Ramakrishnan, K; Dr. Balakrishnan, K G(Cochin University of Science & Technology, 1991)
[+]
[-]
Abstract:
Remote Data acquisition and analysing systems
developed for fisheries and related environmental studies
have been reported. It consists of three units. The first
one namely multichannel remote data acquisition system is
installed at the remote place powered by a rechargeable
battery. It acquires and stores the 16 channel environmental
data on a battery backed up RAM. The second unit
called the Field data analyser is used for insitue display
and analysis of the data stored in the backed up RAM. The
third unit namely Laboratory data analyser is an IBM
compatible PC based unit for detailed analysis and interpretation
of the data after bringing the RAM unit to the
laboratory. The data collected using the system has been
analysed and presented in the form of a graph. The system
timer operated at negligibly low current, switches on the
power to the entire remote operated system at prefixed time
interval of 2 hours.Data storage at remote site on low power battery
backedupRAM and retrieval and analysis of data using PC are
the special i ty of the system. The remote operated system takes about 7 seconds including the 5 second stabilization
time to acquire and store data and is very ideal for remote
operation on rechargeable bat tery. The system can store
16 channel data scanned at 2 hour interval for 10 days on
2K backed up RAM with memory expansion facility for 8K RAM.
Description:
Department of Electronics,
Cochin University of Science and Technology
Ravindranathan, S; Dr.Unnikrishnan, A(Cochin University of Science & Technology, October , 1991)
[+]
[-]
Abstract:
Neural Network has emerged as the topic of the day.
The spectrum of its application is as wide as from ECG noise
filtering to seismic data analysis and from elementary
particle detection to electronic music composition. The
focal point of the proposed work is an application of a
massively parallel connectionist model network for detection
of a sonar target. This task is segmented into: (i) generation of training patterns from sea noise that
contains radiated noise of a target, for teaching the
network;(ii) selection of suitable network topology and learning
algorithm and (iii) training of the network and its subsequent testing
where the network detects, in unknown patterns applied
to it, the presence of the features it has already
learned in. A three-layer perceptron using backpropagation
learning is initially subjected to a recursive training
with example patterns (derived from sea ambient noise with
and without the radiated noise of a target). On every
presentation, the error in the output of the network is
propagated back and the weights and the bias associated with
each neuron in the network are modified in proportion to
this error measure. During this iterative process, the network converges and extracts the target features which get
encoded into its generalized weights and biases.In every unknown pattern that the converged
network subsequently confronts with, it searches for the
features already learned and outputs an indication for their
presence or absence. This capability for target detection is
exhibited by the response of the network to various test
patterns presented to it.Three network topologies are tried with two
variants of backpropagation learning and a grading of the
performance of each combination is subsequently made.
Description:
Department of Electronics, Cochin University of Science and Technology