Search

As the ear biometric needed for forensic analysis and surveillance is acquired under the unconstrained environment, it suffers from the problems of illumination, pose and occlusion. To mitigate these problems, representation of both possibilistic certainty and uncertainty in the gray levels termed as the information source values of ear biometric is attempted at using the Hanman-Anirban entropy (HAE) function. An adaptive form of this entropy function helps derive Hanman transform that represents the higher level possibilistic certainty. The sum of information values constituting the information set gives the possibilistic certainty/uncertainty. The information values are modified to generate information set features such as sigmoid, energy, effective information source and effective information. Hanman filter is developed to modify the frequency content of the information values. The information rules are framed to facilitate the unsupervised learning and a new classifier called Weighted Hanman Classifier (WHC) is developed using t-normed error vectors and HAE function.WHC outperforms the other classifiers on the proposed feature types for the ear-based authentication under both constrained and unconstrained conditions. [ABSTRACT FROM AUTHOR]

A novel speed‐invariant gait features called two‐fold information set (2FInS) features that capture both spatial and temporal variations in a gait cycle are proposed in this study. These features are obtained by applying first histogram of oriented gradients descriptors on the gait images followed by the representation of the underlying possibilistic uncertainty using the Hanman–Jeevan entropy function. The 2FInS features are validated on three databases: CASIA‐C, OU‐ISIR Treadmill‐A and OU‐ISIR Treadmill‐D using Procrustes distance based classifier. In view of accounting both spatial and temporal information distributed throughout a gait cycle, the results obtained are superior to those of the existing methods. [ABSTRACT FROM AUTHOR]

This paper presents the Generalized New Entropy (GNE) gait image based authentication system using Information Set concept. A GNE function with free parameters is defined and its properties are presented. A variant of this entropy function called the dynamic entropy function is used in formulating the Dynamic Information Set based Particle Swarm Optimization (DISPSO) technique to learn the parameters. Two types of entropy features called GNE features and GNE based on Histogram of Oriented Gradients (GNE-HOG) features are formulated. After the gait cycle extraction, the farmer features are derived from the probability frames corresponding to the occurrences of 0׳s and 1׳s in every pixel location from all frames (binary silhouette images) contained in a gait cycle whereas the latter features are derived from the HOG descriptors corresponding to the probability frames termed as the possibility frames. The features are validated on three databases (CASIA, OUISIR Treadmill and SOTON small database) using Support Vector Machine (SVM), Euclidean Classifier (EC) and Improved Hanman Classifier (IHC) which is an enhanced version of Hanman Classifier in the literature. The proposed features outperform the existing features using IHC. [ABSTRACT FROM AUTHOR]

The levels of heavy metals are measured at different dumpsites with different distances and directions under the jurisdiction of Greater Municipal Corporation of Hyderabad for ascertaining the soil and groundwater quality and forecasting as a part of integrated municipal solid waste (MSW) management study. The datasets indicate a steady decrease in the concentrations of ions and heavy metals in groundwater with distance from the MSW dumpsites. Similar trends are observed for the levels of heavy metals in soil at dump sites around the MSW dumpsite. In this study, we have used both linear and quadratic regression to predict water and soil constituents. As the datasets on the components of solid waste and groundwater are limited, the desired level of forecasting accuracy could not be achieved. However, for some components the results are promising. This study suggests that improvement can be achieved by removing the outliers from the dataset. If the errors are large for a component, it would mean that we need a better way of separation of this component from the waste. [ABSTRACT FROM AUTHOR]

This paper presents a method for the extraction of twofold information set (TFIS) features for the text-independent speaker recognition. The method takes the Mel frequency cepstral coefficients from the frames of a sample speech signal and forms a matrix. From this, both spatial and temporal information components are derived based on the information set concept using the entropy framework. The TFIS features comprising their combination of two components are less in number thus reducing the computational time, complexity and improving the performance under the noisy environment. The proposed approach is tested on three datasets namely NIST-2003, VoxForge 2014 speech corpus and VCTK speech corpus in terms of speed, computational complexity, memory requirement and accuracy. Its performance is validated under different noisy environments at different signal-to-noise ratios. [ABSTRACT FROM AUTHOR]