检索结果-内蒙古大学图书馆

1st International Conference on Pervasive Knowledge and Collective Intelligence on Web and Social Media, PerSOM 2022

作者： Gul, Faiza Mir, Imran Gul, Uzma Forestiero, Agostino Aerospace and Aviation Campus Kamra Air University Kamra Pakistan School of Avionics and Electrical Engineering College of Aeronautical Engineering NUST Risalpur Pakistan Taxila Pakistan Institute for High-Performance Computing and Networking National Research Council of Italy Rome Italy

ISBN: (纸本)9783031314681

Autonomous systems have achieved great success over the last couple of decades. They have bring the revolutionary change in the world, either its ground vehicles, aerial systems or underground vehicles. Number of research papers have been written on the importance of autonomous systems and their applications in different field. Keeping in view the pattern of research done by authors, an effort has been made to provide a single platform for readers to familiarize themselves with applications involved in terrestrial, aerial and undersea systems along with different sets of dimensions involved in achieving these applications. Therefore, the article provides a summary of the main communication methods used by terrestrial, aerial, and undersea space research vehicles. In addition to providing an exhaustive summary of the difficulties encountered in trajectory planning, space exploration, optimization, and other areas, the research also presents optimization methods applicable to aerial, undersea, and terrestrial applications. As the literature lacks extensive studies like this one, hence an effort has been made to fill the gap for readers interested in path design. This study tackles numerical, bioinspired, and hybrid techniques for each of the dimensions given. With this study, we attempted to provide a single repository for a plethora of research on autonomous land vehicles, their trajectory optimization, as well as research on aerial and undersea vehicles. The article ends with the most practical directions for future research. © 2023, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

关键词： Antennas

来源：评论

学校读者我要写书评

暂无评论

Visualization and Analysis of Transformer Attention 1

Visualization and Analysis of Transformer Attention

引用

1st Workshop on Artificial Intelligence for Perception and Artificial Consciousness, AIxPAC 2023

作者： Calderaro, Salvatore Lo Bosco, Giosué Rizzo, Riccardo Vella, Filippo Department of Mathematics and Computer Science Università degli Studi di Palermo via Archirafi 34 Palermo Italy Institute of High Performance Computing and Networking National Research Council of Italy CNR via Ugo La Malfa 153 Palermo Italy

The capability to select the relevant portion of the input is a key feature to limit the sensory input and focus on the most informative collected part. The transformer architecture is among the most performing deep neural network architectures due to the attention mechanism. The attention allows us to spot relevant connections between portions of the images and highlight these connections. Since the model is complex, it is not easy to determine which are these connections and the important areas. We discuss a technique to show these areas and highlight the regions most relevant for label attribution. © 2023 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Privacy-Oriented Architecture for Building Automatic Voice Interaction Systems in Smart Environments in Disaster Recovery Scenarios

Privacy-Oriented Architecture for Building Automatic Voice I...

引用

International Conference on Information and Communication Technologies for Disaster Management (ICT-DM)

作者： Antonio Francesco Gentile Davide Macrì Emilio Greco Agostino Forestiero ICAR CNR Cosenza Italy Institute for High Performance Computing and Networking National Research Council Rende (CS) Italy

In the wake of increasing natural disasters and emergency situations, the deployment of Smart Environments with automatic voice interaction systems has become vital for efficient disaster recovery efforts. However, the widespread adoption of such systems raises significant concerns about user privacy and data security. This paper proposes a novel privacy-oriented architecture tailored explicitly for building automatic voice interaction systems in Smart Environments, designed to address the privacy challenges inherent in disaster recovery scenarios. The proposed architecture emphasizes the implementation of robust privacy-preserving mechanisms, ensuring that sensitive user data remains secure and inaccessible to unauthorized entities. To demonstrate the practicality and effectiveness of the proposed architecture, a proto-type voice interaction system was developed and deployed in a simulated environment. The system's performance is evaluated against traditional architectures, showcasing its superior ability to safeguard user privacy while delivering accurate and responsive voice-based services.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SynGraphy: Succinct Summarisation of Large Networks via Small Synthetic Representative Graphs

arXiv

引用

arXiv 2023年

作者： Kunegis, Jérôme Kumar, Pawan Sun, Jun Samoilenko, Anna Pirró, Giuseppe University of Namur Belgium University of Koblenz Landau Germany University of Stuttgart Germany Institute for High Performance Computing and Networking Italy

We describe SynGraphy, a method for visually summarising the structure of large network datasets that works by drawing smaller graphs generated to have similar structural properties to the input graphs. Visualising complex networks is crucial to understand and make sense of networked data and the relationships it represents. Due to the large size of many networks, visualisation is extremely difficult;the simple method of drawing large networks like those of Facebook or Twitter leads to graphics that convey little or no information. While modern graph layout algorithms can scale computationally to large networks, their output tends to a common hairball look, which makes it difficult to even distinguish different graphs from each other. Graph sampling and graph coarsening techniques partially address these limitations but they are only able to preserve a subset of the properties of the original graphs. In this paper we take the problem of visualising large graphs from a novel perspective: we leave the original graph’s nodes and edges behind, and instead summarise its properties such as the clustering coefficient and bipartivity by generating a completely new graph whose structural properties match that of the original graph. To verify the utility of this approach as compared to other graph visualisation algorithms, we perform an experimental evaluation in which we repeatedly asked experimental subjects (professionals in graph mining and related areas) to determine which of two given graphs has a given structural property and then assess which visualisation algorithm helped in identifying the correct answer. Our summarisation approach SynGraphy compares favourably to other techniques on a variety of networks. © 2023, CC BY-SA.

关键词： Structural properties

来源：评论

学校读者我要写书评

暂无评论

MMOP-AI Reference Architecture: Paving the Way towards Cultural Heritage Preservation

MMOP-AI Reference Architecture: Paving the Way towards Cultu...

引用

IEEE Sensors Applications Symposium, SAS

作者： Ilenia Ficili Giuseppe Tricomi Antonio Puliafito Department of Engineering University of Messina Italy Messina Italy Institute for High Performance Computing and Networking of National Research Council of Italy (ICAR-CNR) Naples Italy

ISBN: (数字)9798350369250

ISBN: (纸本)9798350369267

Preserving cultural heritage is not only about safe-guarding artifacts and monuments but also about cherishing the identity and narrative of societies. With the advent of the Internet of Things (IoT), a potent tool emerges for enhancing cultural asset conservation efforts. By deploying smart sensors, cameras, and drones, IoT enables comprehensive, real-time monitoring of heritage sites, facilitating proactive interventions in case of threats such as natural disasters, vandalism, or deterioration. This paper aims to delve into the multifaceted ways in which IoT technologies can be harnessed to protect and preserve our diverse cultural heritage. By examining case studies and possibleimplementations, it drafts a reference architecture and an open-source infrastructure aiming to highlight the transformative potential of IoT in culturalconservation practices, offering insights for policymakers, researchers, andheritage professionals alike.

关键词： Disasters Cameras Real-time systems Cultural differences Internet of Things Synthetic aperture sonar Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Detecting DoS and DDoS Attacks through Sparse U-Net-like Autoencoders

Detecting DoS and DDoS Attacks through Sparse U-Net-like Aut...

引用

International Conference on Tools for Artificial Intelligence (ICTAI)

作者： Nunziato Cassavia Francesco Folino Massimo Guarascio Institute for High Performance Computing and Networking (ICAR-CNR) Rende CS Italy

In the last few years, we experienced exponential growth in the number of cyber-attacks performed against com-panies and organizations. In particular, because of their ability to mask themselves as legitimate traffic, DoS and DDoS have become two of the most common kinds of attacks on computer networks. Modern Intrusion Detection Systems (IDSs) represent a precious tool to mitigate the risk of unauthorized network access as they allow for accurately discriminating between benign and malicious traffic. Among the plethora of approaches proposed in the literature for detecting network intrusions, Deep Learning (DL)-based IDSs have been proved to be an effective solution because of their ability to analyze low-level data (e.g., flow and packet traffic) directly. However, many current solutions require large amounts of labeled data to yield reliable models. Unfortunately, in real scenarios, small portions of data carry label information due to the cost of manual labeling conducted by human experts. Labels can even be completely missing for some reason (e.g., privacy concerns). To cope with the lack of labeled data, we propose an unsupervised DL-based intrusion detection methodology, combining an ad-hoc preprocessing procedure on input data with a sparse U-Net-like autoencoder architecture. The experimentation on an IDS benchmark dataset substantiates our approach's ability to recognize malicious behaviors correctly.

关键词： Deep learning Privacy Data preprocessing Intrusion detection Organizations Manuals Denial-of-service attack

来源：评论

学校读者我要写书评

暂无评论

CEER:Cooperative Energy-Efficient Routing Mechanism for Underwater Wireless Sensor Networks Using Clusters

引用

Computer Systems Science & Engineering 2023年第6期45卷 2587-2602页

作者： Sayyed Mudassar Shah Tariq Hussain Babar Shah Farman Ali Khalid Zaman Kyung-Sup Kwak Institute of Computer Science&Information Technology the University of Agriculture Peshawar25000Pakistan High Performance Computing and Networking Institute National Research Council(ICAR-CNR)Naples80131Italy College of Technological Innovation Zayed UniversityDubai19282UAE Department of Software Sejong UniversitySeoul05006Korea Department of Information and Communication Engineering Inha UniversityIncheon22212Korea

Underwater acoustic sensor networks(UWASNs)aim to find varied offshore ocean monitoring and exploration *** most of these applications,the network is composed of several sensor nodes deployed at different depths in the *** nodes located at depth on the seafloor cannot invariably communicate with nodes close to the surface level;these nodes need multihop communication facilitated by a suitable routing *** this research work,a Cluster-based Cooperative Energy Efficient Routing(CEER)mechanism for UWSNs is proposed to overcome the shortcomings of the Co-UWSN and LEACH *** optimal role of clustering and cooperation provides load balancing and improves the network *** simulation results using MATLAB show better performance of CEER routing protocol in terms of various parameters as compared to Co-UWSN routing protocol,i.e.,the average end-to-end delay of CEER was 17.39,Co-UWSN was 55.819 and LEACH was *** addition,the average total energy consumption of CEER was 9.273,Co-UWSN was 12.198,and LEACH was *** packet delivery ratio of CEER was 53.955,CO-UWSN was 42.047,and LEACH was *** stability period CEER was 130.9,CO-UWSN was 129.3,and LEACH was *** obtained results maximized the lifetime and improved the overall performance of the CEER routing protocol.

关键词： Cluster head co-UWSN UWSN relay LEACH CEER

来源：评论

学校读者我要写书评

暂无评论

THE GECO ALGORITHM FOR GRAPH NEURAL NETWORKS EXPLANATION

arXiv

引用

arXiv 2024年

作者： Calderaro, Salvatore Amato, Domenico Vella, Filippo Bosco, Giosuè Lo Rizzo, Riccardo Dept of Mathematics and Computer Science University of Palermo Palermo90123 Italy Institute for High Performance Computing and Networking National Research Council of Italy Palermo90146 Italy

Graph Neural Networks (GNNs) are powerful models that can manage complex data sources and their interconnection links. One of GNNs’ main drawbacks is their lack of interpretability, which limits their application in sensitive fields. In this paper, we introduce a new methodology involving graph communities to address the interpretability of graph classification problems. The proposed method, called GECo, exploits the idea that if a community is a subset of graph nodes densely connected, this property should play a role in graph classification. This is reasonable, especially if we consider the message-passing mechanism, which is the basic mechanism of GNNs. GECo analyzes the contribution to the classification result of the communities in the graph, building a mask that highlights graph-relevant structures. GECo is tested for Graph Convolutional Networks on six artificial and four real-world graph datasets and is compared to the main explainability methods such as PGMExplainer, PGExplainer, GNNExplainer, and SubgraphX using four different metrics. The obtained results outperform the other methods for artificial graph datasets and most real-world datasets. 1 © 2024, CC BY.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

AIxPAC 2024-Preface to the 2nd Workshop on Artificial Intelligence for Perception and Artificial Consciousness 2

AIxPAC 2024-Preface to the 2nd Workshop on Artificial Intell...

引用

2nd Workshop on Artificial Intelligence for Perception and Artificial Consciousness, AIxPAC 2024

作者： Bruno, Alessandro Pipitone, Arianna Manzotti, Riccardo Augello, Agnese Mazzeo, Pier Luigi Mazzola, Giuseppe Vella, Filippo IULM University Via Carlo Bo 1 Milano20143 Italy University of Palermo Via delle Scienze Palermo90128 Italy ICAR Institute for High Performance Computing and Networking CNR Via Ugo La Malfa 153 Palermo90146 Italy ISASI Institute of Applied Sciences Intelligent Systems CNR Via Monteroni sn Lecce73100 Italy

The AIxPAC workshop seeks to unite academic and industry researchers to explore the latest developments in AI related to perception and consciousness. The event includes expert presentations on topics such as the physicalist ontology of consciousness, artificial consciousness, color perception, and computer vision. Key research questions addressed at AIxPAC include: Is it possible to integrate visual perception systems into machines? How effectively does AI handle visual attention processes? What is the connection between attention and consciousness? Can AI architectures and methodologies be leveraged to create Artificial Consciousness? What are the advantages and disadvantages of Large Language Models? These research questions encourage multidisciplinary collaboration and provide a foundation for critical analysis of the discussed topics © 2024 Copyright for this paper by its authors.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

A Real Network performance Analysis Testbed for Encrypted MQTT in DMS

A Real Network Performance Analysis Testbed for Encrypted MQ...

引用

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

作者： Antonio Francesco Gentile Emilio Greco Domenico Luca Carnì Institute for High-Performance Computing and Networking National Research Council of Italy (ICAR-CNR) Rende CS Italy Electronic and System Science University of Calabria Rende CS Italy

ISBN: (数字)9798350385014

ISBN: (纸本)9798350385021

The widespread adoption of IoT devices has led to the development of Distributed Measurement Systems (DMS). However, cyber attacks aimed at destroying critical infrastructure and retrieving sensitive data are rising. We proposed a security-oriented VLAN testbed deployed with opensource firmware and constrained hardware to address this issue. The approach uses local MQTT brokers, TLS tunnels for local sensor data, and an SSL tunnel to transmit encrypted data to a cloud-based central broker. The proposal evaluates critical metrics such as Total Ratio, Total Runtime, Average Runtime, Message time, Average Bandwidth, and Total Bandwidth to predict the minimum network throughput for the selected QoS and security. From a measurement science perspective, lower productivity may result in phenomena being observed less frequently, potentially leading to misinterpretations. This paper does not introduce a new method for safeguarding measurement data, but rather evaluates the network performance of commonly used methods applicable to captive and commercial hardware. This scenario is typical for IoT-based DMS. The proposal considers a security-focused VLAN approach, along with targeted solutions for hardware constraints. Given the nature of the worst case, this allows for broad application of the results obtained. Our study marks the initial phase of a larger and more extensive research effort. Specifically, we used commercial hardware such as the Raspberry Pi 4. Our goal is to extend the scope of the research and delve into more complex and detailed questions in our next work. The primary objective is to identify algorithms that ensure optimal data transmission and encryption ratios and explore algorithms that ensure maximum compatibility with existing infrastructures supporting MQTT technology and will facilitate secure connections for geographically dispersed DMS IoT networks, particularly in challenging environments.

关键词： Productivity Runtime Bandwidth Quality of service Throughput Hardware performance analysis

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：