A Grid-based neural network framework for multimodal biometrics
- Authors: Venkatraman, Sitalakshmi
- Date: 2010
- Type: Text , Journal article
- Relation: Proceedings of World Academy of Science, Engineering and Technology Vol. 72, no. (2010), p. 298-303
- Full Text: false
- Reviewed:
- Description: Recent scientific investigations indicate that multimodal biometrics overcome the technical limitations of unimodal biometrics, making them ideally suited for everyday life applications that require a reliable authentication system. However, for a successful adoption of multimodal biometrics, such systems would require large heterogeneous datasets with complex multimodal fusion and privacy schemes spanning various distributed environments. From experimental investigations of current multimodal systems, this paper reports the various issues related to speed, error-recovery and privacy that impede the diffusion of such systems in real-life. This calls for a robust mechanism that caters to the desired real-time performance, robust fusion schemes, interoperability and adaptable privacy policies. The main objective of this paper is to present a framework that addresses the abovementioned issues by leveraging on the heterogeneous resource sharing capacities of Grid services and the efficient machine learning capabilities of artificial neural networks (ANN). Hence, this paper proposes a Grid-based neural network framework for adopting multimodal biometrics with the view of overcoming the barriers of performance, privacy and risk issues that are associated with shared heterogeneous multimodal data centres. The framework combines the concept of Grid services for reliable brokering and privacy policy management of shared biometric resources along with a momentum back propagation ANN (MBPANN) model of machine learning for efficient multimodal fusion and authentication schemes. Real-life applications would be able to adopt the proposed framework to cater to the varying business requirements and user privacies for a successful diffusion of multimodal biometrics in various day-to-day transactions.
Optimal sensing requirement for slippage prevention in robotic grasping
- Authors: Dzitac, Pavel , Mazid, Abdul Md , Ibrahim, Yousef , Appuhamillage, Gayan , Choudhury, Tanveer
- Date: 2015
- Type: Text , Conference proceedings
- Full Text: false
- Description: This paper presents a new theoretical development and modelling related to the requirement of the minimum number of sensors necessary for slippage prevention in robotic grasping. A fundamental experimental investigation has been conducted to support the newly developed postulate. A series of basic experiments proved that it is possible to evaluate the contributions of various sensors to slippage prevention and control in robotic grasping. The use of three discrete physical sensors, one for each of the three sensing functions (normal, tangential and slippage), has been proven to be the most reliable combination for slippage prevention in robotic grasping. It was also proven that the best performance from a two-sensor combination can be achieved when normal grasp force and tangential force are both monitored in the grasping process. © 2015 IEEE.