检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Heidari, Moein Azad, Reza Kolahi, Sina Ghorbani Arimond, René Niggemeier, Leon Sulaiman, Alaa Bozorgpour, Afshin Aghdam, Ehsan Khodapanah Kazerouni, Amirhossein Hacihaliloglu, Ilker Merhof, Dorit School of Biomedical Engineering University of British Columbia BC Canada Faculty of Electrical Engineering and Information Technology RWTH Aachen University Aachen Germany Department of Industrial and Systems Engineering Tarbiat Modares University Tehran Iran Faculty of Information Science and Technology Universiti Kebangsaan Bangi Malaysia Faculty of Informatics and Data Science University of Regensburg Regensburg Germany Department of Electrical Engineering Shahid Beheshti University Tehran Iran Department of Computer Science University of Toronto Toronto Canada Department of Radiology Department of Medicine University of British Columbia BC Canada Fraunhofer Institute for Digital Medicine MEVIS Bremen Germany

Intrigued by the inherent ability of the human visual system to identify salient regions in complex scenes, attention mechanisms have been seamlessly integrated into various computer Vision (CV) tasks. Building upon this paradigm, Vision Transformer (ViT) networks exploit attention mechanisms for improved efficiency. This review navigates the landscape of redesigned attention mechanisms within ViTs, aiming to enhance their performance. This paper provides a comprehensive exploration of techniques and insights for designing attention mechanisms, systematically reviewing recent literature in the field of CV. This survey begins with an introduction to the theoretical foundations and fundamental concepts underlying attention mechanisms. We then present a systematic taxonomy of various attention mechanisms within ViTs, employing redesigned approaches. Amulti-perspective categorization is proposed based on their application, objectives, and the type of attention applied. The analysis includes an exploration of the novelty, strengths, weaknesses, and an in-depth evaluation of the different proposed strategies. This culminates in the development of taxonomies that highlight key properties and contributions. Finally, we gather the reviewed studies along with their available open-source implementations at our *** aim to regularly update it with the most recent relevant papers. © 2024, CC BY-NC-SA.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Robust distributed accelerated stochastic gradient methods for multi-agent networks

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2022年第1期23卷 9893-9988页

作者： Alireza Fallah Mert Gürbüzbalaban Asuman Ozdaglar Umut Şimşekli Lingjiong Zhu Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology Cambridge MA Department of Management Science and Information Systems Departments of Electrical Engineering and Statistics Rutgers University Piscataway NJ INRIA - Département d'Informatique de l' École Normale Supérieure PSL Research University Paris France Department of Mathematics Florida State University Tallahassee FL

We study distributed stochastic gradient (D-SG) method and its accelerated variant (D-ASG) for solving decentralized strongly convex stochastic optimization problems where the objective function is distributed over several computational units, lying on a fixed but arbitrary connected communication graph, subject to local communication constraints where noisy estimates of the gradients are available. We develop a framework which allows to choose the stepsize and the momentum parameters of these algorithms in a way to optimize performance by systematically trading off the bias, variance and dependence to network effects. When gradients do not contain noise, we also prove that D-ASG can achieve acceleration, in the sense that it requires O(√κlog(1/ε)) gradient evaluations and O(√κlog(1/ε)) communications to converge to the same fixed point with the non-accelerated variant where κ is the condition number and ε is the target accuracy. For quadratic functions, we also provide finer performance bounds that are tight with respect to bias and variance terms. Finally, we study a multistage version of D-ASG with parameters carefully varied over stages to ensure exact convergence to the optimal solution. It achieves optimal and accelerated O(-k/√κ) linear decay in the bias term as well as optimal O(σ2/k) in the variance term. We illustrate through numerical experiments that our approach results in accelerated practical algorithms that are robust to gradient noise and that can outperform existing methods.

关键词： distributed optimization accelerated methods stochastic optimization robustness multi-agent networks

来源：评论

学校读者我要写书评

暂无评论

Thermal evaluation of plant biomass from the phytostabilisation of soils contaminated by potentially toxic elements

引用

Chemosphere 2023年 342卷 140116页

作者： Gómez, Xiomar Bernal, Maria Pilar Zárate, Piedad P. Álvarez-Robles, M. José González, Rubén Clemente, Rafael Universidad de León Av. de Portugal 41 León24009 Spain Centro de Edafología y Biología Aplicada Del Segura CSIC Campus Universitario de Espinardo Murcia30100 Spain Department of Electrical Systems and Automatic Engineering School of Industrial Computer and Aeronautical Engineering University of León Campus de Vegazana León24071 Spain

The combination of phytoremediation of soils contaminated by potentially toxic elements with energy production by combustion of the generated biomass can be a sustainable land management option, combining the production of renewable bioenergy with soil restoration while minimising energy consumption and CO2 emission. In this work, plant biomass from phytoremediation of soils contaminated by potentially toxic elements was studied as solid biofuel for combustion by thermal analysis and biomass composition. Six plant species were grown in two soils with differing degrees of contamination: Brassica juncea, Cynara cardunculus, Atriplex halimus, Nicotiana glauca, Dittrichia viscosa, Retama sphaerocarpa and Salvia rosmarinus. The composition of the plant biomass was characterised chemically and thermogravimetric analyses were performed for the mass loss (TG), derivative curves of mass loss (DTG) and temperature difference (DTA) signal. The cellulose concentration correlated with the parameters of the thermal analysis in the low temperature range (150–350 °C), while lignin correlated with the thermal parameters of the second peak in the high temperature range. Salvia rosmarinus and R. sphaerocarpa showed the best combustion characteristics according to the thermal profile and mineral residue results. The accumulation of potentially toxic elements in B. juncea grown in heavily contaminated soil led to a higher amount of residue at 750 °C, with a global activation energy lower than the one obtained when this species was grown in a soil with lower contamination. Therefore, the most beneficial combination of soil phytoremediation and energy production (combustion) that can be suggested would depend on the level of soil contamination: in heavily contaminated soil, phytostabilisation using R. sphaerocarpa and S. rosmarinus;in slightly contaminated soil, B. juncea due to its high energy of activation, although the concentrations of potentially toxic elements in the residue must be

关键词： Soils

来源：评论

学校读者我要写书评

暂无评论

Robust Data-Driven Predictive Control of Unknown Nonlinear systems using Reachability Analysis

arXiv

引用

arXiv 2022年

作者： Farjadnia, Mahsa Alanwar, Amr Niazi, Muhammad Umar B. Molinari, Marco Johansson, Karl Henrik Department of Energy Technology School of Industrial Engineering and Management KTH Royal Institute of Technology Stockholm Sweden School of Computer Science and Engineering Constructor University Bremen Germany Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden Laboratory for Information and Decision Systems Massachusetts Institute of Technology Cambridge United States

This work proposes a robust data-driven predictive control approach for unknown nonlinear systems in the presence of bounded process and measurement noise. Data-driven reachable sets are employed for the controller design instead of using an explicit nonlinear system model. Although the process and measurement noise are bounded, the statistical properties of the noise are not required to be known. By using the past noisy input-output data in the learning phase, we propose a novel method to over-approximate exact reachable sets of an unknown nonlinear system. Then, we propose a data-driven predictive control approach to compute safe and robust control policies from noisy online data. The constraints are guaranteed in the control phase with robust safety margins by effectively using the predicted output reachable set obtained in the learning phase. Finally, a numerical example validates the efficacy of the proposed approach and demonstrates comparable performance with a model-based predictive control approach. Copyright © 2022, The Authors. All rights reserved.

关键词： Nonlinear systems

来源：评论

学校读者我要写书评

暂无评论

Risk-Aware Security-Constrained Unit Commitment: Taming the Curse of Real-Time Volatility and Consumer Exposure

arXiv

引用

arXiv 2023年

作者： Bienstock, Daniel Dvorkin, Yury Guo, Cheng Mieth, Robert Wang, Jiayi Department of Industrial Engineering and Operations Research Columbia University New YorkNY10027 United States Department of Electrical and Computer Engineering Department of Civil and System Engineering Ralph O'Connor Sustainable Energy Institute Johns Hopkins University BaltimoreMD21218 United States School of Mathematical and Statistical Sciences Clemson University ClemsonSC29634 United States Department of Industrial and Systems Engineering Rutgers University New BrunswickNJ08901 United States Department of Management Science and Engineering Stanford University StanfordCA94305 United States

We propose an enhancement to wholesale electricity markets to contain the exposure of consumers to increasingly large and volatile consumer payments arising as a byproduct of volatile real-time net loads - i.e., loads minus renewable outputs - and prices, both compared to day-ahead cleared values. We incorporate a trade-off, motivated by portfolio optimization methods, between standard day-ahead payments and a robust estimate of such excess payments into the day-ahead computation and specifically seek to account for volatility in real-time net loads and renewable generation. Our model features a data-driven uncertainty set based on principal component analysis, which accommodates both load and wind production volatility and captures locational correlation of uncertain data. To solve the model more efficiently, we develop a decomposition algorithm that can handle nonconvex subproblems. Our extensive experiments on a realistic NYISO data set show that the risk-aware model protects the consumers from potential high costs caused by adverse circumstances. Copyright © 2023, The Authors. All rights reserved.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

On the comparison of optimal NOMA and OMA in a paradigm shift of emerging technologies

TechRxiv

引用

TechRxiv 2022年

作者： Ghosh, Joydev Ra, In-Ho Singh, Saurabh Haci, Hüseyin Al-Utaibi, Khaled A. Sait, Sadiq M. School of Computer Science and Robotics Tomsk Polytechnic University Tomsk Russia School of Computer Information and Communication Engineering Kunsan National University Gunsan Korea Republic of Department of Industrial & Systems Engineering Dongguk University Korea Republic of Department of Electrical and Electronics Engineering Near East University Mersin 10 Turkey Computer Science and Software Engineering Department University of Ha’il Saudi Arabia Department of Computer Engineering King Fahd University of Petroleum & Minerals Dhahran Saudi Arabia

Non-orthogonal multiple access (NOMA) is a better multiple access technique than orthogonal multiple access (OMA), precisely orthogonal frequency division multiple access (OFDMA) scheme, at the conceptual level for fifth-generation (5G) networks and beyond 5G (B5G) networks. We investigate the potentials of the schemes by comparing the proposed NOMA scheme with the traditional cooperative communication NOMA (CCNOMA) scheme, rather than the comparison between NOMA and OMA only. To probe the effectiveness of NOMA as a multiple access technique, we propose a novel NOMA scheme considering two adjacent BSs with a special design of the transceiver architecture. The proposed scheme provides a reasonable data rate to both near user (NU) and far user (FU) without compromising the quality of service (QoS) to anyone of them. The conclusive analyses on the optimization framework of multi-user sum rate, capacity, transmit power, spectral efficiency (SE), and energy efficiency (EE) trade-off for NOMA and OFDMA schemes have been established to a succession of derivations. Under the analytical optimization framework, we also prove quite a few properties for them. Simulation results confirm the theoretical findings and show that the two schemes can efficiently approach the optimal power allocation, minimization of power consumption, and optimal SE-EE trade-off, and the proposed NOMA scheme provides comparatively better data sum rates than the baseline OMA scheme. © 2022, CC BY.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Time-Domain Channel Estimation for Extremely Large MIMO THz Communication systems Under Dual-Wideband Fading Conditions

arXiv

引用

arXiv 2023年

作者： Vlachos, Evangelos Kaushik, Aryan Eldar, Yonina C. Alexandropoulos, George C. Industrial Systems Institute ATHENA Research and Innovation Centre Rio-Patras26504 Greece School of Engineering and Informatics University of Sussex United Kingdom Faculty of Mathematics and Computer Science Weizmann institute of Science Israel Department of Informatics and Telecommunications National and Kapodistrian University of Athens Athens15784 Greece Department of Electrical and Computer Engineering Department University of Illinois Chicago ChicagoIL60601 United States

In this paper, we study the problem of extremely large (XL) multiple-input multiple-output (MIMO) channel estimation in the terahertz (THz) frequency band, considering the presence of propagation delays across the entire array apertures at both communication ends, which naturally leads to frequency selectivity. This problem is known as beam squint and may be pronounced when communications are subject to multipath fading conditions. Multi-carrier (MC) transmission schemes, which are usually deployed in THz communication systems to address these issues, suffer from high peak-to-average power ratio, which is specifically dominant in this frequency band where low transmit power is mostly feasible. Furthermore, the frequency selectivity caused by severe molecular absorption in the THz band necessitates delicate consideration in MC system design. Motivated by the benefits of single-carrier (SC) waveforms for practical THz communication systems, diverging from the current dominant research trend on MC systems, we devise a novel channel estimation problem formulation in the time domain for SC XL MIMO systems subject to multipath signal propagation, spatial wideband effects, and molecular absorption. An efficient alternating minimization approach is presented to solve the proposed mixed-integer sparse problem formulation. The conducted extensive performance evaluation results validate that the proposed XL MIMO estimation scheme exhibits superior performance than conventional SC- and MC-based techniques, approaching the idealized lower bound. © 2023, CC BY.

关键词： Channel estimation

来源：评论

学校读者我要写书评

暂无评论

Interval type-2 enhanced possibilistic fuzzy c-means clustering for gene expression data analysis

arXiv

引用

arXiv 2021年

作者： Sotudian, Shahabeddin Zarandi, Mohammad Hossein Fazel Department of Electrical and Computer Engineering Division of Systems Engineering Boston University Boston United States Knowledge/Intelligent Systems Laboratory Department of Mechanical and Industrial Engineering University of Toronto Toronto Canada Department of Industrial Engineering Amirkabir University of Technology Tehran Iran

Both FCM and PCM clustering methods have been widely applied to pattern recognition and data clustering. Nevertheless, FCM is sensitive to noise and PCM occasionally generates coincident clusters. PFCM is an extension of the PCM model by combining FCM and PCM, but this method still suffers from the weaknesses of PCM and FCM. In the current paper, the weaknesses of the PFCM algorithm are corrected and the enhanced possibilistic fuzzy c-means (EPFCM) clustering algorithm is presented. EPFCM can still be sensitive to noise. Therefore, we propose an interval type-2 enhanced possibilistic fuzzy c-means (IT2EPFCM) clustering method by utilizing two fuzzifiers (m1, m2)for fuzzy memberships and two fuzzifiers (θ1, θ2)for possibilistic typicalities. Our computational results show the superiority of the proposed approaches compared with several state-of-the-art techniques in the literature. Finally, the proposed methods are implemented for analyzing microarray gene expression data. © 2021, CC BY-NC-ND.

关键词： Cluster analysis

来源：评论

学校读者我要写书评

暂无评论

COMPUTATION-EFFICIENT ERA: A COMPREHENSIVE SURVEY OF STATE SPACE MODELS IN MEDICAL IMAGE ANALYSIS

arXiv

引用

arXiv 2024年

作者： Heidari, Moein Kolahi, Sina Ghorbani Karimijafarbigloo, Sanaz Azad, Bobby Bozorgpour, Afshin Hatami, Soheila Azad, Reza Diba, Ali Bagci, Ulas Merhof, Dorit Hacihaliloglu, Ilker School of Biomedical Engineering University of British Columbia BC Canada Department of Industrial and Systems Engineering Tarbiat Modares University Tehran Iran Faculty of Informatics and Data Science University of Regensburg Regensburg Germany Electrical Engineering and Computer Science Department South Dakota State University Brookings United States Faculty of Mechanical Engineering Tarbiat Modares University Tehran Iran Faculty of Electrical Engineering and Information Technology RWTH Aachen University Aachen Germany Lunit Inc. Amsterdam Netherlands Department of Radiology Northwestern University Chicago United States Fraunhofer Institute for Digital Medicine MEVIS Bremen Germany Department of Radiology Department of Medicine University of British Columbia BC Canada

Sequence modeling plays a vital role across various domains, with recurrent neural networks being historically the predominant method of performing these tasks. However, the emergence of transformers has altered this paradigm due to their superior performance. Built upon these advances, Vision Transformers (ViTs) have conjoined Convolutional Neural Networks (CNNs) as two leading foundational models for learning visual representations. However, transformers are hindered by the O(N2) complexity of their attention mechanisms, while CNNs lack global receptive fields and dynamic weight allocation. State Space Models (SSMs), specifically the Mamba model with selection mechanisms and hardware-aware architecture, have garnered immense interest lately in sequential modeling and visual representation learning, challenging the dominance of transformers by providing infinite context lengths and offering substantial efficiency maintaining linear complexity in the input sequence. Capitalizing on the advances in computer vision, the field of medical imaging has heralded a new epoch with Mamba models. Intending to help researchers navigate the surge, this survey seeks to offer an encyclopedic review of Mamba models in medical imaging. Specifically, we start with a comprehensive theoretical review forming the basis of SSMs, including Mamba architecture and its alternatives for sequence modeling paradigms in this context. Next, we offer a structured classification of Mamba models in the medical field and introduce a diverse categorization scheme based on their application, imaging modalities, and targeted organs. Consequently, we explore various applications and their practical use cases in medicine, such as image segmentation, reconstruction, registration, classification, language processing, multi-modal understanding, and other medically related challenges. Finally, we summarize key challenges, discuss different future research directions of the SSMs in the medical domain, and prop

关键词： Medical applications

来源：评论

学校读者我要写书评

暂无评论

Distributed Learning of Neural Lyapunov Functions for Large-Scale Networked Dissipative systems

arXiv

引用

arXiv 2022年

作者： Jena, Amit Huang, Tong Sivaranjani, S. Kalathil, Dileep Xie, Le The Department of Electrical and Computer Engineering Texas A& M University College StationTX United States The MIT Laboratory of Information & Decision Systems CambridgeMA United States The School of Industrial Engineering Purdue University West LafayetteIN United States

This paper considers the problem of characterizing the stability region of a large-scale networked system comprised of dissipative nonlinear subsystems, in a distributed and computationally tractable way. One standard approach to estimate the stability region of a general nonlinear system is to first find a Lyapunov function for the system and characterize its region of attraction as the stability region. However, classical approaches, such as sum-of-squares methods and quadratic approximation, for finding a Lyapunov function either do not scale to large systems or give very conservative estimates for the stability region. In this context, we propose a new distributed learning based approach by exploiting the dissipativity structure of the subsystems. Our approach has two parts: the first part is a distributed approach to learn the storage functions (similar to the Lyapunov functions) for all the subsystems, and the second part is a distributed optimization approach to find the Lyapunov function for the networked system using the learned storage functions of the subsystems. We demonstrate the superior performance of our proposed approach through extensive case studies in microgrid networks. Copyright © 2022, The Authors. All rights reserved.

关键词： Lyapunov functions

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：