Machine learning for autism spectrum disorder diagnosis using structural magnetic resonance imaging: Promising but challenging.

Autism spectrum disorder (ASD) is a complex neurodevelopmental disorder that affects approximately 1% of the population and causes significant burdens. ASD's pathogenesis remains elusive; hence, diagnosis is based on a constellation of behaviors. Structural magnetic resonance imaging (sMRI) studies have shown several abnormalities in volumetric and geometric features of the autistic brain. However, inconsistent findings prevented most contributions from being translated into clinical practice. Establishing reliable biomarkers for ASD using sMRI is crucial for the correct diagnosis and treatment. In recent years, machine learning (ML) and specifically deep learning (DL) have quickly extended to almost every sector, notably in disease diagnosis. Thus, this has led to a shift and improvement in ASD diagnostic methods, fulfilling most clinical diagnostic requirements. However, ASD discovery remains difficult. This review examines the ML-based ASD diagnosis literature over the past 5 years. A literature-based taxonomy of the research landscape has been mapped, and the major aspects of this topic have been covered. First, we provide an overview of ML's general classification pipeline and the features of sMRI. Next, representative studies are highlighted and discussed in detail with respect to methods, and biomarkers. Finally, we highlight many common challenges and make recommendations for future directions. In short, the limited sample size was the main obstacle; Thus, comprehensive data sets and rigorous methods are necessary to check the generalizability of the results. ML technologies are expected to advance significantly in the coming years, contributing to the diagnosis of ASD and helping clinicians soon.

Student behavior analysis to measure engagement levels in online learning environments.

After the COVID-19 pandemic, no one refutes the importance of smart online learning systems in the educational process. Measuring student engagement is a crucial step towards smart online learning systems. A smart online learning system can automatically adapt to learners' emotions and provide feedback about their motivations. In the last few decades, online learning environments have generated tremendous interest among researchers in computer-based education. The challenge that researchers face is how to measure student engagement based on their emotions. There has been an increasing interest towards computer vision and camera-based solutions as technology that overcomes the limits of both human observations and expensive equipment used to measure student engagement. Several solutions have been proposed to measure student engagement, but few are behavior-based approaches. In response to these issues, in this paper, we propose a new automatic multimodal approach to measure student engagement levels in real time. Thus, to offer robust and accurate student engagement measures, we combine and analyze three modalities representing students' behaviors: emotions from facial expressions, keyboard keystrokes, and mouse movements. Such a solution operates in real time while providing the exact level of engagement and using the least expensive equipment possible. We validate the proposed multimodal approach through three main experiments, namely single, dual, and multimodal research modalities in novel engagement datasets. In fact, we build new and realistic student engagement datasets to validate our contributions. We record the highest accuracy value (95.23%) for the multimodal approach and the lowest value of "0.04" for mean square error (MSE).