Pub Date : 2024-07-02DOI: 10.1109/OJVT.2024.3422253
Mohammed Almehdhar;Abdullatif Albaseer;Muhammad Asif Khan;Mohamed Abdallah;Hamid Menouar;Saif Al-Kuwari;Ala Al-Fuqaha
The rapid evolution of modern automobiles into intelligent and interconnected entities presents new challenges in cybersecurity, particularly in Intrusion Detection Systems (IDS) for In-Vehicle Networks (IVNs). This survey paper offers an in-depth examination of advanced machine learning (ML) and deep learning (DL) approaches employed in developing sophisticated IDS for safeguarding IVNs against potential cyber-attacks. Specifically, we focus on the Controller Area Network (CAN) protocol, which is prevalent in in-vehicle communication systems, yet exhibits inherent security vulnerabilities. We propose a novel taxonomy categorizing IDS techniques into conventional ML, DL, and hybrid models, highlighting their applicability in detecting and mitigating various cyber threats, including spoofing, eavesdropping, and denial-of-service attacks. We highlight the transition from traditional signature-based to anomaly-based detection methods, emphasizing the significant advantages of AI-driven approaches in identifying novel and sophisticated intrusions. Our systematic review covers a range of AI algorithms, including traditional ML, and advanced neural network models, such as Transformers, illustrating their effectiveness in IDS applications within IVNs. Additionally, we explore emerging technologies, such as Federated Learning (FL) and Transfer Learning, to enhance the robustness and adaptability of IDS solutions. Based on our thorough analysis, we identify key limitations in current methodologies and propose potential paths for future research, focusing on integrating real-time data analysis, cross-layer security measures, and collaborative IDS frameworks.
{"title":"Deep Learning in the Fast Lane: A Survey on Advanced Intrusion Detection Systems for Intelligent Vehicle Networks","authors":"Mohammed Almehdhar;Abdullatif Albaseer;Muhammad Asif Khan;Mohamed Abdallah;Hamid Menouar;Saif Al-Kuwari;Ala Al-Fuqaha","doi":"10.1109/OJVT.2024.3422253","DOIUrl":"https://doi.org/10.1109/OJVT.2024.3422253","url":null,"abstract":"The rapid evolution of modern automobiles into intelligent and interconnected entities presents new challenges in cybersecurity, particularly in Intrusion Detection Systems (IDS) for In-Vehicle Networks (IVNs). This survey paper offers an in-depth examination of advanced machine learning (ML) and deep learning (DL) approaches employed in developing sophisticated IDS for safeguarding IVNs against potential cyber-attacks. Specifically, we focus on the Controller Area Network (CAN) protocol, which is prevalent in in-vehicle communication systems, yet exhibits inherent security vulnerabilities. We propose a novel taxonomy categorizing IDS techniques into conventional ML, DL, and hybrid models, highlighting their applicability in detecting and mitigating various cyber threats, including spoofing, eavesdropping, and denial-of-service attacks. We highlight the transition from traditional signature-based to anomaly-based detection methods, emphasizing the significant advantages of AI-driven approaches in identifying novel and sophisticated intrusions. Our systematic review covers a range of AI algorithms, including traditional ML, and advanced neural network models, such as Transformers, illustrating their effectiveness in IDS applications within IVNs. Additionally, we explore emerging technologies, such as Federated Learning (FL) and Transfer Learning, to enhance the robustness and adaptability of IDS solutions. Based on our thorough analysis, we identify key limitations in current methodologies and propose potential paths for future research, focusing on integrating real-time data analysis, cross-layer security measures, and collaborative IDS frameworks.","PeriodicalId":34270,"journal":{"name":"IEEE Open Journal of Vehicular Technology","volume":"5 ","pages":"869-906"},"PeriodicalIF":5.3,"publicationDate":"2024-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10582439","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141965266","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-06-28DOI: 10.1109/OJVT.2024.3420244
Eiman Elghanam;Akmal Abdelfatah;Mohamed S. Hassan;Ahmed H. Osman
The growing penetration of electric vehicles (EVs) and the increasing EV energy demand pose several challenges to the power grid, the power distribution networks and the transportation networks. This growing demand drives the need for effective demand management and energy coordination strategies to maximize the demand covered by the EV charging stations, ensure EV users' satisfaction and prevent grid-side overload. As a result, several optimization problems are formulated and solved in the literature to provide optimal EV charging schedules (i.e. temporal coordination) as well as optimal EV-to-charging-station assignments and routing plans (i.e. spatial coordination). This paper presents a review of the state-of-the-art literature on the utilization of different deterministic optimization techniques to develop optimal EV charging coordination strategies. In particular, these works are reviewed according to their domains of operation (i.e. time-based scheduling, spatial coordination, and spatio-temporal charging coordination), their respective objectives (user-, grid- and operator-related objectives), and the solution algorithms adopted to provide the corresponding optimal coordination plans. This helps in identifying key research gaps and provide recommendations for future research directions to develop comprehensive and computationally efficient charging coordination models.
{"title":"Optimization Techniques in Electric Vehicle Charging Scheduling, Routing and Spatio-Temporal Demand Coordination: A Systematic Review","authors":"Eiman Elghanam;Akmal Abdelfatah;Mohamed S. Hassan;Ahmed H. Osman","doi":"10.1109/OJVT.2024.3420244","DOIUrl":"https://doi.org/10.1109/OJVT.2024.3420244","url":null,"abstract":"The growing penetration of electric vehicles (EVs) and the increasing EV energy demand pose several challenges to the power grid, the power distribution networks and the transportation networks. This growing demand drives the need for effective demand management and energy coordination strategies to maximize the demand covered by the EV charging stations, ensure EV users' satisfaction and prevent grid-side overload. As a result, several optimization problems are formulated and solved in the literature to provide optimal EV charging schedules (i.e. temporal coordination) as well as optimal EV-to-charging-station assignments and routing plans (i.e. spatial coordination). This paper presents a review of the state-of-the-art literature on the utilization of different deterministic optimization techniques to develop optimal EV charging coordination strategies. In particular, these works are reviewed according to their domains of operation (i.e. time-based scheduling, spatial coordination, and spatio-temporal charging coordination), their respective objectives (user-, grid- and operator-related objectives), and the solution algorithms adopted to provide the corresponding optimal coordination plans. This helps in identifying key research gaps and provide recommendations for future research directions to develop comprehensive and computationally efficient charging coordination models.","PeriodicalId":34270,"journal":{"name":"IEEE Open Journal of Vehicular Technology","volume":"5 ","pages":"1294-1313"},"PeriodicalIF":5.3,"publicationDate":"2024-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10577180","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142274846","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-06-28DOI: 10.1109/OJVT.2024.3420224
Jyri Hämäläinen;Rui Dinis;Mehmet C. Ilter
Recently, the paradigm of massive ultra-reliable low-latency Internet of Things (IoT) communications (URLLC-IoT) has gained growing interest. Reliable delay-critical uplink transmission in vehicular IoT is a challenging task since low-complex devices typically do not support multiple antennas or demanding signal processing tasks. However, in many IoT services, the data volumes are small and deployments may include massive number of devices. For this kind of setup, we consider on a clustered uplink transmission with two cooperation approaches: First, we focus on scenario where location-based channel knowledge map (CKM) is applied to enable cooperation. Second, we consider a scenario where scarce channel side-information is applied inuplink transmission. In both scenarios we also model and analyse the impact of erroneous channel information. As being different from the existing literature, in the performance evaluation, we apply the recently introduced data-oriented approach in the context of short-packet transmissions over vehicular IoT networks. Specifically, it introduces a transient performance metric for small data transmissions the so-called delay outage rate (DOR), where the amount of data and available bandwidth play crucial roles. Results show that cooperation between clustered IoT devices may provide notable benefits in terms of increased range. It is noticed that the performance is heavily depending on the strength of the static channel component in the CKM-based cooperation. Also, it is shown that the channel side-information based cooperation is robust against changes in the radio environment but sensitive to possible errors in the channel side-information. Even with large IoT device clusters, side-information errors may set a limit for the use of services assuming high-reliability and low-latency where DOR is the relevant metric. The analytical derivations are validated through corresponding Monte Carlo numerical simulations, with only minor differences at low probability values.
{"title":"Data-Oriented Analysis of Uplink Transmission in Massive IoT System With Limited Channel Information","authors":"Jyri Hämäläinen;Rui Dinis;Mehmet C. Ilter","doi":"10.1109/OJVT.2024.3420224","DOIUrl":"https://doi.org/10.1109/OJVT.2024.3420224","url":null,"abstract":"Recently, the paradigm of massive ultra-reliable low-latency Internet of Things (IoT) communications (URLLC-IoT) has gained growing interest. Reliable delay-critical uplink transmission in vehicular IoT is a challenging task since low-complex devices typically do not support multiple antennas or demanding signal processing tasks. However, in many IoT services, the data volumes are small and deployments may include massive number of devices. For this kind of setup, we consider on a clustered uplink transmission with two cooperation approaches: First, we focus on scenario where location-based channel knowledge map (CKM) is applied to enable cooperation. Second, we consider a scenario where scarce channel side-information is applied inuplink transmission. In both scenarios we also model and analyse the impact of erroneous channel information. As being different from the existing literature, in the performance evaluation, we apply the recently introduced data-oriented approach in the context of short-packet transmissions over vehicular IoT networks. Specifically, it introduces a transient performance metric for small data transmissions the so-called delay outage rate (DOR), where the amount of data and available bandwidth play crucial roles. Results show that cooperation between clustered IoT devices may provide notable benefits in terms of increased range. It is noticed that the performance is heavily depending on the strength of the static channel component in the CKM-based cooperation. Also, it is shown that the channel side-information based cooperation is robust against changes in the radio environment but sensitive to possible errors in the channel side-information. Even with large IoT device clusters, side-information errors may set a limit for the use of services assuming high-reliability and low-latency where DOR is the relevant metric. The analytical derivations are validated through corresponding Monte Carlo numerical simulations, with only minor differences at low probability values.","PeriodicalId":34270,"journal":{"name":"IEEE Open Journal of Vehicular Technology","volume":"5 ","pages":"855-868"},"PeriodicalIF":5.3,"publicationDate":"2024-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10577226","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141729886","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-06-24DOI: 10.1109/OJVT.2024.3418201
Safa Hamdare;David J. Brown;Yue Cao;Mohammad Aljaidi;Omprakash Kaiwartya;Rahul Yadav;Pratik Vyas;Manish Jugran
The widespread adoption of Electric Vehicles (EV) has emphasized the urgent need for efficient and secure charging infrastructure. While existing research in EV charging infrastructure has primarily concentrated on minimizing charging time at charging stations (CSs), neglecting security-centric charging optimization, particularly with scaled charging infrastructure considering multiple CSs. To address this gap, this paper presents an enhanced Hybrid-Electric Vehicle Charging Management and Security (H-EVCMS) framework. The H-EVCMS framework is meticulously designed to optimize charging price, manage load balancing, and provide security across multiple CS by leveraging the Open Charge Point Protocol (OCPP). The proposed framework's performance is evaluated by examining various charging scenarios and analyzing the booking and power consumption patterns of each CS. The results demonstrate the advantages of the hybrid approach used by the proposed H-EVCMS over traditional charging infrastructure management, showcasing its potential to address the challenges of scaling EV charging infrastructure while ensuring security and efficiency.
{"title":"EV Charging Management and Security for Multi-Charging Stations Environment","authors":"Safa Hamdare;David J. Brown;Yue Cao;Mohammad Aljaidi;Omprakash Kaiwartya;Rahul Yadav;Pratik Vyas;Manish Jugran","doi":"10.1109/OJVT.2024.3418201","DOIUrl":"https://doi.org/10.1109/OJVT.2024.3418201","url":null,"abstract":"The widespread adoption of Electric Vehicles (EV) has emphasized the urgent need for efficient and secure charging infrastructure. While existing research in EV charging infrastructure has primarily concentrated on minimizing charging time at charging stations (CSs), neglecting security-centric charging optimization, particularly with scaled charging infrastructure considering multiple CSs. To address this gap, this paper presents an enhanced Hybrid-Electric Vehicle Charging Management and Security (H-EVCMS) framework. The H-EVCMS framework is meticulously designed to optimize charging price, manage load balancing, and provide security across multiple CS by leveraging the Open Charge Point Protocol (OCPP). The proposed framework's performance is evaluated by examining various charging scenarios and analyzing the booking and power consumption patterns of each CS. The results demonstrate the advantages of the hybrid approach used by the proposed H-EVCMS over traditional charging infrastructure management, showcasing its potential to address the challenges of scaling EV charging infrastructure while ensuring security and efficiency.","PeriodicalId":34270,"journal":{"name":"IEEE Open Journal of Vehicular Technology","volume":"5 ","pages":"807-824"},"PeriodicalIF":5.3,"publicationDate":"2024-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10569090","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141583486","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-06-06DOI: 10.1109/OJVT.2024.3410834
Toluwaleke Olutayo;Benoit Champagne
This article addresses the problem of symbol detection in time-varying Massive Multiple-Input Multiple-Output (M-MIMO) systems. While conventional detection techniques either exhibit subpar performance or impose excessive computational burdens in such systems, learning-based methods which have shown great potential in stationary scenarios, struggle to adapt to non-stationary conditions. To address these challenges, we introduce innovative extensions to the Learned Conjugate Gradient Network (LcgNet) M-MIMO detector. Firstly, we expound Preconditioned LcgNet (PrLcgNet), which incorporates a preconditioner during training to enhance the uplink M-MIMO detector's filter matrix. This modification enables the detector to achieve faster convergence with fewer layers compared to the original approach. Secondly, we introduce an adaptation of PrLcgNet referred to as Dynamic Conjugate Gradient Network (DyCoGNet), specifically designed for time-varying environments. DyCoGNet leverages self-supervised learning with Forward Error Correction (FEC), enabling autonomous adaptation without the need for explicit labeled data. It also employs meta-learning, facilitating rapid adaptation to unforeseen channel conditions. Our simulation results demonstrate that in stationary scenarios, PrLcgNet achieves faster convergence than LCgNet, which can be leveraged to reduce system complexity or improve Symbol Error Rate (SER) performance. Furthermore, in non-stationary scenarios, DyCoGNet exhibits rapid and efficient adaptation, achieving significant SER performance gains compared to baseline cases without meta-learning and a recent benchmark using self-supervised learning.
{"title":"Dynamic Conjugate Gradient Unfolding for Symbol Detection in Time-Varying Massive MIMO","authors":"Toluwaleke Olutayo;Benoit Champagne","doi":"10.1109/OJVT.2024.3410834","DOIUrl":"https://doi.org/10.1109/OJVT.2024.3410834","url":null,"abstract":"This article addresses the problem of symbol detection in time-varying Massive Multiple-Input Multiple-Output (M-MIMO) systems. While conventional detection techniques either exhibit subpar performance or impose excessive computational burdens in such systems, learning-based methods which have shown great potential in stationary scenarios, struggle to adapt to non-stationary conditions. To address these challenges, we introduce innovative extensions to the Learned Conjugate Gradient Network (LcgNet) M-MIMO detector. Firstly, we expound Preconditioned LcgNet (PrLcgNet), which incorporates a preconditioner during training to enhance the uplink M-MIMO detector's filter matrix. This modification enables the detector to achieve faster convergence with fewer layers compared to the original approach. Secondly, we introduce an adaptation of PrLcgNet referred to as Dynamic Conjugate Gradient Network (DyCoGNet), specifically designed for time-varying environments. DyCoGNet leverages self-supervised learning with Forward Error Correction (FEC), enabling autonomous adaptation without the need for explicit labeled data. It also employs meta-learning, facilitating rapid adaptation to unforeseen channel conditions. Our simulation results demonstrate that in stationary scenarios, PrLcgNet achieves faster convergence than LCgNet, which can be leveraged to reduce system complexity or improve Symbol Error Rate (SER) performance. Furthermore, in non-stationary scenarios, DyCoGNet exhibits rapid and efficient adaptation, achieving significant SER performance gains compared to baseline cases without meta-learning and a recent benchmark using self-supervised learning.","PeriodicalId":34270,"journal":{"name":"IEEE Open Journal of Vehicular Technology","volume":"5 ","pages":"792-806"},"PeriodicalIF":5.3,"publicationDate":"2024-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10551475","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141439460","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Sixth generation (6G) networks must guarantee radio-resource availability for coexisting users and machines. Here, non-orthogonal multiple access (NOMA) can address resource limitations by serving multiple devices on the same spectral and temporal resources. Meanwhile, cooperative relays can mitigate the impact with excessive large- and small-scale fading and interference. Still, to unlock the full potential of NOMA in 6G deployments, its performance must be analyzed under interference-limited scenarios with NOMA communications occuring across multiple cells. In this paper, the detrimental effect of co-channel interference (CCI) from nearby NOMA transmissions on a relay-aided NOMA network is examined. More specifically, randomly deployed CCI terminals communicate using NOMA and degrade the uplink communication. Network performance is thoroughly analyzed for various metrics, considering independent and identically distributed non-orthogonal CCI. Furthermore, for improved performance, transmit power, power allocation, and relay location optimization is presented. This scenario can correspond to Industry 4.0 settings, relying on private networks that can adjust the transmit power of interferers within the network. Our analytical findings are verified through Monte-Carlo simulations, revealing that non-orthogonal CCI degrades the system performance, causing system coding gain losses. Nonetheless, the proposed optimization framework can mitigate the impact of non-orthogonal CCI and ensure improved uplink performance.
第六代（6G）网络必须保证共存用户和机器的无线电资源可用性。在这方面，非正交多址接入（NOMA）可以通过在相同的频谱和时间资源上为多个设备提供服务来解决资源限制问题。同时，合作中继可减轻大、小范围过度衰落和干扰的影响。不过，要在 6G 部署中释放 NOMA 的全部潜力，必须分析其在干扰受限场景下的性能，即 NOMA 通信跨越多个小区。本文研究了来自附近 NOMA 传输的同信道干扰（CCI）对中继辅助 NOMA 网络的不利影响。更具体地说，随机部署的 CCI 终端使用 NOMA 进行通信，会降低上行链路通信性能。考虑到独立且同分布的非正交 CCI，针对各种指标对网络性能进行了全面分析。此外，为了提高性能，还介绍了发射功率、功率分配和中继位置优化。这种情况可以对应工业 4.0 的设置，依赖于可以调整网络内干扰者发射功率的专用网络。通过蒙特卡洛模拟验证了我们的分析结果，发现非正交 CCI 会降低系统性能，造成系统编码增益损失。然而，所提出的优化框架可以减轻非正交 CCI 的影响，确保改善上行链路性能。
{"title":"Relay-Aided Uplink NOMA Under Non-Orthogonal CCI and Imperfect SIC in 6G Networks","authors":"Volkan Özduran;Nikolaos Nomikos;Ehsan Soleimani-Nasab;Imran Shafique Ansari;Panagiotis Trakadas","doi":"10.1109/OJVT.2024.3392951","DOIUrl":"https://doi.org/10.1109/OJVT.2024.3392951","url":null,"abstract":"Sixth generation (6G) networks must guarantee radio-resource availability for coexisting users and machines. Here, non-orthogonal multiple access (NOMA) can address resource limitations by serving multiple devices on the same spectral and temporal resources. Meanwhile, cooperative relays can mitigate the impact with excessive large- and small-scale fading and interference. Still, to unlock the full potential of NOMA in 6G deployments, its performance must be analyzed under interference-limited scenarios with NOMA communications occuring across multiple cells. In this paper, the detrimental effect of co-channel interference (CCI) from nearby NOMA transmissions on a relay-aided NOMA network is examined. More specifically, randomly deployed CCI terminals communicate using NOMA and degrade the uplink communication. Network performance is thoroughly analyzed for various metrics, considering independent and identically distributed non-orthogonal CCI. Furthermore, for improved performance, transmit power, power allocation, and relay location optimization is presented. This scenario can correspond to Industry 4.0 settings, relying on private networks that can adjust the transmit power of interferers within the network. Our analytical findings are verified through Monte-Carlo simulations, revealing that non-orthogonal CCI degrades the system performance, causing system coding gain losses. Nonetheless, the proposed optimization framework can mitigate the impact of non-orthogonal CCI and ensure improved uplink performance.","PeriodicalId":34270,"journal":{"name":"IEEE Open Journal of Vehicular Technology","volume":"5 ","pages":"658-680"},"PeriodicalIF":6.4,"publicationDate":"2024-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10508052","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140950957","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-19DOI: 10.1109/OJVT.2024.3391380
Muhammad Haris;Dost Muhammad Saqib Bhatti;Haewoon Nam
Particle Swarm Optimization (PSO) stands as a cornerstone among population-based swarm intelligence algorithms, serving as a versatile tool to tackle diverse scientific and engineering optimization challenges due to its straightforward implementation and promising optimization capabilities. Nonetheless, PSO has its limitations, notably its propensity for slow convergence. Traditionally, PSO operates by guiding swarms through positions determined by their initial velocities and acceleration components, encompassing cognitive and social information. In pursuit of expedited convergence, we introduce a novel approach: the Cognitive and Social Information-Based Hyperbolic Tangent Particle Swarm Optimization (HT-PSO) algorithm. This innovation draws inspiration from the activation functions employed in neural networks, with the singular aim of accelerating convergence. To combat the issue of slow convergence, we reengineer the cognitive and social acceleration coefficients of the PSO algorithm, leveraging the power of the hyperbolic tangent function. This strategic adjustment fosters a dynamic balance between exploration and exploitation, unleashing PSO's full potential. Our experimental trials encompass thirteen benchmark functions spanning unimodal and multimodal landscapes. Besides that, the proposed algorithm is also applied to different UAV path planning scenarios, underscoring its real-world relevance. The outcomes underscore the prowess of HT-PSO, showcasing significantly better convergence rates compared to the state-of-the-art.
{"title":"A Fast-Convergent Hyperbolic Tangent PSO Algorithm for UAVs Path Planning","authors":"Muhammad Haris;Dost Muhammad Saqib Bhatti;Haewoon Nam","doi":"10.1109/OJVT.2024.3391380","DOIUrl":"https://doi.org/10.1109/OJVT.2024.3391380","url":null,"abstract":"Particle Swarm Optimization (PSO) stands as a cornerstone among population-based swarm intelligence algorithms, serving as a versatile tool to tackle diverse scientific and engineering optimization challenges due to its straightforward implementation and promising optimization capabilities. Nonetheless, PSO has its limitations, notably its propensity for slow convergence. Traditionally, PSO operates by guiding swarms through positions determined by their initial velocities and acceleration components, encompassing cognitive and social information. In pursuit of expedited convergence, we introduce a novel approach: the Cognitive and Social Information-Based Hyperbolic Tangent Particle Swarm Optimization (HT-PSO) algorithm. This innovation draws inspiration from the activation functions employed in neural networks, with the singular aim of accelerating convergence. To combat the issue of slow convergence, we reengineer the cognitive and social acceleration coefficients of the PSO algorithm, leveraging the power of the hyperbolic tangent function. This strategic adjustment fosters a dynamic balance between exploration and exploitation, unleashing PSO's full potential. Our experimental trials encompass thirteen benchmark functions spanning unimodal and multimodal landscapes. Besides that, the proposed algorithm is also applied to different UAV path planning scenarios, underscoring its real-world relevance. The outcomes underscore the prowess of HT-PSO, showcasing significantly better convergence rates compared to the state-of-the-art.","PeriodicalId":34270,"journal":{"name":"IEEE Open Journal of Vehicular Technology","volume":"5 ","pages":"681-694"},"PeriodicalIF":6.4,"publicationDate":"2024-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10505768","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141096361","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-18DOI: 10.1109/OJVT.2024.3390833
Constantinos M. Mylonakis;Zaharias D. Zaharis
This article aims to constitute a noteworthy contribution to the domain of direction-of-arrival (DoA) estimation through the application of deep learning algorithms. We approach the DoA estimation challenge as a binary classification task, employing a novel grid in the output layer and a deep convolutional neural network (DCNN) as the classifier. The input of the DCNN is the correlation matrix of signals received by a $4 times 4$ uniformly spaced patch antenna array. The proposed model's performance is evaluated based on its capacity to predict angles of arrival from any direction in a three-dimensional space, encompassing azimuth angles within the interval $[0^circ, 360^circ)$ and polar angles within $[0^circ, 60^circ ]$ . We aim to optimize the utilization of spatial information and create a robust, precise, and efficient DoA estimator. To address this, we conduct comprehensive testing in diverse scenarios, encompassing the simultaneous reception of multiple signals across a wide range of signal-to-noise ratio values. Both mean absolute error and root mean squared error are calculated to assess the performance of the DCNN. Rigorous comparison with conventional and state-of-the-art endeavors emphasizes the proposed model's efficacy.
{"title":"A Novel Three-Dimensional Direction-of-Arrival Estimation Approach Using a Deep Convolutional Neural Network","authors":"Constantinos M. Mylonakis;Zaharias D. Zaharis","doi":"10.1109/OJVT.2024.3390833","DOIUrl":"https://doi.org/10.1109/OJVT.2024.3390833","url":null,"abstract":"This article aims to constitute a noteworthy contribution to the domain of direction-of-arrival (DoA) estimation through the application of deep learning algorithms. We approach the DoA estimation challenge as a binary classification task, employing a novel grid in the output layer and a deep convolutional neural network (DCNN) as the classifier. The input of the DCNN is the correlation matrix of signals received by a \u0000<inline-formula><tex-math>$4 times 4$</tex-math></inline-formula>\u0000 uniformly spaced patch antenna array. The proposed model's performance is evaluated based on its capacity to predict angles of arrival from any direction in a three-dimensional space, encompassing azimuth angles within the interval \u0000<inline-formula><tex-math>$[0^circ, 360^circ)$</tex-math></inline-formula>\u0000 and polar angles within \u0000<inline-formula><tex-math>$[0^circ, 60^circ ]$</tex-math></inline-formula>\u0000. We aim to optimize the utilization of spatial information and create a robust, precise, and efficient DoA estimator. To address this, we conduct comprehensive testing in diverse scenarios, encompassing the simultaneous reception of multiple signals across a wide range of signal-to-noise ratio values. Both mean absolute error and root mean squared error are calculated to assess the performance of the DCNN. Rigorous comparison with conventional and state-of-the-art endeavors emphasizes the proposed model's efficacy.","PeriodicalId":34270,"journal":{"name":"IEEE Open Journal of Vehicular Technology","volume":"5 ","pages":"643-657"},"PeriodicalIF":6.4,"publicationDate":"2024-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10504989","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140906933","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-17DOI: 10.1109/OJVT.2024.3390204
João Madeira;Zahra Mokhtari;João Guerreiro;Rui Dinis
Is is widely known that the power consumption of Analog-to-Digital Converters (ADCs) is strongly related with the number of bits of resolution. Using smaller resolutions can greatly reduce the power consumption of the RX frontend. However, the use of low-resolution ADCs introduces significant nonlinear distortion, especially when Orthogonal Frequency Division Multiplexing (OFDM) signals are employed, which might severely degrade performance. In this work, we consider nonlinear effects at the receiver side, associated with quantization and saturation of low-resolution ADCs, and we propose a Generalized Approximate Message Passing (GAMP) receiver that is specially designed to cope with nonlinear effects at the OFDM receiver. We show that our receiver can significantly mitigate the distortion that arises from low-resolution ADCs, allowing larger M-ary Quadrature Amplitude Modulation (M-QAM) constellations to be employed. The proposed receiver is shown to be robust to strong channel fading effects, as well as errors during the channel estimation process.
{"title":"Receiver Design for OFDM Schemes With Low-Resolution ADCs","authors":"João Madeira;Zahra Mokhtari;João Guerreiro;Rui Dinis","doi":"10.1109/OJVT.2024.3390204","DOIUrl":"https://doi.org/10.1109/OJVT.2024.3390204","url":null,"abstract":"Is is widely known that the power consumption of Analog-to-Digital Converters (ADCs) is strongly related with the number of bits of resolution. Using smaller resolutions can greatly reduce the power consumption of the RX frontend. However, the use of low-resolution ADCs introduces significant nonlinear distortion, especially when Orthogonal Frequency Division Multiplexing (OFDM) signals are employed, which might severely degrade performance. In this work, we consider nonlinear effects at the receiver side, associated with quantization and saturation of low-resolution ADCs, and we propose a Generalized Approximate Message Passing (GAMP) receiver that is specially designed to cope with nonlinear effects at the OFDM receiver. We show that our receiver can significantly mitigate the distortion that arises from low-resolution ADCs, allowing larger M-ary Quadrature Amplitude Modulation (M-QAM) constellations to be employed. The proposed receiver is shown to be robust to strong channel fading effects, as well as errors during the channel estimation process.","PeriodicalId":34270,"journal":{"name":"IEEE Open Journal of Vehicular Technology","volume":"5 ","pages":"632-642"},"PeriodicalIF":6.4,"publicationDate":"2024-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10504423","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140818773","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-12DOI: 10.1109/OJVT.2024.3387414
Oumaima Barhoumi;Mohamed H. Zaki;Sofiéné Tahar
Traffic conflict techniques enable a comprehensive assessment of traffic safety analysis. Formal methods allow the identification of factors that contribute to traffic safety issues and provide evidence of potential safety degradation. As such, formal methods provide a novel way to model traffic rules and verify road users' compliance. The paper proposes formalizing a traffic safety rule in differential dynamic logic and using KeYmaera theorem prover for verification. This rule considers time-to-collision (TTC), space headway (SHW), and shockwave speed (SWV). To validate the effectiveness of this rule in realistic traffic scenarios, we conducted a study using calibrated microsimulation data from the SR528 highway in Orlando, Florida. Our analysis examined the TTC, SHW, and SWV values for vehicle platoons on the highway and demonstrated how smaller TTC and SHW values indicate shockwaves and subsequent conflicts. Furthermore, we observed that shockwave speed could contribute to traffic conflicts by enabling evasive actions such as sudden braking or lane changes as the risk of collisions increases. By highlighting these findings, we aim to provide valuable insights into the real-world applicability of formal methods for traffic safety and their potential in promoting safer driving practices that can help create reliable autonomous vehicle control systems.
{"title":"A Formal Approach to Road Safety Assessment Using Traffic Conflict Techniques","authors":"Oumaima Barhoumi;Mohamed H. Zaki;Sofiéné Tahar","doi":"10.1109/OJVT.2024.3387414","DOIUrl":"https://doi.org/10.1109/OJVT.2024.3387414","url":null,"abstract":"Traffic conflict techniques enable a comprehensive assessment of traffic safety analysis. Formal methods allow the identification of factors that contribute to traffic safety issues and provide evidence of potential safety degradation. As such, formal methods provide a novel way to model traffic rules and verify road users' compliance. The paper proposes formalizing a traffic safety rule in differential dynamic logic and using KeYmaera theorem prover for verification. This rule considers time-to-collision (TTC), space headway (SHW), and shockwave speed (SWV). To validate the effectiveness of this rule in realistic traffic scenarios, we conducted a study using calibrated microsimulation data from the SR528 highway in Orlando, Florida. Our analysis examined the TTC, SHW, and SWV values for vehicle platoons on the highway and demonstrated how smaller TTC and SHW values indicate shockwaves and subsequent conflicts. Furthermore, we observed that shockwave speed could contribute to traffic conflicts by enabling evasive actions such as sudden braking or lane changes as the risk of collisions increases. By highlighting these findings, we aim to provide valuable insights into the real-world applicability of formal methods for traffic safety and their potential in promoting safer driving practices that can help create reliable autonomous vehicle control systems.","PeriodicalId":34270,"journal":{"name":"IEEE Open Journal of Vehicular Technology","volume":"5 ","pages":"606-619"},"PeriodicalIF":6.4,"publicationDate":"2024-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10496854","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140648045","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","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：