Adbull Hamed, Haza Nuzly and Kasabov, Nikola and Michlovsky, Zbynek and Shamsuddin, Siti Mariyam (2009) String pattern recognition using evolving spiking neural networks and quantum inspired particle swarm optimization. In: Neural Information Processing: 16th International Conference, ICONIP 2009, Bangkok, Thailand, December 1-5, 2009, Proceedings, Part II. Lecture Notes in Computer Science . Springer, Berlin/ Heidelberg, pp. 611-619. ISBN 978-3-642-10682-8
Full text not available from this repository.
Official URL: http://dx.doi.org/10.1007/978-3-642-10684-2_68
This paper proposes a novel method for string pattern recognition using an Evolving Spiking Neural Network (ESNN) with Quantum-inspired Particle Swarm Optimization (QiPSO). This study reveals an interesting concept of QiPSO by representing information as binary structures. The mechanism optimizes the ESNN parameters and relevant features using the wrapper approach simultaneously. The N-gram kernel is used to map Reuters string datasets into high dimensional feature matrix which acts as an input to the proposed method. The results show promising string classification results as well as satisfactory QiPSO performance in obtaining the best combination of ESNN parameters and in identifying the most relevant features.
|Item Type:||Book Section|
|Uncontrolled Keywords:||string kernels, text classification, evolving spiking neural network, particle swarm, quantum computing|
|Subjects:||T Technology > T Technology (General)|
|Divisions:||Computer Science and Information System (Formerly known)|
|Deposited By:||Siti Khairiyah Nordin|
|Deposited On:||11 Sep 2011 09:18|
|Last Modified:||05 Feb 2017 00:43|
Repository Staff Only: item control page