Pub Date : 2022-12-27DOI: 10.1109/ICCSPA55860.2022.10019201
Noha Ghatwary, Ahmed A. Alzughaibi, Ahmed Kantoush, A. Eltawil, Mohamed Ramadan, Mohamed Yasser
Visual impairments pose a parsing need to develop new automated systems to assist persons presenting visual impairments. The visual impairments have trouble interacting and sensing their surroundings. Their movement is limited and has to rely on a guided stick for them to move safely from one place to another. However, traditional canes have the disadvantage of failing to detect far-away obstacles and small objects. Therefore, this project is proposed to design and develop an Intelligent Assistance System for Visually Impaired People (ISVB). Our proposed system is composed of three interconnected parts, a smart cap, a 3D-printed intelligent cane and a mobile application that connects the system through an online server. The smart cap uses the Raspberry Pi and camera module, along with a deep learning object detection module for obstacle detection. The intelligent cane will provide the feasibility for the visually impaired person to walk without encountering problems by analyzing the surrounding environment through a microcontroller with multiple sensors and a bluetooth module. The mobile application interacts with the cap and the cane. Additionally, it will provide virtual navigation to help visually impaired people in their movement. To evaluate the performance of the system, different experiments for object detection, sensors and mobile applications have been conducted. The overall performance of the model showed an efficiency of 94.6 %.
{"title":"Intelligent Assistance System for Visually Impaired/Blind People (ISVB)","authors":"Noha Ghatwary, Ahmed A. Alzughaibi, Ahmed Kantoush, A. Eltawil, Mohamed Ramadan, Mohamed Yasser","doi":"10.1109/ICCSPA55860.2022.10019201","DOIUrl":"https://doi.org/10.1109/ICCSPA55860.2022.10019201","url":null,"abstract":"Visual impairments pose a parsing need to develop new automated systems to assist persons presenting visual impairments. The visual impairments have trouble interacting and sensing their surroundings. Their movement is limited and has to rely on a guided stick for them to move safely from one place to another. However, traditional canes have the disadvantage of failing to detect far-away obstacles and small objects. Therefore, this project is proposed to design and develop an Intelligent Assistance System for Visually Impaired People (ISVB). Our proposed system is composed of three interconnected parts, a smart cap, a 3D-printed intelligent cane and a mobile application that connects the system through an online server. The smart cap uses the Raspberry Pi and camera module, along with a deep learning object detection module for obstacle detection. The intelligent cane will provide the feasibility for the visually impaired person to walk without encountering problems by analyzing the surrounding environment through a microcontroller with multiple sensors and a bluetooth module. The mobile application interacts with the cap and the cane. Additionally, it will provide virtual navigation to help visually impaired people in their movement. To evaluate the performance of the system, different experiments for object detection, sensors and mobile applications have been conducted. The overall performance of the model showed an efficiency of 94.6 %.","PeriodicalId":106639,"journal":{"name":"2022 5th International Conference on Communications, Signal Processing, and their Applications (ICCSPA)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124182796","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}
Pub Date : 2022-12-27DOI: 10.1109/ICCSPA55860.2022.10019122
Khawla A. Alnajjar, S. Ghunaim, Samreen Ansari
Due to the evolution and availability of vast amounts of data for transferring, receiving, and detection, the field of signal recognition and modulation classification has become vital in various fields and applications. Additionally, the classical approaches to machine learning (ML) no more can satisfy the current needs. Hence, this urged researchers to apply deep learning (DL) algorithms that have a very strong ability to train, learn, and automatically classify types of modulation categories. This paper focuses on three vital DL network algorithms, which are deep neural networks (DNN), convolutional neural networks (CNN), and deep belief networks (DBN). The mentioned algorithms are widely used in many applications for automatic modulation classification/recognition (AMC/AMR). Additionally, an empirical study is performed in this paper to compare a large number of different methods for the performance and recognition percentage of each considered technique.
{"title":"Automatic Modulation Classification in Deep Learning","authors":"Khawla A. Alnajjar, S. Ghunaim, Samreen Ansari","doi":"10.1109/ICCSPA55860.2022.10019122","DOIUrl":"https://doi.org/10.1109/ICCSPA55860.2022.10019122","url":null,"abstract":"Due to the evolution and availability of vast amounts of data for transferring, receiving, and detection, the field of signal recognition and modulation classification has become vital in various fields and applications. Additionally, the classical approaches to machine learning (ML) no more can satisfy the current needs. Hence, this urged researchers to apply deep learning (DL) algorithms that have a very strong ability to train, learn, and automatically classify types of modulation categories. This paper focuses on three vital DL network algorithms, which are deep neural networks (DNN), convolutional neural networks (CNN), and deep belief networks (DBN). The mentioned algorithms are widely used in many applications for automatic modulation classification/recognition (AMC/AMR). Additionally, an empirical study is performed in this paper to compare a large number of different methods for the performance and recognition percentage of each considered technique.","PeriodicalId":106639,"journal":{"name":"2022 5th International Conference on Communications, Signal Processing, and their Applications (ICCSPA)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127009408","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}
Pub Date : 2022-12-27DOI: 10.1109/ICCSPA55860.2022.10018968
M. Sultan, Hesham El-Sayed, M. A. Khan
A Mobil Ad hoc Network (MANET) is a dynamic multi-hop infrastructure-less wireless network that comprises of a collection of mobile, self-organized, self-configured wireless nodes. A routing protocol in MANET is used to find routes between mobile nodes to facilitate communication within the network. Numerous routing protocols have been proposed for MANET. Those routing protocols are designed to adaptively accommodate for dynamic unpredictable changes in network's topology. MANET characteristics such as openness, restricted resources and decentralization impact node's efficiency and made it easy to be affected by various security attacks, especially the Distributed Denial of Service (DDoS) attacks. These DDoS attacks consume all system resources like battery power, bandwidth, energy, CPU, and render those resources and nodes unavailable to the legitimate users. The aim of this research is to implement a simulation model called Distributed Denial of Service Simulation Model (DDoS-Sim) to examine the effect of DDoS attack on various routing protocols in MANETs namely: Ad hoc On-Demand Distance Vector (AODV), Dynamic Source Routing (DSR) and Destination-Sequenced Distance-Vector (DSDV). These routing protocols follow the reactive and proactive routing algorithms. The introduced model uses the network simulator 2 (NS-2) to apply DDoS on the three selected routing protocols. The performance of routings protocols was analyzed under the consequences of the attack in terms of packet delivery fraction and end-to-end delay.
{"title":"Performance Analysis of the Impact of DDoS Attack on Routing Protocols in Infrastructure-less Mobile Networks","authors":"M. Sultan, Hesham El-Sayed, M. A. Khan","doi":"10.1109/ICCSPA55860.2022.10018968","DOIUrl":"https://doi.org/10.1109/ICCSPA55860.2022.10018968","url":null,"abstract":"A Mobil Ad hoc Network (MANET) is a dynamic multi-hop infrastructure-less wireless network that comprises of a collection of mobile, self-organized, self-configured wireless nodes. A routing protocol in MANET is used to find routes between mobile nodes to facilitate communication within the network. Numerous routing protocols have been proposed for MANET. Those routing protocols are designed to adaptively accommodate for dynamic unpredictable changes in network's topology. MANET characteristics such as openness, restricted resources and decentralization impact node's efficiency and made it easy to be affected by various security attacks, especially the Distributed Denial of Service (DDoS) attacks. These DDoS attacks consume all system resources like battery power, bandwidth, energy, CPU, and render those resources and nodes unavailable to the legitimate users. The aim of this research is to implement a simulation model called Distributed Denial of Service Simulation Model (DDoS-Sim) to examine the effect of DDoS attack on various routing protocols in MANETs namely: Ad hoc On-Demand Distance Vector (AODV), Dynamic Source Routing (DSR) and Destination-Sequenced Distance-Vector (DSDV). These routing protocols follow the reactive and proactive routing algorithms. The introduced model uses the network simulator 2 (NS-2) to apply DDoS on the three selected routing protocols. The performance of routings protocols was analyzed under the consequences of the attack in terms of packet delivery fraction and end-to-end delay.","PeriodicalId":106639,"journal":{"name":"2022 5th International Conference on Communications, Signal Processing, and their Applications (ICCSPA)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127856989","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}
Pub Date : 2022-12-27DOI: 10.1109/ICCSPA55860.2022.10019062
M. Abdelazeem
Presently, Galileo satellites are transmitting multi-frequency signals which provides opportunity to enhance Galileo precise point positioning (PPP) accuracy. The objective of this research is to investigate the performance of real-time Galileo-only PPP solution using the Galileo open service (OS) E1, E5a, E5b and E5 signals. Different dual-frequency ionosphere-free Galileo-only PPP processing models are used including, the E1/E5a PPP, E1/E5b PPP and E1/E5 PPP. The real-time precise orbit and clock products available from the Centre National d'Etudes Spatiales (CNES) are used in order to simulate the real-time mode. GPS/Galileo observations, spanning three successive days, from a number of globally distributed reference stations are acquired. Then, the datasets are processed using real-time PPP solution in static and semi-kinematic modes. The traditional real-time GPS L1/L2 PPP solution is used as a reference. The estimated convergence time and positioning accuracy is assessed and then compared with the GPS L1/L2 PPP solution counterparts. It is found that the overall 3D positioning accuracy is enhanced by about 11%, 6% and 8% for the Galileo E1/E5a PPP, E1/E5b PPP and E1/E5 PPP solutions, respectively, with respect to the GPS PPP solution counterparts in static mode. Additionally, improvements in the 3D position by about 25%, 11% and 17% are acquired from the Galileo E1/E5a PPP, E1/E5b PPP and E1/E5 PPP solutions, respectively, compared with the GPS L1/L2 PPP solution in semi-kinematic mode.
{"title":"Performance Analysis of Real-Time Galileo Precise Point Positioning Using Different Dual-Frequency Ionosphere-Free Combinations","authors":"M. Abdelazeem","doi":"10.1109/ICCSPA55860.2022.10019062","DOIUrl":"https://doi.org/10.1109/ICCSPA55860.2022.10019062","url":null,"abstract":"Presently, Galileo satellites are transmitting multi-frequency signals which provides opportunity to enhance Galileo precise point positioning (PPP) accuracy. The objective of this research is to investigate the performance of real-time Galileo-only PPP solution using the Galileo open service (OS) E1, E5a, E5b and E5 signals. Different dual-frequency ionosphere-free Galileo-only PPP processing models are used including, the E1/E5a PPP, E1/E5b PPP and E1/E5 PPP. The real-time precise orbit and clock products available from the Centre National d'Etudes Spatiales (CNES) are used in order to simulate the real-time mode. GPS/Galileo observations, spanning three successive days, from a number of globally distributed reference stations are acquired. Then, the datasets are processed using real-time PPP solution in static and semi-kinematic modes. The traditional real-time GPS L1/L2 PPP solution is used as a reference. The estimated convergence time and positioning accuracy is assessed and then compared with the GPS L1/L2 PPP solution counterparts. It is found that the overall 3D positioning accuracy is enhanced by about 11%, 6% and 8% for the Galileo E1/E5a PPP, E1/E5b PPP and E1/E5 PPP solutions, respectively, with respect to the GPS PPP solution counterparts in static mode. Additionally, improvements in the 3D position by about 25%, 11% and 17% are acquired from the Galileo E1/E5a PPP, E1/E5b PPP and E1/E5 PPP solutions, respectively, compared with the GPS L1/L2 PPP solution in semi-kinematic mode.","PeriodicalId":106639,"journal":{"name":"2022 5th International Conference on Communications, Signal Processing, and their Applications (ICCSPA)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132658008","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}
Pub Date : 2022-11-20DOI: 10.1109/ICCSPA55860.2022.10018994
Mahmoud Selim, Amr Alanwar, M. El-Kharashi, Hazem Abbas, K. Johansson
Reinforcement learning (RL) algorithms can achieve state-of-the-art performance in decision-making and continuous control tasks. However, applying RL algorithms on safety-critical systems still needs to be well justified due to the exploration nature of many RL algorithms, especially when the model of the robot and the environment are unknown. To address this challenge, we propose a data-driven safety layer that acts as a filter for unsafe actions. The safety layer uses a data-driven predictive controller to enforce safety guarantees for RL policies during training and after deployment. The RL agent proposes an action that is verified by computing the data-driven reachability analysis. If there is an intersection between the reachable set of the robot using the proposed action, we call the data-driven predictive controller to find the closest safe action to the proposed unsafe action. The safety layer penalizes the RL agent if the proposed action is unsafe and replaces it with the closest safe one. In the simulation, we show that our method outperforms state-of-the-art safe RL methods on the robotics navigation problem for a Turtlebot 3 in Gazebo and a quadrotor in Unreal Engine 4 (UE4).
{"title":"Safe Reinforcement Learning using Data-Driven Predictive Control","authors":"Mahmoud Selim, Amr Alanwar, M. El-Kharashi, Hazem Abbas, K. Johansson","doi":"10.1109/ICCSPA55860.2022.10018994","DOIUrl":"https://doi.org/10.1109/ICCSPA55860.2022.10018994","url":null,"abstract":"Reinforcement learning (RL) algorithms can achieve state-of-the-art performance in decision-making and continuous control tasks. However, applying RL algorithms on safety-critical systems still needs to be well justified due to the exploration nature of many RL algorithms, especially when the model of the robot and the environment are unknown. To address this challenge, we propose a data-driven safety layer that acts as a filter for unsafe actions. The safety layer uses a data-driven predictive controller to enforce safety guarantees for RL policies during training and after deployment. The RL agent proposes an action that is verified by computing the data-driven reachability analysis. If there is an intersection between the reachable set of the robot using the proposed action, we call the data-driven predictive controller to find the closest safe action to the proposed unsafe action. The safety layer penalizes the RL agent if the proposed action is unsafe and replaces it with the closest safe one. In the simulation, we show that our method outperforms state-of-the-art safe RL methods on the robotics navigation problem for a Turtlebot 3 in Gazebo and a quadrotor in Unreal Engine 4 (UE4).","PeriodicalId":106639,"journal":{"name":"2022 5th International Conference on Communications, Signal Processing, and their Applications (ICCSPA)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125427696","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}
Pub Date : 2022-11-02DOI: 10.1109/ICCSPA55860.2022.10019001
Ziyou Ren, Nan Cheng, Ruijin Sun, Xiucheng Wang, N. Lu, Wenchao Xu
Multiple-input multiple-output and orthogonal frequency-division multiplexing (MIMO-OFDM) are the key technologies in 4G and subsequent wireless communication systems. Conventionally, the MIMO-OFDM receiver is performed by multiple cascaded blocks with different functions and the algorithm in each block is designed based on ideal assumptions of wireless channel distributions. However, these assumptions may fail in practical complex wireless environments. The deep learning (DL) method has the ability to capture key features from complex and huge data. In this paper, a novel end-to-end MIMO-OFDM receiver framework based on transformer, named SigT, is proposed. By regarding the signal received from each antenna as a token of the transformer, the spatial correlation of different antennas can be learned and the critical zero-shot problem can be mitigated. Furthermore, the proposed SigT framework can work well without the inserted pilots, which improves the useful data transmission efficiency. Experiment results show that SigT achieves much higher performance in terms of signal recovery accuracy than benchmark methods, even in a low SNR environment or with a small number of training samples. Code is available at https://github.com/SigTransformer/SigT.
{"title":"SigT: An Efficient End-to-End MIMO-OFDM Receiver Framework Based on Transformer","authors":"Ziyou Ren, Nan Cheng, Ruijin Sun, Xiucheng Wang, N. Lu, Wenchao Xu","doi":"10.1109/ICCSPA55860.2022.10019001","DOIUrl":"https://doi.org/10.1109/ICCSPA55860.2022.10019001","url":null,"abstract":"Multiple-input multiple-output and orthogonal frequency-division multiplexing (MIMO-OFDM) are the key technologies in 4G and subsequent wireless communication systems. Conventionally, the MIMO-OFDM receiver is performed by multiple cascaded blocks with different functions and the algorithm in each block is designed based on ideal assumptions of wireless channel distributions. However, these assumptions may fail in practical complex wireless environments. The deep learning (DL) method has the ability to capture key features from complex and huge data. In this paper, a novel end-to-end MIMO-OFDM receiver framework based on transformer, named SigT, is proposed. By regarding the signal received from each antenna as a token of the transformer, the spatial correlation of different antennas can be learned and the critical zero-shot problem can be mitigated. Furthermore, the proposed SigT framework can work well without the inserted pilots, which improves the useful data transmission efficiency. Experiment results show that SigT achieves much higher performance in terms of signal recovery accuracy than benchmark methods, even in a low SNR environment or with a small number of training samples. Code is available at https://github.com/SigTransformer/SigT.","PeriodicalId":106639,"journal":{"name":"2022 5th International Conference on Communications, Signal Processing, and their Applications (ICCSPA)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124973790","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}
Pub Date : 2022-08-11DOI: 10.1109/ICCSPA55860.2022.10019108
Mhd Saria Allahham, Amr Mohamed, A. Erbad, H. Hassanein
Extreme edge computing (EEC) refers to the end-most part of edge computing wherein computational tasks and edge services are deployed only on extreme edge devices (EEDs). EEDs are consumer or user-owned devices that offer computational resources, which may consist of wearable devices, personal mobile devices, drones, etc. Such devices are opportunistically or naturally present within the proximity of other user devices. Hence, utilizing EEDs to deploy edge services or perform computational tasks fulfills the promise of edge computing of bringing the services and computation as close as possible to the end-users. However, the lack of knowledge and control over the EEDs computational resources raises a red flag, since executing the computational tasks successfully becomes doubtful. To this end, we aim to study the EEDs randomness from the computational perspective, and how reliable is an EED in terms of executing the tasks on time. Specifically, we provide a reliability model for the EEDs that takes into account the probabilistic nature of the availability of the EEDs' computational resources. Moreover, we study the reliability of executing different types of computational tasks in EEC systems that are distributed across the EEDs. Lastly, we carry out experimental results to analyze the EEDs and the EEC systems' reliability behavior in different scenarios.
{"title":"On the Modeling of Reliability in Extreme Edge Computing Systems","authors":"Mhd Saria Allahham, Amr Mohamed, A. Erbad, H. Hassanein","doi":"10.1109/ICCSPA55860.2022.10019108","DOIUrl":"https://doi.org/10.1109/ICCSPA55860.2022.10019108","url":null,"abstract":"Extreme edge computing (EEC) refers to the end-most part of edge computing wherein computational tasks and edge services are deployed only on extreme edge devices (EEDs). EEDs are consumer or user-owned devices that offer computational resources, which may consist of wearable devices, personal mobile devices, drones, etc. Such devices are opportunistically or naturally present within the proximity of other user devices. Hence, utilizing EEDs to deploy edge services or perform computational tasks fulfills the promise of edge computing of bringing the services and computation as close as possible to the end-users. However, the lack of knowledge and control over the EEDs computational resources raises a red flag, since executing the computational tasks successfully becomes doubtful. To this end, we aim to study the EEDs randomness from the computational perspective, and how reliable is an EED in terms of executing the tasks on time. Specifically, we provide a reliability model for the EEDs that takes into account the probabilistic nature of the availability of the EEDs' computational resources. Moreover, we study the reliability of executing different types of computational tasks in EEC systems that are distributed across the EEDs. Lastly, we carry out experimental results to analyze the EEDs and the EEC systems' reliability behavior in different scenarios.","PeriodicalId":106639,"journal":{"name":"2022 5th International Conference on Communications, Signal Processing, and their Applications (ICCSPA)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116392894","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：