Co-Planar Stereotaxic Atlas of the Human Brain—3-Dimensional Proportional System: An Approach to Cerebral Imaging, J. Talairach, P. Tournoux. Georg Thieme Verlag, New York (1988), 122 pp., 130 figs. DM 268

An overview of the self-organizing map algorithm, on which the papers in this issue are based, is presented in this article.

The Self-Organizing Map

In this paper we review classification algorithms used to design brain–computer interface (BCI) systems based on electroencephalography (EEG). We briefly present the commonly employed algorithms and describe their critical properties. Based on the literature, we compare them in terms of performance and provide guidelines to choose the suitable classification algorithm(s) for a specific BCI.

/pdf/a-review-of-classification-algorithms-for-eeg-based-brain-p1h22hb1wr.pdf

A review of classification algorithms for EEG-based brain–computer interfaces

The brain's electrical signals enable people without muscle control to physically interact with the world.

Brain-computer interfaces for communication and control

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.

Deep learning with convolutional neural networks for EEG decoding and visualization.

This paper addresses the problem of human motion encoding for real-time animation in interactive environments. Classically, a motion is stored as a sequence of body postures encoded as a set of joint rotations (quaternions, Euler-like angles or rotation matrices). As a consequence, Cartesian constraints must be solved using inverse kinematics and/or optimization. Those processes involve computation costs that do not allow real-time animation of several characters in interactive environments. To solve such a problem with a minimum computation time, we designed a motion representation independent from the morphology and containing the constraints intrinsically linked to the motion such as feet contacts with the ground. With such a description, a unique motion can be shared by several characters with different morphologies and in different environments. We also adapted a Cyclic Coordinate Descent algorithm that takes advantages of this representation in order to rapidly deal with complex tunable spacetime constraints. For example, this method enables to interactively control at least eight characters with different morphologies that interact each other during a fight training. Hence, each character has to deal with geometric constraints that can change at every time, depending on the opponents’ morphology and gestures.

/pdf/morphology-independent-representation-of-motions-for-4dony0zuza.pdf

Morphology-independent representation of motions for interactive human-like animation

Virtual reality offers new tools for human motion understanding. Several applications have been widely used in teleoperation, military training, driving and flying simulators, and so forth. We propose to test if virtual reality is a valid training tool for the game of handball. We focused on the duel between a handball goalkeeper and a thrower. To this end, we defined a pilot experiment divided into two steps: an experiment with real subjects and another one with virtual throwers. The throwers' motions were captured in order to animate their avatar in a reality center. In this paper, we focused on the evaluation of presence when a goalkeeper is confronting these avatars. To this end, we compared the goalkeeper's gestures in the real and in the virtual experiment to determine if virtual reality engendered the same movements for the same throw. Our results show that gestures did not differ between the real and virtual environment. As a consequence, we can say that the virtual environment offered enough realism to initiate natural gestures. Moreover, as in real games, we observed the goalkeeper's anticipation to allow us to use virtual reality in future work as a way to understand the goalkeeper and thrower interactions. The main originality of this work was to measure presence in a sporting application with new evaluation methods based on motion capture.

Real handball goalkeeper vs. virtual handball thrower

Using virtual reality to analyze links between handball thrower kinematics and goalkeeper's reactions

The Walking-In-Place interaction technique was introduced to navigate infinitely in 3D virtual worlds by walking in place in the real world. The technique has been initially developed for users standing in immersive setups and was built upon sophisticated visual displays and tracking equipments.In this paper, we propose to revisit the whole pipeline of the Walking-In-Place technique to match a larger set of configurations and apply it notably to the context of desktop Virtual Reality. With our novel "Shake-Your-Head" technique, the user is left with the possibility to sit down, and to use small screens and standard input devices such as a basic webcam for tracking. The locomotion simulation can compute various motions such as turning, jumping and crawling, using as sole input the head movements of the user. We also introduce the use of additional visual feedback based on camera motions to enhance the walking sensations.An experiment was conducted to compare our technique with classical input devices used for navigating in desktop VR. Interestingly, the results showed that our technique could even allow faster navigations when sitting, after a short learning. Our technique was also perceived as more fun and increasing presence, and was generally more appreciated for VR navigation.

/pdf/shake-your-head-revisiting-walking-in-place-for-desktop-4k603fofs9.pdf

Bruno Arnaldi

Papers

A review of classification algorithms for EEG-based brain–computer interfaces

Morphology-independent representation of motions for interactive human-like animation

Real handball goalkeeper vs. virtual handball thrower

Using virtual reality to analyze links between handball thrower kinematics and goalkeeper's reactions

Shake-your-head: revisiting walking-in-place for desktop virtual reality