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 Mouldi Bedda
Total Records ( 16 ) for Mouldi Bedda
  Mohamed Fezari , Mounir Bousbia-Salah and Mouldi Bedda
  This study describes the development of a heart rate control system based on a microcontroller. It offers the advantage of portability over tape-based recording systems. The study explains how a single-chip microcontroller can be used to analyse heart beat rate signals in real-time. In addition, it allows doctors to get the heart beat rate file of the patient by e-mail every twenty four hours. It can also be used to control patients or athletic person over a long period. The system reads, stores and analyses the heart beat rate signals repetitively in real-time. The hardware and software design are oriented towards a single-chip microcontoller-based system, hence minimizing the size. The important feature of this study is the use of the zero crossing algorithm to compute heart rate. It then processes on real-time the information to determine some heart diseases.
  Mohamed Fezari , Badji Mokhtar , Mouldi Bedda and Mounir Bousbia-Salah
  Many people with disabilities do not have the dexterity necessary to control a joystick on an electrical wheelchair. The aim of this study is to implement an interesting application using small vocabulary word recognition system. The methodology adopted is based on grouping a microcontroller with a speech recognition development kit for isolated word from a dependent speaker. The resulting design is used to control a wheelchair for a handicapped person based on the vocal command. It therefore involves the recognition of isolated words from a limited vocabulary. In order to gain in time design, tests have shown that it would be better to choose a speech recognition kit and to adapt it to the application. The input of the system is a set of eight words used to control the movement of an Automatic Vehicle Guided (AVG); The output is a corresponding command. The system is developed in order to be installed on the wheelchair. Therefore it should be easy to carry, no bulky, with low power consumption, and easy in operation.
  Brahim Boulebtateche , Mohamed Fezari and Mouldi Bedda
  In this study , a voice guidance system for autonomous robots is designed based on microcontroller. The proposed system consists of a microcontroller and a voice recognition processor that can recognize a limited number of voice patterns. The commands of autonomous robots are classified and organized such that one voice recognition processor can distinguish robot commands under each class. Thus, the proposed system can distinguish more voice commands than one voice recognition processor can. A voice command system for three autonomous robots is implemented with a microcontroller from Microchip PIC16F876, a voice recognition processor RSC364 from Sensory and a set of Infra-red emitters- receivers. A proposal is also outlined for integrating the voice command system into a reinforcement learning scheme in order to enhance the performance of learning task by autonomous robots. This work and design have taken 10 months, starting on january 2004.
  Mohamed Fezari , Mounir Bousbia-salah and Mouldi Bedda
  In this study we propose a simple approach to small vocabulary word recognition applied to control a wheelchair. The methodology adopted is based on hybrid techniques used in speech recognition which are zero crossing and extremes with dynamic time warping followed by a decision system based on independent methods test results. To test the approach on a real application, a PC interface was designed to control the movement of a wheelchair for a handicapped person by simple vocal messages. Tests showed that the decision system outputs follow a logic in line with the words uttered. The experiment aimed to find any problems for running tests in outdoor environments. Also, it was checked whether the basic commands used would be enough to control the vehicle. Some experiments are tested by actually running a powered-toy vehicle.
  Faouzi Bouchareb , Mouldi Bedda and Salim Ouchetati
  This study describes new preprocessing methods for hand-written Arabic word using Hough Transform and geometrical processing applied on the skeleton chain list, using characteristic points (end points, intersection points and coin points) of the word in order to estimate and correct a baseline and slant of the word. We use these algorithms in order to obtain an aligned word which can be well segmented and recognized. The results show that these methods are very powerful for most word images on the Algerian cities name database. The result image is useful for the holistic approach and segmentation approach.
  Waheb Larbi , Mouldi Bedda and Patrick Horrain
  This article presents an application of the digital imaging in the reading of a slide in optical microscopy, by applying a photometric correction of images issued out of the microscope, an interpolation of images captured by a CDD sensor (decoding) and the implementation of a mosaicking in order to obtain a virtual slide of big size. This study is particularly decisive in a context of telediagnosis applications in optical microscopy, using this type of sensor and manipulating images of large dimensions. We also propose some solutions which improve the efficiency of the telediagnosis chain and the quality of the visualized images.
  Salim Ouchtati , Mohamed Redjimi , Mouldi Bedda and Faouzi Bouchareb
  In this study, we present an off line method of handwritten isolated digits Recognition. The study is based on the analysis and the evaluation of multi-layers perceptron performances, trained with the gradient back propagation algorithm. It is hoped that the results of the evaluation contribute to the conception of operational systems. The used parameters to form the input vector of the neural network are extracted on the binary images of the digits by two methods: the centred moments of the distribution sequences and the Barr features
  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.
  Rachid Hamdi and Mouldi Bedda
  This study describes a concept of an Arabic speech synthesis based on optimized neural networks. The genetic algorithm is used to perform the connection weight update. An Arabic database which contains subjects, verbs and complements and a speech synthesizer, whose objective is to make educational oriented verbal Arab sentences, is developed. Based on parallel architecture of neural networks, the system receives a set of sentences of three words. The structure of the network, the algorithms and the results are detailed.
  Hocine Bourouba , Mouldi Bedda and Rafik Djemili
  In this study, we present a new architecture system of isolated spoken word recognition using HMM model. This study is an alternative study used in speech recognition using sex dependent hidden Markov models. The new study is introduced, evaluated and compared with traditional study GHMM for isolated word recognition system. Both these studyes apply the same principles of feature extraction and time-sequence modeling; the principal difference lies in the architecture used for training and recognition phases.
  Mohammed Redjimi , Salim Ouchtati and Mouldi Bedda
  In this study we present an off line system for the recognition of the isolated handwritten Arabic characters. The study is based on the analysis and the evaluation of multi-layers perceptron performances, trained with the gradient back propagation algorithm. It is hoped that the results of the evaluation contribute to the conception of operational systems. The used parameters to form the input vector of the neural network are extracted on the binary images of the characters by the following methods: the centerd moments of the projections sequences, distribution parameters, the Barr features and Coding according the directions of Freeman.
  Rafik Djemili , Mouldi Bedda and Hocine Bourouba
  In this study propose a new approach in using Hidden Markov Models (HMMs) for speech recognition. Although HMMs are the state-of-the art speech recognition systems, they suffer from some inherent limitations. One of these limitations is the independence assumption in the HMMs formalism. In the approach described in this study, we use in the vector quantization process, grouped vectors of different length to explicitly model the natural correlation between adjacent frames, instead of using a single vector in the standard method. The system is tested on an Arabic isolated digits (0-9) recognition task, our method achieves a 21% reduction in word error rate evaluation compared with the standard approach.
  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.
  Salim Ouchtati , Mouldi Bedda , Faouzi Bouchareb and Abderrazak Lachouri
  In this syudy we present an off line system for the recognition of the handwritten numeric chains. Our study is divided in two big parts. The first part is the realization of a recognition system of the isolated handwritten digits. In this study is based mainly on the evaluation of neural network performances, trained with the gradient back propagation algorithm. The used parameters to form the input vector of the neural network are extracted on the binary images of the digits by two methods: the centred moments of the distributions sequences and the Barr features. The second part is the extension of our system for the reading of the handwritten numeric chains constituted of a variable number of digits. The vertical projection is used to segment the numeric chain at isolated digits and every digit (or segment) will be presented separately to the entry of the system achieved in the first part (recognition system of the isolated handwritten digits). The result of the recognition of the numeric chain will be displayed at the exit of the global 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.
  Salah Bensaoula , Brahim Boulebtateche and Mouldi Bedda
  This study presents an auditory guidance system for the blind. We design a simple but useful wearable system composed of two types of sensor subsystems. One is stereoscopic sonar system which functions as an environment sensing and the other is the floor obstacle detection. Wide beam ultrasound sensors are used to detect obstacles in environment sensing function, so a broader range is covered. The second subsystem uses a narrow beam ultrasound sensor to detect obstacles at floor level. This type of sensor is required for sensing a limited surface in the path of the user for detecting holes and small obstacles. These two functions increases the mobility of blind people by offering extends of its own body functions. Experimental results are provided to show the effectiveness of the proposed apparatus.
 
 
 
Copyright   |   Desclaimer   |    Privacy Policy   |   Browsers   |   Accessibility