Romanian Journal of
Human - Computer Interaction
Vol.4, No.2, 2011
Interaction with a Web browser through gestures
Mihaela Coneac, Adrian Iftene
93 - 108 Case Study: Automatic Identification of Romanian Suffixes
Verginica Barbu Mititelu
109 - 130 WikiDetect: Automatic Vandalism Detection On Wikipedia
Dan Cioiu, Traian Eugen Rebedea
131 - 156 Computer Assisted Music Composition
157 - 174 Usability Specific Heuristics for Parallel and Distributed Aplications
Dorian Gorgan, Cristian Rusu, Dănuţ Mihon, Vlad Colceriu, Silvana Roncagliolo, Virginica Rusu
175 - 192
Mihaela Coneac, Adrian Iftene“Al. I. Cuza” University of Iasi, Faculty of Computer Science
16, General Berthelot, 700483, Iasi
E-mail: firstname.lastname@example.org, email@example.com
Abstract. This aim of this article is to present a new way to interact with a personal computer. Thus, a user can use a webcam and hand gestures to give commands when using a common web browser like Internet Explorer. After a training process of the application, where it is learned what means postures palm, two fingers or fist, it uses the AdaBoost algorithm to classify a hand posture received from the user in real time. Combining posture identified with posture trajectory, we obtain the command that gives the user to browser. Implemented operations allow us to perform vertical scroll, zoom in and zoom out, jump between active windows, jump between options and to select an option. The results so far are encouraging and we hope that in future this kind of interaction will be increasingly used.
Keywords: hand gestures, human-computer interaction, the classification algorithm
Verginica Barbu MititeluInstitutul de Cercetări pentru Inteligenţă Artificială, Academia Română – ICIA Bucureşti
Calea 13 Septembrie, nr. 13, 050711, Bucureşti
Abstract. Assuming the perspective of automatically identifying derived words and their bases in the Romanian wordnet, with the aim of enriching it with derivational relations and semantic labels associated to them, in this article we present the results of a case study whose aim was to automatically identify suffixes by means of which new words are created in Romanian. In the beginning of the paper we make a brief overview of derivation in Romanian, also anticipating the challenges of our study. For the automatic identification of the suffixes in words we used generalized suffix trees for representing the lemmas in an electronic Romanian lexicon. We imposed a series of filters, identified via observation, by means of which we improved the results. For the evaluation of the identified suffixes we used gold standard lists of suffixes grouped according to the part of speech of the derived words. The evaluation of results was performed in three stages, by comparing them with the gold standard list of suffixes, with the gold standard list of suffixes and suffixoides, and with the unified gold standard list of suffixes and suffixoides of the parts of speech displaying homonymy in Romanian. We showed how the precision and accuracy of the algorithm change with the threshold imposed on the productivity of suffixes. The present study reveals the necessary knowledge for recognizing the morphological structure of words, the difficulties encountered in this process, and also the importance of this study for linguistic research, for the Artificial Intelligence domain, in tasks such as information retrieval, summarization, question answering and all the other tasks relying on natural language processing.
Keywords: suffix, derivation, stemming, morphological analysis, generalized suffix tree.
Dan Cioiu, Traian Eugen Rebedea
Universitatea Politehnica din Bucureşti – Facultatea de Automatică şi Calculatoare
Splaiul Independenţei, Nr. 313, 060042, Sector 6, Bucureşti
E-mail: firstname.lastname@example.org, email@example.com
Abstract. Article vandalism has always been one of the greatest security issues of Wikipedia, yet few automatic (non-human) solutions for this problem have been developed so far. Large amounts of time are spent by volunteers correcting vandalized edits, instead of using this time to add quality content to Wikipedia articles. The purpose of this paper is to introduce a new vandalism detection system, based on a machine learning technique trained on a corpus of real data, and to test its performance. The application functions in a very realistic environment, as it analyzes expert annotated wikitext, extracted from the encyclopedia’s database, which is used to evaluate different vandalism detection algorithms. The paper presents a critical analysis of the obtained results, comparing them to existing solutions, and suggests different statistical classification methods that bring improvements to the system.
Keywords: Wikipedia, vandalism, spam, classification.
Universitatea Politehnica Bucureşti
Bd. Splaiul Independentei, nr. 313 060032, Bucureşti
Abstract. The belief that computers cannot play a central role in music composition is wrong. Research has been conducted in this field for over 50 years. In this paper, we propose an application which can be of real help to a composer in the music composition process. The chosen music genre is one that is highly formalized, namely strict counterpoint. The rules and constraints of the genre are suitable for a recursive implementation of generating and testing candidates. Using this method, the application composes up to 10.000 lines of valid counterpoint. The results are promising, being similar to those presented by a human composer. The aid provided by computers, if accepted, could transform music composition.
Keywords: music composition, counterpoint, backtracking, music evaluation.
Dorian Gorgan1, Cristian Rusu2, Dănuţ Mihon1, Vlad Colceriu1, Silvana Roncagliolo2, Virginica Rusu21Technical University of Cluj-Napoca
28, Memorandumului Street, 400114, Cluj-Napoca
1Pontificia Universidad Catolica de Valparaiso
Avda. Brasil 2241, Valparaíso, Chile
Abstract: The usability of the applications based on new technologies arises new issues. New evaluation methods or at least classical methods adapted to the new real case requirements have to be defined and developed. One of the most known usability evaluation method is the heuristic one. Many authors have proposed specific set of usability heuritics for particular applications. Nevertheless, new formalisms, methodologies, and documentations have to be developed and adapted to various cases. This paper proposes and experiments a methodology to support the development of new usability heuristics for the parallel and distributed applications. The paper exemplifies the using of the methodology to develop usability heuristics for the grid computing applications.
Keywords: utilisability, usability heuristics, grid computing, distributed applications.