English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Autistic Spectrum Disorder (ASD) is a neurological disease characterized bydifficulties with social interaction, communication, and repetitive activities.While its primary origin lies in genetics, early detection is crucial, andleveraging machine learning offers a promising avenue for a faster and morecost-effective diagnosis. This study employs diverse machine learning methodsto identify crucial ASD traits, aiming to enhance and automate the diagnosticprocess. We study eight state-of-the-art classification models to determinetheir effectiveness in ASD detection. We evaluate the models using accuracy,precision, recall, specificity, F1-score, area under the curve (AUC), kappa,and log loss metrics to find the best classifier for these binary datasets.Among all the classification models, for the children dataset, the SVM and LRmodels achieve the highest accuracy of 100% and for the adult dataset, the LRmodel produces the highest accuracy of 97.14%. Our proposed ANN model providesthe highest accuracy of 94.24% for the new combined dataset whenhyperparameters are precisely tuned for each model. As almost allclassification models achieve high accuracy which utilize true labels, webecome interested in delving into five popular clustering algorithms tounderstand model behavior in scenarios without true labels. We calculateNormalized Mutual Information (NMI), Adjusted Rand Index (ARI), and SilhouetteCoefficient (SC) metrics to select the best clustering models. Our evaluationfinds that spectral clustering outperforms all other benchmarking clusteringmodels in terms of NMI and ARI metrics while demonstrating comparability to theoptimal SC achieved by k-means. The implemented code is available at GitHub.

An Evaluation of Machine Learning Approaches for Early Diagnosis of Autism Spectrum Disorder