▶ Addresses the accessibility, usability, and, ultimately, acceptability of Information Society Technologies by anyone, anywhere, at anytime, and through any media and device. ▶ Focuses on theoretical, methodological, and empirical research, of both technological and non-technological nature. ▶ Features papers that report on theories, methods, tools, empirical results, reviews, case studies, and best-practice examples.

Universal access in the information society

Advances in physics

Objective. Signal classification is an important issue in brain computer interface (BCI) systems. Deep learning approaches have been used successfully in many recent studies to learn features and classify different types of data. However, the number of studies that employ these approaches on BCI applications is very limited. In this study we aim to use deep learning methods to improve classification performance of EEG motor imagery signals. Approach. In this study we investigate convolutional neural networks (CNN) and stacked autoencoders (SAE) to classify EEG Motor Imagery signals. A new form of input is introduced to combine time, frequency and location information extracted from EEG signal and it is used in CNN having one 1D convolutional and one max-pooling layers. We also proposed a new deep network by combining CNN and SAE. In this network, the features that are extracted in CNN are classified through the deep network SAE. Main results. The classification performance obtained by the proposed method on BCI competition IV dataset 2b in terms of kappa value is 0.547. Our approach yields 9% improvement over the winner algorithm of the competition. Significance. Our results show that deep learning methods provide better classification performance compared to other state of art approaches. These methods can be applied successfully to BCI systems where the amount of data is large due to daily recording.

https://iopscience.iop.org/article/10.1088/1741-2560/14/1/016003/pdf

A novel deep learning approach for classification of EEG motor imagery signals

The title of this technical report says almost everything: this is indeed \"a short bibliography on AI and the arts\". It is presented in four sections: General Arguments, Proposals, and Approaches (31 references); Artificial Intelligence in Music (124 references); Artificial Intelligence in Literature and the Performing Arts (13 references), and Artificial Intelligence and Visual Art (57 references). About a quarter of these have short abstracts. Creating a bibliography can be a monumental task, and this bibliography should be viewed as a good and useful start, though it is by no means complete. For comparison, consider the 4,585-entry bibliography Computer Applications in Music by Deta Davis (A-REditions). No direct comparison is intended (or possible), but my point is that many more papers are likely to exist. As a rough check, I looked for several pre-1990 AI and Music articles and books (including my own, of course) in the bibliography. Out of five papers from well-known sources, only one was listed. On the other hand, I discovered a number of papers in this report that were unknown to me, so I am grateful to have a new source of references. In their introduction, the authors acknowledge the need for more references and even offer.a cup of coffee in reward for each new one. I will be sending a number of contributions, so the next time anyone is in Vienna, the coffee is on me. I hope the authors will continue to collect abstracts and publish an updated report in the future.

Auditory Scene Analysis: The Perceptual Organization of Sound by Albert Bregman (review)

Brain-Computer Interface (BCI), in essence, aims at controlling different assistive devices through the utilization of brain waves. It is worth noting that the application of BCI is not limited to medical applications, and hence, the research in this field has gained due attention. Moreover, the significant number of related publications over the past two decades further indicates the consistent improvements and breakthroughs that have been made in this particular field. Nonetheless, it is also worth mentioning that with these improvements, new challenges are constantly discovered. This article provides a comprehensive review of the state-of-the-art of a complete BCI system. First, a brief overview of electroencephalogram (EEG)-based BCI systems is given. Secondly, a considerable number of popular BCI applications are reviewed in terms of electrophysiological control signals, feature extraction, classification algorithms, and performance evaluation metrics. Finally, the challenges to the recent BCI systems are discussed, and possible solutions to mitigate the issues are recommended.

/pdf/current-status-challenges-and-possible-solutions-of-eeg-4el4wek5td.pdf

Current Status, Challenges, and Possible Solutions of EEG-Based Brain-Computer Interface: A Comprehensive Review

This paper presents on-line unsupervised schemes for de-noising the received signal containing additive multimodal non-Gaussian noise, using concepts of probability density function estimation and dynamic state estimation. Novel on-line probability density estimation techniques, using various unsupervised kernel based methods are presented. The proposed methods are stable, based on simple but flexible representations and are computationally tractable in real time. Various experiments are included to demonstrate that the proposed filters can efficiently denoise sinusoidal and amplitude modulated sinusoidal signals immersed in unimodal as well as multimodal Gaussian-exponential noise with very low signal-to-noise ratio. The proposed filters significantly outperform the popular unscented Kalman filter and handle non-zero mean non-Gaussian multimodal noise in a more effective way. Most importantly, the proposed methods do not need any prior assumption about the nature of noise or signal.

Design of distribution independent noise filters with online PDF estimation

The cost of Monte Carlo sampling of lattice conﬁgurations is very high in the critical region of lattice ﬁeld theory due to the high correlation between the samples. This paper suggests a Conditional Normalizing Flow (C-NF) model for sampling lattice conﬁgurations in the critical region to solve the problem of critical slowing down. We train the C-NF model using samples generated by Hybrid Monte Carlo (HMC) in non-critical regions with low simulation costs. The trained C-NF model is employed in the critical region to build a Markov chain of lattice samples with negligible autocorrelation. The C-NF model is used for both interpolation and extrapolation to the critical region of lattice theory. Our proposed method is assessed using the 1+1-dimensional scalar φ 4 theory. This approach enables the construction of lattice ensembles for many parameter values in the critical region, which reduces simulation costs by avoiding the critical slowing down.

Conditional Normalizing flow for Monte Carlo sampling in lattice scalar field theory

Physics aims at building mathematical models of the underlying nature for explaining and predicting our observations. Based on the experimental data, mathematical quantities and concepts are formulated, and physical theories are constructed, from which we derive our ontological understanding of the underlying building blocks of nature. However, at times, certain phenomena, unnoticed before, fail to agree to the predictions made by those theories. This forces us to give up the old theories and construct new ones. In this paper, we argue that we can very effectively avoid this problem by constructing physical theories with observations as the basic building blocks, or the primary properties, and the mathematical constructs as the emergent properties. We provide an outline of the mathematical framework of our approach, and use it to analyze various concepts in physics, e.g., Newton's laws of motion, conservation of energy, wave-particle duality, etc., in terms of relationships between the observations made by different detectors. This approach not only provides a new robust way to do physics, but also leads to an ontological understanding of nature that goes beyond many of the present problems and paradoxes. Normal 0 false false false EN-US X-NONE X-NONE /* Style Definitions */
 table.MsoNormalTable
	{mso-style-name:"Table Normal";
	mso-tstyle-rowband-size:0;
	mso-tstyle-colband-size:0;
	mso-style-noshow:yes;
	mso-style-priority:99;
	mso-style-parent:"";
	mso-padding-alt:0cm 5.4pt 0cm 5.4pt;
	mso-para-margin:0cm;
	mso-para-margin-bottom:.0001pt;
	mso-pagination:widow-orphan;
	font-size:10.0pt;
	font-family:"Times New Roman",serif;
	mso-ansi-language:EN-US;
	mso-fareast-language:EN-US;}

Observations: The Building Blocks of the World

Brain-Computer Interfaces (BCI) provide the users to communicate with computers via brain signals. Significant research within the BCI is devoted to ElectroEncephaloGraphy (EEG), which picks, on the scalp, immensely frail electrical currents delineating brain activity. This paper presents a new ambulatory classification method for EEG Event Related Poten-tials (ERP) for a Practical Brain Computer Interface (BCI). To be more specific, this paper focuses on enhancing the performance of the ERP classification using Ear EEG along with scalp EEG during walking at 1.6m/s. We demonstrate the signal quality of Ear EEG for targets and non-targets. Through a novel estimation of Covariance matrices, this work extends the use of Riemannian Geometry (RG). In addition, the utility of Ear EEG has been justified by the 5% improvement in ERP detection performance after a novel fusion of Riemannian Geometry attributes from Ear EEG and scalp EEG. Further, we also proposed a fusion of feature attributes of both scalp and Ear EEG obtained from the fully connected layer of trained EEGNet CNN model with autoencoders passed through XGBoost. This method improved the state of the art by 10%. The proposed methods serve as novel adaptations of RG and CNN methods for mobile EEG in a practical BCI setup. The proposed method was also validated on the track 5 of the International BCI competition and achieved third position in the challenge.

Comparative Performance Analysis of Scalp EEG and Ear EEG based P300 Ambulatory Brain-Computer Interfaces using Riemannian Geometry and Convolutional Neural Networks

/pdf/conditional-generative-models-for-sampling-and-phase-50ldrhs7oa.pdf

Vipul Arora

Papers

Design of distribution independent noise filters with online PDF estimation

Conditional Normalizing flow for Monte Carlo sampling in lattice scalar field theory

Observations: The Building Blocks of the World

Comparative Performance Analysis of Scalp EEG and Ear EEG based P300 Ambulatory Brain-Computer Interfaces using Riemannian Geometry and Convolutional Neural Networks

Conditional generative models for sampling and phase transition indication in spin systems