BiCurNet: Pre-Movement EEG based Neural Decoder for Biceps Curl Trajectory Estimation DOI Creative Commons

Manali Saini,

Anant Jain, Lalan Kumar

et al.

arXiv (Cornell University), Journal Year: 2023, Volume and Issue: unknown

Published: Jan. 1, 2023

Kinematic parameter (KP) estimation from early electroencephalogram (EEG) signals is essential for positive augmentation using wearable robot. However, work related to of KPs surface EEG sparse. In this work, a deep learning-based model, BiCurNet, presented biceps curl collected signal. The model utilizes light-weight architecture with depth-wise separable convolution layers and customized attention module. feasibility demonstrated brain source imaging. Computationally efficient features in spherical head harmonics domain utilized the first time KP prediction. best Pearson correlation coefficient (PCC) between estimated actual trajectory $0.7$ achieved when combined (spatial domain) delta band utilized. Robustness proposed network subject-dependent subject-independent training, artifacts.

Language: Английский

Linear and nonlinear analysis of multimodal physiological data for affective arousal recognition DOI
Ali Khaleghi, Kian Shahi,

Maryam Saidi

et al.

Cognitive Neurodynamics, Journal Year: 2024, Volume and Issue: 18(5), P. 2277 - 2288

Published: March 6, 2024

Language: Английский

Citations

6
Deep learning-based classification of dementia using image representation of subcortical signals DOI Creative Commons

Shivani Ranjan,

Ayush Tripathi,

Harshal Shende

et al.

BMC Medical Informatics and Decision Making, Journal Year: 2025, Volume and Issue: 25(1)

Published: March 6, 2025

Dementia is a neurological syndrome marked by cognitive decline. Alzheimer's disease (AD) and frontotemporal dementia (FTD) are the common forms of dementia, each with distinct progression patterns. Early accurate diagnosis cases (AD FTD) crucial for effective medical care, as both conditions have similar early-symptoms. EEG, non-invasive tool recording brain activity, has shown potential in distinguishing AD from FTD mild impairment (MCI). This study aims to develop deep learning-based classification system analyzing EEG derived scout time-series signals regions, specifically hippocampus, amygdala, thalamus. Scout time series extracted via standardized low-resolution electromagnetic tomography (sLORETA) technique utilized. The converted image representations using continuous wavelet transform (CWT) fed input learning models. Two high-density datasets utilized validate efficacy proposed method: online BrainLat dataset (128 channels, comprising 16 AD, 13 FTD, 19 healthy controls (HC)) in-house IITD-AIIA (64 including subjects 10 9 MCI, 8 HC). Different strategies classifier combinations been mapping classes data sets. best results were achieved product probabilities classifiers left right subcortical regions conjunction DenseNet model architecture. It yield accuracies 94.17 % 77.72 on datasets, respectively. highlight that representation-based approach differentiate various stages dementia. pave way more early diagnosis, which treatment management debilitating conditions.

Language: Английский

Citations

0
BiCurNet: Premovement EEG-Based Neural Decoder for Biceps Curl Trajectory Estimation DOI

Manali Saini,

Anant Jain, Suriya Prakash Muthukrishnan

et al.

IEEE Transactions on Instrumentation and Measurement, Journal Year: 2023, Volume and Issue: 73, P. 1 - 11

Published: Dec. 25, 2023

Kinematic parameter (KP) estimation from early electroencephalogram (EEG) signals is essential for positive augmentation using wearable robots. However, surface EEG-based KP studies are sparse in the literature. In this study, simultaneous EEG and kinematics data of five participants collected during biceps-curl motor task. The feasibility KPs demonstrated brain source imaging (BSI). Discrete wavelet transform (DWT) utilized subband extraction preprocessed signals. Further, spherical head harmonics domain features extracted subbands A deep-learning-based decoding model, BiCurNet, proposed spatial model utilizes lightweight architecture with depthwise separable convolution layers a customized attention module (CAM). best Pearson correlation coefficient (PCC) between estimated actual trajectory 0.7 achieved when combined (spatial domain) delta band utilized. Intra- intersubject performance analyses performed to evaluate subject-adaptability model. BiCurNet compared existing multilinear regression (mLR) counterpart. robustness additionally illustrated an ablation study. robust will facilitate real-time implementation deployment on microcontroller control BCI-based

Language: Английский

Citations

6
Decoding lower-limb kinematic parameters during pedaling tasks using deep learning approaches and EEG DOI
Cristian Felipe Blanco-Díaz, Cristian David Guerrero-Méndez, Rafhael M. Andrade

et al.

Medical & Biological Engineering & Computing, Journal Year: 2024, Volume and Issue: 62(12), P. 3763 - 3779

Published: July 19, 2024

Language: Английский

Citations

2
Classification of Human Concentration Levels Based on Electroencephalography Signals DOI Creative Commons
B Siregar,

Grace Florence,

Seniman Seniman

et al.

JOIV International Journal on Informatics Visualization, Journal Year: 2024, Volume and Issue: 8(2), P. 923 - 923

Published: May 31, 2024

Concentration denotes the capability to direct one's attention a specific subject matter. Presently, within era characterized by an overwhelming abundance of information inundating human existence, distractions frequently impede concentration, thereby influencing depth knowledge acquisition. Various elements contribute decline in including diminished metabolic states, inadequate sleep, and engaging multiple tasks simultaneously. The cognitive state individual during process thinking can be assessed through analysis electroencephalography signals. primary objective this investigation is facilitate experts' interpretation signal outcomes for categorizing concentration levels. dataset utilized examination comprises unprocessed EEG data obtained from observing individuals both relaxation states. After preprocessing, feature extraction executed, classification performed using Support Vector Machine technique. outcome study reveals accuracy rate 84%. These developments allow continual monitoring brain function, enhanced comprehension cerebral activities, increased operational efficacy end-effectors. implications these advancements on prospective research opportunities are evident potential more accurate diagnosis neurological disorders progression sophisticated BCI applications designed support healthcare monitor evolution technology paving way novel pathways neuroscience human-computer interaction.

Language: Английский

Citations

0
Global synchronization of functional corticomuscular coupling under precise grip tasks using multichannel EEG and EMG signals DOI
Xiaoling Chen, Tingting Shen,

Yingying Hao

et al.

Cognitive Neurodynamics, Journal Year: 2024, Volume and Issue: 18(6), P. 3727 - 3740

Published: Aug. 6, 2024

Language: Английский

Citations

0
Brain Controlled Robotic Arm Using Motor Movements Using EEG Signals DOI Open Access

S Thejaswini,

R. Banuprakash,

Siddiq Iqbal

et al.

International Journal of Electronics and Communication Engineering, Journal Year: 2024, Volume and Issue: 11(11), P. 54 - 61

Published: Nov. 30, 2024

Brain-computer interface systems are a promising technology that allows individuals with physical disabilities to control various devices and applications through their brain activity. One of the vital challenges in developing effective BCI is accurate classification motor actual/imagery movements from electroencephalography signals. This study investigates actual imagery-based tasks identified using convolutional neural networks. Temporal features were extracted spectrogram analysis, resulting images fed CNN model classify data into four distinct classes. The achieved an approximate prediction accuracy 62% rate 100% for Class 1, 50% Classes 2 3, 75% 4. demonstrated reasonably ability detect intended Electroencephalography Additionally, robotic prototype developed capable performing specific functions, including moving backwards, forward, pinching in, out, based on output model.

Language: Английский

Citations

0
Exploring Novel Practical Approach to Post-Stroke Upper-Limb Neurorehabilitation Based on Complex Motor Imagery Tasks DOI
Cristian David Guerrero-Méndez, Hamilton Rivera-Flor, Ana Cecilia Villa-Parra

et al.

Published: July 15, 2024

Motor imagery (MI) is one of the main strategies for upper-limb movement rehabilitation in post-stroke individuals. Promising results MI applied have been reported literature. However, there currently a need related to recovery movements aimed Activities Daily Living (ADLs) individuals with severe motor impairments. Therefore, this study presents evaluation novel protocol neurorehabilitation using complex tasks manipulation drinking cup. The based on Action Observation (AO), which was used under first-person 2D virtual reality. Subjects had simultaneously imagine presented AO cup varying four positions. EEG signals were recorded from 16 channels located mainly cortex brain. Two computational Riemannian Geometry (RG) and without Feature Selection (FS) Pair-Wise Proximity (PWFP) implemented binary identification each MI-Task vs. MI-Rest. This approach evaluated 30 healthy 2 Using Linear Discriminant Analysis (LDA) as classifier, report maximum accuracy 0.78 both individuals, minimum FPR 0.21 0.13 respectively. highlights potential use type paradigms implementation more robust BCI systems that allow close ADLs. may be suitable variant

Language: Английский

Citations

0
ESI-GAL: EEG source imaging-based trajectory estimation for grasp and lift task DOI
Anant Jain, Lalan Kumar

Computers in Biology and Medicine, Journal Year: 2024, Volume and Issue: 186, P. 109608 - 109608

Published: Dec. 29, 2024

Language: Английский

Citations

0
BiCurNet: Pre-Movement EEG based Neural Decoder for Biceps Curl Trajectory Estimation DOI Creative Commons

Manali Saini,

Anant Jain, Lalan Kumar

et al.

arXiv (Cornell University), Journal Year: 2023, Volume and Issue: unknown

Published: Jan. 1, 2023

Kinematic parameter (KP) estimation from early electroencephalogram (EEG) signals is essential for positive augmentation using wearable robot. However, work related to of KPs surface EEG sparse. In this work, a deep learning-based model, BiCurNet, presented biceps curl collected signal. The model utilizes light-weight architecture with depth-wise separable convolution layers and customized attention module. feasibility demonstrated brain source imaging. Computationally efficient features in spherical head harmonics domain utilized the first time KP prediction. best Pearson correlation coefficient (PCC) between estimated actual trajectory $0.7$ achieved when combined (spatial domain) delta band utilized. Robustness proposed network subject-dependent subject-independent training, artifacts.

Language: Английский

Citations

0