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.

Collective behavior of laser-produced plasma from a multicomponent YBa2Cu3O7 target in air

The dynamics of diffusion of electrons and ions from the laser-produced plasma from a multielement superconducting material, namely YBa2Cu3O7, using a Q-switched Nd:YAG laser is investigated by time-resolved emission-spectroscopic techniques at various laser irradiances. It is observed that beyond a laser irradiance of 2.6 \xC3\x97 1011 W cm-2, the ejected plume collectively drifts away from the target with a sharp increase in velocity to 1.25 \xC3\x97 106 cm s-1, which is twice its velocity observed at lower laser irradiances. This sudden drift apparently occurs as a result of the formation of a charged double layer at the external plume boundary. This diffusion is collective, that is, the electrons and ions inside the plume diffuse together simultaneously and hence it is similar to the ambipolar diffusion of charged particles in a discharge plasma

Twin peak distribution of electron emission profile and impact ionization of ambient molecules during laser ablation of silver target

Laser-induced plasma generated from a silver target under partial vacuum conditions using the fundamental output of nanosecond duration from a pulsed Nd:yttrium aluminum garnet laser is studied using a Langmuir probe. The time of flight measurements show a clear twin peak distribution in the temporal profile of electron emission. The first peak has almost the same duration as the laser pulse while the second lasts for several microseconds. The prompt electrons are energetic enough ('60 eV) to ionize the ambient gas molecules or atoms. The use of prompt electron pulses as sources for electron impact excitation is demonstrated by taking nitrogen, carbon dioxide, and argon as ambient gases.

Photoemission optogalvanic studies with copper as target electrode

Photoemission optogalvanaic (POG) effect has been observed by irradiating copper target electrode, in a nitrogen discharge cell using 1.06 μm and frequency doubled 532 nm Nd:YAG laser pulse. Measurement of the nature of the variation of POG signal strength with 532 nm laser fluence confirms the two photon induced photoelectric emission from copper. However, using 1.06 μm laser pulses thermally assisted photoemission is observed.

Temporal and spatial evolution of C2 in laser induced plasma from graphite target

Laser ablation of graphite has been carried out using 1.06mm radiation from a Q-switched Nd:YAG laser and the time of flight distribution of molecular C2 present in the resultant plasma is investigated in terms of distance from the target as well as laser fluences employing time resolved spectroscopic technique. At low laser fluences the intensities of the emission lines from C2 exhibit only single peak structure while beyond a threshold laser fluence, emission from C2 shows a twin peak distribution in time. The occurrence of the faster velocity component at higher laser fluences is explained as due to species generated from recombination processes while the delayed peak is attributed to dissociation of higher carbon clusters resulting in the generation of C2 molecule. Analysis of measured data provides a fairly complete picture of the evolution and dynamics of C2 species in the laser induced plasma from graphite.

Realisation of a Target Classifier For Noise Sources in the Ocean

This thesis addresses one of the emerging topics in Sonar Signal Processing.,viz.the implementation of a target classifier for the noise sources in the ocean, as the operator assisted classification turns out to be tedious,laborious and time consuming.In the work reported in this thesis,various judiciously chosen components of the feature vector are used for realizing the newly proposed Hierarchical Target Trimming Model.The performance of the proposed classifier has been compared with the Euclidean distance and Fuzzy K-Nearest Neighbour Model classifiers and is found to have better success rates.The procedures for generating the Target Feature Record or the Feature vector from the spectral,cepstral and bispectral features have also been suggested.The Feature vector ,so generated from the noise data waveform is compared with the feature vectors available in the knowledge base and the most matching pattern is identified,for the purpose of target classification.In an attempt to improve the success rate of the Feature Vector based classifier,the proposed system has been augmented with the HMM based Classifier.Institutions where both the classifier decisions disagree,a contention resolving mechanism built around the DUET algorithm has been suggested.

Studies on seed pathology and seedling diseases of some important indigenous tree species of kerala

In forestry, availability of healthy seeds is an important factor in raising planting stock. Initial seed health and storage conditions are the major factors governing the germinability of seeds. Like seeds of agricultural and horticultural crops, forest tree seeds are also liable to be affected by micro-organisms during storage, which affects the germination, and reduces the viability. Further introduction of seed-borne diseases into newly sown crops/areas on account of using unhealthy seeds is also not ruled out. Availability of healthy stock of seedlings is intrinsic for raising plantations and to meet this requirement elimination of nursery diseases by appropriate chemicals is of prime imortance. As exotic tree species may become susceptible to various native pathogens, it is generally considered better to select indigenous tree species for large scale plantations as they are well adapted to local environment. However, before taking up large scale afforestation progranme involving any indigenous tree species, it is essential to have knowledge about seed disorders and seedling diseases and their management. with a View to select appropriate tree species with fewer seed disorders and seedling disease problems for use in further plantation programme, four indigenous tree species such as Albizia odoratissima (L.f) Benth., Lagerstroemia microcazpa Wt., Pterocazpus marsupiwn Roxb. and Xylia xylocarpa (Roxb.) Taub. were evaluated to meet the above parameters

Underwater Target Localization, Tracking and Classification

Underwater target localization and tracking attracts tremendous research interest due to various impediments to the estimation task caused by the noisy ocean environment. This thesis envisages the implementation of a prototype automated system for underwater target localization, tracking and classification using passive listening buoy systems and target identification techniques. An autonomous three buoy system has been developed and field trials have been conducted successfully. Inaccuracies in the localization results, due to changes in the environmental parameters, measurement errors and theoretical approximations are refined using the Kalman filter approach. Simulation studies have been conducted for the tracking of targets with different scenarios even under maneuvering situations. This system can as well be used for classifying the unknown targets by extracting the features of the noise emanations from the targets.