VOICE CONTROLLED WHEELCHAIR FOR THE PHYSICALLY DISABLED PERSONS

Republic of the Philippines

Pangasinan State University

Urdaneta City Campus

VOICE CONTROLLED WHEELCHAIR

FOR THE PHYSICALLY DISABLED PERSONS

A Design Project

Presented to

The College of Engineering and Architecture

Computer Engineering Department

In Partial Fulfillment

Of the Requirements for the Degree

Bachelor of Science in Computer Engineering

Collado, Rizelle B.

Taaca, Marianne Rhyngel G.

Zorilla, Renie Grace C.

 VOICE CONTROLLED WHEELCHAIR FOR THE PHYSICALLY DISABLED PERSONS

Chapter IV

PROJECT PRESENTATION

In this chapter, the hardware and software components of the developed system

are introduced and described in depth. Afterwards the working system will be explained

thoroughly together with the results that were collected during the testing for the accuracy in

maneuvering the wheelchair and the response time in performing the movement command.

Proposed System

The proposed system made use of the Easy VR Module. It is in-charge for the recognition

of the voice commands as is received on the microphone included with the module. Whenever a

voice command is fed in the microphone, the Voice Recognition Unit assesses this and after

being recognized, decisions are formed in the Arduino Microcontroller. Decision-making

involves determining the function to be performed, whether Forward, Backward, Left, Right or

Stop. The decisions made are sent as control signals. From the Microcontroller, control signals

flow into the Motor Driver.

Based on the control signals the Motor Driver has received from the Microcontroller, the

Motor Driver passes these as output signals. These output signals answer the question of how or

on what direction the DC motors move, the output being the movement of the wheelchair.

1
 VOICE CONTROLLED WHEELCHAIR FOR THE PHYSICALLY DISABLED PERSONS

EASY VR
MODULE
FORWARD

BACKWARD

RIGHT

LEFT

STOP BATTERY

MICROPHONE

USER’S VOICE

MOTOR DRIVER
ARDUINO UNO SHIELD
R3

WHEELCHAIR

DC MOTORS

FIGURE 4.1 Block Diagram of the System

2
 VOICE CONTROLLED WHEELCHAIR FOR THE PHYSICALLY DISABLED PERSONS

Description of the Components

I. Hardware Components

a. Arduino Uno

A microcontroller board based on the ATmega328P, it has 14 digital

input/output pins (of which 6 can be used as PWM outputs), 6 analog inputs, a 16

MHz quartz crystal, a USB connection, a power jack, an ICSP header and a reset

button. It contains everything needed to support the microcontroller; simply

connect it to a computer with a USB cable or power it with an AC-to-DC adapter

or battery to get started.

FIGURE 4.2 Arduino Uno R3

3
 VOICE CONTROLLED WHEELCHAIR FOR THE PHYSICALLY DISABLED PERSONS

b. EasyVR Module

EasyVR 3.0 is a multi-purpose speech recognition module designed to add

versatile, robust and cost effective speech and voice recognition capabilities to

virtually any application. EasyVR is the third generation version of the successful

VRbot module and builds on the features and functionality of its predecessor. In

addition to the EasyVR 3.0 features like up to 32 user-defined Speaker Dependent

(SD) commands and 26 built-in speaker independent (SI) commands for ready to

run basic controls, the shield has an additional audio line-out/headphone jack, and

access to the I/O pins of the EasyVR module.

FIGURE 4.3 EasyVR Module

4
 VOICE CONTROLLED WHEELCHAIR FOR THE PHYSICALLY DISABLED PERSONS

c. Motor Driver Shield

The Adafruit Motor Shied V1 that is able to power many simple to

medium-complexity projects. It has 2 connections for 5V ‘hobby’ servos and can

connect up to 4 bi-directional DC motors with individual 8-bit speed selection. It

has big terminal block connectors to easily hook up wires and power. It is tested

compatible with Uno, Mega, Diecimila and Duemilanove.

FIGURE 4.4 Motor Driver Shield

5
 VOICE CONTROLLED WHEELCHAIR FOR THE PHYSICALLY DISABLED PERSONS

d. DC Motors

Direct Current Motor is a fairly simple electric motor that uses electricity

and a magnetic field to produce torque, which causes it to turn. At its most simple,

it requires two magnets of opposite polarity and an electric coil, which acts as

an electromagnet. The repellent and attractive electromagnetic forces of the

magnets provide the torque that causes the motor to turn.

FIGURE 4.5 DC Motors

e. Battery

A battery is an alternative to a line-operated power supply; it is

independent of the availability of mains electricity, suitable for portable

equipment and use in locations without mains power. A battery consists of several

electrochemical cells connected in series to provide the voltage desired. Batteries

may be primary (able to supply current when constructed, discarded when

6
 VOICE CONTROLLED WHEELCHAIR FOR THE PHYSICALLY DISABLED PERSONS

drained) or secondary (rechargeable; can be charged, used, and recharged many

times).

The primary cell first used was the carbon-zinc dry cell. It had a voltage of

1.5 volts; later battery types have been manufactured, when possible, to give the

same voltage per cell. Carbon-zinc and related cells are still used, but the alkaline

battery delivers more energy per unit weight and is widely used. The most

commonly used battery voltages are 1.5 (1 cell) and 9V (6 cells).

Various technologies of rechargeable battery are used. Types most

commonly used are NiMH, and lithium ion and variants.

II. Software Components

Arduino 1.6.7

The opne-source Arduino Software (IDE) makes it easy to write code and

upload it to the board. It runs on Windows, Mac OSX, and Linux. The

environment is written in Java and based on Processing and other open-source

software. This software can be used with any Arduino board.

FIGURE 4.6 Arduino IDE

7
 VOICE CONTROLLED WHEELCHAIR FOR THE PHYSICALLY DISABLED PERSONS

Explanation of the System Working

Effectiveness Testing of the Developed System

Chapter 2

REVIEW OF RELATED LITERATURE AND STUDIES

This chapter is intended for the compilation of the literatures and studies, from local and

foreign authors, taken in relation to the proposed study. These said literatures and studies

provided the researchers as much as necessary knowledge and idea in designing the proposed

project.

Related Literature

The related literatures hereunder are the result of collecting, selecting and reading of

research findings in connection with the proposed system and its components contained in books,

published journals, articles, magazines and internet resources.

a. Foreign Literature

8
 VOICE CONTROLLED WHEELCHAIR FOR THE PHYSICALLY DISABLED PERSONS

The book entitled “Medical Legal Aspects of Medical Records”, by Patricia W.

Iyer, Barbara J. Levin, and Mary Ann Shea, 2006, discussed the advantages and

disadvantages of voice recognition software as used for dictation of medical records. The

speech or voice recognition software, which has evolved over the years from its

introduction in 1994, uses a microphone attached to a computer and software that

transfers speech into text. The user of the software has the opportunity to train the

software to recognize words.

Advantages include:

 Documents produced with voice recognition software are immediately available

for review. The user sees the text on the screen and can correct errors and finalize

the report.

 Use of voice recognition software involves minimal if any typing, making it ideal

for dyslexics and those whose typing abilities are nonexistent or impaired by

disorders of the hand.

 Voice recognition software may be effectively used by visually impaired people,

permitting transmission of electronic information in ways not otherwise possible.

 As the software has evolved, the accuracy of the recognition has improved.

 The software is useful for short memos or letters.

Disadvantages include:

 Many find the software difficult to learn and cumbersome to use. A proficient

typist may initially find that the software is more time consuming to use than a

9
 VOICE CONTROLLED WHEELCHAIR FOR THE PHYSICALLY DISABLED PERSONS

keyboard. Time has to be devoted to training the software and working through

the learning curve.

 The software requires a powerful computer.

 Some physicians using the voice recognition recognize that their productivity and

efficiency are initially dramatically decreased. A good touch typist can output

eighty to one-hundred words per minute. The typical person speaking clearly will

only say about forty words per minute. The software may actually result in a

decrease in productivity. The physician may see fewer patients because more time

is spent on dictation, resulting in equal or higher costs, reduced revenues, and

increased frustration.

 Dictation increases the noise level in the work environment.

 Sensitive information may be overheard by others in open areas.

A published review written by Larry Magid, was posted by Scott Conroy, entitled

“Voice Recognition Software Put to Test”. According to Magid, he wasn’t interested in

voice recognition software before until he broke his elbow and he became physically

challenged, unable to type with both hands. After some healing and a new cast, He again

can type but during the interim he had both an incentive and an opportunity try out

Dragon Systems NaturallySpeaking 9 as well as the speech recognition feature that will

be included in Vista, the Windows operating system popular at that time.

For the most part he found both the Vista application and NaturallySpeaking to be

accurate and easy to use. To their credit both programs are accurate and intelligent in that

they recognize not only words but also allow you to issue commands. And because the

10
 VOICE CONTROLLED WHEELCHAIR FOR THE PHYSICALLY DISABLED PERSONS

computer is doing the typing it's less likely to misspell words. There's no question that the

Preferred ($199) version of NaturallySpeaking is more sophisticated than the free voice

recognition application that will ship with Windows Vista. It has support for multiple

languages and special vocabularies and works with portable dictation equipment.

Nuance's $99 standard edition also does a good job recognizing speech and lets you

launch, switch between and control programs with the sound of your voice. Both versions

come with a headset that does a good job picking up your voice. In this review, he wasn’t

writing, he was “speaking” using the application in Vista. At first in using the program,

he admitted that it was hard to get through a paragraph without at least one mistake. But

now, he gets about 99% accurate, which actually isn't bad.

While in the case of Janet Kornblum, a technology writer for USA Today, she has

been using successive versions of NaturallySpeaking for several years. Although she

sometimes does use the keyboard, she prefers to "speak" her articles and email because

she suffers from a repetitive strain injury that makes it harder to type. She said that the

software as improved dramatically over the years but, she tells some funny stories about

mistakes which, if not corrected, could have gotten her into trouble.

In addition to training the software, Kornblum said that she have had to train herself how

to write by speaking which is really different than writing by typing.

From the article, “Time is right for voice recognition”, by Diane Jermyn posted

last March 24, 2010, it talked about the developed Voice on the Go.

The founding employees of the Toronto-based company saw the need coming for

their product - an in-car system that enables a driver to e-mail, text, Facebook, Tweet and

11
 VOICE CONTROLLED WHEELCHAIR FOR THE PHYSICALLY DISABLED PERSONS

more while driving, hands-free and by voice on any mobile phone - and pounced on it as

a killer idea.

Voice on the Go, which has been in development since 2004, came on the market

in 2009. Voice on the Go is available to consumers and professionals, as well as

telecommunications carriers and resellers, in seven languages and in 60 countries around

the world.

The biggest challenge in developing Voice on the Go was creating high quality

voice recognition and making it so that customers wouldn't need training to use it.

Mr. McLeod stated that voice recognition systems generally get a bad rap. It’s

when people call big phone companies or airlines for service, they've often had such a

bad experience [with voice recognition] that they fear or loathe voice systems. For him,

getting those things right so that it would be natural and also to make customers

comfortable with the voice technology was the key.

Their design was intended for drivers, but they are going to have a small

following among the visually impaired too. For Mr. McLeod they will be able to speak

and listen to their e-mails and communicate with friends and family, even if they've never

had a computer. All they need to do is use their cellphone and talk into it.

The essay, “Speech Recognition Technology and its Benefits to the Disabled

Community”, explained that the speech recognition technology was originally designed

as a tool to ease the often heavy paper work loads in professions such as medicine or law.

But it changed to a new technological push which is assisting those with disabilities.

12
 VOICE CONTROLLED WHEELCHAIR FOR THE PHYSICALLY DISABLED PERSONS

People suffering from a variety of disabilities including muscular dystrophy, spinal cord

injury or cerebral palsy can benefit from such software.

Good speech recognition applications not only allows one to transform the spoken

word into text, but also allows the user to command nearly every program in the

computer; surfing the web and navigating the windows desktop and folder trees are some

examples. Because of this, voice recognition technology can be extremely helpful to

people with disabilities, if they are at all computer-savvy.

In the article entitled, “Talk vs. Type: Taking Another Look at Voice

Recognition”, by Marisa Torrieri, as posted on July 8, 2011, voice recognition

technology has evolved over the last ten years; today it's much more sophisticated and

accurate Like EHRs and mobile devices. This may be attributed, at least in part, to better

microphones that come with voice recognition software packages. Microphones don't

pick up as much background noise, so what is really being said is actually recorded.

Kutza also said that ambient noise, the nemesis of speech-enabled applications, is

being managed much better due to the development and implementation of smarter noise

reduction technologies. In addition, the technology can also do more things.

Physicians talking at their EHRs will find that voice recognition technology also

responds to vocal commands so a physician can navigate her EHR's fields without lifting

a finger. The technology analyst, West Richel, added that companies making the

technology are working on software they hope will not only transcribe the spoken text,

but also figure out which fields in a patient's chart to fill in.

13
 VOICE CONTROLLED WHEELCHAIR FOR THE PHYSICALLY DISABLED PERSONS

Nancy Lindo-Drusch, a physician who works at a small practice in Appleton,

Wis., says the voice-activated EHR navigation saves as many as five minutes per visit.

She also added that he more you use it, the more it gets those big words. If it makes a

mistake, you can [program a change].

In addition to having more internal features, the technology is adaptable to a

broader range of external devices, such as smart phones.

b. Local Literature

Wheelchairs in the Philippines

In an Inquirer.net article, posted on February 24, 2013, by Nathaniel R. Melican,

entitled, “PWDs can now live life in the fast lane”, NGO introduced a locally designed

e-wheelchair. In marking the 40th anniversary of the Tahanang Walang Hagdan Inc.

(TWH), the introduced their own version of an electricity-powered wheelchair aimed at

increasing the mobility of the differently-abled.

According to the TWH spokesperson Maricel Abary Candole, it was designed by

Filipino wheelchair users for other Filipino wheelchair users as well. The controls are

easy to reach and also easy to manipulate, the motor is silent and the whole thing is easy

to use.

It is capable, however, of traveling from 15 to 20 kilometers on a single charge of

its zero-maintenance lead-acid gel batteries with a top speed of around 15 kilometers per

14
 VOICE CONTROLLED WHEELCHAIR FOR THE PHYSICALLY DISABLED PERSONS

hour. It takes around five to eight hours for the batteries to fully charge. Handlebars

enable the user to switch the device on and off, brake and control its direction and speed.

According to her, the e-wheelchair is very much adapted to Philippine conditions, such as

our rugged roads, which could be challenging to navigate sometimes.

Candole said the e-wheelchair would benefit people who travel long distances

every day or those who have difficulty using their hands to turn the wheels such as those

suffering from polio.

Modules for Voice Recognition

A voice recognition module is one product almost all electronics enthusiasts want

to have. However, only a handful of specialty manufacturers build this kind of board

making them hard to find and usually sold expensively.

According to a blog, a review has been posted on March 23, 2013 by Enrison

Reinier, about the e-gizmo’s Voice Recognition VR Module. From the last update of the

e-gizmo’s site on June 3, 2015, the price comes at Php 1,999.00.

Following is a short summary of the VR module features:

 Supports up to 15 speaker-dependent SD voice commands

o Organized as 3 groups of 5 voice commands each. Due to limited capacity

of the on board voice controller, it can only process one group, or 5 voice

commands at a time. The host controller takes the responsibility of loading

15
 VOICE CONTROLLED WHEELCHAIR FOR THE PHYSICALLY DISABLED PERSONS

the appropriate voice command set. Each SD voice command can be up to

1.3 seconds long.

 Non-volatile voice commands storage

o The module retains all voice commands prints even after power cycling.

Voice commands will only be replaced or erased at the instruction of the

host controller.

 UART TTL interface

o This allows it to connect with any 5V MCU host that is similarly equipped

with UART port. It can even interface with 3.3V MCU host as long as the

host input is 5V tolerant.

He has noted there that the microphone is strangely constructed. The microphone

mouth is directed on a side, instead of at the top. It does not have gain to compensate for

improperly directed voice inputs. And when not using a guide as shown below, the user

will have a hard time training the VR module.

It also has low sensitivity in that as speaking commands, the mouth should be

kept within an inch or two from the microphone’s pickup port. So when using this in

applications where the voice commands came from a distant, this is not recommended for

use. But according to the author, it is possible to use a microphone (electret type) other

16
 VOICE CONTROLLED WHEELCHAIR FOR THE PHYSICALLY DISABLED PERSONS

that one supplied with the kit. A headset with good quality microphone (i.e. gaming

headset) may actually work wonders for this kit.

In his training experience with the device, he noticed that the VR is not as tolerant

as during recognition mode. The VR requires repeating each voice command twice. The

commands should be pronounced in almost exact manner, same loudness, same inflection

same accent and all. In other words, to train it with your voice, you need to train yourself

as well. It was kind of frustrating the first time, but once you got the hang of it, it

becomes pretty easy.

In tinkbox.ph store, they are selling their version of a voice recognition module.

Their product, Voice Recognition Module V3, is described as a compact and easy-

control speaking recognition board. It is a speaker-dependent voice recognition module.

Now the price is already at Php 1,153.00 from the list price of Php 1,680.00 and only 3

are in stock.

Features of the product include:

 Supports up to maximum 80 voice commands, with each voice 1500ms (one or

two words speaking)

 Maximum 7 voice commands effective at the same time

 Arduino library is supplied

 Easy Control: UART/GPIO

 User-control General Pin Output

17
 VOICE CONTROLLED WHEELCHAIR FOR THE PHYSICALLY DISABLED PERSONS

This board has 2 controlling ways: Serial Port (full function), General Input Pins (part of

function). General Output Pins on the board could generate several kinds of waves while

corresponding voice command was recognized.

Specification:

 Voltage: 4.5-5.5V

 Current <40mA

 Digital Interface: 5V TTL level for UART interface and GPIO

 Analog Interface: 3.5mm mono-channel microphone connector + microphone pin

interface

 Size: 31mm x 50mm

 Recognition accuracy: 99% (under ideal environment)

Related Studies

The related studies present in this chapter focused on the discussion of the previous

studies made by other researchers in relation to the proposed project.

a. Foreign Studies

Under the International Journal of Advanced Research in Computer Science and

Software Engineering, a study by Ms. S.D. Suryawanshi, Mr. J. S. Chitode, and Ms. S. S.

Pethakar entitled, “Voice Operated Intelligent Wheelchair”, dated May, 2013, was

made to provide easy access for patients who are physically disabled which cannot

18
 VOICE CONTROLLED WHEELCHAIR FOR THE PHYSICALLY DISABLED PERSONS

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.

The patient can give voice commands via a head phone. These commands are

processed in the MATLAB software and according signals are then sent to the

microcontroller on board the wheelchair. About the wheelchair, the researchers created a

motorized miniature model and it is operated by 2 DC Motors. The microcontroller

operates these DC motors and controls the wheelchair accordingly. The voice commands

are: Forward, Reverse, Left, Right, and Stop.

From a contributor on engineersgarage, introduced as Alpesh Virpara, he posted a

project entitled, “Voice Controlled Wheelchair for Physically Disabled People”, it

aimed at controlling a wheelchair by means of human voice. It enables a disabled

person to move around independently, using a voice recognition application which is

interfaced with motors. The voice recognition technology used is the HM 2007 module.

This module is used to convert the voice signal into corresponding binary code that is

given to the microcontroller, and the microcontroller gives the output according to the

voice input. The five voice commands to control the direction of the motors are: Forward,

Backward, Stop, Right and Left.

The microcontroller used is a semiconductor chip. It is programmable,

multipurpose and multifunctional. The AT89C51 is a low-power, high-performance

19
 VOICE CONTROLLED WHEELCHAIR FOR THE PHYSICALLY DISABLED PERSONS

CMOS 8-bit microcomputer with 8Kbytes of Flash programmable and erasable read only

memory (PEROM).

The devices manufactured using Atmel’s high-density non-volatile memory

technology and is-compatible with the industry-standard 80C51 and 80C52 instruction set

and pin-out. The on-chip Flash allows the program memory to be reprogrammed in-

system or by a conventional non-volatile memory programmer.

Meanwhile, the motor used is procured from AGNI MOTOR, BANGLORE has

the following specifications: 120W, 9.8Nm, and 60rpm with no load. Two 12V, 32Ah

lead acid AMARON batteries were used.

To minimize the occurrence of vehicle accidents due to an eye or hand

movements while driving, an automatic vehicle human-voice-based safety control is

proposed in a paper entitled, “Arduino-Based Automatic Safety Vehicle Control”.

This was done for the 2nd International Conference on Research in Science, Engineering

and Technology on March 2014 by Othman M.K. Alsmadi, Anas A. Al Jallad, Zaer S.

Abo-Hammoud, and Fares J. Al Majali. The design is implemented using the Arduino

Mega system based on the ATmega2560. One of the most important safety control

features is the automotive speed control (ASC). In this safety control function, which

prevents a vehicle sudden hit, the necessary action is issued based on the vehicle-to-

vehicle distance measure. To prevent the driver from attention withdraw and maintain a

proper road and situation focus (as especially is the case at night), several other

automated safety control operations are provided (i.e., radio, flasher, left flasher, right

20
 VOICE CONTROLLED WHEELCHAIR FOR THE PHYSICALLY DISABLED PERSONS

flasher, wipers, drive, and stop). These features are controlled according to human voice

commands with the use of an EasyVR module. The proposed model has been designed,

built, and tested providing suitable results as desired.

Another study entitled, “Voice Recognition Based Advance Patient’s Room

Automation”, from the International Journal of Research in Engineering and

Technology, was made by student Tejaswiny Signh, with assistant professor Nandlal

Yadav this June 2015. This is a unique and most useful system for totally or partially

handicapped patients who are unable do basic tasks. Patients who are unable do anything

have to totally depend on nurses. Hospitals have to provide a round-the-clock 24 Hour an

attendant for these patients and hence total fees of hospitals gets increased. The device

that we proposed here can actually help these patients and hospitals without requiring 24

hour attendant. With this system, patient can call nurse or any attendant at any time

whenever required by simply voice controlled commands. This system listen voice

commands and can call nurse by simply ringing bell. It can also control basic switching

on/off tasks of fan, light and any device by patient voice.

The system consists of two modules: Handheld Microphone Module with a

ZigBee transceiver and a unit for voice recognition. Two microcontrollers are used in this

project. Two ZigBee chips are used to set up wireless communication. One of them

works as transmitter and is connected to the first ATmega328 the other one is connected

to the second ATmega32 working as the receiver.

21
 VOICE CONTROLLED WHEELCHAIR FOR THE PHYSICALLY DISABLED PERSONS

The system gets activated as soon as any the password is spoken. When the user

says a particular voice instruction, it enters the microphone of the Easy VR 2.0 at first

and then the ATmega328 at the transmitting end receives it. The ATmega328 will

transmit a particular command to the ZigBee device at the transmitting end. On enabling

the ZigBee, it will send the corresponding command to the ZigBee device on the

receiving end. On successful establishment of wireless communication, it will instruct the

ATmega328 microcontroller. Consequently, the appliances can be controlled like

increasing or decreasing the speed or turned ON or OFF depending on the control

commands received.

b. Local Studies

The researchers Rommer Son A. Cañete, Jarrie May C. Lawas and Amilou Jane

D. Suarez made a “Speech-Activated Hotel Room Control System Using VoiceGP

Module” for the Mapua Institute of Technology, School of Electrical Engineering,

Electronics Engineering and Computer Engineering in the year 2011. This system can

manage specific room service calls and appliance control through voice commands. The

design tends to apply voice-command recognition technology in hotel room service

wherein the hotel guest can control the room appliances and make room service calls in

terms of uttering voice commands. The system consists of a VoiceGP voice recognition

module, Arduino microcontroller, led indicators, PC and relay-based AC socket control

circuits.

22
 VOICE CONTROLLED WHEELCHAIR FOR THE PHYSICALLY DISABLED PERSONS

The system does not function well in a noisy environment and not all accents are

supported by it as tested by the researchers.

A high-standard hotel can use this system to further their functionalities,

convenience and thus be considered as a high technology hotel.

Meanwhile, in 2012, from the same school, Mapua Institute of Technology,

School of EECE, there is another research entitled, “Obstacle Detection for a Speech-

Controlled DC Motor Operated Wheelchair with Elevation System”, by Lloyd

Edwinson S. Arellano, Darryll Jade E. Arias, Francis Mark Adriane G. Luna, and Aljon

C. Santillan. This research focused on most handicapped people who suffer mobility

problem primarily depend on using wheelchairs, automated and not. The designs are

made in response to the condition of these target users. Considering the users who

already lost the ability to use their hands, the researchers of this paper believe that

implementing a speech control mechanism and incorporating sensors to the wheelchair

will give solution to this problem. It is also believed that to improve its functionality, a

lifting mechanism should be considered to allow the user to move up by himself into

elevated platforms. As a result, obstacle detection for a speech controlled dc-operated

wheelchair with elevation system is considered in this paper. The wheelchair will use

voice module that will process the user input speech command and a microcontroller to

control the movement of the wheelchair in response to the user input command.

Proximity sensors will also be used to create a system wherein obstacle detection

mechanism is present. Lastly, for the elevation system the wheelchair will be

incorporated by an electric car jack that will allow itself to lift into the elevated platform.

23
 VOICE CONTROLLED WHEELCHAIR FOR THE PHYSICALLY DISABLED PERSONS

TABLE 2.1 Syntheses of Related Literature and Studies

Related Literature and Studies Reason For Including As Reference

Related Literature

a. Foreign
To be aware of the advantages and
disadvantages of Voice Recognition at that
Medical Legal Aspects of Medical Records time and to have ideas on how can the
researchers should deal with those
disadvantages.
To be more conscious on how the voice
recognition can help in the life of physically
Voice Recognition Software Put to Test challenged people and to think of solutions to
overcome those troubles they have
encountered.
To know the challenges the developers have
Time is Right for Voice Recognition experienced in the creation of their product
Voice on the Go.
Speech Recognition Technology and its To have concrete knowledge about the specific
Benefits to the Disabled Community targets of the researcher’s study.
To have better idea at developing and
Talk vs. Type: Taking Another Look at
implementing a project that is smarter and
Voice Recognition
noise interference can be handled well.
b. Local
To be aware of the fact that, even the disabled
PWDs can now live life in the fast lane persons themselves are trying to improve and
increase their mobility.
To have comparison between the locally
Modules for Voice Recognition developed modules and the one the researchers
have used.
Related Studies

a. Foreign
This is made to provide easy access for patients
Voice Operated Intelligent Wheelchair who are physically disabled which cannot
control their movements especially the hands.

24
 VOICE CONTROLLED WHEELCHAIR FOR THE PHYSICALLY DISABLED PERSONS

The powered wheelchair depends on the motor

control and drive system which consists of
ARM Processor LPC2138 and DC Motor.
The aim of this it to control a wheelchair by
means of human voice. It enables a disabled
person to move around independently, using a
Voice Controlled Wheel Chair for voice recognition application which is
Physically Disabled People interfaced with motors. The voice recognition
technology used is the HM 2007 module. The
researchers included this for additional
information on the dc motors this study used.
The design is implemented using the Arduino
Mega system based on the ATmega2560. Its
features are controlled according to human
Arduino-Based Automatic Safety Vehicle
voice commands with the use of an EasyVR
Control
module. The researchers also used the same
module, so this study serves as a reference for
the module.
The system gets activated as soon as the
password is spoken. When the user says a
particular voice instruction, it enters the
Voice Recognition Based Advance Patient’s microphone of the EasyVR 2.0 at first then the
Room Automation ATmega at the transmitting end receives it.
This study is similar to the proposed system
and had given the researchers idea on adding a
trigger word.
b. Local
This system can manage specific room service
calls and appliance control through voice
commands. The design tends to apply voice-
command recognition technology in hotel
room service wherein the hotel guest can
Speech-Activated Hotel Room Control control the room appliances and make room
System Using Voice GP Module service calls in terms of uttering voice
commands. This study is explained in detail
compared to the foreign studies and gave the
researchers as much as necessary knowledge
on the use of voice recognition to be
implemented on the present study.
This research focused also on most
Obstacle Detection for a Speech-Controlled
handicapped people who suffer mobility
DC Motor Operated Wheelchair with
problem. The designs are made in response to
Elevation System
the condition of these target users. Considering

25
 VOICE CONTROLLED WHEELCHAIR FOR THE PHYSICALLY DISABLED PERSONS

the users who already lost the ability to use

their hands, the researchers of this paper
believe that implementing a speech control
mechanism and incorporating sensors to the
wheelchair will give solution to this problem.
This study had given the researchers viewpoint
on the incorporation of the components and the
method of testing and acquiring of the results.

Chapter 3

RESEARCH METHODOLOGY

This chapter provides information on how the research is carried out. Especially, the

procedures by which the researchers go about their work of describing, explaining and predicting

phenomena are included herein.

It mainly consists of and tackles the research design used, the phases which the

researchers has followed throughout the course of study, the sources of data gathered and are

included in this study, and the techniques used by the researchers in gathering these data and

lastly the tools used for the determination or analysis of the testing results.

Research Design

REQUIREMENTS
PLANNING

26

USER DESIGN CONSTUCTION

 VOICE CONTROLLED WHEELCHAIR FOR THE PHYSICALLY DISABLED PERSONS

FIGURE 3.1 Rapid Application Development Model

Rapid application development (RAD) model is a linear sequential software

development process that has much faster development and higher-quality results than those

achieved with the traditional software development life-cycle.

RAD is both a general term used to refer to alternatives to the conventional waterfall

model of software development as well as the name for James Martin's approach to rapid

development. In general, RAD approaches to software development put less emphasis on

planning tasks and more emphasis on development. In contrast to the waterfall model, which

emphasizes rigorous specification and planning, RAD approaches emphasize the necessity of

adjusting requirements in reaction to knowledge gained as the project progresses. This causes

RAD to use prototypes in addition to or even sometimes in place of design specifications. RAD

approaches also emphasize a flexible process that can adapt as the project evolves rather than

rigorously defining specifications and plans correctly from the start.

The researchers used the RAD model as shown on Figure 3.1. It served as a guide for the

researchers to follow and to become organize in the development of the system.

27
 VOICE CONTROLLED WHEELCHAIR FOR THE PHYSICALLY DISABLED PERSONS

Phases of the Rapid Application Development

Below are the various phases or stages involved in the Rapid Application Development

Model and are explained in detail.

A. Requirements Planning Phase

The Requirements Planning stage (also known as the Concept Definition stage)

consists of developing a list of initial requirements as well as setting the project scope.

The objective of this phase is to establish a general understanding of the problems that

surround its development and eventual operation of the proposed project.

During this phase, the researchers gathered information on the Voice Controlled

Wheelchair for Physically Disabled Persons and studied carefully the concepts of other

researchers. This is done to help the researchers understand what particular set of

components are to be used.

B. User Design Phase

In the User Design stage, also known as the Functional Design stage, the

requirements are flushed out in details. Test plans, flow charts and layouts for essential parts

of the system are developed with regards to the Requirements Planning stage.

In order to keep development iterations as short as possible, and to gain the maximum

benefit of RAD's agile nature, core requirements should be identified and targeted for the

28
 VOICE CONTROLLED WHEELCHAIR FOR THE PHYSICALLY DISABLED PERSONS

initial prototype, and secondary requirements should be identified and targeted for future

development iterations. Limiting of scope should be considered as well.

Generally, it is a continuous interactive process that allows users to understand and

eventually approve a working model of the system that meet their needs.

Under this phase, the researchers focus on the software development needed for the

system and the construction of the project's draft design.

HARDWARE
VOICE
ENGINEERING
CONTROLLED
INTEGRATION
WHEELCHAIR
SOFTWARE AND
FOR THE
ENGINEERING AUTOMATION
PHYSICALLY

DISABLED

MICROCONTROLLER PERSONS

TECHNOLOGY

FIGURE 3.2 Conceptual Framework

C. Construction Phase

During the Construction Phase, the project follows iterative cycles of development,

testing, requirements refining, and development again, until it is completed.

29
 VOICE CONTROLLED WHEELCHAIR FOR THE PHYSICALLY DISABLED PERSONS

The objectives of the Rapid Construction stage are (1) to complete the detailed design of

the proposed system; (2) to create and test the software that implements the proposed system;

and (3) to generate a system that operates at an acceptable level of performance.

During the final iterations of development the design team should update user

documentation, perform testing and define the steps necessary for deployment or

implementation. In this phase, the actual prototype is developed.

The researchers were able to construct an idea that is alternative to those related studies.

Brainstorming was done to come up with a general idea that satisfies the requirement of the

system.

D. Cutover Phase

This phase is also known as the Deployment or Implementation stage. This is where

the final user testing, training of the system takes place in preparation for the deployment of

the project.

The researchers tested the effectiveness of the project in terms of its accuracy in

maneuvering and the time it takes to respond to the voice command uttered. And also

includes final furnishing and documentation.

Sources of Data

There has been a lot of helpful information that surfaced in relation to the proposed

project. These were gathered by the researchers for the sole purpose of giving grounds for this

study.

30
 VOICE CONTROLLED WHEELCHAIR FOR THE PHYSICALLY DISABLED PERSONS

Listed in the following are the sources of these data:

Websites. With the help of the Internet’s search engines, such as Google, Bing, Yahoo! and

Ask, the researchers found and collected as much as needed information about the study.

These include all the necessary components, methods, and concepts for the design. And also,

most of the related literatures and definitions of terms were taken from different websites.

PDFs. Portable Document Format is a file format, created by Adobe Systems, typically used

for saving documents that are comprised of more than a simple text element. Ideas, concepts,

and other related studies were taken from downloaded PDFs.

Books. Some data were taken from informative books for a more detailed explanation of the

concepts involved in the study.

Other data came from the problems encountered during the designing and testing of the

design project.

Data Gathering Techniques

Data gathering is an important aspect of any type of research study. It is defined as the

process of collecting and measuring information on targeted variables in an established

systematic fashion, which then enables one to answer relevant questions and evaluate outcomes.

The data gathering techniques which were carried out by the researchers are enumerated

below.

Document Analysis

31
 VOICE CONTROLLED WHEELCHAIR FOR THE PHYSICALLY DISABLED PERSONS

Documents are interpreted by the researchers for giving meaning to the study.

Document analysis was the manner mainly used by the researchers. The documents that

are covered in this analysis are the related studies, both from local and foreign authors.

This is valuable to help the researchers extract the relevant portions that can be deemed

as statement of facts to validate individual research objectives.

Expert Advice

The panels’ suggestions and advices from some of the professionals and

instructors inside and outside the University were acquired for the betterment of the

design project.

Tools for Analysis

In order to determine the proposed project’s descriptive statistics for the level of

effectiveness, the researchers have used the formula below and some testing for the accuracy in

maneuvering the wheelchair and the response time in performing the movement command.

The effectiveness of the system will be determined by using the formula:

32
 VOICE CONTROLLED WHEELCHAIR FOR THE PHYSICALLY DISABLED PERSONS

𝑇𝑜𝑡𝑎𝑙 𝑁𝑢𝑚𝑏𝑒𝑟 𝑜𝑓 𝑆𝑢𝑐𝑐𝑒𝑠𝑠𝑓𝑢𝑙 𝑇𝑟𝑖𝑎𝑙𝑠

𝐸𝑓𝑓𝑒𝑐𝑡𝑖𝑣𝑒𝑛𝑒𝑠𝑠 = × 100%
𝑇𝑜𝑡𝑎𝑙 𝑁𝑢𝑚𝑏𝑒𝑟 𝑜𝑓 𝑇𝑟𝑖𝑎𝑙𝑠

33