Publications

Solar energy is expected to provide a major contribution to the future global energy supply, while helping the transition toward a carbon-free economy. Because of its variable character, its efficient use will necessitate trustworthy forecast information of its availability in a variety of spatial and time scales, depending on application. This study proposes a new forecasting approach for irradiance time series that combines mutual information measures and an Extreme Learning Machine (ELM). The method is referred to as Minimum Redundancy – Maximum Relevance (MRMR). To assess the proposed approach, its performance is evaluated against four scenarios: long window (latest 50 variables), short window (latest 5 variables), standard Principal Components Analysis (PCA) and clear-sky model. All these scenarios are applied to three typical forecasting horizons (15-min ahead, 1-h ahead and 24-h ahead). Based on measured irradiance data from 20 sites representing a variety of climates, the test results reveal that the selection of a good set of relevant variables positively impacts the forecasting performance of global solar radiation. The present findings show that the proposed approach is able to improve the accuracy of solar irradiance forecasting compared to other proposed scenarios.

Multilayer Perceptron (MLP) and Radial Basis Function (RBF) were proposed in this paper as two models of non-linear ANN based equalization techniques in order to optimize processing performance, tracking, and minimize error of the channel effects and the ascending noise with 16 QAM Modulation, this work will be referenced with one of the most used linear adaptive equalization; Recursive least squares (RLS), as an evaluation. The two models will be compared in terms of efficiency and robustness facing noisy channel.

In this paper, an approach of trajectory tracking is proposed. The approach is based on two controls. Firstly, a quasi sliding mode control is proposed of the angular velocity in aim to converge the angle error to zero in short time with asymptotic stability. Secondly, a global sliding mode control for linear velocity is proposed, in order to bring the position error to zero and ensure the asymptotic stability by using the Lyapunov theory. Finally, the proposed control shows the performance of the algorithm, and the simulation results show good convergence for circular, sinusoidal and specific trajectories.

Since our research to study mobility, we noted that the best way to represent the mobility of sensor nodes is to follow a mobility model. Numerous models have been proposed in the literature, they are commonly used as a data source in all kinds of studies, including motion in several networks. To this end, we propose to exploit this mobility, which results in the proposal of a new approach based on a mobility model to ensure routing in networks of mobile and wireless sensors. Inspired from a powerful mobility model (i.e. Random Waypoint), our approach offers many advantages for routing in a dynamic environment based on the collaboration of sensor nodes, and thus to conclude for new and innovative ideas.

In this paper, a new capacitive pressure sensor (CPS) is investigated and modeled by means of neural approach. The sensing principle in our pressure sensor is based on the determination of the change in the capacity induced by the applied pressure. A ring oscillator is used to convert the capacity variation of the pressure sensor to an output frequency. A multilayer perceptron neural network is used to predict the applied pressure which causes a variation of the capacity including the temperature effects. This model is implemented as an electronic device into PSPICE simulator library, where the device should reproduce faithfully the pressure sensor behavior. Moreover, a new inverse model called smart sensor has been developed, in order to remove the nonlinearity behavior of sensor response. The obtained results make the proposed smart sensor as a potential alternative for high performances pressure sensing applications.

  Background: Collaborative learning is an important pedagogical strategy which gained a huge interest in critical domains such as the medical field. However, to ensure the quality of this learning method, it is necessary to focus intention not only on the cognitive aspect but also on the social activities that represent an essential issue during collaborative learning sessions. Our objective in this study is to highlight the collaborative aspect in the group learning method of clinical reasoning. Methods: In this work, we have focused on cognitive studies that are interested in the clinical reasoning processes, while proposing a model dedicated to the design of collaborative clinical reasoning learning environment in synchronous mode. This model is primarily interested in social activities that have a strong influence on the collaborative learning effectiveness, and they are generally treated implicitly by basing on the improvisation and spontaneity of the learners group. Results: The research idea was embodied through a collaborative learning clinical reasoning environment based on Web 2.0 technologies. We chose this technology to benefit from its ease of use and from its technical performances that can significantly contribute to the development of the cognitive and social aspects in the collaborative learning environment. Conclusion: Our first contact with medical students showed us that they are appreciating this learning method. Indeed, to evaluate objectively our choices reliability, we plan to accomplish this research with a quantitative study based on real experiences with clinicians and medical students. The suggested study will allow us to collect the necessary lessons to work in depth on the relevant questions concerning the cognitive and social activities in the collaborative clinical reasoning learning.  

Background: Collaborative learning is an important pedagogical strategy which gained a huge interest in critical domains such as the medical field. However, to ensure the quality of this learning method, it is necessary to focus intention not only on the cognitive aspect but also on the social activities that represent an essential issue during collaborative learning sessions. Our objective in this study is to highlight the collaborative aspect in the group learning method of clinical reasoning. Methods: In this work, we have focused on cognitive studies that are interested in the clinical reasoning processes, while proposing a model dedicated to the design of collaborative clinical reasoning learning environment in synchronous mode. This model is primarily interested in social activities that have a strong influence on the collaborative learning effectiveness, and they are generally treated implicitly by basing on the improvisation and spontaneity of the learners group. Results: The research idea was embodied through a collaborative learning clinical reasoning environment based on Web 2.0 technologies. We chose this technology to benefit from its ease of use and from its technical performances that can significantly contribute to the development of the cognitive and social aspects in the collaborative learning environment. Conclusion: Our first contact with medical students showed us that they are appreciating this learning method. Indeed, to evaluate objectively our choices reliability, we plan to accomplish this research with a quantitative study based on real experiences with clinicians and medical students. The suggested study will allow us to collect the necessary lessons to work in depth on the relevant questions concerning the cognitive and social activities in the collaborative clinical reasoning learning.