Computer Science and Engineerin

This article presents hierarchical fusion models for multi-biometric systems with improved recognition rate. Isolated texture regions are used to encode spatial variations from the composite biometric image which is generated by signal level fusion scheme. In this paper, the prominent issues of the existing multi-biometric system, namely, fusion methodology, storage complexity, reliability and template security are discussed. Here wavelet decomposition driven multi-resolution approach is used to generate the composite images. Texture feature metrics are extracted from multi-level texture regions and principal component analyzes are evaluated to select potentially useful texture values during template creation. Here through consistency and correlation driven hierarchical feature selection both inter-class similarity and intra-class variance problems can be solved. Finally, t-normalized feature level fusion is incorporated as a last stage to create the most reliable template for the i...

The most important parameter for urban information system is the building information which is represented by the geographic location of the buildings as well as the area, perimeter, density, inter building distances. This data is integrated with demographic data for various applications. High resolution Remote sensing images are widely used as primary data for automatic extraction of building information. Many researchers have developed different methods for maximizing the detection percentage with minimum errors. This paper analyzes the primary data available for researchers, deriving the secondary information and utilizing it effectively. Case studies by various researchers were analyzed and a methodology has been outlined using their experiences, which is expected to be more efficient and reduced errors.

The time of enormous information is presently progressing. Be that as it may, the customary information investigation will most likely be unable to wrench such huge amounts of information. The inquiry that emerges now is, the way to build up an elite stage to effectively examine huge information and how to plan a suitable mining calculation to locate the helpful things from enormous information. To profoundly talk about this issue, this paper starts with a concise prologue to information investigation, trailed by the exchanges of enormous information examination.

Heart disease is a very deadly disease. Worldwide, the majority of people are suffering from this problem. Many Machine Learning (ML) approaches are not sufficient to forecast the disease caused by the virus. Therefore, there is a need for one system that predicts disease efficiently. The Deep Learning approach predicts the disease caused by the blocked heart. This paper proposes a Convolutional Neural Network (CNN) to predict the disease at an early stage. This paper focuses on a comparison between the traditional approaches such as Logistic Regression, K-Nearest Neighbors (KNN), Naïve Bayes (NB), Support Vector Machine (SVM), Neural Networks (NN), and the proposed prediction model of CNN. The UCI machine learning repository dataset for experimentation and Cardiovascular Disease (CVD) predictions with 94% accuracy.

In this paper, palmprint verification and identification with minimum number of features is proposed. The wide principal line extractors (WPLEs) on the region of interest (ROI) are applied to generate wide principal line images (WPLIs). The WPLI is segmented into 2 × 2, 4 × 4, 8 × 8 and 16 × 16 and the feature value is extracted directly from each segment. Experiments are conducted by using the extracted features. The results show that the equal error rate (EER), decidability index (DI) and correct recognition rate (CRR) of the proposed approach is better than existing methods for PolyUPalmprint Database.