Romanian Journal of
Human - Computer InteractionVol.11, No.2, 2018
ISSN 1843-4460
Contents
GeoAR - An Augmented Reality Application to Learn Geography
Mirela Chitaniuc, Adrian Iftene
93 - 108 Creating enhanced interfaces for cyber-physical-social systems: the remote drone control experiment
Alexandru Matei, Alexandru Butean
109 - 126 Virtual museums - technologies, opportunities and perspectives
Mihaela Anton, Gabriela Nicolae, Alin Moldoveanu, Oana Balan
127 - 144 Improving multi-choice question answering by identifying essential terms in questions
George-Sebastian Pirtoaca, Stefan Ruseti, Traian Rebedea
145 - 162 A Knowledge-Based Model for Human Motion Tracking and Gesture Recognition in the Context of Natural Interaction with Kinect Devices
Sabin C. Buraga, Elena Creanga
163 - 183
Abstracts
GeoAR - An Augmented Reality Application to Learn Geography
Mirela Chitaniuc, Adrian Iftene
"Alexandru Ioan Cuza" University of Iași, Faculty of Computer Science
General Berthelot 16, Iași
E-mail: mirela2895@gmail.com, adiftene@info.uaic.ro
Abstract: Over the last years, augmented reality was used in various domains, from medical, industrial design, modeling and production, robot teleoperation, military, entertainment, leisure activities to translation, facial recognition, assistance while driving, interior and exterior design, virtual friends, Internet of Things and eLearning. In eLearning, the combination between classical and augmented content (the later coming with 3D models, images, sounds, animations, Internet browsing, etc.) can help the teacher to better explain the content of the courses. GeoAR application was created with the purpose to learn more things about the geography of Europe (countries, capitals, flags and neighbors) in a different and more attractive way. We know that new technologies draw children’s attention, and that’s why we used the Augmented Reality feature in developing our application. Using GeoAR, children can play a game and learn at the same time. Thus, learning geography becomes more interesting and exceeds the traditional way.
Keywords: Augmented reality (AR), eLearning, Unity, Geography.
Cite this paper as:
Chitaniuc, M., Iftene, A. GeoAR - An Augmented Reality Application to Learn Geography. Revista Romana de Interactiune Om-Calculator 11(2), 93-108, 2018.
Creating enhanced interfaces for cyber-physical-social systems: the remote drone control experiment
Alexandru Matei1, Alexandru Butean2
1University “Lucian Blaga” of Sibiu; Connected Intelligence Research Center;
10, Victoriei Bd., Sibiu, 550024, România
E-mail: alex.matei@ulbsibiu.ro
2University “Lucian Blaga” of Sibiu; Department of Computer Science and Electrical Engineering;
4, Emil Cioran, Sibiu, 550024, România
E-mail: alexandru.butean@ulbsibiu.ro
Abstract: In the area of cyber-physical-social systems there is always a huge demand for integration and adaptation; most often, these two tasks go together. There are very few practical cases when every module fits perfectly into a system. The concept of puzzle pieces can be applied only on a high-level logic, but in the experimental development stages things tend to be more complex. The purpose of our work is to be able to integrate various modern interfaces into existing systems in order to ease the interaction process or experiment unexplored areas. Our current contribution presents the case of changing the classic remote control of a drone towards using enhanced interfaces, like using a leap-motion controller and / or a mobile processing device. The main purpose of this work is to understand and observe the proper ways to deal with communication and protocol delays, human adaptation to enhanced controls and identify the integration challenges. Once all this can be achieved at a decent level we plan to extrapolate and conduct more work for trying to apply similar logic for controlling other devices like: collaborative robots, industrial transportation machines and other complex cyber-physical-social devices.
Keywords: cyber-physical-social systems; Leap Motion; human-computer interaction; drone control.
Cite this paper as:
Matei, A., Butean, A. Creating enhanced interfaces for cyber-physical-social systems: the remote drone control experiment. Revista Romana de Interactiune Om-Calculator 11(2), 109-126, 2018.
Virtual museums - technologies, opportunities and perspectives
Mihaela Anton, Gabriela Nicolae, Alin Moldoveanu, Oana Balan
University POLITEHNICA of Bucharest
Splaiul Independenței, Nr. 313,Sector 6, Bucharest, Romania
E-mail: mihaela_1402@yahoo.com, nicolaegabriela16@gmail.com, {alin.moldoveanu, oana.balan}@cs.pub.ro
Abstract: Virtual Reality is a very popular concept all over the world. There are many areas whose activity involves this technology: games, cinemas, museums, medicine, aviation. Although Virtual Reality was more used in games and medicine, in the last period many museums started to adopt it. The museums represent a cultural heritage and also a trust worthy information source in people's lives. Therefore, it is important to attract the audience, especially the young. A very good method to make it possible is to build virtual museums. Our article describes how the virtualization of museums impacts human life, what are the opportunities offered by this change, the steps to build a virtual tour and what are the expectations regarding this subject in the future. In this paper, we also demonstrate how 3D technologies can be used to preserve and display the cultural heritage and as proof we have a dedicated chapter with the top five most amazing virtual museums. .
Keywords: virtual museum, 3D artifacts, adaptive reality.
Cite this paper as:
Anton, M., Nicolae, G., Moldoveanu, A., Balan, O. Virtual museums - technologies, opportunities and perspectives. Revista Romana de Interactiune Om-Calculator 11(2), 127-144, 2018.
Improving multi-choice question answering by identifying essential terms in questions
George-Sebastian Pirtoaca, Stefan Ruseti, Traian Rebedea
University Politehnica of Bucharest
Splaiul Independentei nr. 313, sector 6, 060042, Bucuresti
E-mail: george.pirtoaca@stud.acs.upb.ro, {stefan.ruseti, traian.rebedea}@cs.pub.ro
Abstract: This paper describes a method for identifying the most relevant or essential terms in a question: the words that define the meaning of the question and whose removal makes it impossible to be answered correctly even by human agents. We use an artificial neural network architecture built upon semantic and syntactic features extracted from the question. The neural network prediction represents the degree to which the given term is essential to the question. The model has been trained and validated on a dataset consisting of 2233 questions and about human 18000 labeled terms with essentialness information. It achieves an F1 score of 0.80 which is similar to other state-of-the-art approaches but requires fewer features (15 compared to 120 features used by similar works) and is much easier to train. We further show how using only essential term information can improve the accuracy of a multi-choice question answering system, based on standard information retrieval (IR) techniques, by up to 4%.
Keywords: Natural Language Processing, Question Answering, Information Retrieval; Essential Terms, Dependency Parsing, Neural Networks.
Cite this paper as:
Pirtoaca, G.S., Ruseti, S., Rebedea, T. Improving multi-choice question answering by identifying essential terms in questions. Revista Romana de Interactiune Om-Calculator 11(2), 145-162, 2018.
A Knowledge-Based Model for Human Motion Tracking and Gesture Recognition in the Context of Natural Interaction with Kinect Devices
Sabin C. Buraga, Elena Creangă
Faculty of Computer Science, Alexandru Ioan Cuza University of Iasi, Romania
Berthelot, 16, 700483, Iasi
E-mail: busaco@info.uaic.ro, elena.creanga.mail@gmail.com
Abstract: Human-computer interaction (HCI) was revolutionized by the emergence of new technologies, be they proof of concept or fully functional, which created a more immersive, integrated and interactive experience, interactive systems being now able to understand user's activities and respond accordingly. Our study presents an original knowledge-based model to be used to semantically describe – in terms of the OWL and RDF standards – human gestures and poses tracked by a motion sensor-based device. To prove the feasibility of the proposed conceptualization, two use cases were designed: one for manipulating 3D shapes on a board and one for usability testing by using different Kinect-based applications.
Keywords: natural user interaction, knowledge modeling, human gesture, Kinect, experiments.
Cite this paper as:
Buraga, S.C., Creanga, E. A Knowledge-Based Model for Human Motion Tracking and Gesture Recognition in the Context of Natural Interaction with Kinect Devices. Revista Romana de Interactiune Om-Calculator 11(2), 163-183, 2018.