Hajare P.R.,G.H. Raisoni College of Engineering |
Bawane N.G.,S B Jain Institute Of Technology Management And Research
International Conference on Emerging Trends in Engineering and Technology, ICETET | Year: 2016
This paper is based on feed forward neural network (FFNN) optimization by particle swarm intelligence (PSI) used at the starting point of neural network for initial guess to weights and biases. Once the weights and biases are found, the same are used to train the neural network for prediction and classification benchmark problems. Further the trained neural network is the used to predict future sample and classify the test samples. A comparison is made between normal FFNN with random weights and biases and FFNN with particle swarm optimized weights and biases. Four such benchmark databases are considered in this paper, The Mackey Series, Box Jenkins Database, Breast Cancer Database and the Diabetic Database. Result shows that neural network performs better with initial weights and biases obtained by Particle Swarm optimization. The tendency of back propagation to stuck at local minima and local maxima thus can be overcome, and the network converges faster. Also the prediction error is minimized and classification accuracy is increased. © 2015 IEEE.
Hazare P.R.,S B Jain Institute Of Technology Management And Research
Proceedings - International Conference on Electronic Systems, Signal Processing, and Computing Technologies, ICESC 2014 | Year: 2014
Image transforms are extensively used in image processing and image analysis. Transform is basically a mathematical tool, which allows us to move from one domain to another domain. Transforms play a significant role in various image processing applications such as image analysis, image enhancement, image filtering and image compression. Nowadays, almost all digital images are stored in compressed format in order to save the computational cost and memory. To save the memory cost, all the image processing techniques like feature extraction, image indexing and watermarking techniques are applied in the compressed domain itself rather than in spatial domain. In this paper, for compression purpose, Discrete Cosine Transform (DCT) is used because it has excellent energy compaction. The new approach devised in this paper is, if we will be able to find the relationship between the coefficients of a block to all of its sub-blocks in the DCT domain itself, without decompressing it so that time to extract global features in compressed domain for general image processing tasks will gets minimized. In this paper, composition of a block is obtained from all of its sub-blocks and vice versa directly in DCT domain also it is shown that the result of both operations are same. The computational complexity of the proposed algorithm is lower than that of the existing ones. © 2014 IEEE.