检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Nejadshamsi, Shayan Bentahar, Jamal Wang, Chun Eicker, Ursula Concordia University MontrealQCH3G 1M8 Canada Department of Electrical Engineering and Computer Science Khalifa University Abu Dhabi United Arab Emirates Canada Excellence Research Chair Next Generation Cities Gina Cody School of Engineering and Computer Science Concordia University MontrealQCH3G 1M8 Canada

Bike-sharing systems, popular for eco-friendly travel, face challenges with supply-demand imbalances, resulting in user dissatisfaction and resource inefficiency. Accurately predicting passenger demand is important for optimizing the efficiency of bike-sharing services. Deep learning methods have extensively explored the intricate spatiotemporal dynamics of bike-sharing demand. However, current approaches often overlook analyzing demand at the station level, instead focus on broader geographical areas and grid-based assessments. They primarily rely on geographical proximity for spatial correlation and tend to predict only bike check-in demand, neglecting the correlation of check-in and check-out demand. To this end, this paper introduces a spatial-temporal deep graph-based learning architecture, namely the Multi-Task Semi-Adaptive Graph-based Neural Network (MTSAG), for accurate prediction of hourly bike-sharing demand across the city's bike stations, aiming to address the challenges above. Initially, we analyze historical data and identify three key historical features for each time interval: closeness, period, and trend. Subsequently, we design three separate streams for our proposed architecture, each dedicated to one of these historical features, and design components to capture both spatial and temporal dependencies within each stream. For capturing spatial information, a graph convolution operator is used along with a time-varying semantic adjacency graph generated from the pairwise similarity of stations' historical demand. We employ dual-input Long Short-Term Memory (di-LSTM) recurrent block to learn temporal dependencies and facilitate multi-task learning. This component enables the extraction of hidden pairwise demand correlations by treating the prediction tasks of bike check-in and check-out demands as interrelated. Moreover, we incorporate the effects of global features, such as meteorological information, to account for broader-scale changes in our ana

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

TiCoNE 2: A composite clustering model for robust cluster analyses on noisy data

arXiv

引用

arXiv 2019年

作者： Wiwie, Christian Röttger, Richard Baumbach, Jan Institute of Mathematics and Computer Science University of Southern Denmark Campusvej 55 OdenseDK-5230 Denmark Chair of Experimental Bioinformatics Technical University of Munich Maximus-von-Imhof-Forum 3 Freising-Weihenstephan85354 Germany

Identifying groups of similar objects using clustering approaches is one of the most frequently employed first steps in exploratory biomedical data analysis. Many clustering methods have been developed that pursue different strategies to identify the optimal clustering for a data set. We previously published TiCoNE, an interactive clustering approach coupled with de-novo network enrichment of identified clusters. However, in this first version time-series and network analysis remained two separate steps in that only time-series data was clustered, and identified clusters mapped to and enriched within a network in a second separate step. In this work, we present TiCoNE 2: An extension that can now seamlessly incorporate multiple data types within its composite clustering model. Systematic evaluation on 50 random data sets, as well as on 2,400 data sets containing enriched cluster structure and varying levels of noise, shows that our approach is able to successfully recover cluster patterns embedded in random data and that it is more robust towards noise than non-composite models using only one data type, when applied to two data types simultaneously. Herein, each data set was clustered using five different similarity functions into k=10/30 clusters, resulting to ~5,000 clusterings in total. We evaluated the quality of each derived clustering with the Jaccard index and an internal validity score. We used TiCoNE to calculate empirical p-values for all generated clusters with different permutation functions, resulting in ~80,000 cluster p-values. We show, that derived p-values can be used to reliably distinguish between foreground and background clusters. TiCoNE 2 allows researchers to seamlessly analyze time-series data together with biological interaction networks in an intuitive way and thereby provides more robust results than single data type cluster analyses. Copyright © 2019, The Authors. All rights reserved.

关键词： Cluster analysis

来源：评论

学校读者我要写书评

暂无评论

Softwarization of internet of things infrastructure for secure and smart healthcare

arXiv

引用

arXiv 2018年

作者： Salahuddin, Mohammad A. Al-Fuqaha, Ala Guizani, Mohsen Shuaib, Khaled Sallabi, Farag David R. Cheriton School of Computer Science University of Waterloo WaterlooONN2L 3G1 Canada Department of Computer Science Western Michigan University KalamazooMI49008 United States Chair of the Electrical and Computer Engineering Department University of Idaho MoscowID83844 United States College of Information Technology United Arab Emirates University Al Ain United Arab Emirates

We propose an agile softwarized infrastructure for flexible, cost effective, secure and privacy preserving deployment of Internet of Things (IoT) for smart healthcare applications and services. It integrates state-of-the-art networking and virtualization techniques across IoT, fog and cloud domains, employing Blockchain, Tor and message brokers to provide security and privacy for patients and healthcare providers. We propose a novel platform using Machine-to-Machine (M2M) messaging and rule-based beacons for seamless data management and discuss the role of data and decision fusion in the cloud and the fog, respectively, for smart healthcare applications and services. Copyright © 2018, The Authors. All rights reserved.

关键词： Fog

来源：评论

学校读者我要写书评

暂无评论

Enhanced Federated Anomaly Detection Through Autoencoders Using Summary Statistics-Based Thresholding

arXiv

引用

arXiv 2024年

作者： Laridi, Sofiane Palmer, Gregory Tam, Kam-Ming Mark L3S Research Center Faculty of Electrical Engineering and Computer Science Leibniz University Hannover30167 Germany Department of Architecture University of Hong Kong Knowles Building Pokfulam Road Hong Kong

In Federated Learning (FL), anomaly detection (AD) is a challenging task due to the decentralized nature of data and the presence of non-IID data distributions. This study introduces a novel federated threshold calculation method that leverages summary statistics from both normal and anomalous data to improve the accuracy and robustness of anomaly detection using autoencoders (AE) in a federated setting. Our approach aggregates local summary statistics across clients to compute a global threshold that optimally separates anomalies from normal data while ensuring privacy preservation. We conducted extensive experiments using publicly available datasets, including Credit Card Fraud Detection, Shuttle, and Covertype, under various data distribution scenarios. The results demonstrate that our method consistently outperforms existing federated and local threshold calculation techniques, particularly in handling non-IID data distributions. This study also explores the impact of different data distribution scenarios and the number of clients on the performance of federated anomaly detection. Our findings highlight the potential of using summary statistics for threshold calculation in improving the scalability and accuracy of federated anomaly detection systems. © 2024, CC BY.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

REQUIREMENTS FOR AN EVENT-BASED SIMULATION PACKAGE FOR GRID SYSTEMS

引用

Journal of Interconnection Networks 2007年第2期8卷 163-178页

作者： FATOS XHAFA JAVIER CARRETERO LEONARD BAROLLI ARJAN DURRESI Polytechnic University of Catalonia Department of Languages and Informatics Systems C/Jordi Girona 1-3 08034 Barcelona Spain . Polytechnic University of Catalonia Department of Computer Architecture C/Jordi Girona 1-3 08034 Barcelona Spain Department of Information and Communication Engineering Fukuoka Institute of Technology (FIT) 3-30-1 Wajiro-higashi Higashi-ku Fukuoka 811-0295 Japan Department of Computer Science Louisiana State University 298 Coates Hall Baton Rouge LA 70803 USA

In this paper we present a study on the requirements for the design and implementation of simulation packages for Grid systems. Grids are emerging as new distributed computing systems whose main objective is to manage and allocate geographically distributed computing resources to applications and users in an efficient and transparent manner. Grid systems are at present very difficult and complex to use for experimental studies of large-scale distributed applications. Although the field of simulation of distributed computing systems is mature, recent developments in large-scale distributed systems are raising needs not present in the simulation of the traditional distributed systems. Motivated by this, we present in this work a set of basic requirements that any simulation package for Grid computing should offer. This set of functionalities is obtained after a careful review of most important existing Grid simulation packages and includes new requirements not considered in such simulation packages. Based on the identified set of requirements, a Grid simulator is developed and exemplified for the Grid scheduling problem.

关键词： Grid systems event-based simulation requirements scheduling

来源：评论

学校读者我要写书评

暂无评论

Resilience via Blackbox Self-Piloting Plants 29

Resilience via Blackbox Self-Piloting Plants

引用

29th computer and Electronics Security Application Rendezvous, C and ESAR 2022

作者： Barbeau, Michel Garcia-Alfaro, Joaquin Lübben, Christian Pahl, Marc-Oliver Wüstrich, Lars School of Computer Science Carleton University 1125 Colonel By Drive OttawaONK1S 5B6 Canada Institut Polytechnique de Paris T l com SudParis SAMOVAR Palaiseau 91120 France Institut Für Informatik Der Technischen Universität München Lehrstuhl I8 Boltzmannstr. 3 Garching Bei München85748 Germany IMT Atlantique UMR IRISA CNRS IRISA Rennes6074 France IMT Industrial chair Cybersecurity Critical Networked Infrastructures TUM Smart Space Orchestration team Chair for Network Architectures and Services C&ESAR'22: Computer & Electronics Security Application Rendezvous Nov. 15-16 Rennes2022 France

Distributed control is a reality of today's industrial automation and systems. Parts of a system are on-site, and other elements are on the edge of the cloud. The overall system-functioning relies on the reliable operation of local and remote components. However, all system parts can be attacked. Typically, local entities of a cyber-physical system, such as robot arms or conveyor belts, get affected by cyber attacks. However, attacking the control and monitoring channels between a plant and its remote controller is attractive, too. There is a diversity of attacks, such as manipulating a plant's input signals, controller logic, and output signals. To detect and mitigate the impact of such various attacks and to make a plant more resilient, we introduce a self-learning controller proxy in the plant's communication channel to the controller. It acts as a local trust anchor to the commands received from a remote controller. It does black box self-learning of the controller algorithms and audits its operations. Once an attack is detected, the plant pivots into self-piloting mode. We investigate design alternatives for the controller proxy. We evaluate how complex the control algorithms can be to enable self-piloting resilience. ©2022 Copyright for this paper by its authors.

关键词： Cyber Physical System

来源：评论

学校读者我要写书评

暂无评论

Gcn-Gat-Mlp: A Hybrid Geographic-Semantic Context-Aware Urban Commuting Flow Prediction Model Using Neural Networks

SSRN

引用

SSRN 2023年

作者： Nejadshamsi, Shayan Eicker, Ursula Bentahar, Jamal Wang, Chun Concordia University MontrealQCH3G 1M8 Canada Department of Electrical Engineering and Computer Science Khalifa University Abu Dhabi United Arab Emirates Canada Excellence Research Chair Next Generation Cities Gina Cody School of Engineering and Computer Science Concordia University MontréalQCH3G 1M8 Canada

Prediction of urban-scale commuting flow plays an important role in urban and transportation planning and optimization. The traditional and machine-learning solutions used for this purpose have some limitations. Traditional models, such as gravity, are analytical physics-based models that lack important origin and destination features like land use and sociodemographic information. On the other hand, machine learning-based models leverage the essential information of origin and destination zones, which makes them better than traditional ones;however, they mostly ignore the influence of geographically and semantically nearby zones. To address these issues, we propose a hybrid model that captures the information of the neighbor zones both geographically and semantically and improves the prediction accuracy. In the first step, we extract the features of all geographic units, such as Points of Interest (POIs) and distance to the Central Business District (CBD). Then, we use the geographic adjacency matrix to encapsulate the information of nearby zones into each zone using Graph Convolution Network (GCN). In the third step, we consider spatial flow interaction to construct the semantic adjacency matrix and use it to encode the information of semantically nearby zones using Graph Attention Network (GAT). Finally, a Multilayer Perceptron (MLP) regressor is trained to predict the commuting flow based on the embeddings and flow. We evaluate our proposed model on a real-world Montreal, CA dataset, demonstrating our model's effectiveness relative to the state of the art. © 2023, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Stable information transfer network facilitates the emergence of collective behavior of bird flocks

引用

Physical Review E 2018年第5期98卷 052309-052309页

作者： Jiaping Ren Wanxuan Sun Dinesh Manocha Aming Li Xiaogang Jin State Key Lab of CAD&CG Zhejiang University Hangzhou 310058 China Department of Computer Science and Electrical and Computer Engineering University of Maryland College Park Maryland 20742 USA Department of Zoology and Oxford Centre for Integrative Systems Biology University of Oxford Oxford OX1 3PS United Kingdom Chair of Systems Design ETH Zürich Weinbergstrasse 56/58 Zürich CH-8092 Switzerland

Collective behavior is ubiquitous in living systems such as human crowds, microbial communities, insect swarms, and bird flocks. It is widely reported that simple, local, temporal interactions between individuals may lead to the emergence of collective behavior. In large-scale flocks, however, the global information transfer in dynamical models with time-varying neighborhoods is not normally instantaneous. Here, we present an information transfer network in which interactions last for a certain period of time. We then combine this network with a dynamic model of self-propelled particles. We observe that the resulting model that uses a stable information transfer network creates a bird flock with a more robust performance. We further show that the time of information transfer in a flock grows logarithmically with its size and is proportional to the average response time of the birds. Moreover, we find that the ranking curves displaying the order in which birds first perceive an external stimulus have similar shapes across different flocks. Our results demonstrate that, beyond the traditional local, temporal interactions, our stable information transfer network serves as an efficient mechanism to model the emergence of large-scale collective behavior.

关键词： Collective behavior in networks Self-organized systems Ecological networks

来源：评论

学校读者我要写书评

暂无评论

MLStock:Multi-layer model for sentiment analysis based stock price prediction

MLStock:Multi-layer model for sentiment analysis based stock...

引用

作者： Tianyang Xu Zongyuan Xiang Bingjian Lu Nuo Chen Ziqi Dai School of Computer Science Wuhan University School of Engineering Architecture and Information TechnologyUniversity of Queensland College of Liberal Arts Drew University Maynooth International Engineering College Fuzhou University No.3 Experimental High School in Guiyang

In this paper,we address the task of predicting stock prices using the market sentiments extracted from *** propose MLStock,a multi-layer framework that models the market sentiment with the stock layer,the sector layer,and the market layer using the Gated Recurrent Unit(GRU),and use the sentiment to make directional prediction on stock *** methods consider stocks individually,and might miss the signals in the current market sector which will affect the stock *** contrast,our model summarizes the sector and market states through individual states and shows an improvement over traditional machine learning methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Tools, conceptual frameworks, and empirical studies for early stages of design

Tools, conceptual frameworks, and empirical studies for earl...

引用

Conference on Human Factors in Computing Systems, CHI EA 2001

作者： Nakakoji, Kumiyo Gross, Mark D. Candy, Linda Edmonds, Ernest Toresto Sra Inc. NAIST Grad. Scl. of Info. Sci. 8916-5 Takayama Ikoma Nara 630-0101 Japan Department of Architecture Design Machine Group University of Washington Seattle WA 98195-5720 United States Department of Computer Science LUTCHI Research Centre:C and CRS Loughborough University Loughborough L E l l 3TU United Kingdom

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：