Classification of MI EEG signal using an advanced Deep Learning architecture for a Lower-limb rehabilitation exoskeleton

dc.contributor.authorTitkanlou, Maryam Khoshkhooy
dc.date.accessioned2025-11-12T10:17:52Z
dc.date.available2025-11-12T10:17:52Z
dc.date.issued2025
dc.description.abstract-translatedBrain-computer interface (BCI) systems employ motor imagery (MI) electroencephalogram (EEG) signals to control assistive devices like rehabilitative exoskeletons. To enhance MI EEG classification accuracy, this study suggests a novel structure utilizing an advanced deep learning architecture. Our laboratory dataset and an available public dataset will be utilized for training our model. Then Adaptive preprocessing procedures, effective classification approaches, and creative feature extraction techniques will be used to solve important challenges such as non-stationary signals, inter-subject variability, and real-time implementation constraints. Metrics like accuracy, latency, and robustness will be employed to assess the framework’s performance and make sure it is suitable for real-world applications. The goal of this research is developing a generalized deep learning network to improve the classification accuracy of MI EEG signals to assist in the creation of practical, efficient treatments for people with lower limb mobility problems.en
dc.description.sponsorshipThis work was supported by Grant No. SGS-2022-016 Advanced methods of data processing and analysis.en
dc.format58 s.cs
dc.identifier.urihttp://hdl.handle.net/11025/63850
dc.language.isoenen
dc.publisherUniversity of West Bohemiaen
dc.rights© University of West Bohemiaen
dc.subjectelektroencefalogramcs
dc.subjectexoskelet dolních končetincs
dc.subjectrehabilitacecs
dc.subjecthluboké učenícs
dc.subject.translatedelectroencephalogramen
dc.subject.translatedlower-limb exoskeletonen
dc.subject.translatedrehabilitationen
dc.subject.translateddeep learningen
dc.titleClassification of MI EEG signal using an advanced Deep Learning architecture for a Lower-limb rehabilitation exoskeletonen
dc.typereporten
dc.typezprávacs
local.files.count1*
local.files.size785546*
local.has.filesyes*

Files

Original bundle
Showing 1 - 1 out of 1 results
No Thumbnail Available
Name:
TR_2025_01.pdf
Size:
767.13 KB
Format:
Adobe Portable Document Format
License bundle
Showing 1 - 1 out of 1 results
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:

Collections