Ad Hoc Networks最新文献_第2页

Cross-layer UAV network routing protocol for spectrum denial environments 针对频谱拒绝环境的跨层无人机网络路由协议

IF 4.4 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Ad Hoc Networks

Pub Date : 2024-11-09 DOI: 10.1016/j.adhoc.2024.103702

Siyue Zheng , Xiaojun Zhu , Zhengrui Qin , Chao Dong

Unmanned Aerial Vehicles (UAVs), which connect to one another over wireless networks, are being used in warfare more frequently. Nevertheless, adversarial interference has the potential to disrupt wireless communication, and the UAV routing methods in use today struggle to handle interference. In this paper, we propose a Cross-Layer UAV Link State Routing protocol, CLUN-LSR, to combat against jamming attacks. CLUN-LSR features three designs. First, it obtains real-time spectrum status from the link layer. Such capabilities are provided by many existing radios, especially the ones in military applications, but are ignored by traditional routing protocols. Second, based on the cross-layer information, CLUN-LSR adds efficient routing functions during routing, including the use of the number of two-hop neighbor nodes as a metric for route selection. Third, CLUN-LSR selects nodes that are not in the interference area, thereby reducing network interruptions and improving data transmission efficiency. All table-driven routing protocols can apply CLUN-LSR for better performance. We apply CLUN-LSR to the existing routing protocol MP-OLSR and simulate it using a commercial network simulator. Simulation results show that our innovative routing protocol demonstrates superior performance compared to existing table-driven routing methods, particularly in terms of packet transmission rate and overall throughput.

通过无线网络相互连接的无人飞行器（UAV）在战争中的使用越来越频繁。然而，对抗性干扰有可能破坏无线通信，而目前使用的无人飞行器路由选择方法很难处理干扰。在本文中，我们提出了一种跨层无人机链路状态路由协议 CLUN-LSR，以对抗干扰攻击。CLUN-LSR 有三个特点。首先，它能从链路层获取实时频谱状态。现有的许多无线电设备，尤其是军事应用中的无线电设备都具备这种能力，但传统路由协议却忽略了这一点。其次，基于跨层信息，CLUN-LSR 在路由过程中增加了高效路由功能，包括使用两跳邻居节点数作为路由选择的度量。第三，CLUN-LSR 选择不在干扰区域内的节点，从而减少网络中断，提高数据传输效率。所有表驱动路由协议都可以应用 CLUN-LSR 以获得更好的性能。我们将 CLUN-LSR 应用于现有的路由协议 MP-OLSR，并使用商业网络模拟器进行了仿真。仿真结果表明，与现有的表驱动路由方法相比，我们的创新路由协议表现出更优越的性能，尤其是在数据包传输速率和总体吞吐量方面。

{"title":"Cross-layer UAV network routing protocol for spectrum denial environments","authors":"Siyue Zheng , Xiaojun Zhu , Zhengrui Qin , Chao Dong","doi":"10.1016/j.adhoc.2024.103702","DOIUrl":"10.1016/j.adhoc.2024.103702","url":null,"abstract":"<div><div>Unmanned Aerial Vehicles (UAVs), which connect to one another over wireless networks, are being used in warfare more frequently. Nevertheless, adversarial interference has the potential to disrupt wireless communication, and the UAV routing methods in use today struggle to handle interference. In this paper, we propose a Cross-Layer UAV Link State Routing protocol, CLUN-LSR, to combat against jamming attacks. CLUN-LSR features three designs. First, it obtains real-time spectrum status from the link layer. Such capabilities are provided by many existing radios, especially the ones in military applications, but are ignored by traditional routing protocols. Second, based on the cross-layer information, CLUN-LSR adds efficient routing functions during routing, including the use of the number of two-hop neighbor nodes as a metric for route selection. Third, CLUN-LSR selects nodes that are not in the interference area, thereby reducing network interruptions and improving data transmission efficiency. All table-driven routing protocols can apply CLUN-LSR for better performance. We apply CLUN-LSR to the existing routing protocol MP-OLSR and simulate it using a commercial network simulator. Simulation results show that our innovative routing protocol demonstrates superior performance compared to existing table-driven routing methods, particularly in terms of packet transmission rate and overall throughput.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"167 ","pages":"Article 103702"},"PeriodicalIF":4.4,"publicationDate":"2024-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142656957","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

JamBIT: RL-based framework for disrupting adversarial information in battlefields JamBIT：基于 RL 的战场对抗信息干扰框架

IF 4.4 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Ad Hoc Networks

Pub Date : 2024-11-06 DOI: 10.1016/j.adhoc.2024.103697

Muhammad Salman , Taehong Lee , Ali Hassan , Muhammad Yasin , Kiran Khurshid , Youngtae Noh

During battlefield operations, military radios (hereafter nodes) exchange information among various units using a mobile ad-hoc network (MANET) due to its infrastructure-less and self-healing capabilities. Adversarial cyberwarfare plays a crucial role in modern combat by disrupting communication between critical nodes (i.e., nodes mainly responsible for propagating important information) to gain dominance over the opposing side. However, determining critical nodes within a complex network is an NP-hard problem. This paper formulates a mathematical model to identify important links and their connected nodes, and presents JamBIT, a reinforcement learning-based framework with an encoder–decoder architecture, for efficiently detecting and jamming critical nodes. The encoder transforms network structures into embedding vectors, while the decoder assigns a score to the embedding vector with the highest reward. Our framework is trained and tested on custom-built MANET topologies using the Named Data Networking (NDN) protocol. JamBIT has been evaluated across various scales and weighting methods for both connected node and network dismantling problems. Our proposed method outperformed existing RL-based baselines, with a 24% performance gain for smaller topologies (50–100 nodes) and 8% for larger ones (400–500 nodes) in connected node problems, and a 7% gain for smaller topologies and 15% for larger ones in network dismantling problems.

在战场行动中，军用无线电（以下简称节点）利用移动特设网络（MANET）在不同单位之间交换信息，因为该网络不需要基础设施，而且具有自愈能力。对抗性网络战通过破坏关键节点（即主要负责传播重要信息的节点）之间的通信，在现代作战中发挥着至关重要的作用，从而获得对对方的主导权。然而，在复杂的网络中确定关键节点是一个 NP 难度很高的问题。本文提出了一个数学模型来识别重要链接及其连接的节点，并介绍了基于强化学习、采用编码器-解码器架构的框架 JamBIT，用于高效地检测和干扰关键节点。编码器将网络结构转换为嵌入向量，而解码器则为奖励最高的嵌入向量分配分数。我们的框架使用命名数据网络（NDN）协议在定制的城域网拓扑上进行了训练和测试。JamBIT 针对连接节点和网络解体问题的不同规模和加权方法进行了评估。我们提出的方法优于现有的基于 RL 的基线方法，在连接节点问题中，较小拓扑（50-100 个节点）的性能提高了 24%，较大拓扑（400-500 个节点）的性能提高了 8%；在网络拆除问题中，较小拓扑的性能提高了 7%，较大拓扑的性能提高了 15%。

{"title":"JamBIT: RL-based framework for disrupting adversarial information in battlefields","authors":"Muhammad Salman , Taehong Lee , Ali Hassan , Muhammad Yasin , Kiran Khurshid , Youngtae Noh","doi":"10.1016/j.adhoc.2024.103697","DOIUrl":"10.1016/j.adhoc.2024.103697","url":null,"abstract":"<div><div>During battlefield operations, military radios (hereafter nodes) exchange information among various units using a mobile ad-hoc network (MANET) due to its infrastructure-less and self-healing capabilities. Adversarial cyberwarfare plays a crucial role in modern combat by disrupting communication between critical nodes (i.e., nodes mainly responsible for propagating important information) to gain dominance over the opposing side. However, determining critical nodes within a complex network is an NP-hard problem. This paper formulates a mathematical model to identify important links and their connected nodes, and presents JamBIT, a reinforcement learning-based framework with an encoder–decoder architecture, for efficiently detecting and jamming critical nodes. The encoder transforms network structures into embedding vectors, while the decoder assigns a score to the embedding vector with the highest reward. Our framework is trained and tested on custom-built MANET topologies using the Named Data Networking (NDN) protocol. JamBIT has been evaluated across various scales and weighting methods for both connected node and network dismantling problems. Our proposed method outperformed existing RL-based baselines, with a 24% performance gain for smaller topologies (50–100 nodes) and 8% for larger ones (400–500 nodes) in connected node problems, and a 7% gain for smaller topologies and 15% for larger ones in network dismantling problems.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"167 ","pages":"Article 103697"},"PeriodicalIF":4.4,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142656956","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Wireless sensor networks and machine learning centric resource management schemes: A survey 无线传感器网络和以机器学习为中心的资源管理方案：调查

IF 4.4 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Ad Hoc Networks

Pub Date : 2024-11-05 DOI: 10.1016/j.adhoc.2024.103698

Gururaj S. Kori , Mahabaleshwar S. Kakkasageri , Poornima M. Chanal , Rajani S. Pujar , Vinayak A. Telsang

Wireless Sensor Network (WSN) is a heterogeneous, distributed network composed of tiny cognitive, autonomous sensor nodes integrated with processor, sensors, transceivers, and software. WSNs offer much to the sensing world and are deployed in predefined geographical areas that are out of human interventions to perform multiple applications. Sensing, computing, and communication are the main functions of the sensor node. However, WSNs are mainly constrained by limited resources such as power, computational speed, memory, sensing capability, communication range, and bandwidth. WSNs when shared for multiple tasks and applications, resource management becomes a challenging task. Hence, effective utilization of available resources is a critical issue to prolong the life span of sensor network. Current research has explored various methods for resources management in WSNs, but most of these approaches are traditional and often fall short in addressing the resource management issues during real-time applications. Resource management schemes involves in resource identification, resource scheduling, resource allocation, resource utilization and monitoring, etc. This paper aims to fill the gap by reviewing and analysing the latest Computational Intelligence (CI) techniques, particularly Machine Learning (ML) and Artificial Intelligence (AI). AIML has been applied to countless humdrum and complex problems arising in WSN operation and resource management. AIML algorithms increase the efficiency of the network and speed up the computational time with optimized utilization of the available resources. Therefore, this is a timely perspective on the ramifications of machine learning algorithms for autonomous WSN establishment, operation, and resource management.

无线传感器网络（WSN）是一种异构分布式网络，由集成了处理器、传感器、收发器和软件的微型认知自主传感器节点组成。WSN 为传感世界提供了很多便利，它被部署在预定义的地理区域，不受人为干预，可执行多种应用。传感、计算和通信是传感器节点的主要功能。然而，WSN 主要受限于有限的资源，如功率、计算速度、内存、传感能力、通信范围和带宽。当 WSN 被多个任务和应用共享时，资源管理就成为一项具有挑战性的任务。因此，有效利用可用资源是延长传感器网络寿命的关键问题。目前的研究探索了 WSN 中资源管理的各种方法，但这些方法大多比较传统，往往无法解决实时应用中的资源管理问题。资源管理方案涉及资源识别、资源调度、资源分配、资源利用和监控等方面。本文旨在通过回顾和分析最新的计算智能（CI）技术，特别是机器学习（ML）和人工智能（AI），填补这一空白。AIML 已被应用于 WSN 运行和资源管理中出现的无数琐碎和复杂问题。AIML 算法通过优化利用可用资源，提高了网络效率，加快了计算时间。因此，本文从机器学习算法对自主 WSN 建立、运行和资源管理的影响的角度进行了及时的探讨。

{"title":"Wireless sensor networks and machine learning centric resource management schemes: A survey","authors":"Gururaj S. Kori , Mahabaleshwar S. Kakkasageri , Poornima M. Chanal , Rajani S. Pujar , Vinayak A. Telsang","doi":"10.1016/j.adhoc.2024.103698","DOIUrl":"10.1016/j.adhoc.2024.103698","url":null,"abstract":"<div><div>Wireless Sensor Network (WSN) is a heterogeneous, distributed network composed of tiny cognitive, autonomous sensor nodes integrated with processor, sensors, transceivers, and software. WSNs offer much to the sensing world and are deployed in predefined geographical areas that are out of human interventions to perform multiple applications. Sensing, computing, and communication are the main functions of the sensor node. However, WSNs are mainly constrained by limited resources such as power, computational speed, memory, sensing capability, communication range, and bandwidth. WSNs when shared for multiple tasks and applications, resource management becomes a challenging task. Hence, effective utilization of available resources is a critical issue to prolong the life span of sensor network. Current research has explored various methods for resources management in WSNs, but most of these approaches are traditional and often fall short in addressing the resource management issues during real-time applications. Resource management schemes involves in resource identification, resource scheduling, resource allocation, resource utilization and monitoring, etc. This paper aims to fill the gap by reviewing and analysing the latest Computational Intelligence (CI) techniques, particularly Machine Learning (ML) and Artificial Intelligence (AI). AIML has been applied to countless humdrum and complex problems arising in WSN operation and resource management. AIML algorithms increase the efficiency of the network and speed up the computational time with optimized utilization of the available resources. Therefore, this is a timely perspective on the ramifications of machine learning algorithms for autonomous WSN establishment, operation, and resource management.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"167 ","pages":"Article 103698"},"PeriodicalIF":4.4,"publicationDate":"2024-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142656955","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

V2X application server and vehicle centric distribution of commitments for V2V message authentication V2X 应用服务器和以车辆为中心的 V2V 信息验证承诺分配

IF 4.4 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Ad Hoc Networks

Pub Date : 2024-11-04 DOI: 10.1016/j.adhoc.2024.103701

Mujahid Muhammad , Ghazanfar Ali Safdar

Safety applications, such as intersection collision warnings and emergency brake warnings, enhance road safety and traffic efficiency through periodic broadcast messages by vehicles and roadside infrastructure. While the Elliptic Curve Digital Signature Algorithm (ECDSA) is a widely used security approach, its performance limitations make it unsuitable for time-critical safety applications. As such, a symmetric cryptography-based technique called Timed Efficient Stream Loss-tolerant Authentication (TESLA) offers a viable alternative. However, applying standard TESLA in the context of vehicle-to-vehicle (V2V) communications has its own challenges. One challenge is the difficulty of distributing authentication information called commitments in the highly dynamic V2V environment. In this paper, we propose two novel solutions to this problem, namely, V2X Application Server (VAS)-centric and vehicle-centric. The former is an application-level solution that involves selective unicasting of commitments to vehicles by a central server, the VAS, and the latter is a reactive scheme that involves the periodic broadcast of commitments by the vehicles themselves. Extensive simulations are conducted using representatives of the real V2V environment to evaluate the performance of these approaches under different traffic situations; as well as performance comparison with a state-of-the-art distribution solution. The simulation results indicate that the VAS-centric solution is preferable for use in a TESLA-like V2V security scheme. It demonstrates desirable features, including timely delivery of commitments and high distribution efficiency, with over 95 % of commitments sent by the VAS are associated with relevant safety messages when compared with the vehicle-centric and state-of-the-art solutions. Formal security analysis, conducted using the Random Oracle Model (ROM), proves the correctness of our proposed distribution schemes. Additionally, an informal security analysis shows the resilience of the proposed schemes against various attacks, including impersonation, replay, and bogus commitment messages.

交叉路口碰撞警告和紧急制动警告等安全应用通过车辆和路边基础设施的定期广播信息来提高道路安全和交通效率。虽然椭圆曲线数字签名算法（ECDSA）是一种广泛使用的安全方法，但其性能限制使其不适合时间紧迫的安全应用。因此，一种名为 "定时高效流损容限验证"（TESLA）的对称加密技术提供了一种可行的替代方案。然而，在车对车 (V2V) 通信中应用标准 TESLA 有其自身的挑战。挑战之一是在高度动态的 V2V 环境中难以分发称为承诺的验证信息。本文针对这一问题提出了两种新颖的解决方案，即以 V2X 应用服务器 (VAS) 为中心和以车辆为中心。前者是一种应用级解决方案，包括由中央服务器（VAS）有选择地向车辆单播承诺；后者是一种反应式方案，包括由车辆本身定期广播承诺。我们使用真实 V2V 环境的代表进行了大量模拟，以评估这些方法在不同交通状况下的性能，并与最先进的分配解决方案进行性能比较。模拟结果表明，以 VAS 为中心的解决方案更适合用于类似 TESLA 的 V2V 安全方案。与以车辆为中心的解决方案和最先进的解决方案相比，VAS 发送的承诺中有 95% 以上与相关的安全信息有关，因此它具有及时交付承诺和高分配效率等理想特性。使用随机甲骨文模型（ROM）进行的正式安全分析证明了我们提出的分配方案的正确性。此外，非正式的安全分析表明，所提出的方案能够抵御各种攻击，包括冒名顶替、重放和伪造承诺信息。

{"title":"V2X application server and vehicle centric distribution of commitments for V2V message authentication","authors":"Mujahid Muhammad , Ghazanfar Ali Safdar","doi":"10.1016/j.adhoc.2024.103701","DOIUrl":"10.1016/j.adhoc.2024.103701","url":null,"abstract":"<div><div>Safety applications, such as intersection collision warnings and emergency brake warnings, enhance road safety and traffic efficiency through periodic broadcast messages by vehicles and roadside infrastructure. While the Elliptic Curve Digital Signature Algorithm (ECDSA) is a widely used security approach, its performance limitations make it unsuitable for time-critical safety applications. As such, a symmetric cryptography-based technique called Timed Efficient Stream Loss-tolerant Authentication (TESLA) offers a viable alternative. However, applying standard TESLA in the context of vehicle-to-vehicle (V2V) communications has its own challenges. One challenge is the difficulty of distributing authentication information called commitments in the highly dynamic V2V environment. In this paper, we propose two novel solutions to this problem, namely, V2X Application Server (VAS)-centric and vehicle-centric. The former is an application-level solution that involves selective unicasting of commitments to vehicles by a central server, the VAS, and the latter is a reactive scheme that involves the periodic broadcast of commitments by the vehicles themselves. Extensive simulations are conducted using representatives of the real V2V environment to evaluate the performance of these approaches under different traffic situations; as well as performance comparison with a state-of-the-art distribution solution. The simulation results indicate that the VAS-centric solution is preferable for use in a TESLA-like V2V security scheme. It demonstrates desirable features, including timely delivery of commitments and high distribution efficiency, with over 95 % of commitments sent by the VAS are associated with relevant safety messages when compared with the vehicle-centric and state-of-the-art solutions. Formal security analysis, conducted using the Random Oracle Model (ROM), proves the correctness of our proposed distribution schemes. Additionally, an informal security analysis shows the resilience of the proposed schemes against various attacks, including impersonation, replay, and bogus commitment messages.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"167 ","pages":"Article 103701"},"PeriodicalIF":4.4,"publicationDate":"2024-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142656959","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Deep learning with synthetic data for wireless NLOS positioning with a single base station 利用合成数据进行深度学习，实现单基站无线 NLOS 定位

IF 4.4 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Ad Hoc Networks

Pub Date : 2024-10-31 DOI: 10.1016/j.adhoc.2024.103696

Hrant Khachatrian , Rafayel Mkrtchyan , Theofanis P. Raptis

Traditional wireless positioning methods exhibit limitations in the face of signal distortions prevalent in non-line-of-sight (NLOS) conditions, especially in the case of a single base station (BS). Moreover, the adoption of deep learning (DL) methodologies has lagged behind, largely due to the challenges associated with generating real-world datasets. In this paper, we present a comprehensive approach leveraging DL over large-scale synthetic wireless datasets (the recent WAIR-D in this case, which was co-produced by Huawei) to overcome such challenges and address the case of single-BS NLOS positioning. The aim of the paper is to practically explore the extent to which synthetic wireless datasets can help to achieve the positioning objectives. Towards this direction, we develop a map-based representation of a radio link, demonstrating its synergistic effect with feature-based representations in MLPs. Furthermore, we introduce a UNet-based neural model which incorporates input maps and radio link representations and generates as output a heatmap of potential device positions. This model achieves an 11.3-meter RMSE and 76.5% prediction accuracy on NLOS examples (1.5-meter, 99.9% for LOS) assuming perfect information, surpassing the MLP baseline by 47%. Finally, we provide further insights into the model’s ability to predict top device positions, the characteristics of predicted heatmaps as indicators of confidence, and the crucial role of map availability and radio path angles in model performance, thus revealing an unconventional perspective on incorrect predictions.

面对非视距（NLOS）条件下普遍存在的信号失真，传统的无线定位方法表现出局限性，尤其是在单基站（BS）的情况下。此外，深度学习（DL）方法的采用一直滞后，这主要是由于生成真实世界数据集所面临的挑战。在本文中，我们提出了一种综合方法，利用大规模合成无线数据集上的深度学习（本例中为最近的 WAIR-D，由华为联合制作）来克服这些挑战，并解决单基站 NLOS 定位的情况。本文旨在实际探索合成无线数据集可在多大程度上帮助实现定位目标。为此，我们开发了一种基于地图的无线链路表示法，展示了它与 MLP 中基于特征的表示法之间的协同效应。此外，我们还引入了基于 UNet 的神经模型，该模型结合了输入地图和无线电链路表示法，并生成潜在设备位置的热图作为输出。假设信息完美，该模型在 NLOS 示例（1.5 米，LOS 为 99.9%）上实现了 11.3 米的均方根误差和 76.5% 的预测准确率，比 MLP 基线高出 47%。最后，我们对模型预测顶部设备位置的能力、作为置信度指标的预测热图的特征以及地图可用性和无线电路径角度在模型性能中的关键作用提供了进一步的见解，从而揭示了错误预测的非传统视角。

{"title":"Deep learning with synthetic data for wireless NLOS positioning with a single base station","authors":"Hrant Khachatrian , Rafayel Mkrtchyan , Theofanis P. Raptis","doi":"10.1016/j.adhoc.2024.103696","DOIUrl":"10.1016/j.adhoc.2024.103696","url":null,"abstract":"<div><div>Traditional wireless positioning methods exhibit limitations in the face of signal distortions prevalent in non-line-of-sight (NLOS) conditions, especially in the case of a single base station (BS). Moreover, the adoption of deep learning (DL) methodologies has lagged behind, largely due to the challenges associated with generating real-world datasets. In this paper, we present a comprehensive approach leveraging DL over large-scale synthetic wireless datasets (the recent WAIR-D in this case, which was co-produced by Huawei) to overcome such challenges and address the case of single-BS NLOS positioning. The aim of the paper is to practically explore the extent to which synthetic wireless datasets can help to achieve the positioning objectives. Towards this direction, we develop a map-based representation of a radio link, demonstrating its synergistic effect with feature-based representations in MLPs. Furthermore, we introduce a UNet-based neural model which incorporates input maps and radio link representations and generates as output a heatmap of potential device positions. This model achieves an 11.3-meter RMSE and 76.5% prediction accuracy on NLOS examples (1.5-meter, 99.9% for LOS) assuming perfect information, surpassing the MLP baseline by 47%. Finally, we provide further insights into the model’s ability to predict top device positions, the characteristics of predicted heatmaps as indicators of confidence, and the crucial role of map availability and radio path angles in model performance, thus revealing an unconventional perspective on incorrect predictions.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"167 ","pages":"Article 103696"},"PeriodicalIF":4.4,"publicationDate":"2024-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142593051","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Transitive reasoning: A high-performance computing model for significant pattern discovery in cognitive IoT sensor network 传递推理：认知物联网传感器网络中发现重要模式的高性能计算模型

IF 4.4 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Ad Hoc Networks

Pub Date : 2024-10-31 DOI: 10.1016/j.adhoc.2024.103700

Vidyapati Jha, Priyanka Tripathi

Current research on the Internet of Things (IoT) has given rise to a new field of study called cognitive IoT (CIoT), which aims to incorporate cognition into the designs of IoT systems. Consequently, the CIoT inherits specific attributes and challenges from IoT. The CIoT applications generate vast, diverse, constantly changing, and time-dependent data due to the billions of devices involved. The efficient operation of these CIoT systems requires the extraction of valuable insights from vast data sources in a computationally efficient manner. Therefore, this study proposes transitive reasoning to glean significant concepts and patterns from a 21.25-year environmental dataset. To reduce the effects of missing entries, the proposed methodology includes a grouping of data using probabilistic clustering and applying total variance regularization in the alternate direction method of multipliers (ADMM) to regularize the sensory data. As a result, noisy entries will be less conspicuous. Afterward, it calculates the transitional plausibility value for each cluster using the transited value and then turns it into binary data to create concept lattices. In addition, each concept that is formed is assigned a weight, and the concept with the largest transitive strength value is chosen, followed by calculating the mean value. Therefore, this pattern is seen as significant. Experimental results on 21.25-year environmental data show an accuracy of over 99.5%, outperforming competing methods, as shown by cross-validation using multiple metrics.

当前对物联网（IoT）的研究催生了一个名为认知物联网（CIoT）的新研究领域，其目的是将认知纳入物联网系统的设计中。因此，CIoT 继承了物联网的特定属性和挑战。由于涉及数十亿台设备，CIoT 应用会产生大量、多样、不断变化且与时间相关的数据。这些 CIoT 系统的高效运行需要以计算高效的方式从庞大的数据源中提取有价值的见解。因此，本研究提出了从 21.25 年的环境数据集中提取重要概念和模式的直观推理方法。为了减少缺失条目的影响，所提出的方法包括使用概率聚类对数据进行分组，并在交替乘数方向法（ADMM）中应用总方差正则化对感官数据进行正则化。因此，噪声条目将不那么明显。之后，它利用过渡值计算每个聚类的过渡可信度值，然后将其转化为二进制数据，创建概念网格。此外，形成的每个概念都会被赋予一个权重，并选择过渡强度值最大的概念，然后计算平均值。因此，这种模式被认为是重要的。对 21.25 年环境数据的实验结果表明，该方法的准确率超过 99.5%，优于其他竞争方法。

{"title":"Transitive reasoning: A high-performance computing model for significant pattern discovery in cognitive IoT sensor network","authors":"Vidyapati Jha, Priyanka Tripathi","doi":"10.1016/j.adhoc.2024.103700","DOIUrl":"10.1016/j.adhoc.2024.103700","url":null,"abstract":"<div><div>Current research on the Internet of Things (IoT) has given rise to a new field of study called cognitive IoT (CIoT), which aims to incorporate cognition into the designs of IoT systems. Consequently, the CIoT inherits specific attributes and challenges from IoT. The CIoT applications generate vast, diverse, constantly changing, and time-dependent data due to the billions of devices involved. The efficient operation of these CIoT systems requires the extraction of valuable insights from vast data sources in a computationally efficient manner. Therefore, this study proposes transitive reasoning to glean significant concepts and patterns from a 21.25-year environmental dataset. To reduce the effects of missing entries, the proposed methodology includes a grouping of data using probabilistic clustering and applying total variance regularization in the alternate direction method of multipliers (ADMM) to regularize the sensory data. As a result, noisy entries will be less conspicuous. Afterward, it calculates the transitional plausibility value for each cluster using the transited value and then turns it into binary data to create concept lattices. In addition, each concept that is formed is assigned a weight, and the concept with the largest transitive strength value is chosen, followed by calculating the mean value. Therefore, this pattern is seen as significant. Experimental results on 21.25-year environmental data show an accuracy of over 99.5%, outperforming competing methods, as shown by cross-validation using multiple metrics.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"167 ","pages":"Article 103700"},"PeriodicalIF":4.4,"publicationDate":"2024-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142577912","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

BLE-based sensors for privacy-enabled contagious disease monitoring with zero trust architecture 基于 BLE 的传感器用于零信任架构下的隐私型传染病监测

IF 4.4 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Ad Hoc Networks

Pub Date : 2024-10-28 DOI: 10.1016/j.adhoc.2024.103693

Akshay Madan , David Tipper , Balaji Palanisamy , Mai Abdelhakim , Prashant Krishnamurthy , Vinay Chamola

Digital contact tracing is an important technique to stop the spread of infectious diseases. Due to data integrity, and privacy problems, smartphone apps suffer from low adoption rates. Also, these apps excessively drain batteries and sometimes give false alarms. They are also not able to detect fomite-based contacts or indirect contacts. BEacon-based Contact Tracing or BECT is a contact tracing framework that uses Bluetooth beacon sensors that periodically broadcast “tokens” to close users. Users who are positively diagnosed voluntarily provide their tokens to the health authority-maintained server for tracing contacts. We target environments like campuses like companies, colleges, and prisons, where use can be mandated thus mitigating low adoption rate issues. This approach detects indirect contacts and preserves the device’s battery. We create a simulation to examine the proposed framework’s performance in detecting indirect contacts and compare it with the existing apps’ framework. We also analyze the cost and power consumption for our technique and assess the placement strategies for beacons. Incorporating Zero Trust Architecture enhances the framework’s security and privacy.

数字接触追踪是阻止传染病传播的一项重要技术。由于数据完整性和隐私问题，智能手机应用程序的采用率很低。此外，这些应用程序过度消耗电池，有时还会发出错误警报。此外，它们还无法检测到基于煽动的接触或间接接触。基于信标的接触追踪或 BECT 是一种接触追踪框架，它使用蓝牙信标传感器定期向亲密用户发送 "令牌"。被确诊的用户会自愿向卫生机构维护的服务器提供令牌，以便追踪联系人。我们的目标环境是校园，如公司、学院和监狱，在这些环境中可以强制使用，从而缓解采用率低的问题。这种方法既能检测间接接触，又能保护设备电池。我们创建了一个仿真，以检验建议的框架在检测间接接触方面的性能，并将其与现有的应用程序框架进行比较。我们还分析了我们技术的成本和功耗，并评估了信标的放置策略。零信任架构增强了框架的安全性和隐私性。

{"title":"BLE-based sensors for privacy-enabled contagious disease monitoring with zero trust architecture","authors":"Akshay Madan , David Tipper , Balaji Palanisamy , Mai Abdelhakim , Prashant Krishnamurthy , Vinay Chamola","doi":"10.1016/j.adhoc.2024.103693","DOIUrl":"10.1016/j.adhoc.2024.103693","url":null,"abstract":"<div><div>Digital contact tracing is an important technique to stop the spread of infectious diseases. Due to data integrity, and privacy problems, smartphone apps suffer from low adoption rates. Also, these apps excessively drain batteries and sometimes give false alarms. They are also not able to detect <em>fomite-based</em> contacts or <em>indirect</em> contacts. BEacon-based Contact Tracing or BECT is a contact tracing framework that uses Bluetooth beacon sensors that periodically broadcast “tokens” to close users. Users who are positively diagnosed voluntarily provide their tokens to the health authority-maintained server for tracing contacts. We target environments like campuses like companies, colleges, and prisons, where use can be mandated thus mitigating low adoption rate issues. This approach detects indirect contacts and preserves the device’s battery. We create a simulation to examine the proposed framework’s performance in detecting indirect contacts and compare it with the existing apps’ framework. We also analyze the cost and power consumption for our technique and assess the placement strategies for beacons. Incorporating Zero Trust Architecture enhances the framework’s security and privacy.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"167 ","pages":"Article 103693"},"PeriodicalIF":4.4,"publicationDate":"2024-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142577911","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

ADRP-DQL: An adaptive distributed routing protocol for underwater acoustic sensor networks using deep Q-learning ADRP-DQL：使用深度 Q 学习的水下声学传感器网络自适应分布式路由协议

IF 4.4 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Ad Hoc Networks

Pub Date : 2024-10-28 DOI: 10.1016/j.adhoc.2024.103692

Adi Surendra Mohanraju M., Anjaneyulu Lokam

Underwater Wireless Sensor Networks (UWSNs) face unique constraints due to their unstructured and dynamic underwater environment. Data gathering from these networks is crucial as energy resources are limited. In this regard, efficient routing protocols are needed to optimize energy consumption, increase the network lifetime, and enhance data delivery in these networks. In this work, we develop an Adaptive Distributed Routing Protocol for UWSNs using Deep Q-Learning (ADRP-DQL). This protocol employs the ability of reinforcement learning to dynamically learn the best routing decisions based on the network’s state and action-value estimates. It allows nodes to make intelligent routing decisions, considering residual energy, depth and node degree. A Deep Q-Network (DQN) is employed as the function approximator to estimate action values and choose the optimal routing decisions. The DQN is trained using off-policy and on-policy strategies and the neural network model. Simulation results demonstrate that ADRP-DQL performs well regarding energy efficiency (EE), data delivery ratio, and network lifetime. The results highlight the proposed protocol’s effectiveness and adaptability to UWSNs. The ADRP-DQL protocol contributes to intelligent routing for UWSNs, offering a promising approach to enhance performance and optimize energy utilization in these demanding environments.

水下无线传感器网络（UWSN）因其非结构化和动态的水下环境而面临独特的限制。由于能源资源有限，从这些网络收集数据至关重要。在这方面，需要高效的路由协议来优化能源消耗、延长网络寿命并加强这些网络的数据传输。在这项工作中，我们开发了一种使用深度 Q 学习的 UWSN 自适应分布式路由协议（ADRP-DQL）。该协议利用强化学习的能力，根据网络状态和行动值估计动态学习最佳路由决策。它允许节点在考虑剩余能量、深度和节点度的情况下做出智能路由决策。深度 Q 网络（DQN）被用作函数近似器，用于估计行动值和选择最佳路由决策。DQN 使用非策略和策略策略以及神经网络模型进行训练。仿真结果表明，ADRP-DQL 在能效（EE）、数据交付率和网络寿命方面表现良好。这些结果凸显了所提协议的有效性和对 UWSN 的适应性。ADRP-DQL 协议为 UWSN 的智能路由做出了贡献，为在这些要求苛刻的环境中提高性能和优化能源利用提供了一种有前途的方法。

{"title":"ADRP-DQL: An adaptive distributed routing protocol for underwater acoustic sensor networks using deep Q-learning","authors":"Adi Surendra Mohanraju M., Anjaneyulu Lokam","doi":"10.1016/j.adhoc.2024.103692","DOIUrl":"10.1016/j.adhoc.2024.103692","url":null,"abstract":"<div><div>Underwater Wireless Sensor Networks (UWSNs) face unique constraints due to their unstructured and dynamic underwater environment. Data gathering from these networks is crucial as energy resources are limited. In this regard, efficient routing protocols are needed to optimize energy consumption, increase the network lifetime, and enhance data delivery in these networks. In this work, we develop an Adaptive Distributed Routing Protocol for UWSNs using Deep Q-Learning (ADRP-DQL). This protocol employs the ability of reinforcement learning to dynamically learn the best routing decisions based on the network’s state and action-value estimates. It allows nodes to make intelligent routing decisions, considering residual energy, depth and node degree. A Deep Q-Network (DQN) is employed as the function approximator to estimate action values and choose the optimal routing decisions. The DQN is trained using off-policy and on-policy strategies and the neural network model. Simulation results demonstrate that ADRP-DQL performs well regarding energy efficiency (EE), data delivery ratio, and network lifetime. The results highlight the proposed protocol’s effectiveness and adaptability to UWSNs. The ADRP-DQL protocol contributes to intelligent routing for UWSNs, offering a promising approach to enhance performance and optimize energy utilization in these demanding environments.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"167 ","pages":"Article 103692"},"PeriodicalIF":4.4,"publicationDate":"2024-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142573352","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A context-aware zero trust-based hybrid approach to IoT-based self-driving vehicles security 基于物联网的自动驾驶汽车安全的情境感知零信任混合方法

IF 4.4 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Ad Hoc Networks

Pub Date : 2024-10-28 DOI: 10.1016/j.adhoc.2024.103694

Izhar Ahmed Khan , Marwa Keshk , Yasir Hussain , Dechang Pi , Bentian Li , Tanzeela Kousar , Bakht Sher Ali

With the speedy progression and adoption of IoT devices in modern self-driving vehicles (SDVs), autonomous driving industry is gradually reforming its capabilities to provide better transportation services. However, this domain faces enormous security and privacy challenges and thus has become an attractive target for attackers due to its rapid growth and market worth. Furthermore, the rapid transformation in technological tools in transport industry and speedy evolution of cyber-attacks paved the way for designing efficient IDSs. Motivated by these challenges, we put forward a new secure and efficient IDS approach for the security of SDVs. The propose approach utilizes an emerging strategy to mitigate security vulnerabilities and cyber attacks detection using zero trust (ZT) model. Through this work, we put forward a context-aware zero trust security framework for IoT-based SDVs. The proposed framework utilizes a context-aware design to evaluate the trustworthiness of the devices using multi-source trust and reputation model. Then, to make the framework more effective and reliable, we introduce crawler system into the context of the IoT-devices in SDVs to make the system unbiased. Additionally, an observer module is developed that employs state-of-the-art machine learning algorithm to detect malicious actions. Empirical results on two standard benchmark datasets (i.e., Car Hacking and ToN_IoT) validate the practicality and robustness of propose framework in real-world transport systems with enhanced security and trust management against evolving cyber-threats. Detection results demonstrate that the proposed framework secured the best performance by achieving 99.43% and 99.52% accuracy for Car Hacking and ToN_IoT, respectively. The findings of this study will help the security professionals and researchers to comprehend the importance of ZT architecture in developing effective and robust security solutions for modern IoT-based SDVs.

随着物联网设备在现代自动驾驶汽车（SDV）中的快速发展和采用，自动驾驶行业正在逐步改革其能力，以提供更好的交通服务。然而，这一领域面临着巨大的安全和隐私挑战，因此，由于其快速增长和市场价值，已成为攻击者的诱人目标。此外，运输行业技术工具的快速变革和网络攻击的迅速发展也为设计高效的 IDS 铺平了道路。在这些挑战的激励下，我们针对 SDV 的安全性提出了一种新的安全高效 IDS 方法。我们提出的方法采用了一种新兴的策略，利用零信任（ZT）模型来减轻安全漏洞和网络攻击检测。通过这项工作，我们为基于物联网的 SDV 提出了一个情境感知零信任安全框架。所提出的框架采用情境感知设计，利用多源信任和声誉模型来评估设备的可信度。然后，为了使该框架更有效、更可靠，我们在 SDV 中的物联网设备上下文中引入了爬虫系统，使系统不带偏见。此外，我们还开发了一个观察者模块，采用最先进的机器学习算法来检测恶意行为。在两个标准基准数据集（即 "汽车黑客 "和 "ToN_IoT"）上的实证结果验证了所提框架在现实世界运输系统中的实用性和稳健性，该框架针对不断演变的网络威胁加强了安全性和信任管理。检测结果表明，建议的框架确保了最佳性能，在 "汽车黑客攻击 "和 "ToN_IoT "中分别达到了 99.43% 和 99.52% 的准确率。这项研究的结果将有助于安全专业人员和研究人员理解 ZT 架构在为基于物联网的现代 SDV 开发有效、稳健的安全解决方案方面的重要性。

{"title":"A context-aware zero trust-based hybrid approach to IoT-based self-driving vehicles security","authors":"Izhar Ahmed Khan , Marwa Keshk , Yasir Hussain , Dechang Pi , Bentian Li , Tanzeela Kousar , Bakht Sher Ali","doi":"10.1016/j.adhoc.2024.103694","DOIUrl":"10.1016/j.adhoc.2024.103694","url":null,"abstract":"<div><div>With the speedy progression and adoption of IoT devices in modern self-driving vehicles (SDVs), autonomous driving industry is gradually reforming its capabilities to provide better transportation services. However, this domain faces enormous security and privacy challenges and thus has become an attractive target for attackers due to its rapid growth and market worth. Furthermore, the rapid transformation in technological tools in transport industry and speedy evolution of cyber-attacks paved the way for designing efficient IDSs. Motivated by these challenges, we put forward a new secure and efficient IDS approach for the security of SDVs. The propose approach utilizes an emerging strategy to mitigate security vulnerabilities and cyber attacks detection using zero trust (ZT) model. Through this work, we put forward a context-aware zero trust security framework for IoT-based SDVs. The proposed framework utilizes a context-aware design to evaluate the trustworthiness of the devices using multi-source trust and reputation model. Then, to make the framework more effective and reliable, we introduce crawler system into the context of the IoT-devices in SDVs to make the system unbiased. Additionally, an observer module is developed that employs state-of-the-art machine learning algorithm to detect malicious actions. Empirical results on two standard benchmark datasets (i.e., Car Hacking and ToN_IoT) validate the practicality and robustness of propose framework in real-world transport systems with enhanced security and trust management against evolving cyber-threats. Detection results demonstrate that the proposed framework secured the best performance by achieving 99.43% and 99.52% accuracy for Car Hacking and ToN_IoT, respectively. The findings of this study will help the security professionals and researchers to comprehend the importance of ZT architecture in developing effective and robust security solutions for modern IoT-based SDVs.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"167 ","pages":"Article 103694"},"PeriodicalIF":4.4,"publicationDate":"2024-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142573353","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Indoor localization algorithms based on Angle of Arrival with a benchmark comparison 基于到达角的室内定位算法与基准比较

IF 4.4 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Ad Hoc Networks

Pub Date : 2024-10-25 DOI: 10.1016/j.adhoc.2024.103691

Francesco Furfari, Michele Girolami, Fabio Mavilia, Paolo Barsocchi

Indoor localization is crucial for developing intelligent environments capable of understanding user contexts and adapting to environmental changes. Bluetooth 5.1 Direction Finding is a recent specification that leverages the angle of departure (AoD) and angle of arrival (AoA) of radio signals to locate objects or people indoors. This paper presents a set of algorithms that estimate user positions using AoA values and the concept of the Confidence Region (CR), which defines the expected position uncertainty and helps to remove outlier measurements, thereby improving performance compared to traditional triangulation algorithms. We validate the algorithms with a publicly available dataset, and analyze the impact of body orientation relative to receiving units. The experimental results highlight the limitations and potential of the proposed solutions. From our experiments, we observe that the Conditional All-in algorithm presented in this work, achieves the best performance across all configuration settings in both line-of-sight and non-line-of-sight conditions.

室内定位对于开发能够理解用户背景并适应环境变化的智能环境至关重要。蓝牙 5.1 测向技术是最近推出的一种技术规范，它利用无线电信号的离去角（AoD）和到达角（AoA）来定位室内的物体或人员。本文介绍了一套利用 AoA 值和置信区域 (CR) 概念估算用户位置的算法，CR 定义了预期位置的不确定性，有助于去除离群测量值，从而与传统三角测量算法相比提高性能。我们利用一个公开的数据集对算法进行了验证，并分析了相对于接收单元的身体方位的影响。实验结果凸显了所提解决方案的局限性和潜力。我们从实验中发现，在视距和非视距条件下，本研究提出的条件全进算法在所有配置设置中都达到了最佳性能。

引用次数: 0