An Introductory Guide on Creating a Pandas-based EEG Analysis and Action Prediction Tool for BCI Systems DOI

İbrahim Çağrı Kutlu,

Waheeb Tashan, Ibraheem Shayea

et al.

2022 IEEE 11th International Conference on Communication Systems and Network Technologies (CSNT), Journal Year: 2024, Volume and Issue: 13, P. 1372 - 1378

Published: April 6, 2024

Brain computer interfaces (BCIs) are rapidly gaining a lot of momentum within the biomedical engineer's sphere. The BCI is link between brain's electrical activity and device that monitors actions functions based on its input. In this paper, we have created prediction algorithm for systems takes in EEG data (i.e., classified actions) using machine learning (ML) techniques. Furthermore, obtained subsequently examined under specific conditions. This necessary as would otherwise lack significance computation. due to fact mostly consists highly disordered brain wave activity. analysis phase study, many Python libraries could be used ranging from MNE library which an essential tool scikit branches ML. project has special emphasis use Pandas project's been workers interns Turkish government agency called scientific technological research council Türkiye (TÜBİTAK). While was being recorded, recording software assigns condition inputs attach them epoched time data.

Language: Английский

What Is Brain-Computer Interface (BCI)? DOI
Ujwal Chaudhary

Published: Jan. 1, 2025

Language: Английский

Citations

0
Translation of single channel electro encephalic signals into limb motion DOI Creative Commons
Ana Lara‐Garcia, Oscar E. Ruiz, Lindolpho Oliveira de Araújo

et al.

Biomedical Engineering Advances, Journal Year: 2025, Volume and Issue: unknown, P. 100154 - 100154

Published: March 1, 2025

Language: Английский

Citations

0
Comparing MEG and EEG measurement set-ups for a brain–computer interface based on selective auditory attention DOI Creative Commons
Dovilė Kurmanavičiūtė,

Hanna Kataja,

Lauri Parkkonen

et al.

PLoS ONE, Journal Year: 2025, Volume and Issue: 20(4), P. e0319328 - e0319328

Published: April 10, 2025

Auditory attention modulates auditory evoked responses to target vs. non-target sounds in electro- and magnetoencephalographic (EEG/MEG) recordings. Employing whole-scalp MEG recordings offline classification algorithms has been shown enable high accuracy tracking the of attention. Here, we investigated decrease when moving from lower channel count EEG training classifier only initial or middle part recording instead extracting trials throughout recording. To this end, recorded simultaneous (306 channels) (64 18 healthy volunteers while presented with concurrent streams spoken “Yes”/“No” words instructed attend one them. We then trained support vector machine classifiers predict unaveraged MEG/EEG. Classifiers were on 204 gradiometers 64, 30, nine three channels extracted randomly across beginning The highest accuracy, 73.2% average participants for one-second trials, was obtained With EEG, 69%, 66%, 61% using nine, channels, respectively. When same amount data but recording, dropped by 11%-units average, causing result three-channel fall below chance level. combination five consecutive partially compensated drop such that it 5%-units. Although reduces usable auditory-attention-based brain-computer interfaces can be implemented a small set optimally placed channels.

Language: Английский

Citations

0
A novel precisely designed compact convolutional EEG classifier for motor imagery classification DOI
Muhammad Ahmed Abbasi, Hafza Faiza Abbasi, Muhammad Zulkifal Aziz

et al.

Signal Image and Video Processing, Journal Year: 2024, Volume and Issue: 18(4), P. 3243 - 3254

Published: Feb. 6, 2024

Language: Английский

Citations

3
Could nerve transplantation be the future of this field: a bibliometric analysis about lumbosacral plexus injury DOI Creative Commons
Sheng Wang, Demeng Xia,

Danyan Song

et al.

International Journal of Surgery, Journal Year: 2024, Volume and Issue: unknown

Published: March 21, 2024

Background: Lumbosacral plexus injury is a highly distressing clinical issue with profound implications for patients’ quality of life. Since the publication first relevant study in 1953, there has been very limited progress basic research and treatment this field, developmental trajectory priorities field have not systematically summarized using scientific methods, leaving future direction to be explored. Methods: Utilizing publications from Web Science (WoS) database, our employed bibliometric methodology analyze fundamental components publications, synthesize trends, forecast directions. Results: A total 150 were included study, impressive advancement heat can attributed continuous increase number papers, ranging 14 papers 2000 34 2023 over five years. Regarding country, central position both quantity (H-index=125) (65 publications) occupied by United States, close collaborations other countries are observed. In terms institutions, highest (9 held Second Military Medical University. The journal most (5 Journal Trauma-Injury Infection Critical Care. pivotal role played medical development field. Concerning hotspots, focus core divided into three clusters (etiology, diagnosis treatment; molecular, cells mechanisms; physiology pathology). Conclusion: This marks inaugural analysis lumbosacral injuries, offering comprehensive overview current publications. Our findings illuminate directions, international collaborations, interdisciplinary relationships. Future will emphasize mechanism research, on sacral nerve stimulation transplantation.

Language: Английский

Citations

3
A review of giant magneto-impedance-based MEG detection technique DOI Creative Commons
Wenqi Li, Zongtan Zhou, Jingsheng Tang

et al.

Brain-Apparatus Communication A Journal of Bacomics, Journal Year: 2024, Volume and Issue: 3(1)

Published: March 6, 2024

Aim This article introduces the giant magneto-impedance-based MEG detection technique to facilitate and inspire researchers wishing engage in related studies.

Language: Английский

Citations

2
A comprehensive study on navigating neuroethics in Cyberspace DOI

Er. Kritika

AI and Ethics, Journal Year: 2024, Volume and Issue: unknown

Published: May 2, 2024

Language: Английский

Citations

2
From lab to life: assessing the impact of real-world interactions on the operation of rapid serial visual presentation-based brain-computer interfaces DOI Creative Commons
Muhammad Awais, Tomás E. Ward, Peter Redmond

et al.

Journal of Neural Engineering, Journal Year: 2024, Volume and Issue: 21(4), P. 046011 - 046011

Published: June 28, 2024

Abstract Objective. Brain-computer interfaces (BCI) have been extensively researched in controlled lab settings where the P300 event-related potential (ERP), elicited rapid serial visual presentation (RSVP) paradigm, has shown promising potential. However, deploying BCIs outside of laboratory is challenging due to presence contaminating artifacts that often occur as a result activities such talking, head movements, and body movements. These can severely contaminate measured EEG signals consequently impede detection ERP. Our goal assess impact these real-world noise factors on performance RSVP-BCI, specifically focusing single-trial detection. Approach. In this study, we examine movement activity P300-based RSVP-BCI application designed allow users search images at high speed. Using machine learning, assessed using both data captured optimal recording conditions (e.g. participants were instructed refrain from moving) variety participant intentionally produced movements recording. Main results. The results, presented area under receiver operating characteristic curve (ROC-AUC) scores, provide insight into significant Notably, there reduction classifier accuracy when contaminated RSVP trials are used for training testing, compared non-intentionally trials. Significance. findings underscore necessity addressing mitigating recordings facilitate use settings, thus extending reach technology beyond confines laboratory.

Language: Английский

Citations

2
Brain and Muscle derived features to discriminate simple hand motor tasks for a rehabilitative BCI: comparative study on healthy and post-stroke individuals DOI Creative Commons
Valeria de Seta, Emma Colamarino, Floriana Pichiorri

et al.

Journal of Neural Engineering, Journal Year: 2024, Volume and Issue: 21(6), P. 066015 - 066015

Published: Oct. 17, 2024

Abstract Objective. Brain–Computer Interfaces targeting post-stroke recovery of the upper limb employ mainly electroencephalography to decode movement-related brain activation. Recently hybrid systems including muscular activity were introduced. We compared motor task discrimination abilities three different features, namely event-related desynchronization/synchronization (ERD/ERS) and cortical potential (MRCP) as brain-derived features cortico-muscular coherence (CMC) a brain-muscle derived feature, elicited in 13 healthy subjects stroke patients during execution/attempt two simple hand tasks (finger extension grasping) commonly employed rehabilitation protocols. Approach . three-way statistical design investigate whether their ability discriminate movements follows specific temporal evolution along movement execution is eventually among between groups. also investigated differences performance at single-subject level. Main results The ERD/ERS CMC-based classification showed similar evolutions with significant increase accuracy phase while MRCP-based peaked onset. Such dynamics but slower when attempted affected (AH). Moreover, CMC outperformed performing unaffected hand, whereas higher variability across was observed AH. Interestingly, performed better this latter condition respect subjects. Significance. Our provide hints improve for rehabilitation, emphasizing need personalized approaches tailored patients’ characteristics intended rehabilitative target.

Language: Английский

Citations

2
Electroencephalography-Based Brain-Computer Interfaces in Rehabilitation: A Bibliometric Analysis (2013–2023) DOI Creative Commons

Ana Medina,

Manuel Bonilla,

Ingrid Daniela Rodríguez Giraldo

et al.

Sensors, Journal Year: 2024, Volume and Issue: 24(22), P. 7125 - 7125

Published: Nov. 6, 2024

EEG-based Brain-Computer Interfaces (BCIs) have gained significant attention in rehabilitation due to their non-invasive, accessible ability capture brain activity and restore neurological functions patients with conditions such as stroke spinal cord injuries. This study offers a comprehensive bibliometric analysis of global BCI research from 2013 2023. It focuses on primary review articles addressing technological innovations, effectiveness, system advancements clinical rehabilitation. Data were sourced databases like Web Science, tools (bibliometrix R) used analyze publication trends, geographic distribution, keyword co-occurrences, collaboration networks. The results reveal rapid increase EEG-BCI research, peaking 2022, focus motor sensory EEG remains the most commonly method, contributions Asia, Europe, North America. Additionally, there is growing interest applying BCIs mental health, well integrating artificial intelligence (AI), particularly machine learning, enhance accuracy adaptability. However, challenges remain, inefficiencies slow learning curves. These could be addressed by incorporating multi-modal approaches advanced neuroimaging technologies. Further needed validate applicability both cognitive rehabilitation, especially considering high prevalence cerebrovascular diseases. To advance field, expanding participation, underrepresented regions Latin America, essential. Improving efficiency through AI integration also critical. Ethical considerations, including data privacy, transparency, equitable access technologies, must prioritized ensure inclusive development use these technologies across diverse socioeconomic groups.

Language: Английский

Citations

2