Nowadays, the problem of the coordination of relay protection systems during faults becomes widespread, as the trip of the circuit breaker must be fast. One of the solutions is the application of the Internet of Thing...
详细信息
The paper provides an overview of advancements in bird detection and recognition systems using Machine Learning and Artificial Intelligence (AI). It highlights the increasing adoption of wind farms amid rising electri...
详细信息
ISBN:
(纸本)9783031820724;9783031820731
The paper provides an overview of advancements in bird detection and recognition systems using Machine Learning and Artificial Intelligence (AI). It highlights the increasing adoption of wind farms amid rising electricity demand, underscoring their environmental impact on avian species. To address these ecological challenges, the development of bird recognition solutions is crucial. The paper analyzes various techniques, including radar systems, sound recognition, Convolutional Neural Networks (CNNs), electromagnetic detection, YOLOv5, and color segmentation, discussing their features, computational costs, and constraints. It concludes that while deep learning models offer superior results, they need a balance between accuracy and speed, alongside training with large and representative datasets. Ultimately, the paper aims to contribute to efforts aimed at mitigating the adverse effects of wind farms on bird populations through advanced technologies. Additionally, through this paper we intend to shed light over the state of the art on bird detection systems and provide insights that intends to solve some of these drawbacks.
Virtual and augmented reality are currently enjoying a great deal of attention from the research community and the industry towards their adoption within industrial spaces and processes. However, the current design an...
详细信息
ISBN:
(纸本)9781665493130
Virtual and augmented reality are currently enjoying a great deal of attention from the research community and the industry towards their adoption within industrial spaces and processes. However, the current design and implementation landscape is still very fluid, while the community as a whole has not yet consolidated into concrete design directions, other than basic patterns. Other open issues include the choice over a cloud or edge-based architecture when designing such systems. Within this work, we present our approach for a monitoring intervention inside a factory space utilizing both Virtual Reality (VR) and Augmented Reality (AR), based primarily on edge computing, while also utilizing the cloud. We discuss its main design directions, as well as a basic ontology to aid in simple description of factory assets. In order to highlight the design aspects of our approach, we present a prototype implementation, based on a use case scenario in a factory site, within the context of the EnerMan H2020 project.
Internet of Things (IoT) applications consist of diverse resource-constrained/rich devices with a considerable portion being mobile. Such devices demand lightweight, loosely coupled interactions in terms of time, spac...
详细信息
ISBN:
(纸本)9798350359176;9798350359169
Internet of Things (IoT) applications consist of diverse resource-constrained/rich devices with a considerable portion being mobile. Such devices demand lightweight, loosely coupled interactions in terms of time, space, and synchronization. IoT protocols at the middleware layer support several interaction types (e.g., asynchronous messaging, streaming, etc.) ensuring successful interactions between devices that use the same protocol. Additionally, they introduce different Quality of Service (QoS) delivery modes for data exchange with respect to available device and network resources. On the other hand, interconnecting heterogeneous IoT devices requires mapping both their functional and QoS properties. This calls for advanced interoperability solutions integrated with QoS modeling and analysis techniques. This paper introduces an automated synthesis of QoS-aware mediating artifacts. Such mediators enable the interconnection between IoT devices employing heterogeneous middleware protocols. Additionally, representative QoS models are synthesized. Leveraging these models, system designers can evaluate the effectiveness of the interconnection in terms of end-to-end QoS. We evaluate the usefulness of our approach through experimentation with a case study employing heterogeneous middleware protocols. In particular, we statistically analyze through simulations the effect of varying system parameters on the end-to-end QoS.
The proceedings contain 97 papers. The topics discussed include: HydroDrone: multi-drone network for secure task management in smart water resource management;frequency hopping as diffusion: a new perspective on mitig...
ISBN:
(纸本)9798350363999
The proceedings contain 97 papers. The topics discussed include: HydroDrone: multi-drone network for secure task management in smart water resource management;frequency hopping as diffusion: a new perspective on mitigating Bluetooth packet collisions in dense deployments;fault-aware service scheduling optimization framework in edge data center;VibroFM: towards micro foundation models for robust multimodal IoT sensing;how to budget privacy in federated learning? a correlated equilibrium perspective;a novel collaborative edge caching via user preference awareness and adaptive clustering in MENs;where care: a patient localization system for nursing homes;and collaborative user mobility prediction in distributed edge computing framework.
Smart city, health care, agriculture etc applications under the umbrella of the Internet of Things (loT) which they present a new technology with a millions of devices connected together. In the End, all loT devices a...
详细信息
This research investigates the challenges and effectiveness of various text representation methods (standard vector, grammar-based, and distributed), when applied to clustering short texts. The study explores Bag-of-W...
详细信息
ISBN:
(纸本)9783031820724;9783031820731
This research investigates the challenges and effectiveness of various text representation methods (standard vector, grammar-based, and distributed), when applied to clustering short texts. The study explores Bag-of-Words for standard vector, Linguistic Inquiry and Word Count (LIWC), Part-of-Speech Tagging (POS-Tagging), and the Medical Research Council Psycholinguistic Database (MRC) for grammar-based, and Word2Vec, fastText, Doc2Vec, and SentenceBERT for distributed representations. Utilizing the aiNet bio-inspired clustering algorithm, the results reveal surprising findings, with grammar-based representations demonstrating competitive performance despite their simplicity, while standard vectors exhibit known challenges like high dimensionality. The study contributes insights into the properties of different text representations, providing a foundation for optimizing their application in clustering tasks with short and informal texts.
Digital twins improve the performance of heavy equipment and decrease its operational costs. To be effective, they must run along decades of a real machine lifecycle. Ensuring coherence between a real machine and its ...
详细信息
ISBN:
(纸本)9781665493130
Digital twins improve the performance of heavy equipment and decrease its operational costs. To be effective, they must run along decades of a real machine lifecycle. Ensuring coherence between a real machine and its digital twin over such a long period is a challenging task that has not yet been well-studied. This task involves preserving the design and operational data and periodic execution of digital twin software that processes such data. The circumstances of heavy equipment operation complicate the task. This paper considers the problem of digital twin data and software management in light of the unique challenges related to heavy equipment. It presents an experimental case study for running digital twins of mobile log cranes using a data model and a microservices-based architecture developed by the authors. The results demonstrate the capability of the architecture for running physics-based digital twins of heavy equipment in a heterogeneous execution environment consisting of local, edge, and cloud computing resources.
Facilitated by mobile edge computing (MEC), federated learning (FL) can be deployed at the network edge to protect the local data privacy of mobile devices for real-time data-driven applications. To further prevent pr...
详细信息
ISBN:
(纸本)9798350363999;9798350364002
Facilitated by mobile edge computing (MEC), federated learning (FL) can be deployed at the network edge to protect the local data privacy of mobile devices for real-time data-driven applications. To further prevent privacy inference from local models, FL has been enhanced by differential privacy (DP) technology. The existing DP-enhanced FL studies focus on developing DP mechanisms and designing incentive schemes for DP implementation in FL, overlooking the issue of fair privacy budgeting among all clients. To fill this gap, we achieve fairness by balancing the privacy budget, model performance, and cost via defining a privacy budget determination (PBD) game among clients with similar local models. However, it is nontrivial to achieve this balance due to two challenges: the interdependency among clients regarding choosing privacy budgets and the unavailability of other devices' parameters. To resolve the first challenge, we employ the concept of correlated equilibrium (CE) to capture the mutual influences among clients in deciding privacy budgets. We then formulate an optimization problem with CE and individual rationality (IR) constraints to derive the optimal decision. For the second challenge, we exploit the centralized position of the aggregation server to help calculate the solution to the optimization problem. Experiments on real-world datasets demonstrate that the proposed mechanism ensures fairness while achieving superior client utility and global model performance.
Spiking Neural Networks (SNNs) have emerged as a promising bio-inspired solution to address the need for low-latency, energy-efficient artificial intelligence systems. SNNs pose a challenge to traditional CPUs, GPUs a...
详细信息
ISBN:
(纸本)9798400704925
Spiking Neural Networks (SNNs) have emerged as a promising bio-inspired solution to address the need for low-latency, energy-efficient artificial intelligence systems. SNNs pose a challenge to traditional CPUs, GPUs and neural network accelerators due to their inherent sparsity, spike-based communication between neurons and complex activation functions. Many neuromorphic accelerators have been developed to handle this complex workload, but these systems are often designed solely to accelerate spiking networks, resulting in huge area costs and a lack of flexibility. We address this problem by proposing a novel mapping methodology for Convolutional SNNs (S-CNNs) on a general-purpose open-source RISC-V core equipped with Indirection streaming Semantic Registers, a lightweight ISA extension for accelerating sparse-dense linear algebra. NARS is the first work to map S-CNNs in a classical sparse-dense algebra paradigm. Our methodology shows that it is possible to achieve speedups on S-CNNs microkernels with sparsity degrees compatible with state-of-the-art S-CNNs ranging from 4.33x to 10.23x on a dense baseline and from 1.12x to 2.66x on a optimized dense implementation.
暂无评论