Papers by Ricardo Chavarriaga
Lecture Notes in Computer Science, 2010
The hypothesis of multiple memory systems involved in different learning of navigation strategies... more The hypothesis of multiple memory systems involved in different learning of navigation strategies has gained strong arguments through biological experiments. However, it remains difficult for experimentalists to understand how these systems interact. We propose a new computational model of selection between parallel systems involving cueguided and place-based navigation strategies allows analyses of selection switches between both control systems, while providing information that is not directly accessible in experiments with animals. Contrary to existing models of navigation, its module of selection is adaptive and uses a criterion which allows the comparison of strategies having different learning processes. Moreover, the spatial representation used by the place-based strategy is based on a recent hippocampus model. We illustrate the ability of this navigation model to analyze animal behavior in experiments in which the availability of sensory cues, together with the amount of training, influence the competitive or cooperative nature of their interactions.
For animals as well as for humans, the hypothesis of multiple memory systems involved in differen... more For animals as well as for humans, the hypothesis of multiple memory systems involved in different navigation strategies is supported by several biological experiments. However, due to technical limitations, it remains difficult for experimentalists to elucidate how these neural systems interact. We present how a computational model of selection between navigation strategies can be used to analyse phenomena that cannot be directly observed in biological experiments. We reproduce an experiment where the rat's behaviour is assumed to be ruled by two different navigation strategies (a cue-guided and a map-based one). Using a modelling approach, we can explain the experimental results in terms of interactions between these systems, either competing or cooperating at specific moments of the experiment. Modelling such systems can help biological investigations to explain and predict the animal behaviour.
Brain Correlates of Lane Changing Reaction Time in Simulated Driving
2015 IEEE International Conference on Systems, Man, and Cybernetics, 2015
Adaptive Assistance for Brain-Computer Interfaces by Online Prediction of Command Reliability
IEEE Computational Intelligence Magazine, 2016
One of the main problems of both synchronous and asynchronous EEG-based BCIs is the need of an in... more One of the main problems of both synchronous and asynchronous EEG-based BCIs is the need of an initial calibration phase before the system can be used. This phase is necessary due to the high non-stationarity of the EEG, since it changes between sessions and users. The calibration limits the BCI systems to scenarios where the outputs are very controlled, and makes these systems non-friendly and exhausting for the users. Although it has been studied how to reduce calibration time for asynchronous signals, it is still an open issue for eventrelated potentials. Here, we analyze the differences between users for single-trial error-related potentials, and propose the design of classifiers based on inter-subject features to either remove or minimize the calibration time. The results show that it is possible to have a classifier with a high performance from the beginning of the experiment, which is able to adapt itself without the user noticing.
Anticipation increases the efficiency of a daily task by partial advance activation of neural sub... more Anticipation increases the efficiency of a daily task by partial advance activation of neural substrates involved in it. Single trial recognition of this activation can be exploited for a novel anticipation based Brain Computer Interface (BCI). In the current work we compare different methods for the recognition of Electroencephalogram (EEG) correlates of this activation on single trials as a first step towards building such a BCI. To do so, we recorded EEG from 9 subjects performing a classical Contingent Negative Variation (CNV) paradigm (usually reported for studying anticipatory behavior in neurophysiological experiments) with GO and NOGO conditions. We first compare classification accuracies with features such as Least Square fitting Line (LSFL) parameters and Least Square Fitting Polynomial (LSFP) coefficients using a Quadratic Discriminant Analysis (QDA) classifier. We then test the best features with complex classifiers such as Gaussian Mixture Models (GMMs) and Support Vector Machines (SVMs).
Modelling directional firing properties of place cells
According to experimental data, hippocampal place cells are mostly directional when a rat is in r... more According to experimental data, hippocampal place cells are mostly directional when a rat is in radial or +-mazes, whereas most place cells are non-directional in open environments. Some studies have also reported both directional and non-directional cells in the center of plus or radial mazes (1, 2). We hypothesize that place cells will be initially directional (responding to specific local
According to experimental data, hippocampal place cells are mostly directional when a rat is in r... more According to experimental data, hippocampal place cells are mostly directional when a rat is in radial or +-mazes, whereas most place cells are non-directional in open environments. Some studies have also reported both directional and non-directional cells in the center of plus or radial mazes . We hypothesize that place cells will be initially directional (responding to specific local views), and that directionality is reduced during exploration when the rat is not constrained in the direction of its movements (like in open fields or the center of mazes). Even though place fields are maintained in darkness, vision is crucial for the creation of spatial representation in the hippocampus . In this paper we propose a feed-forward model of vision driven place cells which is able to correlate local views for different headings at the same place to produce place cells with reduced directionality when the agent is allowed exploring open environments. A first model is shown in which allothetic information consists in the distance and bearing angle to detected landmarks, then we introduce a model which is able to handle real visual stimuli based in gabor processing.
Decoding fast-paced error-related potentials in monitoring protocols
2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2015
Error-related EEG potentials (ErrP) can be used for brain-machine interfacing (BMI). Decoding of ... more Error-related EEG potentials (ErrP) can be used for brain-machine interfacing (BMI). Decoding of these signals, indicating subject's perception of erroneous system decisions or actions can be used to correct these actions or to improve the overall interfacing system. Multiple studies have shown the feasibility of decoding these potentials in single-trial using different types of experimental protocols and feedback modalities. However, previously reported approaches are limited by the use of long inter-stimulus intervals (ISI > 2 s). In this work we assess if it is possible to overcome this limitation. Our results show that it is possible to decode error-related potentials elicited by stimuli presented with ISIs lower than 1 s without decrease in performance. Furthermore, the increase in the presentation rate did not increase the subject workload. This suggests that the presentation rate for ErrP-based BMI protocols using serial monitoring paradigms can be substantially increased with respect to previous works.
Detecting intention to grasp during reaching movements from EEG
2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2015
Brain-computer interfaces (BCI) have been shown to be a promising tool in rehabilitation and assi... more Brain-computer interfaces (BCI) have been shown to be a promising tool in rehabilitation and assistive scenarios. Within these contexts, brain signals can be decoded and used as commands for a robotic device, allowing to translate user's intentions into motor actions in order to support the user's impaired neuro-muscular system. Recently, it has been suggested that slow cortical potentials (SCPs), negative deflections in the electroencephalographic (EEG) signals peaking around one second before the initiation of movements, might be of interest because they offer an accurate time resolution for the provided feedback. Many state-of-the-art studies exploiting SCPs have focused on decoding intention of movements related to walking and arm reaching, but up to now few studies have focused on decoding the intention to grasp, which is of fundamental importance in upper-limb tasks. In this work, we present a technique that exploits EEG to decode grasping correlates during reaching movements. Results obtained with four subjects show the existence of SCPs prior to the execution of grasping movements and how they can be used to classify, with accuracy rates greater than 70% across all subjects, the intention to grasp. Using a sliding window approach, we have also demonstrated how this intention can be decoded on average around 400 ms before the grasp movements for two out of four subjects, and after the onset of grasp itself for the two other subjects.
Teaching brain-machine interfaces as an alternative paradigm to neuroprosthetics control
Scientific reports, Jan 10, 2015
Brain-machine interfaces (BMI) usually decode movement parameters from cortical activity to contr... more Brain-machine interfaces (BMI) usually decode movement parameters from cortical activity to control neuroprostheses. This requires subjects to learn to modulate their brain activity to convey all necessary information, thus imposing natural limits on the complexity of tasks that can be performed. Here we demonstrate an alternative and complementary BMI paradigm that overcomes that limitation by decoding cognitive brain signals associated with monitoring processes relevant for achieving goals. In our approach the neuroprosthesis executes actions that the subject evaluates as erroneous or correct, and exploits the brain correlates of this assessment to learn suitable motor behaviours. Results show that, after a short user's training period, this teaching BMI paradigm operated three different neuroprostheses and generalized across several targets. Our results further support that these error-related signals reflect a task-independent monitoring mechanism in the brain, making this t...
Moving Brain-Controlled Devices Outside the Lab: Principles and Applications
Trends in Augmentation of Human Performance, 2015
This paper presents a novel concept of semiautonomous navigation where a mobile robot evolves aut... more This paper presents a novel concept of semiautonomous navigation where a mobile robot evolves autonomously under the monitoring of a human user. The user provides corrective commands to the robot whenever he disagrees with the robot's navigational choices. These commands are not related to navigational values like directions or goals, but to the relevance of the robot's actions to the overall task.
Action prediction based on anticipatory brain potentials during simulated driving
Journal of Neural Engineering, 2015
The ability of an automobile to infer the driver&... more The ability of an automobile to infer the driver's upcoming actions directly from neural signals could enrich the interaction of the car with its driver. Intelligent vehicles fitted with an on-board brain-computer interface able to decode the driver's intentions can use this information to improve the driving experience. In this study we investigate the neural signatures of anticipation of specific actions, namely braking and accelerating. We investigated anticipatory slow cortical potentials in electroencephalogram recorded from 18 healthy participants in a driving simulator using a variant of the contingent negative variation (CNV) paradigm with Go and No-go conditions: count-down numbers followed by 'Start'/'Stop' cue. We report decoding performance before the action onset using a quadratic discriminant analysis classifier based on temporal features. (i) Despite the visual and driving related cognitive distractions, we show the presence of anticipatory event related potentials locked to the stimuli onset similar to the widely reported CNV signal (with an average peak value of -8 μV at electrode Cz). (ii) We demonstrate the discrimination between cases requiring to perform an action upon imperative subsequent stimulus (Go condition, e.g. a 'Red' traffic light) versus events that do not require such action (No-go condition; e.g. a 'Yellow' light); with an average single trial classification performance of 0.83 ± 0.13 for braking and 0.79 ± 0.12 for accelerating (area under the curve). (iii) We show that the centro-medial anticipatory potentials are observed as early as 320 ± 200 ms before the action with a detection rate of 0.77 ± 0.12 in offline analysis. We show for the first time the feasibility of predicting the driver's intention through decoding anticipatory related potentials during simulated car driving with high recognition rates.
Tel/Fax: +33 1 44 27 88 09 Improving autonomous navigation in a bioinspired robot Selection of na... more Tel/Fax: +33 1 44 27 88 09 Improving autonomous navigation in a bioinspired robot Selection of navigation strategies, especially between 'taxon' and 'locale' ones, in various environments Locale • Hidden goal • Learning of associations Stimulus -Location -Response ('place-response') • Allocentric reference Sensory inputs: 270° visual field (horizontal greyscale image; allocentric reference)
A hybrid BCI based on the fusion of EEG and EMG activities
Hybrid Brain-Computer Interfaces (BCI) are representing a recent approach to develop practical BC... more Hybrid Brain-Computer Interfaces (BCI) are representing a recent approach to develop practical BCIs. In such a system disabled users are able to use all their remaining functionalities as control possibilities in parallel with the BCI. Sometimes these people have residual activity of their muscles. Therefore, in the presented hybrid BCI framework we want to explore the parallel usage of electroencephalographic (EEG) and electromyographic (EMG) activity, whereby the control abilities of both channels are fused. Results showed that the participants could achieve a good control of their hybrid BCI independently of their level of muscular fatigue. Thereby the multimodal fusion approach of muscular and brain activity yielded better and more stable performance compared to the single conditions. Even in the case of an increasing muscular fatigue a good control (moderate and graceful degradation of the performance compared to the non-fatigued case) and a smooth handover could be achieved. T...
Context and activity recognition in complex scenarios is prone to data loss due to disconnections... more Context and activity recognition in complex scenarios is prone to data loss due to disconnections, sensor failure, transmission problems, etc. This generally implies significant changes in the recognition performance. In the case of classifier fusion faulty sensors can be removed from the recognition chain to overcome this issue. Alternatively, we can try to compensate or impute data to replace the missing signals. In this paper we proposed a probabilistic method for imputation of missing data. The proposed method is based on conditional Gaussian distribution and has been previously applied in other fields, such as speech recognition and bioinformatics, but not in for activity recognition. Our method exploits the correlation among classifier outputs to infer missing values of decision profile from available values in a probabilistic manner. We assess the method performance using two datasets in a car manufacturing and in a daily activities scenario with three different configuration...
The characterization and recognition of electrical signatures of brain activity constitutes a rea... more The characterization and recognition of electrical signatures of brain activity constitutes a real challenge. Applications such as Brain-Computer Interfaces (BCI) are based on the accurate identification of mental processes in order to control external devices. Traditionally, classification of brain activity patterns relies on the assumption that the neurological phenomena that characterize mental states is continuously present in the signal. However, recent evidence shows that some mental processes are better characterized by episodic activity that is not necessarily synchronized with external stimuli. In this paper, we present a method for classification of mental states based on the detection of this episodic activity. Instead of performing classification on all available data, the proposed method identifies informative samples based on the class sample distribution in a projected canonical feature space. Classification results are compared to traditional methods using both artif...
One important source of performance degradation in BCIs is bias towards one of the men-tal classe... more One important source of performance degradation in BCIs is bias towards one of the men-tal classes. Recent literature has focused on the general problem of classification accuracy drop, identifying non-stationarity as the generating factor, thus leading to several classi-fier adaptation approaches suggested as of today. In this work, we explicitly focus on bias elimination, demonstrating that the problem has two separate components, one related to non-stationarity and another one attributed to the nature of the feature distributions and the assumptions made by the classification methods. We propose a cued recalibration protocol including a supervised adaptation method and a novel framework for unbiased classification with a modified, unbiased Linear Discriminant Analysis classifier. Preliminary results show that our protocol can assist the subject to achieve quickly accurate and unbiased control of the BCI.
This paper is aimed to introduce IDIAP Brain Computer In- terface (IBCI) research that successful... more This paper is aimed to introduce IDIAP Brain Computer In- terface (IBCI) research that successfully applied Ambience Intelligence (AmI) principles in designing intelligent brain-machine interactions. We proceed through IBCI applications describing how machines can decode and react to the human mental commands, cognitive and emotive states. We show how eective human-machine interaction for brain computer interfacing (BCI) can be achieved
Uploads
Papers by Ricardo Chavarriaga