检索结果-内蒙古大学图书馆

IEEE International Symposium on Multimedia

作者： Vincenzo Emanuele Carusotto Giovanni Pilato Fabio Persia Mouzhi Ge University of Palermo Palermo Italy Institute for High Performance Computing and Networking National Research Council of Italy Palermo Italy University of L’Aquila L’Aquila Italy Deggendorf Institute of Technology Deggendorf Germany

For Point of Interest (POI) recommendations or touristic orienteering applications, it is essential to explore the user preference or potential interests to predict potential POIs or touristic routes. One of the state-of-the-art approaches for inferring the user’s interests is social sensing, which is based on implicit feedback and semantic similarities to extract the user preference. In this paper, we profile the user preferences by social sensing to exploit the similarity between users’ reviews and POI descriptions. The experiment is based on the "Yelp!" dataset and provides the labels associated with different businesses considered in the "Yelp!" Social Network. The preliminary results show that the proposed model can automatically estimate the user interests and improve the effectiveness of the user profiling procedure. The results also indicate that our proposed model can offer a foundational approach for ranking POIs and touristic routes.

关键词： Social networking (online) Semantics Sensors Business

来源：评论

学校读者我要写书评

暂无评论

An Energy Management System at the Edge based on Reinforcement Learning

An Energy Management System at the Edge based on Reinforceme...

引用

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

作者： F. Cicirelli A. F. Gentile E. Greco A. Guerrieri G. Spezzano A. Vinci National Research Council of Italy - Institute for High Performance Computing and Networking (ICAR) Rende CS Italy

ISBN: (数字)9781728173436

ISBN: (纸本)9781728173443

In this work, we propose an IoT edge-based energy management system devoted to minimizing the energy cost for the daily-use of in-home appliances. The proposed approach employs a load scheduling based on a load shifting technique, and it is designed to operate in an edge-computing environment naturally. The scheduling considers all together time-variable profiles for energy cost, energy production, and energy consumption for each shiftable appliance. Deadlines for load termination can also be expressed. In order to address these goals, the scheduling problem is formulated as a Markov decision process and then processed through a reinforcement learning technique. The approach is validated by the development of an agent-based real-world test case deployed in an edge context.

关键词： Buildings Learning (artificial intelligence) Home appliances Energy consumption Energy management Markov processes Edge computing

来源：评论

学校读者我要写书评

暂无评论

Machine Learning and Network Traffic to Distinguish Between Malware and Benign Applications 1st

Machine Learning and Network Traffic to Distinguish Between ...

引用

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

作者： Abualigah, Laith Abualigah, Sayel Almahmoud, Mothanna Forestiero, Agostino Sachdeva, Gagan Hanandeh, Essam S. Hourani Center for Applied Scientific Research Al-Ahliyya Amman University Amman Jordan Faculty of Information Technology Middle East University Amman Jordan Applied Science Research Center Applied Science Private University Amman Jordan School of Computer Sciences Universiti Sains Malaysia Pulau Pinang George Town Malaysia Computer Science Department Prince Hussein Bin Abdullah Faculty for Information Technology Al Al-Bayt University Mafraq25113 Jordan Department of Computer Information Systems Jordan University of Science and Technology Ar-Ramtha Jordan Performance Computing and Networking National Research Council of Italy Rende87036 Italy First Abu Dhabi Bank Abu Dhabi United Arab Emirates Department of Computer Information System Zarqa University Zarqa Jordan

ISBN: (纸本)9783031314681

Virus detection software is widely used for servers, systems, and devices that seek to maintain security and reliability. Although these programs provide an excellent safety level, the traditional defense methods fail to detect new Malware. The more advanced approach relies on predicting malicious behavior with dynamic analysis of the process executed. This paper presents a new method for detecting malware using machine learning algorithms applied to data obtained from the Cuckoo sandbox. The Cuckoo sandbox isolates the file being analyzed, providing detailed dynamic analysis reports. The machine learning algorithms were compared and the most important features were identified. The results were obtained using six popular classifiers, including SVM, Random Forest, and LightGBM, and the XGBOOST algorithm had the highest accuracy, at an average of 97%. However, the research on machine learning-based malware analysis is limited in terms of computational complexity and detection accuracy. © 2023, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

关键词： Software reliability

来源：评论

学校读者我要写书评

暂无评论

Cognitive Robots and the Conscious Mind: A Review of the Global Workspace Theory

引用

Current Robotics Reports 2021年第2期2卷 125-131页

作者： Signa, Alessandro Chella, Antonio Gentile, Manuel Department of Engineering University of Palermo Palermo Italy Institute for Educational Technology National Research Council of Italy Palermo Italy Institute for high performance computing and networking National Research Council of Italy Palermo Italy Dipartimento di Informatica Università di Torino Turin Italy

The theory of consciousness is a subject that has kept scholars and researchers challenged for centuries. Even today it is not possible to define what consciousness is. This has led to the theorization of different models of consciousness. Starting from Baars’ Global Workspace Theory, this paper examines the models of cognitive architectures that are inspired by it and that can represent a reference point in the field of robot consciousness. Global Workspace Theory has recently been ranked as the most promising theory in its field. However, this is not reflected in the mathematical models of cognitive architectures inspired by it: they are few, and most of them are a decade old, which is too long compared to the speed at which artificial intelligence techniques are improving. Indeed, recent publications propose simple mathematical models that are well designed for computer implementation. In this paper, we introduce an overview of consciousness and robot consciousness, with some interesting insights from the literature. Then we focus on Baars’ Global Workspace Theory, presenting it briefly. Finally, we report on the most interesting and promising models of cognitive architectures that implement it, describing their peculiarities.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Estimating Server Load Based on its Correlation with TCP SYN Response Time

Estimating Server Load Based on its Correlation with TCP SYN...

引用

2020 IFIP networking Conference and Workshops, networking 2020

作者： De Pedro, Luis Redondo, Marta Martinez Mancha, Cristina De Vergara, Jorge E. Lopez Escuela Politecnica Superior Universidad Autónoma de Madrid Francisco Tomás y Valiente Departamento de Tecnologíia Electronica y de Las Comunicaciones High-Performance Computing and Networking Research Group Madrid28049 Spain

ISBN: (纸本)9783903176287

In this paper, we show that server load correlates with TCP SYN response time (SRT), that is, the time from SYN to SYN+ACK segments at the server side. For this, it applies the innovative approach of modeling the SRT with an appropriate αstable heavy tail distribution. We also show that αstable distribution parameters are related to the server load the connection is attempted to. This approach provides a nonintrusive way to estimate the server load, and it can be useful to identify if a problem in a distributed application is caused by the end system, or to distribute the load among servers. Finally, based on obtained results, we propose a method that estimates server load based on SRT. © 2020 IFIP.

关键词： Transmission control protocol

来源：评论

学校读者我要写书评

暂无评论

The ERN Cryo-EM Federated Instrument Pilot Project: Phase 1

The ERN Cryo-EM Federated Instrument Pilot Project: Phase 1

引用

IEEE/ACM Annual Workshop on Large-scale Experiment-in-the-Loop computing (XLOOP)

作者： Maureen Dougherty Jason Kaelber James Barr von Oehsen Morgan Ludwig Kenneth Dalenberg Jeremy Schafer Michael Zink Boyd Wilson John Goodhue Wolf Hey D. Balamurugan Ecosystem for Research Networking New Brunswick USA Institute for Quantitative Biomedicine Rutgers University New Brunswick USA Office of Advanced Research Computing Rutgers University New Brunswick USA TechSquare Cambridge USA Electrical and Computer Engineering University of Massachusetts Amherst Amherst USA Omnibond Clemson USA Massachusetts Green High Performance Computing Center Holyoke USA Institute for Computational and Data Sciences Pennsylvania State University State College USA

ISBN: (纸本)9781665473613

The Ecosystem for Research networking (ERN) CryoEM Remote Instrument Pilot Project was launched in response to feedback and survey data collected from hundreds of participants of the ERN series of NSF (OAC-2018927) funded community outreach events revealing that Structural Biology instrument driven science is being forced to transition from self-contained islands to federated wide-area internet accessible instruments. Its goal is to facilitate multi-institutional collaboration at the interface of computing and electron microscopy through the implementation of the ERN Federated OpenCI Lab’s Instrument CI Cloudlet design. The conclusion will be a web-based portal leveraging federated access to the instrument, workflows utilizing edge computing in conjunction with cloud computing and real-time monitoring for experimental parameter adjustments and decisions. The intention is to foster team science and scientific innovation, with emphasis on under-represented and under-resourced institutions, through the democratization of these scientific instruments. This paper discusses the latest Phase 1 deployment efforts

关键词： Cloud computing Instruments Ecosystems Collaboration Documentation Real-time systems Software

来源：评论

学校读者我要写书评

暂无评论

New Perspectives on Recommender Systems for Industries

New Perspectives on Recommender Systems for Industries

引用

Artificial Intelligence for Industries (AI4I)

作者： Mouzhi Ge Giovanni Pilato Fabio Persia Daniela D’Auria Faculty of European Campus Rottal-Inn Deggendorf Institute of Technology Deggendorf Germany National Research Council of Italy Institute for High Performance Computing and Networking Palermo italy Department of Information Engineering Computer Science and Mathematics University of L’Aquila L’Aquila italy Faculty of Computer Science Free University of Bozen-Bolzano Bozen-Bolzano italy

Nowadays, recommender systems are increasingly being exploited in many industrial applications, including virtual museums and movie streaming platforms. In the last few years, some new perspectives provided by research paradigms such as deep learning or quantum computing, have arisen. As a result, this paper identifies four new perspectives on recommender systems: e-health, tourism, deep-learning-based, and recommender systems exploiting quantum computing. After discussing them, the paper provides the current state of the art and highlights the possible future directions for industries.

关键词： Industries Deep learning Training Quantum computing Scalability Computational modeling Virtual museums

来源：评论

学校读者我要写书评

暂无评论

Weak Devices Matter: Model Heterogeneity in Resource-Constrained Federated Learning

Weak Devices Matter: Model Heterogeneity in Resource-Constra...

引用

IEEE International Conference on Communications (ICC)

作者： Tzu–Hsuan Peng Cheng-Wei Huang Ai-Chun Pang Te-Chuan Chiu Department of Computer Science and Information Engineering National Taiwan University Taipei Taiwan R.O.C Graduate Institute of Networking and Multimedia National Taiwan University Taipei Taiwan R.O.C High Performance and Scientific Computing Center National Taiwan University Taipei Taiwan R.O.C Research Center for Information Technology Innovation Academia Sinica Taipei Taiwan R.O.C Department of Computer Science National Tsing Hua University Hsinchu Taiwan R.O.C

ISBN: (数字)9781728190549

ISBN: (纸本)9781728190556

Federated Learning (FL) is a promising framework for enabling edge intelligence while preserving privacy and enhancing communication efficiency. In real-world scenarios, limited and heterogeneous hardware resources among users threaten the overall training efficiency in FL. To address this issue, several model heterogeneity frameworks have emerged in recent years. However, existing studies primarily focus on mitigating idle times on powerful devices, overlooking the fact that strong devices may not always have a positive impact and can potentially become a burden instead. Furthermore, as the resource gap among clients widens or the number of weak devices increases, the model may be hindered by the influence of strong devices. Directly applying existing model heterogeneity frameworks leads to model performance degradation due to the neglect of contributions from weak devices. To make a performance breakthrough, we proposed a novel FL framework called Progressive Width Mixing (PWM), which extracts diverse features and balances the contribution of strong and weak devices and mitigates straggler effects under scenarios with various device distributions. To our best knowledge, we are the first model heterogeneity work that considered straggler effects from the weak devices' point of view. The experiments show that PWM maintains stability over different datasets and outperforms all baselines across various device distributions and non-IID scenarios. PWM makes a leap forward and surpasses all baselines by 7%, and mitigates the negative impact from the strong devices.

关键词： performance evaluation Training Privacy Philosophical considerations Federated learning Pulse width modulation System recovery

来源：评论

学校读者我要写书评

暂无评论

Health Data Information Retrieval For Improved Simulation

Health Data Information Retrieval For Improved Simulation

引用

Euromicro Conference on Parallel, Distributed and Network-Based Processing

作者： Mario Ciampi Giuseppe De Pietro Elio Masciari Stefano Silvestri Institute for High Performance Computing and Networking of the National Research Council of Italy Via Pietro Castellino 111 Naples Italy

ISBN: (数字)9781728165820

ISBN: (纸本)9781728165837

In this paper we propose an architecture specifically devoted to the analysis of huge natural language biomedical textual collections, with the purpose of searching for semantic similarity in order to obtain useful hints for effective simulation that could help physicians in diagnosis tasks. We leverage Word Embedding models trained with word2vec algorithm and a Big Data architecture for their processing and management. We performed some preliminary analyses using a dataset extracted from the whole PubMed library and we developed a web front-end to show the usability of this methodology in a real context.

关键词： Big Data Semantics Medical services Tools Data mining Biological system modeling Data models

来源：评论

学校读者我要写书评

暂无评论

Wormhole: A novel big data platform for 100 Gbit/s network monitoring and beyond 22

Wormhole: A novel big data platform for 100 Gbit/s network m...

引用

22nd International Conference on Innovation in Clouds, Internet and Networks and Workshops, ICIN 2019

作者： Leira, Rafael Gifre, Lluis Gonzalez, Ivan De Vergara, Jorge E. Lopez Aracil, Javier Universidad Autónoma de Madrid Spain Naudit High Performance Computing and Networking S.L. Spain

ISBN: (纸本)9781538683361

Internet measurement and analysis is increasingly challenging as the Internet evolves, primarily due to changing-trends, speed increments or new protocols and ciphers. As such, ad-hoc monitoring equipment comes in handy, albeit cost-effectiveness impedes deployment at a very large scale. As an alternative, big data-based distributed architectures are being proposed for network monitoring and analysis. However, in light of the high throughput currently offered by 100 Gbit/s links, it turns out that state-of-the-art big data solutions fall short of capacity, unless a huge amount of computers are used. In order to effectively tackle that issue, we have created Wormhole: a streaming engine that circumvents existing limitations by distributing the input messages/packets coherently among different off-the-shelf analysis equipment, thus reducing costs and equipment. Should the incoming data rate be larger than the system throughput, a distributed file system can be used for temporary data storage, for subsequent filtering and in-depth analysis. The proposed solution provides on-line real-time monitoring metrics with the ability to gain further insights when required. The prototyped architecture is able to deal with 100 Gbit/s networks and can be easily scaled up to higher rates by just adding more computing nodes and/or by trimming encrypted packet payloads. © 2019 IEEE.

关键词： Big data

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：