检索结果-内蒙古大学图书馆

MixGradient: A gradient-based re-weighting scheme with mixup for imbalanced data streams

NEURAL NETWORKS 2023年第1期161卷 525-534页

作者： Peng, Xinyu Wang, Fei-Yue Li, Li Tsinghua Univ Dept Automat Beijing 100084 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100080 Peoples R China Tsinghua Univ Natl Lab Informat Sci & Technol Beijing 100084 Peoples R China

A challenge for contemporary deep neural networks in real-world problems is learning from an imbalanced data stream, where data tends to be received chunk by chunk over time, and the prior class distribution is severely imbalanced. Although many sophisticated algorithms have been derived, most of them overlook the importance of gradient information. From this perspective, the difficulty of learning from imbalanced data streams lies in the fact that the gradient estimated on an uneven class distribution is not informative enough to reflect the critical pattern of each class. To this end, we propose to assign higher weights on the training samples whose gradients are close to the gradient of corresponding typical samples, thus highlighting the important samples in minority classes and suppressing the noisy samples in majority classes. Such an idea can be combined with Mixup, which exploits the interpolation information of data to further compensate for the information of sample space that the typical samples do not provide and expand the role of the proposed re -weighting scheme. Experiments on artificially induced long-tailed CIFAR data streams and long-tailed MiniPlaces data stream show that the resulting method, termed MixGradient, boosts the generalization performance of DNNs under different imbalance ratios and achieves up to 10% accuracy improvement.(c) 2023 Elsevier Ltd. All rights reserved.

关键词： Deep learning Imbalanced data streams Sample gradient Typical samples Mixup

来源：评论

学校读者我要写书评

暂无评论

Dynamic Rigid Bodies Mining and Motion Estimation Based on Monocular Camera

引用

IEEE TRANSACTIONS ON CYBERNETICS 2023年第9期53卷 5655-5666页

作者： Gao, Xuanchang Liu, Xilong Cao, Zhiqiang Tan, Min Yu, Junzhi 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 Peking Univ Coll Engn BIC ESAT Dept Adv Mfg & RobotState Key Lab Turbulence & C Beijing 100871 Peoples R China

Dynamic object perception is an important yet challenging direction in the field of robot navigation. Without any prior knowledge about motion and objects, a novel dynamic rigid bodies mining and motion estimation method based on monocular camera is proposed in this article. Different from the existing works based on sampling that associate feature points to motion hypotheses according to the reprojection errors, our work endeavors to find the intrinsic relevance among motion hypotheses. To represent this relevance, the concept of the probabilistic field on the Lie group Sim(3) manifold is introduced, which is established using random sampling. It provides a computable way for the regions on the manifold where rigid bodies possibly appear. The probability of a motion hypothesis falling on a region is expressed by its confidence. The regions with large confidences in the probabilistic field are selected as potential rigid bodies, whose corresponding feature points are further sampled for pose calculation. As a result, the randomness of sampling is reduced and the inliers for possible rigid bodies are enhanced, which guarantees the accuracy of motion estimation. On this basis, the tracking of rigid bodies is achieved. The proposed method distinguishes the feature points of dynamic objects with 3-D motion from those in the static background, thus enabling simultaneous localization and mapping (SLAM) to be initialized in dynamic environments. The experimental results on the KITTI, Hopkins 155, and MTPV62 datasets demonstrate the effectiveness. Comparison experiments indicate that our method outperforms the other methods in sensitivity of dynamic objects perception.

关键词： Dynamics Motion segmentation Cameras Manifolds Estimation Motion estimation Simultaneous localization and mapping Dynamic rigid bodies monocular camera motion estimation probabilistic field region confidence

来源：评论

学校读者我要写书评

暂无评论

Crowdsensing Intelligence: Advancing Trustworthy, Intelligent, Interactive, and Cooperative Sensing and Computing for Transportation 5.0

IEEE TRANSACTIONS ON INTELLIGENT VEHICLES

引用

IEEE TRANSACTIONS ON INTELLIGENT VEHICLES 2023年第8期8卷 3963-3967页

作者： Wang, Fei-Yue Chen, Bin Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Natl Univ Def Technol Coll Syst Engn Changsha 410073 Peoples R China

Dear All,

关键词： Transportation Simultaneous localization and mapping Object detection Laser radar Estimation Crowdsensing Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Towards Human-Machine Recognition Alignment: An Adversarilly Robust Multimodal Retrieval Hashing Framework

引用

IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL systems 2023年第5期10卷 2847-2859页

作者： Zhang, Xingwei Zheng, Xiaolong Liu, Bin Wang, Xiao Mao, Wenji Zeng, Daniel Dajun Wang, Fei-Yue Chinese Acad Sci State Key Lab Management & Control Complex Syst Inst Automat Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 101408 Peoples R China West Virginia Univ Dept Management Informat Syst Morgantown WV 26506 USA

The multimodality nature of web data has necessitated complex multimodal information retrieval for a wide range of web applications. Deep neural networks (DNNs) have been widely employed to extract semantic features from raw samples to improve retrieval accuracy. In addition, hashing is widely used to improve computational and storage efficiency. As such, deep hashing frameworks have been applied for multimodal retrieval tasks. However, there is still a great recognitive gap between primate brain structure-inspired DNNs and humans. On computer vision tasks, well-crafted DNN models can be easily defeated by invisible small attacks, and this phenomenon indicates a large recognition gap between DNN models and humans. Recently, adversarial defense methods have been shown to improve the human-machine recognition alignment in several classification tasks. However, the robustness problem on the retrieval tasks, especially on the deep hashing-based multimodal retrieval models, is still not well studied. Therefore, in this article, we present an adversarially robust training mechanism to improve model robustness for the purpose of human-machine recognition alignment on retrieval tasks. Through extensive experimental results on several social multimodal retrieval benchmarks, we show that the robust training hashing framework proposed can mitigate the recognition gap on retrieval tasks. Our study highlights the necessity of robustness enhancement on deep hashing models.

关键词： Training Task analysis Semantics Perturbation methods Feature extraction Computational modeling Robustness Adversarial perturbation adversarially robust training deep hashing multimodal retrieval

来源：评论

学校读者我要写书评

暂无评论

Analyzing the Stock Volatility Spillovers in Chinese Financial and Economic Sectors

引用

IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL systems 2023年第1期10卷 269-284页

作者： Li, Jingyu Cheng, Lu Zheng, Xiaolong Wang, Fei-Yue Beijing Univ Technol Sch Econ & Management Beijing 100124 Peoples R China 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 100190 Peoples R China

By regarding the Chinese financial and economic sectors as a system, this article studies the stock volatility spillover in the system and explores its effects on the overall performance of the macroeconomy in China. The recent outbreak of COVID-19, U.S.-China trade friction, and three historical financial turbulences are involved to distinguish the changes in the spillover in these distinct crises, which has seldom been unveiled in the literature. By considering that the stock volatility spillover may vary over distinct timescales, the spillovers are disclosed through innovatively constructing the multi-scale spillover networks, followed by connectedness computation, based on variational mode decomposition (VMD) and generalized vector autoregression (GVAR) process. Our empirical analysis first demonstrates the different levels of increases in the total sectoral volatility spillover and changes in the roles of the sectors in the system under the aforementioned crises. Besides, the increases in the sectoral spillover in the long-term are verified to negatively impact the macroeconomy and can thereby act as warning signals.

关键词： COVID-19 financial and economic system network analysis stock volatility spillover variational mode decomposition (VMD)

来源：评论

学校读者我要写书评

暂无评论

Crowd Evacuation With Multi-Modal Cooperative Guidance in Subway Stations: Computational Experiments and Optimization

引用

IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL systems 2023年第5期10卷 2536-2545页

作者： Zhou, Min Dong, Hairong Ioannou, Petros A. Wang, Fei-Yue Beijing Jiaotong Univ State Key Lab Rail Traff Control & Safety Beijing 100044 Peoples R China Univ Southern Calif Dept Elect Engn Los Angeles CA 90089 USA Univ Southern Calif Ctr Adv Transportat Technol Los Angeles CA 90089 USA Chinese Acad Sci CASIA State Key Lab Management & Control Complex Syst S Inst Automat Beijing 100190 Peoples R China

Setting up guidance equipment and leaders is widely used as an effective measure to improve the operation and evacuation efficiency of subway stations for the safety of passengers. Cooperation among different kinds of guidance modals can benefit the passenger evacuation process and reduce the operating and management costs as well as the risk of injury to people in subway stations. This article proposes a framework of multimodal cooperative guidance (MMCG) systems for commanding the crowd evacuation in case of emergency, where three types of guidance modes are considered. The bi-level MMCG optimization models are constructed to determine the optimal quantities and initial locations of multimodal guidance. The MMCG schemes are designed by minimizing cost functions taking into account the constraints of the number of guidance, valid coverage, and guiding expectation. An extended social force (SF) model is proposed to study crowd evacuation dynamics with multimodal guidance. The computational experiments are conducted to evaluate the performance of the proposed cooperative guidance schemes at the subway platform scenario. Three unimodal guidance schemes and a contrasted scheme without guidance are also proposed as comparison schemes. The results show that the crowd evacuation efficiency and the utilization ratio of exits are improved by taking into account the cooperation among different guidance modals.

关键词： Public transportation Computational modeling Behavioral sciences Force Broadcasting Rails Rail transportation Computational experiment crowd evacuation efficiency multimodal cooperative guidance (MMCG) safety social force (SF) model subway station

来源：评论

学校读者我要写书评

暂无评论

Implementation of Autonomous Docking and Charging for a Supporting Robotic Fish

引用

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS 2023年第7期70卷 7023-7031页

作者： Dong, Huijie Wu, Zhengxing Wang, Jian Chen, Di Tan, Min Yu, Junzhi Taiyuan Univ Technol Key Lab Adv Transducers & Intelligent Control Sys Minist Educ Taiyuan 030024 Peoples R China 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 Peking Univ Coll Engn Dept Adv Mfg & Robot State Key Lab Turbulence & Complex Syst Beijing 100871 Peoples R China Guangdong Ocean Univ Coll Elect & Informat Engn Zhanjiang 524088 Peoples R China

Underwater energy supplements for autonom- ous underwater vehicles (AUVs) are significant for ocean exploitation owing to energy storage and data communication limitations. Aiming at the energy supplement for bionic robotic fish, an autonomous recharging-oriented docking approach is proposed in this article. First, an omnidirectional docking system containing a supporting robotic fish capable of visual recognition and wireless charging and a docking platform is presented. Next, five locomotive modes are designed and analyzed based on the hybrid swimming and gliding patterns for the robot fish. Utilizing the five modes, a docking procedure is planned, and an onboard-visual-based autonomous docking control strategy is presented. Aquatic experiments, including docking with the platform and refloating a small robot, are performed to verify the effectiveness of the proposed approach. The obtained results offer valuable insights into the development of autonomous docking of bionic robots, laying a solid foundation for the permanent operation of various underwater devices and robots.

关键词： Robots Visualization Tail Shape Batteries Cameras Buoyancy Autonomous docking gliding robotic fish motion control underwater energy supplementation underwater robotics

来源：评论

学校读者我要写书评

暂无评论

Event-Triggered Near-Optimal control of Discrete-Time Constrained Nonlinear systems With Application to a Boiler-Turbine System

引用

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS 2022年第6期18卷 3926-3935页

作者： Wei, Qinglai Lu, Jingwei Zhou, Tianmin Cheng, Xiang Wang, Fei-Yue Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100049 Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 100049 Peoples R China Macau Univ Sci & Technol Inst Syst Engn Macau 999078 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

This article presents a novel event-triggered near-optimal control (ETNOC) method for discrete-time (DT) constrained nonlinear systems. First, the tracking error system is constructed to convert the tracking control problem to the regulation problem. By introducing the tracking error system, the asymmetric control constraints design for the original constrained system can be converted to the symmetric control constraints design for the tracking error system. Second, a novel triggering condition is developed using the time-triggered optimal value function and control law. It is proven that the closed-loop system (CLS) is asymptotically stable under the developed ETNOC method, and there exists a predetermined upper bound for the real performance index. Then, to implement the developed ETNOC method, a parallel control approach with neural networks (NNs) and adaptive dynamic programming techniques is proposed to predict the next state of the system and obtain the optimal value function and control law. The stability analysis of the CLS is provided in the consideration of the estimation errors of the NN weights and state. Finally, the effectiveness of the developed ETNOC method is validated by an application to a boiler-turbine system.

关键词： Optimal control Nonlinear systems Informatics control systems Performance analysis Mathematical models Upper bound Adaptive dynamic programming (ADP) boiler-turbine system (BTS) control constraints event-triggered nonlinear optimal control parallel control

来源：评论

学校读者我要写书评

暂无评论

A Novel Iterative Adaptive Critic Design for Smart Home Energy systems with Solar Energy

A Novel Iterative Adaptive Critic Design for Smart Home Ener...

引用

2022 Chinese Automation Congress, CAC 2022

作者： Liao, Zehua Wei, Qinglai Li, Hongyang University of Chinese Academy of Sciences The State Key Laboratory of Management and Control for Complex Systems School of Artificial Intelligence Beijing China

ISBN: (纸本)9781665465335

As a distributed energy storage system, smart home energy (SHE) system can be used to reduce the consumption cost of household users. Aiming at the optimal control SHE systems, a novel multi-iteration adaptive dynamic programming (MIADP) method is constructed. The present algorithm introduces three iterations, namely, exterior iteration, local iteration and interior iteration, to ensure that the iterative Q-function converges to the optimal, and thus the optimal energy storage control scheme of the SHE system with solar energy is obtained. Finally, the present MIADP algorithm is illustrated by the experimental results. © 2022 IEEE.

关键词： Solar energy

来源：评论

学校读者我要写书评

暂无评论

Consistent Matrix: A Feature Selection Framework for Large-Scale Datasets

引用

IEEE TRANSACTIONS ON FUZZY systems 2023年第11期31卷 4024-4038页

作者： Yang, Tian Li, Yuan-Jiang Qian, Yuhua Wang, Fei-Yue Hunan Normal Univ Hunan Prov Key Lab Intelligent Comp & Language Inf Changsha 410081 Peoples R China Shanxi Univ Inst Big Data Sci & Ind Taiyuan 030006 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100080 Peoples R China

Large-scale data processing based on limited computing resources has always been a difficult problem in data mining, where feature selection is often used as an effective data compressing mechanism. For granular computing of Big Data, discernibility matrix and dependency degree are the most representative methods for matrix-based and feature-importance-degree-based feature selection, respectively. However, their temporal and space complexities are high and often lead to poor performance. In this article, a novel feature selection framework for large-scale data processing with linear complexities was proposed for the first time. First, a much more concise fuzzy granule set, called fuzzy arithmetic covering, was introduced to reduce computational costs. Then, a new matrix-based feature selection framework, namely consistent matrix, was proposed for general rough set models. As a result, a heuristic attribute reduction algorithm, i.e., HARCM, was designed accordingly. Compared with six state-of-the-art algorithms for feature selection, the average running time of the newly proposed algorithm was reduced up to 2913 times, with a comparable or even better classification performance.

关键词： Consistent matrix feature selection fuzzy arithmetic covering fuzzy rough sets granular computing

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：