检索结果-内蒙古大学图书馆

Spatiotemporal Feature Enhancement Network for Blur Robust Underwater Object Detection

IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL systemS 2024年第5期16卷 1814-1828页

作者： Zhou, Hao Qi, Lu Huang, Hai Yang, Xu Yang, Jing Harbin Engn Univ Natl Key Lab Sci & Technol Underwater Vehicle Harbin 150000 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100080 Peoples R China Univ Calif Merced Merced CA 95344 USA Nanjing Univ Informat Sci & Technol Sch Artificial Intelligence Nanjing 210044 Peoples R China

Underwater object detection is challenged by the presence of image blur induced by light absorption and scattering, resulting in substantial performance degradation. It is hypothesized that the attenuation of light is directly correlated with the camera-to-object distance, manifesting as variable degrees of image blur across different regions within underwater images. Specifically, regions in close proximity to the camera exhibit less pronounced blur compared to distant regions. Within the same object category, objects situated in clear regions share similar feature embeddings with their counterparts in blurred regions. This observation underscores the potential for leveraging objects in clear regions to aid in the detection of objects within blurred areas, a critical requirement for autonomous agents, such as autonomous underwater vehicles, engaged in continuous underwater object detection. Motivated by this insight, we introduce the spatiotemporal feature enhancement network (STFEN), a novel framework engineered to autonomously extract discriminative features from objects in clear regions. These features are then harnessed to enhance the representations of objects in blurred regions, operating across both spatial and temporal dimensions. Notably, the proposed STFEN seamlessly integrates into two-stage detectors, such as the faster region-based convolutional neural networks (Faster R-CNN) and feature pyramid networks (FPN). Extensive experimentation conducted on two benchmark underwater datasets, URPC 2018 and URPC 2019, conclusively demonstrates the efficacy of the STFEN framework. It delivers substantial enhancements in performance relative to baseline methods, yielding improvements in the mAP evaluation metric ranging from 3.7% to 5.0%.

关键词： Feature extraction Object detection Detectors Proposals Visualization Image color analysis Cameras Blur robust detection feature enhancement spatiotemporal network

来源：评论

学校读者我要写书评

暂无评论

Deep Deterministic Policy Gradient for High-Speed Train Trajectory Optimization

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION systemS 2022年第8期23卷 11562-11574页

作者： Ning, Lingbin Zhou, Min Hou, Zhuopu Goverde, Rob M. P. Wang, Fei-Yue Dong, Hairong Beijing Jiaotong Univ State Key Lab Rail Traff Control & Safety Beijing 100044 Peoples R China Delft Univ Technol Dept Transport & Planning NL-2628 CN Delft Netherlands Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

This paper proposes a novel train trajectory optimization approach for high-speed railways. We restrict our attention to single train operation scenarios with different scheduled/rescheduled running times aiming at generating optimal train recommended trajectories in real time, which can ensure punctuality and energy efficiency of train operation. A learning-based approach deep deterministic policy gradient (DDPG) is designed to generate optimal train trajectories based on the offline training from the interaction between the agent and the trajectory simulation environment. An allocating running time and selecting operation modes (ARTSOM) algorithm is proposed to improve train punctuality and give a series of discrete operation modes (full traction, cruising, coasting, full braking), and thus to produce a feasible training set for DDPG, which can speed up the training process. Numerical experiments show that an optimized speed profile can be generated by DDPG within seconds on a realistic railway line. In addition, the results demonstrate the generalization ability of trained DDPG in solving TTO problems with different running times and line conditions.

关键词： Rail transportation Training Heuristic algorithms Resistance Optimal control Trajectory optimization Switches High-speed railway train trajectory optimization deep deterministic policy gradient energy efficiency

来源：评论

学校读者我要写书评

暂无评论

UNMAS: Multiagent Reinforcement Learning for Unshaped Cooperative Scenarios

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING systemS 2023年第4期34卷 2093-2104页

作者： Chai, Jiajun Li, Weifan Zhu, Yuanheng Zhao, Dongbin Ma, Zhe Sun, Kewu Ding, Jishiyu Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 100049 Peoples R China Second Acad CASIS X Lab Beijing 100854 Peoples R China

Multiagent reinforcement learning methods, such as VDN, QMIX, and QTRAN, that adopt centralized training with decentralized execution (CTDE) framework have shown promising results in cooperation and competition. However, in some multiagent scenarios, the number of agents and the size of the action set actually vary over time. We call these unshaped scenarios, and the methods mentioned above fail in performing satisfyingly. In this article, we propose a new method, called Unshaped Networks for Multiagent systems (UNMAS), which adapts to the number and size changes in multiagent systems. We propose the self-weighting mixing network to factorize the joint action-value. Its adaption to the change in agent number is attributed to the nonlinear mapping from each-agent Q value to the joint action-value with individual weights. Besides, in order to address the change in an action set, each agent constructs an individual action-value network that is composed of two streams to evaluate the constant environment-oriented subset and the varying unit-oriented subset. We evaluate UNMAS on various StarCraft II micromanagement scenarios and compare the results with several state-of-the-art MARL algorithms. The superiority of UNMAS is demonstrated by its highest winning rates especially on the most difficult scenario 3s5z_vs_3s6z. The agents learn to perform effectively cooperative behaviors, while other MARL algorithms fail. Animated demonstrations and source code are provided in https://***/view/unmas.

关键词： Multi-agent systems Training Task analysis Reinforcement learning Sun Learning systems Semantics Centralized training with decentralized execution (CTDE) multiagent reinforcement learning StarCraft II

来源：评论

学校读者我要写书评

暂无评论

Parallel Philosophy for MetaOrganizations With MetaOperations: From Leibniz's Monad to HanoiDAO

引用

IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL systemS 2022年第3期9卷 658-666页

作者： WANG, FEI-YUE DING, W. E. N. W. E. N. QIN, R. U. I. HU, B. I. N. Chinese Acad Sci State Key Lab Management & Control Complex Syst Inst Automat Beijing Peoples R China Macau Univ Sci & Technol Fac Innovat Engn Taipa 999078 Macao Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Beijing Inst Technol Sch Med Technol Beijing 100081 Peoples R China

Welcome to the third issue of IEEE Transactions on Computational Social systems (TCSS) of 2022. According to the latest update of CiteScoreTracker from Elsevier Scopus released on April 6, 2022, the CitesSore of IEEE ...

关键词：

来源：评论

学校读者我要写书评

暂无评论

Digital twins and artificial intelligence in transportation infrastructure: Classification, application, and future research directions

引用

COMPUTERS & ELECTRICAL ENGINEERING 2022年 101卷

作者： Wu, Jingyi Wang, Xiao Dang, Yukun Lv, Zhihan Qingdao Univ Coll Comp Sci & Technol 308 Ningxia Rd Qingdao 266071 Peoples R China State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

Artificial Intelligence (AI) technology is extensively applied in all walks of life with continuous acceleration of the construction of smart cities. The current research status of intelligent development of transportation infrastructure is classified and predicted oriented to smart cities, which is mainly based on space type, function type, and facility use. The classification is mainly between residents and vehicles, between and vehicles, and between vehicles and transportation systems. The related scholars analyzed that Digital Twins (DTs) technology and AI technology show significant advantages in the classification of transportation infrastructure and the management of transportation spatial information network. The intelligent development of transportation infrastructure is analyzed, and it is predicted in functional design, intelligent development, and effective integration with new media, aiming to provide a reference for the subsequent intelligent development and construction of transportation infrastructure in smart cities.

关键词： Transport infrastructure Artificial intelligence Digital twins Damage detection Traffic spatial information network

来源：评论

学校读者我要写书评

暂无评论

A Novel GSP Auction Mechanism for Dynamic Confirmation Games on Bitcoin Transactions

引用

IEEE TRANSACTIONS ON SERVICES COMPUTING 2022年第3期15卷 1436-1447页

作者： Li, Juanjuan Ni, Xiaochun Yuan, Yong Wang, Fei-Yue Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Qingdao Acad Intelligent Ind Qingdao 266109 Peoples R China

Bitcoin is gaining ground in recent years. In the Bitcoin system, miners provide computing power to confirm transactions in pursuit of transaction fees, while users compete by bidding transaction fees for faster confirmation. This process is in essence analogous to online ad auctions, where advertisers bid for more prominent ad slots. Therefore, inspired by ad auction research, we propose to apply the Generalized Second Price (GSP) auction mechanism in the dynamic confirmation game on Bitcoin transactions. Our model is targeted to deal with the problems caused by instability and low efficiency in the currently-adopted Generalized First Price (GFP) auction model in Bitcoin confirmation games. Besides, we use the "rank-by-cost" rule to replace the "rank-by-fee" rule, where each transaction's cost is calculated by the user-submitted fee and the waiting time. Aiming to probe users' equilibrium strategy, we first discuss the GSP game with complete information under synchronous submissions, and show that it has the Locally Envy-Free equilibrium. Then, we study the GSP game with incomplete information under asynchronous submissions, and define two types of strategies, i.e., the Farsighted Balanced (FB) strategy and the Instant Balanced (IB) strategy. The FB strategy is in line with users' practical needs of determining fees so as to maximize the long-term payoffs;however it cannot generate a stable equilibrium. Alternatively, the IB strategy focuses on the instant payoff maximization, and if all users follow the IB strategy, their equilibrium fees can finally converge to a stable profile. Finally, we design computational experiments to validate our theoretical models and analysis. Our research findings indicate that this novel GSP mechanism is superior to the currently adopted GFP mechanism. Besides, the convergence of the GSP game under the IB strategy has also been illustrated by the computational experiments.

关键词： Bitcoin Games Pipelines Computational modeling Nickel Analytical models Blockchain bitcoin transaction confirmation game generalized second price mechanism transaction fee

来源：评论

学校读者我要写书评

暂无评论

A Vectorized Representation Model for Trajectory Prediction of Intelligent Vehicles in Challenging Scenarios

IEEE TRANSACTIONS ON INTELLIGENT VEHICLES

引用

IEEE TRANSACTIONS ON INTELLIGENT VEHICLES 2023年第10期8卷 4301-4306页

作者： Guo, Lulu Shan, Ce Shi, Tengfei Li, Xuan Wang, Fei-Yue Tongji Univ Dept Control Sci & Engn Shanghai 201804 Peoples R China Beihang Univ Sch Comp Sci & Engn Beijing 100083 Peoples R China Peng Cheng Lab Shenzhen 518000 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

Trajectory prediction for challenging scenarios has always been a significant problem in the field due to the complexity of dynamic scenarios and interactions. Furthermore, there is often a dynamic gap between evaluating and validating methods on fixed datasets and real driving scenarios. This letter forms part of a series of reports emanating from the IEEE Transactions on Intelligent Vehicles's Decentralized and Hybrid Workshops (DHW) dedicated to the field of Scenarios Engineering. Our research proposes a scenario engineering-based calibration and validation framework for trajectory prediction of autonomous vehicles to more effectively validate the performance of the method in challenging scenarios. First, Scenarios Engineering (SE) uses OpenSCENARIO and real dataset to generate high-definition maps for challenging driving scenarios. Then, the vectorization approach is employed to extract contextual details from the scene and agent trajectory information from the HD map, and the graph neural network is used to model the high-order interaction to realize the interactive trajectory prediction. Compared with the traditional method, the trajectory prediction can be calibrated through SE so that the prediction process can use more traffic information and attribute characteristics, and improve the evaluation index of prediction. The DHW discusses a practical case to verify the potential of the trajectory prediction framework based on scenarios generation in improving the authenticity and accuracy of trajectory prediction.

关键词： Index Terms-Autonomous vehicles graph neural network HD maps OpenSCENARIO scenarios engineering trajectory prediction

来源：评论

学校读者我要写书评

暂无评论

A Vagueness Adaptive Efficiency Evaluation Method of Science and Technology Resources Opening and Sharing Platforms Based on FAHP and BP Neural Network

引用

IEEE TRANSACTIONS ON ENGINEERING management 2024年 71卷 2049-2062页

作者： Zhang, Hui Feng, Xin Wei, Yigang Li, Zonggan Beihang Univ Sch Comp Sci & Engn State Key Lab Software Dev Environm Beijing 100190 Peoples R China Chinese Acad Sci State Key Lab Management & Control Complex Syst Inst Automat Beijing 100190 Peoples R China Beihang Univ Sch Comp Sci & Engn Beijing 100191 Peoples R China Beihang Univ Sch Econ & Management Beijing 100191 Peoples R China Beihang Univ Lab Low Carbon Intelligent Governance Beijing 100191 Peoples R China Beihang Univ Beijing Key Lab Emergency Support Simulat Technol Beijing 100191 Peoples R China

With the vigorous development of big data and information technology, promoting science and technology resources opening and sharing (STROS) has become a promising strategy to develop national innovation capacity. China has established various STROS platforms (STROSP) at the national and regional levels to encourage resources and knowledge sharing. However, STROSP efficiency evaluation is challenged in a vague environment, in which subjective and imprecise information in acquiring evaluation preferences of decision makers is a key obstacle. To solve these problems, an innovative model for STROSP efficiency evaluation is developed. An indicator assessment system explicitly considers the key evaluation aspects, namely, service quantity, service quality, and service effect. This article combines fuzzy analytic hierarchy process (FAHP) and backpropagation (BP) neural network algorithm into an integrated model to quantify the efficiency of STROS. Prior knowledge of experts was fully utilized by FAHP. The neural network algorithm enabled the intelligent extraction and rapid inference of sample data features. The proposed model maximizes fuzzy mathematics in solving fuzzy and nonquantifiable problems and utilizes the advantages of the BP neural network on nonlinear mapping. The accuracy and reliability of the model are validated by a case study of six national STROSP in China. Estimation results demonstrate that the model is a powerful method for the real-time evaluation of STROS efficiency evaluation.

关键词： Backpropagation (BP) neural network China efficiency evaluation fuzzy analytic hierarchy process (FAHP) science and technology resources opening and sharing vague environment

来源：评论

学校读者我要写书评

暂无评论

Knowledge-Embedded Mutual Guidance for Visual Reasoning

引用

IEEE TRANSACTIONS ON CYBERNETICS 2024年第4期54卷 2579-2591页

作者： Zheng, Wenbo Yan, Lan Chen, Long Li, Qiang Wang, Fei-Yue Wuhan Univ Technol Sch Comp Sci & Artificial Intelligence Wuhan 430070 Peoples R China Wuhan Univ Technol Sanya Sci & Educ Innovat Pk Sanya 572000 Peoples R China Hunan Univ Coll Comp Sci & Engn Changsha 410082 Peoples R China Natl Supercomp Ctr Changsha Changsha 410082 Hunan Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100864 Peoples R China Waytous Inc Beijing 100864 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

Visual reasoning between visual images and natural language is a long-standing challenge in computer vision. Most of the methods aim to look for answers to questions only on the basis of the analysis of the offered questions and images. Other approaches treat knowledge graphs as flattened tables to search for the answer. However, there are two major problems with these works: 1) the model disregards the fact that the world we surrounding us interlinks our hearing and speaking of natural language and 2) the model largely ignores the structure of the KG. To overcome these challenging deficiencies, a model should jointly consider two modalities of vision and language, as well as the rich structural and logical information embedded in knowledge graphs. To this end, we propose a general joint representation learning framework for visual reasoning, namely, knowledge-embedded mutual guidance. It realizes mutual guidance not only between visual data and natural language descriptions but also between knowledge graphs and reasoning models. In addition, it exploits the knowledge derived from the reasoning model to boost knowledge graphs when applying the visual relation detection task. The experimental results demonstrate that the proposed approach performs dramatically better than state-of-the-art methods on two benchmarks for visual reasoning.

关键词： Attention model joint learning knowledge embedding visual reasoning

来源：评论

学校读者我要写书评

暂无评论

Supervised learning for parameterized Koopmans-Beckmann's graph matching

引用

PATTERN RECOGNITION LETTERS 2021年 143卷 8-13页

作者： Zeng, Shaofeng Liu, Zhiyong Yang, Xu Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing Peoples R China

In this paper, we discuss a novel graph matching problem, namely the parameterized Koopmans- Beckmann's graph matching (KBGMw). KBGMw is defined by a weighted linear combination of a series of Koopmans-Beckmann's graph matching. First, we show that KBGMw can be taken as a special case of the parameterized Lawler's graph matching, subject to certain conditions. Second, based on structured SVM, we propose a supervised learning method for automatically estimating the parameters of KBGMw. Experimental results on both synthetic and real image matching data sets show that the proposed method achieves relatively better performances, even superior to some deep learning methods. (c) 2020 Elsevier B.V. All rights reserved.

关键词： Graph matching Koopmans-Beckmann Supervised learning Structured SVM

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：