2021 18th International Multi-Conference on Systems, Signals & Devices (SSD)最新文献_第10页

Deep Pre-trained Models for Computer Vision Applications: Traffic sign recognition 计算机视觉应用的深度预训练模型:交通标志识别

2021 18th International Multi-Conference on Systems, Signals & Devices (SSD) Pub Date : 2021-03-22 DOI: 10.1109/SSD52085.2021.9429420

Soulef Bouaafia, Seifeddine Messaoud, Amna Maraoui, A. Ammari, L. Khriji, M. Machhout

{"title":"Deep Pre-trained Models for Computer Vision Applications: Traffic sign recognition","authors":"Soulef Bouaafia, Seifeddine Messaoud, Amna Maraoui, A. Ammari, L. Khriji, M. Machhout","doi":"10.1109/SSD52085.2021.9429420","DOIUrl":"https://doi.org/10.1109/SSD52085.2021.9429420","url":null,"abstract":"Objects detection and Recognition are an important task for computer vision field and intelligent transportation systems. Generally, these tasks remain challenging for the artificial machines due to the need of pre-learning phase in which the machine acquires an intelligent brain. Some researchers have shown that deep learning tools work well in computer vision, image processing, and pattern recognition. To solve such tasks, this paper focuses on deep Convolutional Neural Network (CNN) and its architectures, such as, VGG16, VGG19, AlexNet, and Resnet50. An overview for the techniques and schemes used for computer vision applications such as Road Sign Recognition will be introduced. Then by customizing the hyperparameters for each pre-trained models, we re-implement these models for the traffic sign recognition application. In the experiments, these pre-trained CNN classifiers are trained and tested with the German Traffic Sign Recognition Benchmark dataset (GTSRB). Experimental results show that the proposed scheme achieved a good performance results in terms of evaluations metrics of traffic signs recognition. A performance comparison analysis between the selected pre-trained models for traffic sign recognition confirmed that the AlexNet model outperforms all other implemented models.","PeriodicalId":6799,"journal":{"name":"2021 18th International Multi-Conference on Systems, Signals & Devices (SSD)","volume":"73 1","pages":"23-28"},"PeriodicalIF":0.0,"publicationDate":"2021-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89430000","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}

引用次数: 6

Flexible Control Strategies with Current Limitation of VSI Under Unbalanced Grid Voltage Sags 电网不平衡电压跌落下具有电流限制的VSI柔性控制策略

2021 18th International Multi-Conference on Systems, Signals & Devices (SSD) Pub Date : 2021-03-22 DOI: 10.1109/SSD52085.2021.9429489

Fathia Letaief, A. Rhouma, M. Hamouda

引用次数: 0

Maximum Power Point Tracking Controller for Pumping Photovoltaic System Based on Induction Motor 基于感应电机的抽水光伏系统最大功率点跟踪控制器

2021 18th International Multi-Conference on Systems, Signals & Devices (SSD) Pub Date : 2021-03-22 DOI: 10.1109/SSD52085.2021.9429448

Abderrazek Saoudi, Saber Krim, M. Mimouni

引用次数: 1

A Novel Inverse Gaussian Profile for Orbital Angular Momentum Mode Division Multiplexing Optical Networks 一种新的轨道角动量模分复用光网络反高斯分布

2021 18th International Multi-Conference on Systems, Signals & Devices (SSD) Pub Date : 2021-03-22 DOI: 10.1109/SSD52085.2021.9429400

Alaaeddine Rjeb, Hussein E. Seleem, H. Fathallah, M. Machhout

{"title":"A Novel Inverse Gaussian Profile for Orbital Angular Momentum Mode Division Multiplexing Optical Networks","authors":"Alaaeddine Rjeb, Hussein E. Seleem, H. Fathallah, M. Machhout","doi":"10.1109/SSD52085.2021.9429400","DOIUrl":"https://doi.org/10.1109/SSD52085.2021.9429400","url":null,"abstract":"Orbital angular momentum modes have shown promising achievements, as data carriers, in ameliorating the transmission capacity and raising the spectral efficiency. This has leaded to an increasing interest in exploiting appropriate specialty fibers for supporting robust OAM channels. In this work, we propose a novel inner graded ring core fiber referred to as inverse Gaussian fiber (IGF). To the best of our knowledge, IGF has never been used as optical fiber profile before. We optimize IGF key parameters in order to design optimized IG-few mode fibers (FMF) supporting low radial modes with high intermodal separation that outperforms those reported in literature (minimum of $Delta n_{text{eff}}=2.74times 10^{-4}$), this limits mode coupling and reduces channels crosstalk. We investigate the impacts of smoothness parameters ($alpha$ & $P$) on the properties of OAM channels in the IG-FMFs. We evaluate and compare (with literature) their intermodal separation, their chromatic dispersion, and their associated differential group delay over the C+L ITU-T bands. The selected designs are proposed as favorable candidate to guide OAM modes in next generation OAM-MDM multiplexing optical networks.","PeriodicalId":6799,"journal":{"name":"2021 18th International Multi-Conference on Systems, Signals & Devices (SSD)","volume":"110 1","pages":"480-487"},"PeriodicalIF":0.0,"publicationDate":"2021-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77969111","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}

引用次数: 3

Traction Mode of an Electric Vehicle based on a Delta Inverter feeding a Split Stator Windings PMSM 基于三角逆变器馈入分离定子绕组永磁同步电机的电动汽车牵引模式

2021 18th International Multi-Conference on Systems, Signals & Devices (SSD) Pub Date : 2021-03-22 DOI: 10.1109/SSD52085.2021.9429528

A. Rhouma

引用次数: 0

Numerical validation of experimental results for the dynamic behavior of sandwich structures 夹层结构动力特性试验结果的数值验证

2021 18th International Multi-Conference on Systems, Signals & Devices (SSD) Pub Date : 2021-03-22 DOI: 10.1109/SSD52085.2021.9429366

Najah Hamamed, S. Bouaziz, H. Hentati, M. Haddar, R. Guerjouma, N. Yaakoubi

引用次数: 2

Chaos Elimination in Power System Using Synergetic Control Theory 基于协同控制理论的电力系统混沌消除

2021 18th International Multi-Conference on Systems, Signals & Devices (SSD) Pub Date : 2021-03-22 DOI: 10.1109/SSD52085.2021.9429398

Abdul-Basset A. Al-Hussein, Fadhil Rahma, O. Boubaker

引用次数: 2

PGTLP: A Dataset for Tunisian License Plate Detection and Recognition PGTLP:突尼斯车牌检测与识别数据集

2021 18th International Multi-Conference on Systems, Signals & Devices (SSD) Pub Date : 2021-03-22 DOI: 10.1109/SSD52085.2021.9429447

Amir Ismail, Maroua Mehri, A. Sahbani, N. Amara

引用次数: 0

Inverse Kinematics of a Team of 5-DOF Holonomic Mobile Cooperative Rover Manipulators 一组五自由度完整移动协作漫游机器人的运动学逆解

2021 18th International Multi-Conference on Systems, Signals & Devices (SSD) Pub Date : 2021-03-22 DOI: 10.1109/SSD52085.2021.9429336

Emory Salberg, J. Sanjuan, Ivan Rulik, M. Rahman, B. Brahmi

引用次数: 0

DRNNA: Decomposable Reverse Nearest Neighbor Algorithm for Vertically Distributed Databases 垂直分布数据库的可分解反向最近邻算法

2021 18th International Multi-Conference on Systems, Signals & Devices (SSD) Pub Date : 2021-03-22 DOI: 10.1109/SSD52085.2021.9429512

A. Khedr, P. Raj

{"title":"DRNNA: Decomposable Reverse Nearest Neighbor Algorithm for Vertically Distributed Databases","authors":"A. Khedr, P. Raj","doi":"10.1109/SSD52085.2021.9429512","DOIUrl":"https://doi.org/10.1109/SSD52085.2021.9429512","url":null,"abstract":"There are many applications for the Reverse Nearest Neighbor (RNN) problem, including continuous referral systems, resource allocation, decision support, location-based services, bioinformatics, profile-based marketing, and many others. Although there exist numerous studies on RNN problem, most of the existing algorithms for RNN works on a single database. In contrast to the existing approaches, we propose a Decomposable Reverse Nearest Neighbor Algorithm (DRNNA), which computes RNN in a high dimensional space across distributed databases. DRNNA helps in minimizing the amount of data transferred between sites and hence provides data privacy and security for each site. Our approach aims to achieve valid results through minimum information disclosure. The data privacy at individual sites are preserved as our approach requires only minimal transmission of information between sites. Only a minimal count of higher-level summaries is exchanged for performing computations and therefore an intruder cannot obtain the actual data tuples even if they try to capture the exchanged summaries. The simulation results prove that the algorithm can correctly find the RNN set for a given point.","PeriodicalId":6799,"journal":{"name":"2021 18th International Multi-Conference on Systems, Signals & Devices (SSD)","volume":"12 1","pages":"681-686"},"PeriodicalIF":0.0,"publicationDate":"2021-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85248265","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}

引用次数: 5