检索结果-内蒙古大学图书馆

2025 IEEE/CVF Winter Conference on Applications of computer Vision, WACV 2025

作者： Liao, Guiqiu Jogan, Matjaz Koushik, Sai Eaton, Eric Hashimoto, Daniel A. University of Pennsylvania Pcaso Laboratory Department of Surgery United States University of Pennsylvania Department of Electrical and Systems Engineering United States University of Pennsylvania Department of Computer and Information Science United States

ISBN: (纸本)9798331510831

Weakly supervised video object segmentation (WSVOS) enables the identification of segmentation maps without requiring extensive annotations of object masks, relying instead on coarse video labels indicating object presence. WSVOS in surgical videos is, however, more challenging due to the complex interaction of multiple transient objects, such as surgical tools moving in and out of the surgical field. In this scenario, state-of-the-art WSVOS methods struggle to learn accurate segmentation maps. We address this problem by introducing ViDeo Spatio-Temporal disentanglement Networks (VDST-Net), a framework to disentangle complex spatio-temporal object interactions using semi-decoupled knowledge distillation to predict high-quality class activation maps (CAMs). A teacher network is designed to help a temporal-reasoning student network resolve activation conflicts, as the student leverages temporal dependencies when specifics about object location and timing in the video are not provided. We demonstrate the efficacy of our framework on a challenging surgical video dataset where objects are, on average, present in less than 60% of annotated frames, and compare our method to state-of-the-art methods on surgical data and on a public dataset commonly used to benchmark WSVOS. Our method outperforms state-of-the-art techniques and generates accurate segmentation masks under video-level weak supervision. Our code is available at: https://***/PCASOlab/VDST-net. © 2025 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Reinforcement learning-based unknown reference tracking control of HMASs with nonidentical communication delays

引用

Science China(Information Sciences) 2023年第7期66卷 46-57页

作者： Yong XU Zheng-Guang WU Wei-Wei CHE Deyuan MENG School of Automation Beijing Institute of Technology Institute of Cyber-Systems and Control Zhejiang University College of Mathematics and Computer Science Zhejiang Normal University Department of Automation Qingdao University School of Automation Science and Electrical Engineering Beihang University(BUAA)

This paper focuses on the optimal output synchronization control problem of heterogeneous multiagent systems(HMASs) subject to nonidentical communication delays by a reinforcement learning *** with existing studies assuming that the precise model of the leader is globally or distributively accessible to all or some of the followers, the leader's precise dynamical model is entirely inaccessible to all the followers in this paper. A data-based learning algorithm is first proposed to reconstruct the leader's unknown system matrix online. A distributed predictor subject to communication delays is further devised to estimate the leader's state, where interaction delays are allowed to be nonidentical. Then, a learning-based local controller, together with a discounted performance function, is projected to reach the optimal output synchronization. Bellman equations and game algebraic Riccati equations are constructed to learn the optimal solution by developing a model-based reinforcement learning(RL) algorithm online without solving regulator equations, which is followed by a model-free off-policy RL algorithm to relax the requirement of all agents' dynamics faced by the model-based RL algorithm. The optimal tracking control of HMASs subject to unknown leader dynamics and communication delays is shown to be solvable under the proposed RL algorithms. Finally, the effectiveness of theoretical analysis is verified by numerical simulations.

关键词： heterogeneous multiagent systems HMAS reinforcement learning RL optimal output synchronization communication delays

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of Heart Disease Detection Using Different Machine Learning Approaches 6

Performance Analysis of Heart Disease Detection Using Differ...

引用

6th International Conference on electrical engineering and Information and Communication Technology, ICEEICT 2024

作者： Tousif, Md. Noumil Rabbi Ushan, Md. Nahian Akhter, Rumana Mahmud, Sadia Rashid, Sakera Mohammad, Sakib University of Dhaka Department of Biomedical Physics and Technology Dhaka Bangladesh Ahsanullah University of Science and Technology Department of Electrical and Electronic Engineering Dhaka Bangladesh European University of Bangladesh Department of Electrical and Electronic Engineering Dhaka Bangladesh Southern Illinois University Carbondale Department of Electrical Computer and Biomedical Engineering CarbondaleIL United States

ISBN: (纸本)9798350385779

The leading cause of illness and mortality globally, heart disease is a serious global health problem. For successful prevention and intervention, timely and precise cardiac disease prediction is essential. Using the well-known Cleveland dataset from the UCI repository, we underwent an extensive performance examination of several ML approaches in the context of heart disease prediction in this study. The 303 cases and 14 features in this collection include essential clinical factors. The KNN, Random Forest, Naive Bayes, AdaBoost, Decision Tree, and Logistic Regression machine learning algorithms are among those being examined. Each is being assessed for its predictive efficacy. Our work reveals fascinating insights into algorithm performance through substantial data preparation, robust model training, and a thorough assessment utilizing measures like accuracy, sensitivity, specificity, and PPV, NPV. Notably, our results show that the KNN algorithm is the most effective at predicting heart disease by 93%. This finding has implications for improving clinical decision support systems and early heart disease detection, thereby lowering the prevalence of the condition and its negative effects on public health. This research highlights the crucial contribution of ML to the development of cardiovascular medicine and the significance of algorithm choice for predicting accuracy. © 2024 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

SWIR-transparent silicon hot-carrier photodetector for unobstructed real-time laser power monitoring

引用

Optica 2025年第5期12卷 654-665页

作者： Ryu, Eui-Hyoun Hwang, Sunghyun Kim, Nayeon Son, Ji-Hwan Han, Jae-Hoon Ahn, Jongtae Park, Donghee Seong, Tae-Yeon Lee, In-Ho Seoul02792 Korea Republic of Department of Materials Science and Engineering Korea University Seoul02841 Korea Republic of School of Electrical Engineering Korea University Seoul02841 Korea Republic of Korea University Department of Micro/Nano Systems Seoul02841 Korea Republic of Department of Physics Changwon National University Changwon51139 Korea Republic of

Optically transparent photodetectors are becoming essential components in next-generation photonic technologies such as augmented reality and light-field imaging. While transparent photodetectors have been extensively developed for the visible spectrum, extending this capability to the short-wavelength infrared (SWIR) regime remains a significant challenge. This is primarily due to the lack of suitable transparent electrodes and the difficulty in minimizing the thickness of light-absorbing layers. In this work, we demonstrate an SWIR-transparent silicon hot-carrier photodetector, enabled by an ultrathin silver film topped with a high-refractive-index overlayer, serving as a transparent electrode. The electrode design exploits destructive interference to minimize reflection, achieving an 86% transmittance at 1300 nm and a normalized transmittance of 123% relative to a silicon substrate. Integrating this electrode into a silicon substrate forms a metal–silicon Schottky junction for SWIR photon detection through hot-carrier injection, with photon absorption confined to a sub-10 nm metal layer. By leveraging the optical transparency of our photodetector, we demonstrate a laser power monitoring strategy that enables real-time optical power measurements without compromising the spatial profile of the laser beam and altering its optical path. This work paves the way for compact, streamlined designs in applications such as optical data transmission and light detection and ranging (LiDAR), where continuous laser power monitoring is crucial. © 2025 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement.

关键词： Photodetectors

来源：评论

学校读者我要写书评

暂无评论

Using Combined Knapsack and Shortest Path Problems for Planning Optimal Navigation Paths for Robotic Deliveries 10

Using Combined Knapsack and Shortest Path Problems for Plann...

引用

10th International Conference on Automation, Robotics, and Applications, ICARA 2024

作者： Voloch, Nadav Zadok, Yair Voloch-Bloch, Noa Hajaj, Maor Meir Ruppin Academic Center Computer Engineering department Emek Hefer Israel Achva Academic College Information Systems department Shikmim Israel Ruppin Academic Center Electrical Engineering department Emek Hefer Israel University of Haifa Information Systems department Haifa Israel

ISBN: (纸本)9798350394245

Today., the use of robotic navigational tools is widely used both in academical research and the technological industry., there is a growing need for planning paths of navigation to autonomous machines., robots and transportation vehicles. In this paper we relate to a specific problem in which the robot has to navigate between several points of delivery., every point contains several items that all have different weights and different values. There are two widely researched problems in computer science algorithms., namely the knapsack problem and the shortest paths on weighted graphs problem. Typically., dynamic programming solutions for the knapsack problem involve using the shortest path problem and creating a knapsack graph. However., this approach only considers the weight and value of each item or vertex. In our case., we introduce a different problem where we consider three properties: item weight., item value., and edge weight (which connects two items but is not dependent on its vertices). Each vertex in this particular graph represents a set of knapsack items. This scenario is applicable to real-life situations where a path has a non-dependent attribute (such as physical distance or travel time) and various types of items need to be selected at different locations along this path. The problem we address here is finding the most efficient path between two vertices (source and target) based on three aspects: minimal edge weight., maximum knapsack value., or a combination of both properties. We present an algorithm for finding these optimal paths., along with detailed explanations of its decision-making process and implementation. © 2024 IEEE.

关键词： Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Stochastic physics-Informed Deep Generative Network Scenario Generation: Application on Responsive Residential Load Management

Stochastic Physics-Informed Deep Generative Network Scenario...

引用

2023 IEEE International Conference on Energy Technologies for Future Grids, ETFG 2023

作者： Afrasiabi, Mousa Afrasiabi, Shahabodin Allahmoradi, Sarah Aghaei, Jamshid Chung, C.Y. University of Saskatchewan Department of Electrical and Computer Engineering Saskatoon Canada Lappeenranta University of Technology School of Energy Systems Department of Electrical Engineering Lappeenranta Finland Central Queensland University School of Engineering and Technology Department of Electrical Engineering Rockhampton Australia The Hing Kong Polytechnic University Department of Electrical Engineering Hong Kong

ISBN: (纸本)9781665471640

This paper introduces a stochastic model for the optimal residential responsive loads power scheduling considering participants' satisfaction. In this context, firstly, a physical-informed based generative adversarial network (PI-GAN) network is designed for scenario generation with a high correlation with the actual data. In this network, conventional GANs are improved to learn spatial-temporal features of the residential loads and physics-informed concepts. To realize the spatial feature of the complex and highly nonlinear time series like residential loads, a residual convolutional neural network (Res-CNN) is considered to learn the spatial features, while the fully temporal features are realized by gated recurrent neural networks (GNN). Then, generated scenarios are used to cover the uncertainty associated with residential loads and provide the optimal results for responsive loads, including shiftable and curtailable loads. The numerical results on actual data in London, England, verify the effectiveness of the proposed stochastic framework and superiority by comparison with conditional GAN and improved version of GAN in scenario generations impact of stochastic demand response program. © 2023 IEEE.

关键词： Demand response gated recurrent neural network physics-informed based generative adversarial network residual convolutional neural network scenario-generation

来源：评论

学校读者我要写书评

暂无评论

Machine learning electron-phonon interactions in two-dimensional semiconducting materials: The case of zero-point renormalization

引用

Physical Review Materials 2024年第10期8卷 L101001页

作者： Anubhab Haldar Quentin Clark Marios Zacharias Feliciano Giustino Sahar Sharifzadeh Department of Electrical and Computer Engineering Department of Philosophy Oden Institute for Computational Engineering and Sciences Department of Physics Division of Materials Science and Engineering

We utilize first-principles theory to investigate the role of electron-phonon interactions within a dataset of monolayer materials. Using density functional theory to describe excited-state transitions and the special displacement method to describe the role of phonons, we analyze the relationship between simple physical observables and electron-phonon coupling strength. For over 100 materials, we compute the band gap renormalization due to zero-point vibrational (ZPR) motion as a measure of electron-phonon interactions and train a machine learning model based on physical parameters. We demonstrate that the strength of electron-phonon interactions is highly dependent on the band gap, dielectric constant, and degree of ionicity, all of which can be physically justified. We then apply this model to 1302 2D materials, predicting the ZPR, which for five randomly selected materials tested agree well with the first-principles predictions. This work provides an approach for quantitatively predicting the ZPR as a measure of electron-phonon interactions in 2D materials.

关键词： Electron-phonon coupling Electronic structure 2-dimensional systems Machine learning

来源：评论

学校读者我要写书评

暂无评论

Experimental measurement and numerical modeling of deformation behavior of breast cancer cells passing through constricted microfluidic channels

引用

Microsystems & Nanoengineering 2024年第1期10卷 129-147页

作者： Pouyan Keshavarz Motamed Hesam Abouali Mahla Poudineh Nima Maftoon Department of Systems Design Engineering University of WaterlooWaterlooON N2L 3G1Canada Center for Bioengineering and Biotechnology University of WaterlooWaterlooON N2L 3G1Canada Department of Electrical and Computer Engineering University of WaterlooWaterlooON N2L 3G1Canada

During the multistep process of metastasis,cancer cells encounter various mechanical forces which make them deform *** accurate in-silico models,capable of simulating the interactions between the mechanical forces and highly deformable cancer cells,can pave the way for the development of novel diagnostic and predictive methods for metastatic ***-network models of cancer cell,empowered by our recently proposed identification approach,promises a versatile numerical tool for developing experimentally validated models that can simulate complex interactions at cellular *** this numerical tool,we presented spring-network models of breast cancer cells that can accurately replicate the experimental data of deformation behavior of the cells flowing in a fluidic domain and passing narrow constrictions comparable to ***,using high-speed imaging,we experimentally studied the deformability of breast cancer cell lines with varying metastatic potential(MCF-7(less invasive),SKBR-3(medium-high invasive),and MDA-MB-231(highly invasive)in terms of their entry time to a constricted microfluidic *** observed that MDA-MB-231,that has the highest metastatic potential,is the most deformable cell among the ***,by focusing on this cell line,experimental measurements were expanded to two more constricted microchannel *** experimental deformability data in three constricted microchannel sizes for various cell sizes,enabled accurate identification of the unknown parameters of the spring-network model of the breast cancer cell line(MDA-MB-231).Our results show that the identifed parameters depend on the cell size,suggesting the need for a systematic procedure for identifying the size-dependent parameters of spring-network models of *** the numerical results show,the presented cell models can simulate the entry process of the cell into constricted channels with very good agreements with the measured experimen

关键词： strict passing numerical

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Based Analysis of Cyber-Attacks Targeting Smart Grid Infrastructure 2nd

Machine Learning Based Analysis of Cyber-Attacks Targeting S...

引用

2nd International Conference on Advances in Computing Research, ACR 2024

作者： Nijim, Mais Kanumuri, Viswas Al Aqqad, Waseem Albataineh, Hisham Department of Electrical Engineering and Computer Science Texas A&M University-Kingsville KingsvilleTX United States Department of Electrical and Computer Engineering West Virginia Tech BeckleyWV United States Department of Physics and Geosciences Texas A&M University-Kingsville KingsvilleTX United States

ISBN: (纸本)9783031569494

The transformation of traditional electric power systems into smart grids has allowed for improved monitoring and control capabilities. However, this evolution has also brought about new challenges in the form of malware and vulnerabilities, creating significant security concerns. To address this issue, sensors are being deployed to the grid, leading to a large influx of data that needs to be analyzed for accurate results. Machine learning algorithms are being utilized to process this data and extract important information. This paper explores the application of various machine learning algorithms in smart grids, with a specific focus on their use in cybersecurity. We identify different types of cyber threats affecting smart grids and examine defense strategies to counter these threats. Through this study, we provide insights into the potential of machine learning in addressing the cybersecurity challenges in smart grids. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Extending Topological Edge States to Visible Wavelengths in a Silicon Nitride Ring-Resonator Lattice

Extending Topological Edge States to Visible Wavelengths in ...

引用

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

作者： Sharp, David Flower, Christopher Manna, Arnab Rarick, Hannah Mehrabad, Mahmoud Jalali Chen, Rui Hafezi, Mohammad Majumdar, Arka Department of Physics University of Washington SeattleWA98189 United States Department of Electrical Engineering University of Maryland College ParkMD20742 United States Department of Electrical and Computer Engineering University of Washington SeattleWA98189 United States

Previous work in topological ring-resonator lattices has focused on infrared wavelengths where imaging technology is limited. In this work, this concept is extended to the visible regime with a silicon nitride platfor... 详细信息

ISBN: (纸本)9781957171395

关键词： Silicon nitride

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：