[9]
[10]
[11]

[12]

[13]

[14]

REFERENCES
[1]

[2]
[3]

[4]

[5]
[6]

[7]

[8]

Ruzaij
Mohammed
Faiek
and
S.
Poonguzhali,
Design and implementation of low cost intelligent wheelchair, Recent
Trends In Information Technology (ICRTIT), 2012 Publication Year:
2012, Page(s): 468 471.
Switch-It, Inc. Touch drive.
http://www.switchit-inc.com/pages/Touch%20Drive.html
Thomas Rofer
Controlling an Automated Wheelchair via
Joystick/Head-Joystick Supported by Smart Driving Assistance, 2009
IEEE 11th International Conference on Rehabilitation Robotics Kyoto
International Conference Center, Japan, June 23-26, 2009
Yuhong
zhu ,
Controlling the Intelligent Wheelchair by
distinguishing emotion, illness and Environment
Artificial
Intelligence,
Management Science and Electronic Commerce
(AIMSEC), 2011 2nd International Conference on Publication Year:
2011, Page(s): 2016 2019
Kevin B. Stanton , PSUBOT-a voice-controlled wheelchair for the
handicapped, Publication Year: 1990, Page(s): 669 - 672 vol.2.
Ronald H. Rockland, Stanely Riesman,.
Voice activated wheelchair controller, Bioengineering Conference,
1998. Proceedings of the IEEE 24th Annual Northeast Publication Year:
1998, Page(s): 128 129
Kayoko Komiya, Kiyosi Morita, Kouu Kagekawa and Kenji Kurosu,
Guidance of a wheelchair by voice, Industrial Electronics Society,
2000. IECON 2000. 26th Annual Conference of the IEEE Volume: 1
Publication Year: 2000, Page(s): 102 - 107 vol.1
G.Pacnik
,
K.
Benkic
and
B.
Brecko,
Voice operated intelligent wheelchair VOIC, Industrial Electronics,
2005. ISIE 2005. Publication Year: 2005, Page(s):1221 - 1226 vol. 3

[15]
[16]
[17]
[18]
[19]
[20]
[21]

[22]
[23]

[24]
[25]
[26]
[27]

[28]

Nishimori , Voice controlled intelligent wheelchair, 2007 Annual

Conference Publication Year: 2007, Page(s): 336 340
HM2007 Data sheet, www.imagesco.com
T.Z. Moir T.J. Qi,
Automotive Speech Control in a Non-Stationary
Noisy Environment, Mechatronics and Machine Vision in Practice,
2008. M2VIP 2008. 15th International Conference on Publication Year:
2008, Page(s): 374 377
A.Murai,M.Mizuguchi, Masato Nishimori,Takeshi Saitoh, T.Osaki and
R. Konishi, Voice activated wheelchair with collision avoidance
using sensor information, ICCAS-SICE, 2009 Publication Year: 2009,
Page(s): 4232 4237
H.Uchiyama , W.D.Potter,M.A.Covington, J.Tarver and R.Eunice,
Perceptual navigation for semi autonomous wheelchair operations,
www.intechopen.com/download/pdf/5308
MegalingamRajeshKannan,Ramesh Nammily Nair and Sai Manoj
Prakhya,
Automated voice based home navigation
system for
the elderly and the physically challenged, Advanced Communication
Technology (ICACT), 2011, 13th International Conference
on Publication Year: 2011, Page(s): 603 608
Harrisons Principles of Internal Medicines edition 16th vol. 1&2.
Sensors 2010, 10, 1399-1422; doi: 10.3390/s100201399
www.mdpi.com/journal/sensors
http://cooley.libarts.wsu.edu/schwartj/pdf/logicofscientificinquiry.pdf
IR Proximity Sensor, http://www.sunrom.com/p-554.html
Ultra Sonic object detection and range finder sensor,
www.sunrom.com/p-710.html
IR Sharp range Sensor, http://www. robokits.co.in
Parekh Dhvani, Designing Heart Rate, Blood Pressure and Body
Temperature Sensors for Mobile On-Call System (2010) EE4BI6,
Electrical Engineering Biomedical Capstones. Paper 39.
http://digitalcommons.mcmaster.ca/ee4bi6
Heart beat Sensor, www.sunrom.com/p-556.html
Liting Yao, Physiological system modeling applied to an
intelligent wheel chair, Information Acquisition in 2005 IEEE
International Conference on Publication Year: 2005
Tremor Sensor, www.sunrom.com/p-1256.html
L293D datasheet, www.datasheets360.com/L293D
GSM module, www.nskelectronics.com/gsm-module.html
G. Pires, Autonomous Wheelchair for Disabled People, in proc. IEEE
Int. Symposium on Industrial Electronics (ISIE97), Guimaraes, 797801.
Richard Simpson , The Smart Wheelchair Component System, JRRD
Volume 41, Number 3B, Pages 429442, May/June 2004 Journal of
Rehabilitation Research & Development

Pradeep Kumar Rattewal, IJECS Volume 3 Issue 6 June, 2014 Page No.6432-6437

Page 6437