Accurate modeling of the nonlinear relationship between the open circuit voltage (OCV) and the state of charge (SOC) is required for adaptive SOC estimation during the lithium-ion (Li-ion) battery operation. Online SOC estimation should meet several constraints, such as the computational cost, the number of parameters, as well as the accuracy of the model. In this paper, these challenges are considered by proposing an improved simplified and accurate OCV model of a nickel manganese cobalt (NMC) Li-ion battery, based on an empirical analytical characterization approach. In fact, composed of double exponential and simple quadratic functions containing only five parameters, the proposed model accurately follows the experimental curve with a minor fitting error of 1 mV. The model is also valid at a wide temperature range and takes into account the voltage hysteresis of the OCV. Using this model in SOC estimation by the extended Kalman filter (EKF) contributes to minimizing the execution time and to reducing the SOC estimation error to only 3% compared to other existing models where the estimation error is about 5%. Experiments are also performed to prove that the proposed OCV model incorporated in the EKF estimator exhibits good reliability and precision under various loading profiles and temperatures.

A novel approach for the Arabic handwriting recognition is presented. The use of a Planar Hidden Markov Model (PHMM) has permitted to split the Arabic script into five homogeneous horizontal regions. Each region was described by a 1D-HMM. This modeling is based on different levels of segmentation: horizontal, natural and vertical. Both holistic and analytical approaches have been tested for the description of the median band of the Arabic writing. We show finally that a hybrid approach conducted to the improvement of the whole system performances.

No abstract

In this paper, we tackle the problem of domain adaptation to perform object-classification and detection tasks in video surveillance starting by a generic trained detector. Precisely, we put forward a new transductive transfer learning framework based on a sequential Monte Carlo filter to specialize a generic classifier towards a specific scene. The proposed algorithm approximates iteratively the target distribution as a set of samples (selected from both source and target domains) which feed the learning step of a specialized classifier. The output classifier is applied to pedestrian detection into a traffic scene. We have demonstrated by many experiments, on the CUHK Square Dataset and the MIT Traffic Dataset, that the performance of the specialized classifier outperforms the generic classifier and that the suggested algorithm presents encouraging results.

No abstract

No abstract

No abstract

This study presents a novel approach for Arabic video text recognition based on recurrent neural networks. In fact, embedded texts in videos represent a rich source of information for indexing and automatically annotating multimedia documents. However, video text recognition is a non-trivial task due to many challenges like the variability of text patterns and the complexity of backgrounds. In the case of Arabic, the presence of diacritic marks, the cursive nature of the script and the non-uniform intra/inter word distances, may introduce many additional challenges. The proposed system presents a segmentation-free method that relies specifically on a multi-dimensional long short-term memory coupled with a connectionist temporal classification layer. It is shown that using an efficient pre-processing step and a compact representation of Arabic character models brings robust performance and yields a low-error rate than other recently published methods. The authors' system is trained and evaluated using the public AcTiV-R dataset under different evaluation protocols. The obtained results are very interesting. They also outperform current state-of-the-art approaches on the public dataset ALIF in terms of recognition rates at both character and line levels.