Benaissa Amami

Intelligent tutoring systems founded on the multi-agent incremental dynamic case based reasoning

In E-learning, there is still the problem of knowing how to ensure an individualized and continuous learners follow-up during learning process, indeed among the numerous tools proposed, very few systems concentrate on a real time learners follow-up. Our work in this field develops the design and implementation of a Multi-Agent Systems Based on Dynamic Case Based Reasoning which can initiate learning and provide an individualized follow-up of learner. When interacting with the platform, every learner leaves his/her traces in the machine. These traces are stored in a basis under the form of scenarios which enrich collective past experience. The system monitors, compares and analyses these traces to keep a constant intelligent watch and therefore detect difficulties hindering progress and/or avoid possible dropping out. The system can support any learning subject. The success of a case-based reasoning system depends critically on the performance of the retrieval step used and, more specifically, on similarity measure used to retrieve scenarios that are similar to the course of the learner (traces in progress). We propose a complementary similarity measure, named Inverse Longest Common Sub-Sequence (ILCSS). To help and guide the learner, the system is equipped with combined virtual and human tutors.

MultiAgent case-based reasoning and individualized follow-up of learner in remote learning

In distance learning/training in a Computing Environment for Human Learning (CEHL), among the numerous methods proposed, very few concentrate on a real time follow-up of learner/trainee. Our work develops the design and implementation of a MultiAgent System based on case based reasoning which can initiate learning and provide an individualized monitoring of learner/trainee. When interacting with the platform, every learner/trainee leaves his/her traces in the machine. They are stored in a basis under the form of scenarios thus enriching collective past experience. The system monitors, compares and analyses these traces to keep a constant intelligent watch and therefore detect difficulties hindering progress and/or avoid possible dropping out. To help and guide the learner the system is equipped with combined virtual and human tutors.

Modelisation and implementation of our system incremental dynamic case based reasoning founded In the MAS under JADE plate-form

The aim of this paper is to present our approach in the field of Intelligent Tutoring System (ITS), in fact there is still the problem of knowing how to ensure an individualized and continuous learners follow-up during learning process, indeed among the numerous methods proposed, very few systems concentrate on a real time learners follow-up. Our contribution in these areas is to design and develop an adaptive Multi-Agent Systems Based on Dynamic Case Based Reasoning which can initiate learning and provide an individualized follow-up of learner. This approach involves 1) the use of Dynamic Case Based Reasoning to retrieve the past experiences that are similar to the learners traces, and 2) the use of Multi-Agents System. Our Work focuses on the use of the learner traces. When interacting with the platform, every learner leaves his/her traces in the machine. The traces are stored in database, this operation enriches collective past experiences. The traces left by the learner during the learning session evolve dynamically over time; the case-based reasoning must take into account this evolution in an incremental way. In other words, we do not consider each evolution of the traces as a new target, so the use of classical cycle Case Based reasoning in this case is insufficient and inadequate. In order to solve this problem, we propose a dynamic retrieving method based on a complementary similarity measure, named Inverse Longest Common Sub-Sequence (ILCSS). Through monitoring, comparing and analyzing these traces, the system keeps a constant intelligent watch on the platform, and therefore it detects the difficulties hindering progress, and it avoids possible dropping out. The system can support any learning subject.

A map matching algorithm based on a particle filter

Map matching is the process of finding a match for each GPS point in a vehicles trajectory to roads on a digital map. Extensive research has been conducted during the last years yielding many algorithms based on different approaches. One of the challenges that face those algorithms is the interruption of GPS signals that occurs specially in dense urban environments. In these cases on-board sensors like odometers and accelerometers can be used temporarily for positioning, however due to the poor accuracy of these methods, the quality of map matching decreases significantly. In this paper, we propose a method that improves the quality of map matching when GPS signals are not available. This method is based on a particle filter using heading and velocity measurement. We evaluate this method through its integration with an existing topological map matching algorithm. We compare the performances when this algorithm is used alone and when associated with the particle filter.

Our System IDCBR-MAS: from the Modelisation by AUML to the Implementation under JADE Platform

This paper presents our work in the field of Intelligent Tutoring System (ITS), in fact there is still the problem of knowing how to ensure an individualized and continuous learners follow-up during learning process, indeed among the numerous methods proposed, very few systems concentrate on a real time learners follow-up. Our work in this field develops the design and implementation of a Multi-Agents System Based on Dynamic Case Based Reasoning which can initiate learning and provide an individualized follow-up of learner. This approach involves 1) the use of Dynamic Case Based Reasoning to retrieve the past experiences that are similar to the learners traces (traces in progress), and 2) the use of Multi-Agents System. Our Work focuses on the use of the learner traces. When interacting with the platform, every learner leaves his/her traces on the machine. The traces are stored in database, this operation enriches collective past experiences. The traces left by the learner during the learning session evolve dynamically over time; the case-based reasoning must take into account this evolution in an incremental way. In other words, we do not consider each evolution of the traces as a new target, so the use of classical cycle Case Based reasoning in this case is insufficient and inadequate. In order to solve this problem, we propose a dynamic retrieving method based on a complementary similarity measure, named Inverse Longest Common Sub-Sequence (ILCSS). Through monitoring, comparing and analyzing these traces, the system keeps a constant intelligent watch on the platform, and therefore it detects the difficulties hindering progress, and it avoids possible dropping out. The system can support any learning subject. To help and guide the learner, the system is equipped with combined virtual and human tutors.

Computer Vision Control System for Food Industry

Defects in production can appear as a result of material and human errors. A food product with a defect may be the cause of direct and indirect losses caused by product recalls, logistic problems, destruction of defective products, reputation issues, possible penalties, etc. The purpose of this work is to minimize the human intervention and substitute it to the maximum extent with an automatic inspection system based on the artificial vision technology that will carry out the inspection task. To do so, the main functions of the system had to be elaborated in a specification. Examples of the inspection functions are barcode reading, label verification, content level checking, etc. Each function is performed and tested independently. The tests carried out made it possible to record the conditions necessary for the execution of each inspection, which is an indispensable factor in achieving the appropriate physical design. These functions are grouped in a single application with three interfaces (login, inspection and configuration). It allows the user to inspect the products according to a configuration that he can define. This work was developed based on National Instrument platform, the software code was made with LabVIEW software, which resources and libraries are adequate for such a work.

Indoor localization by particle map matching

This article presents the implementation of an indoor localization approach that combines map matching and a circular particle filter defined in a Bayesian framework. The technique relies only on velocity and heading observations coupled with a map of the road network. No prior knowledge of the initial position is given. A circular distribution is used to match the vehicles heading with the roads direction. This allows to detect turns and provide a more accurate position estimate. The algorithm is assessed with a synthetic dataset in a real context.

Influence of failure modes and effects analysis on the average probability of failure on demand for a safety instremented system

The international standard IEC 61508 presents the basis activities related to the life cycle of Electrical, Electronic and Programmable Electronic Systems (E/E/PE) that are used to perform safety functions. This international standard provides in part 6 the techniques used to evaluate the safety related systems by the calculation of average probability of failure on demand. This calculation depends on the safety related system architecture : 1oo1, 1oo2, 1oo2D, 2oo3 or 1oo3 where MooN (M out of N) and MooND (M out of N with diagnostic), means M channels among N channels must properly work for executing the safety function for safety instrumented system (SIS) [1] and [2]. In this paper, we propose to compare different architectures by the calculation of the average probability of failure on demand and show the influence of the diagnostic coverage DC, the proof test interval T1, the common cause failure factors β and ßD and the efficiency K, which is associated to the 1oo2D architecture, on the calculation of the PFDavg.

Dynamic Case-Based Reasoning Based on the Multi-Agent Systems: Individualized Follow-Up of Learners in Distance Learning

In a Computing Environment for Human Learning (CEHL), there is still the problem of knowing how to ensure an individualized and continuous learner’s follow-up during learning process, indeed among the numerous methods proposed, very few systems concentrate on a real time learner’s followup. Our work in this field develops the design and implementation of a Multi-Agent Systems Based on Dynamic Case Based Reasoning which can initiate learning and provide an individualized follow-up of learner. When interacting with the platform, every learner leaves his/her traces in the machine. These traces are stored in a basis under the form of scenarios which enrich collective past experience. The system monitors, compares and analyses these traces to keep a constant intelligent watch and therefore detect difficulties hindering progress and avoid possible dropping out. The system can support any learning subject. To help and guide the learner, the system is equipped with combined virtual and human tutors.

Static approach for switching between different operating modes

This work deals with operating mode management applied to discrete event systems (DES). Studied systems present several operating modes thus causing complexity of state space explosion. Therefore, we propose, firstly, a multi-model approach; each model describes a system in a given operating mode. In order to ensures the alternating between these operating modes; we propose, secondly, a static approach whose information depends on states of systems. We assume that only one attempted operating mode is activated at a time whilst other modes must be inactivated. The commutation problem can be defined as search the compatible states when the behavior of the physical system switches from operating mode to another. For this purpose, we propose an optimal algorithm to find compatibles states when a switching occurs.