Standardization of Neurotechnology for Brain-Machine Interfacing: State of the Art and Recommendations

Chavarriaga, Ricardo; Carey, Carole; Contreras-Vidal, José L.; McKinney, Zach; Bianchi, Luigi

doi:10.1109/ojemb.2021.3061328

Cited by 6 publications

(7 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lastly, we strongly recommend that the “Neurotechnologies for Brain–Machine Interfacing” group of the Institute of Electrical and Electronics Engineers Standards Association (IEEE SA) consider and adopt these guidelines for all future proposals of standards. In this group’s most recent Standards Roadmap [ 52 ], stakeholders and experts across government, academia, and industry identified the existing gap in the standardization of performance assessment and benchmarking for BMI as a clear priority for standardization [ 53 ]. Specifically, the proposal should identify these guidelines as a minimal reporting requirement for performance evaluation of EEG cross-participant models, leading to standardization in reporting how the data are partitioned, identifying their limitations, and curbing performance claims accordingly.…”

Section: Discussionmentioning

confidence: 99%

The Effects of Individual Differences, Non-Stationarity, and the Importance of Data Partitioning Decisions for Training and Testing of EEG Cross-Participant Models

Kamrud

Borghetti

Kabban

2021

Sensors

View full text Add to dashboard Cite

EEG-based deep learning models have trended toward models that are designed to perform classification on any individual (cross-participant models). However, because EEG varies across participants due to non-stationarity and individual differences, certain guidelines must be followed for partitioning data into training, validation, and testing sets, in order for cross-participant models to avoid overestimation of model accuracy. Despite this necessity, the majority of EEG-based cross-participant models have not adopted such guidelines. Furthermore, some data repositories may unwittingly contribute to the problem by providing partitioned test and non-test datasets for reasons such as competition support. In this study, we demonstrate how improper dataset partitioning and the resulting improper training, validation, and testing of a cross-participant model leads to overestimated model accuracy. We demonstrate this mathematically, and empirically, using five publicly available datasets. To build the cross-participant models for these datasets, we replicate published results and demonstrate how the model accuracies are significantly reduced when proper EEG cross-participant model guidelines are followed. Our empirical results show that by not following these guidelines, error rates of cross-participant models can be underestimated between 35% and 3900%. This misrepresentation of model performance for the general population potentially slows scientific progress toward truly high-performing classification models.

show abstract

Section: Discussionmentioning

confidence: 99%

The Effects of Individual Differences, Non-Stationarity, and the Importance of Data Partitioning Decisions for Training and Testing of EEG Cross-Participant Models

Kamrud

Borghetti

Kabban

2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Translating Brain-Machine Interface (BMI) systems onto real applications requires accepted, well-defined criteria to assess their effectiveness, usability, and safety. Benchmarking, specification, and performance evaluation are perceived as main priorities for standardization in the field [292,303,304]. This workshop discussed translational challenges, and ethical issues of BMI systems, as well as existing initiatives to address them.…”

Section: On the Need Of Good Practices And Standards For Benchmarking...mentioning

confidence: 99%

Workshops of the eighth international brain–computer interface meeting: BCIs: the next frontier

Huggins

Krusienski

Vansteensel

et al. 2022

Brain-Computer Interfaces

View full text Add to dashboard Cite

The Eighth International Brain-Computer Interface (BCI) Meeting was held June 7-9, 2021 in a virtual format. The conference continued the BCI Meeting series' interactive nature with 21 workshops covering the breadth of topics in BCI (also called brain-machine interface) research. Some workshops provided detailed examinations of methods, hardware, or processes. Others focused on BCI applications or user groups. Several workshops continued consensus building efforts designed to create BCI standards and improve comparisons between studies and the potential for meta-analysis and large multi-site clinical trials. Ethical and translational considerations were the primary topic for some workshops or an important secondary consideration for others. The range of BCI applications continues to expand, with more workshops focusing on approaches that can extend beyond the needs of those with physical impairments. This paper summarizes each workshop, provides background information and references for further study, summarizes discussions, and describes the resulting conclusion, challenges, or initiatives.

show abstract

“…There has been a growing interest in the development of non-invasive acute brain injury detection and continuous monitoring systems in recent years [1]- [12]. Advances in microelectronics is also contributing to significant progress in invasive monitoring systems such as intra cranial pressure and brain oxygenation monitoring [5]- [8].…”

Section: Introductionmentioning

confidence: 99%

“…Advances in microelectronics is also contributing to significant progress in invasive monitoring systems such as intra cranial pressure and brain oxygenation monitoring [5]- [8]. In addition, Brain Computer Interface (BCI) as a multidisciplinary research area has drawn considerable attention due to its attractive and transformative applications across many verticals in wireless communications including E-Health [1], [2], [3], [9]. Low-power, reliability, and security are essential requirements for wireless monitoring of the brain signals.…”

Section: Introductionmentioning

confidence: 99%

“…Low-power, reliability, and security are essential requirements for wireless monitoring of the brain signals. Some BCI applications may require wireless links that can support high data rates reaching 100 Mbps [1], [2]. In order to meet these requirements, in-depth propagation studies at various frequency bands are essential in the design of a wireless brain telemetry system.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Preliminary Study of RF Propagation for High Data Rate Brain Telemetry

Särestöniemi

Pomalaza‐Ráez

Sayrafian

et al. 2022

Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering

View full text Add to dashboard Cite

This paper presents the preliminary results of a study on the radio frequency (RF) propagation inside the human skull at several Industrial, Scientific and Medical (ISM) and ultrawideband UWB frequencies. These frequency bands are considered as possible candidates for high data rate wireless brain telemetry. The study is conducted using a high-resolution 3D computational model of the human head. Power flow analysis is conducted to visualize propagation inside the brain for two different on-body antenna locations. Furthermore, channel attenuation between an on-body directional mini-horn antenna and an implant antenna at different depths inside the brain is evaluated. It is observed that radio frequency propagation at 914 MHz sufficiently covers the whole volume of the brain. The coverage reduces at higher frequencies, specially above 3.1 GHz. The objective of this comparative analysis is to provide some insight on the applicability of these frequencies for high data rate brain telemetry or various monitoring, and diagnostic tools.

show abstract

Standardization of Neurotechnology for Brain-Machine Interfacing: State of the Art and Recommendations

Cited by 6 publications

References 5 publications

The Effects of Individual Differences, Non-Stationarity, and the Importance of Data Partitioning Decisions for Training and Testing of EEG Cross-Participant Models

The Effects of Individual Differences, Non-Stationarity, and the Importance of Data Partitioning Decisions for Training and Testing of EEG Cross-Participant Models

Workshops of the eighth international brain–computer interface meeting: BCIs: the next frontier

A Preliminary Study of RF Propagation for High Data Rate Brain Telemetry

Contact Info

Product

Resources

About