Ahmed Tamtaoui

Followers

Following

Public Views

Uploads

Papers by Ahmed Tamtaoui

A CAD system for the detection and classification of abnormalities in dense mammograms using electromagnetism-like optimization algorithm

2017 International Conference on Advanced Technologies for Signal and Image Processing (ATSIP), 2017

The detection of abnormalities in the breast at an early stage can be so helpful for breast cance... more The detection of abnormalities in the breast at an early stage can be so helpful for breast cancer treatment. Currently, mammography is the cheapest and the most efficient technique in terms of identifying the suspicious lesions in the breast. However, the interpretation of this screening remains so hard and could lead to inaccurate detection known as false positive and false negative. Dense breast category mammograms particularly, are difficult to read, because it may contain abnormal structures that are similar to the normal breast tissue. In this paper, we introduce an effecient Computer-Aided-Diagnosis system for the detection and classification of the ambiguous areas in dense breast mammograms. After noise and artifacts removal from the images using 2D Median filtering and labeling, we isolate the abnormalities using the metaheuristic algorithm Electromagnetism-like Optimization (EML), then we extract shape-based descriptors from the region of interest(ROI) using Zernike Moments. The detected abormal regions were classified into normal and abnormal based on the extracted shape features and through the Support Vector Machine(SVM) classification.

Improving the transfer learning performances in the classification of the automotive traffic roads signs

E3S Web of Conferences, 2021

This paper represents a study for the realization of a system based on Artificial Intelligence, w... more This paper represents a study for the realization of a system based on Artificial Intelligence, which allows the recognition of traffic road signs in an intelligent way, and also demonstrates the performance of Transfer Learning for object classification in general. When systems are trained on the aspects of human visualization (HVS), which helps or generates the same decisions, the construct robust and efficient systems. This allows us to avoid many environmental risks, both for weather conditions, such as cloudy or rainy weather that causes obscured vision of signs, but the main objective is to avoid all road risks that are dangerous to achieve road safety, such as accidents due to non-compliance with traffic rules, both for vehicles and passengers. However, simply collecting road signs in different places does not solve the problem, an intelligent system for classifying road signs is needed to improve the safety of people in its environment. This study proposed a traffic road sig...

Download

Performance analysis for amplify and forward full-duplex relaying with direct link over Nakagami-m fading channel

2017 International Conference on Wireless Networks and Mobile Communications (WINCOM), 2017

In order to keep up with countless emerging applications requirements, cellular systems have to e... more In order to keep up with countless emerging applications requirements, cellular systems have to embed new flexible aspects, with the aim of satisfying future wireless environments expectations. In this context, we consider a cellular system based a full-duplex amplify-and-forward cooperative communication over Nakagami-m channel. We assume the direct link between the source and the destination is non-negligible and we propose a combining scheme, at the destination side, that captures the joint benefit of relay and direct links. In order to meet with mission-critical applications requirements namely, low latency and reliability, the paper investigates the latency impact on the system performance and highlights the system diversity through the use of a combining scheme. First, we derive a new closedform expression of the studied system outage probability. Then, we confirm the theoretical results with Monte-carlo simulations. Furthermore, for more consistent analysis, we compare our combining scheme to Selective Decode-and-forward (SDF) scheme, recently proposed for full-duplex relaying as well as to some classical schemes. Simulation results show that they outperform each other depending on the relay processing delay, packet length, and the direct link gain.

An Enhanced Artificial Intelligence-Based Approach Applied to Vehicular Traffic Signs Detection and Road Safety Enhancement

Advances in Science, Technology and Engineering Systems Journal, 2021

The paper treats a problem for detection and recognition objects in computer vision sector, where... more The paper treats a problem for detection and recognition objects in computer vision sector, where researchers recommended OpenCV software and development tool, it's several and better-remembered library resource for isolating, detecting, and recognition of particular objects, what we would find an appropriate system for detecting and recognition traffic roads signs. The robustness with optimization is a necessary element in the computer vision algorithms, we can find a very large number of technics in object detection, for example, shapes transformation, color selection, a region of interest ROI, and edge detection, combined all these technics to reach high precision in animated video or still image processing. The system we are trying to develop, is in high demand in the automotive sector such as intelligent vehicles or autonomous driving assist systems ADAS, based on intelligent recognition, applying Artificial Intelligence, by using Deep Learning, exactly Convolutional Neural Network (CNN) architecture, our system improves the high accuracy of detection and recognition of traffic road signs with lower loss.

Download

Robust video coding based on perceptual unequal protection

2016 5th International Conference on Multimedia Computing and Systems (ICMCS), 2016

To increase the overall visual quality of the video services without increasing data rate, we dev... more To increase the overall visual quality of the video services without increasing data rate, we developed an unequal protection technique called UEP3D (Unequal Error Protection 3D) based on a hierarchy of the video stream in different levels of importance,. The determination of levels of importance takes three classification criteria: pixel level, macroblock level and image level. At the end of the classification process, an interpolation between the results of the three-level selection allows the award of a importance index for each macroblock of the image to be encoded. In this article we present the method used for classification at the macroblock level.

A Perceptually Optimized Embedded Image Coder and Quality Assessor Based on Visual Tools

2018 International Symposium on Advanced Electrical and Communication Technologies (ISAECT), 2018

In this paper, we propose a new Perceptually Optimized Embedded ZeroTree Image Coder EVIC and Qua... more In this paper, we propose a new Perceptually Optimized Embedded ZeroTree Image Coder EVIC and Quality Assessor WVDP. The coder introduces a perceptual weighting to wavelet coefficients prior to control SPIHT encoding algorithm in order to reach a targeted bit rate with a perceptual quality improvement with respect to the coding quality of the SPIHT algorithm only. The paper also, introduces a new objective quality metric based on Daly visual model known as Visible Difference Predictor that integrates the properties of the HVS and plays an important role in our EVIC quality assessment. Our EVIC coder is based on a vision model that incorporates various masking effects of human visual system HVS perception. Thus, our coder weights the wavelet coefficients based on that model and enhances the perceptual quality for a given bit rate and observation distance. The model weights within all wavelet sub bands are computed with respect to 1) luminance masking and Contrast masking deployed to ...

Fast Intra Prediction Algorithm for H.264/AVC Based on Quadratic and Gradient Model

International Journal of Electrical and Computer Engineering, 2010

With the development of Cloud Computing, the popularity of E learning, the increasing of social n... more With the development of Cloud Computing, the popularity of E learning, the increasing of social networking services, Smart Cloud E-Learning System with Social Networking has become a research topic. The characteristics of E learning Cloud and requirements of Social networking services in environments raise a challenge on building an Architecture and Implementation quite strong. In this paper, we elaborate a Smart Cloud E-Learning System with Social Networking based on architecture level of social networking and E learning cloud system to support E learning interactions in worldwide environments. A prototype of Cloud E-Learning System with Social Networking is developed on cloud, and several applications features are described based on the proposed architecture to demonstrate the effectiveness of the architecture. DOI: http://dx.doi.org/10.11591/ijece.v4i3.5933

Download

Experimental Study: Influence of Feature Extraction in Objects Multiclassification

2018 IEEE International Conference on Technology Management, Operations and Decisions (ICTMOD), 2018

Moving object multiclassification is an important step in a smart video surveillance system. Howe... more Moving object multiclassification is an important step in a smart video surveillance system. However, the relevance of its results depends not only on the classifier but also on the used data. Instead of the edge characteristic of the moving targets, representative characteristic features are extracted and used in the classification. In this paper, firstly, we present a comparative and experimental study of the effectiveness of several features and their influence on the classification accuracy. Secondly, we evaluate the performance of SVM-Multiclass, Artificial Neural Network (ANN), and K-nearest neighbor (KNN) with the extracted features. Also, we propose the use of feature fusion and the experimental results show that it improves the performance of the used classifiers and increase the classification accuracy up to 94%.

Reduction of the effect of impulsive noise on image transmission in OFDM-based power line communications

2016 International Conference on Information Technology for Organizations Development (IT4OD), 2016

Sending multimedia data (e.g. data, image and video) using Power Line Communications (PLC) has be... more Sending multimedia data (e.g. data, image and video) using Power Line Communications (PLC) has been growing significantly. In fact, impulsive noise (IN) causes significant degradation which restricts communication performance in PLC. In this paper, we propose to study the impact of IN on image communication in Orthogonal Frequency Division Multiplexing (OFDM) based PLC. A strightforward conventional iterative IN reduction algorithm, presented in [9] can be applied to improve bit-error rate (BER) in OFDM system. But, this iterative algorithm is insufissant to improve the visual quality Peak Signal-to-Noise Ratio (PSNR) performance in image communication. First, we study its performance in terms of BER and PSNR using a convolutional encoder (CE). Then, we modify its concept by introducing CE and Viterbi decoder into the iterative algorithm. Finally, we aim to show the impact of BER degradation on visual quality PSNR performance of the reconstructed image. Our results lay out that the proposed method provides good PSNR and visual quality improvement than the conventional algorithm with and without CE.

An Enhanced Approach in Detecting Object Applied to Automotive Traffic Roads Signs

2020 IEEE 6th International Conference on Optimization and Applications (ICOA), 2020

In this article, we use among and the best-known library is Open Computer Vision we call it for s... more In this article, we use among and the best-known library is Open Computer Vision we call it for short OpenCV. It is used for image processing, to do all operations we want, to isolate and detect a specific object, which in our case are traffic road signs. We process to find the most efficient methods of detection of traffic road signs. Our objective is to demonstrate the links the elements for optimized and powerful to computer vision algorithms that are easy to use as typing in an image and video processing. Most of the techniques they employed the color selection, edge detection, a region of interest selection, and shapes transformation of detection. Many applications require the recognition of traffic road signs in urban areas. The automation of this task is necessary, for example, ADAS systems, and the application of vision robotics or an autonomous vehicle, consist of recognizing and identifying traffic road signs as quickly as possible with errors to be minimized, in images of their type acquired by an embedded camera on board a vehicle.

A Comprehensive Survey of Medium Access Control Protocols for Wireless Body Area Networks

Wireless Communications and Mobile Computing, 2021

Wireless body area networks (WBANs) have emerged as a promising technology for health monitoring ... more Wireless body area networks (WBANs) have emerged as a promising technology for health monitoring due to their high utility and important role in improving human health. WBANs consist of a number of small battery-operated biomedical sensor nodes placed on the body or implanted, which are used to monitor and transmit important parameters such as blood pressure, electrocardiogram (ECG), and electroencephalogram (EEG). WBANs have strict requirements on energy efficiency and reliability during data collection and transmission. The most appropriate layer to address these requirements is the MAC layer. Medium access control protocols play an essential role in controlling the operation of radio transceivers and significantly affect the power consumption of the whole network. In this paper, we present a comprehensive survey of the most relevant and recent MAC protocols developed for WBANs. We discuss design requirements of a good MAC protocol for WBANs. We further review the different channe...

Download

An evaluation and ranking of evolutionary algorithms in segmenting abnormal masses in digital mammograms

Multimedia Tools and Applications, 2020

Breast cancer is the most common cancer in women worldwide and the second main cause of cancer mo... more Breast cancer is the most common cancer in women worldwide and the second main cause of cancer mortality after lung cancer. Up to now, there still no prevention nor early symptoms of breast cancer. Early detection can decrease significantly the mortality rate as the disease can be treated at an early stage. X-Ray is the current screening method that helps in detecting the most two common abnormalities of the breast, masses and micro-calcifications. However, interpreting mammograms is challenging in dense breasts as the abnormal masses and the normal glandular tissue of the breast have similar characteristics. Recently, the evolutionary algorithms have been widely used in image segmentation. In this paper, we evaluate and compare the performance of six most used evolutionary algorithms, invasive weed optimization (IWO), genetic algorithm (GA), particle swarm optimization (PSO), electromagnetism-like optimization (EMO), ant colony optimization (ACO), and artificial bee colony (ABC) in terms of clustering abnormal masses in the breast, particularly dense and extremely dense breasts. This evaluation is conducted based on quantitative metrics including Cohen's Kappa, correlation, and false positive and false negative rates. The evolutionary algorithms are then ranked based on two multi-criteria decision analysis methods, the Preference Ranking Organization Method for the Enrichment of Evaluations (PROMETHEE) and the Graphical Analysis for Interactive Aid (GAIA).

Download

Iterative algorithms for impulsive noise reduction in OFDM-based power line communications

International Journal of Embedded Systems, 2019

Power line communications (PLC) is a technology that permits data transmission using electrical n... more Power line communications (PLC) is a technology that permits data transmission using electrical networks. In the last few years, multimedia transmission (e.g., audio, image and video) over electrical signals has received a huge amount of research interest thanks to the already-existing indoor networks. However, impulsive noise presents the most impairments in PLC systems caused by switching transients in the in-home networking. In this paper, we propose some iterative suppression algorithms based on accurate impulsive noise estimation, using an adaptive threshold under a target false alarm probability. The proposed algorithms detect the amplitudes of impulsive noise, and then cancel them iteratively from the received contaminated signal. The results show that the proposed algorithms provide noticeable improvement in terms of bit error rate, peak signal-to-noise ratio, and visual reconstructed image quality, when compared to that of the conventional methods.

Download

Improving low cost sensor based vehicle positioning with Machine Learning

Control Engineering Practice, 2018

Current fleet management solutions rely on real time vehicle information to efficiently resolve t... more Current fleet management solutions rely on real time vehicle information to efficiently resolve transportation problems. In this study, a novel robust approach based on combining the Extended Kalman Filter (EKF) with Machine Learning techniques, Neural Networks or Support Vector Machines, is introduced to improve the accuracy of vehicle position estimation and circumvent the EKF limitations. The proposed solution guarantees also a low cost by using the Global Positioning System enhanced with Dead Reckoning integrated sensors. To verify our approach, extensive simulation tests are conducted on field data sets and very promising progress is obtained in the estimated vehicle position.

Download

Impulsive noise reduction techniques in power line communication: a survey

International Journal of Autonomous and Adaptive Communications Systems, 2019

Power line communication (PLC) is a technology that permits data transmission using the electrica... more Power line communication (PLC) is a technology that permits data transmission using the electrical networks. In the last few years, research in the area of efficient wired home-networking services and smart grid has received a great interest thanks to the already-existing electrical networks and the ubiquitous sockets (outlets). However, the power line channel presents a challenging task and provides drastic medium for multimedia (audio, image and video) transmission. In fact, over the last decades, there has been an intense research in the area of impulsive noise reduction in PLC environments and numerous error-mitigation strategies have been proposed, thus the need for such a broad survey. To this end, this paper presents a comprehensive overview, with major emphasis on identifying strengthens and weaknesses of the state-of-the-art techniques, and discusses some challenges and future research directions thorough consolidation of related works on PLC signal protection strategies against impulsive noise effects.

Download

Generic spatial-color metric for scale-space processing of catadioptric images

Computer Vision and Image Understanding, 2018

Images produced by omnidirectional catadioptric systems provide a larger field of view than conve... more Images produced by omnidirectional catadioptric systems provide a larger field of view than conventional cameras. However, these images contain significant radial distortions making classical processing unadapted. In addition, color information is almost neglected in omnidirectional imaging. In this paper, we propose a unifying framework, for central catadioptric color image processing, using Riemannian embedding that deals simultaneously with the geometric deformation due to the use of curved mirrors, and the multi-dimensional characteristic of the image. Based on the introduced Riemannian metric, we derive an adapted Gaussian kernel which is essential in widely used image processing. The resulting new formulation is then applied to various image processing: Image smoothing, Difference of Gaussians filtering and scalespace analysis, edge extraction and corner feature detection using Gaussian derivatives. The experiments illustrate the potential of the proposed approach, and show the higher quality of the adapted processing.

Download

A hybrid low cost approach using Extended Kalman filter and neural networks for real time positioning

2016 International Conference on Information Technology for Organizations Development (IT4OD), 2016

Global Positioning System (GPS) and Inertial Navigation Systems (INS) are usually used for real t... more Global Positioning System (GPS) and Inertial Navigation Systems (INS) are usually used for real time vehicle positioning. Unfortunately, this high cost solution still suffers from GPS outages due to multipath errors. To perform data fusion, the Extended Kalman filter (EKF) has been widely adopted as an optimal estimation tool for non-linear systems. However, it has some drawbacks in terms of stability, immunity to noise effects and observability. Furthermore, the filter is unfluenced by the vehicle dynamic variations and environment changes. On the other hand, neural networks can map input data to output data without any prior knowledge of the relationship involved. This paper presents a hybrid EKF and neural networks approach to improve the real time vehicle positioning performance while using GPS with nothing else than an odometer and a gyrometer low cost aiding sensors. While GPS signals are available, the neural networks are trained on different dynamics and outage times to learn the position errors so they can correct the future EKF predictions during GPS signal outages. The simulation results of this approach show a minimal improvement of 39% over the EKF predictions.

Schemas de compression de sequence d''images stereoscopiques par compensation de mouvement et dispar

Estimation de descripteurs de mouvement : Application au codage de séquences monoculaires et stéréoscopiques

L'étude proposée ici tente de fournir une estimation compacte d'un champ de mouvement par... more L'étude proposée ici tente de fournir une estimation compacte d'un champ de mouvement par descripteurs globaux sur des régions homogènes au sens d'un modèle de mouvement et qui soit efficace en reconstruction par compensation de mouvement. Le cadre méthodologique réside en les méthodes de minimisation par gradient (cas monoculaire) et son extension aux méthodes de minimisation sous contraintes (cas stéréoscopique). L'évaluation des résultats se fait en termes d'erreur de reconstruction et de qualité d'interprétation des champs de vecteurs mouvements apparents reconstruits.

Sur une approche visuelle de protection inégale des images codées DCT

La protection inégale (UEP) peut être une bonne solution pour coder et transmettre de façon effic... more La protection inégale (UEP) peut être une bonne solution pour coder et transmettre de façon efficace et fiable des sources d'information telles la vidéo ou l'image; pourvu que ces sources présentent dans leur structure intrinsèque des propriétés permettant un critère de hiérarchisation de leurs composantes en plus importantes d'une part et moins importantes d'autre part avec probablement des niveaux d'importance intermédiaires. S'ingénier à élaborer une telle hiérarchie revient à concevoir ce qui est connu sous les termes anglais Source Significance Information (SSI). Dans cet article, des images codées DCT sont soumises à une conception de SSI basée sur une approche visuelle. Une analyse comparative de performances est faite en simulant l'UEP sur différentes SSI d'images DCT.

Download

Ahmed Tamtaoui

Uploads

Papers by Ahmed Tamtaoui

Log In