Name
Title | ||
|---|---|---|
Risk minimization in biometric sensor networks: an evolutionary multi-objective optimization approach |
Abstract | ||
|---|---|---|
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. |
Year | DOI | Venue |
|---|---|---|
2013 | 10.1007/s00500-012-0906-5 | Soft Computing - A Fusion of Foundations, Methodologies and Applications |
Keywords | Field | DocType |
Biometric sensors,Multi-objective optimization,Decomposition technique,MOEA/D,Fuzzy dominance | A priori probability,Mathematical optimization,Evolutionary algorithm,Computer science,Fuzzy logic,Sensor fusion,Multi-objective optimization,Minification,Artificial intelligence,Wireless sensor network,Machine learning,Pareto principle | Journal |
Volume | Issue | ISSN |
17 | 1 | 1432-7643 |
Citations | PageRank | References |
2 | 0.38 | 16 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Soumyadip Sengupta | 1 | 211 | 10.08 |
| Swagatam Das | 2 | 6026 | 276.66 |
| Md Nasir | 3 | 123 | 4.75 |
| P. N. Suganthan | 4 | 10876 | 412.72 |