No abstract

This paper deals with Artificial Neural Networks as a basis for the automation of existing Air Traffic Control System (ATC).The air traffic control task involves huge complexity in terms of work load on air traffic controller. This task is having complex cognitive nature, with main objective is to maintain safe distance between two aircrafts during departure, landing and in middle air traffic. The approach used is back propagation network for the decision making. The approach used is gradient Descent. A simulator is design which simulates control of Air Traffic and Landing Clearance and departure by Artificial intelligence. Decisions can be given based on various controlling parameters. The intelligent decision making can be implemented by using "Back propagation Network" (BPN). The system simulates various parameters and the effect of these parameters on the output decision of BPN can be analyzed. The output decision will vary according to the updated flight record.

No abstract

No abstract

The paper "A Colour Code Algorithm for Signature Recognition" accounts an image processing application where any user can verify signature instantly. The system deals with a Colour code algorithm, which is used to recognize the signature.The paper deals with the recognition of the signature, as human operator generally make the work of signature recognition. Hence the algorithm simulates human behavior, to achieve perfection and skill through AI. The logic that decides the extent of validity of the signature must implement Artificial Intelligence Pattern recognition is the science that concerns the description or classification of measurements, usually based on underlying model. Since most pattern recognition tasks are first done by humans and automated later, the most fruitful source of features has been to asked the people who classify the objects how they tell them a part . Signatures are a behavioural biometric that change over a period of time and are influenced by physical and emotional conditions of a subject. In addition to the general shape of the signed nameThe algorithm is tested on various operating systems & we find that it works very well & satisfactory. While implementing the recognition process, we have used quite simpler way. At this stage we are getting accuracy up to about 80% to 90%.