Location plays a crucial role in many applications of Wireless Sensor Networks (WSNs), and accura... more Location plays a crucial role in many applications of Wireless Sensor Networks (WSNs), and accurate sensor localization is an important aspect of the acquired data. While connectivity algorithms are commonly used for localizing multi-hop WSNs because their simplicity and acceptable accuracy, their effectiveness can be limited in two-dimensional (2D) or three-dimensional (3D) environments. An analytic model that incorporates hop size quantization and the Recursive Least Squares (RLS) method can be advantageous for Range-Free 3D wireless sensor networks (WSNs) in localization. This approach reduces computational complexity, memory requirements, and localization errors. The third dimension significantly impacts localization accuracy, necessitating the development of effective self-localization algorithms for 3D WSNs. This article introduces a novel probabilistic quantization technique for hop sizes in 3D-WSNs, specifically designed to address the uniform distribution of sensor nodes. T...
International Journal of Informatics and Communication Technology (IJ-ICT)
Localization is a critical concern in many wireless sensor network (WSN) applications. Furthermor... more Localization is a critical concern in many wireless sensor network (WSN) applications. Furthermore, correct information regarding the geographic placements of nodes (sensors) is critical for making the collected data valuable and relevant. Because of their benefits, such as simplicity and acceptable accuracy, the based connectivity algorithms attempt to localize multi-hop WSN. However, due to environmental factors, the precision of localisation may be rather low. This publication describes an Extreme Learning Machine (ELM) technique for minimizing localization error in range-free WSN. In this paper, we propose a Cascade Extreme Learning Machine (Cascade-ELM) to increase localization accuracy in Range-Free WSNs. We tested the proposed approaches in a variety of multi-hop WSN scenarios. Our research focused on an isotropic and irregular environment. The simulation results show that the proposed Cascade-ELM algorithm considerably improves localization accuracy when compared to previous...
Artificial Intelligence for Smart Cities and Villages: Advanced Technologies, Development, and Challenges
Traffic sign detection is one of the most important tasks for autonomous public transport vehicle... more Traffic sign detection is one of the most important tasks for autonomous public transport vehicles. It provides a global view of the traffic signs on the road. In this chapter, we introduce a traffic sign detection method based on auto-encoders and Convolutional Neural Networks. For this purpose, we propose an end-to-end unsupervised/supervised learning method to solve a traffic sign detection task. The main idea of the proposed approach aims to perform an interconnection between an auto-encoder and a Convolutional Neural Networks to act as a single network to detect traffic signs under real-world conditions. The auto-encoder enhances the resolution of the input images and the convolutional neural network was used to detect and identify traffic signs. Besides, to build a traffic signs detector with high performance, we proposed a new traffic sign dataset. It contains more classes than the existing ones, which contain 10000 images from 73 traffic sign classes captured on the Chinese ...
The complexity of embedded systems is growing rapidly and demand for new approaches to meet the n... more The complexity of embedded systems is growing rapidly and demand for new approaches to meet the needs of businesses. the design of SoC and SOPC becomes increasingly complex as they incorporate more and more IP and peripheral controllers such as HDMI, Ethernet, wireless controller. For this reason the presence of an operating system is essential to manage all these features. This paper is the state of the art reconfigurable hardware operating systems. It addresses several aspects of dynamic reconfiguration and presents implementation issues associated with implementation. Aspects communications, scheduling and placement tasks are described and solutions are presented.
2021 International Conference on Control, Automation and Diagnosis (ICCAD)
In most cases of Wireless Sensor Network (WSN) application, the event information transmitted via... more In most cases of Wireless Sensor Network (WSN) application, the event information transmitted via the connected wireless sensor has not great significance without a precise valuation of its geographical position. In this work, we exploit the Machine Learning Technique (MLT) to improve node localization accuracy in WSN. The adopted MLT was applied with a range-free technique which is founded on the multi-hop localization process. The proposed methods are based on the Extreme Learning Machine (ELM) and the On-line Sequential Extreme Learning Machine. Simulation results demonstrate that the proposed algorithms permit to greatly minimize the average localization errors of the estimated node’s position compared to the basis ELM learning machine and the well know Distance Vector Hop (Dv-Hop). Satisfactory results were obtained for isotropic and anisotropic environments in range free case.
2020 IEEE 4th International Conference on Image Processing, Applications and Systems (IPAS), 2020
Advanced driver assistance system (ADAS) is one of the most important systems for human assistanc... more Advanced driver assistance system (ADAS) is one of the most important systems for human assistance. It assists the drivers to control the vehicle by providing essential information about the environment objects. In this paper, we propose a traffic signs recognition application for ADAS. The proposed application is based on the deep learning technique. In particular, we used the convolutional neural networks (CNN) to process the data provided by the system cameras. The proposed CNN was scaled in a way to get a light model size without decreasing the accuracy. The proposed CNN is suitable for embedded implementation while keeping high performance and real-time processing. The evaluation of the proposed CNN on the European dataset results in 99.32% accuracy and 250 FPS of inference speed when implemented on an Nvidia GTX960 GPU. The achieved results proved the efficiency of the scaling technique. It is a very good technique to get a small model size and high performance.
Abstract. This paper focus on the study of the color structure descriptor (CSD) for shot boundary... more Abstract. This paper focus on the study of the color structure descriptor (CSD) for shot boundary detection in video sequences. We interest in the validation and the optimisation of this descriptor in the aim of its real time implementation on hardware architecture. In this ...
In this study we propose a framework and a combined temporal partitioning and designspace explora... more In this study we propose a framework and a combined temporal partitioning and designspace exploration method for run time reconfigurable processors. Our objective is to help designers toimplement an algorithm in limited FPGA area resources while respecting the execution time constraint.The algorithm to be implemented is represented by a task graph with different implementationalternatives (design points) for each task. We study the effect of hardware resources limitation in thechoice of the algorithm implementation design point. The proposed method is based on an heuristictechnique which consists on combining temporal partitioning and task design points selection to obtainsolutions that satisfy the imposed constraints.
Location plays a crucial role in many applications of Wireless Sensor Networks (WSNs), and accura... more Location plays a crucial role in many applications of Wireless Sensor Networks (WSNs), and accurate sensor localization is an important aspect of the acquired data. While connectivity algorithms are commonly used for localizing multi-hop WSNs because their simplicity and acceptable accuracy, their effectiveness can be limited in two-dimensional (2D) or three-dimensional (3D) environments. An analytic model that incorporates hop size quantization and the Recursive Least Squares (RLS) method can be advantageous for Range-Free 3D wireless sensor networks (WSNs) in localization. This approach reduces computational complexity, memory requirements, and localization errors. The third dimension significantly impacts localization accuracy, necessitating the development of effective self-localization algorithms for 3D WSNs. This article introduces a novel probabilistic quantization technique for hop sizes in 3D-WSNs, specifically designed to address the uniform distribution of sensor nodes. T...
International Journal of Informatics and Communication Technology (IJ-ICT)
Localization is a critical concern in many wireless sensor network (WSN) applications. Furthermor... more Localization is a critical concern in many wireless sensor network (WSN) applications. Furthermore, correct information regarding the geographic placements of nodes (sensors) is critical for making the collected data valuable and relevant. Because of their benefits, such as simplicity and acceptable accuracy, the based connectivity algorithms attempt to localize multi-hop WSN. However, due to environmental factors, the precision of localisation may be rather low. This publication describes an Extreme Learning Machine (ELM) technique for minimizing localization error in range-free WSN. In this paper, we propose a Cascade Extreme Learning Machine (Cascade-ELM) to increase localization accuracy in Range-Free WSNs. We tested the proposed approaches in a variety of multi-hop WSN scenarios. Our research focused on an isotropic and irregular environment. The simulation results show that the proposed Cascade-ELM algorithm considerably improves localization accuracy when compared to previous...
Artificial Intelligence for Smart Cities and Villages: Advanced Technologies, Development, and Challenges
Traffic sign detection is one of the most important tasks for autonomous public transport vehicle... more Traffic sign detection is one of the most important tasks for autonomous public transport vehicles. It provides a global view of the traffic signs on the road. In this chapter, we introduce a traffic sign detection method based on auto-encoders and Convolutional Neural Networks. For this purpose, we propose an end-to-end unsupervised/supervised learning method to solve a traffic sign detection task. The main idea of the proposed approach aims to perform an interconnection between an auto-encoder and a Convolutional Neural Networks to act as a single network to detect traffic signs under real-world conditions. The auto-encoder enhances the resolution of the input images and the convolutional neural network was used to detect and identify traffic signs. Besides, to build a traffic signs detector with high performance, we proposed a new traffic sign dataset. It contains more classes than the existing ones, which contain 10000 images from 73 traffic sign classes captured on the Chinese ...
The complexity of embedded systems is growing rapidly and demand for new approaches to meet the n... more The complexity of embedded systems is growing rapidly and demand for new approaches to meet the needs of businesses. the design of SoC and SOPC becomes increasingly complex as they incorporate more and more IP and peripheral controllers such as HDMI, Ethernet, wireless controller. For this reason the presence of an operating system is essential to manage all these features. This paper is the state of the art reconfigurable hardware operating systems. It addresses several aspects of dynamic reconfiguration and presents implementation issues associated with implementation. Aspects communications, scheduling and placement tasks are described and solutions are presented.
2021 International Conference on Control, Automation and Diagnosis (ICCAD)
In most cases of Wireless Sensor Network (WSN) application, the event information transmitted via... more In most cases of Wireless Sensor Network (WSN) application, the event information transmitted via the connected wireless sensor has not great significance without a precise valuation of its geographical position. In this work, we exploit the Machine Learning Technique (MLT) to improve node localization accuracy in WSN. The adopted MLT was applied with a range-free technique which is founded on the multi-hop localization process. The proposed methods are based on the Extreme Learning Machine (ELM) and the On-line Sequential Extreme Learning Machine. Simulation results demonstrate that the proposed algorithms permit to greatly minimize the average localization errors of the estimated node’s position compared to the basis ELM learning machine and the well know Distance Vector Hop (Dv-Hop). Satisfactory results were obtained for isotropic and anisotropic environments in range free case.
2020 IEEE 4th International Conference on Image Processing, Applications and Systems (IPAS), 2020
Advanced driver assistance system (ADAS) is one of the most important systems for human assistanc... more Advanced driver assistance system (ADAS) is one of the most important systems for human assistance. It assists the drivers to control the vehicle by providing essential information about the environment objects. In this paper, we propose a traffic signs recognition application for ADAS. The proposed application is based on the deep learning technique. In particular, we used the convolutional neural networks (CNN) to process the data provided by the system cameras. The proposed CNN was scaled in a way to get a light model size without decreasing the accuracy. The proposed CNN is suitable for embedded implementation while keeping high performance and real-time processing. The evaluation of the proposed CNN on the European dataset results in 99.32% accuracy and 250 FPS of inference speed when implemented on an Nvidia GTX960 GPU. The achieved results proved the efficiency of the scaling technique. It is a very good technique to get a small model size and high performance.
Abstract. This paper focus on the study of the color structure descriptor (CSD) for shot boundary... more Abstract. This paper focus on the study of the color structure descriptor (CSD) for shot boundary detection in video sequences. We interest in the validation and the optimisation of this descriptor in the aim of its real time implementation on hardware architecture. In this ...
In this study we propose a framework and a combined temporal partitioning and designspace explora... more In this study we propose a framework and a combined temporal partitioning and designspace exploration method for run time reconfigurable processors. Our objective is to help designers toimplement an algorithm in limited FPGA area resources while respecting the execution time constraint.The algorithm to be implemented is represented by a task graph with different implementationalternatives (design points) for each task. We study the effect of hardware resources limitation in thechoice of the algorithm implementation design point. The proposed method is based on an heuristictechnique which consists on combining temporal partitioning and task design points selection to obtainsolutions that satisfy the imposed constraints.
Uploads
Papers by Abdessalem Ben Abdelali