An Analysis of Autism Disorder Factors using Different Classification Techniques

Aloumi, Maryam; Al-Safadi, Lilac; Al-Ayadhi, Laila

doi:10.1109/ncg.2018.8593109

Cited by 4 publications

(4 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…So, he stressed the need to work with current data. Aloumi et al [ 16 ] supplied the current scale data with a fresh investigation. Aloumi et al [ 16 ] used a subset of data from scientific articles for children in this investigation.…”

Section: Applicationmentioning

confidence: 99%

See 1 more Smart Citation

Early Detection of Autism Spectrum Disorders (ASD) with the Help of Data Mining Tools

Abdulrazzaq

Hamid²,

Al-Douri³

et al. 2022

BioMed Research International

View full text Add to dashboard Cite

Autism is a disorder of neurobiological origin that originates a different course in the development of verbal and nonverbal communication, social interactions, the flexibility of behavior, and interests. The results obtained offer relevant information to reflect on the practices currently used in assessing the development of children and the detection of ASD and suggest the need to strengthen the training of health professionals in aspects such as psychology and developmental disorders. This study, based on genuine and current facts, used data from 292 children with an autism spectrum disorder. The input dataset has 20 characteristics, and the output dataset has one attribute. The output property indicates whether or not a certain person has autism. The research study first and foremost performed data pretreatment activities such as filling in missing data gaps in the data collection, digitizing categorical data, and normalizing. The features were then clustered using k -means and x -means clustering methods, then artificial neural networks and a linguistic strong neurofuzzy classifier were used to classify them. The outcomes of each strategy were examined, and their respective performances were compared.

show abstract

Section: Applicationmentioning

confidence: 99%

“…Aloumi et al [ 16 ] supplied the current scale data with a fresh investigation. Aloumi et al [ 16 ] used a subset of data from scientific articles for children in this investigation. The dataset used 292 samples and 21 characteristics.…”

Section: Applicationmentioning

confidence: 99%

Early Detection of Autism Spectrum Disorders (ASD) with the Help of Data Mining Tools

Abdulrazzaq

Hamid²,

Al-Douri³

et al. 2022

BioMed Research International

View full text Add to dashboard Cite

show abstract

“…The current scenario of ASD‐diagnosis studies used the sociodemographic and family characteristics scope by using the ML model based on pure machine learning techniques without attributing importance to the ASD features obtained from knowledge experts. Studies on predictive model have been conducted 19–21 . Several classification techniques are widely used in the AQ‐10 dataset to specify an individual's situation on the autism‐normality continuum in children, adolescents and adults 20,22–28 .…”

Section: Introductionmentioning

confidence: 99%

“…Studies on predictive model have been conducted. [19][20][21] Several classification techniques are widely used in the AQ-10 dataset to specify an individual's situation on the autism-normality continuum in children, adolescents and adults. 20,[22][23][24][25][26][27][28] However, these works have a limitation in applying the knowledge of experts when processing the dataset for constructing the ML model.…”

mentioning

confidence: 99%

Towards physician's experience: Development of machine learning model for the diagnosis of autism spectrum disorders based on complex T‐spherical fuzzy‐weighted zero‐inconsistency method

Albahri

Zaidan

Alsattar³

et al. 2022

Computational Intelligence

View full text Add to dashboard Cite

Autism spectrum disorders (ASD) are a diverse group of conditions characterized by difficulty with social interaction and communication. ASD is expected to be a high‐risk disease. Recent studies have focused on the diagnosis based on sociodemographic and family characteristics factors. The development of a diagnosis model, which is primarily based on machine learning methods, has been carried out to alleviate the detection of autism. However, they neglected the importance of ASD features in a training dataset, especially because some features have different levels of contributions to the processing data and possess more relevancies to the classification information than others. Such limitations use preprocessing techniques for the construction of the machine learning model, but the role of the physician's experience towards feature contributions remains limited. However, for certain autism datasets, the relevancies of sociodemographic and family characteristic feature concerning the given class labels should be considered. Accordingly, this study developed a new machine learning model for the diagnosis of ASD based on multi‐criteria decision‐making (MCDM). By using three methodology phases, the model combines two representative theories, namely, MCDM and machine learning. The identification phase for imbalance ASD dataset and application of pre‐possessing stages by imputing missing values, feature selection of sociodemographic and family characteristics, and data imbalanced approach resulted in balanced ASD dataset, including 107,573 cases. The development phase for the new model was achieved by the proposed complex T‐spherical fuzzy‐weighted zero‐inconsistency (CT‐SFWZIC) method. CT‐SFWZIC was developed based on a new fuzzy set (i.e., complex T‐spherical fuzzy) for weighting affected features, and then applied for training and testing the machine learning model considering various complex T‐spherical fuzzy membership functions (i.e., T = 1, 2, 3, 5, 7, and 10). The results obtained from a 10‐fold cross‐validation test for all T values by using nine machine learning classifiers were measured under seven evaluation metrics, namely AUC, accuracy, F1, precision, recall, training time (s), and test time (s). Performance evaluation results reveal that AdaBoost can be used to boost the ASD diagnosis as the best machine learning algorithm for all T values based on all metrics to improve the diagnosis based on physician's assessment. Under the most extreme evaluation metric, which is accuracy, the results of the AdaBoost classifiers for T = 1, 2, 3, 5, 7, 10 have obtained 0.99948, 0.99934, 0.99930, 0.99939, 0.99910, and 0.99930, respectively.

show abstract

Early automated prediction model for the diagnosis and detection of children with autism spectrum disorders based on effective sociodemographic and family characteristic features

Albahri

Hamid

Zaidan

et al. 2022

Neural Comput & Applic

View full text Add to dashboard Cite

An Analysis of Autism Disorder Factors using Different Classification Techniques

Cited by 4 publications

References 30 publications

Early Detection of Autism Spectrum Disorders (ASD) with the Help of Data Mining Tools

Early Detection of Autism Spectrum Disorders (ASD) with the Help of Data Mining Tools

Towards physician's experience: Development of machine learning model for the diagnosis of autism spectrum disorders based on complex T‐spherical fuzzy‐weighted zero‐inconsistency method

Early automated prediction model for the diagnosis and detection of children with autism spectrum disorders based on effective sociodemographic and family characteristic features

Contact Info

Product

Resources

About