Pervasive and Mobile Computing最新文献_第9页

A Real-time skeleton-based fall detection algorithm based on temporal convolutional networks and transformer encoder 一种基于时间卷积网络和变压器编码器的基于骨骼的实时跌倒检测算法

IF 3 3区计算机科学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

Pervasive and Mobile Computing

Pub Date : 2025-02-01 DOI: 10.1016/j.pmcj.2025.102016

Xiaoqun Yu , Chenfeng Wang , Wenyu Wu , Shuping Xiong

As the population of older individuals living independently rises, coupled with the heightened risk of falls among this demographic, the need for automatic fall detection systems becomes increasingly urgent to ensure timely medical intervention. Computer vision (CV)-based methodologies have emerged as a preferred approach among researchers due to their contactless and pervasive nature. However, existing CV-based solutions often suffer from either poor robustness or prohibitively high computational requirements, impeding their practical implementation in elderly living environments. To address these challenges, we introduce TCNTE, a real-time skeleton-based fall detection algorithm that combines Temporal Convolutional Network (TCN) with Transformer Encoder (TE). We also successfully mitigate the severe class imbalance issue by implementing weighted focal loss. Cross-validation on multiple publicly available vision-based fall datasets demonstrates TCNTE's superiority over individual models (TCN and TE) and existing state-of-the-art fall detection algorithms, achieving remarkable accuracies (front view of UP-Fall: 99.58 %; side view of UP-Fall: 98.75 %; Le2i: 97.01 %; GMDCSA-24: 92.99 %) alongside practical viability. Visualizations using t-distributed stochastic neighbor embedding (t-SNE) reveal TCNTE's superior separation margin and cohesive clustering between fall and non-fall classes compared to TCN and TE. Crucially, TCNTE is designed for pervasive deployment in mobile and resource-constrained environments. Integrated with YOLOv8 pose estimation and BoT-SORT human tracking, the algorithm operates on NVIDIA Jetson Orin NX edge device, achieving an average frame rate of 19 fps for single-person and 17 fps for two-person scenarios. With its validated accuracy and impressive real-time performance, TCNTE holds significant promise for practical fall detection applications in older adult care settings.

随着独立生活的老年人人口的增加，加上这一人口中跌倒风险的增加，对自动跌倒检测系统的需求变得越来越迫切，以确保及时的医疗干预。基于计算机视觉（CV）的方法由于其非接触式和普及性而成为研究人员的首选方法。然而，现有的基于cv的解决方案往往存在鲁棒性差或计算需求过高的问题，阻碍了它们在老年人生活环境中的实际实现。为了解决这些挑战，我们引入了TCNTE，这是一种结合了时间卷积网络（TCN）和变压器编码器（TE）的基于骨骼的实时跌倒检测算法。我们还成功地缓解了严重的类不平衡问题，通过实现加权焦点损失。在多个公开可用的基于视觉的跌倒数据集上的交叉验证表明，TCNTE优于单个模型（TCN和TE）和现有的最先进的跌倒检测算法，实现了显着的准确性(UP-Fall的前视图：99.58%；上下侧视图：98.75%；Le2i: 97.01%；gmdsa -24: 92.99%)和实际可行性。使用t分布随机邻居嵌入（t-SNE）的可视化显示，与TCN和TE相比，TCNTE在跌倒类和非跌倒类之间具有更好的分离裕度和内聚性。至关重要的是，TCNTE是为移动和资源受限环境中的普遍部署而设计的。该算法集成了YOLOv8姿态估计和BoT-SORT人体跟踪，在NVIDIA Jetson Orin NX边缘设备上运行，单人场景平均帧率为19 fps，两人场景平均帧率为17 fps。凭借其经过验证的准确性和令人印象深刻的实时性能，TCNTE在老年人护理环境中的实际跌倒检测应用中具有重要的前景。

{"title":"A Real-time skeleton-based fall detection algorithm based on temporal convolutional networks and transformer encoder","authors":"Xiaoqun Yu , Chenfeng Wang , Wenyu Wu , Shuping Xiong","doi":"10.1016/j.pmcj.2025.102016","DOIUrl":"10.1016/j.pmcj.2025.102016","url":null,"abstract":"<div><div>As the population of older individuals living independently rises, coupled with the heightened risk of falls among this demographic, the need for automatic fall detection systems becomes increasingly urgent to ensure timely medical intervention. Computer vision (CV)-based methodologies have emerged as a preferred approach among researchers due to their contactless and pervasive nature. However, existing CV-based solutions often suffer from either poor robustness or prohibitively high computational requirements, impeding their practical implementation in elderly living environments. To address these challenges, we introduce TCNTE, a real-time skeleton-based fall detection algorithm that combines Temporal Convolutional Network (TCN) with Transformer Encoder (TE). We also successfully mitigate the severe class imbalance issue by implementing weighted focal loss. Cross-validation on multiple publicly available vision-based fall datasets demonstrates TCNTE's superiority over individual models (TCN and TE) and existing state-of-the-art fall detection algorithms, achieving remarkable accuracies (front view of UP-Fall: 99.58 %; side view of UP-Fall: 98.75 %; Le2i: 97.01 %; GMDCSA-24: 92.99 %) alongside practical viability. Visualizations using t-distributed stochastic neighbor embedding (t-SNE) reveal TCNTE's superior separation margin and cohesive clustering between fall and non-fall classes compared to TCN and TE. Crucially, TCNTE is designed for pervasive deployment in mobile and resource-constrained environments. Integrated with YOLOv8 pose estimation and BoT-SORT human tracking, the algorithm operates on NVIDIA Jetson Orin NX edge device, achieving an average frame rate of 19 fps for single-person and 17 fps for two-person scenarios. With its validated accuracy and impressive real-time performance, TCNTE holds significant promise for practical fall detection applications in older adult care settings.</div></div>","PeriodicalId":49005,"journal":{"name":"Pervasive and Mobile Computing","volume":"107 ","pages":"Article 102016"},"PeriodicalIF":3.0,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143155592","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

Machinery detection by impulsive noise recognition using WiFi sensing 基于WiFi传感的脉冲噪声识别机械检测

IF 3 3区计算机科学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

Pervasive and Mobile Computing

Pub Date : 2025-02-01 DOI: 10.1016/j.pmcj.2025.102018

Iratxe Landa , Guillermo Diaz , Iker Sobron , Iñaki Eizmendi , Manuel Velez

Engines and electrical devices in operation generate electromagnetic pulses, also called impulsive noise (IN), that interfere with wireless signals. The IN shall affect the channel estimation process and is, therefore, present in the channel state information (CSI) provided by wireless receivers. In this paper, impulsive noise (IN) is used as a fingerprint of electrical devices to identify the IN sources that interfere with a WiFi signal, taking into account that each individual machine has a unique pattern of impulsive noise. In this sense, the WiFi CSI provides valuable information to recognize the IN sources through deep learning (DL) strategies. Two DL models have been proposed and tested on two experimental data sets for multiclass and multilabel analysis; in multiclass, devices can operate alone during the measurement, and in multilabel, multiple devices can work simultaneously in a more realistic scenario. The model transferability between location and days has also been evaluated by analyzing two different IN feature sets for device classification with the Few-shot-learning (FSL) model. Results show that the proposed DL models can recognize multiple devices working simultaneously through the IN and also offer an acceptable transferability performance (

\sim

80% accuracy for a five-class problem).

发动机和运行中的电气设备产生电磁脉冲，也称为脉冲噪声（in），干扰无线信号。IN将影响信道估计过程，因此，它存在于无线接收器提供的信道状态信息（CSI）中。在本文中，考虑到每台机器都有独特的脉冲噪声模式，脉冲噪声（In）被用作电子设备的指纹来识别干扰WiFi信号的In源。从这个意义上说，WiFi CSI通过深度学习（DL）策略为识别In源提供了有价值的信息。提出了两个深度学习模型，并在两个实验数据集上进行了多类和多标签分析的测试；在多类别中，设备可以在测量过程中单独运行，而在多标签中，多个设备可以在更现实的场景中同时工作。通过使用Few-shot-learning （FSL）模型分析两种不同的设备分类IN特征集，还评估了模型在位置和日期之间的可转移性。结果表明，所提出的深度学习模型可以识别通过IN同时工作的多个设备，并且还提供了可接受的可转移性性能（对于五类问题的准确率为80%）。

{"title":"Machinery detection by impulsive noise recognition using WiFi sensing","authors":"Iratxe Landa , Guillermo Diaz , Iker Sobron , Iñaki Eizmendi , Manuel Velez","doi":"10.1016/j.pmcj.2025.102018","DOIUrl":"10.1016/j.pmcj.2025.102018","url":null,"abstract":"<div><div>Engines and electrical devices in operation generate electromagnetic pulses, also called impulsive noise (IN), that interfere with wireless signals. The IN shall affect the channel estimation process and is, therefore, present in the channel state information (CSI) provided by wireless receivers. In this paper, impulsive noise (IN) is used as a fingerprint of electrical devices to identify the IN sources that interfere with a WiFi signal, taking into account that each individual machine has a unique pattern of impulsive noise. In this sense, the WiFi CSI provides valuable information to recognize the IN sources through deep learning (DL) strategies. Two DL models have been proposed and tested on two experimental data sets for multiclass and multilabel analysis; in multiclass, devices can operate alone during the measurement, and in multilabel, multiple devices can work simultaneously in a more realistic scenario. The model transferability between location and days has also been evaluated by analyzing two different IN feature sets for device classification with the Few-shot-learning (FSL) model. Results show that the proposed DL models can recognize multiple devices working simultaneously through the IN and also offer an acceptable transferability performance (<span><math><mo>∼</mo></math></span> 80% accuracy for a five-class problem).</div></div>","PeriodicalId":49005,"journal":{"name":"Pervasive and Mobile Computing","volume":"107 ","pages":"Article 102018"},"PeriodicalIF":3.0,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143348979","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

Advancing user-space networking for DDS message-oriented middleware: Further extensions 为DDS面向消息的中间件推进用户空间网络：进一步扩展

IF 3 3区计算机科学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

Pervasive and Mobile Computing

Pub Date : 2025-02-01 DOI: 10.1016/j.pmcj.2025.102013

Vincent Bode , Carsten Trinitis , Martin Schulz , David Buettner , Tobias Preclik

Due to the flexibility it offers, publish–subscribe messaging middleware is a popular choice in Industrial IoT (IIoT) applications. The Data Distribution Service (DDS) is a widely used industry standard for these systems with a focus on versatility and extensibility, implemented by multiple vendors and present in myriad deployments across industries like aerospace, healthcare and industrial automation. However, many IoT scenarios require real-time capabilities for deployments with rigid timing, reliability and resource constraints, while publish–subscribe mechanisms currently rely on components that are not strictly real-time capable, such as the Linux networking stack, making it hard to provide robust performance guarantees without large safety margins.

In order to make publish–subscribe approaches viable and efficient also in such real-time scenarios, we introduce user-space DDS networking transport extensions, allowing us to fast-track the communication hot path by bypassing the Linux kernel. For this purpose, we extend the best-performing vendor implementation from a previous study, CycloneDDS, to include modules for two widespread user-space networking technologies, the Data Plane Development Kit (DPDK) and the eXpress Data Path (XDP). Building on this, we additionally offer two more extensions to the second most performant implementation FastDDS, also based on DPDK and XDP, and realize novel optimizations not present in the original extension implementations. We evaluate each extension’s performance benefits against four existing DDS implementations (OpenDDS, RTI Connext, FastDDS and CycloneDDS). The DPDK-based and XDP-based extensions offer a performance benefit of 31%–38% and 18%–22% reduced mean latency, respectively, as well as an increase in bandwidth and sample rate throughput of at least 160%, while reducing the latency bound by at least 93%, demonstrating the performance and dependability advantages of circumventing the kernel for real-time communications.

由于其提供的灵活性，发布-订阅消息传递中间件是工业物联网（IIoT）应用程序中的流行选择。数据分发服务（DDS）是这些系统广泛使用的行业标准，其重点是多功能性和可扩展性，由多个供应商实现，并在航空航天、医疗保健和工业自动化等行业的无数部署中出现。然而，许多物联网场景需要具有严格定时、可靠性和资源约束的部署的实时能力，而发布-订阅机制目前依赖于不具有严格实时能力的组件，例如Linux网络堆栈，因此在没有大安全裕度的情况下很难提供强大的性能保证。为了使发布-订阅方法在这种实时场景中也可行且高效，我们引入了用户空间DDS网络传输扩展，允许我们绕过Linux内核快速跟踪通信热路径。为此，我们从之前的研究中扩展了性能最好的供应商实现，CycloneDDS，包括两种广泛的用户空间网络技术的模块，数据平面开发工具包（DPDK）和快速数据路径（XDP）。在此基础上，我们还为性能第二高的实现FastDDS（同样基于DPDK和XDP）提供了另外两个扩展，并实现了原始扩展实现中没有的新优化。我们针对四种现有的DDS实现（OpenDDS、RTI Connext、FastDDS和CycloneDDS）评估了每个扩展的性能优势。基于dpdk和基于xdp的扩展分别提供了31%-38%和18%-22%的性能优势，平均延迟分别减少了31%-38%和18%-22%，带宽和采样率吞吐量增加了至少160%，同时延迟限制减少了至少93%，证明了绕过内核进行实时通信的性能和可靠性优势。

{"title":"Advancing user-space networking for DDS message-oriented middleware: Further extensions","authors":"Vincent Bode , Carsten Trinitis , Martin Schulz , David Buettner , Tobias Preclik","doi":"10.1016/j.pmcj.2025.102013","DOIUrl":"10.1016/j.pmcj.2025.102013","url":null,"abstract":"<div><div>Due to the flexibility it offers, publish–subscribe messaging middleware is a popular choice in Industrial IoT (IIoT) applications. The Data Distribution Service (DDS) is a widely used industry standard for these systems with a focus on versatility and extensibility, implemented by multiple vendors and present in myriad deployments across industries like aerospace, healthcare and industrial automation. However, many IoT scenarios require real-time capabilities for deployments with rigid timing, reliability and resource constraints, while publish–subscribe mechanisms currently rely on components that are not strictly real-time capable, such as the Linux networking stack, making it hard to provide robust performance guarantees without large safety margins.</div><div>In order to make publish–subscribe approaches viable and efficient also in such real-time scenarios, we introduce user-space DDS networking transport extensions, allowing us to fast-track the communication hot path by bypassing the Linux kernel. For this purpose, we extend the best-performing vendor implementation from a previous study, CycloneDDS, to include modules for two widespread user-space networking technologies, the Data Plane Development Kit (DPDK) and the eXpress Data Path (XDP). Building on this, we additionally offer two more extensions to the second most performant implementation FastDDS, also based on DPDK and XDP, and realize novel optimizations not present in the original extension implementations. We evaluate each extension’s performance benefits against four existing DDS implementations (OpenDDS, RTI Connext, FastDDS and CycloneDDS). The DPDK-based and XDP-based extensions offer a performance benefit of 31%–38% and 18%–22% reduced mean latency, respectively, as well as an increase in bandwidth and sample rate throughput of at least 160%, while reducing the latency bound by at least 93%, demonstrating the performance and dependability advantages of circumventing the kernel for real-time communications.</div></div>","PeriodicalId":49005,"journal":{"name":"Pervasive and Mobile Computing","volume":"107 ","pages":"Article 102013"},"PeriodicalIF":3.0,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143356384","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

FastPlan: A three-step framework for accelerating drone-centric search operations in post-disaster relief FastPlan：在灾后救援中加速以无人机为中心的搜索行动的三步框架

IF 3 3区计算机科学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

Pervasive and Mobile Computing

Pub Date : 2025-02-01 DOI: 10.1016/j.pmcj.2025.102017

Sunho Lim , Ingyu Lee , Gyu Sang Choi , Jinseok Chae , Ellora Ashish , Eric Ward , Cong Pu

Commercially well-known drones are increasingly popular and have been deployed in post-disaster relief to support traditional search and rescue operations. However, there are still barriers to conducting a drone-centric search operation, including but not limited to operational difficulty for non-professional drone pilots, inefficient pre-planned path, and more importantly initial setup delay. In this paper, we propose a small-scale prototype of a mobile framework, called FastPlan, to facilitate the development for expediting drone-centric search decisions and operations. The basic idea is to automate the required search operations with no or minimized user intervention. The framework consists of three major operations: map extraction, clustering, and path planning. We extract a set of target POIs and metadata from a public map (i.e., Google Maps) integrated with a customized local database to decide where and what to search. Then we deploy simple density-based clustering and search priority-based path planning strategies to efficiently group and cover the POIs. The framework can be extended flexibly by replacing individual operations with an alternative depending on the search priority, like a Lego block. We implement the framework as an Android-based mobile software (App) for a proof-of-the-concept and conduct extensive simulation experiments for performance evaluation. We analyze the different performance behavior and their implication and applicability. The results indicate that the proposed framework can be a viable approach to post-disaster relief.

商业上知名的无人机越来越受欢迎，并已部署在灾后救援中，以支持传统的搜救行动。然而，进行以无人机为中心的搜索操作仍然存在障碍，包括但不限于非专业无人机飞行员的操作难度，低效的预先规划路径，更重要的是初始设置延迟。在本文中，我们提出了一个名为FastPlan的小型移动框架原型，以促进以无人机为中心的搜索决策和操作的快速发展。其基本思想是在没有或最小化用户干预的情况下自动执行所需的搜索操作。该框架包括三个主要操作：地图提取、聚类和路径规划。我们从公共地图（即谷歌Maps）中提取一组目标poi和元数据，并与定制的本地数据库集成，以决定搜索的位置和内容。然后，我们部署简单的基于密度的聚类和基于搜索优先级的路径规划策略来有效地分组和覆盖poi。通过根据搜索优先级（如乐高积木）替换单个操作，可以灵活地扩展框架。我们将该框架作为基于android的移动软件（App）实现，以进行概念验证，并进行广泛的模拟实验以进行性能评估。分析了不同的性能行为及其含义和适用性。结果表明，该框架是一种可行的灾后救援方法。

{"title":"FastPlan: A three-step framework for accelerating drone-centric search operations in post-disaster relief","authors":"Sunho Lim , Ingyu Lee , Gyu Sang Choi , Jinseok Chae , Ellora Ashish , Eric Ward , Cong Pu","doi":"10.1016/j.pmcj.2025.102017","DOIUrl":"10.1016/j.pmcj.2025.102017","url":null,"abstract":"<div><div>Commercially well-known drones are increasingly popular and have been deployed in post-disaster relief to support traditional search and rescue operations. However, there are still barriers to conducting a drone-centric search operation, including but not limited to operational difficulty for non-professional drone pilots, inefficient pre-planned path, and more importantly initial setup delay. In this paper, we propose a small-scale prototype of a mobile framework, called <em>FastPlan</em>, to facilitate the development for expediting drone-centric search decisions and operations. The basic idea is to automate the required search operations with no or minimized user intervention. The framework consists of three major operations: map extraction, clustering, and path planning. We extract a set of target POIs and metadata from a public map (i.e., Google Maps) integrated with a customized local database to decide where and what to search. Then we deploy simple density-based clustering and search priority-based path planning strategies to efficiently group and cover the POIs. The framework can be extended flexibly by replacing individual operations with an alternative depending on the search priority, like a Lego block. We implement the framework as an Android-based mobile software (App) for a proof-of-the-concept and conduct extensive simulation experiments for performance evaluation. We analyze the different performance behavior and their implication and applicability. The results indicate that the proposed framework can be a viable approach to post-disaster relief.</div></div>","PeriodicalId":49005,"journal":{"name":"Pervasive and Mobile Computing","volume":"107 ","pages":"Article 102017"},"PeriodicalIF":3.0,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143155593","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

TrustMD — A multi-layer framework for domain, edge and D2D caching based on trust dissemination and blockchain TrustMD——基于信任传播和区块链的域、边缘和D2D缓存的多层框架

IF 3 3区计算机科学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

Pervasive and Mobile Computing

Pub Date : 2025-02-01 DOI: 10.1016/j.pmcj.2025.102015

Acquila Santos Rocha , Billy Anderson Pinheiro , Weverton Cordeiro , Vinicius C.M. Borges

Device-to-Device communication (D2D), combined with edge caching and distinct domains, is a promising approach for offloading data from wireless mobile networks. However, user security is still an open issue in D2D communication. Security vulnerabilities remain possible as a side effect of enabling straightforward, direct, and spontaneous interactions between untrustworthy users. To address this issue, this work involves designing TrustMD (Trust Multiple Domain), a multi-layer framework combining diverse technologies inspired by blockchain and trust management to develop a secure and scalable framework for multi-domain, edge, and D2D caching layers. Specifically, TrustMD combines edge trust storage with blockchain for distributed storage management in a multi-layer architecture designed to store trust control data in edge efficiently and D2D networks across different domains. Our experiments with TrustMD showed a significant improvement in data goodput, reaching as high as 95% of the total network throughput. In contrast, state-of-the-art approaches without trust control dissemination achieved at most 80%. Even though we observed a 7% increase in D2D overhead, TrustMD can effectively control latency levels. TrustMD managed security effectively without compromising network performance, reducing false negative rates up to 31% in the best-case scenario. TrustMD offers a scalable and effective security solution that boosts network performance and ensures robust protection.

设备到设备通信（D2D）结合边缘缓存和不同域，是一种很有前途的从无线移动网络中卸载数据的方法。然而，在D2D通信中，用户安全仍然是一个悬而未决的问题。在不可信的用户之间支持直接、直接和自发交互的副作用仍然存在安全漏洞。为了解决这个问题，这项工作涉及设计TrustMD（信任多域），这是一个多层框架，结合了受区块链和信任管理启发的各种技术，为多域、边缘和D2D缓存层开发一个安全且可扩展的框架。具体来说，TrustMD将边缘信任存储与区块链相结合，在多层架构中进行分布式存储管理，旨在有效地将信任控制数据存储在边缘和跨不同域的D2D网络中。我们对TrustMD的实验表明，在数据传输方面有了显著的改善，达到了总网络吞吐量的95%。相比之下，没有信任控制传播的最先进方法最多达到80%。尽管我们观察到D2D开销增加了7%，但TrustMD可以有效地控制延迟水平。TrustMD在不影响网络性能的情况下有效地管理安全性，在最佳情况下可将误报率降低31%。TrustMD提供了一个可扩展和有效的安全解决方案，提高网络性能，并确保强大的保护。

{"title":"TrustMD — A multi-layer framework for domain, edge and D2D caching based on trust dissemination and blockchain","authors":"Acquila Santos Rocha , Billy Anderson Pinheiro , Weverton Cordeiro , Vinicius C.M. Borges","doi":"10.1016/j.pmcj.2025.102015","DOIUrl":"10.1016/j.pmcj.2025.102015","url":null,"abstract":"<div><div>Device-to-Device communication (D2D), combined with edge caching and distinct domains, is a promising approach for offloading data from wireless mobile networks. However, user security is still an open issue in D2D communication. Security vulnerabilities remain possible as a side effect of enabling straightforward, direct, and spontaneous interactions between untrustworthy users. To address this issue, this work involves designing TrustMD (Trust Multiple Domain), a multi-layer framework combining diverse technologies inspired by blockchain and trust management to develop a secure and scalable framework for multi-domain, edge, and D2D caching layers. Specifically, TrustMD combines edge trust storage with blockchain for distributed storage management in a multi-layer architecture designed to store trust control data in edge efficiently and D2D networks across different domains. Our experiments with TrustMD showed a significant improvement in data goodput, reaching as high as 95% of the total network throughput. In contrast, state-of-the-art approaches without trust control dissemination achieved at most 80%. Even though we observed a 7% increase in D2D overhead, TrustMD can effectively control latency levels. TrustMD managed security effectively without compromising network performance, reducing false negative rates up to 31% in the best-case scenario. TrustMD offers a scalable and effective security solution that boosts network performance and ensures robust protection.</div></div>","PeriodicalId":49005,"journal":{"name":"Pervasive and Mobile Computing","volume":"107 ","pages":"Article 102015"},"PeriodicalIF":3.0,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143376981","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

Enhancing crowdsourcing through skill and willingness-aligned task assignment with workforce composition balance 通过技能和意愿与劳动力构成平衡相一致的任务分配来增强众包

IF 3 3区计算机科学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

Pervasive and Mobile Computing

Pub Date : 2025-02-01 DOI: 10.1016/j.pmcj.2025.102012

Riya Samanta , Soumya K. Ghosh , Sajal K. Das

Crowdsourcing platforms face critical challenges in task assignment and workforce retention, particularly in aligning complex, skill-intensive tasks with crowd-worker willingness and potential while ensuring workforce diversity and balanced composition. This study introduces the Skill-Aligned Task Assignment and Potential-Aware Workforce Composition (SATA-PAW) framework to address these challenges. The proposed framework formulates the Task Assignment with Workforce Composition Balance (TACOMB) problem as a multi-constraint optimization task, aiming to maximize net utility under task budget constraints while promoting balanced workforce composition. SATA-PAW integrates two novel algorithms, Skill-Aligned Task Assignment (SATA), which optimizes task-worker matching by considering skills, willingness, and budget constraints, and Potential-Aware Workforce Composition (PAW), which leverages satisfaction score and latent potential to retain skilled workers and improve workforce diversity. Experimental evaluations on real-world (UpWork) and synthetic datasets demonstrate SATA-PAW’s superiority over five state-of-the-art methods. The results highlight SATA-PAW’s ability to integrate human-centric factors with efficient optimization, setting a new benchmark for skill-oriented task assignment and balanced workforce composition in crowdsourcing systems.

众包平台在任务分配和员工保留方面面临着严峻的挑战，特别是在确保劳动力多样性和平衡构成的同时，如何将复杂的、技能密集型的任务与众包工人的意愿和潜力结合起来。本研究引入了技能对齐任务分配和潜力感知劳动力构成（SATA-PAW）框架来解决这些挑战。该框架将劳动力构成平衡任务分配（Task Assignment with Workforce Composition Balance， TACOMB）问题表述为一个多约束优化任务，目的是在任务预算约束下实现净效用最大化，同时促进劳动力构成平衡。SATA-PAW集成了两种新颖的算法，一种是技能对齐任务分配（SATA）算法，它通过考虑技能、意愿和预算约束来优化任务与工人的匹配；另一种是潜力感知劳动力构成（PAW）算法，它利用满意度评分和潜在潜力来留住熟练工人，并提高劳动力多样性。在真实世界（UpWork）和合成数据集上的实验评估表明，SATA-PAW优于五种最先进的方法。结果表明，SATA-PAW能够将以人为中心的因素与高效优化相结合，为众包系统中以技能为导向的任务分配和平衡的劳动力构成设定了新的基准。

{"title":"Enhancing crowdsourcing through skill and willingness-aligned task assignment with workforce composition balance","authors":"Riya Samanta , Soumya K. Ghosh , Sajal K. Das","doi":"10.1016/j.pmcj.2025.102012","DOIUrl":"10.1016/j.pmcj.2025.102012","url":null,"abstract":"<div><div>Crowdsourcing platforms face critical challenges in task assignment and workforce retention, particularly in aligning complex, skill-intensive tasks with crowd-worker willingness and potential while ensuring workforce diversity and balanced composition. This study introduces the Skill-Aligned Task Assignment and Potential-Aware Workforce Composition (SATA-PAW) framework to address these challenges. The proposed framework formulates the Task Assignment with Workforce Composition Balance (TACOMB) problem as a multi-constraint optimization task, aiming to maximize net utility under task budget constraints while promoting balanced workforce composition. SATA-PAW integrates two novel algorithms, Skill-Aligned Task Assignment (SATA), which optimizes task-worker matching by considering skills, willingness, and budget constraints, and Potential-Aware Workforce Composition (PAW), which leverages satisfaction score and latent potential to retain skilled workers and improve workforce diversity. Experimental evaluations on real-world (UpWork) and synthetic datasets demonstrate SATA-PAW’s superiority over five state-of-the-art methods. The results highlight SATA-PAW’s ability to integrate human-centric factors with efficient optimization, setting a new benchmark for skill-oriented task assignment and balanced workforce composition in crowdsourcing systems.</div></div>","PeriodicalId":49005,"journal":{"name":"Pervasive and Mobile Computing","volume":"107 ","pages":"Article 102012"},"PeriodicalIF":3.0,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143155954","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

Vspp: Verifiable, shareable, and privacy-preserving access control scheme for IoV Vspp：可验证、可共享、保护隐私的IoV访问控制方案

IF 3 3区计算机科学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

Pervasive and Mobile Computing

Pub Date : 2025-02-01 DOI: 10.1016/j.pmcj.2025.102014

Youwang Sun , Chunhua Jin , Xinying Liu , Lingwen Kong , Changhui Yu , Guanhua Chen , Liqing Chen

Internet of Vehicles (IoV) is a specialized application of Internet of Things (IoT), which interconnects vehicles and cloud platforms by using various communication devices and computing technologies to realize the transmission and sharing of vehicle information and enhance the driving experience. However, vehicle users face challenges in identity, data, and inside security when using IoV. In order to solve these problems, we propose a verifiable, shareable, and privacy-preserving access control scheme for IoV. In our scheme, we use zero-knowledge proof (ZKP) to ensure the security of user identity. More specifically, it can enable user anonymity and authenticity without revealing any additional information associated with the user. Meanwhile, we employ proxy re-encryption (PRE) to provide confidential sharing and secure the operation of data. In addition, we use the cryptographic reverse firewall (CRF) to ensure users’ internal security. It can prevent algorithm substitution attacks while ensuring chosen plaintext attack security. Finally, compared to other schemes, our scheme not only enables anonymity, traceability, unlinkability, and confidentiality but is also resistant to insider attacks. Performance evaluation shows that our scheme surpasses the other schemes in terms of time and storage costs.

车联网（IoV）是物联网（IoT）的专门应用，通过各种通信设备和计算技术将车辆与云平台互联，实现车辆信息的传输和共享，提升驾驶体验。然而，车辆用户在使用车联网时面临着身份、数据和内部安全方面的挑战。为了解决这些问题，我们提出了一种可验证、可共享、保护隐私的车联网访问控制方案。在我们的方案中，我们使用零知识证明（ZKP）来确保用户身份的安全性。更具体地说，它可以实现用户匿名性和真实性，而不会泄露与用户相关的任何附加信息。同时，采用代理再加密（PRE）技术实现数据的保密共享，保证数据的安全运行。此外，我们使用加密反向防火墙（CRF）来确保用户的内部安全。在保证所选明文攻击安全性的同时，可以防止算法替代攻击。最后，与其他方案相比，我们的方案不仅具有匿名性、可追溯性、不可链接性和保密性，而且还具有抗内部攻击的能力。性能评估表明，我们的方案在时间和存储成本方面优于其他方案。

{"title":"Vspp: Verifiable, shareable, and privacy-preserving access control scheme for IoV","authors":"Youwang Sun , Chunhua Jin , Xinying Liu , Lingwen Kong , Changhui Yu , Guanhua Chen , Liqing Chen","doi":"10.1016/j.pmcj.2025.102014","DOIUrl":"10.1016/j.pmcj.2025.102014","url":null,"abstract":"<div><div>Internet of Vehicles (IoV) is a specialized application of Internet of Things (IoT), which interconnects vehicles and cloud platforms by using various communication devices and computing technologies to realize the transmission and sharing of vehicle information and enhance the driving experience. However, vehicle users face challenges in identity, data, and inside security when using IoV. In order to solve these problems, we propose a verifiable, shareable, and privacy-preserving access control scheme for IoV. In our scheme, we use zero-knowledge proof (ZKP) to ensure the security of user identity. More specifically, it can enable user anonymity and authenticity without revealing any additional information associated with the user. Meanwhile, we employ proxy re-encryption (PRE) to provide confidential sharing and secure the operation of data. In addition, we use the cryptographic reverse firewall (CRF) to ensure users’ internal security. It can prevent algorithm substitution attacks while ensuring chosen plaintext attack security. Finally, compared to other schemes, our scheme not only enables anonymity, traceability, unlinkability, and confidentiality but is also resistant to insider attacks. Performance evaluation shows that our scheme surpasses the other schemes in terms of time and storage costs.</div></div>","PeriodicalId":49005,"journal":{"name":"Pervasive and Mobile Computing","volume":"107 ","pages":"Article 102014"},"PeriodicalIF":3.0,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143387009","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

Collective victim counting in post-disaster response: A distributed, power-efficient algorithm via BLE spontaneous networks 灾后响应中的集体受害者计数：一种基于BLE自发网络的分布式节能算法

IF 3 3区计算机科学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

Pervasive and Mobile Computing

Pub Date : 2024-11-28 DOI: 10.1016/j.pmcj.2024.101997

Giacomo Longo , Alessandro Cantelli-Forti , Enrico Russo , Francesco Lupia , Martin Strohmeier , Andrea Pugliese

Accurately determining the number of people affected by emergencies is essential for deploying effective response measures during disasters. Traditional solutions like cellular and Wi-Fi networks are often rendered ineffective during such emergencies due to widespread infrastructure damage or non-functional connectivity, prompting the exploration of more resilient methods. This paper proposes a novel solution utilizing Bluetooth Low Energy (BLE) technology and decentralized networks composed entirely of mobile and wearable devices to count individuals autonomously without reliance on external communication equipment or specialized personnel. This count leverages uncoordinated relayed communication among devices within these networks, enabling us to extend our counting capabilities well beyond the direct range of rescuers. A formally evaluated, experimentally validated, and privacy-preserving counting algorithm that demonstrates rapid convergence and high accuracy even in large-scale scenarios is employed.

准确确定受紧急情况影响的人数对于在灾害期间部署有效的应对措施至关重要。在这种紧急情况下，蜂窝和Wi-Fi网络等传统解决方案往往因基础设施大面积受损或连接功能不佳而失效，这促使人们探索更有弹性的方法。本文提出了一种新颖的解决方案，利用蓝牙低功耗（BLE）技术和完全由移动和可穿戴设备组成的分散网络，在不依赖外部通信设备或专业人员的情况下自主计数个体。这种计数利用了这些网络中设备之间不协调的中继通信，使我们能够将计数能力扩展到救援人员的直接范围之外。采用了一种经过正式评估、实验验证和保护隐私的计数算法，即使在大规模场景中也能显示出快速收敛和高精度。

{"title":"Collective victim counting in post-disaster response: A distributed, power-efficient algorithm via BLE spontaneous networks","authors":"Giacomo Longo , Alessandro Cantelli-Forti , Enrico Russo , Francesco Lupia , Martin Strohmeier , Andrea Pugliese","doi":"10.1016/j.pmcj.2024.101997","DOIUrl":"10.1016/j.pmcj.2024.101997","url":null,"abstract":"<div><div>Accurately determining the number of people affected by emergencies is essential for deploying effective response measures during disasters. Traditional solutions like cellular and Wi-Fi networks are often rendered ineffective during such emergencies due to widespread infrastructure damage or non-functional connectivity, prompting the exploration of more resilient methods. This paper proposes a novel solution utilizing Bluetooth Low Energy (BLE) technology and decentralized networks composed entirely of mobile and wearable devices to count individuals autonomously without reliance on external communication equipment or specialized personnel. This count leverages uncoordinated relayed communication among devices within these networks, enabling us to extend our counting capabilities well beyond the direct range of rescuers. A formally evaluated, experimentally validated, and privacy-preserving counting algorithm that demonstrates rapid convergence and high accuracy even in large-scale scenarios is employed.</div></div>","PeriodicalId":49005,"journal":{"name":"Pervasive and Mobile Computing","volume":"106 ","pages":"Article 101997"},"PeriodicalIF":3.0,"publicationDate":"2024-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142757430","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

Three-dimensional spectrum coverage gap map construction in cellular networks: A non-linear estimation approach 蜂窝网络中三维频谱覆盖缺口图的构建：一种非线性估计方法

IF 3 3区计算机科学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

Pervasive and Mobile Computing

Pub Date : 2024-11-23 DOI: 10.1016/j.pmcj.2024.101998

Ahmed Fahim Mostafa , Mohamed Abdel-Kader , Yasser Gadallah

Data collection techniques can be used to determine the coverage conditions of a cellular communication network within a given area. In such tasks, the data acquisition process faces significant challenges for larger or inaccessible locations. Such challenges can be alleviated through the use of unmanned aerial vehicles (UAVs). This way, data acquisition obstacles can be overcome to acquire and process the necessary data points with relative ease to estimate a full area coverage map for the concerned network. In this study, we formulate the problem of deploying a UAV to acquire the minimum possible measurement data points in a geographical region for the purpose of constructing a full communication coverage gap map for this region. We then devise an estimation model that utilizes the measured data samples and determines the noise/loss levels of the communication links at the other unvisited spots of the region accordingly. The proposed estimation model is based on a cascade-forward neural network to allow for both nonlinear and direct linear relationships between the input data and the output estimations. We further investigate the conventional method of using linear regression estimators to decide on the received power levels at the different locations of the examined area. Our simulation evaluations show that the proposed nonlinear estimator outperforms the conventional linear regression technique in terms of the communication coverage error level while using the minimum possible collected data points. These minimum data points are then used in constructing a complete coverage gap map visualization that demonstrates the overall network service conditions within the surveyed region.

数据收集技术可用于确定给定区域内蜂窝通信网的覆盖条件。在这些任务中，对于较大或难以进入的位置，数据采集过程面临重大挑战。这些挑战可以通过使用无人驾驶飞行器（uav）来缓解。这样，可以克服数据获取障碍，相对容易地获取和处理必要的数据点，以估计有关网络的全区域覆盖图。在本研究中，我们提出了部署无人机获取地理区域内尽可能少的测量数据点的问题，目的是构建该区域的全通信覆盖缺口图。然后，我们设计了一个估计模型，该模型利用测量的数据样本，并相应地确定该地区其他未访问点的通信链路的噪声/损耗水平。所提出的估计模型基于级联前向神经网络，允许输入数据和输出估计之间的非线性和直接线性关系。我们进一步研究了使用线性回归估计的传统方法来确定在检查区域不同位置的接收功率水平。我们的模拟评估表明，所提出的非线性估计器在使用尽可能少的收集数据点的情况下，在通信覆盖误差水平方面优于传统的线性回归技术。然后使用这些最小数据点构建完整的覆盖缺口图可视化，显示调查区域内的整体网络服务状况。

{"title":"Three-dimensional spectrum coverage gap map construction in cellular networks: A non-linear estimation approach","authors":"Ahmed Fahim Mostafa , Mohamed Abdel-Kader , Yasser Gadallah","doi":"10.1016/j.pmcj.2024.101998","DOIUrl":"10.1016/j.pmcj.2024.101998","url":null,"abstract":"<div><div>Data collection techniques can be used to determine the coverage conditions of a cellular communication network within a given area. In such tasks, the data acquisition process faces significant challenges for larger or inaccessible locations. Such challenges can be alleviated through the use of unmanned aerial vehicles (UAVs). This way, data acquisition obstacles can be overcome to acquire and process the necessary data points with relative ease to estimate a full area coverage map for the concerned network. In this study, we formulate the problem of deploying a UAV to acquire the minimum possible measurement data points in a geographical region for the purpose of constructing a full communication coverage gap map for this region. We then devise an estimation model that utilizes the measured data samples and determines the noise/loss levels of the communication links at the other unvisited spots of the region accordingly. The proposed estimation model is based on a cascade-forward neural network to allow for both nonlinear and direct linear relationships between the input data and the output estimations. We further investigate the conventional method of using linear regression estimators to decide on the received power levels at the different locations of the examined area. Our simulation evaluations show that the proposed nonlinear estimator outperforms the conventional linear regression technique in terms of the communication coverage error level while using the minimum possible collected data points. These minimum data points are then used in constructing a complete coverage gap map visualization that demonstrates the overall network service conditions within the surveyed region.</div></div>","PeriodicalId":49005,"journal":{"name":"Pervasive and Mobile Computing","volume":"106 ","pages":"Article 101998"},"PeriodicalIF":3.0,"publicationDate":"2024-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142758973","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

Blockchain-Inspired Trust Management in Cognitive Radio Networks with Cooperative Spectrum Sensing 合作频谱感知认知无线电网络中的区块链启发式信任管理

IF 3 3区计算机科学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

Pervasive and Mobile Computing

Pub Date : 2024-11-20 DOI: 10.1016/j.pmcj.2024.101999

Mahsa Mahvash , Neda Moghim , Mojtaba Mahdavi , Mahdieh Amiri , Sachin Shetty

Cooperative spectrum sensing (CSS) in cognitive radio networks (CRNs) enhances spectral decision-making precision but introduces vulnerabilities to malicious secondary user (SU) attacks. This paper proposes a decentralized trust and reputation management (TRM) framework to address these vulnerabilities, emphasizing the need to mitigate risks associated with centralized systems. Inspired by blockchain technology, we present a distributed TRM method for CSS in CRNs, significantly reducing the impact of malicious attacks. Our approach leverages a Proof of Trust (PoT) system to enhance the integrity of CSS, thereby improving the accuracy of spectral decision-making while reducing false positives and false negatives. In this system, SUs’ trust scores are dynamically updated based on their sensing reports, and they will collaboratively participate in new blocks' formation using the trust scores. Simulation results validate the effectiveness of the proposed method, indicating its potential to enhance security and reliability in CRNs.

认知无线电网络（CRN）中的合作频谱感知（CSS）提高了频谱决策的精确度，但也带来了受到恶意次级用户（SU）攻击的漏洞。本文提出了一种去中心化的信任和声誉管理（TRM）框架来解决这些漏洞，强调需要降低与中心化系统相关的风险。受区块链技术的启发，我们提出了一种适用于 CRN 中 CSS 的分布式 TRM 方法，大大降低了恶意攻击的影响。我们的方法利用信任证明（PoT）系统来增强 CSS 的完整性，从而提高频谱决策的准确性，同时减少误报和误报。在该系统中，SU 的信任分数会根据其感知报告动态更新，它们将利用信任分数协同参与新区块的形成。仿真结果验证了所提方法的有效性，表明该方法具有提高 CRN 安全性和可靠性的潜力。

引用次数: 0