Rafael A. Calvo

Affect Detection: An Interdisciplinary Review of Models, Methods, and Their Applications

This survey describes recent progress in the field of Affective Computing (AC), with a focus on affect detection. Although many AC researchers have traditionally attempted to remain agnostic to the different emotion theories proposed by psychologists, the affective technologies being developed are rife with theoretical assumptions that impact their effectiveness. Hence, an informed and integrated examination of emotion theories from multiple areas will need to become part of computing practice if truly effective real-world systems are to be achieved. This survey discusses theoretical perspectives that view emotions as expressions, embodiments, outcomes of cognitive appraisal, social constructs, products of neural circuitry, and psychological interpretations of basic feelings. It provides meta-analyses on existing reviews of affect detection systems that focus on traditional affect detection modalities like physiology, face, and voice, and also reviews emerging research on more novel channels such as text, body language, and complex multimodal systems. This survey explicitly explores the multidisciplinary foundation that underlies all AC applications by describing how AC researchers have incorporated psychological theories of emotion and how these theories affect research questions, methods, results, and their interpretations. In this way, models and methods can be compared, and emerging insights from various disciplines can be more expertly integrated.

Fast Dimensionality Reduction and Simple PCA

A fast and simple algorithm for approximately calculating the principal components PCs of a dataset and so reducing its dimensionality is described. This Simple Principal Components Analysis SPCA method was used for dimensionality reduction of two high-dimensional image databases, one of handwritten digits and one of handwritten Japanese characters. It was tested and compared with other techniques. On both databases SPCA shows a fast convergence rate compared with other methods and robustness to the reordering of the samples.

A new EEG recording system for passive dry electrodes

OBJECTIVE We present a new, low power EEG recording system with an ultra-high input impedance that enables the use of long-lasting, passive dry electrodes. It incorporates Bluetooth wireless connectivity and is designed to be suitable for long-term monitoring during daily activities. METHODS The new EEG system is compared to a standard and clinically available reference EEG system using wet electrodes in three separate sets of experiments. In the first two experiments, each dry electrode was surrounded by four standard wet electrodes and the alpha and mu-rhythms were recorded. In the third experiment, serial monopolar (referred to the left ear) recordings of flash visual evoked potential were performed using the new EEG system and a reference system. RESULTS These experiments showed that the signal recorded using the new EEG system is almost identical to that recorded with standard clinical EEG equipment; our measurements showed that the correlation coefficient between the dry electrode recordings and the average of the four standard electrodes surrounding each dry electrode is greater than 0.85. CONCLUSION We conclude that the new EEG system performs similarly to reference EEG systems, while providing the advantages of portability, ease of application and minimal scalp preparation. SIGNIFICANCE The proposed system using passive dry electrodes suitable for single use while performing as good as standard EEG equipment provides ease of application and minimal scalp preparation.

Collaborative Writing Support Tools on the Cloud

Academic writing, individual or collaborative, is an essential skill for todays graduates. Unfortunately, managing writing activities and providing feedback to students is very labor intensive and academics often opt out of including such learning experiences in their teaching. We describe the architecture for a new collaborative writing support environment used to embed such collaborative learning activities in engineering courses. iWrite provides tools for managing collaborative and individual writing assignments in large cohorts. It outsources the writing tools and the storage of student content to third party cloud-computing vendors (i.e., Google). We further describe how using machine learning and NLP techniques, the architecture provides automated feedback, automatic question generation, and process analysis features.

A mobile EEG system with dry electrodes

A new EEG recording device demonstrating an ultra-high input impedance is presented. Dry electrodes made of conductive rubber were employed for this study with careful shielding of the electrodes and cables. The device has a small form factor, so it is wearable, and has continuous Bluetooth connectivity. Tests were performed to assess features of the proposed device and to compare it with standard clinical devices. Simultaneous EEG recordings were measured from adjacent sites on the scalp using the new EEG device with dry electrodes and a reference EEG device with standard electrodes. The gain and bandwidth settings for the two devices were set similarly. Traditional closing eyes alpha-wave replacement and mu-rhythm were compared in both the time and frequency domains. Results from eight subjects show a high correlation coefficient (0.83 on average) between recordings of contiguous dry and standard electrodes. We conclude that the performance of the new device is comparable with standard EEG recording equipment, but offers a shorter set-up time, the possibility of long-term recording, and a wireless connection - all of which are advantages valuable in the field of brain computer interfaces and neurofeedback.

Learning Through Discussions in Blended Environments

This paper reports research into the student experience of learning through discussions in a blended environment. Third year engineering students studying e‐commerce engaged in both face‐to‐face discussions and online asynchronous discussions as key aspects of their learning experience. Adopting a quantitative methodology, questionnaires were completed by students at the end of their learning experience. The results suggest qualitatively different experiences of learning through discussions. The results show that students who have a deep understanding of how the discussions are related to their learning outcomes tend to approach the discussions in more meaningful ways. In the face‐to‐face context, their approach emphasizes learning through the experience of others and, in the online environment, their approach emphasizes reflecting on the problems discussed from a variety of perspectives. Formation par discussions dans des environnements intégrés. Une étude a été menée sur les expériences d’étudiants avec la formation par discussions dans un environnement intégré. Des étudiants d’ingénierie de troisième année ont engagé des discussions personnelles et des discussions en ligne différés lors de leurs études de commerce en ligne représentant les aspects clés pour leur expérience de formation. En adoptant une méthode quantitative, des questionnaires ont été remplis par des étudiants à la fin de leur expérience de formation. Les résultats suggèrent des expériences de formation qualitativement différentes par discussions. Les résultats montrent que les étudiants qui ont une grande connaissance sur le fait que les discussions influent sur leur issue de formation, tendent à aborder les discussions de manière plus significative. Dans un contexte personnel, cette évaluation met l’accent sur la formation par l’expérience d’autres, et dans l’environnement en ligne, elle met l’accent sur la réflexion des problèmes discutés avec une variété de perspectives. Lernen durch Diskussionen in integrierten Lernumfeldern. Diese Studie berichtet über die Erfahrungen von Studenten beim Lernen durch Diskussionen innerhalb eines integrierten Lernumfelds. Studenten des Ingenieurwesens im dritten Studienjahr befassten sich während ihres e‐Commerce Studiums sowohl mit persönlichen Diskussionen als auch mit zeitlich versetzt geführten Online‐Diskussionen, die Schlüsselaspekte für ihre Lernerfahrungen darstellten. Mit einer quantitativen Methode wurden am Ende der Lernerfahrung durch die Studenten Fragebögen ausgefüllt. Die Ergebnisse zeigen qualitativ unterschiedliche Lernerfahrungen durch Diskussionen auf. Sie belegen, dass Studenten, die gute Kenntnisse darüber haben, wie Diskussionen ihren Lernerfolg beeinflussen, bedeutend mehr dazu tendieren, an Diskussionen teilzunehmen. Dieser Ansatz beweist, dass in persönlichen Diskussionen der Lernerfolg durch die Erfahrung anderer erreicht wird, wohingegen bei einer Problemdiskussion innerhalb eines Online‐Umfelds der Schwerpunkt auf die Vielfältigkeit der Betrachtungsweisen aus verschiedenen Blickwinkeln gelegt wird. Dieser Ansatz hebt im persönlichen Kontext das Lernen durch die Erfahrung anderer und in der Online‐Umgebung die Betrachtung über die aus vielen Blickwinkeln diskutierten Probleme hervor.

A platform for secure monitoring and sharing of generic health data in the Cloud

The growing need for the remote caring of patients at home combined with the ever-increasing popularity of mobile devices due to their ubiquitous nature has resulted in many apps being developed to enable mobile telecare. The Cloud, in combination with mobile technologies has enabled doctors to conveniently monitor and assess a patients health while the patient is at the comfort of their own home. This demands sharing of health information between healthcare teams such as doctors and nurses in order to provide better and safer care of patients. However, the sharing of health information introduces privacy and security issues which may conflict with HIPAA standards. In this paper, we attempt to address the issues of privacy and security in the domain of mobile telecare and Cloud computing. We first demonstrate a telecare application that will allow doctors to remotely monitor patients via the Cloud. We then use this system as a basis to showcase our model that will allow patients to share their health information with other doctors, nurses or medical professional in a secure and confidential manner. The key features of our model include the ability to handle large data sizes and efficient user revocation.

Discontinuities in university student experiences of learning through discussions

This article reports on research into the student experience of learning through discussions in a third-year undergraduate engineering subject. Information engineering students studying e-commerce were required to engage in face-to-face and online discussions as a key aspect of their learning experience. This study investigates the quality of the experience of learning through those discussions using quantitative methodologies from Student Learning Research. Analyses of student ratings on the closed-ended questionnaires identify qualitatively different approaches to learning through discussions, both in face-to-face contexts and online. Relationships are found among the variation in the quality of these approaches and how students perceive issues such as workload, what they thought they were learning through discussions and performance. Implications arising from these results identify different suggestions for teaching students to discuss successfully in different contexts.

Neural network prediction of solar activity

The neural network technique is used to analyze the time series of solar activity, as measured through the relative Wolf number. Firstly, the embedding dimension of the time-series characteristic attractor is obtained. Secondly, after describing the design and training of the net, the performance of the present approach in forecasting yearly mean sunspot numbers is favorably compared to that of conventional statistical methods. Finally, predictions for the remaining part of the 22th and the whole 23th cycle are presented.

EMOTIONS IN TEXT: DIMENSIONAL AND CATEGORICAL MODELS

Text often expresses the writers emotional state or evokes emotions in the reader. The nature of emotional phenomena like reading and writing can be interpreted in different ways and represented with different computational models. Affective computing (AC) researchers often use a categorical model in which text data are associated with emotional labels. We introduce a new way of using normative databases as a way of processing text with a dimensional model and compare it with different categorical approaches. The approach is evaluated using four data sets of texts reflecting different emotional phenomena. An emotional thesaurus and a bag‐of‐words model are used to generate vectors for each pseudo‐document, then for the categorical models three dimensionality reduction techniques are evaluated: Latent Semantic Analysis (LSA), Probabilistic Latent Semantic Analysis (PLSA), and Non‐negative Matrix Factorization (NMF). For the dimensional model a normative database is used to produce three‐dimensional vectors (valence, arousal, dominance) for each pseudo‐document. This three‐dimensional model can be used to generate psychologically driven visualizations. Both models can be used for affect detection based on distances amongst categories and pseudo‐documents. Experiments show that the categorical model using NMF and the dimensional model tend to perform best.