Background: The spectrum of autism encompasses High Functioning Autism (HFA) and Low Functioning Autism (LFA). Brain mapping studies have revealed that autism individuals have overlaps in brain behavioural characteristics. Generally, high functioning individuals are known to exhibit higher intelligence and better language processing abilities. However, specific mechanisms associated with their functional capabilities are still under research. Objective: This work addresses the overlapping phenomenon present in autism spectrum through functional connectivity patterns along with brain connectivity parameters and distinguishes the classes using deep belief networks. Methods: The task-based functional Magnetic Resonance Images (fMRI) of both high and low functioning autistic groups were acquired from ABIDE database, for 58 low functioning against 43 high functioning individuals while they were involved in a defined language processing task. The language processing regions of the brain, along with Default Mode Network (DMN) have been considered for the analysis. The functional connectivity maps have been plotted through graph theory procedures. Brain connectivity parameters such as Granger Causality (GC) and Phase Slope Index (PSI) have been calculated for the individual groups. These parameters have been fed to Deep Belief Networks (DBN) to classify the subjects under consideration as either LFA or HFA. Results: Results showed increased functional connectivity in high functioning subjects. It was found that the additional interaction of the Primary Auditory Cortex lying in the temporal lobe, with other regions of interest complimented their enhanced connectivity. Results were validated using DBN measuring the classification accuracy of 85.85% for high functioning and 81.71% for the low functioning group. Conclusion: Since it is known that autism involves enhanced, but imbalanced components of intelligence, the reason behind the supremacy of high functioning group in language processing and region responsible for enhanced connectivity has been recognized. Therefore, this work that suggests the effect of Primary Auditory Cortex in characterizing the dominance of language processing in high functioning young adults seems to be highly significant in discriminating different groups in autism spectrum.

Down Syndrome is a genetic condition that occurs when there is an extra copy of a chromosome 21 in the newly formed fetus. EIF is observed as one of the possible symptoms of DS. But in comparison to the other symptoms like nasal bone hypoplasia, increased thickness in the nuchal fold, EIF is very much less prone to DS. Hence, recommending the pregnant women with EIF to undergo the diagnostic process like amniocentesis, CVS and PUBS is not always a right choice as these diagnostic processes suffer serious drawbacks like miscarriage, uterine infections. This chapter “Ultrasonic Detection of Down Syndrome Using Multiscale Quantiser With Convolutional Neural Network” presents a new ultrasonic method to detect EIF that can cause DS. Ultrasonic Detection of Down Syndrome Using Multiscale Quantiser with Convolutional Neural Network entails two stages namely i) training phase and ii) testing phase. Training phase aims at learning the features of EIF that can cause DS whereas testing phase classifies the EIF into DS positive or DS negative based on the knowledge cluster formed during the training phase. A new algorithm Multiscale Quantiser with the convolutional neural network is used in the training phase. Enhanced Learning Vector Classifier is used in the testing phase to differentiate the normal EIF from EIF causing DS. The performance of the proposed system is analysed in terms of sensitivity, accuracy and specificity.

Cognitive measures are directed to assess the load of working memory while performing different tasks. Excessive load on working memory hinders learning or performance of individuals. Lexile measure is the current tool used in assessing the difficulty levels of text reading in English language. Studies on correlating the cognitive load with EEG for classifying tasks based on Lexile measures have been performed for native English speakers. In this work, an attempt has been made to analyze the scope of Lexile measure for assessing the cognitive load of normal subjects. The protocol included reading and recall of texts with different Lexile complexities followed by resting phases. For increasing Lexile level complexities, a considerable increase in cognitive processing was noticed during task phase. Further, an increase in beta power was noticed at the central region indicating active information processing and decision making. Relative theta power (R?=0.11) was significant (p=0.022) in low Lexile level material and gradually decreased as the difficulty level of the tasks increased. Relative theta power was found to be decreasing as the complexity level of the text material increased and was found to dominate in both mid frontal and mid parietal regions during the recall phase. During test phase an increase in alpha power was observed at parietal region reflecting active information processing. This was evident from the highly significant (p=0.022), relative alpha power (Ra =0.036) for recall of high complexity Lexile material compared to medium (Ra=0.005) and low (Ra=0.005) level materials. Thus, it is seen that this study could be more effective in analyzing the cognitive load of subjects with different working memory efficiency. Also, while performing analysis on instructional material design based on cognitive load of different subjects, such procedures seem to be more significant.

Autism Spectrum Disorder(ASD) is a collection of heterogeneous disorders with prevalent cognitive and behavioral abnormalities. ASD is generally considered a life-long disability occurring as a stand-alone disorder but it occurs with possible co-morbid conditions such as Attention Deficit Hyperactivity Disorder (ADHD), epilepsy, Obsessive-Compulsive Disorder (OCD), Anxiety etc., Electroencephalography (EEG) studies have been identified as one of the most widely used tool for assessing the cognitive functions. Literature suggests strong evidences of stable pattern of EEG associated with Autism Spectrum Disorder. But the understanding of the subtle variations between various co-morbidities and the pathophysiology behind it needs appropriate signal processing routines. Hence, this work focuses on the identification of electrophysiological biomarkers from the acquired EEG signals of low-functioning autistic children to distinguish between the various co-morbidities of autism. Results show that the sub band power and coherence parameters estimated from segmented resting state EEG waveforms are capable of differentiating the various subgroups under consideration. The identified biomarkers can thus act as supportive tools for the physician in clinically assessing the Autistic children of different groups and to define the various training approaches for children who differ widely.