AN ARTIFICIAL NEURAL NETWORK FOR SONAR TARGET DETECTION

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.

Studies On Oxygen Minimum Layer In The Arabian Sea In Relation To The Oceanic Circulation

The thesis is divided into six chapters, with Further subdivisions.’ Chapter one has two sections. Section one deals with a general introduction, and section two,with the material and treatment of data For the present investigation. The second chapter concerns with the distribution of oxyty in the oxygen minimum layer and its topography during the southwest and northeast monsoons. The distribution of oxyty at various isanosteric surfaces within which the oxygen minimum layer lies during southwest and northeast monsoons and their topographies Form chapter three. In the fourth chapter the Flow pattern and its influence on the oxygen minimum layer are discussed. The fifth chapter presents the scatter diagrams of oxyty against temperature at the various isanosteric surfaces. The sixth chapter summarises the results of the investigation and presents the conclusions drawn therefrom

Variations of surface boundary layer parameters associated with Cyclone Gonu over the Arabian Sea using QuikSCAT data

This study attempted to quantify the variations of the surface marine atmospheric boundary layer (MABL) parameters associated with the tropical Cyclone Gonu formed over the Arabian Sea during 30 May–7 June 2007 (just after the monsoon onset). These characteristics were evaluated in terms of surface wind, drag coefficient, wind stress, horizontal divergence, and frictional velocity using 0.5◦ × 0.5◦ resolution Quick Scatterometer (QuikSCAT) wind products. The variation of these different surface boundary layer parameters was studied for three defined cyclone life stages: prior to the formation, during, and after the cyclone passage. Drastic variations of the MABL parameters during the passage of the cyclone were observed. The wind strength increased from 12 to 22 m s−1 in association with different stages of Gonu. Frictional velocity increased from a value of 0.1–0.6 m s−1 during the formative stage of the system to a high value of 0.3–1.4 m s−1 during the mature stage. Drag coefficient varied from 1.5 × 10−3 to 2.5 × 10−3 during the occurrence of Gonu. Wind stress values varied from 0.4 to 1.1 N m−2. Wind stress curl values varied from 10 × 10−7 to 45 × 10−7 N m−3. Generally, convergent winds prevailed with the numerical value of divergence varying from 0 to –4 × 10−5 s−1. Maximum variations of the wind parameters were found in the wall cloud region of the cyclone. The parameters returned to normally observed values in 1–3 days after the cyclone passage