Yassine EL Hafid - Academia.edu (original) (raw)

Uploads

Papers by Yassine EL Hafid

Procedia Computer Science

This work aims to evaluate the real-time processing system in the context of an autonomous vehicl... more This work aims to evaluate the real-time processing system in the context of an autonomous vehicle with limited hardware and software capabilities. We elaborate algorithm implemented in 1/10 scale electric car using a line scan camera, speed sensors, and embedded electronic control system. The vehicle navigates in an arbitrary one-lane circuit using an edge detection algorithm. The challenge was to make a complete one loop of the arbitrary circuit in the shortest time with various lighting conditions. The experiments show that several issues were revealed in each step of data sensors processing and need a robust algorithm to handle exceptions caused by multiple disturbances. Furthermore, we paid particular attention to time constraints in embedded processor calculation and actuators response time to achieve reliable critical software control algorithms.

Procedia Computer Science, 2021

Proceedings of the Third International Conference on Computing and Wireless Communication Systems, ICCWCS 2019, April 24-25, 2019, Faculty of Sciences, Ibn Tofaïl University -Kénitra- Morocco, 2019

Spectrum sensing is the most important technique used to implement cognitive radio; this approach... more Spectrum sensing is the most important technique used to implement cognitive radio; this approach allows opportunistic and dynamic allocation of spectral bands. Among the methods used for detection, there are Artificial Neural Networks (ANN) and Energy Detection (ED); those exploit the signals coming from a Fast Fourier Transformed block (FFT). In this work, we focus on improving the performance of these three blocks by performing parallel computing, and considering the fusion of the two detectors ANN and ED. In this context, we implement three algorithms on GPU, which consist on exploiting the large number of cores to perform parallel calculation. The experimental results are compared with those obtained for CPU implementations. Our study presents how calculations distribution on GPU cores influences the global performance, and how to reduce execution time by optimizing data transfer. Furthermore, by exploiting the fine-grained parallel processing, and using a suitable choice of pa...

Human Centred Intelligent Systems

Computer and Information Science, Jan 28, 2015

Spectrum sensing is the most important technique used to implement cognitive radio; this approach... more Spectrum sensing is the most important technique used to implement cognitive radio; this approach allows opportunistic and dynamic allocation of spectral bands. Among the methods used for detection, there are Artificial Neural Networks (ANN) and Energy Detection (ED); those exploit the signals coming from a Fast Fourier Transformed block (FFT). In this work, we focus on improving the performance of these three blocks by performing parallel computing, and considering the fusion of the two detectors ANN and ED. In this context, we implement three algorithms on GPU, which consist on exploiting the large number of cores to perform parallel calculation. The experimental results are compared with those obtained for CPU implementations. Our study presents how calculations distribution on GPU cores influences the global performance, and how to reduce execution time by optimizing data transfer. Furthermore, by exploiting the fine-grained parallel processing, and using a suitable choice of parameters, we find a considerable advantage of GPUs compared to CPUs, specifically for high data volumes.

Procedia Computer Science

This work aims to evaluate the real-time processing system in the context of an autonomous vehicl... more This work aims to evaluate the real-time processing system in the context of an autonomous vehicle with limited hardware and software capabilities. We elaborate algorithm implemented in 1/10 scale electric car using a line scan camera, speed sensors, and embedded electronic control system. The vehicle navigates in an arbitrary one-lane circuit using an edge detection algorithm. The challenge was to make a complete one loop of the arbitrary circuit in the shortest time with various lighting conditions. The experiments show that several issues were revealed in each step of data sensors processing and need a robust algorithm to handle exceptions caused by multiple disturbances. Furthermore, we paid particular attention to time constraints in embedded processor calculation and actuators response time to achieve reliable critical software control algorithms.

Procedia Computer Science, 2021

Proceedings of the Third International Conference on Computing and Wireless Communication Systems, ICCWCS 2019, April 24-25, 2019, Faculty of Sciences, Ibn Tofaïl University -Kénitra- Morocco, 2019

Spectrum sensing is the most important technique used to implement cognitive radio; this approach... more Spectrum sensing is the most important technique used to implement cognitive radio; this approach allows opportunistic and dynamic allocation of spectral bands. Among the methods used for detection, there are Artificial Neural Networks (ANN) and Energy Detection (ED); those exploit the signals coming from a Fast Fourier Transformed block (FFT). In this work, we focus on improving the performance of these three blocks by performing parallel computing, and considering the fusion of the two detectors ANN and ED. In this context, we implement three algorithms on GPU, which consist on exploiting the large number of cores to perform parallel calculation. The experimental results are compared with those obtained for CPU implementations. Our study presents how calculations distribution on GPU cores influences the global performance, and how to reduce execution time by optimizing data transfer. Furthermore, by exploiting the fine-grained parallel processing, and using a suitable choice of pa...

Human Centred Intelligent Systems

Computer and Information Science, Jan 28, 2015

Spectrum sensing is the most important technique used to implement cognitive radio; this approach... more Spectrum sensing is the most important technique used to implement cognitive radio; this approach allows opportunistic and dynamic allocation of spectral bands. Among the methods used for detection, there are Artificial Neural Networks (ANN) and Energy Detection (ED); those exploit the signals coming from a Fast Fourier Transformed block (FFT). In this work, we focus on improving the performance of these three blocks by performing parallel computing, and considering the fusion of the two detectors ANN and ED. In this context, we implement three algorithms on GPU, which consist on exploiting the large number of cores to perform parallel calculation. The experimental results are compared with those obtained for CPU implementations. Our study presents how calculations distribution on GPU cores influences the global performance, and how to reduce execution time by optimizing data transfer. Furthermore, by exploiting the fine-grained parallel processing, and using a suitable choice of parameters, we find a considerable advantage of GPUs compared to CPUs, specifically for high data volumes.