Novel seizure detection algorithm based on multi-dimension feature selection

Dong, Fang; Yuan, Zhanxing; Wu, Duanpo; Jiang, Lurong; Liu, Junbiao; Hu, Wei

doi:10.1016/j.bspc.2023.104747

Cited by 10 publications

(1 citation statement)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The K-nearest neighbor approach was shown to be the best machine learning algorithm for detecting epileptic seizure activity in children when analyzing EEG signals [51]. Feature selection in a wavelet packet decomposed signal using a random forest algorithm was shown to improve seizure detection accuracy in detecting seizures [52].…”

Section: Deductive Content Analysis Of the Most Prolific Machine Lear...mentioning

confidence: 99%

Artificial Intelligence and Pediatrics: Synthetic Knowledge Synthesis

Završnik,

Kokol,

Žlahtič

et al. 2024

Electronics

View full text Add to dashboard Cite

The first publication on the use of artificial intelligence (AI) in pediatrics dates back to 1984. Since then, research on AI in pediatrics has become much more popular, and the number of publications has largely increased. Consequently, a need for a holistic research landscape enabling researchers and other interested parties to gain insights into the use of AI in pediatrics has arisen. To fill this gap, a novel methodology, synthetic knowledge synthesis (SKS), was applied. Using SKS, we identified the most prolific countries, institutions, source titles, funding agencies, and research themes and the most frequently used AI algorithms and their applications in pediatrics. The corpus was extracted from the Scopus (Elsevier, The Netherlands) bibliographic database and analyzed using VOSViewer, version 1.6.20. Done An exponential growth in the literature was observed in the last decade. The United States, China, and Canada were the most productive countries. Deep learning was the most used machine learning algorithm and classification, and natural language processing was the most popular AI approach. Pneumonia, epilepsy, and asthma were the most targeted pediatric diagnoses, and prediction and clinical decision making were the most frequent applications.

show abstract

Section: Deductive Content Analysis Of the Most Prolific Machine Lear...mentioning

confidence: 99%