Accepted Papers

  • A Novel Procedure for Virtual Measurements Generation suitable for Training and Testing in the context of Non Intrusive Load Monitoring
    Alaa Saleh, Pirmin Held and Dirk Benyoucef Furtwangen University Furtwangen, Germany, Djaffar Ould Abdeslam Universite de Haute-Alsace Mulhouse,France

    Getting "smarter" Energy by means of advanced electrical and computer engineering tools is the theme of our digital age. This paper presents a new concept for virtual data generation in the context of non-intrusive load monitoring, where the goal is to fill in the gap when aggregate measurements are needed along with individuals ones. We develop a method to generate aggregate measurements starting from single ones. the performance of standard NILM tools and algorithms on both original and "virtual" data is compared using own lab measurements.

    Thomas Schmitz and Jean-Jacques Embrechts, Liege University, Montefiore Institute, Belgium

    Numerous audio systems for musicians are expensive and bulky. Therefore, it could be advantageous to model them and to replace them by computer emulation. In guitar players world, audio systems could have a desirable nonlinear behavior (distortion effects). It is thus difficult to find a simple model to emulate them in real time. Volterra series model and its subclass are usual ways to model nonlinear systems. Unfortunately, these systems are difficult to identify in an analytic way. In this paper we propose to take advantage of the new progress made in neural networks to emulate them in real time. We show that an accurate emulation can be reached with less than 1% of root mean square error between the signal coming from a tube amplifier and the output of the neural network. Moreover, the research has been extended to model the Gain parameter of the amplifier.

  • Authorship Attribution of noisy Arabic text Using Advanced methods
    S. Bourib , and H. Sayoud, USTHB University , Bab El Zouar , Algeria

    In the present research work, we have treated the problem of authorship attribution of Ancient Arabic Philosophers’ text documents. For that purpose, we conducted several authorship attribution experiments applied to different noisy Arabic text . A special dataset, called '' A4P '' (Authorship Attribution for Ancient Arabic Philosophers), has been constructed by extracting texts from the books of 5 Ancient Arabic Philosophers, where the genre and the topic are similar. In our approach two types of features were employed; character N-grams and words and several classifiers are used, namely: SMO based SVM, Multi Layer Perceptron , Linear Regression, Stamatatos distance and Manhattan distance. The obtained results show interesting results required for getting good scores for the authorship attribution, depends on the used features n-grams and the classification technique SMO_SVM , Centroid driver and MLP, Nearest Neighbor Driver, but in the overall the performances of the proposed techniques depends on noise level in a text are quite interesting. The size of these texts takes 1000 words per text. The obtained results show that the minimum text size required for getting good scores for the authorship attribution, depends on the used features and the classification technique, but in the overall the performances of the proposed techniques are quite interesting. Keywords: Authorship attribution; NND ; SMO_SVM ; MLP Artificial Intelligence