John Atkinson

Improving BCI-based emotion recognition by combining EEG feature selection and kernel classifiers

A feature-based emotion recognition model is proposed for EEG-based BCI.The approach combines statistical-based feature selection methods and SVM emotion classifiers.The model is based on Valence/Arousal dimensions for emotion classification.Our combined approach outperformed other recognition methods. Current emotion recognition computational techniques have been successful on associating the emotional changes with the EEG signals, and so they can be identified and classified from EEG signals if appropriate stimuli are applied. However, automatic recognition is usually restricted to a small number of emotions classes mainly due to signals features and noise, EEG constraints and subject-dependent issues. In order to address these issues, in this paper a novel feature-based emotion recognition model is proposed for EEG-based Brain-Computer Interfaces. Unlike other approaches, our method explores a wider set of emotion types and incorporates additional features which are relevant for signal pre-processing and recognition classification tasks, based on a dimensional model of emotions: Valence and Arousal. It aims to improve the accuracy of the emotion classification task by combining mutual information based feature selection methods and kernel classifiers. Experiments using our approach for emotion classification which combines efficient feature selection methods and efficient kernel-based classifiers on standard EEG datasets show the promise of the approach when compared with state-of-the-art computational methods.

Designing a feedback component of an intelligent tutoring system for foreign language

In this paper, we provide a model of corrective feedback generation for an intelligent tutoring system for Spanish as a foreign language. We have studied two kind of strategies: (1) Giving-Answer Strategies (GAS), where the teacher directly gives the desired target form or indicates the location of the error and (2) Prompting-Answer Strategies (PAS), where the teacher pushes the student less directly to notice and repair their own error. Based on different experimental settings and comparisons with face-to-face tutoring mode, we propose the design of a component of effective teaching strategies into ITS for Spanish as a foreign language.

Discovering implicit intention-level knowledge from natural-language texts

In this paper, we propose a new approach to automatic discovery of implicit rhetorical information from texts based on evolutionary computation methods. In order to guide the search for rhetorical connections from natural-language texts, the model uses previously obtained training information which involves semantic and structural criteria. The main features of the model and new designed operators and evaluation functions are discussed, and the different experiments assessing the robustness and accuracy of the approach are described. Experimental results show the promise of evolutionary methods for rhetorical role discovery.

Rhetorics-based multi-document summarization

In this paper, a new multi-document summarization framework which combines rhetorical roles and corpus-based semantic analysis is proposed. The approach is able to capture the semantic and rhetorical relationships between sentences so as to combine them to produce coherent summaries. Experiments were conducted on datasets extracted from web-based news using standard evaluation methods. Results show the promise of our proposed model as compared to state-of-the-art approaches.

Adaptive feedback selection for intelligent tutoring systems

In this work, an adaptive method for feedback strategy selection is proposed in the context of intelligent tutoring systems. This uses a combination of machine learning methods to automatically select the best feedback strategy for students engaging in a foreign language learning context. Experiments show that our adaptive multi-strategy feedback model allows students to achieve correct answers by reducing their errors. Results also show the promise of the method compared with traditional methods of feedback generation. The approach is not only capable of dynamically adapting a feedback strategy, but also guiding the tutorial conversation so that students correct answers can be obtained with a minimum feedback. Our approach also suggested that combining SVM and CRF models are promising to get effective feedback correction from student tutoring, showing that our multi-strategy selection approach outperformed the traditional meta-linguistic rules based feedback strategies. Experiments also showed a good correlation between the best strategy generated by our model and the decision taken by a human tutor.

Intelligent search agents using web-driven natural-language explanatory dialogs

A computational linguistics approach for Web-based cooperative dialogs focuses on the users requests by automatically generating language. driven interactions that take into account the context, user feedback, and the initial searchs results.

A multi-strategy approach to biological named entity recognition

Recognizing and disambiguating bio-entities (genes, proteins, cells, etc.) names are very challenging tasks as some biologica databases can be outdated, names may not be normalized, abbreviations are used, syntactic and word order is modified, etc. Thus, the same bio-entity might be written into different ways making searching tasks a key obstacle as many candidate relevant literature containing those entities might not be found. As consequence, the same protein mention but using different names should be looked for or the same discovered protein name is being used to name a new protein using completely different features hence named-entity recognition methods are required. In this paper, we developed a bio-entity recognition model which combines different classification methods and incorporates simple pre-processing tasks for bio-entities (genes and proteins) recognition is presented. Linguistic pre-processing and feature representation for training and testing is observed to positively affect the overall performance of the method, showing promising results. Unlike some state-of-the-art methods, the approach does not require additional knowledge bases or specific-purpose tasks for post processing which make it more appealing. Experiments showing the promise of the model compared to other state-of-the-art methods are discussed.

Discovering Novel Causal Patterns From Biomedical Natural-Language Texts Using Bayesian Nets

Most of the biomedicine text mining approaches do not deal with specific cause-effect patterns that may explain the discoveries. In order to fill this gap, this paper proposes an effective new model for text mining from biomedicine literature that helps to discover cause-effect hypotheses related to diseases, drugs, etc. The supervised approach combines Bayesian inference methods with natural-language processing techniques in order to generate simple and interesting patterns. The results of applying the model to biomedicine text databases and its comparison with other state-of-the-art methods are also discussed.

Using Genetic Algorithms to Model Road Networks

A model based on genetic algorithms views the allocation of people and private vehicles as an optimization problem, anticipating traffic congestion effects and adjusting the infrastructure accordingly.

On-the-fly generation of multi-robot team formation strategies based on game conditions

This paper describes a new model to automatically generating dynamic formation strategies for robotic soccer applications based on game conditions, regarded to as favorable or unfavorable for a robotic team. Decisions are distributedly computed by the players of a multi-agent team. A game policy is defined and applied by a human coach who establishes the attitude of the team for defending or attacking. A simple neural net model is applied using current and previous game experience to classify the games parameters so that the new game conditions can be determined so that a robotic team can modify its strategy on-the-fly. Experiments and results of the proposed model for a robotic soccer team show the promise of the approach.