Multi-stimuli multi-channel data and decision fusion strategies for dyslexia prediction using neonatal ERPs

A Dynamic Multi-Channel Decision-Fusion Strategy to Classify Differential Brain Activity

“…The real 6-channel and 14-channel EP data from the 2-category match/mismatch paradigm described in [4] and the real neonatal EP data of the 3-category multi-stimuli paradigm to predict poor/dyslexic/normal readers [2] were used to design and test the dynamic multi-channel decision fusion classification strategy. For brevity, the EP experiments are described briefly, however, the exact details of the experiments can be found in the respective references.…”

“…For brevity, the EP experiments are described briefly, however, the exact details of the experiments can be found in the respective references. The ensembles of each EP category were partitioned into equal-size training and test sets using the random partitioning method described in [2], [4]. All the parameters of the discriminant functions were estimated from the training sets of each ensemble.…”

“…The 14-channel data contained 71 EPs in each ensemble. The single-trial EPs were averaged over r trials [2], [4] and the decision fusion classification results, using Gaussian discriminant functions, are presented as a function of r in Table I. Also included in the tables are the best single-channel results from a more complex Gaussian multivariate vector classifier described in [4].…”

“…EPs are used extensively in human brain function studies and in clinical investigations to study normal and abnormal brain functions [1]. The strategy introduced is derived from our studies that have shown the following: (a) there is no single best time-instant across all recording channels, (b) there is no single best channel across all time and (c) there is no single best stimulus across all time and channels [2]. That is, the classification ranking is dispersed across the H. Kook stimuli, channels, and time.…”

The development of an ontology model for early identification of children with specific learning disabilities

“…In education, many ontology-based applications have been developed to effectively overcome the barriers of sharing information across educational applications [7], teaching problem solving [8], providing frameworks for learning outcomes reuse [9,10] and enabling intelligent and personalized student support [11,12]. Furthermore, ontology also has been adopted in special education domain to identify types of special education [2,13] and recommend suitable teaching and learning process according to the special needs ISSN: 2088-8708 …”