Improved machine learning based classification model for early Autism detection

Tania Akter, Md Imran Khan, Mohammad Hanif Ali, Md Shahriare Satu, Md Jamal Uddin, Mohammad Ali Moni

Research output: Book chapter/Published conference paperConference paperpeer-review

22 Citations (Scopus)

Abstract

Autism spectrum disorder is a complex, lifelong developmental disability where the affected people show repetitive behavior and faces abnormal communication challenges. The goal of this work is to propose an enhanced machine learning model that detects autism more accurately. Hence, we collected ASD datasets of toddler, child, adolescent, and adult from kaggle and UCI machine learning repository. The correlation among individual features was scrutinized and eliminated highly co-linear features in these datasets. Then, feature transformation methods including standardization and normalization were applied in these datasets. Different classifiers like artificial neural network, recurrent neural network, decision tree, extreme learning machine, gradient boost, k nearest neighbor, logistic regression, multilayer perceptron, naïve bayes, random forest, support vector machine, and xgboost were employed in these altered ASD datasets and determined their performances. Logistic regression shows the best result that outperforms other classifiers. This model is useful to extract significant traits and detect autism more precisely.

Original languageEnglish
Title of host publicationICREST 2021 - 2nd International Conference on Robotics, Electrical and Signal Processing Techniques
Pages742-747
Number of pages6
ISBN (Electronic)9781665415767, 9781665415750 (USB)
DOIs
Publication statusPublished - 2021
Event2nd International Conference on Robotics, Electrical and Signal Processing Techniques (ICREST 2021) - Online, Bangladesh, Bangladesh
Duration: 05 Jan 202107 Jan 2021
https://web.archive.org/web/20211019063858/https://icrest.aiub.edu/ (Conference website)
https://web.archive.org/web/20210416114026/https://icrest.aiub.edu/wp-content/uploads/2021/01/Detailed_PROGRAMME-SCHEDULE-ICREST-2021_Final.pdf (Program)

Publication series

NameInternational Conference on Robotics, Electrical and Signal Processing Techniques

Conference

Conference2nd International Conference on Robotics, Electrical and Signal Processing Techniques (ICREST 2021)
Country/TerritoryBangladesh
CityBangladesh
Period05/01/2107/01/21
OtherThe 2nd International Conference on Robotics, Electrical and Signal Processing Techniques 2021 (ICREST 2021) will be organized by Faculty of Engineering, American International University-Bangladesh (AIUB). The aim of 2nd ICREST 2021 is to encourage and interact young researchers with the academic and industrial leaders to recognize the forthcoming penstock. Hence, ICREST 2021 is looking for the innovative research and ideas on the emerging developments in Computer, Electrical and Electronics, Quantum Computing, Machine and Deep Learning, Artificial Intelligence and Robotic Technologies. This platform may be a unique opportunity to develop future direction from Science and Engineering Professionals.
Internet address

Fingerprint

Dive into the research topics of 'Improved machine learning based classification model for early Autism detection'. Together they form a unique fingerprint.

Cite this