Please use this identifier to cite or link to this item:
|Title:||Meta-cognitive sequential learning in RBF network for diagnosis of neurodegenerative diseases||Authors:||Giduthuri Sateesh Babu||Keywords:||DRNTU::Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence||Issue Date:||2014||Source:||Giduthuri Sateesh Babu. (2014). Meta-cognitive sequential learning in RBF network for diagnosis of neurodegenerative diseases. Doctoral thesis, Nanyang Technological University, Singapore.||Abstract:||This research work focuses on the development of meta-cognitive sequential learning algorithms in Radial Basis Function (RBF) network classifiers, and their application to the early diagnosis of neurodegenerative diseases. The important issues in existing sequential learning algorithms are proper selection of training samples, finding minimal network structure and selection of an appropriate learning strategy. In addition, the random sequence of sample arrival influences the performance significantly. It has been reported in human learning that best learning strategies employ meta-cognition (meta-cognition means cognition about cognition) to address fundamental problems of what-to-learn, when-to-learn and how-to-learn. This thesis develops such meta-cognitive sequential learning algorithms in RBF network for classification problems. We call a RBF network employing meta-cognitive algorithm as `meta-cognitive RBF network' (McRBFN). McRBFN is developed based on Nelson and Narens model of meta-cognition for human learning. Accordingly, McRBFN has two components, namely cognitive and meta-cognitive components. A RBF network with evolving structure is the cognitive component and a self-regulatory learning mechanism is its meta-cognitive component. The meta-cognitive component controls the learning of cognitive component by choosing suitable learning strategies for each sample. When a new sample is presented, the meta-cognitive component either deletes the sample or learns the sample or reserves the sample for future use. Learning includes adding a new neuron or updating the parameters of the existing neurons using an extended Kalman filter (EKF). The McRBFN using EKF for parameter updates are referred as `EKF-McRBFN'. EKF-McRBFN uses computationally intensive EKF based parameter update and does not utilize the past knowledge stored in the network. Therefore, an efficient Projection Based Learning (PBL) algorithm for McRBFN referred as PBL-McRBFN has been developed. When a neuron is added to the cognitive component, the Gaussian parameters are determined based on the current sample and the output weights are estimated using the PBL algorithm. When a new neuron is added, existing neurons in the cognitive component will be used as pseudo-samples in PBL. There-by, the proposed algorithm exploits the knowledge stored in the network for proper initialization. The performance of EKF-McRBFN and PBL-McRBFN has been evaluated using a number of benchmark classification problems. The statistical performance comparisons on multiple data sets clearly indicate the superior performance of the proposed PBL-McRBFN and EKF-McRBFN over existing popular classifiers. Experimental results also show that PBL-McRBFN performance is better than EKF-McRBFN classifier. Another significant contribution of this thesis is in early diagnosis of neurodegenerative diseases. In this thesis, we employed PBL-McRBFN to early diagnosis of Alzheimer's disease (AD) and Parkinson's disease (PD). The early diagnosis of AD problem from Magnetic Resonance Imaging (MRI) scans is formed as a binary classification problem. The performance of the PBL-McRBFN classifier has been evaluated on two well-known open access Open Access Series of Imaging Studies (OASIS) and Alzheimer's disease Neuroimaging Initiative (ADNI) data sets. Morphometric features are extracted from MRI scans using Voxel-Based Morphometry (VBM). The study results clearly show that the PBL-RBFN classifier produces a better generalization performance compared to the state-of-the-art AD detection results. Also, generalization conducted on ADNI data set with PBL-McRBFN classifier trained on OASIS data set shows that the proposed PBL-McRBFN can also achieve significant results on the unseen data set. Finally, PBL-McRBFN-RFE feature selection approach has been proposed to detect imaging biomarkers responsible for AD for different age groups and for both genders using OASIS data set. The early diagnosis of PD problem is also formed as a binary classification problem. PBL-McRBFN classifier is used to predict PD using microarray gene expression data. Next, PBL-McRBFN classifier is used to predict PD from MRI scans. Further, imaging biomarkers responsible for PD are detected with the proposed PBL-McRBFN-RFE approach based on MRI scans. For completeness, PBL-McRBFN classifier is also used to detect PD from vocal and gait features. From the performance evaluation study, it is evident that the generalization performance of proposed PBL-McRBFN classifier is better than the state-of-the-art PD detection results.||URI:||https://hdl.handle.net/10356/61782||DOI:||10.32657/10356/61782||Fulltext Permission:||open||Fulltext Availability:||With Fulltext|
|Appears in Collections:||SCSE Theses|
Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.