Complexity-Based Analysis of Muscle Activation During Walking at Different Speeds

Analysis of brain activity for patients with brain disorders is an important research area. Mild cognitive impairment (MCI) is a condition in which patients have more memory or thinking problems compared to healthy people of the same age. In this work, we studied the alterations in brain activity among control subjects and patients with MCI. Three complexity techniques, namely sample entropy, approximate entropy, and fractal dimension, were employed to study electroencephalogram (EEG) signals recorded from 102 control (healthy) subjects, and seven subjects with MCI in a comfortable position, on a bed, with their eyes closed. The results showed that the EEG signals of patients with MCI show greater complexity than the EEG signals of healthy subjects. This analysis method can be applied to compare brain activity among healthy subjects and patients with other brain diseases.

Investigating the Variations in the Brain Activity Between Healthy Subjects and Mild Cognitive Impairment (Mci) Patients

PAKNIYAT,

RAMAKRISHNAN,

PALLAVI

et al. 2023

Complexity-Based Analysis in Biomedical Image Analysis: A Review

PAKNIYAT,

ABDULLAH,

KREJCAR

et al. 2024

This review paper provides an overview of complexity-based analysis techniques in biomedical image analysis, examining their theoretical foundations, computational methodologies, and practical applications across various medical imaging modalities. Through a synthesis of relevant literature, we explore the utility of complexity-based metrics such as fractal dimension, entropy measures, and network analysis in characterizing the complexity of biomedical images (e.g. magnetic resonance imaging (MRI), computed tomography (CT) scans, X-ray images). Additionally, we discuss the clinical implications of complexity-based analysis in areas such as cancer detection, neuroimaging, and cardiovascular imaging, highlighting its potential to improve diagnostic accuracy, prognostic assessment, and treatment outcomes. The review concludes that complexity-based analysis significantly enhances the interpretability and diagnostic power of biomedical imaging, paving the way for more personalized and precise medical care. By elucidating the role of complexity-based analysis in biomedical image analysis, this review aims to provide insights into current trends, challenges, and future directions in this rapidly evolving field.

Complexity-Based Analysis of the Correlation of Brain and Heart Activity in Younger and Older Subjects

PAKNIYAT,

VIVEKANANDHAN,

DAWI

et al. 2023

Studying the activity of organs during aging is a very important research area. On the other hand, simultaneous analysis of the activities of various organs is important to understand how their activities are correlated. For the first time, this research analyzes the brain-heart correlation in younger and older subjects. We analyzed the sample entropy (SampEn) and approximate entropy (ApEn) of EEG and R-R signals (as heart rate variability (HRV)) of younger and older participants while they sat comfortably in an armchair with their eyes open. The results indicated that older subjects’ EEG and R-R signals have greater values of sample and approximate entropies than younger subjects. Therefore, as subjects age, their EEG and R-R signals become more complex. This analysis can be extended to investigate the correlation between other physiological signals among different age groups.