Serious games have become a much-discussed trend topic in recent years, as the concept promises higher productivity while increasing user satisfaction. In this paper we present JeuTICE an Arabic serious game project model for mathematics learning. this digital resource was approved by VAREN project and hosted at the portal TICE of Moroccan Education Ministry on open access for students and educators. this resource revealed a several additions targeted mathematics learning for students of the 5th and 6th primary school. The goal is to successfully trans-fer positive properties of digital games, such as motivation and commitment, to a different usage context. Potentially, this goal is achieved by focusing on user ex-perience and integrating game elements into the consideration subject. JeuTICE was evaluated by GENIE program by a range of 60 students from different pub-lic Moroccan primary schools the result obtained are very satisfied to ensure the quality and usability of the serious game.

At present, serious games are experiencing a growing popularity and popularity, with areas of application that extend not only to education, but also to other sec-tors such as the military, health and business sectors, among others. Since video games facilitate the learning of complex processes, their associated benefits have been reoriented principally to the educational, training and information processes. This paper presents of "ImALeG" project, a 3D serious game, whose objective is to develop and auto evaluate competencies of Amazigh language learning in a vir-tual environment. ImALeG is a serious language game designed for all age groups who want to learn Tifinaghe in an interactive way. The game leverages the use of virtual reality developed with Unity 3D game engine to implement immer-sive learning as well as a multi-agent system to ensure game interactivity.

No abstract

<span>A new method for recognizing automatically Arabic handwritten words was presented using convolutional neural network architecture. The proposed method is based on global approaches, which consists of recognizing all the words without segmenting into the characters in order to recognize them separately. Convolutional neural network (CNN) is a particular supervised type of neural network based on multilayer principle; our method needs a big dataset of word images to obtain the best result. To optimize our system, a new database was collected from the benchmarking Arabic handwriting database using the pre-processing such as rotation transformation, which is applied on the images of the database to create new images with different features. The convolutional neural network applied on our database that contains 40320 of Arabic handwritten words (26880 images for training set and 13440 for test set). Thus, different configurations on a public benchmark database were evaluated and compared with previous methods. Consequently, it is demonstrated a recognition rate with a success of 96.76%.</span>

No abstract