检索结果-内蒙古大学图书馆

IET International Radar Conference 2020, IET IRC 2020

作者： Dong, Henan Zheng, Cheng Tian, Weiming Radar Research Lab School of Information and Electronics Beijing Institute of Technology Beijing100081 China Beijing Key Laboratory of Embedded Real-Time Information Processing Technology Beijing100081 China

ISBN: (纸本)9781839535635

in view of the central processing unit (CPU) platform processing performance limits on computationally intensive tasks, as well as the FPGA + DSP[1-3] platform of software and hardware of high coupling and difficult defects, using the graphics processor (GPU) powerful parallel computing power, the CPU and GPU pipeline technology, heterogeneous systems with multithreading, GPU more and more flow, such as strategy, puts forward the real-time signal processing system of the multiple perspectives analysis methods, make full use of the independence between modules and signal processing algorithm concurrency features within the *** experimental results show that, compared with the traditional MATLAB platform, the maximum acceleration ratio based on CPU-GPU heterogeneous platform can reach more than 20000, and the parallel architecture designed can fully meet the real-time requirements of radar signal processing. © 2020 Institution of Engineering and technology. All rights reserved.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Research on Enhanced Perception and Attention-Driven Person Re-Identification

Research on Enhanced Perception and Attention-Driven Person ...

引用

International Conference on Fuzzy Systems and Knowledge Discovery (FSKD)

作者： Cancan Wu Dong Li Zhi Zhang College of Computer Science and Technology Wuhan University of Science and Technology Wuhan Hubei China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan Hubei China Big Data Science and Engineering Research Institute Wuhan University of Science and Technology Wuhan Hubei China

ISBN: (数字)9798350356328

ISBN: (纸本)9798350356335

When matching similarity among pedestrians in images, pedestrian re-identification algorithms are often disturbed by occlusions. A typical tactic is to improve the robustness of occlusion features in the model. However, this approach neglects the noise introduced by other pedestrians in the image, leading to limited learning of relevant information between images. To address these issues, this paper introduces a pedestrian re-identification model that leverages perception-enhanced and attention mechanisms. By enhancing the perception of non-pedestrian noise and erasing non-pedestrian features, we then employ a cross-attention mechanism to subtly embed global and local features for finer feature recognition. Finally, through context attention, we learn the interaction between pedestrian images to improve re-identification accuracy. Results from studies performed on the Market-1501, CUHK03-D, and Duke-ReID datasets indicate that the suggested model surpasses leading contemporary models regarding Rank-1 scores and mean Average Precision (mAP), while maintaining good robustness.

关键词： Pedestrians Accuracy Attention mechanisms Computational modeling Noise Knowledge discovery Robustness Noise measurement Identification of persons Fuzzy systems

来源：评论

学校读者我要写书评

暂无评论

Unknown Task Selection and Worker Recruitment Using Two-Stage Multi-Armed Bandit in Crowdsensing

引用

IEEE Internet of Things Journal 2025年

作者： Song, Haoyuan Li, Peng Du, Rui Yu, Hai Huang, Weiyi Nie, Lei Bao, Haizhou Liu, Qin Wuhan University of Science and Technology School of Computer Science and Technology Wuhan430065 China Wuhan University of Science and Technology Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan430065 China Hubei Polytechnic University School of Computer Huangshi435003 China Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Changchun130012 China Wuhan University School of Cyber Science and Engineering Wuhan430072 China

Mobile Crowdsensing (MCS) faces significant challenges in selecting tasks with expected high revenue and recruiting workers with expected high qualities to maximize overall utility. Existing approaches often assume the revenue of posting tasks or the quality of workers is determined, which limits their practical applicability. This paper tackles these challenges by modeling the long-term multi-task, multi-worker selection problem as a Two-Stage Multi-Armed Bandit (TS-MAB) problem under uncertainty. In each round, the MCS platform selects a long-term task from a pool and recruits the necessary workers, determining payments accordingly. We model the task selection phase as a MAB problem, and the worker recruitment phase, influenced by the task selection, as a Combinatorial MAB (CMAB) problem. We propose an extended Upper Confidence Bound (UCB)-based strategy and develop an incentive mechanism based on Auction theory, combined with TS-MAB (i.e., ATS-MAB), for unknown task selection and worker recruitment. Our mechanism theoretically guarantees truthfulness and individual rationality, with a theoretical analysis of its regret bounds. Furthermore, we introduce an adaptive incentive mechanism called AATS-MAB, which improves worker recruitment and quality updates, achieving higher total sensing quality and lower regret. Extensive simulations demonstrate the effectiveness and scalability of the proposed methods. © 2014 IEEE.

关键词： Personnel selection

来源：评论

学校读者我要写书评

暂无评论

Spatio-Temporal Transformer-Based Reinforcement Learning for Robot Crowd Navigation

Spatio-Temporal Transformer-Based Reinforcement Learning for...

引用

IEEE International Conference on Robotics and Biomimetics

作者： Haodong He Hao Fu Qiang Wang Shuai Zhou Wei Liu Yang Chen School of Computer Science and Technology Wuhan University of Science and Technology Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System Wuhan China Engineering Research Center for Metallurgical Automation and Measurement Technology of Ministry of Education Wuhan China

Ensuring robots can move safely and adhere to social norms in dynamic human environments is a crucial step towards robot autonomous decision-making. In existing work, double serial separate modules are generally used to capture spatial and temporal interactions, respectively. However, such methods lead to extra difficulties in improving the utilization of spatio-temporal features and reducing the conservatism of navigation policy. In light of this, this paper proposes a spatiotemporal transformer-based policy optimization algorithm to more effectively preserve the human-robot interactions. Specifically, a gated embedding mechanism is introduced to effectively fuses the spatial and temporal representations by integrating both modalities at the feature level. Then Transformer is leveraged to encode the spatio-temporal semantic information, with the hope of finding the optimal navigation policy. Finally, a combination of spatio-temporal Transformer and self-adjusting policy entropy significantly reduce the conservatism of navigation policies. Experimental results demonstrate the priority of the proposed algorithm over the state-of-the-art methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Accurate slant range model in ground-based radar imaging of the lunar 5

Accurate slant range model in ground-based radar imaging of ...

引用

IET International Radar Conference 2020, IET IRC 2020

作者： Liu, Siyuan Ding, Zegang Li, Gen Beijing Key Laboratory of Embedded Real-Time Information Processing Technology Beijing Institute of Technology Beijing100081 China The Beijing Institute of Technology Chongqing Innovation Center Chongqing China

ISBN: (纸本)9781839535635

Ground-based radar imaging is an important approach for lunar observation. However, due to the long round-trip time delay and long integration time, the invalidation of "stop-and-go" hypothesis presents challenge to the radar imaging algorithms. In this paper, firstly, the accurate ephemeris of large-scale lunar surface is created based on the coordinate transformations. Secondly, considering the error of "stop-and-go" hypothesis, the accurate slant range model between the ground-based radar and lunar surface is presented. Finally, the simulation results are presented to verify the correctness of the ephemeris calculation, and demonstrate the slant range difference caused by the "stop-and-go" hypothesis. © 2020 Institution of Engineering and technology. All rights reserved.

关键词： Radar imaging

来源：评论

学校读者我要写书评

暂无评论

A Bilayer Segmentation-Recombination Network for Accurate Segmentation of Overlapping C. elegans

arXiv

引用

arXiv 2024年

作者： Ding, Mengqian Liu, Jun Luo, Yang Tang, Jinshan Wuhan University of Science and Technology Wuhan430081 China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan China AI in Medicine Lab College of Public Health George Mason University FairfaxVA22312 United States

Caenorhabditis elegans (C. elegans) is an excellent model organism because of its short lifespan and high degree of homology with human genes, and it has been widely used in a variety of human health and disease models. However, the segmentation of C. elegans remains challenging due to the following reasons: 1) the activity trajectory of C. elegans is uncontrollable, and multiple nematodes often overlap, resulting in blurred boundaries of C. elegans. This makes it impossible to clearly study the life trajectory of a certain nematode;and 2) in the microscope images of overlapping C. elegans, the translucent tissues at the edges obscure each other, leading to inaccurate boundary segmentation. To solve these problems, a Bilayer Segmentation-Recombination Network (BR-Net) for the segmentation of C. elegans instances is proposed. The network consists of three parts: A Coarse Mask Segmentation Module (CMSM), a Bilayer Segmentation Module (BSM), and a Semantic Consistency Recombination Module (SCRM). The CMSM is used to extract the coarse mask, and we introduce a Unified Attention Module (UAM) in CMSM to make CMSM better aware of nematode instances. The Bilayer Segmentation Module (BSM) segments the aggregated C. elegans into overlapping and non-overlapping regions. This is followed by integration by the SCRM, where semantic consistency regularization is introduced to segment nematode instances more accurately. Finally, the effectiveness of the method is verified on the C. elegans dataset. The experimental results show that BR-Net exhibits good competitiveness and outperforms other recently proposed instance segmentation methods in processing C. elegans occlusion images. Copyright © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Drug-Target Interactions Prediction with Feature Extraction Strategy Based on Graph Neural Network 17th

Drug-Target Interactions Prediction with Feature Extraction ...

引用

17th International Conference on Intelligent Computing, ICIC 2021

作者： Li, Aoxing Lin, Xiaoli Xu, Minqi Yu, Haiping Hubei Key Laboratory of Intelligent Information Processing and Real-Time Industrial System School of Computer Science and Technology Wuhan University of Science and Technology Wuhan430065 China School of Computer Huanggang Normal University Huanggang438000 China

ISBN: (纸本)9783030845315

The binding of drug compounds with their targets affects the physiological functions and metabolic effects of the body, as well as the pharmacological effects leading to phenotypic effects. Studying drug-target interactions can facilitate the evaluation or identification of new targets for existing drugs. In order to better extract drug-target features and further improve the progress of model prediction, this paper investigates and analyzes a variety of graphical neural network models to predict drug-target interaction. In these models, compounds are represented as two-dimensional molecular graphs and SMILES sequences are algorithmically encoded as graph structures, which can better learn the characteristics of compound molecules. Three feature extraction strategies are experimented on the basis of two loss functions. The experimental results show that GROAN has the best results with binary cross-entropy. Compared to other methods, GROAN-based prediction model achieves better results on the benchmark dataset. © 2021, Springer Nature Switzerland AG.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Design and implementation of intelligent question and answer electronic dictionary in the context of big data

Design and implementation of intelligent question and answer...

引用

Communications technology and Computer Science (ACCTCS), Asia-Pacific Conference on

作者： Rui Qiao Xiaolei Zhong School of Computer Science and Technology Wuhan University of Science and Technology Wuhan China Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System Wuhan University of Science and Technology Wuhan China Yunnan University Dianchi College Kunming China

In the current era of the Internet, social life is inseparable from data, and people also live in a network. For people, network technology and smartphones are like swimming fish without water. The swimming fish, a pond obviously cannot meet the demand, people need the sea, and the development of science and technology is as broad as the sea and has unlimited future development space [1]-[4]. The Android system is the main part of the mobile smart phone system. For this, I have developed an English-Chinese electronic dictionary app based on android. It realizes the functions of registration, login, vocabulary query, input translation, and new words of dictionary on the platform. In order to take into account various factors and user needs, the software interface design is concise and clear, and the use and operation are convenient and easy to understand. All functions are operated according to the preset plan, and the project functions are fully realized, except for some functions that cannot be completed due to technical reasons or other force majeure factors [5]-[6]. The software platform can run normally on the Android system smart terminal. After installing the software, users can use it to query English vocabulary in a normal network environment. On this basis, speech recognition translation and photo recognition translation are also added. The basic knowledge and technology of android can be used to quickly complete the production and design of the ui. The Android electronic dictionary app is based on the Android electronic dictionary app. After running the test work on various Android mobile devices and emulators, the requirements design is debugged, and the concept of the software is explained. The main significance of the design and its specific implementation process is to allow more Android users to fully enjoy and understand the software running under the android platform.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Evaluating the Performance to Detecting Topic Shift of Large Language Models: A Study

Evaluating the Performance to Detecting Topic Shift of Large...

引用

6th International Conference on Intelligent Computing and Signal processing (ICSP)

作者： Pingfang Tian Deting Liu Department of Computer Science and Technology Wuhan University of Science and Technology Wuhan China The Key Laboratory of the Rich Media Knowledge Organisation and Service of Digital Publishing Content Institute of Scientific and Technical Information of China Beijing China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan China Big Data Science and Engineering Research Institute Wuhan University of Science and Technology Wuhan China

ISBN: (数字)9798350376548

ISBN: (纸本)9798350376555

Topic shift detection aims to identify whether there is a change in the current topic of conversation or if a change is needed. The study found previous work did not evaluate the performance of large language models like ChatGPT on the task of topic shift. Therefore, this paper's main task and innovation lie in analyzing ChatGPT's performance on topic shift detection. To provide a more comprehensive evaluation, we conducted topic shift detection tasks on ChatGPT from three aspects: single utterances, adjacent utterances, and contextual levels. Additionally, to gauge the performance of large language models, we conducted experiments on multiple small-scale models and compared the results of the two models. Experimental results on the publicly available English TIAGE dataset showed that small-scale models exhibited lower recall in all three aspects, while ChatGPT performed better in the recall. This suggests that compared to small-scale models, large models are more capable of accurately detecting topic shifts. However, large models also exhibited lower precision, indicating that while ChatGPT can recognize content differences in utterances, its judgment on whether these different contents belong to the same topic is poor.

关键词： Technological innovation Large language models Oral communication Signal processing Chatbots Context modeling

来源：评论

学校读者我要写书评

暂无评论

Nonparametric resampling for high-squint synthetic aperture radar imaging 5

Nonparametric resampling for high-squint synthetic aperture ...

引用

IET International Radar Conference 2020, IET IRC 2020

作者： Li, Linghao Wang, Yan Ding, Zegang Min, Rui School of Information and Electronics Beijing Institute of Technology Beijing China Beijing Key Laboratory of Embedded Real-Time Information Processing Technology China Beijing Institute of Technology of Chongqing Innovation Center Chongqing China

ISBN: (纸本)9781839535635

Synthetic aperture radar (SAR) image resampling is a key technology for SAR image geometric correction, interferometric and tomographic registration. In some geometry like the high-squint (HS) case, image spectrum will be distorted, folded and therefore, existing resampling methods will fail due to the resulting serious image degradation. To solve this problem, we propose a general nonparametric image resampling method for SAR. The main contribution is the new non-parametric method of morphologically generating image-domain interpolation kernel, which can be theoretically applied for an arbitrary SAR image focused either on slant range plane or ground plane. The presented approach is evaluated by showing resampled image quality improvement via the computer simulations. © 2020 Institution of Engineering and technology. All rights reserved.

关键词： Synthetic aperture radar

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：