检索结果-内蒙古大学图书馆

Travel Time Delay Model of Mixed Traffic Flow Considering Different Dedicated Lane Management Policies for Cavs

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Ren, Tingting Yao, Zhihong Jiang, Yangsheng School of Transportation and Logistics National Engineering Laboratory of Integrated Transportation Big Data Application Technology National United Engineering Laboratory of Integrated and Intelligent Transportation Southwest Jiaotong University Sichuan Chengdu611756 China

To investigate the impact of dedicated lane management policies for connected automated vehicles (CAVs) on travel time delay, this paper proposes a general framework of the travel time delay model considering different dedicated lane management policies for CAVs. First, the car-following modes and their proportions in CAVs dedicated lanes and normal lanes with different dedicated lane management policies are analyzed, and the average time headways are further derived. Second, the travel time delay model with sufficiently high demand and low/medium demand is derived based on the point queue (P-Q) model, respectively. Then, the relevant properties of the travel time delay model with different dedicated lane management policies for CAVs are proposed and proved. Finally, multiple parameters, such as traffic saturation, the penetration rate of CAVs, and the arrival rate of vehicles, are adopted to discuss their impact on the optimal split ratio, traffic capacity, average reduced delay, optimal CAVs penetration rate interval, optimal CAVs penetration rate, and optimal lane management policy. Results show that (1) when the traffic saturation is less than or equal to 1, the optimal split ratio is always 0;when the traffic saturation is greater than 1, the optimal split ratio remains 0 first and then increases with the CAVs penetration rate;(2) the average reduced delay of (C, M) and (C, H) policies is always 0 when the traffic saturation is less than or equal to 1, and the average delay of (C, M) and (C, H) policies is minimum 0.63 times that of the mixed traffic flow without CAVs dedicated lanes;(3) the optimal CAVs penetration rate to reduce the average delay most for both (C, M) and (C, H) policies first increases to and then remains unchanged with the increase of traffic saturation. In particular, the optimal CAVs penetration rate for (C, M) and (C, H) policies is always 0.53 when the traffic saturation is more than or equal to 1.79 and 2.24, respectively;(4) only when

关键词： Time delay

Co-Occurrence Matters: Learning Action Relation for Temporal Action Localization

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Cao, Congqi Wang, Yizhe Lu, Yue Zhang, Xin Zhang, Yanning The National Engineering Laboratory for Integrated AeroSpace-Ground-Ocean Big Data Application Technology School of Computer Science Northwestern Polytechnical University Xi’an710129 China

Temporal action localization (TAL) is a prevailing task due to its great application potential. Existing works in this field mainly suffer from two weaknesses: (1) They often neglect the multi-label case and only focus on temporal modeling. (2) They ignore the semantic information in class labels and only use the visual information. To solve these problems, we propose a novel Co-Occurrence Relation Module (CORM) that explicitly models the co-occurrence relationship between actions. Besides the visual information, it further utilizes the semantic embeddings of class labels to model the co-occurrence relationship. The CORM works in a plug-and-play manner and can be easily incorporated with the existing sequence models. By considering both visual and semantic co-occurrence, our method achieves high multi-label relationship modeling capacity. Meanwhile, existing datasets in TAL always focus on low-semantic atomic actions. Thus we construct a challenging multi-label dataset UCF-Crime-TAL that focuses on high-semantic actions by annotating the UCF-Crime dataset at frame level and considering the semantic overlap of different events. Extensive experiments on two commonly used TAL datasets, i.e., MultiTHUMOS and TSU, and our newly proposed UCF-Crime-TAL demenstrate the effectiveness of the proposed CORM, which achieves state-of-the-art performance on these datasets. Copyright © 2023, The Authors. All rights reserved.

关键词： Crime

Unsupervised video summarization with a convolutional attentive adversarial network

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Liang, Guoqiang Lv, Yanbing Li, Shucheng Zhang, Shizhou Zhang, Yanning National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science Northwestern Polytechnical University Xi'an China

With the explosive growth of video data, video summarization, which attempts to seek the minimum subset of frames while still conveying the main story, has become one of the hottest topics. Nowadays, substantial achievements have been made by supervised learning techniques, especially after the emergence of deep learning. However, it is extremely expensive and difficult to collect human annotation for large-scale video datasets. To address this problem, we propose a convolutional attentive adversarial network (CAAN), whose key idea is to build a deep summarizer in an unsupervised way. Upon the generative adversarial network, our overall framework consists of a generator and a discriminator. The former predicts importance scores for all frames of a video while the latter tries to distinguish the score-weighted frame features from original frame features. Specifically, the generator employs a fully convolutional sequence network to extract global representation of a video, and an attention-based network to output normalized importance scores. To learn the parameters, our objective function is composed of three loss functions, which can guide the frame-level importance score prediction collaboratively. To validate this proposed method, we have conducted extensive experiments on two public benchmarks SumMe and TVSum. The results show the superiority of our proposed method against other state-of-the-art unsupervised approaches. Our method even outperforms some published supervised approaches. Copyright © 2021, The Authors. All rights reserved.

关键词： Generative adversarial networks

Dynamic Textual Prompt For Rehearsal-free Lifelong Person Re-identification

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Chen, Hongyu Jiao, Bingliang Wang, Wenxuan Wang, Peng Zhang, Yanning The National Engineering Laboratory for Integrated AeroSpace-Ground-Ocean Big Data Application Technology School of Computer Science Northwestern Polytechnical University Xi’an710060 China

Lifelong person re-identification attempts to recognize people across cameras and integrate new knowledge from continuous data streams. Key challenges involve addressing catastrophic forgetting caused by parameter updating and domain shift, and maintaining performance in seen and unseen domains. Many previous works rely on data memories to retain prior samples. However, the amount of retained data increases linearly with the number of training domains, leading to continually increasing memory consumption. Additionally, these methods may suffer significant performance degradation when data preservation is prohibited due to privacy concerns. To address these limitations, we propose using textual descriptions as guidance to encourage the ReID model to learn cross-domain invariant features without retaining samples. The key insight is that natural language can describe pedestrian instances with an invariant style, suggesting a shared textual space for any pedestrian images. By leveraging this shared textual space as an anchor, we can prompt the ReID model to embed images from various domains into a unified semantic space, thereby alleviating catastrophic forgetting caused by domain shifts. To achieve this, we introduce a task-driven dynamic textual prompt framework in this paper. This model features a dynamic prompt fusion module, which adaptively constructs and fuses two different textual prompts as anchors. This effectively guides the ReID model to embed images into a unified semantic space. Additionally, we design a text-visual feature alignment module to learn a more precise mapping between fine-grained visual and textual features. We also developed a learnable knowledge distillation module that allows our model to dynamically balance retaining existing knowledge with acquiring new knowledge. Extensive experiments demonstrate that our method remarkably outperforms SOTAs under various settings. Our model even outperforms rehearsal-based state-of-the-art approaches by

关键词： Semantics

Identifying Flight Trajectory Patterns via a Density-Aided Hierarchical Clustering Algorithm 5th

学校读者我要写书评

暂无评论

Identifying Flight Trajectory Patterns via a Density-Aided H...

5th China Aviation Science and technology Conference, 2021

作者： Zhang, Zhuxi Chen, Yichong Fang, Jing Zhou, Xueyang An, Yuhang Zhu, Xi National Engineering Laboratory for Comprehensive Transportation Big Data Application Technology Beihang University Beijing100191 China Unit 32751 Beijing China School of Electronics and Information Engineering Beihang University Beijing100191 China Aviation Data Communication Corporation Beijing100191 China School of Computer Science and Engineering Beihang University Beijing100191 China Research Institute for Frontier Science Beihang University Beijing100191 China

ISBN: (纸本)9789811674228

Identifying flight trajectory patterns is a vital task that helps controllers better understand the flight operation mechanism, so as to effectively recognize flight anomalies and manage traffic flow, etc. However, flight operation is sensitively affected by the weather and instant airspace regulation, making the flight trajectory pattern too intertwined to be easily distinguished. In this work, we propose a trajectory pattern identification method based on a density-aided hierarchical clustering algorithm. This method employs a weighted trajectory clustering mechanism to keep the minor trajectory patterns from being improperly "swallowed" by other large trajectory patterns. Experimental results show that the proposed method can explicitly distinguish different trajectory patterns and achieve more accurate results than existing approaches. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Clustering algorithms

APADGCN: Adaptive Partial Attention Diffusion Graph Convolutional Network for Traffic Flow Forecasting 4th

学校读者我要写书评

暂无评论

APADGCN: Adaptive Partial Attention Diffusion Graph Convolut...

4th International Conference on Spatial data and Intelligence, SpatialDI 2023

作者： Zhang, Bowen Li, Bohan Wei, Jinzhan Wen, Hao College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing211106 China Key Laboratory of Safety-Critical Software Ministry of Industry and Information Technology Beijing China National Engineering Laboratory for Integrated Aero-Space-Ground Ocean Big Data Application Technology Xi’an China School of Electronic Information and Automation Guilin University of Aerospace Technology Guilin541010 China College of Aerospace Engineering Nanjing University of Aeronautics and Astronautics Nanjing211106 China

ISBN: (纸本)9783031329098

Traffic flow forecasting is a core task of urban governance and plays a vital role in the development of ITS. Because of the complexity and uncertainty of traffic patterns, it is of great challenge to capture spatial-temporal correlations. Recent researches mainly focus on the pre-defined adjacency matrix based on prior knowledge as the basis of spatial-temporal correlation modeling, but the fixed graph structure cannot adequately describe the dependency between traffic sensors. To tackle this issue, a novel deep learning model framework is proposed in this paper: Adaptive Partial Attention Diffusion Graph Convolutional Network(APADGCN), which consists of three main parts: 1) the Multi-Component module that divides the historical traffic flow into recent, daily-periodic, and weekly-periodic, to capture the traffic patterns of different periodic;2) the spatial correlation modeling which can dynamically capture node relationships and model spatial dependency, and enhance the aggregation ability of low-order information;3) the temporal correlation modeling which models long-term time dependencies using convolution and gating. The final result is obtained by the weighted fusion of the results of the multi-components. We compared our APADGCN with various baseline models in the four real datasets from the Caltrans Performance Measurement System (PeMS). The experimental results show that the prediction accuracy of APADGCN is better than that of the baseline models. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Convolution

QCluster: Clustering Packets for Flow Scheduling

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Yang, Tong Wang, Hao Li, Jizhou Jiang, Jie Zhao, Yikai Zhang, Yinda Yang, Kaicheng Zhang, Nicholas School of Computer Science National Engineering Laboratory for Big Data Analysis Technology and Application Peking University China Peng Cheng Laboratory Shenzhen China Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong Huawei Theory Lab China

Flow scheduling is crucial in data centers, as it directly influences user experience of applications. According to different assumptions and design goals, there are four typical flow scheduling problems/solutions: SRPT, LAS, Fair Queueing, and Deadline-Aware scheduling. When implementing these solutions in commodity switches with limited number of queues, they need to set static parameters by measuring traffic in advance, while optimal parameters vary across time and space. This paper proposes a generic framework, namely QCluster, to adapt all scheduling problems for limited number of queues. The key idea of QCluster is to cluster packets with similar weights/properties into the same queue. QCluster is implemented in Tofino switches, and can cluster packets at a speed of 3.2 Tbps. To the best of our knowledge, QCluster is the fastest clustering algorithm. Experimental results in testbed with programmable switches and ns-2 show that QCluster reduces the average flow completion time (FCT) for short flows up to 56.6%, and reduces the overall average FCT up to 21.7% over state-of-the-art. All the source code in ns-2 is available in Github [45]. Copyright © 2020, The Authors. All rights reserved.

关键词： Queueing theory

Car Collision Warning System for Cornering on Mountain Roads 4th

学校读者我要写书评

暂无评论

Car Collision Warning System for Cornering on Mountain Roads

4th Euro-China Conference on Intelligent data analysis and applications, ECC 2017

作者： Meng, S.H. Hu, S.B. Huang, A.C. Huang, T.J. Jia, J.J. Huang, Xuhong School of Information Science and Engineering Fujian University of Technology FuzhouFujian350118 China Key Laboratory of Big Data Mining and Application School of Information Science and Engineering Fujian University of Technology Minhou FuzhouFujian350118 China Institute of Electro-Optical Science and Engineering National Cheng Kung University Tainan70101 Taiwan Department of Electrical Engineering National Sun Yat-Sen University Kaohsiung Taiwan Kaohsiung Municipal ChungShan Senior High School Kaohsiung Taiwan

ISBN: (纸本)9783319685267

This study proposes an ultrasound-based collision avoidance/warning safety system for vehicles cornering on mountain roads. The design includes a hardware and a software system. The hardware system consists of a single-chip microcontroller with a minimum system board, a power module, and an automotive radar system. The radar system includes a stc98c52 control module, LCD 1602 display module, and hc-sr04 ultrasonic detection module. The software was programmed using C on the Keil uVision4 platform. © 2018, Springer International Publishing AG.

关键词： Liquid crystal displays

A new runoff calculation model based on multi-source radar remote sensing technology 6

学校读者我要写书评

暂无评论

A new runoff calculation model based on multi-source radar r...

6th Asia-Pacific Conference on Synthetic Aperture Radar, APSAR 2019

作者： Zhao, Jianhui Wang, Ning Wu, Lin Min, Lin College of Computer and Information Engineering Henan University Kaifeng475004 China College of Environment and Planning Henan University Kaifeng475004 China Network Information Center Office Henan University Kaifeng475004 China Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng475004 China Henan Engineering Research Center of Intelligent Technology and Application Kaifeng475004 China

ISBN: (纸本)9781728129129

River runoff changing will directly affect the safety of the surrounding areas. In theory, river runoff can be calculated from water depth, river width and flow velocity. But in the actual monitoring, the observation of water depth, river width and flow velocity is complex. Radar remote sensing can observe target all-time and all-weather, and has the ability to penetrate clouds, rain and fog. The common Radar remote sensing runoff calculation model is depth-runoff relationship model, which is constructed by fitting water depth and in-situ runoff. The river depth is derived from Radar Altimetry (RA) data. But this model has only one input parameter, the accuracy of this model inverted runoff is not high. In view of the above problems, this paper proposed the Multi-source Radar Remote Sensing Runoff Calculation Model (MRRS-RCM). Firstly, river width and relative water depth were derived from Synthetic Aperture Radar (SAR) images and RA data. Secondly, based on the Manning's equation, the flow velocity were described from river width and relative water depth. Thirdly, river width relative water depth, and in-situ runoff were fitted to construct MRRS-RCM. Experiments show the accuracy of MRRS-RCM estimated runoff is better than depth-runoff relationship model, the RRMSE values of MRRS-RCM reach 13%. © 2019 IEEE.

关键词： Synthetic aperture radar