The objective of augmented reality (AR) is to add digital content to natural images and videos to create an interactive experience between the user and the environment. Scene analysis and object recognition play a cru...
详细信息
This paper starts from the observation that mobile and edge devices are powerful enough to execute Machine Learning (ML) application components, which in turn creates opportunities to keep privacy-sensitive data close...
详细信息
ISBN:
(纸本)9781665439299
This paper starts from the observation that mobile and edge devices are powerful enough to execute Machine Learning (ML) application components, which in turn creates opportunities to keep privacy-sensitive data close to its source. Composing and deploying a distributed ML application is far from trivial because the optimal configuration depends on the application's goals and execution context, both of which may change throughout its lifetime. Prior research on context-aware reconfigurations in ML based applications offer limited capabilities for dynamically migrating software components between mobile, edge and cloud devices. In this paper, we propose a context-aware middleware that enables automated optimizations of the application deployment in order to satisfy the application's functional goals while the execution context changes in terms of available computation, memory and network resources. We use finite state machines to model the reconfiguration of the application based on contextual triggers and facilitate system design through the abstraction of system states. We illustrate the benefits of our approach with an image recognition application with well-defined performance goals that is deployed in a three-tier mobile-edge-cloud architecture.
Mobile Cyber-Physical System (CPS) Swarms are likely to change our daily lives significantly in several application domains, including smart cities, space exploration, environmental monitoring, and transporting system...
详细信息
ISBN:
(纸本)9798350333398
Mobile Cyber-Physical System (CPS) Swarms are likely to change our daily lives significantly in several application domains, including smart cities, space exploration, environmental monitoring, and transporting systems. Yet, industrial projects fundamentally rely on centralized communication infrastructures which in turn lead to suboptimal performance and limited autonomy for both sensing and actuating. To enhance communication and distributed coordination within the swarm, reliable distributedcomputing through consensus protocols constitutes a promising approach. Nonetheless, only a handful of studies has considered evaluating reliable distributedcomputing in Mobile CPS Swarms. The goal of this work is to evaluate the performance of consensus protocols on CPS swarms with processing units deployed on mobile nodes. Running on top of an emulation framework for mobile CPS, our preliminary evaluation focuses on evaluating three key deployment aspects of Mobile CPS Swarms executing a consensus protocol: the effective cost of mobility;the impact of the connectivity of nodes and the eventual network partitions;and the price of continuous routing updates in the mobile environment. Our experimental results indicate the transient network partition in mobile environments are common. They also suggest that the sparsity of dynamic communication network and continuous routing updates have a major impact on the performance of distributed consensus protocols.
Federated Learning (FL) has emerged as a novel distributed Machine Learning (ML) approach, to tackle the challenges associated with data privacy and overload in ML-based intrusion detection systems (IDSs). Drawing ins...
详细信息
ISBN:
(纸本)9798350361261;9798350361278
Federated Learning (FL) has emerged as a novel distributed Machine Learning (ML) approach, to tackle the challenges associated with data privacy and overload in ML-based intrusion detection systems (IDSs). Drawing inspiration from the FL architecture, we have introduced a hybrid ML IDS tailored for Wireless sensor Networks (WSNs). This system is crafted to leverage ML for achieving a two-layer intrusion detection mechanism in WSNs free from constraints posed by specific attack types. The architecture follows a server-client model compatible with the configuration of sensor nodes, sink nodes, and gateways in WSNs. In this setup, client models located at sink nodes undergo training using sensing data while the server model at the gateway is trained using network traffic data. This two-layer training approach amplifies the efficiency of intrusion detection and ensures comprehensive network coverage. The results derived from our simulation experiments corroborate the effectiveness of the proposed hybrid ML IDS. It generates precise aggregation predictions and leads to a substantial reduction in redundant data transmissions. Furthermore, the system exhibits efficacy in detecting intrusions through a dual validation process.
In this paper, we study gossip algorithms in communication models that describe the peer-to-peer networking functionality included in most standard smartphone operating systems. We begin by describing and analyzing a ...
详细信息
ISBN:
(纸本)9781665439299
In this paper, we study gossip algorithms in communication models that describe the peer-to-peer networking functionality included in most standard smartphone operating systems. We begin by describing and analyzing a new synchronous gossip algorithm in this setting that features both a faster round complexity and simpler operation than the best-known existing solutions. We also prove a new lower bound on the rounds required to solve gossip that resolves a minor open question by establishing that existing synchronous solutions are within logarithmic factors of optimal. We then adapt our synchronous algorithm to produce a novel gossip strategy for an asynchronous model that directly captures the interface of a standard smartphone peer-to-peer networking library (enabling algorithms described in this model to be easily implemented on real phones). Using new analysis techniques, we prove that this asynchronous strategy efficiently solves gossip. This is the first known efficient asynchronous information dissemination result for the smartphone peer-to-peer setting. We argue that our new strategy can be used to implement effective information spreading subroutines in real world smartphone peer-to-peer network applications, and that the analytical tools we developed to analyze it can be leveraged to produce other broadly useful algorithmic strategies for this increasingly important setting.
As the current detection solutions of distributed denial of service attacks (DDoS) need additional infrastructures to handle high aggregate data rates, they are not suitable for sensor networks or the internet of thin...
详细信息
ISBN:
(纸本)9781665439299
As the current detection solutions of distributed denial of service attacks (DDoS) need additional infrastructures to handle high aggregate data rates, they are not suitable for sensor networks or the internet of things. Besides, the security architecture of software-defined sensor networks needs to pay attention to the vulnerabilities of both software-defined networks and sensor networks. In this paper, we propose a networka-ware automated machine learning (AutoML) framework, which detects DDoS attacks in software-defined sensor networks. Our framework selects an ideal machine learning algorithm to detect DDoS attacks in network-constrained environments, using the metrics such as variable traffic load, heterogeneous traffic rate, and detection time while preventing over-fitting. Our contributions are two-fold: (i) we first investigate the trade-off between the efficiency of ML algorithms and network/traffic state in the scope of DDoS detection. (ii) we design and implement a software architecture containing open-source network tools, with the deployment of multiple ML algorithms. Lastly, we show that under the denial of service attacks, our framework ensures the traffic packets are still delivered within the network with additional delays.
Internet of Things has emerged as a key technological enabler for broader socio-technical and socio-economic paradigms, such as smart cities and Circular Economy. However, IoT systems are characterised by constraints ...
详细信息
ISBN:
(纸本)9781665439299
Internet of Things has emerged as a key technological enabler for broader socio-technical and socio-economic paradigms, such as smart cities and Circular Economy. However, IoT systems are characterised by constraints and limitations which in order to be overcome they need to be deployed in conjunction and in synergy with other emerging ICT. distributed Ledger Technologies (DLT) can help overcome challenges pertaining to data immutability, timeliness and security. However, the use of DLT does not satisfactorily mitigate security risks and vulnerabilities per se and currently cybersecurity aspects of IoT systems are addressed in a fragmented way. Furthermore, the conflict between the resource demanding Blockchains and the highly constrained nature of IoT devices hinders implementation efforts of corresponding systems. We consider networked systems that comprise both IoT and DLT technologies via the prism of Intelligent Transportation systems (ITS). We elicit a three-tier threat model identifying attack vectors at the Device, the Network and the DLT layers. The identified attacks are then ranked by using the DREAD ranking scheme. The use of the threat model is demonstrated on a novel proof-of-concept IoT networked system implemented using the IOTA Tangle distributed ledger, where it helps to critically appraise the design of the system against the most critical attacks. Furthermore, the developed system is among the first in the literature to demonstrate the synergy of IoT and DLT on actual constrained embedded devices. The performance evaluation provides insights showing that such systems can be efficient and suitable for real-life deployment.
The operation of Internet of Things (IoT) networks and Wireless sensor Networks (WSN) is often disrupted by a number of problems, such as path disconnections, network segmentations, node faults, security attacks, etc....
详细信息
ISBN:
(纸本)9781665439299
The operation of Internet of Things (IoT) networks and Wireless sensor Networks (WSN) is often disrupted by a number of problems, such as path disconnections, network segmentations, node faults, security attacks, etc. A method that gains momentum in resolving some of those issues is the use of mobile nodes or nodes deployed by mobile robots. The use of mobile elements essentially increases the resources and the capacity of the network. In this work, we propose a scheme that utilizes mobile nodes for the creation of alternative paths from source to sink by also accounting the energy levels of the nodes as a contributing factor regarding the creation of alternative paths. We offer both a high level description of the concept and also a detailed algorithmic solution. The evaluation of the solution was performed in a case study of resolving congestion in the network. Results have shown that the proposed algorithm can significantly contribute to the alleviation of the problem of congestion in IoT and WSNs and can easily be used for other types of network problems.
In large cities, road traffic congestion is a big concern especially with its negative effects on the economy and the environment. Hence, with the advance of the IoT and AI many smart solutions are proposed to deal wi...
详细信息
ISBN:
(纸本)9798350333398
In large cities, road traffic congestion is a big concern especially with its negative effects on the economy and the environment. Hence, with the advance of the IoT and AI many smart solutions are proposed to deal with this problem. Yet, those solutions enclosed traffic congestion detection and light street manipulation. However, road jams still occur far away from street lights especially in rush hours and in unexpected situations such as accidents and extreme weather conditions. The aim of this study is to propose a solution that helps vehicles avoid traffic jams and congestions based on data analysis gathered from traffic sensors and from a publish-subscribe application integrated with a distributed system to give vehicle driver a real-time updates about the situation of his road traffic.
Recent advances in Unmanned Aerial Vehicle (UAV) technologies make their use as data collection sinks feasible for practical applications of Wireless sensor Networks (WSN). Using UAVs as mobile data collection agents ...
详细信息
ISBN:
(纸本)9781665439299
Recent advances in Unmanned Aerial Vehicle (UAV) technologies make their use as data collection sinks feasible for practical applications of Wireless sensor Networks (WSN). Using UAVs as mobile data collection agents can improve network performance by reducing the horizontal radio pollution in animal sanctuaries or conservations, for example. This may also positively improve energy consumption of both UAV and sensor nodes (SN) on the ground. Designing an efficient UAV trajectory which has the capability of data gathering from randomly distributed large number of SNs has been one of the challenges for the UAV-aided WSN data gathering solutions. This paper aims at conceptualizing a solution for UAV path planning in gathering data of distributed wireless sensors over a large space. Both efficient flight path and dynamic orchestration of sensor grouping are considered as two key factors for improving the flight performance in data collection. Herein, a classical Travel Salesman Problem (TSP) solution supported by the ground group offerings are used for manipulating a simplified centroid-based trajectory and turning it into a more relaxed fuzzy route. This in turn would offer a ground for smoother and more efficient flight paths. While preliminary modelling of the approach offers encouraging results, the demand for fluidity in dynamically re-orchestrating the ground sensor networks must be carefully considered. Successful implementation of this concept would support a wide range of applications such as the farming and conservation used cases.
暂无评论