Integrating vision-based technologies into distributedsensor domains offers unprecedented potential for data collection. However, it raises privacy concerns over the incredible amount of extra information inadvertent...
详细信息
ISBN:
(纸本)9798350304367;9798350304374
Integrating vision-based technologies into distributedsensor domains offers unprecedented potential for data collection. However, it raises privacy concerns over the incredible amount of extra information inadvertently carried by the video stream. On the other hand, the advent of tiny machine learning models running on edge devices with embedded GPUs/TPUs is revolutionizing computer vision and real-time tracking systems, enabling the local execution of computationally demanding tasks traditionally performed in the cloud. This study focuses on developing and characterizing vision-based virtual sensors capable of processing data from a local camera source to provide real-time measures of relevant metrics without storing or transmitting any video stream. The main advantages of vision-based virtual sensors running on the edge are data protection, reduced communication cost, and reduced detection latency. In addition, we propose a dynamic inference power manager (DIPM), based on adaptive frame rate, that allows us to explore the trade-off between power consumption and accuracy. Experimental results conducted on a real hardware platform show that the proposed virtual sensor, equipped with DIPM, can save up to 40% of the processing energy with a reduction of tracking accuracy lower than 10%, while retaining the privacy preservation benefits of virtual sensors.
In response to the demands and harsh conditions of underwater environments, developing sensor networks and underwater Internet of Things (IoT) has paved the way for wireless communication, ocean exploration, and vario...
详细信息
The measured output current data of distributed energy resources is crucial in realizing cyber-physical DC microgrids (DCMG) and achieving distributed control objectives. This paper proposes an artificial neural netwo...
详细信息
ISBN:
(纸本)9798350363029;9798350363012
The measured output current data of distributed energy resources is crucial in realizing cyber-physical DC microgrids (DCMG) and achieving distributed control objectives. This paper proposes an artificial neural network-based output current estimation at the secondary control level. The estimated output current value is used to implement distributed control successfully for the DCMG. The proposed artificial neural network (ANN) acts as a virtual sensor to alleviate problems associated with physical sensors, such as faults and biasing effects. The ANN's input features and training performance are detailed for the considered DCMG. The performance of the proposed virtual sensor-based distributed controlled DCMG is validated on an experimental hardware setup under multiple load changes and communication delays.
Microservice architectures have become the standard framework for developing scalable distributedsystems, offering significant advantages in managing the integration and evolution of complex applications. Despite the...
详细信息
ISBN:
(纸本)9798350354720;9798350354713
Microservice architectures have become the standard framework for developing scalable distributedsystems, offering significant advantages in managing the integration and evolution of complex applications. Despite their benefits, these architectures face challenges, particularly in effectively diagnosing and resolving performance and reliability issues. Traditional centralized telemetry models, such as those implemented by Prometheus, ELK, and various cloud-based platforms like Datadog or NewRelic, often require complex and costly configurations and are not inherently tailored to the unique requirements of RESTful microservices. While the OpenAPI Specification (OAS) has established itself as a key standard for describing microservice APIs, current centralized tools do not leverage this standard to enhance service analysis effectively. This paper introduces a novel, lightweight, and distributed approach to telemetry that capitalizes on the API information provided by the OAS. Our proposed model aims to simplify the diagnostic process by offering an automated, configuration-free system that provides developers and operations teams access to root cause analysis tools. Additionally, it allows for effective management of telemetry without impacting service performance, thanks to the ability to toggle telemetry features on or off as needed;in doing so, our approach is specially suitable to the dynamic nature of distributedcomputing Continuum (DCC) systems where resources and services may fluctuate and scale. As validation, we provide a first proof of concept consisting of a ready-touse package for the NodeJS ecosystem that has been tested to demonstrate that it can operate with minimal impact on system performance and resource usage.
Dense, low-cost sensor networks can monitor environmental hazards that urban residents are exposed to and that are not always captured by sparsely distributed regulatory monitors. However, knowing where to place senso...
详细信息
ISBN:
(纸本)9798350304367;9798350304374
Dense, low-cost sensor networks can monitor environmental hazards that urban residents are exposed to and that are not always captured by sparsely distributed regulatory monitors. However, knowing where to place sensor nodes in a city remains an open research question, making it difficult to deploy the networks. Network designers generally optimize for area coverage, which does not account for the three-dimensional or social and political nature of cities. Thus, there is a need for new evaluation metrics that network designers can optimize for when deploying urban environmental sensor networks. My PhD thesis addresses this need by proposing new quality metrics that focus on key features needed for successful real-world deployments, including reliability, maintainability, social equity, and certainty of data. This work will help increase the deployment of real-world sensor network deployments by helping cities and network designers see the values of different optimization metrics with the real-world trade-offs, making it easier to determine where to place nodes and how to address the multifaceted needs of cities.
The concept of a distributedcomputing continuum promises to offer a unified view of computing, communication and data resources scattered across edge, fog, and cloud, and utilize them for real-time data analysis, red...
详细信息
ISBN:
(纸本)9798350354720;9798350354713
The concept of a distributedcomputing continuum promises to offer a unified view of computing, communication and data resources scattered across edge, fog, and cloud, and utilize them for real-time data analysis, reducing latency, and improving operational efficiency in industrial settings. This paper explores a special utility of this continuum, i.e. the role of the continuum in facilitating the creation of an industrial metaverse. The concept of the Industrial Metaverse provides a major opportunity for the seamless integration of digital and physical assets in industrial settings. The metaverse consists of multiple worlds, generally manifested as 3D environments enhanced by AR/VR/XR technologies. These virtual worlds can also interact with the physical world, merging realities. In practice, companies within a supply chain network are interconnected;similarly, many metaverse worlds owned by different companies can also be expected to interlink. This necessitates the development of an interconnection fabric for the computing continuum which takes the intricacies of the metaverse into account, i.e. facilitating not only the integration of visual, aural, and other interactive 3D content but also various modalities and non-functional attributes such as ownership and privacy. Furthermore, this interconnection must adhere to the business agreements governing content flow among Metaverse worlds owned by disparate companies. This paper presents a novel data fabric model designed specifically for the interconnection of various private metaverses, emphasizing its potential to enable seamless data integration, support real-time analytics, and ensure operational scalability.
Federated learning (FL) emerges as a promising solution to train machine learning (ML) models from distributed data sources. In FL, the heterogeneous and imbalanced data distribution of local clients could severely hu...
详细信息
ISBN:
(纸本)9798350386066;9798350386059
Federated learning (FL) emerges as a promising solution to train machine learning (ML) models from distributed data sources. In FL, the heterogeneous and imbalanced data distribution of local clients could severely hurt the fairness of the aggregated global model. In this paper, we identify two key obstacles of developing fair FL models w.r.t. the global distribution: the domain shifts from local clients to the global data distribution and the fairness heterogeneity across local clients. Therefore, considering these two obstacles, we present a novel fairness-aware FL training framework Robust-Fair Domain Smoothing (RFDS) to address the bias issue of FL models from a unique domain-shifting perspective. In particular, we design two novel components to build RFDS: 1) local robust-fair training, and 2) reference domain smoothing. Local robust-fair training aims to train robust-fair local models whose fairness is robust against the domain shifts from local distributions to the global distribution. Reference domain smoothing reduces the heterogeneity of fairness across clients to improve the fairness of the aggregated global model. We further provide a theoretical analysis to show the connection between the domain discrepancy of local data distributions and the heterogeneity of fairness across clients. Empirical evaluation results on multiple real-world datasets show that RFDS achieves promising performance gains in improving demographic fairness compared to state-of-the-art baselines.
In the realm of IoT/CPS systems connected over mobile networks, traditional intrusion detection methods analyze network traffic across multiple devices using anomaly detection techniques to flag potential security thr...
详细信息
ISBN:
(纸本)9798350354720;9798350354713
In the realm of IoT/CPS systems connected over mobile networks, traditional intrusion detection methods analyze network traffic across multiple devices using anomaly detection techniques to flag potential security threats. However, these methods face significant privacy challenges, particularly with deep packet inspection and network communication analysis. This type of monitoring is highly intrusive, as it involves examining the content of data packets, which can include personal and sensitive information. Such data scrutiny is often governed by stringent laws and regulations, especially in environments like smart homes where data privacy is paramount. Synthetic data offers a promising solution by mimicking real network behavior without revealing sensitive details. Generative models such as Generative Adversarial Networks (GANs) can produce synthetic data, but they often struggle to generate realistic data in specialized domains like network activity. This limitation stems from insufficient training data, which impedes the model's ability to grasp the domain's rules and constraints adequately. Moreover, the scarcity of training data exacerbates the problem of class imbalance in intrusion detection methods. To address these challenges, we propose a Privacy-Driven framework that utilizes a knowledge-infused Generative Adversarial Network for generating synthetic network activity data (KiNETGAN). This approach enhances the resilience of distributed intrusion detection while addressing privacy concerns. Our Knowledge Guided GAN produces realistic representations of network activity, validated through rigorous experimentation. We demonstrate that KiNETGAN maintains minimal accuracy loss in downstream tasks, effectively balancing data privacy and utility.
With the rapid development of information technology, people have put forward higher requirements for the audio-visual experience and usage functions of conference spaces. The traditional, single-function conference r...
详细信息
ISBN:
(纸本)9798350391961;9798350391954
With the rapid development of information technology, people have put forward higher requirements for the audio-visual experience and usage functions of conference spaces. The traditional, single-function conference room configuration can no longer adapt to the diverse needs of modern work and interactive activities. How to achieve efficient management and control, seamless interconnection, and resource sharing of audio systems across spaces, while ensuring the acoustic characteristics and flexibility of each independent space, has become a core issue that needs to be urgently resolved in building a multi-hall, multi-functional conference room cluster. Based on the audio system project of the Academic Center of the Communication University of China, this paper proposes a solution for a conference room cluster audio system based on a distributed architecture. This solution not only overcomes the limitations of traditional systems in terms of scalability, collaborative work, and resource scheduling but also promotes lossless transmission, real-time processing, and adaptive configuration of audio signals. Thus, it ensures the consistency and high quality of the audio experience within the entire cluster, providing practical guidance for the design and optimization of future conference room audio systems.
Detecting and handling network partitions is a fundamental requirement of distributedsystems. Although existing partition detection methods in arbitrary graphs tolerate unreliable networks, they either assume that al...
详细信息
ISBN:
(纸本)9798350386066;9798350386059
Detecting and handling network partitions is a fundamental requirement of distributedsystems. Although existing partition detection methods in arbitrary graphs tolerate unreliable networks, they either assume that all nodes are correct or that a limited number of nodes might crash. In particular, Byzantine behaviors are out of the scope of these algorithms despite Byzantine fault tolerance being an active research topic for important problems such as consensus. Moreover, Byzantine-tolerant protocols, such as broadcast or consensus, always rely on the assumption of connected networks. This paper addresses the problem of detecting partition in Byzantine networks (without connectivity assumption). We present a novel algorithm, which we call NECTAR, that safely detects partitioned and possibly partitionable networks and prove its correctness. NECTAR allows all correct nodes to detect whether a network could suffer from Byzantine nodes. We evaluate NECTAR's performance and compare it to two existing baselines using up to 100 nodes running real code, on various realistic topologies. Our results confirm that NECTAR maintains a 100% accuracy while the accuracy of the various existing baselines decreases by at least 40% as soon as one participant is Byzantine. Although NECTAR's network cost increases with the number of nodes and decreases with the network's diameter, it does not go above around 500KB in the worst cases.
暂无评论