检索结果-内蒙古大学图书馆

24th COTA International Conference of Transportation Professionals: Resilient, Intelligent, Connected, and Lowcarbon Multimodal Transportation, CICTP 2024

作者： Chang, Yuchen Zong, Mengya Dang, Yutian Wang, Kaiping Dept. of Computer Science Xi’an Univ. of Architecture and Technology Xi’an China Dept. of Architecture Xi’an Univ. of Architecture and Technology Xi’an China

ISBN: (数字)9780784485484

ISBN: (纸本)9780784485484

Transport hubs play a major role in the national transport network. Larger and deeper subway stations attract a considerable influx of passengers, particularly during peak hours. Therefore, long-term pedestrian flow prediction is important for subway station management. This paper proposes an end-to-end learning framework based on the Graph Convolutional Network and the Attention Mechanism. In the first phase, key functional facilities within the subway station are abstracted into a graph structure. Subsequently, pedestrian flow data for graph nodes are obtained using Anylogic pedestrian simulation. In the second phase, a Graph Convolutional Network is employed to extract spatial features among nodes to capture the spatial dependencies of each node. The temporal attention operation is utilized to capture long-term temporal dependencies among nodes. This aids in the rational allocation of subway personnel and reducing congestion. Results demonstrate the validity and robustness of our model for pedestrian prediction. © ASCE.

关键词： Subway stations

来源：评论

学校读者我要写书评

暂无评论

Predicting Crowd Movement Trajectories: A Graph Network-Based Approach Informed by Simulation Data 24

Predicting Crowd Movement Trajectories: A Graph Network-Base...

引用

24th COTA International Conference of Transportation Professionals: Resilient, Intelligent, Connected, and Lowcarbon Multimodal Transportation, CICTP 2024

作者： Zong, Mengya Chang, Yuchen Dang, Yutian Wang, Kaiping Dept. of Computer Science Xi’an Univ. of Architecture and Technology Xi’an China Dept. of Architecture Xi’an Univ. of Architecture and Technology Xi’an China

ISBN: (数字)9780784485484

ISBN: (纸本)9780784485484

As-built assessment of transport hubs, based on large-scale simulation and passenger big data, has been an active area of research recently. Exploring the direction of crowd flow at future moments within a building is crucial for the rational assessment of the layout within the building. To tackle this problem, this paper proposes a two-stage framework for predicting passenger trajectories. In the first stage, our graph LSTM models the passenger’s trajectory sequence with the aim of capturing the temporal and spatial correlations in the passenger’s historical trajectory. In the second stage, different attentional weights are assigned to the previously embedded information to capture the interaction between pedestrians and the surrounding crowd. Finally, an LSTM decodes the information encoded for the passenger, predicting multiple plausible future trajectories. Experiments show that our model achieves excellent performance in the metrics ADE and FDE compared to the existing baseline of pedestrian trajectory prediction models. © ASCE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Survey on Use of AI/ML Algorithms in Enhancing Filesystem Performance and Efficiency 11

Survey on Use of AI/ML Algorithms in Enhancing Filesystem Pe...

引用

11th International Conference on Reliability, Infocom Technologies and Optimization, ICRITO 2024

作者： Olekar, Vijay Patil, Yash Pawar, Vishvam Pitale, Shubham Jaiswal, V.R. Naranje, Vishal Pune Institute of Computer Technology Pune Dept. of Information Technology Pune India School of Engineering Architecture and Interior Design Amity University Dubai United Arab Emirates

ISBN: (纸本)9798350350357

The processing power of CPUs is increasing day by day, but systems often struggle to fully utilize this power due to the bottleneck of file access time from the disk. Over the years, various techniques have been devised to reduce I/O latency while considering various file parameters. Our survey paper aims to shed light on these techniques, efficiently comparing them and highlighting the benefits and drawbacks of each approach. For our evaluation, we have considered various file parameters, such as access time, file size, directory structure, and kernel execution flow. We have combined these parameters with a range of supervised and unsupervised machine learning algorithms, including Decision Tree, ABLE, RNN, GNN, CART, XGBoost, CNN, and more. This survey aims to highlight the use of ML/AI algorithms in the intelligent detection of file access and I/O patterns to optimize the performance of modern applications. © 2024 IEEE.

关键词： Cyber Physical System

来源：评论

学校读者我要写书评

暂无评论

QVal: A Novel Routing Algorithm for Dragonfly Networks 25

QVal: A Novel Routing Algorithm for Dragonfly Networks

引用

25th IEEE International Conferences on High Performance Computing and Communications, 9th International Conference on Data Science and Systems, 21st IEEE International Conference on Smart City and 9th IEEE International Conference on Dependability in Sensor, Cloud and Big Data Systems and Applications, HPCC/DSS/SmartCity/DependSys 2023

作者： Navaridas, Javier Pascual, Jose A. Dept. of Computer Architecture and Technology Paseo Manuel de Lardizabal 1 Donostia-San Sebastián20018 Spain

ISBN: (纸本)9798350330014

Dragonfly is becoming one of the networks of choice for high-performance computer systems as it offers a sweet spot in terms of cost, simplicity, performance, fault-tolerance and power. In a Dragonfly topology, compute nodes are connected to routers forming fully-connected groups, which are then connected to every other group. This provides very high connectivity with very low diameter which are desired characteristics of high performance interconnection networks. In this work, we propose Quick Valiant, a new routing algorithms for dragonfly networks which leverages Valiant routing with novel proxy selection criteria which reduce the utilization of network resources and eases congestion under pathological loads. These criteria restrict the possible proxies to these that are adjacent to either the local or the remote router, codenamed QVL and QVR, respectively. We compare our proposals with canonical routing functions and observe reductions of average path length of up to 27% and throughput improvements of up to 46% when compared with Valiant routing. Out of these criteria, restricting to local proxies only, QVL, obtains the best results in all scenarios. © 2023 IEEE.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Acceleration and energy consumption optimization in cascading classifiers for face detection on low-cost ARM *** asymmetric architectures

arXiv

引用

arXiv 2024年

作者： Corpas, Alberto Costero, Luis Botella, Guillermo Igual, Francisco D. García, Carlos Rodríguez, Manuel Dept. of Architecture and Computer Technology ETSIIT University of Granada Granada18071 Spain Dept. Computer Architecture and Automation Complutense University of Madrid Madrid28040 Spain

This paper proposes a mechanism to accelerate and optimize the energy consumption of a face detection software based on Haar-like cascading classifiers, taking advantage of the features of low-cost Asymmetric Multicore Processors (AMPs) with limited power budget. A modelling and task scheduling/allocation is proposed in order to efficiently make use of the existing features on *** ARM processors, including: (I) source-code adaptation for parallel computing, which enables code acceleration by applying the OmpSs programming model, a task-based programming model that handles data-dependencies between tasks in a transparent fashion;(II) different OmpSs task allocation policies which take into account the processor asymmetry and can dynamically set processing resources in a more efficient way based on their particular features. The proposed mechanism can be efficiently applied to take advantage of the processing elements existing on low-cost and low-energy multi-core embedded devices executing object detection algorithms based on cascading classifiers. Although these classifiers yield the best results for detection algorithms in the field of computer vision, their high computational requirements prevent them from being used on these devices under real-time requirements. Finally, we compare the energy efficiency of a heterogeneous architecture based on asymmetric multicore processors with a suitable task scheduling, with that of a homogeneous symmetric architecture. Copyright © 2024, The Authors. All rights reserved.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Identify Initial Nodes for Spreader in A New Diffusion Model Based on Topology (DBT) in Social Networks 9

Identify Initial Nodes for Spreader in A New Diffusion Model...

引用

9th International Conference on Web Research, ICWR 2023

作者： Khosravi, Ehsan Yazdanifar, Fatemeh Salimi, Nikoo Beni, Hamid Ahmadi Sharif University of Technology Dept. of Computer Engineering Tehran Iran Amirkabir University of Technology Dept. of Mathematics and Computer Science Tehran Iran Engineering and Naval Architecture University of Genoa Dept. of the Electrical Electronics Electronics and Telecommunication Genoa Italy Azarbaijan Shahid Madani University Dept. of Software Engineering Tabriz Iran

ISBN: (纸本)9798350399691

With the development of science and technology through social networks, the process of diffusion has become a controversial subject. In social networks, the process of diffusion is transmitted from one individual to another. The influence maximization problem, in which at least k nodes are chosen as the initial nodes of the spreader in the smallest amount of time, is one of the most critical aspects of the diffusion process. Furthermore, the initial nodes in the social network should generate the most influence on the other nodes in the network. However, in the algorithms proposed to solve the problem of influence maximization, the real-world factors which affect the influence probability in diffusion models are ignored for example, the influence probability is determined randomly. This problem causes influence maximization algorithms based on diffusion models to face the challenge of time-consuming Monte Carlo simulation. So, the RIM algorithm presented in this article which this method selects the initial nodes of the spreader according on their local reachability. In addition, Due to privacy in social networks, complete information about people such as gender, education, etc. is not available. For this reason, in the RIM algorithm, using the graph structure in social networks, the influence probability is calculated in the new DBT diffusion model. In addition, the RIM algorithm exhibits stable performance in the selection of the spreader's initial nodes in terms of influence spread, and execution time. © 2023 IEEE.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Concept of an Optical Distance and Speed Sensor Using Novel Offsetless Spatial Frequency Filters in the Area of Functional Safety 32

Concept of an Optical Distance and Speed Sensor Using Novel ...

引用

32nd IEEE International Symposium on Industrial Electronics, ISIE 2023

作者： Wasinski, Frank Bonath, Werner Ricklefs, Ubbo Borcsok, Josef Schwarz, Michael Hahn, Eike University of Applied Sciences THM Dept. of Electrical Engineering and Information Technology Giessen Germany Institute for Computer Architecture and System Programming University of Kassel ICAS Kassel Germany

ISBN: (纸本)9798350399714

Optical speed sensors based on the spatial frequency filter method are a proven technology that offer high measurement accuracy over a wide speed range. Newly developed variants also enable measurements at very low speeds and increase the robustness of the method [1]. This makes the sensor very suitable for use in the area of functional safety. A measurement chain up to safety integrity level 3 (SIL3) should be feasible via a combination with a safety system on a chip (SoC) for evaluating the measurement data and an extension of the sensor module to include safety-related elements [2], [3]. By integrating the sensor at IC level, a compact overall solution is to be made possible. After the first successful tests with the safety SoC, further examinations of the measuring method with regard to functional safety are now necessary. © 2023 IEEE.

关键词： System-on-chip

来源：评论

学校读者我要写书评

暂无评论

Improving the performance of Dragonfly networks through restrictive Proxy routing strategies

引用

computer Networks 2025年 267卷

作者： Navaridas, Javier Pascual, Jose A. Dept. of Computer Architecture and Technology Faculty of Computer Science University of the Basque Country UPV/EHU Paseo Manuel de Lardizabal 1 Donostia-San Sebastián20018 Spain

Dragonfly has become the network of choice for large-scale high-performance computing systems and, indeed, it dominates the top positions of supercomputer rankings. The reason for this is that it offers a sweet spot in terms of cost, simplicity, performance, fault-tolerance and power consumption. In this work, we propose a collection of routing strategies which restrict proxies to be adjacent to either the local or the remote router. This way, it features shorter paths than the standard Valiant routing. We carry out an extensive simulation-based evaluation to assess their performance. Our experiments found latency reductions of up to 76% and throughput improvements of up to 26% when compared with standard Valiant routing when using synthetic traffic from independent sources at different scales. Furthermore, when using realistic application-inspired workloads, we found the strategies required between 5% and 20% less time to perform communications. In general, we observe that selecting proxies that are adjacent to the sender is more beneficial than those adjacent to the destination because the latter tends to generate backpressure in the last level of the interconnect. Interestingly, we found that the most restrictive proxy routing strategies obtain the best results in all scenarios and show that counterintuitively, the lower the path diversity, the more balanced the use of network resources. Our study includes investigating the interplay between routing and Dragonfly parameters and provide optimal parameters for proxy-based routing algorithms. Finally, we discuss some practical considerations related to the deployment of our strategies. © 2025 The Authors

关键词： Interconnection networks (circuit switching)

来源：评论

学校读者我要写书评

暂无评论

Allocating and Routing Resources in an IoT Network with an Efficient Hybrid Optimization Approach 1

Allocating and Routing Resources in an IoT Network with an E...

引用

1st International Conference on Applied Artificial Intelligence and Computing, ICAAIC 2022

作者： Umar, Syed Reddy, N Linga Yadesa, Tariku Birhanu Deressa, Tadele Debisa Fikadu, Etana College of Engineering & Technology Wollega University Dept. of Computer Science Nekemte Ethiopia Dr Ysr Architecture and Fine Arts University Dept. of Computer Science Andhra Pradesh Kadapa India

ISBN: (纸本)9781665497107

technology, economics, government, people, management, and infrastructure all play a role in creating a Smart City. This indicates that a Smart City may have different communication requirements than a traditional city. The introduction of wireless technologies like WiFi, Bluetooth, ZigBee, WiMax, and 4G/LTE has made them a viable option for facilitating communication in Smart City projects. As long as they are using unlicensed interference, coexistence and band problems will continue to be a problem. Smart cities utilize the Internet of Things (IoT) to address this issue. Using hybrid optimization methods, this article tackles the problems of resource allocation and routing for the Internet of Things (IoT) by proposing the ECRR protocol (energy efficient, congestion aware resource allocation and routing). Data clustering and met heuristic algorithms are usedin the first step of the ECRR method to better distribute IoT devices and gateways throughout the network. It also proposes a method for selecting the best future route by using a queue-based swarm optimization algorithm, which enhancesthe route discovery process. With Network Simulator (NS-2), the proposed ECRR approach is simulated and compared to existing state-of-the-art methods in terms of energy consumption, node lifetime, throughput, end-to end latency, packet delivery ratio, and packet overheads. © 2022 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Supporting Disaster Resilience Building through Cross-Community Knowledge Sharing 13

Supporting Disaster Resilience Building through Cross-Commun...

引用

13th Annual IEEE Global Humanitarian technology Conference, GHTC 2023

作者： Koga, Motoya Kaneko, Tetsuya Leleito, Emanuel Karashima, Kazuki Aharari, Ari Sojo University Department of Architecture Kumamoto Japan Nagoya University Graduate School of Engineering Nagoya Japan Maebashi Institute of Technology Dept.of Architecture Maebashi Japan Sojo University Department of Computer and Information Sciences Kumamoto Japan

ISBN: (纸本)9798350321326

Collaborative action in disaster mitigation efforts contributes to knowledge and experience sharing, resource sharing, improvement of response and coordination, and standardization of good practice. In this study, we propose a workshop model and develop a virtual collaboration tool to support and promote cross-community knowledge sharing and collaboration focusing on disaster mitigation efforts. The workshop model involves pre-fieldwork training, actual fieldwork, and post-fieldwork information exchange. The collaboration tool enables information collection, sharing and record keeping. The effectiveness of the workshop model and the collaboration tool is demonstrated through use in a citizen participatory disaster preparedness workshops linking two elementary schools located in the central and southern regions of Japan. © 2023 IEEE.

关键词： Disaster prevention

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：