Lamsade

OBJECTIVE: Most current electroencephalography (EEG)-based brain-computer interfaces (BCIs) are based on machine learning algorithms. There is a large diversity of classifier types that are used in this field, as described in our 2007 review paper. Now, approximately ten years after this review publication, many new algorithms have been developed and tested to classify EEG signals in BCIs. The time is therefore ripe for an updated review of EEG classification algorithms for BCIs. APPROACH: We surveyed the BCI and machine learning literature from 2007 to 2017 to identify the new classification approaches that have been investigated to design BCIs. We synthesize these studies in order to present such algorithms, to report how they were used for BCIs, what were the outcomes, and to identify their pros and cons. MAIN RESULTS: We found that the recently designed classification algorithms for EEG-based BCIs can be divided into four main categories: adaptive classifiers, matrix and tensor classifiers, transfer learning and deep learning, plus a few other miscellaneous classifiers. Among these, adaptive classifiers were demonstrated to be generally superior to static ones, even with unsupervised adaptation. Transfer learning can also prove useful although the benefits of transfer learning remain unpredictable. Riemannian geometry-based methods have reached state-of-the-art performances on multiple BCI problems and deserve to be explored more thoroughly, along with tensor-based methods. Shrinkage linear discriminant analysis and random forests also appear particularly useful for small training samples settings. On the other hand, deep learning methods have not yet shown convincing improvement over state-of-the-art BCI methods. SIGNIFICANCE: This paper provides a comprehensive overview of the modern classification algorithms used in EEG-based BCIs, presents the principles of these methods and guidelines on when and how to use them. It also identifies a number of challenges to further advance EEG classification in BCI.

International audience

The rapidly-growing field of computational social choice, at the intersection of computer science and economics, deals with the computational aspects of collective decision making. This handbook, written by thirty-six prominent members of the computational social choice community, covers the field comprehensively. Sections devoted to each of the field's major themes offer detailed introductions. Topics include computational voting theory (such as the computational complexity of winner determination and manipulation in elections), fair allocation (such as algorithms for dividing divisible and indivisible goods), coalition formation (such as matching and hedonic games), and many more.

Although promising from numerous applications, current brain-computer interfaces (BCIs) still suffer from a number of limitations. In particular, they are sensitive to noise, outliers and the non-stationarity of electroencephalographic (EEG) signals, they require long calibration times and are not reliable. Thus, new approaches and tools, notably at the EEG signal processing and classification level, are necessary to address these limitations. Riemannian approaches, spearheaded by the use of covariance matrices, are such a very promising tool slowly adopted by a growing number of researchers. This article, after a quick introduction to Riemannian geometry and a presentation of the BCI-relevant manifolds, reviews how these approaches have been used for EEG-based BCI, in particular for feature representation and learning, classifier design and calibration time reduction. Finally, relevant challenges and promising research directions for EEG signal classification in BCIs are identified, such as feature tracking on manifold or multi-task learning.

Papers presented at the Twenty-Seventh International Joint Conference on Artificial Intelligence(IJCAI) held in Stockholm, Sweden, from July 13-19, 2018.International Joint Conferences on Artificial Intelligence is a non-profit corporation founded in California, in 1969 for scientific and educational purposes, including dissemination of information on Artificial Intelligence at conferences in which cutting-edge scientific results are presented and through dissemination of materials presented at these meetings in form of Proceedings, books, video recordings, and other educational materials. IJCAI consists of two divisions: the Conference Division and the AI Journal Division. IJCAI conferences present premier international gatherings of AI researchers and practitioners and they were held biennially in odd-numbered years since 1969.

In this paper, we introduce the Choquet integral as a general tool for dealing with multiple criteria decision making. After a theoretical exposition giving the fundamental basis of the methodology, practical problems are addressed, in particular the problem of determining the fuzzy measure. We give an example of application, with two different approaches, together with their comparison. 1

The role of contextual information in intelligent assistant systems is controversial. In this paper, we start from our experience of Intelligent Assistant System developers to clarify some notions about context and to study the question of context sharing. Moreover, we consider two important aspects of man-machine cooperation, namely explanation generation and incremental knowledge acquisition. Making context explicit in cooperative systems is the key factor for any implementation of these two concepts. Starting from our experience in the development of knowledge-based systems, especially of an interactive system for incident management in subway control, we explain our views about context for the development of intelligent assistant systems.

We present a new structural (or syntatic) approach for estimating the satisfiability threshold of random 3-SAT formulae. We show its efficiency in obtaining a jump from the previous upper bounds, lowering them to 4.506. The method combines well with other techniques, and also applies to other problems, such as the 3-colourability of random graphs.

International audience

Angiogenesis is the formation of new capillaries from pre-existing blood vessels and participates in proper vasculature development. In pathological conditions such as cancer, abnormal angiogenesis takes place. Angiogenesis is primarily carried out by endothelial cells, the innermost layer of blood vessels. The vascular endothelial growth factor-A (VEGF-A) and its receptor-2 (VEGFR-2) trigger most of the mechanisms activating and regulating angiogenesis, and have been the targets for the development of drugs. However, most experimental assays assessing angiogenesis rely on animal models. We report an in vitro model using a microvessel-on-a-chip. It mimics an effective endothelial sprouting angiogenesis event triggered from an initial microvessel using a single angiogenic factor, VEGF-A. The angiogenic sprouting in this model is depends on the Notch signaling, as observed in vivo. This model enables the study of anti-angiogenic drugs which target a specific factor/receptor pathway, as demonstrated by the use of the clinically approved sorafenib and sunitinib for targeting the VEGF-A/VEGFR-2 pathway. Furthermore, this model allows testing simultaneously angiogenesis and permeability. It demonstrates that sorafenib impairs the endothelial barrier function, while sunitinib does not. Such in vitro human model provides a significant complimentary approach to animal models for the development of effective therapies.

This chapter reviews some results from the literature in which power indices related to the Shapley value are developed. First, a class of power indices for so-called effectivity functions is axiomatically characterized, based on [1]. An effectivity function describes for each coalition of players each set of alternatives such that the coalition can make sure that the final alternative is in that set. As a special case, the Owen-Shapley spatial power index as proposed in [2] is obtained. Second, following [3], a class of power indices for situations in which subsets of players control other players is described. Examples of such situations include financial structures in which firms and other shareholders exercise control through shares in each other. Formally, such a situation is described by a collection of simple games: for each player there is a simple game of which the winning coalitions control that player. Third, following [4], a class of power indices is considered where relations between the players are determined via a directed graph.

A multiagent system may be thought of as an artificial society of autonomous software agents and we can apply concepts borrowed from welfare economics and social choice theory to assess the social welfare of such an agent society. In this paper, we study an abstract negotiation framework where agents can agree on multilateral deals to exchange bundles of indivisible resources. We then analyse how these deals affect social welfare for different instances of the basic framework and different interpretations of the concept of social welfare itself. In particular, we show how certain classes of deals are both sufficient and necessary to guarantee that a socially optimal allocation of resources will be reached eventually.

International audience

International audience

International audience

Among the novelties introduced by 5G networks, the formalization of the `network slice' as a resource allocation unit is an important one. In legacy networks, resources such as link bandwidth, spectrum, computing capacity are allocated independently of each other. In 5G environments, a network slice is meant to directly serve end-to-end services, or verticals: behind a network slice demand, a tenant expresses the need to access a precise service type, under a fully qualified set of computing and network requirements. The resource allocation decision encompasses, therefore, a combination of different resources. In this paper, we address the problem of fairly sharing multiple resources between slices, in the critical situation in which the network does not have enough resources to fully satisfy slice demands. We model the problem as a multi-resource allocation problem, proposing a versatile optimization framework based on the Ordered Weighted Average (OWA) operator, that takes into account different fairness approaches. We show how, adapting the OWA utility function, our framework can generalize classical single-resource allocation methods, existing multi-resource allocation solutions at the state of the art, and implement novel multi-resource allocation solutions. We compare analytically and by extensive simulations the different methods in terms of fairness and system efficiency.

1. 1 Motivations Deciding is a very complex and difficult task. Some people even argue that our ability to make decisions in complex situations is the main feature that distinguishes us from animals (it is also common to say that laughing is the main difference). Nevertheless, when the task is too complex or the interests at stake are too important, it quite often happens that we do not know or we are not sure what to decide and, in many instances, we resort to a decision support technique: an informal one-we toss a coin, we ask an oracle, we visit an astrologer, we consult an expert, we think-or a formal one. Although informal decision support techniques can be of interest, in this book, we will focus on formal ones. Among the latter, we find some well-known decision support techniques: cost-benefit analysis, multiple criteria decision analysis, decision trees, . . . But there are many other ones, sometimes not presented as decision support techniques, that help making decisions. Let us cite but a few examples. • When the director of a school must decide whether a given student will pass or fail, he usually asks each teacher to assess the merits of the student by means of a grade. The director then sums the grades and compares the result to a threshold. • When a bank must decide whether a given client will obtain a credit or not, a technique, called credit scoring, is often used.

We study elections in which voters may submit partial ballots consisting of truncated lists: each voter ranks some of her top candidates (and possibly some of her bottom candidates) and is indifferent among the remaining ones. Holding elections with such votes requires adapting classical voting rules (which expect complete rankings as input) and these adaptations create various opportunities for candidates who want to increase their chances of winning. We provide complexity results regarding planning various kinds of campaigns in such settings, and we study the complexity of the possible winner problem for the case of truncated votes.

Context is the challenge for the coming years in Artificial Intelligence. In the companion paper [8], we present the main results of discussions at two workshops and at the first conference focusing on the notion of context. In this paper, we present a view of how context is considered in knowledge acquisition, machine learning, communication, and databases and ontologies. We describe the way in which context is modeled and represented in the logic formalism and a rulebased formalism. We present briefly after some of the other approaches, and sum up the different points that may be of interest for modeling effectively context.

This paper is devoted to the proportional representation (PR) problem when the preferences are clustered single-peaked. PR is a “multi-winner” election problem, that we study in Chamberlin and Courant's scheme [6]. We define clustered single-peakedness as a form of single-peakedness with respect to clusters of candidates, i.e. subsets of candidates that are consecutive (in arbitrary order) in the preferences of all voters. We show that the PR problem becomes polynomial when the size of the largest cluster of candidates (width) is bounded. Furthermore, we establish the polynomiality of determining the single-peaked width of a preference profile (minimum width for a partition of candidates into clusters compatible with clustered single-peakedness) when the preferences are narcissistic (i.e., every candidate is the most preferred one for some voter).