检索结果-内蒙古大学图书馆

22nd IEEE International Symposium on Intelligent Systems and Informatics, SISY 2024

作者： Safarpour Motealegh Mahalegi, Homayoun Farhadi, Amirfarhad Molnar, Gyorgy Nagy, Eniko Obuda University Institute of Mechatronics and Vehicle Engineering Budapest Hungary Islamic Azad University Department of Computer Engineering Science and Research Branch Tehran Iran Obuda University Hungary Szechenyi University Apaczai Csere János Faculty of Humanities Education and Social Sciences Kando Kalman Faculty of Electrical Engineering Budapest Gyor Hungary Obuda University Antal Bejczy Center for Intelligent Robotics John von Neumann Faculty of Informatics Budapest Hungary

ISBN: (纸本)9798350385601

In recent years, the number of unmanned aerial vehicle (UAV) applications has increased. However, navigating them indoors is still tricky because no GPS signals are available, and the obstacles constantly change. This study exploits the collaboration between convolutional neural networks (CNNs) and reinforcement learning (RL) to overcome these challenges, improving the level of independence of UAVs in indoor settings. We present a new technique known as potential-based reward shaping, which directly incorporates expert knowledge into the reinforcement learning framework. This technique efficiently addresses the problem of sparse rewards that often hinder learning in conventional RL configurations. In addition, we have created a reflective reinforcement learning agent that systematically assesses its actions to prioritize those that result in the most substantial enhancements. We have extensively evaluated the performance of our method with the High-Definition Indoor Navigation (HDIN) dataset to show that our method continuously outperformed current non-introspective RL techniques in terms of decision-making speed and navigation accuracy in this evaluation. The results show that this new CNN-RL combination is feasible and suggests a scalable method for complex indoor navigation problems. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Neural MPC-Based Decision-Making Framework for Autonomous Driving in Multi-Lane Roundabout

Neural MPC-Based Decision-Making Framework for Autonomous Dr...

引用

International Conference on Intelligent Transportation

作者： Yao Mu Zhiqian Lan Chen Chen Chang Liu Ping Luo Shengbo Eben Li Department of Computer Science The University of Hong Kong School of Vehicle and Mobility Tsinghua University Department of Advanced Manufacturing and Robotics College of Engineering Peking University

The multi-lane roundabout poses significant challenges for autonomous driving due to its complex road structure and traffic conditions. To address these challenges, this paper proposes a novel Neural Model Predictive Control (NMPC)-based decision-making framework that integrates prediction, planning, and control for autonomous vehicles to navigate multi-lane roundabouts. The proposed NMPC framework learns a dynamical model, incorporating interaction data, to accurately predict the behavior of surrounding traffic participants. Multiple candidate static paths are then generated based on the road structure, and the decision-making problem is formulated as a series of parallel static path tracking control problems subject to safety constraints. The static path with minimal tracking cost is selected as the target reference path, and the tracking control is generated simultaneously. To enhance computational efficiency, NMPC utilizes a critic network and an actor network to approximate the tracking cost and the control policy, respectively. Experimental evaluation on a multi-lane roundabout simulator, based on a real roundabout in Beijing, demonstrates that the proposed method performs better in terms of driving safety and efficiency compared to several baseline algorithms across various traffic densities.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Ultrafast Negative Diffusion in gold films

Ultrafast Negative Diffusion in gold films

引用

CLEO: Fundamental science, CLEO:FS 2024 - Part of Conference on Lasers and Electro-Optics, CLEO 2024

作者： Block, A. Yu, R. Un, I.W. Varghese, S. Liebel, M. van Hulst, N.F. Fan, S. Tielrooij, K.J. Sivan, Y. BIST and CSIC Bellaterra Spain Department of Electrical Engineering Ginzton Laboratory Stanford University StanfordCA94305 United States School of Electrical and Computer Engineering Ben-Gurion University of the Negev Be'er Sheva8410501 Israel ICFO - Institut de Ciencies Fotoniques The Barcelona Institute of Science and Technology Castelldefels Barcelona08860 Spain Department of Applied Physics TU Eindhoven Den Dolech 2 Eindhoven5612 AZ Netherlands

Using ultrafast thermo-modulation microscopy, we show that the spatio-temporal heat diffusion in gold films has an initial ps-scale, electron-dominated diffusion, followed by an unexpected negative diffusion stage, an... 详细信息

ISBN: (纸本)9781957171395

关键词： Heat flux

来源：评论

学校读者我要写书评

暂无评论

Fast Diffeomorphic Image Registration using Patch based Fully Convolutional Networks

arXiv

引用

arXiv 2024年

作者： Wu, Jiong Zhou, Shuang Lin, Li Wang, Xin Tan, Wenxue School of Computer and Electrical Engineering Hunan University of Arts and Science Hunan China Furong College Hunan University of Arts and Science Hunan China Department of Electrical and Electronic Engineering The University of Hong Kong Hong Kong

Diffeomorphic image registration is a fundamental step in medical image analysis, owing to its capability to ensure the invertibility of transformations and preservation of topology. Currently, unsupervised learning-based registration techniques primarily extract features at the image level, potentially limiting their efficacy. This paper proposes a novel unsupervised learning-based fully convolutional network (FCN) framework for fast diffeomorphic image registration, emphasizing feature acquisition at the image patch level. Furthermore, a novel differential operator is introduced and integrated into the FCN architecture for parameter learning. Experiments are conducted on three distinct T1-weighted magnetic resonance imaging (T1w MRI) datasets. Comparative analyses with three state-of-the-art diffeomorphic image registration approaches including a typical conventional registration algorithm and two representative unsupervised learning-based methods, reveal that the proposed method exhibits superior performance in both registration accuracy and topology preservation. Copyright © 2024, The Authors. All rights reserved.

关键词： Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Depth from Coupled Optical Differentiation

arXiv

引用

arXiv 2024年

作者： Luo, Junjie Liu, Yuxuan Alexander, Emma Guo, Qi Elmore Family School of Electrical and Computer Engineering Purdue University 501 Northwestern Ave West LafayetteIN47906 United States Department of Computer Science McCormick School of Engineering and Applied Science Northwestern University 2233 Tech Drive EvanstonIL60208 United States

We propose depth from coupled optical differentiation, a low-computation passive-lighting 3D sensing mechanism. It is based on our discovery that per-pixel object distance can be rigorously determined by a coupled pair of optical derivatives of a defocused image using a simple, closed-form relationship. Unlike previous depth-from-defocus (DfD) methods that leverage spatial derivatives of the image to estimate scene depths, the proposed mechanism’s use of only optical derivatives makes it significantly more robust to noise. Furthermore, unlike many previous DfD algorithms with requirements on aperture code, this relationship is proved to be universal to a broad range of aperture codes. We build the first 3D sensor based on depth from coupled optical differentiation. Its optical assembly includes a deformable lens and a motorized iris, which enables dynamic adjustments to the optical power and aperture radius. The sensor captures two pairs of images: one pair with a differential change of optical power and the other with a differential change of aperture scale. From the four images, a depth and confidence map can be generated with only 36 floating point operations per output pixel (FLOPOP), more than ten times lower than the previous lowest passive-lighting depth sensing solution to our knowledge. Additionally, the depth map generated by the proposed sensor demonstrates more than twice the working range of previous DfD methods while using significantly lower *** Codes 68U10 © 2024, CC BY-NC-ND.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Angularly Stable, Single-Layer Absorptive Metasurface for X-Band Applications

Angularly Stable, Single-Layer Absorptive Metasurface for X-...

引用

Microwave, Antennas & Circuits (ICMAC), International Conference on

作者： Muhammad Danial Shafi Ahsaan Gul Hassan Harun Ildeş Inam Ullah Nosherwan Shoaib Symeon Nikolaou School of Electrical Engineering and Computer Science (SEECS) National University of Sciences and Technology (NUST) Islamabad Pakistan Department of Electrical and Electronics Engineering Hacettepe University Ankara Turkey Frederick Research Center Nicosia Cyprus Electrical Engineering Department Frederick University Nicosia Cyprus

ISBN: (数字)9798331518424

ISBN: (纸本)9798331518431

This work presents the design of a single-layer absorptive metasurface capable of achieving broadband absorption across the X -band over a wide range of incidence angles. The design introduces novelty through its unit cell configuration, angular stability, enhanced fractional bandwidth, and absorption without the use of an air gap. Both measured and simulated results are in strong agreement, underscoring the potential of the proposed metasurface for radar cross-section (RCS) reduction applications. Overall, the absorption ratio (AR) exceeds 80% for incidence angles up to 50°, highlighting its effectiveness for practical applications.

关键词： Electric potential Radar cross-sections Absorption Circuits Bandwidth Metasurfaces Stability analysis Broadband communication Circuit stability Electromagnetics

来源：评论

学校读者我要写书评

暂无评论

Graph-based deep learning models in the prediction of early-stage Alzheimers

Graph-based deep learning models in the prediction of early-...

引用

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： Bishal Thapaliya Zundong Wu Ram Sapkota Bhaskar Ray Pranav Suresh Santosh Ghimire Vince Calhoun Jingyu Liu Department of Computer Science Georgia State University Atlanta USA Tri-Institutional Center for Translational Research in Neuroimaging and Data Science School of Electrical and Computer Engineering Georgia Institute of Technology Atlanta USA Department of Applied Sciences and Chemical Engineering Tribhuvan University Nepal

ISBN: (数字)9798350371499

ISBN: (纸本)9798350371505

Alzheimer's disease is the most common age-related problem and progresses in different stages, from cognitively normal to early mild cognitive impairment, and severe dementia. This study investigates the predictive potential of resting-state functional magnetic resonance imaging (rs-fMRI) and its derived functional connectivity (FC) in understanding Alzheimer's progression. Leveraging deep learning and graph-based models, we introduce two key contributions: 1) a comparative analysis of rs-fMRI time points and FC for Alzheimer's prediction. 2) an innovative graph transformer variant incorporating self-clustering for enhanced prediction accuracy. Experiments on the Alzheimer's Disease Neuroimaging Initiative dataset with 830 subjects reveal two notable conclusions. Firstly, rs-fMRI time points offer limited utility compared to functional network connectivity for transformer-based models, even when considering temporal information. Secondly, a clustering-based attention module proves effective for classifying brain networks in predicting Alzheimer's disease progression, providing valuable insights for future research and clinical applications.

关键词： Deep learning Neuroimaging Analytical models Biological system modeling Predictive models Functional magnetic resonance imaging Transformers Brain modeling Alzheimer's disease engineering in medicine and biology

来源：评论

学校读者我要写书评

暂无评论

Towards cross-modal causal structure and representation learning 2

Towards cross-modal causal structure and representation lear...

引用

2nd Machine Learning for Health Symposium, ML4H 2022

作者： Mao, Haiyi Liu, Hongfu Xiaotian Dou, Jason Benos, Panayiotis V. Joint CMU-Pitt PhD Program in Computational Biology University of Pittsburgh United States Michtom School of Computer Science Brandeis University United States Department of Electrical and Computer Engineering University of Pittsburgh United States Department of Epidemiology University of Florida United States

Does the SARS-CoV-2 virus cause patients' chest X-Rays ground-glass opacities? Does an IDH-mutation cause differences in patients' MRI images? Conventional causal discovery algorithms, although well developed to uncover the cause-effect relationships on structured data, cannot elucidate causal relations between unstructured images and structured scalar variables due to the complexity of the former. In this paper, we consider causal discovery between images and structured (scalar) variables. Specifically, we derive low dimensional image representations to analyze with structured variables. We propose a two-module amortized variational algorithm named Cross-Modal Variational Causal representation and structure Learning (CMCL). CMCL jointly learns identifiable representations given a set of independent structured variables and causal relations via formulating latent representations and structured variables into a direct acyclic graph. Moreover, we further enforce counterfactual invariance/variance onto representations. We demonstrate that CMCL outperforms other related methods on synthetic datasets and validate causal relations on semi-synthetic datasets by visualization. © 2022 P.N. Argaw, E. Healey & I.S. Kohane.

关键词： Coronavirus

来源：评论

学校读者我要写书评

暂无评论

Reconfigurable Intelligent Surface Aided Integer Forcing MIMO

引用

IEEE Transactions on Wireless Communications 2025年

作者： Chae, Sung Ho Jeon, Sang-Woon Kwangwoon University Department of Electronic Engineering Seoul01897 Korea Republic of Zhejiang Normal University School of Computer Science and Technology Jinhua321004 China Hanyang University Department of Electrical and Electronic Engineering Ansan15588 Korea Republic of

This paper studies a cooperative relaying communication scheme that employs a single passive reconfigurable intelligent surface (RIS), utilizing integer forcing (IF) as a multiple-input multiple-output (MIMO) technique. In the case of IF-based transceivers, the transmitter sends independently encoded data streams using the same lattice code, and the receiver decodes integer-linear combinations of codewords instead of decoding each codeword separately. Although the flexible decoding provided by IF improves achievable rates compared to conventional separate decoding, the integer-linear combinations observed at the IF-based receiver must remain unchanged throughout the codeword’s duration, even in the presence of channel variations, to enable the decoding of summed codewords. Motivated by this fact, we introduce a novel strategy tailored for IF that involves adjusting the reflection matrix of the RIS to reduce fluctuations in the resulting end-to-end channel between the transmitter and receiver throughout codeword transmission, which we refer to as channel stabilization. Furthermore, we develop a novel IF-based transceiver scheme called successive cancellation IF (SC-IF), which effectively integrates successive IF (S-IF) sum decoding with minimum mean square error–successive interference cancellation (MMSE–SIC) individual decoding within a unified MIMO framework to achieve improved performance. Simulation results demonstrate that when a large number of reflective elements are employed in the RIS, the proposed channel stabilization scheme significantly outperforms benchmark schemes that aim to individually optimize the reflection matrix for each sub-block, and the proposed SC-IF can achieve a rate comparable to the theoretical upper bound represented by the joint maximal likelihood (ML) receiver. © 2002-2012 IEEE.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Optimizing Spectrum Prediction in Cognitive Radio: Genetic Algorithm-Enhanced Neural Networks and Radial Basis Functions 16

Optimizing Spectrum Prediction in Cognitive Radio: Genetic A...

引用

16th International Conference on Developments in eSystems engineering, DeSE 2023

作者： Ansari, Sam Kaissar, Antanios Khater, Tarek Alnajjar, Khawla A. Mahmoud, Soliman Hussain, Abir University of Sharjah Department of Electrical Engineering Sharjah United Arab Emirates University of Khorfakkan Khor fakkan United Arab Emirates Liverpool John Moores University School of Computer Science and Mathematics Faculty of Engineering LiverpoolL3 3AF United Kingdom

ISBN: (纸本)9798350381344

Throughout recent years, the field of wireless communication has experienced exponential growth. This expansion has been propelled by the continual innovation of diverse wireless standards and the evolution of high-speed applications, resulting in a mounting scarcity of spectrum and an intensified demand for bandwidth. Regrettably, existing studies substantiate an inefficient utilization of available frequency bands. Channel bandwidth and effective spectrum utilization persist as formidable challenges in the realm of wireless communication. Addressing these challenges, cognitive radio stands as a pivotal solution, enabling the efficient sharing of available spectrum among primary/secondary or licensed/unlicensed users. The successful implementation of cognitive radio relies significantly on accurate spectrum sensing and prediction to avert interference or collisions among users. This work introduces a neural network-based model augmented and fine-tuned by a genetic algorithm, exemplifying state-of-the-art effectiveness in spectrum prediction. To expand the horizon, this paper investigates a novel approach based on the radial basis function network, further enriching the exploration. The proposed model demonstrates exceptional performance as validated through rigorous MATLAB simulations. The comparative analysis of these simulations serves as a robust benchmark, illuminating the superior efficacy and practicality of the model in real-world scenarios. © 2023 IEEE.

关键词： Genetic 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：