|
|
SPEECH
CODER FOR MULTIMEDIA COMMUNICATIONS
|
|
COLLEGE: K.L.E.S, GOGTE INSTITUTE OF TECH.,
BELGAUM
RECOGNITION: FIRST PRIZE
This coder is designed to operate with a digital signal obtained by first
performing telephone bandwidth filtering (Recommendation G.712) of the analog
input, then sampling at 8000 Hz and then converting to 16-bit linear PCM
for the input to the encoder.The output of the decoder is converted back
to analog by similar means.The coder is based on the principles of linear
prediction nalysis-by-
synthesis coding and attempts to minimize a perceptually weighted error
signal. The encoder operates on blocks (frames) of 240 samples each.
The combination of the LPC synthesis filter, the formant perceptual weighting
filter, and the harmonic noise shaping filter is used to create an impulse
response. The impulse response is then used for further computations.Using
the pitch period estimation and the impulse response, a closed loop pitch
predictor is computed. A fifth order pitch predictor is used.Both the
pitch period and the differential value are transmitted to the decoder.
Finally the non-periodic component of the excitation is approximated.
|
REMOTE PROCESS CONTROL USING MOBILE
|
|
COLLEGE: K. L. E. SOCIETY'S COLLEGE OF ENGG.
AND TECH., BELGAUM.
RECOGNITION: SECOND PRIZE
The basic purpose of the project being done is to show the applications of
mobile phones to get the status of various electronic / electrical devices, and control
these same devices at industry or home using the SMS facility provided by all mobile phone
networks. We have interfaced a mobile phone with a PC via an infrared port.
All operations to be performed are received by this mobile phone as a SMS from any other
mobile phone. A PC at he process end regularly poll’s the mobile phone to check for new SMS’s
and on receiving any new SMS’s it decodes them. After decoding the PC performs the required
operation through an external micro-controller. The micro-controller also keeps sending the
status of the devices to the PC. Currently we are demonstrating the use of three systems :
.Temperature Controller.
.Level controller
.Monitoring Current through the Motor.
One important factor to be considered here is that the whole system should be
controlled by only the concerned user and any other person should not be able to perform these operations, even if he sends a SMS to the process end PC. To this end we have kept a four character password, with which each SMS must begin.
If the password is not there or incorrect password is sent, the process end PC will simply ignore that SMS. Also the format of the SMS to be sent is fixed, with the first four character being the password.
A visual display is also made where the status of the two devices is shown. Apart from the automatic mode, we can do all of the above mentioned operations manually as well as send and receive SMS’s via the computer. In the manual mode of operation, the PC will not automatically read any incoming SMS’s. To change from automatic mode to manual mode we again require a password.
|
Face Recognitiopn Using Artificial Neural Network.
|
|
COLLEGE: Jawaharlal Darda Institute of Engineering And Technology.
This project proposes a new measure of “distance” between faces. This measure involves
the estimation of the set of possible transformations between face images of the same person.
The global transformation, which is assumed to be too complex for direct modeling, is
approximated by a patchwork of local transformation, under a constraint imposing consistency
between neighboring local transformation. The proposed system of local transformation and
neighboring constraints is embedded within the probailistics framework of a two-dimensional
hidden Markov model. More specifically, we model two types of interclass variability’s
involving variations in facial expressions and illumination, respectively.
The performance of the resulting method is assessed on a large data set consisting of four
face databases. In particular, it is shown to outperform a leading approach to face
recognition, namely, the Bayesian intra/extrapersonal classifier.
A novel method for enhancing the performance of elastic graph matching in frontal face
authentication is proposed. The starting point is to weigh the local similarity values
at the nodes of an elastic graph according to their discriminatory power. Powerful and
well-established optimization techniques are used to derive the weights of the linear
combination. More specifically, we propose a novel approach that reformulates Fisher’s
discriminate radio to a quadratic optimization problem subject to a set of inequality
constraints by combining statistical pattern recognition and Support Vector Machines.
Both linear and nonlinear support vector machines are then constructed to yield the optimal
separating hyperplanes frontal face authentication on the M2VIS database. Experimental results
indicate that the performance of morphological elastic graph matching is highly improved by
using the proposed weighting technique.
|
COMPUTERIZED
CONTROL OF JACQUARD -PINS OF JACQUARD POWER LOOM
|
|
COLLEGE: K. L. E. S'S COLLEGE OF ENGG .AND
TECH., BELGAUM
RECOGNITION : APPRECIATION PRIZE
The following are the few important parameters involved in the project :
1. Graph diagram
2. Algorithm for file mapping
3. Interface Unit
4. Electromechanical Actuators
The computerization of the Jacquard design mechanism has both advantages
and disadvantages. A present they are almost equally balanced but continuously
the effort will be to over weight the advantages. In fact presently the
users are convenient with the punched cards. The system however would
definitely enhance the productivity and hence efficiency of the machine.
And since the principle of operation of all Jacquard machines is basically
the same we can implement the same system to machines with different number
of pins, with minor modifications.
|
FLUID FLOW
RATE CONTROL USING MICRO-CONTROLLER
|
[ Top ] |
COLLEGE: K.V.G. COLLEGE OF ENGINEERING,
SULLIA
RECOGNITION: APPRECIATION PRIZE
This system has been planned to control the water flow to the sprinkler,
thereby covering the region within the specified radius. The whole system
works on microcontroller 8051 along with some peripherals, in which microcontroller
is the heart of the system.
The present system works in two modes, namely automatic mode and timer
mode. In timer mode sprinkler will start functioning within the specified
timings as entered by the operator and in automatic mode when the moisture
content in the soil is zero or soil is dry. The flow of fluid is controlled
by mechanical valve, which is driven by stepper motor for which the driving
sequence is generated by microcontroller.
The main objective of the project is for irrigation and in chemical industries.
This project facilitates the farmers who are not in a position to frequently
look after the sprinkler systems etc. The flow of different fluids in
a chemical factory can also be done in a controlled manner. The project
is cost effective and accurate.
|
|

|
 |