Biomedical Signal Processing / Medical Signal Processing / Biosignal Processing
Behnaz Sheikholeslami; Ghasem Sadeghi Bajestani; Reza Yaghoobi Karimui; Reyhaneh Zarifiyan
Volume 15, Issue 1 , May 2021, , Pages 29-46
Abstract
Attention Deficit/Hyperactivity Disorder (ADHD) is a neurodevelopmental disorder that can affect people of all ages in the community, especially children, and cause changes in their behavior. Previous studies have often focused on frequency domain processing or the nonlinear dynamic aspects of EEG signals ...
Read More
Attention Deficit/Hyperactivity Disorder (ADHD) is a neurodevelopmental disorder that can affect people of all ages in the community, especially children, and cause changes in their behavior. Previous studies have often focused on frequency domain processing or the nonlinear dynamic aspects of EEG signals such as correlation dimension, fractal dimension, Lyapunov exponent, entropy, and recurrence rate of brain processes to differentiate individuals with ADHD. In this study, we evaluate the volume of the EEG signal oscillation basin using Poincare sections in the phase space of EEG signals of people with ADHD and healthy people and sort this space as well as extract various geometric features. We present a different perspective of complexity of brain activity and the level of dynamism of people with ADHD compared to healthy individuals. Finally, by evaluating the extracted features and using the SFS algorithm based on the RBF-SVM classifier, we were able to separate people with ADHD from healthy people in the groups of children and adults, with accuracy of 93.20±2.04 and 95.60±1.13. The results of this study showed that the volume of the EEG signal oscillation basin in people with ADHD was significantly higher than healthy people, which indicates an increase in the degree of dynamism and thus a decrease in the complexity of brain activity in these people. It was also identified in this study that the increase in the volume of the EEG signal oscillation basin in children is more than adults, which indicates an increase in the level of dynamism of children compared to adults. Therefore, ADHD and age can be introduced as two important factors in changing the volume of the EEG signal oscillation basin.
Ghasem Sadeghi Bajestani; Abbas Monzavi; Seyed Mohammad Reza Hashemi Golpayegani; Farah Ashrafzadeh
Volume 11, Issue 2 , June 2017, , Pages 167-185
Abstract
Autism spectrum disorder (ASD) is a common disorder among children which despite painstakingly effort, it is not yet possible to be precisely detected using paraclinical methods. On the other hand, early detection, before 18th month, has pivotal role in treatment procedure. In this study, we present ...
Read More
Autism spectrum disorder (ASD) is a common disorder among children which despite painstakingly effort, it is not yet possible to be precisely detected using paraclinical methods. On the other hand, early detection, before 18th month, has pivotal role in treatment procedure. In this study, we present a method for early diagnosis of ASD based on the qualitative analysis of the Electroencephalogram (EEG) signal. We develop a new domain for quantifying the quality of interaction is present. We name it 'stretching – folding space’ (SFS). This domain is based on cybernetics, holistic and information-based analysis approaches. Therefore, it provides a non-deterministic approach to the biosignals. We collected data from 60 normal and 60 children with ASD in the range of 3-10 years old. We extracted features from the data in the SFS domain. The design of the study is self-controlled, meaning that each child serves as his/her own control. Each subject in the study watched a cartoon with and without sound, and the EEG signals were recorded. Statistical tests are applied on the extracted qualitative features in the SFS domain. The difference between the features of the data for each group (normal and ASD) was extracted, and the difference were compared between the groups. The results indicate that there is a statistically significant difference between the SFS features of normal and autism children. We conclude that our proposed method can serve as a new signal processing tool for diagnosing autism.
