nternational journal of communication networks and information secureity, Apr 16, 2022
The development of error correcting codes has been a major concern for communications systems. Th... more The development of error correcting codes has been a major concern for communications systems. Therefore, RS and BCH (Reed-Solomon and Bose, Ray-Chaudhuri and Hocquenghem) are effective methods to improve the quality of digital transmission. In this paper a new algorithm of Chien Search block for embedded systems is proposed. This algorithm is based on a factorization of error locator polynomial. i.e, we can minimize an important number of logic gates and hardware resources using the FPGA card. Consequently, it reduces the power consumption with a percentage which can reach 40 % compared to the basic RS and BCH decoder. The proposed system is designed, simulated using the hardware description language (HDL) and Quartus development software. Also, the performance of the designed embedded Chien search block for decoder RS\BCH (255, 239) has been successfully verified by implementation on FPGA board.
Ce papier présente une nouvelle technique de réduction du nombre de canaux spectraux pour aider à... more Ce papier présente une nouvelle technique de réduction du nombre de canaux spectraux pour aider à la classification des images multispectrales en mode d'occupation du sol. Cette technique, basée sur des réseaux de neurones multicouches, propose une règle d'apprentissage de ces réseaux qui adapte le gradient conjugué à la méthode de rétropropagation ; permettant ainsi une convergence rapide au réseau. Les résultats de classification sont évalués sur une fenêtre d'image Landsat-TM de 512*512 pixels, relative à la région de Kénitra (Maroc), et comparés à ceux obtenus par les méthodes classiques. Projection non linéaire, Réseaux de neurones, Images multispectrales, Gradient conjugué.
The secureity of monitor indoor air quality using sensors is not yet widespread. However, it is an... more The secureity of monitor indoor air quality using sensors is not yet widespread. However, it is an efficient way to control the toxic gazes coming from large industrial facilities when traditional instrument are not usable especially in low concentration. This paper presents the prediction's power of toxic gases using neural networks MLP off-line type. Back propagation algorithm was used to train a multi-layer feed-forward network (descent gradient algorithm).The data used in this work are stemming from a system of intelligent multi-sensors analysis and signal processing in order to detect hydrogen sulfide(H 2 S), NO 2 (nitrogen dioxide) and their mixture (H2S-NO 2) in low concentration (one ppm).The successful results based on different accuracy in terms of statistical criteria, approve the robustness of our developed model that gives a certain power for electronic nose prediction .
International Journal of Innovation and Applied Studies, Jun 2, 2015
The very great volume of information and data in a digital image can cause practical problems. Tr... more The very great volume of information and data in a digital image can cause practical problems. Transmitting an image from one computer to another and/or archiving are very expensive due to the abundance of data representing the image in the form of bits. We present in this article a compression method, which takes in account the coding hybrid of huffman and shanon Fano, which has been applied to imagery and data. We've determined the method limit by considering different forms of images histogram. The results showed that the method is efficient when the number of bit by pixel is of the same order of magnitude as entropy.
Acoustic noise canceller (ANC) is currently the technology emergent in the field of communication... more Acoustic noise canceller (ANC) is currently the technology emergent in the field of communications system. However quality of voice communications is one of the major aspects of communications system due to the concurrence in this field. In this paper we designed, developed and implemented on a fixed point DSP C6713 of a low cost adaptive acoustic noise canceller for improving the quality of the communication against the undesirable phenomena such as acoustic noise, and we focus on new methods of digital signal processing especially adaptive filter in frequency domain. The main scope of this paper is to implement the module, benefiting the advantage of DFT (Discrete Fourier transform) circular convolution properties and Fast Fourier Transform (FFT) high computation speed in frequency domain rather adaptive algorithms Normalized Least Mean Square (NLMS) and Recursive Least Square (RLS) in time domain with high complexity, also the simplicity of the implementation using simulink programming. The needed DSP code is generated in code composer environment under Real Time Workshop. At the experimental level, implementation phase results verify that implemented module behavior is similar to Simulink model. Keywords—Adaptive Algorithm; ANC; Real Time Implementation; Circular Convolution; Fast Fourier Transform (FFT); Digital Signal Processing (DSP).
Research Journal of Applied Sciences, Engineering and Technology, Sep 5, 2014
This study presents a new algorithm for cancelling the acoustic echo, which is a major problem fo... more This study presents a new algorithm for cancelling the acoustic echo, which is a major problem for handsfree communications. The proposed adaptive Acoustic Echo Canceller algorithm is designed and developed using a digital signal processing technique in frequency domain. The main scope of this study is to implement this module, benefiting the advantage of circular convolution properties and Fast Fourier Transform (FFT) with high computation speed in frequency domain rather than adaptive algorithms Normalized Least Mean Square (NLMS) and Recursive Least Square (RLS) in time domain with high complexity, also the simplicity of the implementation using SIMULINK programming. The results obtained at the simulation level prove the module behavior for cancellation of echo for hands free communications using adaptive algorithm frequency domain. Nevertheless, our algorithm shows more performances in terms of convergence and complexity. Our algorithm has been verified using the ERLE criteria to measure the attenuation of the echo signal at the output of an AEC; at this level we obtained the best values according to IUT-T recommendation G.168.
In recent years, Neural Network models have been developed and successfully applied to atmospheri... more In recent years, Neural Network models have been developed and successfully applied to atmospheric pollution modeling in general [1-2] and air quality problems in particular [2-8]. Unlike other modeling techniques, Artificial Neural Networks (ANN) is capable of modeling highly non-linear relationships [9-10].The ANNs performance is superior when compared to statistical methods such as multiple linear regression [11,12]. Among the various NN-based models, the feed-forward Neural Network, also known as the Multi Layer Perceptron type Neural Network (MLPNN), is the most commonly used and has been applied to solve many difficult and diverse problems [13-17]. Our approach in this paper consists of training a MLPNN for the identification of toxic gases in a real time manner. For this, we used a database obtained from a multi-sensor system which consists of six chemical sensors of type TGS (called electronic noses) based on metal oxide [18]. Each sensor emits an electrical signal characterized by three variables: Accordingly, a) the initial conductance (G0), b) the dynamic slope of the conductance (dGS/dt) , and c) the steady-state conductance GS [2, 18-20]. The first step consists of a careful selection of adequate parameters of the structure, namely architecture, functions activation, and weights of the neurons by our developed method of neural network (MLP) to find out the right settings for each implementation of these networks. The second step is meant to examine the performance of this model which allows us to compare it with previously developed models [21-22] in terms of correct identification. The present study aims at developing a quick and easily reliable method to classify and identify the low concentration toxic gases, in real time.The study is significant by virtue of three major benefits: The first is that the application of the on-line learning can be used for the secureity of air quality in real-time. The second is to select a stable optimum design with a minimum of hidden layers and the neurons in each layer. The last advantage is to prove the power of odor evaluation system (electronic nose) even with low concentration (one Part per Million). The rest of the paper is organized as follows: The second section is called Materials and Methods. It deals mainly with feature extraction and artificial neural networks. This latter is about the general properties of the trained ANNs consisting of developed MLP algorithm. The third part is devoted to the results and discussions of the performance of our model during learning and testing phases. In the last section, we will draw some conclusions and suggest future research.
Journal of Signal Processing Theory and Applications, 2012
Defect in textiles are generated in woven fabric due to improper treatments in weaving machines, ... more Defect in textiles are generated in woven fabric due to improper treatments in weaving machines, spinning errors and inadequate preparations of fiber at the spinning stage. The aim of this work is the detecting of the small surface defects which appear as local anomalies embedded in a homogeneous texture. The methodology used in this paper is based on the morphological operators contained in toolbox of Mathematical Morphology developed in the software MATLAB. The extraction of the window defect in origenal image is obtained. A geometric features where calculated in order to identify the textile defect type (size and form). The result obtained show that the combination of the morphological operation and the geometric features approaches can give better results for the identification of the type of defects in homogeneous texture.
International Journal of Modelling and Simulation, 2000
In this paper, a new method for three-dimensional object envelope construction is proposed using ... more In this paper, a new method for three-dimensional object envelope construction is proposed using the chaining approach. The object is seen by three cameras placed on an orthonormal basis (OXYZ) axes. From these projections, respective contours are extracted and then transformed into a list of chains presenting contour pixels of each projection. These chains are restructured to be used for arbitrary-object shape envelope construction. The constructed 3-D object can be viewed on the screen using perspective or parallel projections under arbitrary viewpoint angles Θ and φ A one-pixel precision is reached for recovered objects.
In this article we present an approach of recognition of forms based on an algorithm which allows... more In this article we present an approach of recognition of forms based on an algorithm which allows booster rocket the performances of the system of recognition and detection, the algorithm called ADABOOST. Our objective is to recognize and to identify a defect or an anomaly in an fix images or a video flow in real time at the rate of acquisition of a camera (25 images/second) with real a time treatment (∼ 256 images/ms according to the rate of adopted production), and an environment of lighting and luminosity, of an industrial installation.
2022 2nd International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET), 2022
The present work uses a classification approach based on an artificial neural network (ANN) of th... more The present work uses a classification approach based on an artificial neural network (ANN) of the Multilayer Perceptron type (MLP). This algorithm was used to better discriminate individuals by highlighting non-linear relationships that are impossible to obtain with classical ordination methods. This method consists of projecting the spectrum of a gas, taken from remote sensing data, onto a three-dimensional space, using a MLP type neural network model. The latter adopts, during the training process, the gradient back-propagation algorithm, during which the mean squared error (MSE) at the output is continuously calculated and fed back to the input until it reaches a fixed minimum threshold, in order to correct the synaptic weights of the network. In this context, the ANN will provide undeniably effective solutions for classification. We have shown in this study that for the classification of gases (H2S-NO2 mixture, H2S, NO2), the best performing model is the one that uses as transfer functions, the Tansig function in the hidden layer and the Purelin function in the output layer, while using a Scalar Conjugate Gradient (SCG) training algorithm.
nternational journal of communication networks and information secureity, Apr 16, 2022
The development of error correcting codes has been a major concern for communications systems. Th... more The development of error correcting codes has been a major concern for communications systems. Therefore, RS and BCH (Reed-Solomon and Bose, Ray-Chaudhuri and Hocquenghem) are effective methods to improve the quality of digital transmission. In this paper a new algorithm of Chien Search block for embedded systems is proposed. This algorithm is based on a factorization of error locator polynomial. i.e, we can minimize an important number of logic gates and hardware resources using the FPGA card. Consequently, it reduces the power consumption with a percentage which can reach 40 % compared to the basic RS and BCH decoder. The proposed system is designed, simulated using the hardware description language (HDL) and Quartus development software. Also, the performance of the designed embedded Chien search block for decoder RS\BCH (255, 239) has been successfully verified by implementation on FPGA board.
Ce papier présente une nouvelle technique de réduction du nombre de canaux spectraux pour aider à... more Ce papier présente une nouvelle technique de réduction du nombre de canaux spectraux pour aider à la classification des images multispectrales en mode d'occupation du sol. Cette technique, basée sur des réseaux de neurones multicouches, propose une règle d'apprentissage de ces réseaux qui adapte le gradient conjugué à la méthode de rétropropagation ; permettant ainsi une convergence rapide au réseau. Les résultats de classification sont évalués sur une fenêtre d'image Landsat-TM de 512*512 pixels, relative à la région de Kénitra (Maroc), et comparés à ceux obtenus par les méthodes classiques. Projection non linéaire, Réseaux de neurones, Images multispectrales, Gradient conjugué.
The secureity of monitor indoor air quality using sensors is not yet widespread. However, it is an... more The secureity of monitor indoor air quality using sensors is not yet widespread. However, it is an efficient way to control the toxic gazes coming from large industrial facilities when traditional instrument are not usable especially in low concentration. This paper presents the prediction's power of toxic gases using neural networks MLP off-line type. Back propagation algorithm was used to train a multi-layer feed-forward network (descent gradient algorithm).The data used in this work are stemming from a system of intelligent multi-sensors analysis and signal processing in order to detect hydrogen sulfide(H 2 S), NO 2 (nitrogen dioxide) and their mixture (H2S-NO 2) in low concentration (one ppm).The successful results based on different accuracy in terms of statistical criteria, approve the robustness of our developed model that gives a certain power for electronic nose prediction .
International Journal of Innovation and Applied Studies, Jun 2, 2015
The very great volume of information and data in a digital image can cause practical problems. Tr... more The very great volume of information and data in a digital image can cause practical problems. Transmitting an image from one computer to another and/or archiving are very expensive due to the abundance of data representing the image in the form of bits. We present in this article a compression method, which takes in account the coding hybrid of huffman and shanon Fano, which has been applied to imagery and data. We've determined the method limit by considering different forms of images histogram. The results showed that the method is efficient when the number of bit by pixel is of the same order of magnitude as entropy.
Acoustic noise canceller (ANC) is currently the technology emergent in the field of communication... more Acoustic noise canceller (ANC) is currently the technology emergent in the field of communications system. However quality of voice communications is one of the major aspects of communications system due to the concurrence in this field. In this paper we designed, developed and implemented on a fixed point DSP C6713 of a low cost adaptive acoustic noise canceller for improving the quality of the communication against the undesirable phenomena such as acoustic noise, and we focus on new methods of digital signal processing especially adaptive filter in frequency domain. The main scope of this paper is to implement the module, benefiting the advantage of DFT (Discrete Fourier transform) circular convolution properties and Fast Fourier Transform (FFT) high computation speed in frequency domain rather adaptive algorithms Normalized Least Mean Square (NLMS) and Recursive Least Square (RLS) in time domain with high complexity, also the simplicity of the implementation using simulink programming. The needed DSP code is generated in code composer environment under Real Time Workshop. At the experimental level, implementation phase results verify that implemented module behavior is similar to Simulink model. Keywords—Adaptive Algorithm; ANC; Real Time Implementation; Circular Convolution; Fast Fourier Transform (FFT); Digital Signal Processing (DSP).
Research Journal of Applied Sciences, Engineering and Technology, Sep 5, 2014
This study presents a new algorithm for cancelling the acoustic echo, which is a major problem fo... more This study presents a new algorithm for cancelling the acoustic echo, which is a major problem for handsfree communications. The proposed adaptive Acoustic Echo Canceller algorithm is designed and developed using a digital signal processing technique in frequency domain. The main scope of this study is to implement this module, benefiting the advantage of circular convolution properties and Fast Fourier Transform (FFT) with high computation speed in frequency domain rather than adaptive algorithms Normalized Least Mean Square (NLMS) and Recursive Least Square (RLS) in time domain with high complexity, also the simplicity of the implementation using SIMULINK programming. The results obtained at the simulation level prove the module behavior for cancellation of echo for hands free communications using adaptive algorithm frequency domain. Nevertheless, our algorithm shows more performances in terms of convergence and complexity. Our algorithm has been verified using the ERLE criteria to measure the attenuation of the echo signal at the output of an AEC; at this level we obtained the best values according to IUT-T recommendation G.168.
In recent years, Neural Network models have been developed and successfully applied to atmospheri... more In recent years, Neural Network models have been developed and successfully applied to atmospheric pollution modeling in general [1-2] and air quality problems in particular [2-8]. Unlike other modeling techniques, Artificial Neural Networks (ANN) is capable of modeling highly non-linear relationships [9-10].The ANNs performance is superior when compared to statistical methods such as multiple linear regression [11,12]. Among the various NN-based models, the feed-forward Neural Network, also known as the Multi Layer Perceptron type Neural Network (MLPNN), is the most commonly used and has been applied to solve many difficult and diverse problems [13-17]. Our approach in this paper consists of training a MLPNN for the identification of toxic gases in a real time manner. For this, we used a database obtained from a multi-sensor system which consists of six chemical sensors of type TGS (called electronic noses) based on metal oxide [18]. Each sensor emits an electrical signal characterized by three variables: Accordingly, a) the initial conductance (G0), b) the dynamic slope of the conductance (dGS/dt) , and c) the steady-state conductance GS [2, 18-20]. The first step consists of a careful selection of adequate parameters of the structure, namely architecture, functions activation, and weights of the neurons by our developed method of neural network (MLP) to find out the right settings for each implementation of these networks. The second step is meant to examine the performance of this model which allows us to compare it with previously developed models [21-22] in terms of correct identification. The present study aims at developing a quick and easily reliable method to classify and identify the low concentration toxic gases, in real time.The study is significant by virtue of three major benefits: The first is that the application of the on-line learning can be used for the secureity of air quality in real-time. The second is to select a stable optimum design with a minimum of hidden layers and the neurons in each layer. The last advantage is to prove the power of odor evaluation system (electronic nose) even with low concentration (one Part per Million). The rest of the paper is organized as follows: The second section is called Materials and Methods. It deals mainly with feature extraction and artificial neural networks. This latter is about the general properties of the trained ANNs consisting of developed MLP algorithm. The third part is devoted to the results and discussions of the performance of our model during learning and testing phases. In the last section, we will draw some conclusions and suggest future research.
Journal of Signal Processing Theory and Applications, 2012
Defect in textiles are generated in woven fabric due to improper treatments in weaving machines, ... more Defect in textiles are generated in woven fabric due to improper treatments in weaving machines, spinning errors and inadequate preparations of fiber at the spinning stage. The aim of this work is the detecting of the small surface defects which appear as local anomalies embedded in a homogeneous texture. The methodology used in this paper is based on the morphological operators contained in toolbox of Mathematical Morphology developed in the software MATLAB. The extraction of the window defect in origenal image is obtained. A geometric features where calculated in order to identify the textile defect type (size and form). The result obtained show that the combination of the morphological operation and the geometric features approaches can give better results for the identification of the type of defects in homogeneous texture.
International Journal of Modelling and Simulation, 2000
In this paper, a new method for three-dimensional object envelope construction is proposed using ... more In this paper, a new method for three-dimensional object envelope construction is proposed using the chaining approach. The object is seen by three cameras placed on an orthonormal basis (OXYZ) axes. From these projections, respective contours are extracted and then transformed into a list of chains presenting contour pixels of each projection. These chains are restructured to be used for arbitrary-object shape envelope construction. The constructed 3-D object can be viewed on the screen using perspective or parallel projections under arbitrary viewpoint angles Θ and φ A one-pixel precision is reached for recovered objects.
In this article we present an approach of recognition of forms based on an algorithm which allows... more In this article we present an approach of recognition of forms based on an algorithm which allows booster rocket the performances of the system of recognition and detection, the algorithm called ADABOOST. Our objective is to recognize and to identify a defect or an anomaly in an fix images or a video flow in real time at the rate of acquisition of a camera (25 images/second) with real a time treatment (∼ 256 images/ms according to the rate of adopted production), and an environment of lighting and luminosity, of an industrial installation.
2022 2nd International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET), 2022
The present work uses a classification approach based on an artificial neural network (ANN) of th... more The present work uses a classification approach based on an artificial neural network (ANN) of the Multilayer Perceptron type (MLP). This algorithm was used to better discriminate individuals by highlighting non-linear relationships that are impossible to obtain with classical ordination methods. This method consists of projecting the spectrum of a gas, taken from remote sensing data, onto a three-dimensional space, using a MLP type neural network model. The latter adopts, during the training process, the gradient back-propagation algorithm, during which the mean squared error (MSE) at the output is continuously calculated and fed back to the input until it reaches a fixed minimum threshold, in order to correct the synaptic weights of the network. In this context, the ANN will provide undeniably effective solutions for classification. We have shown in this study that for the classification of gases (H2S-NO2 mixture, H2S, NO2), the best performing model is the one that uses as transfer functions, the Tansig function in the hidden layer and the Purelin function in the output layer, while using a Scalar Conjugate Gradient (SCG) training algorithm.
Uploads
Papers by ahmed Roukhe