Risk minimization in biometric sensor networks: an evolutionary multi-objective optimization approach

Biometric systems aim at identifying humans by their characteristics or traits. This article addresses the problem of designing a biometric sensor management unit by optimizing the risk, which is modeled as a multi-objective optimization (MO) problem with global false acceptance rate and global false rejection rate as the two objectives. In practice, when multiple biometric sensors are used, the decision is taken locally at each sensor and the data are passed to the sensor manager. At the sensor manager, the data are fused using a fusion rule and the final decision is taken. The optimization process involves designing the data fusion rule and setting of the sensor thresholds. In this work, we employ a fuzzy dominance and decomposition-based multi-objective evolutionary algorithm (MOEA) called MOEA/DFD and compare its performance with two state-of-the-art MO algorithms: MOEA/D and NSGA-II in context to the risk minimization task. The algorithm introduces a fuzzy Pareto dominance concept to compare two solutions and uses the scalar decomposition method only when one of the solutions fails to dominate the other in terms of a fuzzy dominance level. The MO algorithms are simulated on different number of sensor setups consisting of three, six, and eight sensors. The a priori probability of imposter is also varied from 0.1 to 0.9 to verify the performance of the system with varying degrees of threat. One of the most significant advantages of using the MO framework is that with a single run, just by changing the decision-making logic applied to the obtained Pareto front, one can find the required threshold and decision strategies for varying threats of imposter. However, with single-objective optimization, one needs to run the algorithms each time with change in the threat of imposter. Thus, multi-objective formulation of the problem appears to be more useful and better than the single-objective one. In all the test instances, MOEA/DFD performs better than all the other algorithms.

[1]  David Zhang,et al.  A New Framework for Adaptive Multimodal Biometrics Management , 2010, IEEE Transactions on Information Forensics and Security.

[2]  Sanjoy Das,et al.  Fuzzy Dominance Based Multi-objective GA-Simplex Hybrid Algorithms Applied to Gene Network Models , 2004, GECCO.

[3]  L. Hong,et al.  Can multibiometrics improve performance , 1999 .

[4]  David Zhang,et al.  Comments on "An Adaptive Multimodal Biometric Management Algorithm" , 2008, IEEE Trans. Syst. Man Cybern. Part C.

[5]  J. Mendel.  Fuzzy logic systems for engineering: a tutorial , 1995, Proc. IEEE.

[6]  M. Faundez-Zanuy,et al.  Data fusion in biometrics , 2005, IEEE Aerospace and Electronic Systems Magazine.

[7]  Yingxu Wang,et al.  A novel fuzzy multimodal information fusion technology for human biometric traits identification , 2011, IEEE 10th International Conference on Cognitive Informatics and Cognitive Computing (ICCI-CC'11).

[8]  R. Storn,et al.  Differential evolution a simple and efficient adaptive scheme for global optimization over continu , 1997 .

[9]  Kaisa Miettinen,et al.  Nonlinear multiobjective optimization , 1998, International series in operations research and management science.

[10]  Arun Ross,et al.  Decision-level fusion strategies for correlated biometric classifiers , 2008, 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.

[11]  David Zhang,et al.  Multimodal biometrics management using adaptive score-level combination , 2008, 2008 19th International Conference on Pattern Recognition.

[12]  Qingfu Zhang,et al.  The performance of a new version of MOEA/D on CEC09 unconstrained MOP test instances , 2009, 2009 IEEE Congress on Evolutionary Computation.

[13]  Ajith Abraham,et al.  An improved Multiobjective Evolutionary Algorithm based on decomposition with fuzzy dominance , 2011, 2011 IEEE Congress of Evolutionary Computation (CEC).

[14]  Marco Farina,et al.  A fuzzy definition of "optimality" for many-criteria optimization problems , 2004, IEEE Trans. Syst. Man Cybern. Part A.

[15]  Kalyan Veeramachaneni,et al.  Biometric Sensor Management: Tradeoffs in Time, Accuracy and Energy , 2009, IEEE Systems Journal.

[16]  Rainer Storn,et al.  Differential Evolution – A Simple and Efficient Heuristic for global Optimization over Continuous Spaces , 1997, J. Glob. Optim..

[17]  Pramod K. Varshney,et al.  Adaptive multimodal biometric fusion algorithm using particle swarm , 2003, SPIE Defense + Commercial Sensing.

[18]  Josef Kittler,et al.  Quality-Based Score Normalization With Device Qualitative Information for Multimodal Biometric Fusion , 2010, IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans.

[19]  Kalyanmoy Deb,et al.  A fast and elitist multiobjective genetic algorithm: NSGA-II , 2002, IEEE Trans. Evol. Comput..

[20]  Jason D. Papastavrou,et al.  Decentralized decision making in a hypothesis testing environment , 1990 .

[21]  Pramod K. Varshney,et al.  An adaptive multimodal biometric management algorithm , 2005, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[22]  Qingfu Zhang,et al.  MOEA/D: A Multiobjective Evolutionary Algorithm Based on Decomposition , 2007, IEEE Transactions on Evolutionary Computation.

[23]  Anil K. Jain,et al.  Integrating Faces and Fingerprints for Personal Identification , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[24]  Qingfu Zhang,et al.  Multiobjective Optimization Problems With Complicated Pareto Sets, MOEA/D and NSGA-II , 2009, IEEE Transactions on Evolutionary Computation.

[25]  Kushan Ahmadian,et al.  Multi-objective Evolutionary Approach for Biometric Fusion , 2009, 2009 International Conference on Biometrics and Kansei Engineering.