Micro Matlab PDF
Micro Matlab PDF
Micro Matlab PDF
Abstract — Powered wheelchairs with the standard joystick interface are unable to control by many people. A voice
controlled wheelchair can provide easy access for physical disabled person who cannot control their movements
especially the hands. The powered wheelchair depends on the motor control and drive system which consists of ARM
Processor LPC2138 and DC Motor. Once the voice recognition system recognizes the voice commands in comparison
to the prestored memory, the respective coded digital signals would be sent to ARM Processor which then controls the
wheelchair accordingly.
I. INTRODUCTION
The goal of this smart wheelchair project is to enhance an ordinary powered wheelchair using sensors to perceive the
wheelchair's surroundings, a speech interface to interpret commands. Intelligent wheelchair will play an important role in
the future welfare society. The use of intelligent wheelchair encourages the view of the machine as a partner rather than
as a tool. The population of people with disabilities has risen markedly during the past century. As the data come from
the National Health Interview Survey (NHIS), two distinct trends have contributed to the increasing overall prevalence of
disability: a gradual rise, due largely to demographic shifts associated with an aging population, as well as a rapid
increase that is due to health impairments and accidents. Many individuals have problems to use a conventional
wheelchair. A recent clinical survey indicated that 9%-10% of patients who received power wheelchair training found it
extremely difficult or impossible to use it for their activities of daily living, and 40% of patients found the steering and
maneuvering tasks difficult or impossible. These people, suffering from motor deficits, disorientation, amnesia, or
cognitive deficits, are dependent upon others to push them, so often feel powerless and out of control. Intelligent
wheelchair has the potential to provide these people with effective ways to alleviate the impact of their limitations, by
compensating for their specific impairments. In particular, robotic wheelchairs may help in maneuvering a wheelchair
and planning motion. Recently, research of assistant robots is also emerging field of robotic applications.
Tyre
1
Voice
RS
Recogniti Microcontro DC
on 23 ller Based Motor
System 2 Wheelchair interfa Tyre
ce 2
In our project, voice recognition system is used as user interface. The block diagram of the intelligent wheelchair with
motor drive and control system is shown in figure 1.
Here we are making a speech recognition based wheel chair for patients. The patients who cannot walk and have to use a
wheel chair can navigate the wheel chair by their voice. Here we are using the voice recognition using pattern recognition
in MATLAB s/w.
Input Data Patter Featu Add Input Data Patte Feat Find
Decomp n re Record Decomp rn Match
ure
Audi osition Extra Extra to Audio osition Extra Extr in
o ction ction Databa
ction Datab
se actio
ase
n
Fig2 Procedure for Speech Feature’s Extraction. Fig3 Procedure for Speech Recognition
Pattern recognition aims to classify data (patterns) based on either a priori knowledge or on statistical
information extracted from the patterns. The patterns to be classified are usually groups of measurements or observations,
defining points in an appropriate multidimensional space. This in contrast to pattern matching, where the pattern is
rigidly specified. A complete pattern recognition system consists of a method that gathers the observations to be
classified or described; a feature extraction mechanism that computes numeric or symbolic information from the
observations, and a classification or description scheme that does the actual job of classifying or describing observations,
relying on the extracted features. The classification or description scheme is usually based on the availability of a set of
patterns that have already been classified or described. This set of patterns is termed the training set and the resulting
learning strategy is characterized as supervised learning. Learning can also be unsupervised, in the sense that the system
is not given an a priori labelling of patterns, instead it establishes the classes itself based on the statistical regularities of
the patterns. The classification or description scheme usually uses statistical approach. Statistical pattern recognition is
based on statistical characterizations of patterns, assuming that the patterns are generated by a probabilistic system. A
wide range of algorithms can be applied for pattern recognition, from very simple Bayesian classifiers to much more
powerful neural networks. An intriguing problem in pattern recognition yet to be solved is the relationship between the
problem to be solved (data to be classified) and the performance of various pattern recognition algorithms (classifiers).
Four wheels are used in the wheelchair for proper balancing. The movement of wheels is controlled by DC motors
which are attached to the wheelchair. Two wheels located on left side of the wheelchair are controlled by one motor and
similarly the wheels on the right side are controlled by the second motor.
The other circuitry built into the wheelchair includes the transmitter and receiver circuits and the obstacle detection
circuit. It involves two IR signal emitters which emit IR signals continuously when some obstacle appears in front of the
wheelchair, these IR signals are obstructed, and reflected back. These reflected signals are then detected by the IR sensor
V. Results:
Fig 8: Wheelchair
References:
[1] S.A. Chhabria and R.V. Dharaskar ‘Multimodal Interface for Disabled Persons’,international Journal of
Computer Science and Communication-January-June 2011,
[2] R.C. Simpson, ‘Smart Wheelchairs: A Literature Review’, J. Rehabil. Res. Develop., 42, pp. 423-436, 2005.
[3] J.Z. Yi, Y.K. Tan, Z.R. Ang,’ Microcontroller Based Voice-Activated Powered Wheelchair Control’ ACM 2007
ISBN: 978-1-59593-852-7.
[4] L. Fehr, W. Edwin Langbein, and S.B. Skaar, ‘Adequacy of Power Wheelchair Control Interfaces for Persons with
Severe Disabilities: A Clinical Survey’, J. Rehabil. Res. Develop, 37 (3), pp. 353-360, 2000.
[5] Yasunari Obuchi, Multiple-Microphone Robust Speech Recognition Using Decoder-Based Channel Selection,
Advanced Research Laboratory, Japan, 2004
[6] Javier Hernando and Climent Nadeu, Speech Recognition In Noisy Car Enviornment Based On OsaLPC
Representation And Robust Similarity Measuring Techniques, Signal Theory and comm.. Dept., Spain, 1994
[7] Shahina, B. Yenanarayana and M.R. Kesheory, Throat Microphone signal for speaker recognition