chenghnn's starred repositories
arl-eegmodels
This is the Army Research Laboratory (ARL) EEGModels Project: A Collection of Convolutional Neural Network (CNN) models for EEG signal classification, using Keras and Tensorflow
ADHD_Dataset
**Sample** : * Women (n = 57) * Men (n = 39) * Adhd subtype : hyperactive (n = 2), inattentive (n = 48), mixed (n = 46) ### Types of measures **Conners questionnaire** : standardized questionnaire. Comprizes 66 items about ADHD symptoms and behaviors. Answers are given using a Likert scale (0 = not at all/never and 3 = very often/very frequent). The items are compiled into 4 scales; * inattention/memory (IM) * hyperactivity/restlessness (HR) * impulsivity/emotional lability (IE) * problems with self concept (SC) (refers to self esteem). These four scores are used as the 4 self report symptoms measures. Test-retest correlation for 18-29 years old ranges from 0,8 to 0,92 depending on items. **IVA-II** : Behavioral test. Participants are presented with visual and auditive stimuli (numbers). If the stimulus is 1, whether it is visual or auditive, subjects must click as quickly as possible. If the stimulus is 2, whether it is visual or auditive, subjects must refrain from clickling. Stimuli are presented in a randomized order and at random time. 2 main scales are extracted, comprising 2 subscales each. 1st main scale is Attention Quotient (AQ) and its subscales are AQ auditive and AQ visual. 2nd main scale is Response Control Quotient (RCQ) and its subscales are RCQ auditive and RCQ visual. **Electroencephalography (EEG)** : 19 electrodes caps were used, positioned according to the 10-20 international system and referenced to both ear lobes. Recordings lasted 5 minutes, were participants were instructed to be as still as possible and to keep their eyes opened. The Mitsar System 201 and WinEEG (Mitast) softwares were used for recording. Test-retest and split-half correlations were higher than 0,9.
EEG-ADHD-Project
In this research, we utilized data from a study that collected EEG data from 41 five-month-old infants with ADHD and 41 infants without ADHD with similar demographic information. The goal of the study is to create an optimal predictive model to identify which parts of the brain contribute heavily to the development of ADHD. Techniques: Data Processing, Logistic Regression, Elastic Net Regression, Random Forest, Cross Validation, Boostrapping, Parameter Tuning
EEG-classification-code
learn github
eeg-processing-toolbox
Matlab code for proccesing EEG signals.
preprocessing_pipelines
Preprocessing Pipelines for EEG (MNE-python), fMRI (nipype), MEG (MNE-python/autoreject) data
meeg-preprocessing
Preprocessing tools for MEG/EEG
Attention-based-spatio-temporal-spectral-feature-learning-for-subject-specific-EEG-classification
Official code for "Attention-Based Spatio-Temporal-Spectral Feature Learning for Subject-Specific EEG Classification" paper
detection-of-adhd
We tried to detect ADHD with EEG brain recording data of ADHD and non-ADHD individuals using Random Forest classifier with an accuracy of 97% and also getting some insights to the prediction by the use of Explainable AI algorithms like LIME and SHAP.
Diagnosis-and-prediction-of-ADHD-disease-using-Machine-Learning-method-on-EEG-data
This repository contains the code and resources for the major project named "Diagnosis and Prediction of ADHD Disease using Machine Learning Methods on EEG Data."
ADHD-Detection-from-EEG-Signal
Signal Processing project: Extraction of Feature from EEG Signal to Detect ADHD
ADHDsubtypes_project
ADHD subtypes classification project with 3 different datatypes
Gohyperactivity
Exploratory data analysis and different machine learning algorithms were applied to the ADHD dataset from the IEEE data port.
FMRI_ADHD_Classification
3D_CNN classification of ADHD from FMRI data
EEG-Inherent-Fuzzy-Entropy
EEG Signal Processing - Entropy
FuzzyEntropy_Matlab
Here are the Matlab codes used in "Fuzzy Entropy Metrics for the Analysis of Biomedical Signals: Assessment and Comparison, IEEE ACCESS, 2019", including fuzzy entropy with triangular, trapezoidal, Z-shaped, bell-shaped, Gaussian, constant-Gaussian, and exponential functions.
fatigue-detection-eeg
Classification of Fatigue in Consumer-grade EEG Using Entropies as Features