检索结果-内蒙古大学图书馆

14th International Conference on Digital Image Processing, ICDIP 2022

作者： Wang, Zewei Zhang, Jingjing Du, Xingzhuo Cao, Sihua Wei, Wenxuan School of Automation China University of Geosciences Wuhan430074 China Hubei key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education China

ISBN: (纸本)9781510657564

When projecting onto a non-white surface, the projected image is distorted or color mixing by complex luminance and chrominance information, which makes the projection result different from the visual perception of the human eye. The purpose of projection image correction is to remove these effects, and traditional solutions usually estimate parameters from the collected projection samples, compute an inverse model of the projection imaging process, and try to fit a correction function. In this paper, a deep neural network-based projection image correction network (PICN) is designed to implicitly learn complex correction functions. PICN consists of a U-shaped backbone network, a convolutional neural network that extracts projected surface features, and a perceptual loss network that optimizes the correction results. Such a structure can not only extract the deep features and surface interference features of the projected image, but also make the corrected projected image more in line with human visual perception. In addition, we built a projector-camera system under the condition of a fixed global illumination environment for verification experiment, and proved the effectiveness of the proposed method by calculating the evaluation metrics of projected images before and after correction. © 2022 SPIE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Bayesian Exponential Regularized Tensor Based Approach for Sparse Geomagnetic Data Completion

Bayesian Exponential Regularized Tensor Based Approach for S...

引用

2023 International Conference on Sensing, Measurement and Data Analytics in the Era of Artificial Intelligence, ICSMD 2023

作者： Li, Guoyu Bin, Junchi Liu, Huan School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China School of Engineering University of British Columbia OkanaganBCV1V 1V7 Canada

ISBN: (纸本)9798350318012

Geomagnetic data is vital for predicting earthquakes and magnetic storms. In this regard, a new Bayesian exponential regularized tensor completion framework for sparse geomagnetic data, i.e. BERTC, is proposed to address this problem in the study. First, the spatiotemporal geomagnetic data is reshaped into a 3D tensor with days and hours that features random missing elements. Second, a Gibbs sampling algorithm is developed to achieve probabilistic inference on matrices' factors and corresponding parameters in this model. Thus, the sparse tensor can be gradually optimized to fill the missing entries during iterations. Third, an exponential regularizer is proposed to reduce oscillations before and after iterations to enhance imputation quality further. Finally, the derived factor matrices are aggregated from Gibbs sampling to complete the sparse tensor. Numerical geomagnetic datasets from 13 cities are employed, and extensive comparison experiments are conducted to evaluate the imputation performance of the BERTC. The results show the superiority of the proposed BERTC compared to the state-of-the-art methods in terms of imputation accuracy, with an approximate improvement of the imputation accuracy as no less than 20%. © 2023 IEEE.

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

Optimized Hybrid Control for Attitude Adjustment of Downhole Directional Drilling Tools

Optimized Hybrid Control for Attitude Adjustment of Downhole...

引用

Annual Conference of Industrial Electronics Society

作者： Jing Xiao She Wang Zhen Cai School of Information Engineering Wuhan City Polytechnic University Wuhan China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China

ISBN: (数字)9781665464543

ISBN: (纸本)9781665464550

This study delves into the critical role of attitude control in downhole directional drilling tools, focusing on the complex coupling between inclination and azimuth in the motion model, particularly the time-varying nature of azimuth adjustments. By implementing separate control strategies for inclination and azimuth, the research integrates a comprehensive hybrid control system. It rigorously examines the stability of the closed-loop systems and validates the effectiveness and applicability of the hybrid control method through extensive simulations. The system demonstrates significant robustness and adaptability, enhancing drilling precision and efficiency.

关键词： Drilling Couplings Industrial electronics Azimuth Attitude control Simulation Focusing Stability analysis Robustness Linear matrix inequalities

来源：评论

学校读者我要写书评

暂无评论

Human-like conceptual representations emerge from language prediction

arXiv

引用

arXiv 2025年

作者： Xu, Ningyu Zhang, Qi Du, Chao Luo, Qiang Qiu, Xipeng Huang, Xuanjing Zhang, Menghan School of Computer Science Fudan University Shanghai China Institute of Modern Languages and Linguistics Fudan University Shanghai China Shanghai Key Laboratory of Intelligent Information Processing Shanghai China Research Institute of Intelligent Complex Systems Fudan University Shanghai China Shanghai Collaborative Innovation Center of Intelligent Visual Computing Shanghai China Ministry of Education Key Laboratory of Contemporary Anthropology Fudan University Shanghai China

People acquire concepts through rich physical and social experiences and use them to understand the world. In contrast, large language models (LLMs), trained exclusively through next-token prediction over language data, exhibit remarkably human-like behaviors. Are these models developing concepts akin to humans, and if so, how are such concepts represented and organized? To address these questions, we reframed the classic reverse dictionary task to simulate human concept inference in context and investigated the emergence of human-like conceptual representations within LLMs. Our results demonstrate that LLMs can flexibly derive concepts from linguistic descriptions in relation to contextual cues about other concepts. The derived representations converged towards a shared, context-independent structure that effectively predicted human behavior across key psychological phenomena, including computation of similarities, categories and semantic scales. Moreover, these representations aligned well with neural activity patterns in the human brain, even in response to visual rather than linguistic stimuli, providing evidence for biological plausibility. These findings establish that structured, human-like conceptual representations can naturally emerge from language prediction without real-world grounding. More broadly, our work positions LLMs as promising computational tools for understanding complex human cognition and paves the way for better alignment between artificial and human intelligence. Copyright © 2025, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Adaptive Temporal Aggregation Network for Online Video Visual Relation Detection

SSRN

引用

SSRN 2023年

作者： He, Yuxuan Gan, Ming-Gang Ma, Qianzhao Wang, Chenyu State Key Laboratory of Intelligent Control and Decision of Complex Systems School of Automation Beijing Institute of Technology Beijing100081 China

Nowadays, more and more researchers pay attention to scene perception of artificial robot. Video visual relation detection is an essential task for scene perception but existing methods are all offline methods which are unsuitable for real-time application. Thus, we first introduce online video visual relation detection task which aims at localizing and classifying relations in the current frame. Then, we propose Adaptive Temporal Aggregation Network for online video visual relation detection. In this network, we design content-based adaptive sampling method to sample historical frames which contain dynamic scene information. In order to extract history knowledge from these discrete features, we propose adaptive spatio-temporal activation module which consists of adaptive spatial activation unit and adaptive temporal aggregation unit to extract history knowledge from history memory. After obtaining history knowledge and current state, the proposed attention-based knowledge-state fusion module is used to fuse these dynamic and static visual information. We also construct spatial location features and semantic embedding features to improve final relation representations. Experiments show the effectiveness and efficiency of our method. Moreover, we implement our network on fetch robot and visualize the online video visual relation detecting process. © 2023, The Authors. All rights reserved.

关键词： Chemical activation

来源：评论

学校读者我要写书评

暂无评论

Dual-polarization Dual-mode Silicon 3dB Beam Splitter Based on Shallow Etched Multimode Interference Coupler

Dual-polarization Dual-mode Silicon 3dB Beam Splitter Based ...

引用

Optoelectronics Global Conference (OGC)

作者： Hong Ma Mengyuan Ye Jie Liu Duowei Zeng Yang Chen School of Automation Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems China University of Geosciences Wuhan China

In this paper, we propose a dual polarization dual mode 3dB beam splitter. By utilizing the shallow etched multimode interference (MMI) coupler, the proposed device can handle TE 0 , TE 1 , TM 0 and TM 1 modes simul...

关键词：

来源：评论

学校读者我要写书评

暂无评论

Trajectory Planning Based on Spatio-Temporal Map with Collision Avoidance Guaranteed by Safety Strip

引用

IEEE Transactions on intelligent Transportation systems 2022年第2期23卷 1030-1043页

作者： Zhang, Ting Fu, Mengyin Song, Wenjie Yang, Yi Wang, Meiling State Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing Institute of Technology Beijing China

Trajectory planning for the unmanned vehicle in the complex environment has always been a challenging task. Planned trajectory with the corresponding target velocity or acceleration sequence must be collision-free guaranteed and as comfortable as possible on the premise of obeying the traffic rules and interaction with other dynamic social vehicles. To meet this requirement, this paper proposes a framework for trajectory planning based on spatio-Temporal map. Due to the time layer architecture in the map, the trajectory can be generated with velocity and acceleration simultaneously, and the whole trajectory is constrained within a 'safety strip', resulting in an efficient and safety guaranteed trajectory. The framework is composed of three sections: rough search, fine optimization and safety strip-based collision avoidance. For rough search, we propose an improved A∗ algorithm implemented in the discrete time layer to find out the suboptimal states efficiently. In fine optimization, the B-spline curve is exploited to connect the searched states into a continuous trajectory. And the optimal control points of B-spline are further grouped into several segments, forming the safety strip which is actually the distribution space of the planned trajectory. If necessary, an adjustment will be applied to keep the strip away from the collision zone, making the entire trajectory completely collision-free. Experiments on both public dataset and self-driving simulator show that the proposed framework can adapt to different kinds of complex traffic scenes well. © 2000-2011 IEEE.

关键词： Collision avoidance

来源：评论

学校读者我要写书评

暂无评论

Polarization-independent Dual Mode Silicon Spot Size Converter Using Gradual Index Distributed Subwavelength Gratings

Polarization-independent Dual Mode Silicon Spot Size Convert...

引用

Optoelectronics Global Conference (OGC)

作者： Jie Liu Mengyuan Ye Hong Ma Duowei Zeng Yang Chen School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China

We propose and demonstrate a polarization-independent dual mode spot size converter (SSC) on silicon integrated platform. By utilizing gradual index distributed subwavelength gratings (GRIN-SWG). The proposed device c...

关键词：

来源：评论

学校读者我要写书评

暂无评论

FESSNC: fast exponentially stable and safe neural controller 24

FESSNC: fast exponentially stable and safe neural controller

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Jingdong Zhang Luan Yang Qunxi Zhu Wei Lin School of Mathematical Sciences LMNS and SCMS and Research Institute of Intelligent Complex Systems Fudan University China Research Institute of Intelligent Complex Systems and State Key Laboratory of Medical Neurobiology and MOE Frontiers Center for Brain Science Institutes of Brain Science Fudan University China and Shanghai Artificial Intelligence Laboratory China School of Mathematical Sciences LMNS and SCMS and Research Institute of Intelligent Complex Systems and State Key Laboratory of Medical Neurobiology and MOE Frontiers Center for Brain Science Institutes of Brain Science Fudan University China and Shanghai Artificial Intelligence Laboratory China

In order to stabilize nonlinear systems modeled by stochastic differential equations, we design a Fast Exponentially Stable and Safe Neural Controller (FESSNC) for fast learning controllers. Our framework is parameterized by neural networks, and realizing both rigorous exponential stability and safety guarantees. Concretely, we design heuristic methods to learn the exponentially stable and the safe controllers, respectively, in light of the classical theory of stochastic exponential stability and our established theorem on guaranteeing the almost-sure safety for stochastic dynamics. More significantly, to rigorously ensure the stability and the safety guarantees for the learned controllers, we develop a projection operator, projecting to the space of exponentially-stable and safe controllers. To reduce the highly computational cost for solving the projection operation, approximate projection operators are delicately proposed with closed forms that map the learned controllers to the target controller space. Furthermore, we employ Hutchinson's trace estimator for a scalable unbiased estimate of the Hessian matrix that is used in the projection operator, which thus allows for reducing computational cost and, therefore, can accelerate the training and testing processes. More importantly, our approximate projection operations are applicable to the nonparametric control methods, improving their stability and safety performance. We empirically demonstrate the superiority of the FESSNC over the existing methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on Dynamic Labels in Network Pruning

Research on Dynamic Labels in Network Pruning

引用

Industrial Cyber-Physical systems (ICPS)

作者： Lijun Zhang Yaomin Luo Shiqi Xie Xiucheng Wu Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems School of Automation China University of Geosciences Wuhan China

Convolutional neural network compression technology plays an extremely important role in model transplantation and deployment, especially in mobile and embedded hardware platforms with small memory and low computing power, compression technology is even more critical. Convolutional neural network channel pruning technology has developed rapidly in recent years, and a number of excellent pruning algorithms have emerged. The channel pruning technology has gradually developed from the earliest static pruning to dynamic pruning, which adopts different pruning schemes for different inputs. However, the current dynamic pruning scheme needs to introduce multiple modules to predict the mask to prune the feature maps, and some schemes also introduce multiple hyperparameters in the loss function to balance the model accuracy and pruning rate, which leads to The model has difficulty converging during training. We propose a dynamic pruning method, each convolution structure configures a simple prediction module, and generating dynamic labels through the input's norm and similarity to guide the prediction module training, which will not bring new parameters to the loss function. We conducted related experiments on multiple models on the Cifar10 datasets. The experiments on ResNet56 show that our scheme is 1.3% higher than the most advanced scheme in terms of compression rate under the premise of the same accuracy.

关键词： Training Convolution Heuristic algorithms Computational modeling Predictive models Cyber-physical systems Prediction algorithms

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：