Difficulties in Facial Emotion Recognition (FER) are commonly associated with individuals diagnosed with Autism Spectrum Disorder (ASD). However, the mechanisms underlying these impairments remain inconclusive. While atypical cortical connectivity has been observed in autistic individuals, there is a paucity of investigation during cognitive tasks such as FER. It is possible that atypical cortical connectivity may underlie FER impairments in this population. Electroencephalography (EEG) Imaginary Coherence was examined in 22 autistic adults and 23 typically developing (TD) matched controls during a complex, dynamic FER task. Autistic adults demonstrated reduced coherence between both short and long range inter-hemispheric electrodes. By contrast, short range intra-hemispheric connectivity was increased in frontal and occipital regions during FER. These findings suggest altered network functioning in ASD

Abstract-Understanding the development of the brain's neural networks can reveal critical insights into the cognitive changes that occur from infancy to late childhood. Behavioural metrics including: task accuracy, stimuli recognition, and reaction time show dramatic changes over childhood. In this study we investigated response control using the Erikson Flanker task. In a dataset of 45 EEG recordings, we calculated spectral coherence to measure connectivity between all possible electrode pairs. Coherence measures were performed on two different trial conditions -congruent (where there is no response conflict) and incongruent (where response conflict is induced). The increase in incongruent coherence compared to the congruent was investigated for each electrode pair over 45 healthy subjects aged seven years. The same calculation was then performed on the same group of subjects two years later when they were aged nine years. The results revealed that at age seven years, increased coherence was detected in the left prefrontal to right and left parieto-occipital -i.e. an anatomical region located between the parietal and occipital lobes -within theta band. No increase was found for the older group-at age nine years-which may indicate cognitive development in conflict processing mechanism.

No abstract

Investigating cognitive development of children poses interesting challenges pertaining to emergence of children's' ability to think and understand. Psychological tasks that involve conflict, like the Flanker task, are widely used to understand development of response conflict processes. In this study, EEG signals were used to examine the coherence and imaginary part of coherency within the delta, theta, alpha and beta bands across different conditions of the Flanker task. Longitudinal data were collected from a group of typically developing children at ages of seven and nine. We found that the imaginary part of coherency was more helpful in distinguishing between stimuli - alpha and beta bands resulted in 90.90% classification rate in seven year old children. The beta and theta bands were found to be more effective for stimuli classification in nine year old children - more than 84.09% classification accuracy was achieved.

Automatic license plate recognition system plays an essential role in real life applications, especially those related to security and traffic managements. It essentially extracts and recognizes number plate information from videos or captured images of the targeted vehicle. Vehicle license plates differ from one country to another and because of this the effectiveness of implementing any particular method or system varies based on the plate type. In this study, we present an automatic detection, segmentation and recognition system for Libyan vehicle license plates. The main challenge in this work is our determination to use images of real vehicle plates in Libya, and the majority of these plates are not in a good condition because of poor vehicle maintenance. Three different approaches were used in the proposed system as follows:(1) Projection histogram based approach is used to locate the authorized plate license; (2) Connected component analysis based approach is used to segment the plate characters; (3) The template matching based approach is used to recognise the extracted characters. The proposed system was tested on 200 vehicle images varying in illumination conditions and backgrounds. The detection accuracy of the implemented system was 87%, the segmentation accuracy was 90% and the recognition accuracy was 86%. CCS CONCEPTS • Computing methodologies • Artificial intelligence • Computer vision • Computer vision problems • Object recognition