Single-trial EEG Classification Research Articles

PSAEEGNet: pyramid squeeze attention mechanism-based CNN for single-trial EEG classification in RSVP task.

Accurate classification of single-trial electroencephalogram (EEG) is crucial for EEG-based target image recognition in rapid serial visual presentation (RSVP) tasks. P300 is an important component of a single-trial EEG for RSVP tasks. However, single-trial EEG are usually characterized by low signal-to-noise ratio and limited sample sizes. Given these challenges, it is necessary to optimize existing convolutional neural networks (CNNs) to improve the performance of P300 classification. The proposed CNN model called PSAEEGNet, integrates standard convolutional layers, pyramid squeeze attention (PSA) modules, and deep convolutional layers. This approach arises the extraction of temporal and spatial features of the P300 to a finer granularity level. Compared with several existing single-trial EEG classification methods for RSVP tasks, the proposed model shows significantly improved performance. The mean true positive rate for PSAEEGNet is 0.7949, and the mean area under the receiver operating characteristic curve (AUC) is 0.9341 (p < 0.05). These results suggest that the proposed model effectively extracts features from both temporal and spatial dimensions of P300, leading to a more accurate classification of single-trial EEG during RSVP tasks. Therefore, this model has the potential to significantly enhance the performance of target recognition systems based on EEG, contributing to the advancement and practical implementation of target recognition in this field.

Single-Trial EEG Classification Using Spatio-Temporal Weighting and Correlation Analysis for RSVP-Based Collaborative Brain Computer Interface.

Since single brain computer interface (BCI) is limited in performance, it is necessary to develop collaborative BCI (cBCI) systems which integrate multi-user electroencephalogram (EEG) information to improve system performance. However, there are still some challenges in cBCI systems, including effective discriminant feature extraction of multi-user EEG data, fusion algorithms, time reduction of system calibration, etc. Methods: This study proposed an event-related potential (ERP) feature extraction and classification algorithm of spatio-temporal weighting and correlation analysis (STC) to improve the performance of cBCI systems. The proposed STC algorithm consisted of three modules. First, source extraction and interval modeling were used to overcome the problem of inter-trial variability. Second, spatio-temporal weighting and temporal projection were utilized to extract effective discriminant features for multi-user information fusion and cross-session transfer. Third, correlation analysis was conducted to match target/non-target templates for classification of multi-user and cross-session datasets. The collaborative cross-session datasets of rapid serial visual presentation (RSVP) from 14 subjects were used to evaluate the performance of the EEG classification algorithm. For single-user/collaborative EEG classification of within-session and cross-session datasets, STC had significantly higher performance than the existing state-of-the-art machine learning algorithms. It was demonstrated that STC was effective to improve the classification performance of multi-user collaboration and cross-session transfer for RSVP-based BCI systems, and was helpful to reduce the system calibration time.

An ensemble deep-learning approach for single-trial EEG classification of vibration intensity

Objective. Single-trial electroencephalography (EEG) classification is a promising approach to evaluate the cognitive experience associated with haptic feedback. Convolutional neural networks (CNNs), which are among the most widely used deep learning techniques, have demonstrated their effectiveness in extracting EEG features for the classification of different cognitive functions, including the perception of vibration intensity that is often experienced during human-computer interaction. This paper proposes a novel CNN ensemble model to classify the vibration-intensity from a single trial EEG data that outperforms the state-of-the-art EEG models. Approach. The proposed ensemble model, named SE NexFusion, builds upon the observed complementary learning behaviors of the EEGNex and TCNet Fusion models, exhibited in learning personal as well generic neural features associated with vibration intensity. The proposed ensemble employs multi-branch feature encoders corroborated with squeeze-and-excitation units that enables rich-feature encoding while at the same time recalibrating the weightage of the obtained feature maps based on their discriminative power. The model takes in a single trial of raw EEG as an input and does not require complex EEG signal-preprocessing. Main results. The proposed model outperforms several state-of-the-art bench-marked EEG models by achieving an average accuracy of 60.7% and 61.6% under leave-one-subject-out and within-subject cross-validation (three-classes), respectively. We further validate the robustness of the model through Shapley values explainability method, where the most influential spatio-temporal features of the model are counter-checked with the neural correlates that encode vibration intensity. Significance. Results show that SE NexFusion outperforms other benchmarked EEG models in classifying the vibration intensity. Additionally, explainability analysis confirms the robustness of the model in attending to features associated with the neural correlates of vibration intensity.

Riemannian classification of single-trial surface EEG and sources during checkerboard and navigational images in humans.

Different visual stimuli are classically used for triggering visual evoked potentials comprising well-defined components linked to the content of the displayed image. These evoked components result from the average of ongoing EEG signals in which additive and oscillatory mechanisms contribute to the component morphology. The evoked related potentials often resulted from a mixed situation (power variation and phase-locking) making basic and clinical interpretations difficult. Besides, the grand average methodology produced artificial constructs that do not reflect individual peculiarities. This motivated new approaches based on single-trial analysis as recently used in the brain-computer interface field. We hypothesize that EEG signals may include specific information about the visual features of the displayed image and that such distinctive traits can be identified by state-of-the-art classification algorithms based on Riemannian geometry. The same classification algorithms are also applied to the dipole sources estimated by sLORETA. We show that our classification pipeline can effectively discriminate between the display of different visual items (Checkerboard versus 3D navigational image) in single EEG trials throughout multiple subjects. The present methodology reaches a single-trial classification accuracy of about 84% and 93% for inter-subject and intra-subject classification respectively using surface EEG. Interestingly, we note that the classification algorithms trained on sLORETA sources estimation fail to generalize among multiple subjects (63%), which may be due to either the average head model used by sLORETA or the subsequent spatial filtering failing to extract discriminative information, but reach an intra-subject classification accuracy of 82%.

DC-tCNN: A Deep Model for EEG-Based Detection of Dim Targets.

Dim target detection in remote sensing images is a significant and challenging problem. In this work, we seek to explore event-related brain responses of dim target detection tasks and extend the brain-computer interface (BCI) systems to this task for efficiency enhancement. We develop a BCI paradigm named Asynchronous Visual Evoked Paradigm (AVEP), in which subjects are required to search the dim targets within satellite images when their scalp electroencephalography (EEG) signals are simultaneously recorded. In the paradigm, stimulus onset time and target onset time are asynchronous because subjects need enough time to confirm whether there are targets of interest in the presented serial images. We further propose a Domain adaptive and Channel-wise attention-based Time-domain Convolutional Neural Network (DC-tCNN) to solve the single-trial EEG classification problem for the AVEP task. In this model, we design a multi-scale CNN module combined with a channel-wise attention module to effectively extract event-related brain responses underlying EEG signals. Meanwhile, domain adaptation is proposed to mitigate cross-subject distribution discrepancy. The results demonstrate the superior performance and better generalizability of this model in classifying the single-trial EEG data of AVEP task in contrast to typical EEG deep learning networks. Visualization analyses of spatiotemporal features also illustrate the effectiveness and interpretability of our proposed paradigm and learning model. The proposed paradigm and model can effectively explore ambiguous event-related brain responses on EEG-based dim target detection tasks. Our work can provide a valuable reference for BCI-based image detection of dim targets.

Single-Trial EEG Classification via Orthogonal Wavelet Decomposition-Based Feature Extraction.

Achieving high classification performance is challenging due to non-stationarity and low signal-to-noise ratio (low SNR) characteristics of EEG signals. Spatial filtering is commonly used to improve the SNR yet the individual differences in the underlying temporal or frequency information is often ignored. This paper investigates motor imagery signals via orthogonal wavelet decomposition, by which the raw signals are decomposed into multiple unrelated sub-band components. Furthermore, channel-wise spectral filtering via weighting the sub-band components are implemented jointly with spatial filtering to improve the discriminability of EEG signals, with an l2-norm regularization term embedded in the objective function to address the underlying over-fitting issue. Finally, sparse Bayesian learning with Gaussian prior is applied to the extracted power features, yielding an RVM classifier. The classification performance of SEOWADE is significantly better than those of several competing algorithms (CSP, FBCSP, CSSP, CSSSP, and shallow ConvNet). Moreover, scalp weight maps of the spatial filters optimized by SEOWADE are more neurophysiologically meaningful. In summary, these results demonstrate the effectiveness of SEOWADE in extracting relevant spatio-temporal information for single-trial EEG classification.

A deep learning method for single-trial EEG classification in RSVP task based on spatiotemporal features of ERPs

Objective. Single-trial electroencephalography (EEG) classification is of great importance in the rapid serial visual presentation (RSVP) task. Convolutional neural networks (CNNs), as one of the mainstream deep learning methods, have been proven to be effective in extracting RSVP EEG features. However, most existing CNN models for EEG classification do not consider the phase-locked characteristic of event-related potential (ERP) components very well in the architecture design. Here, we propose a novel CNN model to make better use of the phase-locked characteristic to extract spatiotemporal features for single-trial RSVP EEG classification. Based on the phase-locked characteristic, the spatial distributions of the main ERP component in different periods can be learned separately. Approach. In this work, we propose a novel CNN model to achieve superior performance on single-trial RSVP EEG classification. We introduce the combination of the standard convolutional layer, the permute layer and the depthwise convolutional layer to separately operate the spatial convolution in different periods, which more fully utilizes the phase-locked characteristic of ERPs for classification. We compare our model with several traditional and deep-learning methods in the classification performance. Moreover, we use spatial topography and saliency map to visually analyze the ERP features extracted by our model. Main results. The results show that our model obtains better classification performance than those of reference methods. The spatial topographies of each subject exhibit the typical ERP spatial distribution in different time periods. And the saliency map of each subject illustrates the discriminant electrodes and the meaningful temporal features. Significance. Our model is designed with better consideration of the phase-locked ERP characteristic and reaches excellent performance on single-trial RSVP EEG classification.

Single-Trial EEG Classification via Common Spatial Patterns with Mixed Lp- and Lq-Norms

As a multichannel spatial filtering technique, common spatial patterns (CSP) have been successfully applied in brain-computer interfaces (BCI) community based on electroencephalogram (EEG). However, it is sensitive to outliers because of the employment of the L2-norm in its formulation. It is beneficial to perform robust modelling for CSP. In this paper, we propose a robust framework, called CSP-Lp/q, by formulating the variances of two EEG classes with Lp- and Lq-norms (0&lt;p and q&lt;2) separately. The method CSP-Lp/q with mixed Lp- and Lq-norms takes the class-wise difference into account in formulating the sample dispersion. We develop an iterative algorithm to optimize the objective function of CSP-Lp/q and show its monotonity theoretically. The superiority of the proposed CSP-Lp/q technique is experimentally demonstrated on three real EEG datasets of BCI competitions.

Recognizing single-trial motor imagery EEG based on interpretable clustering method

This work explores an approach for single-trial motor imagery (MI) electroencephalography (EEG) classification in interpretable clustering. The tensor structured EEG data under Mu rhythm is first processed by Common Spatial Subspace Decomposition (CSSD) to obtain the multi-dimensional CSSD-mapped EEG. In the dimensional feature reduction, Fisher’s ratio is used as the cost function to automatically find the optimal projection plane with two feature vectors of CSSD-mapped EEG corresponding to the largest Fisher’s ratio. Then, Discriminative Rectangle Mixture Model (DRMM) that gives a rectangular decision rule is used to identify optimal feature vectors to realize single-trial motor imagery EEG classification in an interpretable way. This innovative data analysis model generates reasonable cluster results driven by optimal feature data. The probability density distribution functions of EEG data in two classes can effectively explain the reliability of the rectangular decision rule given by the DRMM. The proposed method has been validated using the areas under the receiver operating characteristic curve (AUC) and cluster quality evaluation metrics. Experimental results demonstrate its performance is comparable to existing clustering and gives interpretable clustering results when detecting the motor intention involving EEG signals. This paper provides a novelty method based on interpretable clustering for single-trial MI EEG classification. And it may promote the development of BCI application.

Decoding Visual Motions from EEG Using Attention-Based RNN

The main objective of this paper is to use deep neural networks to decode the electroencephalography (EEG) signals evoked when individuals perceive four types of motion stimuli (contraction, expansion, rotation, and translation). Methods for single-trial and multi-trial EEG classification are both investigated in this study. Attention mechanisms and a variant of recurrent neural networks (RNNs) are incorporated as the decoding model. Attention mechanisms emphasize task-related responses and reduce redundant information of EEG, whereas RNN learns feature representations for classification from the processed EEG data. To promote generalization of the decoding model, a novel online data augmentation method that randomly averages EEG sequences to generate artificial signals is proposed for single-trial EEG. For our dataset, the data augmentation method improves the accuracy of our model (based on RNN) and two benchmark models (based on convolutional neural networks) by 5.60%, 3.92%, and 3.02%, respectively. The attention-based RNN reaches mean accuracies of 67.18% for single-trial EEG decoding with data augmentation. When performing multi-trial EEG classification, the amount of training data decreases linearly after averaging, which may result in poor generalization. To address this deficiency, we devised three schemes to randomly combine data for network training. Accordingly, the results indicate that the proposed strategies effectively prevent overfitting and improve the correct classification rate compared with averaging EEG fixedly (by up to 19.20%). The highest accuracy of the three strategies for multi-trial EEG classification achieves 82.92%. The decoding performance for the methods proposed in this work indicates they have application potential in the brain–computer interface (BCI) system based on visual motion perception.

Towards error categorisation in BCI: single-trial EEG classification between different errors

Objective. Error-related potentials (ErrP) are generated in the brain when humans perceive errors. These ErrP signals can be used to classify actions as erroneous or non-erroneous, using single-trial electroencephalography (EEG). A small number of studies have demonstrated the feasibility of using ErrP detection as feedback for reinforcement-learning-based brain-computer interfaces (BCI), confirming the possibility of developing more autonomous BCI. These systems could be made more efficient with specific information about the type of error that occurred. A few studies differentiated the ErrP of different errors from each other, based on direction or severity. However, errors cannot always be categorised in these ways. We aimed to investigate the feasibility of differentiating very similar error conditions from each other, in the absence of previously explored metrics. Approach. In this study, we used two data sets with 25 and 14 participants to investigate the differences between errors. The two error conditions in each task were similar in terms of severity, direction and visual processing. The only notable differences between them were the varying cognitive processes involved in perceiving the errors, and differing contexts in which the errors occurred. We used a linear classifier with a small feature set to differentiate the errors on a single-trial basis. Main results. For both data sets, we observed neurophysiological distinctions between the ErrPs related to each error type. We found further distinctions between age groups. Furthermore, we achieved statistically significant single-trial classification rates for most participants included in the classification phase, with mean overall accuracy of 65.2% and 65.6% for the two tasks. Significance. As a proof of concept our results showed that it is feasible, using single-trial EEG, to classify these similar error types against each other. This study paves the way for more detailed and efficient learning in BCI, and thus for a more autonomous human-machine interaction.

Feature Space Reduction for Single Trial EEG Classification based on Wavelet Decomposition.

In contrary to recent signal/information processing advancements, human brain remains the most intriguing signal processing unit in existence with inconceivable capabilities to fuse various multi-modal signals, adaptively and in real-time fashion. To connect brain with the outer world, brain computer interfacing (BCI) via Electroencephalography (EEG) signals has received extensive attention. Extracting informative and discriminating features from EEG signals and decomposing the recorded signals into their underlying components is believed to yield compromising results. Different algorithms, therefore, are recently proposed combining signal decomposition techniques (e.g., spectral filterbanks, and Wavelet decomposition) with feature extracting methodologies (e.g., common spatial patterns (CSP), and Riemannian manifold learning). Although coupling filterbanks and Wavelet with the CSP has been investigated, to best of our knowledge, the potentials of coupling Wavelet with Riemannian manifold learning are not yet studied. The paper addresses this gap. In particular, we propose a level-based classification approach that couples the Wavelet decomposition with Riemannian manifold spatial learning (WvRiem). In the proposed WvRiem framework, the EEG signals are decomposed into several components (levels) and then spatial filtering via Riemannian manifold learning is performed on the best level which yields the most discriminating features. The proposed WvRiem is evaluated on the BCI Competition IV2a dataset and noticeably outperforms its counterparts.

Multiclass Support Matrix Machines by Maximizing the Inter-Class Margin for Single Trial EEG Classification.

Accurate classification of Electroencephalogram (EEG) signals plays an important role in diagnoses of different type of mental activities. One of the most important challenges, associated with classification of EEG signals is how to design an efficient classifier consisting of strong generalization capability. Aiming to improve the classification performance, in this paper, we propose a novel multiclass support matrix machine (M-SMM) from the perspective of maximizing the inter-class margins. The objective function is a combination of binary hinge loss that works on C matrices and spectral elastic net penalty as regularization term. This regularization term is a combination of Frobenius and nuclear norm, which promotes structural sparsity and shares similar sparsity patterns across multiple predictors. It also maximizes the inter-class margin that helps to deal with complex high dimensional noisy data. The extensive experiment results supported by theoretical analysis and statistical tests show the effectiveness of the M-SMM for solving the problem of classifying EEG signals associated with motor imagery in brain-computer interface applications.

Bayesian Optimized Spectral Filters Coupled With Ternary ECOC for Single-Trial EEG Classification.

Motivated by the promising emergence of brain-computer interfaces (BCIs) within assistive/rehabilitative systems for therapeutic applications, this paper proposes a novel Bayesian framework that simultaneously optimizes a number of subject-specific filter banks and spatial filters. Optimized double-band spectro-spatial filters are derived based on common spatial patterns coupled with the error-correcting output coding (ECOC) classifiers. The proposed framework constructs optimized subject-specific spectral filters in an intuitive fashion resulting in creation of significantly discriminant features, which is a crucial requirement for any EEG-based BCI system. Through incorporation of the ECOC approach, the classification problem is then modeled as communication over a noisy channel where the misclassification error is corrected by error correction techniques borrowed from an information theory. This paper also proposes a modified version of the ECOC adopted to EEG classification problems by deploying ternary class codewords to increase the Hamming distance between the codewords and introduce more robustness to misclassification error. The proposed framework is evaluated over two different datasets from the BCI Competition (i.e., BCIC- and BCIC- ). The results indicate that the proposed approach outperforms its counterparts and validate the essential role of optimized spectral filters on the overall classification accuracy.

Single-Trial EEG Classification of Similar Errors.

When humans recognise errors, either committed by themselves or observed, error-related potentials (ErrP) are produced in the brain. Recently, a few studies have shown that it is possible to differentiate between the ErrPs generated for errors of different direction, severity, or type (e.g., response errors, interaction errors). However, in real-world scenarios, errors cannot always be delineated by these metrics. As such, it is important to consider whether errors that are similar in all of the aforementioned aspects can be classified against each other on a single-trial basis. In this paper, for the first time, we consider two different response errors, which are of equal severity and have no associated direction. This study used electroencephalogram (EEG) data from a sustainedattention based time-critical reaction task, where time pressure caused subjects to commit two different errors. Using data from 16 subjects, we applied time domain EEG features and an ensemble of linear classifiers to separate these two error conditions on a single-trial basis. We achieved a mean balanced accuracy of 63.23% and, for most of these subjects, achieved statistically significant (p ¡ 0.05) separation of the two error conditions. The ability to classify similar error conditions, such as these, increases the scope of possible applications for EEG error detection, and has the potential to improve brain-machine interaction.

Multi-Tasking and Choice of Training Data Influencing Parietal ERP Expression and Single-Trial Detection-Relevance for Neuroscience and Clinical Applications.

Event-related potentials (ERPs) are often used in brain-computer interfaces (BCIs) for communication or system control for enhancing or regaining control for motor-disabled persons. Especially results from single-trial EEG classification approaches for BCIs support correlations between single-trial ERP detection performance and ERP expression. Hence, BCIs can be considered as a paradigm shift contributing to new methods with strong influence on both neuroscience and clinical applications. Here, we investigate the relevance of the choice of training data and classifier transfer for the interpretability of results from single-trial ERP detection. In our experiments, subjects performed a visual-motor oddball task with motor-task relevant infrequent (targets), motor-task irrelevant infrequent (deviants), and motor-task irrelevant frequent (standards) stimuli. Under dual-task condition, a secondary senso-motor task was performed, compared to the simple-task condition. For evaluation, average ERP analysis and single-trial detection analysis with different numbers of electrodes were performed. Further, classifier transfer was investigated between simple and dual task. Parietal positive ERPs evoked by target stimuli (but not by deviants) were expressed stronger under dual-task condition, which is discussed as an increase of task emphasis and brain processes involved in task coordination and change of task set. Highest classification performance was found for targets irrespective whether all 62, 6 or 2 parietal electrodes were used. Further, higher detection performance of targets compared to standards was achieved under dual-task compared to simple-task condition in case of training on data from 2 parietal electrodes corresponding to results of ERP average analysis. Classifier transfer between tasks improves classification performance in case that training took place on more varying examples (from dual task). In summary, we showed that P300 and overlaying parietal positive ERPs can successfully be detected while subjects are performing additional ongoing motor activity. This supports single-trial detection of ERPs evoked by target events to, e.g., infer a patient's attentional state during therapeutic intervention.

Multiclass support matrix machine for single trial EEG classification

Abstract We propose a novel multiclass classifier for single trial electroencephalogram (EEG) data in matrix form, namely multiclass support matrix machine (MSMM), aiming at improving the classification accuracy of multiclass EEG signals, and hence enhancing the performance of EEG-based brain computer interfaces (BCIs) involving multiple mental activities. In order to construct the MSMM, we propose a novel objective function, which is composed of a multiclass hinge loss term and a combined regularization term. We first formulate the multiclass hinge loss by extending the margin rescaling loss to support matrix-form data. We then devise the regularization term by combining the squared Frobenius norm of tensor-form model parameter and the nuclear norm of matrix-form hyperplanes extracted from the model parameter. While the Frobenius norm prevents over-fitting when training the model, the nuclear norm captures the structural information within the matrix data. We further propose an efficient solver for MSMM based on the alternating direction method of multipliers (ADMM) framework. We conduct extensive experiments on two benchmark EEG datasets. Experimental results show that MSMM achieves much better performance than state-of-the-art classifiers and yields a mean kappa value of 0.880 and 0.648 for dataset IIIa of BCI III and dataset IIa of BCI IV, respectively. To our best knowledge, MSMM is the first classifier that supports multiclass classification for matrix-form EEG data. The proposed MSMM enables easier and more efficient implementation of robust multi-task BCIs, and therefore has potential to promote the wider use of BCI technology.

Classification of single-trial motor imagery EEG by complexity regularization

Brain computer interface based on electroencephalogram is a popular way to enable communication between brain and output devices helping elderly and disabled people and in rehabilitation. In practice, the effectiveness of brain computer interface has a strong relationship with the classification accuracy of single trials. Common spatial pattern is believed to be an effective algorithm for classifying the single-trial brain signal. Since it is based on the characteristics of a broad frequency band which is manually selected and not individual variability, it is sensitive to noise and individual variability. In this paper, the common spatial pattern was extended in order to improve classification accuracies and to mitigate these influences. The channel-specific complexity weights of characteristic on montage were derived and added to improve the effects of the relevant function area and the separability between classes. The proposed method was evaluated using two public datasets, and achieved an average accuracy of 18.4% higher than conventional common spatial pattern, and the performance of the proposed method over conventional common spatial pattern was significant (p < 0.05). It indicates that the proposed method extracts subject-specific characteristics and outperforms the conventional common spatial pattern in single-trial EEG classification.

Classification of Single Trial EEG During Automatic Correction of Finger Movement

Classification of Single Trial EEG During Automatic Correction of Finger Movement

Interpretable deep neural networks for single-trial EEG classification

BackgroundIn cognitive neuroscience the potential of deep neural networks (DNNs) for solving complex classification tasks is yet to be fully exploited. The most limiting factor is that DNNs as notorious ‘black boxes’ do not provide insight into neurophysiological phenomena underlying a decision. Layer-wise relevance propagation (LRP) has been introduced as a novel method to explain individual network decisions. New methodWe propose the application of DNNs with LRP for the first time for EEG data analysis. Through LRP the single-trial DNN decisions are transformed into heatmaps indicating each data point's relevance for the outcome of the decision. ResultsDNN achieves classification accuracies comparable to those of CSP-LDA. In subjects with low performance subject-to-subject transfer of trained DNNs can improve the results. The single-trial LRP heatmaps reveal neurophysiologically plausible patterns, resembling CSP-derived scalp maps. Critically, while CSP patterns represent class-wise aggregated information, LRP heatmaps pinpoint neural patterns to single time points in single trials. Comparison with existing method(s)We compare the classification performance of DNNs to that of linear CSP-LDA on two data sets related to motor-imaginary BCI. ConclusionWe have demonstrated that DNN is a powerful non-linear tool for EEG analysis. With LRP a new quality of high-resolution assessment of neural activity can be reached. LRP is a potential remedy for the lack of interpretability of DNNs that has limited their utility in neuroscientific applications. The extreme specificity of the LRP-derived heatmaps opens up new avenues for investigating neural activity underlying complex perception or decision-related processes.