A granular functional network classifier for brain diseases analysis

Tomasiello, Stefania

doi:10.1080/21681163.2019.1627910

Cited by 10 publications

(8 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…With regards to the databases, through the literature search we were able to locate the ADHD-200 database (Alexander et al, 2017), which provides handedness data for ADHD and control participants. The ADHD-200 database is partially used in other publications (e.g., Tomasiello, 2020;Wang et al, 2019;Wyciszkiewics et al 2017), so we opted to include the full database as provided to us in January 2021 instead of those publications. Moreover, we came across the ENIGMA ADHD working group (Hoogman et al, 2017), via which we were able to locate six more databases (namely, Würzburg, Niche, ACPU, NICAP, IMpACT2) that were not used in any of the included studies.…”

Section: Included Studiesmentioning

confidence: 99%

Handedness in ADHD: Meta-Analyses

Nastou

Ocklenburg

Hoogman³

et al. 2022

Neuropsychol Rev

View full text Add to dashboard Cite

show abstract

Section: Included Studiesmentioning

confidence: 99%

Handedness in ADHD: Meta-Analyses

Nastou

Ocklenburg

Hoogman³

et al. 2022

Neuropsychol Rev

View full text Add to dashboard Cite

show abstract

“…This new GCF will provide transparent structures and enhance the efficiency of computation. In their study, the classification result shows that classifier using GCF algorithm has an accuracy of 90.4% in ABIDE I dataset in NYU [6].…”

Section: Main Contents 21 Granular Functional Network (Fn)mentioning

confidence: 96%

“…Tomasiello et al [6] employs a new type of classifier for ASD identification and diagnose. The classifier uses a refined Functional Network, adding a new layer called the granular layer to conduct information granulation.…”

Section: Main Contents 21 Granular Functional Network (Fn)mentioning

confidence: 99%

Comparative study of machine learning algorithms for early autism spectrum disorder identification

Tang

2023

Second International Conference on Biological Engineering and Medical Science (ICBioMed 2022)

View full text Add to dashboard Cite

For decades, research scientists have utilized the newly developed machine learning and Artificial Intelligence technologies to treat complicated neurological disorders. Due to the growing trend of autism spectrum disorder (ASD), various research has been conducted in this field, using machine learning classifiers for early ASD identification. Compared with traditional ASD screening methods, new classification methods involving different machine learning algorithms have displayed significant advantages in accuracy, efficiency, and reliability. The choice of machine learning algorithms is important since different algorithms will have different performances under specific circumstances. In this study, resources of information from recent research in this field were carefully gathered. Various machine learning algorithms employed in the collected research have been thoroughly studied and summarized. The experimental data derived from such research, as well as the principle and function of these algorithms have been comprehensively analyzed. Advantages, disadvantages, and suggestion of the applied circumstances for the involved algorithms were also provided for further discussion.

show abstract

“…We used the total average score to evaluate the mental health of middle-school students: 2-2.99 points indicate that there are mild mental health problems. A score of 3-3.99 indicates that there is a moderate mental health problem [5]. A score of 4-4.99 indicates that there is a severe mental health problem.…”

Section: Mental Health Assessmentmentioning

confidence: 99%

Children’s cognitive function and mental health based on finite element nonlinear mathematical model

Luo

Fakieh

Hasan

2021

Applied Mathematics and Nonlinear Sciences

View full text Add to dashboard Cite

This article uses a finite element nonlinear mathematical model to analyse the psychological conditions of children with certain physical defects. The thesis uses exercise and psychological intervention to intervene in children with material defects and scores the children’s mental state and cognitive status after the intervention. After our training and psychological intervention, the study found that the psychological evaluation scores of children with physical defects increased significantly. Before and after the intervention, there are apparent differences in children’s cognition in vocabulary and arithmetic. There is a nonlinear negative correlation between children’s cognitive abilities with physical defects and the scores of mental health status and neuropsychological evaluation. For this reason, the study concluded that movement and psychological intervention play a significant role in improving the cognitive function of children with physical defects.

show abstract

A granular functional network classifier for brain diseases analysis

Cited by 10 publications

References 26 publications

Handedness in ADHD: Meta-Analyses

Handedness in ADHD: Meta-Analyses

Comparative study of machine learning algorithms for early autism spectrum disorder identification

Children’s cognitive function and mental health based on finite element nonlinear mathematical model

Contact Info

Product

Resources

About