检索结果-内蒙古大学图书馆

IEEE Conference on Global Communications (GLOBECOM)

作者： Mouad Rahmouni Ouassim Karrakchou Majdoulayne Hanifi Claudio Savaglio Giancarlo Fortino Mounir Ghogho TICLab College of Engineering & Architecture International University of Rabat Morocco Institute for High-Performance Computing and Networking (ICAR) University of Calabria Italy National Research Council (CNR) of Italy School of Electronic and Electrical Engineering University of Leeds UK

ISBN: (数字)9798350351255

ISBN: (纸本)9798350351262

Artificial Intelligence of Things (AIot) has made Stream Processing (SP) an essential element for data analytics. However, the dynamic nature of AIoT data streams incurs significant challenges in SP systems, especially when real-time data processing is required. While traditional approaches rely on resource scaling to meet the AIoT application requirements, our work explores a complementary approach by optimizing in real-time the configuration of SP systems to balance operational and resource efficiencies with data throughput and latency considerations. At the core of our work is the application of a Q-learning algorithm, enabling dynamic and responsive tuning of the SP system configuration parameters to adapt to the fluctuating demands of real-time data processing. Through empirical testing, our approach’s ability to improve SP efficiency in various data environments is demonstrated, providing insights into its practical application and effectiveness. The research concludes by highlighting the potential of extending this optimization approach to broader real-time data processing scenarios, suggesting avenues for future exploration in SP optimization.

关键词： Q-learning Heuristic algorithms Throughput Real-time systems Internet of Things Global communication Artificial intelligence Optimization Tuning Testing

来源：评论

学校读者我要写书评

暂无评论

A deep learning approach for unsupervised failure detection in smart industry 29

A deep learning approach for unsupervised failure detection ...

引用

29th Italian Symposium on Advanced Database Systems, SEBD 2021

作者： Liguori, Angelica Manco, Giuseppe Ritacco, Ettore Ruffolo, Massimilano Iiritano, Salvatore Department of Computer Engineering Modeling Electronics and Systems University of Calabria Italy Institute for High Performance Computing and Networking of Italian National Research Council Revelis S.r.l.

We propose an unsupervised anomaly detection model that is able to identify abnormal behavior by analysing streaming data coming from IoT sensors installed on critical devices. The proposed model is based on a Siamese neural network which embeds time series windows in a latent space, thus generating distance-based clusters of normal behavior. We experiment the proposed model on a case study aimed at the predictive maintenance of elevators where specific sensors measure the oscillations of the lift during its daily use. The experiments show that the proposed model successfully isolates anomalous oscillations thus correlating them to prospective malfunctions and thus preventing possible faults. © 2021 Copyright for this paper by its authors.

关键词： Time series analysis

来源：评论

学校读者我要写书评

暂无评论

A Multi-Level Parallel Algorithm for Detection of Single Scatterers in SAR Tomography

A Multi-Level Parallel Algorithm for Detection of Single Sca...

引用

Euromicro Conference on Parallel, Distributed and Network-Based Processing

作者： Massimiliano Russo Mehwish Nisar Antonio Pauciullo Pasquale Imperatore Marco Lapegna Diego Romano Dept. of Mathematics and Applications University of Naples Federico II Naples Italy Institute for the Electromagnetic Sensing of the Environment (IREA) National Research Council Naples Italy Inst. for High Performance Computing and Networking National Research Council Naples Italy

ISBN: (数字)9798331524937

ISBN: (纸本)9798331524944

Synthetic Aperture Radar (SAR) tomography is an advanced technique for monitoring deformations of the Earth’s surface. However, the computational complexity of SAR tomography algorithms often restricts their application to large-scale datasets. To address this issue, we introduce a multi-level parallel implementation of a single scatterer detection algorithm specifically designed to exploit the capabilities of modern heterogeneous High-performance computing (HPC) systems. By efficiently distributing the computational workload at different levels across multiple processing units, our parallel approach significantly reduces processing time, facilitating the analysis of extensive SAR datasets. We assess the performance of our parallel implementation using real-world SAR data, showcasing its effectiveness in enhancing both the efficiency and scalability of SAR tomography. Our work contributes to advancing remote sensing techniques and offers valuable insights into the application of HPC for large-scale environmental monitoring.

关键词： High performance computing Scalability Graphics processing units Tomography performance analysis Parallel algorithms Synthetic aperture radar Surface treatment Remote sensing Optimization

来源：评论

学校读者我要写书评

暂无评论

Bridging Clinical Gaps: Multi-Dataset Integration for Reliable Multi-Class Lung Disease Classification with DeepCRINet and Occlusion Sensitivity

Bridging Clinical Gaps: Multi-Dataset Integration for Reliab...

引用

IEEE Symposium on Computers and Communications (ISCC)

作者： Naeem Ullah Javed Ali Khan Ivanoe De Falco Giovanna Sannino Department of Electrical Engineering and Information Technology University of Naples "Federico II" Naples Italy Department of Computer Science University of Hertfordshire Hatfield UK Institute for High-Performance Computing and Networking (ICAR) National Research Council (CNR) Naples Italy

ISBN: (数字)9798350354232

ISBN: (纸本)9798350354249

This research presents DeepCRINet, a deep learning (DL) model designed for reliable performance across various Chest Radiography Images (CRIs) datasets, in response to the urgent need for quick and accurate lung disease identification utilizing CRIs. Our method builds on earlier research, which frequently used single-source datasets that might not adequately represent the heterogeneity present in clinical situations. Our model’s diagnostic adaptability and real-world dependability are improved by utilizing images from different datasets, which helps us overcome limitations such as dataset bias, robustness, generalizability, and underrepresentation of conditions. With validation on a broad dataset consisting of 14,096 images (from three different datasets), DeepCRINet provides a solution that demonstrates excellent flexibility in recognizing illnesses including TuBerculosis, Pneumonia, COVID-19, and Lung Opacity. Through data augmentation, we improve the dataset, supporting training and testing procedures and confirming the model’s ability to generalize. We used occlusion sensitivity as a kind of explainable AI to openly identify and visually emphasize regions important to proper classification. This ability not only shows that DeepCRINet is analytically better than other DL models and hybrid techniques, but it also improves patient outcomes and diagnosis, which makes it a vital tool for medical professionals like radiologists.

关键词： COVID-19 Training Analytical models Pneumonia Accuracy Tuberculosis Sensitivity analysis Robustness Diagnostic radiography Testing

来源：评论

学校读者我要写书评

暂无评论

Safeguarding Sensitive Data in the Era of IoT: A Study on Security Protocols for Distributed Measurement Systems

Safeguarding Sensitive Data in the Era of IoT: A Study on Se...

引用

Metrology for Living Environment (MetroLivEn), IEEE International Workshop on

作者： Antonio Francesco Gentile Davide Macrì Francesco Lamonaca Institute for High-Performance Computing and Networking National Research Council of Italy (ICAR-CNR) Rende (CS) Italy Department of Computer Engineering Modeling Electronics and Systems Rende (CS) Italy University of Calabria CNR-NANOTEC Rende (CS) Italy

ISBN: (数字)9798350385014

ISBN: (纸本)9798350385021

IoT devices have led to the development of Distributed Measurement Systems (DMS). However, cyber-attacks have increased, making it crucial to implement security protocols without reducing network throughput. Open firmware on constrained devices offers another layer of customization, essential for the flexibility required in DMS. This allows software updates and modifications in real-time, which is crucial for adapting to evolving cybersecurity threats and managing device functionality. The objective is to identify algorithms that ensure optimal data transmission and encryption ratios and maximum compatibility with existing infrastructures and commercial hardware that support MQTT technology. This approach utilizes local MQTT brokers and TLS tunnels to secure local sensor data transmissions. This design enhances security and maintains the efficiency of data flow across the network. The primary objective moving forward is to refine and identify algorithms that ensure optimal data transmission and encryption ratios and uphold maximum compatibility with existing infrastructures that support MQTT technology. This is critical as MQTT is a standard protocol for IoT communications.

关键词： Protocols Software algorithms Throughput Software Real-time systems Encryption Internet of Things

来源：评论

学校读者我要写书评

暂无评论

An Efficient Algorithm for Clustering Sets

An Efficient Algorithm for Clustering Sets

引用

International Workshop/Symposium on Distributed Simulation and Real-Time Applications (DS-RT)

作者： Libero Nigro Franco Cicirelli Engineering Department of Informatics Modelling Electronics and Systems Science DIMES University of Calabria Rende Italy CNR National Research Council of Italy - Institute for High Performance Computing and Networking (ICAR) Rende Italy

This paper proposes an algorithm, named HWK-Sets, based on K-Means, suited for clustering data which are variable-sized sets of elementary items. Clustering sets is difficult because data objects do not have numerical attributes and it is not possible to use the classical Euclidean distance upon which K-Means is normally based. An adaptation of the Jaccard distance between sets is used, which exploits application-sensitive information. More in particular, the Hartigan and Wong variation of K-Means is adopted which uses medoids as cluster representatives, can work with several seeding methods and can favor the fast attainment of a careful solution. The paper introduces HWK-Sets which is implemented in Java by parallel streams. Then, the efficiency and accuracy of HWK-Sets are demonstrated by simulation experiments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Task-Driven Priority-Aware Computation Offloading Using Deep Reinforcement Learning

引用

IEEE Transactions on Wireless Communications 2025年

作者： Hao, Hao Xu, Changqiao Zhang, Wei Yang, Shujie Muntean, Gabriel-Miro Jinan China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Jinan China Beijing University of Posts and Telecommunications State Key Laboratory of Networking and Switching Technology Beijing China Dublin City University Performance Engineering Laboratory School of Electronic Engineering Dublin Ireland

Computation offloading is an effective method for reducing the pressure put on networks and improving the service experience. However, most existing research on computation offloading is timeslot-driven and treats all tasks equally, resulting in decision waiting delays and failure to complete some important tasks. In this paper, we propose a novel priority-aware task-driven computation offloading model with system performance gain as the optimization objective based on a combination of task delay and energy consumption aspects. The new model is formulated as a Markov decision process (MDP). Considering the discrete-continuous hybrid action space of the optimization problem, we construct a dependence-aware latent space and propose a novel algorithm based on the Twin Delayed Deep Deterministic policy gradient algorithm (TD3). Additionally, we present the neural network structure and analyze the complexity of the algorithm. Extensive simulations show how our algorithm achieves superior performance compared to three state-of-the-art alternative approaches. © 2002-2012 IEEE.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Mimicking human autonomy in industrial robotic enabled sensing

Mimicking human autonomy in industrial robotic enabled sensi...

引用

IEEE International Workshop on Robot and Human Communication (ROMAN)

作者： Carmelo Mineo Donatella Cerniglia Umberto Maniscalco Institute for High Performance Computing and Networking (ICAR) National Research Council of Italy (CNR) Palermo Italy Department of Engineering University of Palermo Italy

ISBN: (数字)9781728188591

ISBN: (纸本)9781665406802

Humans have an immediate perception of shapes and surroundings through their senses and their cognitive capabilities. This innate ability enables the manual inspection of components in manufacturing environments. Trained inspectors combine their senses and handling skills with bespoke nondestructive testing instrumentation. However, manual inspections can be slow for large and/or complex geometries and prone to human factors. Automated non-destructive testing systems have emerged in recent years, to increase data acquisition speed, part coverage and inspection reliability. These tools work well when the robotic inspection takes place in a well-structured environment and an accurate part model is available. However, precisely registering the position of a part in the robot reference system makes the inspection setup very time-consuming. Furthermore, the geometry of a part may differ from its digital model, spoiling the inspection accuracy. This work introduces a new approach that mimics the human perception capability and gives full manipulation autonomy to robotic sensing applications. We use a single robotized sensor to introduce a fully autonomous single-pass geometric and volumetric inspection of complex parts. Our approach can be used to solve some key challenges in quality assurance for Industry 4.0 and can find applicability beyond robotic nondestructive testing.

关键词： Geometry Service robots Shape Nondestructive testing Manuals Inspection Robot sensing systems

来源：评论

学校读者我要写书评

暂无评论

Design of an Air Pollution Monitoring System Based on a Low-Cost Sensor Node

Design of an Air Pollution Monitoring System Based on a Low-...

引用

Metrology for Living Environment (MetroLivEn), IEEE International Workshop on

作者： Rocío-Alejandra Guerrón Domenico-Luca Carnì Marco Lanuzza Francesco D' Amore Mariantonia Bencardino Francesco Lamonaca Ramiro Taco Department of Computer Engineering Modeling Electronics and Systems University of Calabria Rende Italy Institute for High Performance Computing and Networking Italian National Research Council Rende Italy Institute of Atmospheric Pollution Research Italian National Research Council Rende Italy

ISBN: (数字)9798350385014

ISBN: (纸本)9798350385021

Air quality influences the life of the living beings that inhabit planet Earth. High levels of air pollutants in ambient air are in fact able to affect human health and also ecosystem integrity. Their monitoring allows for regulating the most appropriate air quality indices and verifying whether they are below the established harmful levels. However, this is a task that requires many physical and economic resources. For this reason, the research activity herein presented proposes a low-cost system, which is able to qualitatively evaluate the meteorological conditions and the main pollutants that affect a certain area. Through this proposal, the behavior of Alphasense's electrochemical gas low-cost sensors is studied. Their response to the concentrations of the main air pollutants regulated by the relevant European Directive (2008/50/CE), such as Carbon Monoxide, Nitrogen Dioxide, Ozone, and Sulfur Dioxide, is characterized and analyzed under various environmental conditions of Temperature and Relative Humidity and as a function of the electrical current signal obtained by the chemistry of the sensor.

关键词： Temperature sensors Chemical sensors Sensor phenomena and characterization Air pollution Sensor systems Sulfur Proposals

来源：评论

学校读者我要写书评

暂无评论

Machine learning with sub-diffraction resolution in the photon-counting regime

arXiv

引用

arXiv 2024年

作者： Buonaiuto, Giuseppe Lupo, Cosmo Institute for High Performance Computing and Networking [ICAR National Research Council [CNR Naples80131 Italy Dipartimento Interateneo di Fisica Politecnico Università di Bari Bari70126 Italy INFN Sezione di Bari Bari70126 Italy

The resolution of optical imaging is classically limited by the width of the point-spread function, which in turn is determined by the Rayleigh length. Recently, spatial-mode demultiplexing (SPADE) has been proposed as a method to achieve sub-Rayleigh estimation and discrimination of natural, incoherent sources. Here we show that SPADE yields sub-diffraction resolution in the broader context of image classification. To achieve this goal, we outline a hybrid machine learning algorithm for image classification that includes a physical part and a computational part. The physical part implements a physical pre-processing of the optical field that cannot be simulated without essentially reducing the signal-to-noise ratio. In detail, a spatial-mode demultiplexer is used to sort the transverse field, followed by mode-wise photon detection. In the computational part, the collected data are fed into an artificial neural network for training and classification. As a case study, we classify images from the MNIST dataset after severe blurring due to diffraction. Our numerical experiments demonstrate the ability to classify highly blurred images that would be otherwise indistinguishable by direct imaging without the physical pre-processing of the optical field. Copyright © 2024, The Authors. All rights reserved.

关键词： Optical transfer function

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：