This paper investigates a method of Handwritten English Character Recognition using Artificial Neural Network (ANN). This work has been done in offline Environment for non correlated characters, which do not possess any linear relationships among them. We test that whether the particular tested character belongs to a cluster or not. The implementation is carried out in Matlab environment and successfully tested. Fifty-two sets of English alphabets are used to train the ANN and test the network. The algorithms are tested with 26 capital letters and 26 small letters. The testing result showed that the proposed ANN based algorithm showed a maximum recognition rate of 85%.
Path planning of Robot is one of the challenging fields in the area of Robotics research. In this paper, we proposed a novel algorithm to find path between starting and ending position for an intelligent system. An intelligent system is considered to be a device/robot having an antenna connected with sensor-detector system. The proposed algorithm is based on Neural Network training concept. The considered neural network is Adapti ve to the knowledge bases. However, implementation of this algorithm is slightly expensive due to hardware it requires. From detailed analysis, it can be proved that the resulted path of this algorithm is efficient.
Solving Quadratic equation is one of the intrinsic interests as it is the simplest nonlinear equations. A novel approach for solving Quadratic Equation based on Genetic Algorithms (GAs) is presented. Genetic Algorithms (GAs) are a technique to solve problems which need optimization. Generation of trial solutions have been formed by this method. Many examples have been worked out, and in most cases we find out the exact solution. We have discussed the effect of different parameters on the performance of the developed algorithm. The results are concluded after rigorous testing on different equations.
This work focuses on development of a Offline Hand Written English Character Recognition algorithm based on Artificial Neural Network (ANN). The ANN implemented in this work has single output neuron which shows whether the tested character belongs to a particular cluster or not. The implementation is carried out completely in 'C' language. Ten sets of English alphabets (small-26, capital-26) were used to train the ANN and 5 sets of English alphabets were used to test the network. The characters were collected from different persons over duration of about 25 days. The algorithm was tested with 5 capital letters and 5 small letter sets. However, the result showed that the algorithm recognized English alphabet patterns with maximum accuracy of 92.59% and False Rejection Rate (FRR) of 0%.