An important contribution to computer vision applications has been made by recognizing human emotion. Although it is very significant, this work considers the security of autistic people while in meltdown crisis by introducing a new system to warn caregivers through facial expressions detection. A precautionary approach has been taken to deal with meltdown crisis. Certainly, the indications of Meltdown are linked to abnormal facial expressions related to compound emotions. Actually, researchers thought long ago that Human Facial Expressions (HFE) are not able to express more than the seven basics emotions. HFE have been considered by psychologists as very complicated one, which can indicate two or even more emotions known as compound or mixed ones. A few studies have been done concerning Compound Emotion (CE). As well as, many difficult tasks to detect Compound Emotion Recognition (CER). In this paper, we empirically assess a group of deep spatio-temporal geometric features of micro-expressions of autistic children during a meltdown crisis. To achieve this goal, we make a comparison of the CER performance and diverse collections of micro-expressions features to select the features which best differentiates autistic children CE in meltdown crisis from normal state, and the best classifier performance. We record autistic children videos in normal and meltdown crisis using Kinect camera in serious circumstances. The experimental evaluation shows that the deep spatio-temporal geometric features and Recurrent Neural Network RNN with 3 hidden layer using Information Gain Feature Selection methods provide best performance (85.8%).

Autism spectrum disorder (ASD) affects approximately 1.4% of the population and imposes significant social and economic burdens. Because its etiology is unknown, effective diagnosis is challenging. Advancements in structural magnetic resonance imaging (sMRI) allow for the objective assessment of ASD by examining structural brain changes. Recently, machine learning (ML)-based diagnostic systems have emerged to expedite and enhance the diagnostic process. However, the expected success in ASD was not yet achieved. This study evaluates and compares the performance of seven optimized ML models to identify sMRI-based biomarkers for early and accurate detection of ASD in children aged 5 to 10 years. The effect of using hyperparameter tuning and feature selection techniques are investigated using two public datasets from Autism Brain Imaging Data Exchange Initiative. Furthermore, these models are tested on a local Saudi dataset to verify their generalizability. The integration of the grey wolf optimizer with a support vector machine achieved the best performance with an average accuracy of 71% (with further improvement to 71% after adding personal features) using 10-fold Cross-validation. The optimized models identified relevant biomarkers for diagnosis, lending credence to their truly generalizable nature and advancing scientific understanding of neurological changes in ASD.

This review paper focuses on the progress of deep learning-based methods for multi-view 3D object recognition. It covers the state-of-the-art techniques in this field, specifically those that utilize 3D multi-view data as input representation. The paper provides a comprehensive analysis of the pipeline for deep learning-based multi-view 3D object recognition, including the various techniques employed at each stage. It also presents the latest developments in CNN-based and transformer-based models for multi-view 3D object recognition. The review discusses existing models in detail, including the datasets, camera configurations, view selection strategies, pre-trained CNN architectures, fusion strategies, and recognition performance. Additionally, it examines various computer vision applications that use multi-view classification. Finally, it highlights future directions, factors impacting recognition performance, and trends for the development of multi-view 3D object recognition method.