检索结果-内蒙古大学图书馆

An interactive city choice model and its application for measuring the intercity interaction

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Jia, Xiang-Yu Liu, Er-Jian Chen, Chun-Yan Yan, Xiao-Yong Key Laboratory of Transport Industry of Big Data Application Technologies for Comprehensive Transport Ministry of Transport Beijing Jiaotong University Beijing100044 China Institute of Transportation System Science and Engineering Beijing Jiaotong University Beijing100044 China Traffic Control Technology Co. Ltd Beijing100875 China

Measuring the interaction between cities is an important research topic in many disciplines, such as sociology, geography, economics and transportation science. The traditional and most widely used spatial interaction model is the gravity model, but it requires the parameters to be artificially set. In this paper, we propose a parameter-free interactive city choice (ICC) model that measures intercity interaction from the perspective of individual choice behavior. The ICC model assumes that the probability of an individual choosing to interact with a city is proportional to the number of opportunities in the destination city and inversely proportional to the number of intervening opportunities between the origin city and the destination city, calculated using the travel time in the transportation network. The intercity interaction intensity can be obtained by calculating the product of this probability and the origin city's population. We apply the ICC model to measure the interaction intensity among 339 cities in China and analyze the impact of changes in the Chinese land transportation network from 2005 to 2018 on the intercity and city interaction intensity. Compared with the previously widely used spatial interaction models, the measurement results of the ICC model are more consistent with the actual situation. © 2021, CC BY.

关键词： Travel time

Capacity analysis of ship-tugging operations in a large container port

学校读者我要写书评

暂无评论

Asian Transport Studies 2020年 6卷

作者： Kang, Liujiang Gao, Song Meng, Qiang Key Laboratory of Transport Industry of Big Data Application Technologies for Comprehensive Transport Ministry of Transport Beijing Jiaotong University 100044 China Intelligent Transportation Systems Research Center Wuhan University of Technology Wuhan 430063 China Department of Civil and Environmental Engineering National University of Singapore Singapore 117576 Singapore

In this study, we deal with the simulation problem of ship-tugging operations in a large container port. First, we build a tugboat-service network using a directed graph, where the nodes consist of tugboat bases, anchorages, and berths while the arcs represent the directed links between nodes. Second, we develop a marine traffic simulation system, which can simulate maritime traffic conditions in restricted waters, such as large container ports and busy straits. The marine traffic simulation system is a customized system. Users are allowed to set their study areas and virtual traffic environment (such as traffic demand and network structure) at will. Finally, we conduct various simulations for a real tugboat-service network of Singapore Port, which includes one anchorage, one tugboat base, two berths, and two channels between the anchorage and berths. A detailed analysis of the tugging capacity is provided based on simulation results. © 2020 The Authors

关键词： Capacity estimation Container ports Simulation system development Tugging operations

DNN Task Assignment in UAV Networks: A Generative AI Enhanced Multi-Agent Reinforcement Learning Approach

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Tang, Xin Chen, Qian Weng, Wenjie Liao, Binhan Wang, Jiacheng Cao, Xianbin Li, Xiaohuan Guangxi University Key Laboratory of Intelligent Networking and Scenario System School of Information and Communication Guilin University of Electronic Technology Guilin541004 China The College of Computing and Data Science Nanyang Technological University 639798 Singapore School of Architecture and Transportation Engineering Guilin University of Electronic Technology Guilin541004 China National Engineering Laboratory for Comprehensive Transportation Big Data Application Technology Guangxi Nanning530001 China College of Computing and Data Science Nanyang Technological University 639798 Singapore School of Electronic and Information Engineering The Key Laboratory of Advanced Technology of Near Space Information System Ministry of Industry and Information Technology of China Beihang University Beijing100191 China

Unmanned Aerial Vehicles (UAVs) possess high mobility and flexible deployment capabilities, prompting the development of UAVs for various application scenarios within the Internet of Things (IoT). The unique capabilities of UAVs give rise to increasingly critical and complex tasks in uncertain and potentially harsh environments. The substantial amount of data generated from these applications necessitates processing and analysis through deep neural networks (DNNs). However, UAVs encounter challenges due to their limited computing resources when managing DNN models. This paper presents a joint approach that combines multiple-agent reinforcement learning (MARL) and generative diffusion models (GDM) for assigning DNN tasks to a UAV swarm, aimed at reducing latency from task capture to result output. To address these challenges, we first consider the task size of the target area to be inspected and the shortest flying path as optimization constraints, employing a greedy algorithm to resolve the subproblem with a focus on minimizing the UAV’s flying path and the overall system cost. In the second stage, we introduce a novel DNN task assignment algorithm, termed GDM-MADDPG, which utilizes the reverse denoising process of GDM to replace the actor network in multi-agent deep deterministic policy gradient (MADDPG). This approach generates specific DNN task assignment actions based on agents’ observations in a dynamic environment. Simulation results indicate that our algorithm performs favorably compared to benchmarks in terms of path planning, Age of Information (AoI), energy consumption, and task load balancing. Copyright © 2024, The Authors. All rights reserved.

关键词： Motion planning

Secondary Access Class Barring for Machine Type Communications with PUSCH Resource Constraints

学校读者我要写书评

暂无评论

Secondary Access Class Barring for Machine Type Communicatio...

IEEE Conference on Vehicular technology (VTC)

作者： Yuxuan Wen Liu Yang Chaoyuan Bai Heng Liu Communication and Sensor Network for Modern Transportation International Cooperation Center(CSNMT) Southwest Jiaotong University Chengdu P.R.China Key Lab of Information Coding & Transmission Institude of Mobile Communication Southwest Jiaotong University Chengdu P.R.China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Chengdu P.R.China

ISBN: (数字)9798331517786

ISBN: (纸本)9798331517793

With the continuous increase of IoT devices, multiple devices desire to use network resources simultaneously during peak hours and overload conditions, leading to collisions and a reduction in the network’s effective throughput. The Access Class Barring (ACB) method has been proposed as the optimal potential solution in LTE communication networks to overcome this problem. However, existing ACB schemes do not fully utilize preamble resources, and most schemes do not consider the situation where PUSCH resources are limited. Therefore, this paper proposes a two-stage ACB algorithm that considers the situation of limited PUSCH resources. This algorithm recycles part of the preamble resources and sets the ACB factor based on the number of PUSCH resources. Simulation results show that our proposed algorithm significantly outperforms traditional schemes in terms of total service time, delay, throughput, and PUSCH resource efficiency.

关键词： Vehicular and wireless technologies Delay effects Computer simulation Throughput Delays Internet of Things Communication networks Long Term Evolution

A Survey of Route Recommendations: Methods, applications, and Opportunities

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Shiming Luo, Zhipeng Yang, Li Teng, Fei Li, Tianrui School of Computing and Artificial Intelligence Southwest Jiaotong University China Engineering Research Center of Sustainable Urban Intelligent Transportation Ministry of Education China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University China Manufacturing Industry Chains Collaboration and Information Support Technology Key Laboratory of Sichuan Province Southwest Jiaotong University Sichuan Chengdu611756 China

Nowadays, with advanced information technologies deployed citywide, large data volumes and powerful computational resources are intelligentizing modern city development. As an important part of intelligent transportation, route recommendation and its applications are widely used, directly influencing citizens' travel habits. Developing smart and efficient travel routes based on big data (possibly multi-modal) has become a central challenge in route recommendation research. Our survey offers a comprehensive review of route recommendation work based on urban computing. It is organized by the following three parts: 1) Methodology-wise. We categorize a large volume of classic methods and modern deep learning methods. Also, we discuss their historical relations and reveal the edge-cutting progress. 2) application-wise. We present numerous novel applications related to route commendation within urban computing scenarios. 3) We discuss current problems and challenges and envision several promising research directions. We believe that this survey can help relevant researchers quickly familiarize themselves with the current state of route recommendation research and then direct them to future research trends. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep learning

Continual Learning for Smart City: A Survey

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yang, Li Luo, Zhipeng Zhang, Shiming Teng, Fei Li, Tianrui School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu611756 China Engineering Research Center of Sustainable Urban Intelligent Transportation Ministry of Education National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University China Manufacturing Industry Chains Collaboration and Information Support Technology Key Laboratory of Sichuan Province Southwest Jiaotong University Sichuan Chengdu611756 China

With the digitization of modern cities, large data volumes and powerful computational resources facilitate the rapid update of intelligent models deployed in smart cities. Continual learning (CL) is a novel machine learning paradigm that constantly updates models to adapt to changing environments, where the learning tasks, data, and distributions can vary over time. Our survey provides a comprehensive review of continual learning methods that are widely used in smart city development. The content consists of three parts: 1) Methodology-wise. We categorize a large number of basic CL methods and advanced CL frameworks in combination with other learning paradigms including graph learning, spatial-temporal learning, multi-modal learning, and federated learning. 2) application-wise. We present numerous CL applications covering transportation, environment, public health, safety, networks, and associated datasets related to urban computing. 3) Challenges. We discuss current problems and challenges and envision several promising research directions. We believe this survey can help relevant researchers quickly familiarize themselves with the current state of continual learning research used in smart city development and direct them to future research trends. Copyright © 2024, The Authors. All rights reserved.

关键词： Smart city

Bicycle flow dynamics on wide roads: Experiment and modeling

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Guo, Ning Jiang, Rui Wong, S.C. Hao, Qing-Yi Xue, Shu-Qi Hu, Mao-Bin School of Automotive and Transportation Engineering Hefei University of Technology Hefei230009 China Key Lab. of Transport Industry of Big Data Application Technologies for Comprehensive Transport Ministry of Transport Beijing Jiaotong University Beijing100044 China Department of Civil Engineering University of Hong Kong Pokfulam Road Hong Kong School of Mathematics and Computational Science Anqing Normal University Anqing246133 China School of Engineering Science University of Science and Technology of China Hefei230026 China

Cycling is a green transportation mode, and is promoted by many governments to mitigate traffic congestion. However, studies concerning the traffic dynamics of bicycle flow are very limited. This study experimentally investigated bicycle flow dynamics on a wide road, modeled using a 3-m-wide track. The results showed that the bicycle flow rate remained nearly constant across a wide range of densities, in marked contrast to single-file bicycle flow, which exhibits a unimodal fundamental diagram. By studying the weight density of the radial locations of cyclists, we argue that this behavior arises from the formation of more lanes with the increase of global density. The extra lanes prevent the longitudinal density from increasing as quickly as in single-file bicycle flow. When the density is larger than 0.5 bicycles/m2, the flow rate begins to decrease, and stop-and-go traffic emerges. A cognitive-science-based model to reproduce bicycle dynamics is proposed, in which cyclists apply simple cognitive procedures to adapt their target directions and desired riding speeds. To incorporate differences in acceleration, deceleration, and turning, different relaxation times are used. The model can reproduce the experimental results acceptably well and may also provide guidance on infrastructure design. Copyright © 2019, The Authors. All rights reserved.

关键词： Traffic congestion

Improved Sparse Activity Detection Based on Optimized Measurement Matrix in mMTC

学校读者我要写书评

暂无评论

Improved Sparse Activity Detection Based on Optimized Measur...

IEEE Conference on Vehicular technology (VTC)

作者： Jianyu Wang Liu Yang Chaoyuan Bai Heng Liu Communication and Sensor Network for Modern Transportation International Cooperation Center(CSNMT) Southwest Jiaotong University Chengdu P.R.China Key Lab of Information Coding & Transmission Institude of Mobile Communication Southwest Jiaotong University Chengdu P.R.China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu P.R.China

ISBN: (数字)9798331517786

ISBN: (纸本)9798331517793

Device activity detection and channel estimation are central problems in massive Machine Type Communication (mMTC) scenarios. Given the sparse distribution of active devices, compressive sensing (CS) emerges as a viable solution at the gNB to mitigate interference stemming from non-orthogonal preamble sets. This paper proposes an algorithm for optimizing measurement matrix, thereby elevating the performance of signal recovery in CS. Within the proposed algorithm, a optimization model that integrates eigenvalue averaging and equiangular tight frame (ETF) theory is formulated, and an iterative algorithm is devised to approximate the optimal solution utilizing singular value decomposition (SVD). Further, a weight-based strategie is discussed with respect to the feasibility of the proposed algorithm, accompanied by the introduction of iteration termination condition. Experimental results corroborate the algorithm’s swift convergence, underpinning the efficient production of high-performance matrices that refine the accuracy of joint device activity detection and channel estimation.

关键词： Vehicular and wireless technologies Optimization models Channel estimation Approximation algorithms Eigenvalues and eigenfunctions Sparse matrices Matrix decomposition Optimization Convergence Singular value decomposition

Hands Activities Detection in Egocentric Interactions Using YOLOv5

学校读者我要写书评

暂无评论

Hands Activities Detection in Egocentric Interactions Using ...

UK/ China Emerging Technologies (UCET)

作者： Christyn Akosua Owusu-Agyei Jin Hou School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu Sichuan P.R. China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu Sichuan P.R. China School of Information Science and Technology Southwest Jiaotong University Chengdu Sichuan P.R. China

ISBN: (纸本)9781665495769

Hands emerge quite often in egocentric video, and their structure and disposition reveal a lot as to what individuals have been engaged and showing interest to. Earlier researches in hand detection, on the other hand, have depended on significant effect that only operate in limited situations, such as lab settings or with minimal social interaction. This work investigates the recently developed YOLO architectural for object recognition in egocentric video, which offers a good balance of precision and performance. We performed an experiment of assessments utilizing various different architecture configurations and training methods. Our experiment leads to all sorts of conclusions about the most cost - effective methodologies to our strategic objectives, and leads us to further research to enhance detection of smart glasses videos. We tested these approaches on an existing dataset that contains 48 first individual footage of people interacting in situations in real life as well as the bounding box on a pixel level for more than 15,000 hand gestures.

关键词： Training Costs data models Object recognition Smart glasses