{"title":"AI-based embedded systems for autonomous driving","authors":"S. Niar","doi":"10.1109/EDiS49545.2020.9296453","DOIUrl":"https://doi.org/10.1109/EDiS49545.2020.9296453","url":null,"abstract":"The transportation industry (automotive, railway and avionics) continues to look for ways to reduce the fatalities and the severity of accidents. Autonomous driving (AD) not only reduces the number of accidents, but offers also a better use of road infrastructures and may protect the environment. However, AD comes with inherent challenges. Specifically, many of the actions taken by the autonomous vehicle are based on increasingly complex algorithms, mainly applied from the artificial intelligence (AI) domain such as deep neural networks (DNN). These algorithms are known for their greed of computing and memory resources.In this presentation, I will talk about projects we are developing at Université Polytechnique Hauts-de-France in the design of optimized embedded systems for highly complex AD functionalities. The use of techniques such approximate computing, dynamic and partial reconfiguration and hierarchical cloud/fog/edge platforms will be explored.","PeriodicalId":119426,"journal":{"name":"2020 Second International Conference on Embedded & Distributed Systems (EDiS)","volume":"237 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122865228","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Multiuser Access via OFDMA Technology in High Density IEEE 802.11ax WLANs: A Survey","authors":"Saloua Brahmi, M. Yazid, Mawloud Omar","doi":"10.1109/EDiS49545.2020.9296440","DOIUrl":"https://doi.org/10.1109/EDiS49545.2020.9296440","url":null,"abstract":"IEEE 802.11ax known as HEW (High Efficiency WLANs: Wireless Local Area Networks) is the new standard designed to meet the objectives of the next generation of high density wireless networks, such as: airports, bus stations, stadiums, etc. The key innovative feature introduced in IEEE 802.11ax is the OFDMA (Orthogonal Frequency Division Multiple Access) technology. The basic principle of OFDMA at PHY (physical) layer is dividing a radio channel into smaller sub-channels, and hence enabling multiple and independent transmissions between multiple wireless devices. At MAC (Medium Access Control) layer, the OFDMA technology is thus intended to allow a massive connection of users, while reducing access delay and increasing individual throughput. This is why, several OFDMA MAC protocols, based on different approaches, have been designed and implemented for the purpose of efficiently using the radio resources supplied by the OFDMA technology at PHY layer. In this paper, we aim at: (i) reviewing the main existing OFDMA MAC protocols available in the literature with the goal of highlighting the strengths and weaknesses of each protocol, (ii) proposing a new classification of OFDMA MAC protocols, and (iii) drawing some perspectives for future research.","PeriodicalId":119426,"journal":{"name":"2020 Second International Conference on Embedded & Distributed Systems (EDiS)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130283137","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"[EDiS 2020 Blank Page]","authors":"","doi":"10.1109/edis49545.2020.9296460","DOIUrl":"https://doi.org/10.1109/edis49545.2020.9296460","url":null,"abstract":"","PeriodicalId":119426,"journal":{"name":"2020 Second International Conference on Embedded & Distributed Systems (EDiS)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134452898","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Karim Meddah, Hadjer Zairi, Besma Bessekri, Hachemi Cherrih, M. Kedir-Talha
{"title":"FPGA implementation of Epileptic Seizure detection based on DWT, PCA and Support Vector Machine","authors":"Karim Meddah, Hadjer Zairi, Besma Bessekri, Hachemi Cherrih, M. Kedir-Talha","doi":"10.1109/EDiS49545.2020.9296466","DOIUrl":"https://doi.org/10.1109/EDiS49545.2020.9296466","url":null,"abstract":"The study aims to establish an FPGA design model for epileptic seizures with discrete wavelet decomposition (DWT) and principal component analysis (PCA) to determine the optimum parameters of support vector machine (SVMs) for the EEG classification data. The FPGA Hardware implementation is described in this paper. Firstly, an optimized software-based medical diagnostic approach has been developed to determine the EEG class using only the variance calculated for each DWT level. This features extracted optimization leads to reduce the FPGA prototype size and to save energy consumption. Secondly, the proposed method has been designed and implemented on the Nexys 4 Artix 7 board using the Xilinx System Generator (XSG) for DSP. The performance evaluation of the proposed system has been made through two comparative studies, the first one, between the floating-point Matlab results and the fixed-point XSG results. The classification performances obtained from the proposed FPGA fixed-point implementation were compared to those obtained from the MATLAB floating-point. The second comparison was performed between the resulting performances and those obtained with the existing work in literature.","PeriodicalId":119426,"journal":{"name":"2020 Second International Conference on Embedded & Distributed Systems (EDiS)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133990900","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Toward a MAC Protocol Overcoming Hidden Stations Issue in IEEE 802.11ax Unidirectional Full Duplex Radio Communications","authors":"Kenza Hocini, M. Yazid","doi":"10.1109/EDiS49545.2020.9296431","DOIUrl":"https://doi.org/10.1109/EDiS49545.2020.9296431","url":null,"abstract":"The Full Duplex (FD) radio technology has been spotlighted as one of the key technologies in the future generation of High Efficiency WLANs (Wireless Local Area Networks). Indeed, it has the advantage of doubling the throughput of the Half Duplex radio (HD) through the adoption of SIC (Self-Interference Cancellation) antennas. By means of said antennas, simultaneous transmissions and receptions are therefore possible at the same time on the same radio frequencies. The Full Duplex radio communications are classified into two types: Bidirectional Full Duplex (BFD) and Unidirectional Full Duplex (UFD). In case of UFD communications, the Access Point (AP) shall not accept any Up-Link (UL) traffic from any wireless station, as this traffic could interfere with Down-Link (DL) traffic. Thus, UFD communications are only possible when the station that has UL traffic is hidden to the other station that has traffic to receive from AP. The main goal of this paper is extending the operation rules of the exiting 02-MAC (OFDMA Two symbol coordination Medium Access Control) protocol, thereby enabling the AP to select between candidate hidden stations which could participate in an UFD communication without interference. The obtained simulations results demonstrate that the proposal provides better performances in terms of throughput and overhead.","PeriodicalId":119426,"journal":{"name":"2020 Second International Conference on Embedded & Distributed Systems (EDiS)","volume":"139 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134357045","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Graph Convolutional Networks and Functional Connectivity for Identification of Autism Spectrum Disorder","authors":"Hichem Felouat, Saliha Oukid-Khouas","doi":"10.1109/EDiS49545.2020.9296476","DOIUrl":"https://doi.org/10.1109/EDiS49545.2020.9296476","url":null,"abstract":"The purpose of this study is to apply graph convolutional networks (GCNs) for feature extraction and classification of patients with autism spectrum disorder (ASD). The number of people with (ASD) increases every year and poses a threat to the life and future of many children which makes this study very important. We used the resting-state fMRI data from a large multi-site dataset called Autism Brain Imaging Data Exchange I (ABIDE I) to validate our proposed approach. Based on functional connectivity (FC), we represented the brain through a complex network where the regions of the brain represent the nodes in the network and the correlation coefficient between two regions represents the weight of the edge connects them. The data were preprocessed, and we constructed a functional connectivity graph for each subject by parcellation of the whole brain into 392 distinct regions using the (CC400) atlas. The graph measures were then calculated and used as features for both nodes and edges to classify these subjects by graph convolutional networks’ classifier which proposed in this study. The results we achieved in our experiments were with accuracy of 70% to identify patients with autism spectrum disorder from healthy individuals, which proved the accuracy and robustness of our approach in classifying brain diseases.","PeriodicalId":119426,"journal":{"name":"2020 Second International Conference on Embedded & Distributed Systems (EDiS)","volume":"84 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130683081","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Quality of Context in the internet of things: Parametres and models.","authors":"Elhannani souad, S. Benslimane","doi":"10.1109/EDiS49545.2020.9296479","DOIUrl":"https://doi.org/10.1109/EDiS49545.2020.9296479","url":null,"abstract":"In the internet of things word, the ability of a system to adapt and react to the changes accruing in the environment is the most important feature in a context aware system. This system relays on gathered context information that is imperfect due to the limitation of the sensors and the dynamicity of the environment, therefore, considering the quality of the context (QoC) is curial and important to ensure the right system performance. In this paper, we present the concepts of context, context awareness, and QoC. We define the most relevant QoC parameters, present a comparison of their relevant denomination and introduce our QoC parameters definition. Finally, we highlight the main QoC evaluation method and models that been suggested in the literature.","PeriodicalId":119426,"journal":{"name":"2020 Second International Conference on Embedded & Distributed Systems (EDiS)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134097355","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Chawki Benchehida, M. K. Benhaoua, H. Zahaf, G. Lipari
{"title":"Task and Communication Allocation for Real-time Tasks to Networks-on-Chip Multiprocessors","authors":"Chawki Benchehida, M. K. Benhaoua, H. Zahaf, G. Lipari","doi":"10.1109/EDiS49545.2020.9296446","DOIUrl":"https://doi.org/10.1109/EDiS49545.2020.9296446","url":null,"abstract":"In this paper, we address the problem of analyzing the behavior of a set of real-time tasks on a Network-on-chip-based (NoC) architecture. Our approach is to transform the allocation of tasks and communications within a NoC into a classical real-time allocation problem. It provides an extension of classical bin-packing heuristics to allocate a set of real-time applications modeled using a directed acyclic graphs (DAGs) to a set of processors interconnected through a NoC.The paper describes the schedulability analysis, including allocation and communication. It provides also a comparative study of different allocation and communication algorithms and presents accordingly a set of promising research insights.","PeriodicalId":119426,"journal":{"name":"2020 Second International Conference on Embedded & Distributed Systems (EDiS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124204606","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A novel combined SLM-PTS technique based on Genetic Algorithms for PAPR reduction in OFDM systems","authors":"T. H. Ali, A. Hamza","doi":"10.1109/EDiS49545.2020.9296434","DOIUrl":"https://doi.org/10.1109/EDiS49545.2020.9296434","url":null,"abstract":"0FDM has today becoming the modulation of choice for most modern broadband communication systems in use, either wireline or wireless. The main reasons is that OFDM provides the best usage of the available frequency band which maximizes the spectral efficiency and also its robustness to the multipath fading channel. However, OFDM has a major drawback of having a large Peak-to-Average Power Ratio (PAPR). The larger peak-to-average power ratio (PAPR) leads to frequency spread spectrum along with the in-band distortion, this is because of the non linearity present in the high power amplifiers.Most of the promising PAPR reduction methods are the Selective Mapping method (SLM) and Partial Transmit Sequence (PTS) which can achieve better PAPR performance without signal distortion. In this paper, a novel efficient PAPR reduction method using combined SLM and PTS techniques based on the Genetic Algorithms (GA) is proposed. GA is a kind of evolutionary computing algorithms that is applied to the combined SLM-PTS technique to get optimal phase rotation factors. The simulation results show that the proposed technique performance is better than the conventional SLM, conventional PTS and combined SLM-PTS techniques and also reduces the computational burden of the combined SLM-PTS scheme.","PeriodicalId":119426,"journal":{"name":"2020 Second International Conference on Embedded & Distributed Systems (EDiS)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121126245","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A new Levy Flight Trajectory-Based Grasshopper optimization Algorithm for Multi-objective optimization Problems","authors":"D. Mokeddem, Dallel Nasri","doi":"10.1109/EDiS49545.2020.9296480","DOIUrl":"https://doi.org/10.1109/EDiS49545.2020.9296480","url":null,"abstract":"This work proposes a new improved version of the nature-inspired multi-objective grasshopper optimization algorithm (MOGOA), based on a Levy flight method and called the Levy flight trajectory-based multi-objective grasshopper optimization algorithm (LMOGOA). It is worth mentioning that, the Levy flight trajectory is applied for the first time to enhance MOGOA algorithm by increasing the diversity of solution, avoiding premature convergence and local optima stagnation. The main advantage of LMOGOA is fast convergence speed to the true Pareto-optimal front while maintaining good diversity of solutions. To benchmark the performance of the proposed algorithm, a set of diverse standard multi-objective test problems is utilized. Results show that the proposed LMOGOA significantly outperforms the standard MOGOA algorithm.","PeriodicalId":119426,"journal":{"name":"2020 Second International Conference on Embedded & Distributed Systems (EDiS)","volume":"213 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134630530","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}