检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Li, Zhixun Wang, Liang Sun, Xin Luo, Yifan Zhu, Yanqiao Chen, Dingshuo Luo, Yingtao Zhou, Xiangxin Liu, Qiang Wu, Shu Yu, Jeffrey Xu Department of Systems Engineering and Engineering Management The Chinese University of Hong Kong Hong Kong Center for Research on Intelligent Perception Computing State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China Department of Automation University of Science and Technology of China China School of Cyberspace Security Beijing University of Posts and Telecommunications China Department of Computer Science University of California Los Angeles United States Heinz College of Information Systems and Public Policy Machine Learning Department School of Computer Science Carnegie Mellon University United States

Graph Structure Learning (GSL) has recently garnered considerable attention due to its ability to optimize both the parameters of Graph Neural Networks (GNNs) and the computation graph structure simultaneously. Despite the proliferation of GSL methods developed in recent years, there is no standard experimental setting or fair comparison for performance evaluation, which creates a great obstacle to understanding the progress in this field. To fill this gap, we systematically analyze the performance of GSL in different scenarios and develop a comprehensive Graph Structure Learning Benchmark (GSLB) curated from 20 diverse graph datasets and 16 distinct GSL algorithms. Specifically, GSLB systematically investigates the characteristics of GSL in terms of three dimensions: effectiveness, robustness, and complexity. We comprehensively evaluate state-of-the-art GSL algorithms in node- and graph-level tasks, and analyze their performance in robust learning and model complexity. Further, to facilitate reproducible research, we have developed an easy-to-use library for training, evaluating, and visualizing different GSL methods. Empirical results of our extensive experiments demonstrate the ability of GSL and reveal its potential benefits on various downstream tasks, offering insights and opportunities for future research. The code of GSLB is available at: https://***/GSL-Benchmark/GSLB. © 2023, CC BY.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

S$^{\text{4}}$TP: Social-Suitable and Safety-Sensitive Trajectory Planning for Autonomous Vehicles

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on intelligent Vehicles 2023年第2期9卷 3220-3231页

作者： Xiao Wang Ke Tang Xingyuan Dai Jintao Xu Quancheng Du Rui Ai Yuxiao Wang Weihao Gu Engineering Research Center of Autonomous Unmanned System Technology Ministry of Education Anhui University Hefei China Haomo Technology Company Ltd. Beijing China State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Qingdao Academy of Intelligent Industries Qingdao China School of Computer and Communication Engineering University of Science and Technology Beijing Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China

In public roads, autonomous vehicles (AVs) face the challenge of frequent interactions with human-driven vehicles (HDVs), which render uncertain driving behavior due to varying social characteristics among humans. To effectively assess the risks prevailing in the vicinity of AVs in social interactive traffic scenarios and achieve safe autonomous driving, this article proposes a social-suitable and safety-sensitive trajectory planning (S $^{\text{4}}$ TP) framework. Specifically, S $^{\text{4}}$ TP integrates the Social-Aware Trajectory Prediction (SATP) and Social-Aware Driving Risk Field (SADRF) modules. SATP utilizes Transformers to effectively encode the driving scene and incorporates an AV's planned trajectory during the prediction decoding process. SADRF assesses the expected surrounding risk degrees during AVs-HDVs interactions, each with different social characteristics, visualized as two-dimensional heat maps centered on the AV. SADRF models the driving intentions of the surrounding HDVs and predicts trajectories based on the representation of vehicular interactions. S $^{\text{4}}$ TP employs an optimization-based approach for motion planning, utilizing the predicted HDVs' trajectories as input. With the integration of SADRF, S $^{\text{4}}$ TP executes real-time online optimization of the planned trajectory of AV within low-risk regions, thus improving the safety and the interpretability of the planned trajectory. We have conducted comprehensive tests of the proposed method using the SMARTS simulator. Experimental results in complex social scenarios, such as unprotected left-turn intersections, merging, cruising, and overtaking, validate the superiority of our proposed S $^{\text{4}}$ TP in terms of safety and rationality. S $^{\text{4}}$ TP achieves a pass rate of 100% across all scenarios, surpassing the current state-of-the-art methods Fanta of 98.25% and Predictive-Decision of 94.75%.

关键词： Trajectory Safety Vehicles Trajectory planning Autonomous vehicles Risk management Behavioral sciences

来源：评论

学校读者我要写书评

暂无评论

Lightdet: A Lightweight and Accurate Object Detection Network

Lightdet: A Lightweight and Accurate Object Detection Networ...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Qiankun Tang Jie Li Zhiping Shi Yu Hu Research Center for Intelligent Computing Systems State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing Advanced Innovation Center for Imaging Theory and Technology Capital Normal University

ISBN: (数字)9781509066315

ISBN: (纸本)9781509066322

The extensive computational burden limits the usage of accurate but complex object detectors in resource-bounded scenarios. In this paper, we present a lightweight object detector, named LightDet, to address this dilemma. We design a lightweight backbone that is able to capture rich low-level features by the proposed Detail-Preserving Module. To effectively aggregate bottom and top-down features, we introduce an efficient Feature-Preserving and Refinement Module. A lightweight prediction head is employed to further reduce the entire network complexity. Experimental results show that our LightDet achieves 75.5% mAP on PASCAL VOC 2007 at the speed of 250 FPS and 24.0% mAP on MS COCO dataset.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Graph Confidence Intercalibration Network for Intracranial Aneurysm Lesion Instance Segmentation in Dsa

SSRN

引用

SSRN 2024年

作者： Ye, Haili Mo, Yancheng Tang, Chen Liao, Mingqian Zhang, Xiaoqing Dai, Limeng Li, Baihua Liu, Jiang Research Institute of Trustworthy Autonomous Systems Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China Department of Computer Science Loughborough University LoughboroughLE11 3TU United Kingdom School of Ophthalmology and Optometry Eye Hospital Wenzhou Medical University Wenzhou325027 China Center for High Performance Computing and Shenzhen Key Laboratory of Intelligent Bioinformatics Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China Shenzhen People’s Hospital Neurosurgery Department Shenzhen518020 China China

Intracranial aneurysm (IA) lesion segmentation is significant for its treatment and prognosis. Although exiting deep network-based instance methods have good IA lesion segmentation results based on digital subtraction angiography (DSA) images, they still face great challenges with instance confidence bias and imprecise boundary segmentation, which may negatively affect IA diagnosis. To tackle these problems, this paper proposes a novel graph confidence intercalibration network (GCINet) to automatically segment IA lesions from DSA images. To be specific, we design a graph confidence intercalibration (GCI) module to mitigate instance confidence bias by dynamically adjusting their confidence distributions. At the same time, we propose an edge space perception (ESP) module to correct ambiguous segmentation boundaries. Extensive experiments on a clinical IA-DSA and a publicly available LiTS dataset demonstrate that our GCINet outperforms state-of-the-art methods. Additionally, visual analysis and ablation studies are provided to verify the effectiveness of each module in GCINet. © 2024, The Authors. All rights reserved.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Modeling and Random Search Optimization Method for the Polysilicon Cvd Reactor

SSRN

引用

SSRN 2022年

作者： Xi, Bangwen Xiong, Gang Shen, Zhen Tamir, Tariku Sinshaw He, Chang Song, Yonggang Liu, Xiong State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Chinese Academy of Sciences Beijing100190 China Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Chinese Academy of Sciences Dongguan523808 China Intelligent Manufacturing Center Qingdao Academy of Intelligent Industries Qingdao266109 China Xinte Energy Co. Ltd Urumqi830000 China

Polysilicon is mainly obtained by chemical vapor deposition(CVD) reaction, in which hydrogen gas and trichlorosilane(TCS) are fed into the CVD reactor to produce polysilicon. However, the feeding parameters are mainly adjusted in a step-by-step manner according to the actual deposition results, which is inefficient to optimize and prone to resource wastage. In this paper, based on the existing mechanistic model of the CVD reactor, we combine the history data with the specific parameters to construct a simulator. A random search algorithm is used to determine the optimal feeding parameters. With the simulator, the polysilicon productivity can be increased by 704 kg, and the power consumption reduced by 3.8 kWh/kg. © 2022, The Authors. All rights reserved.

关键词： Simulators

来源：评论

学校读者我要写书评

暂无评论

Decoding split-frequency representation for cross-scale tracking

引用

Neural Networks 2025年 189卷 107587页

作者： Yuanming Zhang Hao Sun State Key Laboratory of Robotics and Systems Harbin Institute of Technology Harbin 150001 China Research Institute of Intelligent Control and Systems Harbin Institute of Technology Harbin 150001 China Bio-Computing Research Center Harbin Institute of Technology Shenzhen Shenzhen 518055 China

Learning tailored target representations for tracking is a promising direction in visual object tracking. Most state-of-the-art methods utilize autoencoders to generate representations by reconstructing the target’s appearance. However, these reconstructions are often augmented to mimic scale jitter and alteration, neglecting physical scale observations such as those in aerial videos. This article addresses the challenge of representation learning for cross-scale tracking in generalized scenarios. Specifically, we incorporate target scale directly into the positional encoding, indicating scale through relative pixel density rather than the conventional metric of image resolution. This scale-aware encoding is then integrated into the proposed asymptotic hierarchy of decoders, designed to reconstruct representations by emphasizing the restoration of high- and low-frequency features at large and tiny scales. The reconstruction process is guided by supervised learning using split losses, enabling the generation of robust cross-scale representations for generic objects. Extensive experiments on six benchmarks — GOT-10k, LaSOT, TrackingNet, DTB70, UAV123, and TNL2K — validate the superior performance of our method. Additionally, our tracker achieves a remarkable speed of 123 frames per second on a Graphics Processing Unit, surpassing the previous best autoencoder-based tracker. The code and raw results will be made publicly available at: https://***/pellab/DSC .

关键词： Autoencoder Cross-correlation Representation learning Siamese network Visual object tracking

来源：评论

学校读者我要写书评

暂无评论

Consistency and Diversity induced Human Motion Segmentation

arXiv

引用

arXiv 2022年

作者： Zhou, Tao Fu, Huazhu Gong, Chen Shao, Ling Porikli, Fatih Ling, Haibin Shen, Jianbing The PCA Lab The Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China Institute of High Performance Computing Agency for Science Technology and Research Singapore Riyadh Saudi Arabia The Research School of Engineering The Australian National University Australia The Department of Computer Science Stony Brook University Strony Brook NY United States The State Key Laboratory of Internet of Things for Smart City Department of Computer and Information Science University United States

Subspace clustering is a classical technique that has been widely used for human motion segmentation and other related tasks. However, existing segmentation methods often cluster data without guidance from prior knowledge, resulting in unsatisfactory segmentation results. To this end, we propose a novel Consistency and Diversity induced human Motion Segmentation (CDMS) algorithm. Specifically, our model factorizes the source and target data into distinct multi-layer feature spaces, in which transfer subspace learning is conducted on different layers to capture multi-level information. A multi-mutual consistency learning strategy is carried out to reduce the domain gap between the source and target data. In this way, the domain-specific knowledge and domain-invariant properties can be explored simultaneously. Besides, a novel constraint based on the Hilbert Schmidt Independence Criterion (HSIC) is introduced to ensure the diversity of multi-level subspace representations, which enables the complementarity of multi-level representations to be explored to boost the transfer learning performance. Moreover, to preserve the temporal correlations, an enhanced graph regularizer is imposed on the learned representation coefficients and the multi-level representations of the source data. The proposed model can be efficiently solved using the Alternating Direction Method of Multipliers (ADMM) algorithm. Extensive experimental results on public human motion datasets demonstrate the effectiveness of our method against several state-of-the-art approaches. Copyright © 2022, The Authors. All rights reserved.

关键词： Motion analysis

来源：评论

学校读者我要写书评

暂无评论

Reconfigurable Distributed Antennas and Reflecting Surface: A New architecture for Wireless Communications

arXiv

引用

arXiv 2023年

作者： Ma, Chengzhi Yang, Xi Wang, Jintao Yang, Guanghua Zhang, Wei Ma, Shaodan The State Key Laboratory of Internet of Things for Smart City The Department of Electrical and Computer Engineering University of Macau China The Shanghai Key Laboratory of Multidimensional Information Processing School of Communication and Electronic Engineering East China Normal University Shanghai200241 China The School of Intelligent Systems Science and Engineering GBA and B&R International Joint Research Center for Smart Logistics Jinan University Zhuhai519070 China The School of Electrical Engineering & Telecommunications University of New South Wales Sydney Australia

Distributed Antenna systems (DASs) employ multiple antenna arrays in remote radio units to achieve highly directional transmission and provide great coverage performance for future-generation networks. However, the utilization of fully digital or hybrid active antenna arrays results in a significant increase in hardware costs and power consumption for DAS. To address these issues, integrating DAS with Reconfigurable intelligent Surfaces (RIS) offers a viable approach to ensure coverage and transmission performance while maintaining low hardware costs and power consumption. To incorporate the merits of RIS into the DAS from practical consideration, a novel architecture of "Reconfigurable Distributed Antennas and Reflecting Surfaces (RDARS)" is proposed in this paper. Specifically, based on the design of the additional direct-through state together with the existing high-quality fronthaul link, any element of the RDARS can be dynamically programmed to connect with the base station (BS) via fibers and perform the connected mode as remote distributed antennas of the BS to receive or transmit signals. Additionally, RDARS also inherits the low-cost and low-energy-consumption benefits of fully passive RISs by default configuring the elements as passive to perform the reflection mode. As a result, RDARS encompasses both DAS and RIS as special cases, offering flexible control over the trade-off between distribution gain and reflection gain to enhance performance. To unveil the potential of such architecture, the ergodic achievable rate under the RDARS architecture is analyzed and closed-form expression with meaningful insights is derived. The theoretical analysis proves that the RDARS can achieve a higher achievable rate than both DAS and fully passive RIS with the passive beamforming gain provided by elements acting reflection mode while combating the "multiplicative fading" suffered by RISs through the connected mode performed at the RDARS. Simulation results also demonstr

关键词： Reconfigurable architectures

来源：评论

学校读者我要写书评

暂无评论

RDARS Empowered Massive MIMO System: Two-Timescale Transceiver Design with Imperfect CSI

arXiv

引用

arXiv 2023年

作者： Ma, Chengzhi Wang, Jintao Yang, Xi Yang, Guanghua Zhang, Wei Ma, Shaodan State Key Laboratory of Internet of Things for Smart City the Department of Electrical and Computer Engineering University of Macau China Shanghai Key Laboratory of Multidimensional Information Processing School of Communication and Electronic Engineering East China Normal University Shanghai200241 China School of Intelligent Systems Science and Engineering and GBA B&R International Joint Research Center for Smart Logistics Jinan University Zhuhai519070 China School of Electrical Engineering & Telecommunications University of New South Wales Sydney Australia

In this paper, we investigate a novel reconfigurable distributed antennas and reflecting surface (RDARS) aided multi-user massive multiple-input multiple-output (MIMO) system with imperfect channel state information (CSI) and propose a practical two-timescale (TTS) transceiver design to reduce the communication overhead and computational complexity of the system. In the RDARS-aided system, not only distribution gain but also reflection gain can be obtained by a flexible combination of the distributed antennas and reflecting surface, which differentiates the system from the others and also makes the TTS design challenging. To enable the optimal TTS transceiver design, the achievable rate of the system is first derived in closed-form. The rate expression is general and covers that of the distributed antenna systems (DAS) and reconfigurable intelligent surface (RIS) aided systems as special cases. Then the TTS design aiming at the weighted sum rate maximization is considered. To solve the challenging non-convex optimization problem with high order design variables, i.e., the transmit powers and the phase shifts at the RDARS, a block coordinate descent based method is proposed to find the optimal solutions in semi-closed forms iteratively. Specifically, two efficient algorithms are proposed with provable convergence for the optimal phase shift design, i.e., Riemannian Gradient Ascent based algorithm by exploiting the unit-modulus constraints, and Two-Tier Majorization-Minimization based algorithm with closed-form optimal solutions in each iteration. Simulation results validate the effectiveness of the proposed algorithm and demonstrate the superiority of deploying RDARS in massive MIMO systems to provide substantial rate improvement with a significantly reduced total number of active antennas/RF chains and lower transmit power when compared to the DAS and RIS-aided systems. Copyright © 2023, The Authors. All rights reserved.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Enhanced Particle Swarm Optimization for Workflow Scheduling in Clouds

Enhanced Particle Swarm Optimization for Workflow Scheduling...

引用

Symposium of Image, Signal Processing, and Artificial Vision (STSIVA)

作者： Chang Lu Dayu Feng Jie Zhu Haiping Huang Nanjing University of Posts & Telecommunications Nanjing China Jiangsu Key Laboratory of Big Data Security & Intelligent Processing Nanjing China State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing China Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks Nanjing China

ISBN: (纸本)9781665426565

As a NP-hard problem, it is always baffling to figure out a scheduling strategy to arrange the interconnected tasks of a workflow on the infinite number of resources in the cloud environment so that the workflow can be addressed efficiently and robustly. This paper focuses on scheduling the workflow’s tasks on the cloud resources with less rental cost of resources while the whole schedule length (makespan) will not exceed the given deadline. As one of the most popular evolutionary algorithms, particle swarm optimization (PSO) has been successfully applied for the workflow scheduling problem. Inspired by the idea of multiple groups and the distributed parallel computing, we develop an enhanced PSO algorithm for the workflow scheduling problem in clouds. Besides, a pretreatment strategy is adopted to simplify the workflow’s structure. The experimental results demonstrate that our proposal has good performance on improving the algorithm’s searching ability and finding better solutions.

关键词： Schedules Costs Processor scheduling NP-hard problem Parallel processing Scheduling Proposals

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：