Asian Science Citation Index is committed to provide an authoritative, trusted and significant information by the coverage of the most important and influential journals to meet the needs of the global scientific community.  
ASCI Database
308-Lasani Town,
Sargodha Road,
Faisalabad, Pakistan
Fax: +92-41-8815544
Contact Via Web
Suggest a Journal
Articles by Messaoud Ramdani
Total Records ( 7 ) for Messaoud Ramdani
  Djemil Messadeg , Messaoud Ramdani , Mouldi Bedda and Herman Akdag
  In this study, we propose a neural network model for the electrocardiogram (ECG) beat recognition. The description of the ECG signals consists of a multi-domain features which contain a set of meaningful and non redundant parameters. The construction of the system is accomplished by a data-driven learning scheme based on a clustering process to find an initial or coarse neuronal structure and a fine tuning hybrid learning algorithm, including gradient descent nonlinear optimization procedure and a least squares optimization step. The salient features of the system are an effective mechanism for variable learning rates and an adaptive metric norm for the distance. The results of experiments show the good efficiency of the proposed solution.
  Messaoud Ramdani and Noureddine Doghmane
  The supervision of many technical systems is often a challenging task due mainly to various nonlinearities. In this study, a multi-model approach for fault detection and diagnosis is proposed as an effective way since it allows to derive good process models valid over a wide range of operation and subsequently to detect changes of the current process behaviour. The diagnosis task is accomplished by decomposing the complex process into several sub-processes in order to generate a set of structured residuals. The validity of the approach is illustrated on the well known academic three tanks benchmark and different faults can be detected and isolated continuously, over several operating regimes.
  Noureddine Guersi , Messaoud Djeghaba and Messaoud Ramdani
  The PMSM (Permanent Magnet Synchronous Motor) drive systems are often used in electrical drives because of their simple structures, ease of maintenance and efficiency. However, the nonlinear behaviour which arises mainly from motor dynamics and load characteristics and the presence of uncertainties make their control an extremely difficult task. So, the speed control strategy should be adaptive and robust for successful industrial applications. To handle the control issue more effectively, three artificial intelligence control strategies namely, Fuzzy Logic (FL), Artificial Neural Network (ANN) and Neuro-Fuzzy (NF) are proposed since they require only a reduced computation power, while maintaining satisfactory static and dynamic performance and a good insensitivity to perturbations and parameter uncertainties. The traditional back-propagation learning algorithm is used for training the ANN and the NF controllers. The performances of the three control strategies are investigated and compared in simulation. The results show that the intelligent controllers are reliable and highly effective in the speed control of the PMSM.
  Azzeddine Amri , Messaoud Ramdani and Mouldi Bedda
  Monitoring of fermentation processes is of great importance to ensure their safe operation and consistent high quality products. Unfortunately, some of the difficulties such as the lack of on-line sensors for indication of fermentation performance, the presence of significant nonlinear behaviour and difficulties in designing accurate mechanistic models limit our ability to provide adequate monitoring. The amount of time and cost involved in developing detailed fundamental models combined with the commercial pressure to reduce the time-to-market requires different modelling, monitoring and control techniques. The local modelling methodology can be used in the design of soft-sensors. In this study, we propose a Local Model Network (LMN) with improved learning scheme for the bioprocess monitoring. The validity of the approach is illustrated on a gluconic acid fermentation process for the design of a soft-sensor to provide an estimation of the product concentration.
  Salah Chenikher , Messaoud Ramdani and Bedda Mouldi
  In this study, a condition monitoring system for fault diagnosis of ball bearings in rotating machines was developed. Features extraction is based on the relevant information calculated from the vibration signal by wavelet transform. The faults diagnosis procedure is achieved by Hidden Markov Models and uses the wavelet feature as inputs to the HMM. This procedure includes training of the HMM and faults recognition by choosing the model that gives maximum probability of the observation. The designed system was developed to be able to classify four types of pre-established faults in ball bearings and the normal condition. The system was trained and tested by experimental data collected from drive end ball bearing of an induction motor, operating under several shaft speeds and load conditions. The method was applied successfully. It permits the separation of different faults with high recognition rate, almost all fault samples of the database were assigned to the appropriate classes.
  Nadia Bouteraa , Salah Chenikher , Noureddine Doghmane and Messaoud Ramdani
  This study presents a multi-stage system for reliable heart rhythm monitoring and diagnosis. It is comprised of three components including data pre-processing and feature extraction, abnormal arrhythmia detection and diagnosis. In the first stage, three different feature extraction methods are applied together to obtain a composite representation of the ECG waveform. In the second stage, the Multivariate Statistical Process Monitoring (MSPM) approach is used to capture the natural variations of the normal cardiac state and to detect any abnormal arrhythmia. Then a feed-forward neural network is used to classify the abnormal arrhythmia in 5 different classes. The results of experiments show the good performance of the proposed system.
  Narima Zermi , Messaoud Ramdani and Mouldi Bedda
  This study describes a hidden Markov model using a grapheme neural networks approach designed to recognize off-line unconstrained Arabic handwritten words. After pre-processing, a word image is segmented into characters or pseudo-characters called graphemes and represented by a sequence of observations. Each observation consists of a set of global and local features that reflect the geometrical and topological properties of a grapheme accompanied with information concerning its affiliation to one of five predefined groups. Within its group, the classification of a grapheme is done by a neural network trained with fuzzy class memberships rather than crisp class memberships as desired outputs because it results in more useful grapheme recognition modules for handwritten word recognition. The experimental results on a test database are presented to demonstrate the reliability of this study.
Copyright   |   Desclaimer   |    Privacy Policy   |   Browsers   |   Accessibility