Neurological disorders affect communication ability, social interaction, and a person’s conduct. Early diagnosis and treatment of ASD during the early stages of a person’s life may result in better outcomes and a higher quality of life for patients. Current methods of diagnosis are based on behavioral observations and interviews, which are subjective, time-consuming, and costly. EEG does not include invasive techniques, and it is a safe and painless way of measuring electrical activity in the brain. EEG signals may reflect neural differences and abnormalities related to ASD and serve as a potential biomarker for diagnosis. Due to the increase in prevalence, there has been an increased need to develop more sensitive and unbiased diagnostic methods for ASD. ML and DL are two sophisticated methods that researchers developed for detecting ASD by doing neural network analyses. The review paper incorporates the analysis of previous studies; more than 200 works have been analyzed from top publishers like Elsevier, IEEE, MDPI, and Springer, specifically related to EEG signal analysis and feature extraction techniques. It considers significant methods for ASD detection, including SVMs, CNN, and other models like KNN, ResNet50, and ANFIS. Other datasets central in these studies are KAU, BCIAUT-P300, and ADOS-2. The performance metrics adopted in this research include accuracy, sensitivity, and specificity. For example, the cubic SVM realized an accuracy of 95.8%, while the CNN models reached 95%. Other models, like ResNet50, achieved 99.39%, while ANFIS reached 98.9%. Sensitivity and specificity also showed varying scores across the methods, between 85 and 100%, indicating the high potential of these approaches in ASD diagnosis. Future studies could pay more attention to dataset representativeness improvements and do the clinical validation of these models for better generalization and relevance toward early diagnosis in ASD.

Autism spectrum disorder (ASD) poses a severe challenge to effective communication and social interaction abilities for a large number of individuals worldwide. The P300 signal is difficult to detect in individuals with ASD due to noise, low amplitude, and increased latency compared to others. We enhance in this work the P300 classification in electroencephalogram (EEG) signals for autism disease using Riemannian geometry along with various conventional classifiers and ensemble learning approaches like bagging and boosting techniques (AdaBoostM1, GentleBoost, and LogitBoost), and developing sophisticated pre-processing methods for feature extraction. Using the BCIAUT-P300 dataset, our work achieved 96.37% accuracy, 97.51% sensitivity, and 91.11% specificity compared to existing processes, ranging from 67.2% to 92.3% accuracy. This work highlights the potential of our technique in assisting in diagnosis and supportive ASD technologies