A Projection Based Learning Meta-cognitive RBF Network Classifier for Effective Diagnosis of Parkinson’s Disease
In this paper, we proposed a ‘Projection Based Learning for Meta-cognitive Radial Basis Function Network (PBL-McRBFN)’ classifier for effective diagnosis of Parkinson’s disease. McRBFN is inspired by human meta-cognitive learning principles. McRBFN uses the estimated class label, the maximum hinge error and class-wise significance to address the self-regulating principles of what-to-learn, when-to-learn and how-to-learn in a meta-cognitive framework. Initially, McRBFN begins with zero hidden neurons and adds required number of neurons to approximate the decision surface. When a neuron is added, network parameters are initialized based on the sample overlapping conditions. The output weights are updated using a PBL algorithm such that the network finds the minimum point of an energy function defined by the hinge-loss error. The experimental results on parkinson’s data sets based on vocal and gait features clearly highlight the superior performance of PBL-McRBFN classifier over results reported in the literature for detection of individual with or without PD.
KeywordsExtreme Learn Machine Hide Neuron Radial Basis Function Neural Network Radial Basis Function Network Cognitive Component
Unable to display preview. Download preview PDF.
- 5.Jeon, H.S., Han, J., Yi, W.J., Jeon, B., Park, K.S.: Classification of Parkinson gait and normal gait using Spatial-Temporal Image of Plantar pressure. In: 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, pp. 4672–4675 (2008)Google Scholar
- 8.Isaacson, R., Fujita, F.: Metacognitive knowledge monitoring and self-regulated learning: Academic success and reflections on learning. Journal of the Scholarship of Teaching and Learning 6(1), 39–55 (2006)Google Scholar
- 13.Suresh, S., Subramanian, K.: A sequential learning algorithm for meta-cognitive neuro-fuzzy inference system for classification problems. In: The International Joint Conference on Neural Networks (IJCNN), pp. 2507–2512 (2011)Google Scholar
- 18.Chang, C.-C., Lin, C.-J.: LIBSVM: A library for support vector machines. ACM Transactions on Intelligent Systems and Technology 2, 27:1–27:27 (2011) software available at, http://www.csie.ntu.edu.tw/~cjlin/libsvm