Related references
Note: Only part of the references are listed.
Article
Computer Science, Artificial Intelligence
Jian Cui et al.
Summary: In the field of driver drowsiness recognition based on EEG, it is challenging to design a calibration-free system. This article introduces a novel convolutional neural network combined with an interpretation technique to perform sample-wise analysis of important features for classification, achieving improved recognition accuracy.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Engineering, Biomedical
Sukru Demir et al.
Summary: The study proposed an intelligent assistant system for automated detection of knee ligament injuries, achieving high classification accuracy on MRI datasets.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2022)
Article
Engineering, Biomedical
Betul Erdogdu Sakar et al.
Summary: Traditionally, emboli detection is done visually and aurally by experts, but a new study proposes an automated emboli detection system using complex wavelet transform for feature extraction. The research shows that ensemble learning has higher performance than single classifiers when training samples are limited, and using the Boruta algorithm can achieve close prediction performance with fewer samples.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2022)
Article
Neurosciences
Turker Tuncer et al.
Summary: A new emotion recognition model was proposed using EEG signals, achieving high accuracy through a hand-crafted feature generation and deep classifier approach. The model utilized a multilevel fused feature generation network, including TQWT, statistical feature generation, and nonlinear textural feature generation phases. The proposed model demonstrated excellent classification accuracies on two emotion datasets, showcasing the success of the LEDPatNet19 approach.
COGNITIVE NEURODYNAMICS
(2022)
Article
Computer Science, Artificial Intelligence
Lakhan Dev Sharma et al.
Summary: This study introduces a novel approach for stress detection using entropy-based features extracted from short-duration EEG signals, classified using various supervised machine learning algorithms. By optimizing SVM parameters and feature weighting, the accuracy of stress detection was significantly improved.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Review
Computer Science, Hardware & Architecture
Varun Kohli et al.
Summary: This paper reviews the BCI and XR technologies and discusses their potential applications in smart cities, including rehabilitation, navigation, entertainment, robotics, and home control.
MICROPROCESSORS AND MICROSYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Atta Ur Rahman et al.
Summary: Mental stress creates limitations in the workplace and can lead to various psychophysiological sicknesses. This study focuses on the perception of biological motion in the human brain and utilizes EEG signals to classify stress levels. The proposed model achieves state-of-the-art results in EEG signal classification for stress identification.
Article
Clinical Neurology
Stefanie Liebl et al.
Summary: The study found that doctors are open-minded towards new technical rehabilitation systems, emphasizing the importance of understanding the system's functionality and meaningfulness, as well as its motivational and meaningful movement generation for individuals. The system should be easy to use, evidence-based, and quick to set up, but concerns exist regarding the understanding of the system's processes in the acute phase after a stroke and the excessive expectation of results from the system.
Article
Optics
Ankita Wadhera et al.
Summary: This study proposes a robust pattern for face recognition by combining Weber pattern and pentagonal-triangle graph structure pattern to tackle the challenges of variations in facial images. Experimental results demonstrate the excellent robustness of this method in handling facial images with different expressions, illuminations, and occlusions.
Article
Engineering, Biomedical
Kevin M. Pitt et al.
Summary: The perspectives and opinions of speech-language pathologists who are experts in augmentative and alternative communication were explored to assess the potential impact and implementation barriers of brain-computer interface for AAC.
BRAIN-COMPUTER INTERFACES
(2022)
Review
Neurosciences
Matthew M. Nour et al.
Summary: Psychiatric disorders involve complex cognitive and affective abnormalities, and current treatments primarily focus on brain function and learning processes. However, despite advancements in functional neuroimaging, we still lack a neurobiological understanding of psychiatric conditions, and functional neuroimaging does not play a role in clinical decision making.
Article
Multidisciplinary Sciences
Navneet Tibrewal et al.
Summary: This study evaluated the effectiveness of deep learning models in capturing motor imagery features in motor imagery brain-computer interfaces (MI-BCIs), particularly in inefficient users. The results showed that the convolutional neural network (CNN) model improved the classification accuracy for all subjects, with a significantly larger improvement for low performers. These findings suggest promise for the employment of deep learning models in future MI-BCI systems for users who are unable to produce desired sensorimotor patterns for conventional machine learning approaches.
Review
Computer Science, Cybernetics
Baoquan Cheng et al.
Summary: This study aims to answer how to adopt EEG for measuring and computing construction workers' cognitive statuses through a critical review. The literature search and selection process included 21 eligible articles. The content analysis was then conducted from three aspects of investigated cognitive statuses, experiment design, and data analysis. This review provides guidance for researchers to use EEG for measuring and computing various cognitive statuses of construction workers, and it also offers valuable suggestions for future research and on-site construction management.
IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS
(2022)
Article
Engineering, Biomedical
Kishore Medhi et al.
Summary: Differently-abled individuals require support from others, and Brain Computer Interface (BCI) can help them with basic activities. The combination of Artificial Intelligence (AI) and Internet of Things (IoT) ecosystem enhances the effectiveness and usefulness of BCI technology. This paper presents a hybrid deep learning architecture for analyzing EEG signals, and achieves superior performance through experiments.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2022)
Article
Computer Science, Interdisciplinary Applications
Ela Kaplan et al.
Summary: This study proposes a handcrafted image classification model that accurately classifies different stages of Parkinson's disease, detects comorbid dementia, and discriminates PD-related motor symptoms. The model achieved high accuracies through the extraction of texture features, the use of multiple feature selectors and classifiers.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2022)
Article
Computer Science, Artificial Intelligence
Sengul Dogan et al.
Summary: This work develops an accurate fire warning model using images, utilizing two new deep feature engineering models and pretrained ResNet networks for feature extraction. Support vector machine classifiers and ensemble models are used for classification. The developed models achieve high classification accuracy and further testing on larger databases is recommended.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Clinical Neurology
Xiaoya Liu et al.
Summary: This study is the first attempt to investigate the altered gamma oscillations in first-episode MDD, particularly the beta-gamma coupling, and to determine the potential symptomatic relationship with the identified gamma dysregulation. The results showed significantly decreased gamma powers in the left temporal and the bilateral occipital regions in MDD patients compared to healthy control subjects, as well as weakened gamma connectivity between the left hemisphere and the right frontal region.
JOURNAL OF AFFECTIVE DISORDERS
(2022)
Review
Computer Science, Artificial Intelligence
Dongrui Wu et al.
Summary: A brain-computer interface (BCI) allows users to communicate with external devices using brain signals, and transfer learning (TL) has been widely used in MI-based BCIs to reduce calibration effort and improve utility.
Review
Chemistry, Analytical
Ilona Karpiel et al.
Summary: The COVID-19 pandemic has led to increased interest in using artificial intelligence (AI) in healthcare. This paper provides a systematic review of EEG findings in COVID-19 patients and the databases and tools used in AI algorithms to support the diagnosis of lung diseases and the correlation between lung disease and brain damage.
Review
Clinical Neurology
Mubeen Janmohamed et al.
Summary: The application of deep learning approaches for the detection of interictal epileptiform discharges is a promising area of research. However, the lack of standardized methods, variations in performance evaluation, and deficiencies in dataset descriptions have hindered the comparison and clinical validity of these algorithms. Recent publications have provided detailed datasets and performance metrics to demonstrate the potential of deep learning in epileptiform discharge detection. Standardization of dataset descriptions and reporting metrics, as well as code-sharing and accessibility to public EEG datasets, are recommended to improve the quality and progress of this field.
BRAIN COMMUNICATIONS
(2022)
Article
Health Care Sciences & Services
Emrah Aydemir et al.
Summary: This research introduces an effective schizophrenia hand-modeled classification method using a public EEG signal dataset and a feature extraction model. By iteratively analyzing and classifying features, high accuracy classification results are obtained.
Article
Engineering, Electrical & Electronic
Hemant Choubey et al.
Summary: This paper focuses on classifying EEG signals into healthy, inter-ictal, and ictal signals using statistical parameters, and accurately detecting epilepsy with reduced sets of parameters. The study compares the performance of k-nearest neighbor and artificial neural network classifiers for this classification task.
SIGNAL IMAGE AND VIDEO PROCESSING
(2021)
Review
Neurosciences
Nibras Abo Alzahab et al.
Summary: This study reviewed 47 papers from 2015 to 2020 that applied hDL to the BCI system, revealing EEG as the most commonly used technique, temporal features being the most effective, and CNN-RNN as the most used architecture.
Article
Neurosciences
Alvaro Fernandez-Rodriguez et al.
Summary: This study aimed to examine the impact of background speech on selection performance and user workload in auditory BCI systems. The results showed that shared attention to auditory BCI and background speech required a higher cognitive workload. The P300 target stimuli in the non-attentional condition were significantly higher than those in the attentional condition for several channels.
Article
Mathematics, Interdisciplinary Applications
Turker Tuncer et al.
Summary: This research introduces an automated EEG-based emotion recognition method utilizing a novel fractal pattern feature extraction approach and TQWT signal decomposition technique, achieving a high accuracy of 99.82% with SVM classifier after feature selection and shallow classifiers processing.
CHAOS SOLITONS & FRACTALS
(2021)
Article
Acoustics
Turker Tuncer et al.
Summary: This study presents a bird sound classification method based on multilevel ternary pattern and iterative ReliefF, achieving 96.67% accuracy using SVM on an 18-class bird sound dataset.
Article
Computer Science, Information Systems
Abhishek Varshney et al.
Summary: This paper proposes a computerized approach using multi-channel EEG signals for automated classification of cognitive workload tasks. By evaluating various entropy features and utilizing recurrent neural network models, high accuracy in classifying mental-arithmetic-based cognitive workload tasks was achieved.
Article
Health Care Sciences & Services
Nilima Salankar et al.
Summary: In the study, stress recognition from multimodal sensor based physiological signals like EEG and ECG signals is explored, with a dataset of 36 participants. Analysis involves decomposition and feature extraction, with classification using MPLN and SVM algorithms showing promising results, paving the way for automated stress identification systems based on noninvasive EEG signal processing.
JOURNAL OF HEALTHCARE ENGINEERING
(2021)
Article
Engineering, Biomedical
Turker Tuncer et al.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2020)
Article
Engineering, Electrical & Electronic
Shichao Chen et al.
JOURNAL OF SENSORS
(2020)
Article
Engineering, Multidisciplinary
Fatma Kuncan et al.
JOURNAL OF THE FACULTY OF ENGINEERING AND ARCHITECTURE OF GAZI UNIVERSITY
(2019)
Article
Computer Science, Information Systems
Igor Zyma et al.
Article
Computer Science, Artificial Intelligence
Jesus Maillo et al.
KNOWLEDGE-BASED SYSTEMS
(2017)
Article
Biochemical Research Methods
Ahnaf Rashik Hassan et al.
JOURNAL OF NEUROSCIENCE METHODS
(2016)
Article
Biology
Abdulhamit Subasi
COMPUTERS IN BIOLOGY AND MEDICINE
(2013)
Article
Engineering, Biomedical
Qiang Wang et al.
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING
(2013)
Article
Engineering, Electrical & Electronic
Ivan W. Selesnick
IEEE TRANSACTIONS ON SIGNAL PROCESSING
(2011)
Article
Mathematics, Interdisciplinary Applications
Matthijs J. Warrens
JOURNAL OF CLASSIFICATION
(2008)
Article
Engineering, Biomedical
Ramaswamy Palaniappan
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING
(2006)
Article
Cardiac & Cardiovascular Systems
AL Goldberger et al.