Journal of Biometrics & Biostatistics

Classification of the biometrics data for identity validation can be modeled as a single-class problem, where the identity is confirmed by comparing the biometrics of the unknown person with those of the claimed identity. However, current feature selection techniques do not differentiate between single-class and multi-class problems when determining the suitable feature set and select the feature-set that is suitable for representing or discriminating for all the available classes. This may not be the best representation of the biometrics data of an individual because different people may have differences in the most suitable features to represent their biometrical data.

 

In this paper, a class-specific feature selection method has been proposed and experimentally validated using dynamic signatures. This method is based on the coefficient of variance within the feature set, where the features with smaller variance are selected and the ones with larger variance are rejected. The proposed technique was compared with the other feature selection methods, and the results show that a significant improvement in the classification accuracy, specificity and sensitivity was obtained when using class-specific feature selection.

Models for spatial variation in relative disease risk often consider posterior probabilities of elevated disease risk in each area, but for health prioritisation, the interest may also be in the broader clustering pattern across neighbouring areas. The classification of a particular area as high risk may or may not be consistent with risk levels in the surrounding areas. Local join-count statistics are used here in conjunction with Bayesian models of area disease risk to detect different forms of disease clustering over groups of neighbouring areas. A particular interest is in spatial clustering of high risk, which can be assessed by high probabilities of elevated risk across both a focus area and its surrounding locality. An application considers univariate spatial clustering in suicide deaths in 922 small areas in the North West of England, extending to an analysis of bivariate spatial clustering in suicide deaths and hospital admissions for intentional

self-harm in these areas.

The purpose of the present study was to establish an extension of generalized tri-phasic logistic human growth model. This model was applied through the higher dimensional growth process. Bayesian method of estimation was applied to estimate the parameters of the model. Principal component regression method was applied when there was a problem of multicollinearity in the model. The biological characteristics of the human growth process were extracted from the velocity and acceleration curve using gradient vector and Hessian matrix.

The need for an increase of reliability and security in a biometric system is motivated by the fact that there is no single technology that can realize multi-purpose scenarios. Experimental results showed that the recognition rate of Heart Sound Identification (HSI) model is 81.9%, while the rate for Speaker Identification (SI) model is 99.3% from 20 clients and 70 impostors. Heart Sound-Verification (HSV) provides an average Equal Error Rate (EER) of 13.8%, while the average EER for the Speaker Verification model (SV) is 2.1%. Electrocardiogram Identification (ECGI), on the other hand, provides an accuracy of 98.5% and ECG Verification (ECGV) EER of 4.5%. In order to reach a higher security level, an alternative multimodal and a fusion technique were implemented into the system. Through the performance analysis of the three biometric system and their combination using two multimodal biometric score level fusion, this paper found the optimal combination of those systems. The best performance of the work is based on simple-sum score fusion, with a piecewise-linear normalization technique which provides an EER of 0.7%.