Pre-Trial EEG-Based Single-Trial Motor Performance Prediction to Enhance Neuroergonomics for a Hand Force Task

Meinel, Andreas; Castaño-Candamil, Sebastián; Reis, Janine; Tangermann, Michael

doi:10.3389/fnhum.2016.00170

Cited by 26 publications

(43 citation statements)

References 76 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…6 nicely demonstrates C E subject S1 S2 S3 S4 S5 S6 S7 S8 S9 S10 S11 S12 S13 S14 S15 S16 S17 S18 that the majority of clusters clearly exceed these reliability criteria. The decoding accuracies are in a comparable range as in earlier work on performance decoding for SVIPT [26]. 2) Homogeneity of clusters: DBSCAN separates between cluster and outlier samples.…”

Section: B Group-level Validation Of the Methodssupporting

confidence: 52%

See 1 more Smart Citation

Mining Within-Trial Oscillatory Brain Dynamics to Address the Variability of Optimized Spatial Filters

Meinel

Kolkhorst

Tangermann

2019

IEEE Trans. Neural Syst. Rehabil. Eng.

Self Cite

View full text Add to dashboard Cite

Data-driven spatial filtering algorithms optimize scores such as the contrast between two conditions to extract oscillatory brain signal components. Most machine learning approaches for filter estimation, however, disregard within-trial temporal dynamics and are extremely sensitive to changes in training data and involved hyperparameters. This leads to highly variable solutions and impedes the selection of a suitable candidate for, e.g., neurotechnological applications. Fostering component introspection, we propose to embrace this variability by condensing the functional signatures of a large set of oscillatory components into homogeneous clusters, each representing specific within-trial envelope dynamics.The proposed method is exemplified by and evaluated on a complex hand force task with a rich within-trial structure. Based on electroencephalography data of 18 healthy subjects, we found that the components' distinct temporal envelope dynamics are highly subject-specific. On average, we obtained seven clusters per subject, which were strictly confined regarding their underlying frequency bands. As the analysis method is not limited to a specific spatial filtering algorithm, it could be utilized for a wide range of neurotechnological applications, e.g., to select and monitor functionally relevant features for brain-computer interface protocols in stroke rehabilitation.Index Terms-brain-computer interface, oscillatory component introspection, EEG, machine learning, MEG

show abstract

Section: B Group-level Validation Of the Methodssupporting

confidence: 52%

“…As an application scenario, we chose to decode trial-wise reaction time from multi-channel EEG recordings segmented relative to a time interval close to the SVIPT go-cue. A more detailed description can be found in our initial paper [26].…”

Section: B Optimized Spatial Filtering For Single-trial Eeg Analysismentioning

confidence: 99%

Mining Within-Trial Oscillatory Brain Dynamics to Address the Variability of Optimized Spatial Filters

Meinel

Kolkhorst

Tangermann

2019

IEEE Trans. Neural Syst. Rehabil. Eng.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Moreover, it could be even more interesting to investigate whether novel or so‐far unknown features are used and to characterize them. This could be especially informative for tasks where the discriminative features are less well known than for motor decoding, for example, for less‐investigated tasks such as decoding of task performance [Meinel et al, ]. But even for the data used in this study, our results show hints that deep ConvNets used different features than shallow ConvNets and the FBCSP‐based decoding, as there are statistically significant differences between their confusion matrices (Result 3).…”

Section: Discussionmentioning

confidence: 69%

Deep learning with convolutional neural networks for EEG decoding and visualization

Schirrmeister

Springenberg

Fiederer

et al. 2017

Human Brain Mapping

Self Cite

2,272

2,128

View full text Add to dashboard Cite

Deep learning with convolutional neural networks (deep ConvNets) has revolutionized computer vision through end‐to‐end learning, that is, learning from the raw data. There is increasing interest in using deep ConvNets for end‐to‐end EEG analysis, but a better understanding of how to design and train ConvNets for end‐to‐end EEG decoding and how to visualize the informative EEG features the ConvNets learn is still needed. Here, we studied deep ConvNets with a range of different architectures, designed for decoding imagined or executed tasks from raw EEG. Our results show that recent advances from the machine learning field, including batch normalization and exponential linear units, together with a cropped training strategy, boosted the deep ConvNets decoding performance, reaching at least as good performance as the widely used filter bank common spatial patterns (FBCSP) algorithm (mean decoding accuracies 82.1% FBCSP, 84.0% deep ConvNets). While FBCSP is designed to use spectral power modulations, the features used by ConvNets are not fixed a priori. Our novel methods for visualizing the learned features demonstrated that ConvNets indeed learned to use spectral power modulations in the alpha, beta, and high gamma frequencies, and proved useful for spatially mapping the learned features by revealing the topography of the causal contributions of features in different frequency bands to the decoding decision. Our study thus shows how to design and train ConvNets to decode task‐related information from the raw EEG without handcrafted features and highlights the potential of deep ConvNets combined with advanced visualization techniques for EEG‐based brain mapping. Hum Brain Mapp 38:5391–5420, 2017. © 2017 Wiley Periodicals, Inc.

show abstract

“…Taking a closer look into the BCI decoding literature, a variety of methods for oscillatory EEG classification problems can be found, but for the regression case the choice still is extremely limited (Wu et al, 2017) even though regression methods allow tackling highly interesting problems. Examples are the estimation of continuous mental workload levels (Frey et al, 2016;Schultze-Kraft et al, 2016), decoding the depth of cognitive processing (Nicolae et al, 2017), predicting singletrial motor performance (Meinel et al, 2016) or continuous decoding of movement trajectories (Úbeda et al, 2017). A spatial filtering solution, which solves an EEG regression problem, was provided by Dähne et al (2014) with the source power comodulation algorithm (SPoC).…”

Section: Introductionmentioning

confidence: 99%

Characterizing Regularization Techniques for Spatial Filter Optimization in Oscillatory EEG Regression Problems

et al. 2018

Self Cite

View full text Add to dashboard Cite

We report on novel supervised algorithms for single-trial brain state decoding. Their reliability and robustness are essential to efficiently perform neurotechnological applications in closed-loop. When brain activity is assessed by multichannel recordings, spatial filters computed by the source power comodulation (SPoC) algorithm allow identifying oscillatory subspaces. They regress to a known continuous trial-wise variable reflecting, e.g. stimulus characteristics, cognitive processing or behavior. In small dataset scenarios, this supervised method tends to overfit to its training data as the involved recordings via electroencephalogram (EEG), magnetoencephalogram or local field potentials generally provide a low signal-to-noise ratio. To improve upon this, we propose and characterize three types of regularization techniques for SPoC: approaches using Tikhonov regularization (which requires model selection via cross-validation), combinations of Tikhonov regularization and covariance matrix normalization as well as strategies exploiting analytical covariance matrix shrinkage. All proposed techniques were evaluated both in a novel simulation framework and on real-world data. Based on the simulation findings, we saw our expectations fulfilled, that SPoC regularization generally reveals the largest benefit for small training sets and under severe label noise conditions. Relevant for practitioners, we derived operating ranges of regularization hyperparameters for cross-validation based approaches and offer open source code. Evaluating all methods additionally on real-world data, we observed an improved regression performance mainly for datasets from subjects with initially poor performance. With this proof-of-concept paper, we provided a generalizable regularization framework for SPoC which may serve as a starting point for implementing advanced techniques in the future.

show abstract

Pre-Trial EEG-Based Single-Trial Motor Performance Prediction to Enhance Neuroergonomics for a Hand Force Task

Cited by 26 publications

References 76 publications

Mining Within-Trial Oscillatory Brain Dynamics to Address the Variability of Optimized Spatial Filters

Mining Within-Trial Oscillatory Brain Dynamics to Address the Variability of Optimized Spatial Filters

Deep learning with convolutional neural networks for EEG decoding and visualization

Characterizing Regularization Techniques for Spatial Filter Optimization in Oscillatory EEG Regression Problems

Contact Info

Product

Resources

About