检索结果-内蒙古大学图书馆

Pay Less But Get More: A Dual-Attention-based Channel Estimation Network for Massive MIMO systems with Low-Density Pilots

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhou, Binggui Yang, Xi Ma, Shaodan Gao, Feifei Yang, Guanghua The School of Intelligent Systems Science and Engineering Jinan University Zhuhai519070 China The State Key Laboratory of Internet of Things for Smart City The Department of Electrical and Computer Engineering University of Macau 999078 China The Shanghai Key Laboratory of Multidimensional Information Processing School of Communication and Electronic Engineering East China Normal University Shanghai200241 China Department of Automation Tsinghua University Beijing100084 China The School of Intelligent Systems Science and Engineering The GBA and B&R International Joint Research Center for Smart Logistics Jinan University Zhuhai519070 China

To reap the promising benefits of massive multiple-input multiple-output (MIMO) systems, accurate channel state information (CSI) is required through channel estimation. However, due to the complicated wireless propagation environment and large-scale antenna arrays, precise channel estimation for massive MIMO systems is significantly challenging and costs an enormous training overhead. Considerable time-frequency resources are consumed to acquire sufficient accuracy of CSI, which thus severely degrades systems’ spectral and energy efficiencies. In this paper, we propose a dual-attention-based channel estimation network (DACEN) to realize accurate channel estimation via low-density pilots, by jointly learning the spatial-temporal domain features of massive MIMO channels with the temporal attention module and the spatial attention module. To further improve the estimation accuracy, we propose a parameter-instance transfer learning approach to transfer the channel knowledge learned from the high-density pilots pre-acquired during the training dataset collection period. Experimental results reveal that the proposed DACEN-based method achieves better channel estimation performance than the existing methods under various pilot-density settings and signal-to-noise ratios. Additionally, with the proposed parameter-instance transfer learning approach, the DACEN-based method achieves additional performance gain, thereby further demonstrating the effectiveness and superiority of the proposed method. Copyright © 2023, The Authors. All rights reserved.

关键词： Channel estimation

Path Planning of Mobile Robot Based on an Improved Genetic Algorithm

学校读者我要写书评

暂无评论

Path Planning of Mobile Robot Based on an Improved Genetic A...

Digital Twins and Parallel Intelligence (DTPI), IEEE International Conference on

作者： Zenghua Chen Gang Xiong Sheng Liu Zhen Shen Yue Li State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Chinese Academy of Sciences Dongguan China School of Automobile Chang'an University Xi'an China

ISBN: (数字)9781665492270

ISBN: (纸本)9781665492287

In order to solve the problem of premature convergence of the basic genetic algorithm when planning the robot running path, the basic genetic algorithm is improved and optimized. Different population initialization methods are used to initialize multiple populations randomly, so as to improve the diversity of populations; Improve the adaptive strategy and elite strategy of crossover and mutation operators to improve the convergence speed of the algorithm; Add the path tortuosity as the planning index in the fitness function to make the planned path smoother, and add constraints to the model to avoid obstacles; Finally, through the transformation of the coding paradigm of the above improved genetic algorithm, it can run on Flink distributed cluster to obtain faster solution speed, so as to meet the efficiency requirements of path planning in large-scale robot cluster system. The optimized algorithm is compared with the basic genetic algorithm. The simulation results show that the improved algorithm is efficient in robot path planning.

关键词： Sociology Clustering algorithms Path planning Planning Trajectory Statistics Collision avoidance

ChartKG: A Knowledge-Graph-Based Representation for Chart Images

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhou, Zhiguang Wang, Haoxuan Zhao, Zhengqing Zheng, Fengling Wang, Yongheng Chen, Wei Wang, Yong School of Media and Design Hangzhou Dianzi University CO Hangzhou310018 China School of Media and Design Hangzhou Dianzi University China Big Data Visualization and Human Computer Collaborative Intelligent Laboratory Hangzhou Dianzi University China Research Center of Big Data Intelligence Zhejiang Lab Hangzhou China State Key Lab of CAD&CG Zhejiang University China College of Computing and Data Science Nanyang Technological University Singapore

Chart images, such as bar charts, pie charts, and line charts, are explosively produced due to the wide usage of data visualizations. Accordingly, knowledge mining from chart images is becoming increasingly important, which can benefit downstream tasks like chart retrieval and knowledge graph completion. However, existing methods for chart knowledge mining mainly focus on converting chart images into raw data and often ignore their visual encodings and semantic meanings, which can result in information loss for many downstream tasks. In this paper, we propose ChartKG, a novel knowledge graph (KG) based representation for chart images, which can model the visual elements in a chart image and semantic relations among them including visual encodings and visual insights in a unified ***, we develop a general framework to convert chart images to the proposed KG-based representation. It integrates a series of image processing techniques to identify visual elements and relations, e.g., CNNs to classify charts, yolov5 and optical character recognition to parse charts, and rule-based methods to construct graphs. We present four cases to illustrate how our knowledge-graph-based representation can model the detailed visual elements and semantic relations in charts, and further demonstrate how our approach can benefit downstream applications such as semantic-aware chart retrieval and chart question answering. We also conduct quantitative evaluations to assess the two fundamental building blocks of our chart-to-KG framework, i.e., object recognition and optical character recognition. The results provide support for the usefulness and effectiveness of ChartKG. © 2024, CC BY.

关键词： Knowledge graph

Segment Anything Model is a Good Teacher for Local Feature Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wu, Jingqian Xu, Rongtao Wood-Doughty, Zach Wang, Changwei Xu, Shibiao Lam, Edmund Y. The University of Hong Kong Pokfulam Hong Kong The State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100190 China Northwestern University EvanstonIL60201 United States The Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center National Supercomputer Center in Jinan Qilu University of Technology Shandong Academy of Sciences Jinan250013 China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China The School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing100876 China

Local feature detection and description play an important role in many computer vision tasks, which are designed to detect and describe keypoints in any scene and any downstream task. Data-driven local feature learning methods need to rely on pixel-level correspondence for training. However, a vast number of existing approaches ignored the semantic information on which humans rely to describe image pixels. In addition, it is not feasible to enhance generic scene keypoints detection and description simply by using traditional common semantic segmentation models because they can only recognize a limited number of coarse-grained object classes. In this paper, we propose SAMFeat to introduce SAM (segment anything model), a foundation model trained on 11 million images, as a teacher to guide local feature learning. SAMFeat learns additional semantic information brought by SAM and thus is inspired by higher performance even with limited training samples. To do so, first, we construct an auxiliary task of Attention-weighted Semantic Relation Distillation (ASRD), which adaptively distillates feature relations with category-agnostic semantic information learned by the SAM encoder into a local feature learning network, to improve local feature description using semantic discrimination. Second, we develop a technique called Weakly Supervised Contrastive Learning Based on Semantic Grouping (WSC), which utilizes semantic groupings derived from SAM as weakly supervised signals, to optimize the metric space of local descriptors. Third, we design an Edge Attention Guidance (EAG) to further improve the accuracy of local feature detection and description by prompting the network to pay more attention to the edge region guided by SAM. SAMFeat’s performance on various tasks such as image matching on HPatches, and long-term visual localization on Aachen Day-Night showcases its superiority over previous local features. The release code is available at https://***/vignywang/SAMFeat

关键词： computer vision

HARQ-IR Aided Short Packet Communications: BLER Analysis and Throughput Maximization

学校读者我要写书评

暂无评论

arXiv 2023年

作者： He, Fuchao Shi, Zheng Yang, Guanghua Li, Xiaofan Ye, Xinrong Ma, Shaodan the School of Intelligent Systems Science and Engineering and GBA B&R International Joint Research Center for Smart Logistics Jinan University Zhuhai519070 China the School of Physics and Electronic Information Anhui Normal University Wuhu241002 China the State Key Laboratory of Internet of Things for Smart City the Department of Electrical and Computer Engineering University of Macau China

This paper introduces hybrid automatic repeat request with incremental redundancy (HARQ-IR) to boost the reliability of short packet communications. The finite blocklength information theory and correlated decoding events tremendously preclude the analysis of average block error rate (BLER). Fortunately, the recursive form of average BLER motivates us to calculate its value through the trapezoidal approximation and Gauss–Laguerre quadrature. Moreover, the asymptotic analysis is performed to derive a simple expression for the average BLER at high signal-to-noise ratio (SNR). Then, we study the maximization of long term average throughput (LTAT) via power allocation meanwhile ensuring the power and the BLER constraints. For tractability, the asymptotic BLER is employed to solve the problem through geometric programming (GP). However, the GP-based solution underestimates the LTAT at low SNR due to a large approximation error in this case. Alternatively, we also develop a deep reinforcement learning (DRL)based framework to learn power allocation policy. In particular, the optimization problem is transformed into a constrained Markov decision process, which is solved by integrating deep deterministic policy gradient (DDPG) with subgradient method. The numerical results finally demonstrate that the DRL-based method outperforms the GP-based one at low SNR, albeit at the cost of increasing computational burden. Copyright © 2023, The Authors. All rights reserved.

关键词： Reinforcement learning

Adaptive Optimal Electrical Resistance Tomography for Large-Area Tactile Sensing

学校读者我要写书评

暂无评论

Adaptive Optimal Electrical Resistance Tomography for Large-...

IEEE International Conference on Robotics and Automation (ICRA)

作者： Wendong Zheng Huaping Liu Di Guo Wuqiang Yang Department of Computer Science and Technology Tsinghua University Beijing China the State Key Laboratory of Intelligent Technology and Systems Beijing National Research Center for Information Science and Technology Tsinghua University Beijing China School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing China Department of Electrical and Electronic Engineering The University of Manchester Manchester U.K.

It is critical to perceive physical contact for intelligent robots to safely interact in dynamic, unstructured environments. As physical contacts can occur at any location, a well-performing tactile sensing system should be able to deploy a large area on robotic surface. Some researchers have implemented large-area tactile sensors by using sensing arrays, but it is challenging to deploy many sensing elements. Electrical resistance tomography (ERT) has recently been introduced into tactile sensing to overcome some of the limitations with conventional tactile sensing arrays, and good results have been achieved for some robotic applications. However, a particular challenge is that spatial resolution is low. Although various attempts have been made to improve the performance of ERT-based tactile sensors, the intrinsic resolution issue remains unsolved. In this paper, we propose a novel adaptive optimal drive strategy for efficient ERT-based large-area tactile sensing for robotic applications, which can adaptively select the current injection and voltage measurement pattern for optimal tactile stimulus. In particular, regions of tactile contacts are preliminarily detected and localized by a base scanning pattern with only a few measurement data. According to this detected region, the adaptive strategy can select the optimal current injection and voltage measurement pattern to improve the sensing performance by maximizing the current density. To verify the effectiveness of the proposed strategy, the proposed method is comprehensively evaluated by simulation and experiments. The results revealed that the optimal strategy can effectively improve both spatial and temporal resolution.

关键词：

Exploring Spatial-Temporal Multi-Frequency Analysis for High-Fidelity and Temporal-Consistency Video Prediction

学校读者我要写书评

暂无评论

Exploring Spatial-Temporal Multi-Frequency Analysis for High...

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Beibei Jin Yu Hu Qiankun Tang Jingyu Niu Zhiping Shi Yinhe Han Xiaowei Li Research Center for Intelligent Computing Systems State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences Capital Normal University

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

Video prediction is a pixel-wise dense prediction task to infer future frames based on past frames. Missing appearance details and motion blur are still two major problems for current models, leading to image distortion and temporal inconsistency. We point out the necessity of exploring multi-frequency analysis to deal with the two problems. Inspired by the frequency band decomposition characteristic of Human Vision System (HVS), we propose a video prediction network based on multi-level wavelet analysis to uniformly deal with spatial and temporal information. Specifically, multi-level spatial discrete wavelet transform decomposes each video frame into anisotropic sub-bands with multiple frequencies, helping to enrich structural information and reserve fine details. On the other hand, multilevel temporal discrete wavelet transform which operates on time axis decomposes the frame sequence into sub-band groups of different frequencies to accurately capture multifrequency motions under a fixed frame rate. Extensive experiments on diverse datasets demonstrate that our model shows significant improvements on fidelity and temporal consistency over the state-of-the-art works. Source code and videos are available at https://***/Bei-Jin/STMFANet.

关键词： Discrete wavelet transforms Predictive models Wavelet analysis Streaming media Time-frequency analysis

Exploring spatial-temporal multi-frequency analysis for high-fidelity and temporal-consistency video prediction

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Jin, Beibei Hu, Yu Tang, Qiankun Niu, Jingyu Shi, Zhiping Han, Yinhe Li, Xiaowei Research Center for Intelligent Computing Systems State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences Capital Normal University

Video prediction is a pixel-wise dense prediction task to infer future frames based on past frames. Missing appearance details and motion blur are still two major problems for current predictive models, which lead to image distortion and temporal inconsistency. In this paper, we point out the necessity of exploring multi-frequency analysis to deal with the two problems. Inspired by the frequency band decomposition characteristic of Human Vision System (HVS), we propose a video prediction network based on multi-level wavelet analysis to deal with spatial and temporal information in a unified manner. Specifically, multi-level spatial discrete wavelet transform decomposes each video frame into anisotropic sub-bands with multiple frequencies, helping to enrich structural information and reserve fine details. On the other hand, multi-level temporal discrete wavelet transform which operates on time axis decomposes the frame sequence into sub-band groups of different frequencies to accurately capture multi-frequency motions under fixed frame rate. Extensive experiments on diverse datasets demonstrate that our model shows significant improvements on fidelity and temporal consistency over the state-of-the-art works. Copyright © 2020, The Authors. All rights reserved.

关键词： Discrete wavelet transforms

architecture and key Technologies of Parallel Dispatching System for Railway Technical Operation Stations

学校读者我要写书评

暂无评论

Architecture and Key Technologies of Parallel Dispatching Sy...

Complex systems and intelligent Science (CSIS-IAC), International Annual Conference on

作者： Gang Xiong Donghu Yang Wei Xu Runmei Li Shichao Chen Bing Song Xisong Dong Fenghua Zhu State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China Signal and Communication Research Institute China Academy of Railway Science Corporation Limited Beijing China The School of Electronic and Information Engineering Beijing Jiaotong University Beijing China Beijing Huairou Academy of Parallel Sensing Beijing China Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Chinese Academy of Sciences Dongguan China

A railroad technical operation station is an extensive and complex operation system and a variety of random disturbing factors further increase the complexity of its command and dispatching. To enhance the railroad technical operation stations' intelligence, and integration level, and enhance its dispatching management ability of complex operation plans, based on the ACP approach, this paper designs the parallel dispatching system (PDS) architecture, and describes its key technologies including the artificial dispatching system (ADS), computing experiments, parallel execution, etc. On the basis of the artificial dispatching system, computational experiments can optimize various types of technical operations and the overall operational process, to achieve parallel execution between the actual dispatching system and ADS. PDS can provide more efficient and intelligent command and dispatching solutions for railroad technical work stations, and promote the development of the railroad transportation industry in the direction of higher quality and efficiency.

关键词：