This paper proposes a methodology for the robust classification of neurophysiological data into four emotional states collected during passive viewing of emotional evocative pictures selected from the International Affective Picture System. The proposed classification model is formed according to the current neuroscience trends, since it adopts the independency of two emotional dimensions, namely arousal and valence, as dictated by the bidirectional emotion theory, whereas it is gender-specific. A two-step classification procedure is proposed for the discrimination of emotional states between EEG signals evoked by pleasant and unpleasant stimuli, which also vary in their arousal/intensity levels. The first classification level involves the arousal discrimination. The valence discrimination is then performed. The Mahalanobis (MD) distance-based classifier and support vector machines (SVMs) were used for the discrimination of emotions. The achieved overall classification rates were 79.5% and 81.3% for the MD and SVM, respectively, significantly higher than in previous studies. The robust classification of objective emotional measures is the first step toward numerous applications within the sphere of human-computer interaction.

Recent neuroscience findings demonstrate the fundamental role of emotion in the maintenance of physical and mental health. In the present study, a novel architecture is proposed for the robust discrimination of emotional physiological signals evoked upon viewing pictures selected from the International Affective Picture System (IAPS). Biosignals are multichannel recordings from both the central and the autonomic nervous systems. Following the bidirectional emotion theory model, IAPS pictures are rated along two dimensions, namely, their valence and arousal. Following this model, biosignals in this paper are initially differentiated according to their valence dimension by means of a data mining approach, which is the C4.5 decision tree algorithm. Then, the valence and the gender information serve as an input to a Mahalanobis distance classifier, which dissects the data into high and low arousing. Results are described in Extensible Markup Language (XML) format, thereby accounting for platform independency, easy interconnectivity, and information exchange. The average recognition (success) rate was 77.68% for the discrimination of four emotional states, differing both in their arousal and valence dimension. It is, therefore, envisaged that the proposed approach holds promise for the efficient discrimination of negative and positive emotions, and it is hereby discussed how future developments may be steered to serve for affective healthcare applications, such as the monitoring of the elderly or chronically ill people.

This paper addresses the problem of low impact of smart city applications observed in the fields of energy and transport, which constitute high-priority domains for the development of smart cities. However, these are not the only fields where the impact of smart cities has been limited. The paper provides an explanation for the low impact of various individual applications of smart cities and discusses ways of improving their effectiveness. We argue that the impact of applications depends primarily on their ontology, and secondarily on smart technology and programming features. Consequently, we start by creating an overall ontology for the smart city, defining the building blocks of this ontology with respect to the most cited definitions of smart cities, and structuring this ontology with the Protégé 5.0 editor, defining entities, class hierarchy, object properties, and data type properties. We then analyze how the ontologies of a sample of smart city applications fit into the overall Smart City Ontology, the consistency between digital spaces, knowledge processes, city domains targeted by the applications, and the types of innovation that determine their impact. In conclusion, we underline the relationships between innovation and ontology, and discuss how we can improve the effectiveness of smart city applications, combining expert and user-driven ontology design with the integration and or-chestration of applications over platforms and larger city entities such as neighborhoods, districts, clusters, and sectors of city activities.

BackgroundIt has been shown that exergames have multiple benefits for physical, mental and cognitive health. Only recently, however, researchers have started considering them as health monitoring tools, through collection and analysis of game metrics data. In light of this and initiatives like the Quantified Self, there is an emerging need to open the data produced by health games and their associated metrics in order for them to be evaluated by the research community in an attempt to quantify their potential health, cognitive and physiological benefits.MethodsWe have developed an ontology that describes exergames using the Web Ontology Language (OWL); it is available at http://purl.org/net/exergame/ns#. After an investigation of key components of exergames, relevant ontologies were incorporated, while necessary classes and properties were defined to model these components. A JavaScript framework was also developed in order to apply the ontology to online exergames. Finally, a SPARQL Endpoint is provided to enable open data access to potential clients through the web.ResultsExergame components include details for players, game sessions, as well as, data produced during these game-playing sessions. The description of the game includes elements such as goals, game controllers and presentation hardware used; what is more, concepts from already existing ontologies are reused/repurposed. Game sessions include information related to the player, the date and venue where the game was played, as well as, the results/scores that were produced/achieved. These games are subsequently played by 14 users in multiple game sessions and the results derived from these sessions are published in a triplestore as open data.ConclusionsWe model concepts related to exergames by providing a standardized structure for reference and comparison. This is the first work that publishes data from actual exergame sessions on the web, facilitating the integration and analysis of the data, while allowing open data access through the web in an effort to enable the concept of Open Trials for Active and Healthy Ageing.

It is possible to have reliable predictions of the severity of OSAS using linear and nonlinear indices from only two respiratory signals during sleep instead of performing full polysomnography. The proposed algorithm could be used for screening patients suspected to suffer from OSAS.

In recent years data journalism has drawn significant attention not only in academic literature but also in the media sector. Data Journalism is a new form of journalism that has gradually appeared over the last decade, driven by the availability of data in digital form. Currently a significant amount of data journalism projects are being produced all over the world. These projects vary considerably in terms of structure and visualization characteristics. As a result of the above it would be interesting to propose a taxonomy of data journalism projects that can help future data journalists to choose the appropriate type of projects that will be suitable for their needs. This classification could be based on certain characteristics of the data journalism projects. The proposed taxonomy will take into account various parameters that play an important role in data journalist projects and especially in the type and the role of the visualization.

In the past, journalists were responsible for reporting the news. But today news stories disseminate as the incidents unfold, from multiple sources. Thus, gathering, filtering and visualizing events has a growing value. Huge amounts of data are available, but exploiting them is not an easy task. Data journalism can be defined as a journalism speciality in which numerical data are used in the production and distribution of information. This article investigates the necessary skills that journalists must have in order to cope with data journalism. More precisely, it defines data journalism, and discusses journalists’ Information and Communication Technology (ICT) skills, as well as the necessary skills for supporting data journalism. Special attention is given to Web 3.0 and open data that can play an important role in data journalism. A survey conducted among professional journalists in Greece concerning data journalism is also presented and discussed.

Rising interest in the field of Intelligent Transportation Systems combined with the increased availability of collected data allows the study of different methods for prevention of traffic congestion in cities. A common need in all of these methods is the use of traffic predictions for supporting planning and operation of the traffic lights and traffic management schemes. This paper focuses on comparing the forecasting effectiveness of three machine learning models, namely Random Forests, Support Vector Regression, and Multilayer Perceptron—in addition to Multiple Linear Regression—using probe data collected from the road network of Thessaloniki, Greece. The comparison was conducted with multiple tests clustered in three types of scenarios. The first scenario tests the algorithms on specific randomly selected dates on different randomly selected roads. The second scenario tests the algorithms on randomly selected roads over eight consecutive 15 min intervals; the third scenario tests the algorithms on random roads for the duration of a whole day. The experimental results show that while the Support Vector Regression model performs best at stable conditions with minor variations, the Multilayer Perceptron model adapts better to circumstances with greater variations, in addition to having the most near-zero errors.