A significant amount of effort and cost is required to collect training samples for remote sensing image classifications. The study of remote sensing and how to read multispectral images is becoming more important. High-dimensional multispectral images are created by the various bands that show how materials behave. The need for more information about things and the improvement of sensor resolutions have led to the creation of multispectral data with a higher size. In recent years, it has been shown that the high dimensionality of these data makes it hard to preprocess them in multiple ways. Recent research has demonstrated that one of the most crucial methods to address this issue is by adopting a variety of learning strategies. But as the data gets more complicated, these methodologies are not adequate to support. The proposed methodology shows that the classification experiment using remote sensing images indicates the maximum likelihood classifier with different deep learning models; weight vector (WV) AdaBoost and ADAM can greatly limit overfitting, and it obtains high classification accuracy. Proposed VGG16 and Inception v3 increase classification accuracy along with optimization process produce 96.08%.
Nowadays digital transactions play a vital role in money transaction processes. Last 5 years statistical report portrays the growth of internet money transaction especially credit card and unified payments interface. Mean time increasing numerous banking threats and digital transaction fraud rates also growing significantly. Data engineering techniques provide ultra supports to detect credit card forgery problems in online and offline mode transactions. This credit card fraud detection (CCFD) and prevention-based data processing issues raising because of two major reasons first, classification rate of legitimate and forgery uses is frequently changing, and next one is fraud detection dataset values are vastly asymmetric. Through this research work investigating performance of various existing classifier with our proposed cognitive convolutional neural network (CCNN) classifier. Existing classifiers like Logistic Regression (LR), K-nearest neighbor (KNN), Decision Tree (DT) and Support Vector Machine (SVM). These models are facing various challenges of low performance rate and high complexity because of low hit rate and accuracy. Through this research work we introduce cognitive learning-based CCNN classifier methodology with artificial intelligence for achieve maximum accuracy rate and minimal complexity issues. For experimental data analysis uses dataset of credit card transactions attained from specific region cardholders containing 284500 transactions and its various features. Also, this dataset contains unstructured and non-dimensional data are converted into structured data with the help of over sample and under sample method. Performance analysis shows proposed CCNN classifier model provide significant improvement on accuracy, specificity, sensitivity and hit rate. The results are shown in comparison. After cross-validation, the accuracy of the CCNN classification algorithm model for transaction fraudulent detection archived 99% which using the over-sampling model.
Abstract-- The main objective of this paper is to examine the performance of Neuro- Statistical sparse transformation function for implementation in a still image vector coding based compression system. This paper discusses the important features of low bit-rate image coding which is based on recent developments in the theory of multivariate nonlinear piecewise polynomial approximation in still images. It combines Binary Space Partition (BSP) scheme with Geometric Wavelet (GW) tree approximation so as to efficiently capture curve singularities and provide a sparse representation of the image. The quality of the reconstructed image is measured objectively using Peak Signal to Noise Ratio. Experimental results show that the proposed image compression system yields higher compression with minimal loss.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.