The Internet of Things (IoT) networks are poised to play a critical role in providing ultra-low latency and high bandwidth communications in various real-world IoT scenarios. Assuring end-to-end secure, energy- aware,...
详细信息
The Internet of Things (IoT) networks are poised to play a critical role in providing ultra-low latency and high bandwidth communications in various real-world IoT scenarios. Assuring end-to-end secure, energy- aware, reliable, real-time IoT communication is hard due to the heterogeneity and transient behavior of IoT networks. Additionally, the lack of integrated approaches to efficiently schedule IoT tasks and holistically offload computing resources, and computational limits in IoT systems to achieve effective resource utilization. This paper makes three contributions to research on overcoming these problems in the context of distributed IoT systems that use the Software Defined Networking (SDN) programmable control plane in symbiosis with blockchain to benefit from the dispersed or decentralized, and efficient environment of distributed IoT transactions over Wide Area networks (WANs). First, it introduces a Blockchain-SDN architectural component to reinforce flexibility and trustworthiness and improve the Quality of Service (QoS) of IoT networks. Second, it describes the design of an IoT-focused smart contract that implements the control logic to manage IoT data, detect and report suspected IoT nodes, and mitigate malicious traffic. Third, we introduce a novel consensus algorithm based on the Proof-of-Authority (PoA) to achieve agreements between blockchain-enabled IoT nodes, improve the reliability of IoT edge devices, and establish absolute trust among all smart IoT systems. Experimental results show that integrating SDN with blockchain outperforms traditional Proof-of-Work (PoW) and Practical Byzantine Fault Tolerance (PBFT) algorithms, delivering up to 68% lower latency, 87% higher transaction throughput, and 45% better energy savings.
Collaborative learning in peer-to-peer networks offers the benefits of distributed learning while mitigating the risks associated with single points of failure inherent in centralized servers. However, adversarial wor...
详细信息
ISBN:
(纸本)9783031820724;9783031820731
Collaborative learning in peer-to-peer networks offers the benefits of distributed learning while mitigating the risks associated with single points of failure inherent in centralized servers. However, adversarial workers pose potential threats by attempting to inject malicious information into the network. Thus, ensuring the resilience of peer-to-peer learning emerges as a pivotal research objective. The challenge is exacerbated in the presence of non-convex loss functions and non-iid data distributions. This paper introduces a resilient aggregation technique tailored for such scenarios, aimed at fostering similarity among peers' learning processes. The aggregation weights are determined through an optimization procedure, and use the loss function computed using the neighbor's models and individual private data, thereby addressing concerns regarding data privacy in distributed machine learning. Theoretical analysis demonstrates convergence of parameters with non-convex loss functions and non-iid data distributions. Empirical evaluations across three distinct machine learning tasks support the claims. The empirical findings, which encompass a range of diverse attack models, also demonstrate improved accuracy when compared to existing methodologies.
The advancement towards B5G/6G relies on the synthesis of connect-compute platforms and their use in highly heterogeneous clusters featuring hardware accelerators. While these accelerators offer improved computational...
详细信息
ISBN:
(纸本)9798400704130
The advancement towards B5G/6G relies on the synthesis of connect-compute platforms and their use in highly heterogeneous clusters featuring hardware accelerators. While these accelerators offer improved computational efficiency, sill, they make development, deployment, and orchestration of services more complex, with ***, and necessitate domain-speci.c knowledge. In AI@EDGE we are targeting seamless integration of such diverse platforms for executing AI-related tasks. This paper focuses on acceleration aspects and presents a MEC system that facilitates AI servicing over a cluster of FPGA, GPU, and CPU nodes. To this end, we develop our custom tools for generating multi-variant AI models, informative function descriptors,.exible MEC orchestrators, and runtime resource managers. The results show successful interoperability, with generic Python models getting deployed/migrated across distinct platforms for performance gains in the area of 10x.
In this paper, a new distributed approach for maximizing coverage in a mobile sensor network is proposed. Some results from the multi-agent systems theory are used to generate a control signal composed of both the vel...
详细信息
distributed radar applications have received significant attention in recent years owing to their potential to substantially improve radar performance compared to existing monostatic radar systems. However, in order f...
详细信息
ISBN:
(纸本)9798350375053;9798350375046
distributed radar applications have received significant attention in recent years owing to their potential to substantially improve radar performance compared to existing monostatic radar systems. However, in order for these distributedsystems to work reliably, individual radar nodes in the network must be accurately synchronized in time, phase, and frequency. Synchronization procedures have been recently proposed which enable the compensation of time, phase, and frequency errors entirely in software with no external references or hardware. While previous efforts have demonstrated the time and phase synchronization in hardware, the software-defined frequency synchronization technique has only been demonstrated in theory and simulation. Thus, this paper provides a first-time hardware demonstration of the software-defined frequency synchronization technique using digital radar transceivers. The resulting compensation is demonstrated to achieve better than 10 ppb error on average and is shown to enable coherent summation of signals transmitted by different radar platforms.
This paper introduces a novel ensemble Spike Timing Dependent Plasticity (EnsembleSTDP) approach for implementing Spiking Neural networks (SNNs) with on-chip, online (in-situ) unsupervised learning to accelerate train...
详细信息
Designing and testing distributedsystems can be a daunting task, especially when the system is composed of heterogeneous devices, it is expected to be robust to disruptions, and is meant to scale to a large number of...
详细信息
In recent years, the growth of data has promoted the development of parallel and distributedsystems. Graph embedding is of great importance in improving parallel and distributed system performance. The quality of an ...
详细信息
In recent years, the growth of data has promoted the development of parallel and distributedsystems. Graph embedding is of great importance in improving parallel and distributed system performance. The quality of an embedding can be measured by many important metrics, and wirelength is one of the critical metrics related to communication performance and layout costs of physical systems. The hierarchical cubic network is a well-performing interconnection network and the k-rooted complete binary tree is a data structure with a hierarchical relationship among its various elements in algorithms and programming. In this paper, we solve the problem of the embedding of hierarchical cubic networks into k-rooted complete binary trees with minimum wirelength. We first study the optimal set of the hierarchical cubic network, and propose algorithms to give embedding het which is an embedding scheme of hierarchical cubic networks into k-rooted complete binary trees with minimum wirelength. Moreover, we give the exact minimum wirelength of this embedding. Finally, we conduct comparative experiments to evaluate the performance of embedding het.
The brain-computer interface (BCI) establishes a connection between a device and the human brain, with electroencephalography (EEG) signal is being used as the most common means for such a communication. We use EEG si...
详细信息
ISBN:
(纸本)9798350330991;9798350331004
The brain-computer interface (BCI) establishes a connection between a device and the human brain, with electroencephalography (EEG) signal is being used as the most common means for such a communication. We use EEG signal data that has a very limited number of samples for the motor imagery (MI) classification task. This paper proposes a novel densely connected residual graph convolutional network (DenseResGCN) and uses it in developing a few-shot learning method called FewShotEEG method. Our proposed method is capable of classifying the limited EEG signal data into four MI classes. The proposed method outperforms the state-of-the-arts few-shot methods in terms of the accuracy.
With the rapid development of computer vision technology, automatic image detection technology has become more and more important in various fields. This paper focuses on the reconstruction algorithm in computer image...
详细信息
暂无评论