Loading presentation...

Present Remotely

Send the link below via email or IM

Copy

Present to your audience

Start remote presentation

  • Invited audience members will follow you as you navigate and present
  • People invited to a presentation do not need a Prezi account
  • This link expires 10 minutes after you close the presentation
  • A maximum of 30 users can follow your presentation
  • Learn more about this feature in our knowledge base article

Do you really want to delete this prezi?

Neither you, nor the coeditors you shared it with will be able to recover it again.

DeleteCancel

Make your likes visible on Facebook?

Connect your Facebook account to Prezi and let your likes appear on your timeline.
You can change this under Settings & Account at any time.

No, thanks

final project

No description
by

Riyadh Alsharafi

on 21 November 2013

Comments (0)

Please log in to add your comment.

Report abuse

Transcript of final project

Smart Homes Using Voice Recognition
Chapter2:
Hardware Design

Chapter 3:
Voice recognition technique
& Implementation

Introduction
Introduction
Smart Home means:
A home that “ listen to you……
A home that “ protect you………
A home that make you more comfortable.
Smart Home System
*A common definition of Smart Home is of an “electronic networking technology to integrate devices and appliances so that the entire home can be monitored and controlled centrally as a singl machine”
*In our project we can describe smart house as a house that has highly advanced automatic systems for lighting, temperature control, multi-media, security, and window and door operations by voice control.
Definition of smart home
- Lighting.
- Security & Access.
- Telecommunication.
- Temperature .
- Networking.
What can we control?
1-intelligent control.
2-home automation .
3-internal network.
Components of a Smart Home System
The intelligent control is provided by a control system, comprised of two types of elements: sensors, which will monitor, control and report the status of the home environment, and a control agent (human or software based) which acts on the information provided by the sensors.
intelligent control
- the home automation function by electrical or electronic devices (actuators)

- They will interact and modify the environment by accomplishing specialized tasks.
home automation
The purpose of the home network is simply
to ensure that all the components can receive
and send instructions to each other.
The home network
a) Poor understanding of user needs
b) Users’ lack of understanding about potential benefits
c) Difficulties in installing and integrating solutions into existing households
d) Costs
Design Challenges
Aims and Objectives :

-The aim of this project is to develop a proof-of- concept prototype for a Smart Home and presenting some applications in the security and protection.

-It will also aim at improving the “effectiveness” of Smart Home systems.
Outline
Chapter 1 (introduction): We will talk about the importance of minerals and goals of the project and the date of the device and its development through the ages.
Chapter 2 (Hardware): Contains the practical side of the project and a detailed explanation of the circuit and pieces.
Chapter 3(Implementation): talking about the voice recognition technique and whole project diagram.

Chapter 4 (Conclusion and Future Work): Summarized for each project ideas and future developments that will improve the work.
The following sections present the hardware design and components that are used in this thesis.
The following sections present the hardware design and components that are used in this thesis.
The following sections present the hardware design and components that are used in this thesis.
The following sections present the hardware design and components that are used in this thesis.
The following sections present the
hardware design and components
that are used in this thesis.
1. Arduino Mega 2560 R3 Microcontroller
It is a physical computing platform based on a simple i/o board and a development
environment that implements the Processing/Wiring language. Arduino can be used to develop stand-alone interactive objects or can be connected to software on your computer
(e.g. Flash, Processing, MaxMSP). The open-source IDE can be downloaded for free
(currently for Mac OS X, Windows, and Linux).
a) ATmega2560 microcontroller
b) Input voltage - 7-12V
c) 54 Digital I/O Pins
d) 16 Analogue Inputs
e) 256k Flash Memory(RAM)
f) 16Mhz Clock Speed
Features:
- Here is a simple, low-cost,
high quality servo for all your
mechanics needs.
- Large servo with a standard
3 pin power and control cable.
Servo Motor
a) Weight: 41g
b) Dimensions: 41 x 20 x 38mm
c) 3 pole ferrite, all nylon gear
d) Operating Voltage: 4.8V~6.0V
Features:
Beefcake Relay Control Kit
Our 5 volt system can wield great power with this big beefy relay board. The Beefcake Relay Control Kit contains all the parts you need to get your high-power load under control.
The heart of the board is a sealed, SPST-NO 20A Relay. The relay is controlled by 5V logic through a transistor and an LED tells you when the relay is closed. This is a kit, so it comes as through-hole parts with assembly required which makes for some nice soldering practice. Screw terminal connectors on either side of the board make it easy to incorporate into your project.
RFID Reader ID-12 (125 kHz)
This is a very simple to use RFID reader module from ID Innovations. With a built in antenna, the only holdup is the 2mm pin spacing (breakout board available below). Power the module, hold up a card, and get a serial string output containing the unique ID of the card.
Features:
a) 5V supply
b) 125kHz read frequency
c) 9600bps
d) Magnetic stripe emulation output
e) 100mm read range
f) Dimensions: 25x26mm
RFID USB Reader
* The RFID USB Reader is a simple to use, USB to serial base unit for the ID-2, ID-12, and ID-20 readers.
* We open a terminal program of our choice at 9600bps , then scan our 125 kHz ID tag will be shown on the screen. The unit is based on a FTDI chip and comes with a read LED and buzzer.
Features
*Calibrated directly in ° Celsius (Centigrade)
*Linear + 10.0 mV/°C scale factor
*0.5°C accuracy guaranteeable (at +25°C)
*Rated for full −55° to +150°C range
*Low cost due to wafer-level trimming
*Operates from 4 to 30 v
TMP36 - Temperature Sensor
EasyVR Shield - Voice Recognition Shield
The EasyVR Shield is a
voice recognition shield
for Arduino boards integrating
an EasyVR module. It includes
all of the features of the EasyVR
module in a shield form factor that
simplifies connection to the
Arduino main board and PC.
a) A host of built-in speaker independent (SI) commands (available in US English, Italian, Japanese, German, Spanish and French) for ready to run basic controls.
b) Supports up to 32 user-defined Speaker Dependent (SD) triggers or commands (any language) as well as Voice Passwords.
c) Easy-to-use and simple Graphical User Interface to program Voice Commands to your robot.
Features

a) Baud Rate: 9600 (default), 19200, 38700, 57600, 115200


b) Frame: 8 Data bits, No parity, 1 Stop bit
Serial Interface
The microphone provided with the EasyVR module is an omnidirectional electret condenser microphone (Horn EM9745P-382):
a) Sensitivity -38dB
b) Load Impedance 2.2K
c) Operating Voltage 3V
Microphone
The voice recognition is
“the ability of a machine or program to receive and interpret command, or to understand and carry out spoken commands.”
Introduction
EasyVR GUI
Speech recognition fundamentally functions as a pipeline that converts PCM (Pulse Code Modulation) digital audio from a sound card into recognized speech
How Speech Recognition Works
1.Transform the PCM digital audio into a better acoustic representation.
2.Apply a "grammar" so the speech recognizer knows what phonemes to expect. A grammar could be anything from a context-free grammar to full-blown Language.
3.Figure out which phonemes are spoken.
4.Convert the phonemes into words.
The elements of the pipeline are:
 the PCM digital audio is transformed into the "frequency domain." Transformations are done using a windowed Fast-Fourier Transform (FFT).
Transform the PCM digital audio
The FFT analyzes every 1/100th of a second and converts the audio data into the frequency domain.
Each 1/100th of second's results are a graph of the amplitudes of frequency components, describing the sound heard for that 1/100th of a second.
The speech recognizer has a database of several thousand such graphs (called a codebook) that identify different types of sounds the human voice can make.
The sound is "identified" by matching it to its closest entry in the codebook, producing a number that describes the sound.
This number is called the "feature number." (Actually, there are several feature numbers generated for every 1/100th of a second, but the process is easier to explain assuming only one.)

The input to the speech recognizer began as a stream of 16,000 PCM values per second.

By using Fast-Fourier Transforms and the codebook, it is boiled down into essential information, producing 100 feature numbers per second.
Whole Project Block Diagram
Relay circuit diagram
temp = (5.0 * analogRead(tempPin) * 100.0) / 1024
~ temp/2
The original equation came from replacing
The value of Ra by this factor and the fact of
The ratio of (+ 10.0 mV/°C scale factor)
From data sheet
Ra = Vc /(48.8*10-6 )for Vc=5vRa=102.4 Kohm
Temperature Equation
Conclusion and Future Work
a) Poor understanding of user needs
b) Users’ lack of understanding about potential benefits
c) Difficulties in installing and integrating solutions into existing households
d) Costs
Design Challenges
One of the most basic voice recognition problems is the quality of the input devices being used.
If a microphone is not sensitive enough — or is overly sensitive — then it can create audio information that is difficult for the software to recognize.
The microphone isn't close enough to pick up our voice.
Another problem from background noise that can be problematic to separate out from the main speech and can cause inaccurate translations when included in the speech processing.
Problems in VR
All voice-recognition systems or programs make errors. Screaming children, barking dogs, and loud external conversations can produce false input.
Much of this can be avoided only by using the system in a quiet room.
There is also a problem with words that sound alike but are spelled differently and have different meanings -- for example, "hear" and "here." This problem might someday be largely overcome using stored contextual information. However, this will require more RAM and faster processors than are currently available in personal computers.
We must choose the microphone to be in high quality and with good sensitivity.
We can use remote microphone (wireless microphone)
for the problem that the microphone
isn't close enough to pick up our voice.
We can use de-noise technique.
Suggested solutions:
May we add security system using GSM for alarming us on phone when we are away. And use motion sensors and cameras.
Also may we embed energy controlling.
We can add IR sensor in the door .
recommendations for future work


Thank You


Done by:
Faten Ahmad Mansour.
Riyadh Mohammed Hasan.
Malek Ayman Ramadan.
Voice commands in this project:

Open door
Open window
Close window
Light on
Light off
Types of voice recognition techniques:
Speaker dependent.

Speaker independent.
Full transcript