http://dspace.uiu.ac.bd/handle/52243/27 2026-04-12T21:10:53Z http://dspace.uiu.ac.bd/handle/52243/2814 B-SAHIC: A blockchain based secured and automated health insurance claim processing system Khatun, Mahafuja; Islam, Ridwan Arefin; Islam, Salekul 2023-03-09T00:00:00Z http://dspace.uiu.ac.bd/handle/52243/79 Enhanced Classification Accuracy on Naive Bayes Data Mining Models Rahman, Chowdhury Mofizur; Kabir, Md. Faisal; Hossain, Alamgir; Dahal, Keshav A classification paradigm is a data mining framework containing all the concepts extracted from the training dataset to differentiate one class from other classes existed in data. The primary goal of the classification frameworks is to provide a better result in terms of accuracy. However, in most of the cases we can not get better accuracy particularly for huge dataset and dataset with several groups of data . When a classification framework considers whole dataset for training then the algorithm may become unusuable because dataset consisits of several group of data. The alternative way of making classification useable is to identify a similar group of data from the whole training data set and then training each group of similar data. In our paper, we first split the training data using kmeans clustering and then train each group with Naive Bayes Classification algorithm. In addition, we saved each model to classify sample or unknown or test data. For unknown data, we classify with the best match group/model and attain higher accuracy rate than the conventional Naive Bayes classifier. 2011-08-01T00:00:00Z http://dspace.uiu.ac.bd/handle/52243/78 On the Power of Feature Analyzer for Signature Verification Rahman, Chowdhury Mofizur; Mahmud, Jalal Uddin This paper is concerned with verification of signatures using feature analysis and non linear classifier. Signatures are collected and scanned to obtain input image. Preprocessing involves removal of noise and making the input image size invariant. Feature analyzer can reduce the large domain of feature space and extract invariable information. Because of non linearity present in the input, a non linear classifier is used. Instead of using feed forward neural network, multiple feed forward neural networks are used which are trained in the form of ensemble. Using such ensemble makes the system more general than a regular single neural network based system. Resilient back propagation algorithm has been used for each neural network training to achieve faster recognition. Significant amount of training and testing has been performed using 10 fold cross validation and resultant impressive recognition accuracy (More than 90%) proves the effectiveness of the system. 2012-12-06T00:00:00Z http://dspace.uiu.ac.bd/handle/52243/75 A New Approach for Compressing Color Images using Neural Network Rahman, Chowdhury Mofizur; Rahman, A. K. M. Ashikur In this paper a neural network based image compression method is presented. Neural networks offer the potential for providing a novel solution to the problem of data compression by its ability to generate an internal data representation. Our network, which is an application of counter propagation network, accepts a large amount of image data, compresses it for storage or transmission, and subsequently restores it when desired. A new approach for reducing training time by reconstructing representative vectors has also been proposed. Performance of the network has been evaluated using some standard real world images. It is shown that the development architecture and training algorithm provide high compression ratio and low distortion while maintaining the ability to generalize and is very robust as well. 2003-02-14T00:00:00Z