检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Liu, Xueqing Zhang, Yuhui Ytterdal, Trond Shur, Michael The Department of Electrical Computer and Systems Engineering Rensselaer Polytechnic Institute 110 8th Street Troy NY12180 United States The Department of Electronic Systems Norwegian University of Science and Technology Trondheim7491 Norway

This paper presents an improved compact model for TeraFETs employing a nonlinear transmission line approach to describe the non-uniform carrier density oscillations and electron inertia effects in the TeraFET channels. By calculating the equivalent components for each segment of the channel—conductance, capacitance, and inductance—based on the voltages at the segment's nodes, our model accommodates non-uniform variations along the channel. We validate the efficacy of this approach by comparing terahertz (THz) response simulations with experimental data and MOSA1, EKV TeraFET SPICE models, analytical theories, and Multiphysics simulations. © 2024, CC BY-NC-ND.

关键词： Terahertz wave detectors

来源：评论

学校读者我要写书评

暂无评论

Securing Smart Grids: Deep Reinforcement Learning Approach for Detecting Cyber-Attacks

Securing Smart Grids: Deep Reinforcement Learning Approach f...

引用

International Conference on Smart Communications and Networking (SmartNets)

作者： Ahmed T. El-Toukhy Islam Elgarhy Mahmoud M. Badr Mohamed Mahmoud Mostafa M. Fouda Mohamed I. Ibrahem Fathi Amsaad Department of Electrical and Computer Engineering Tennessee Tech. University Cookeville TN USA Department of Electrical Engineering Faculty of Engineering Al-Azhar University Cairo Egypt Department of Computer Systems Faculty of Computer and Information Sciences Ain Shams University Egypt Department of Network and Computer Security: Cybersecurity SUNY Polytechnic Institute Utica NY USA Department of Electrical Engineering Faculty of Engineering at Shoubra Benha University Cairo Egypt Department of Electrical and Computer Engineering Idaho State University Pocatello ID USA Center for Advanced Energy Studies (CAES) Idaho Falls ID USA School of Computer and Cyber Sciences Augusta University Augusta GA USA Department of Computer Science and Engineering Wright State University Dayton OH USA

ISBN: (数字)9798350385328

ISBN: (纸本)9798350385335

Smart meters (SMs) are deployed in smart power grids to monitor customer power consumption and facilitate energy management. However, fraudulent customers can compromise these SMs to manipulate power readings and engage in electricity theft cyber-attacks, resulting in reduced electricity bills. While various machine learning approaches have been employed for detecting such attacks, the potential of reinforcement learning (RL) remains unexplored. To bridge this gap, we propose a deep reinforcement learning (DRL) approach that leverages RL's adapt-ability to dynamic cyber-attacks and consumption patterns. This approach integrates exploration and exploitation mechanisms, enabling optimal decision-making. In this study, we present our approach in two scenarios. Firstly, we develop comprehensive detection models using deep Q networks (DQN) and double deep Q networks (DDQN) with various deep neural network architectures. Secondly, we address the challenges of defending against newly launched cyber-attacks. Extensive experimentation provides strong evidence of the effectiveness of our DRL approach in improving the detection of electricity theft cyber-attacks, as well as its capacity to efficiently adapt and defend against newly launched cyber-attacks.

关键词： Adaptation models Power demand Electricity Power system dynamics Detectors Deep reinforcement learning Smart meters

来源：评论

学校读者我要写书评

暂无评论

Simulation Framework for Vehicle and Electric Scooter Interaction

Simulation Framework for Vehicle and Electric Scooter Intera...

引用

International Conference on Intelligent Transportation

作者： Zhitong He Lingxi Li Department of Electrical and Computer Engineering Transportation and Autonomous Systems Institute (TASI) Indiana University-Purdue University Indianapolis Indianapolis Indiana USA

The number of shared micro-mobility services such as electric scooters (e-scooters) has an increasing trend due to the advantages of high efficiency and low cost in short-range travel in urban areas. However, due to the unique characteristics of moving behavior, it is commonly seen that e-scooters may share the road with other motor vehicles. The lack of protection may lead to severe injury for e-scooter riders. The scenario where an e-scooter crosses an intersection or makes a lane change while interacting with an approaching vehicle was commonly seen in real-life traffic data. Such scenarios are hazardous because the intention and behavior of the e-scooter may vary significantly based on the traffic environment conditions. Furthermore, some other vehicles may occlude the presence of the moving e-scooter, which can result in an unexpected collision. In this paper, we propose a simulation platform to mimic the interactions between vehicles and e-scooters. Several traffic scenarios are studied via qualitative and quantitative analysis. The proposed framework is shown to be valuable and efficient for the general risk analysis for vehicle and e-scooter interactions (VEI).

关键词：

来源：评论

学校读者我要写书评

暂无评论

KGNet: Knowledge-Guided Networks for Category-Level 6D Object Pose and Size Estimation

KGNet: Knowledge-Guided Networks for Category-Level 6D Objec...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Qiwei Meng Jason Gu Shiqiang Zhu Jianfeng Liao Tianlei Jin Fangtai Guo Wen Wang Wei Song Zhejiang Lab Research Center for Intelligent Robotics Research Institute of Interdis-ciplinary Innovation Hangzhou China Zhejiang Engineering Research Center for Intelligent Robotics Hangzhou China Department of Electrical and Computer Engineering Dalhousie University Halifax NS Canada

Despite the giant leap made in object 6D pose estimation and robotic grasping under structured scenarios, most approaches depend heavily on the exact CAD models of target objects beforehand, thereby limiting their wide applications. To address this, we propose a novel knowledge-guided network - KGNet to estimate the pose and size of category-level unseen objects. This network includes three primary innovations: knowledge-guided categorical model generation, pointwise deformation probability matrix and synergetic RGBD feature fusion, with the former two leveraging categorical object knowledge for unseen object reconstruction and the latter one facilitating pose-sensitive feature extraction. Exten-sive experiments on CAMERA25 and REAL275 verify their effectiveness, and KGNet achieves the SOTA performance on these two acknowledged benchmarks. Additionally, a real-world robotic grasping experiment is conducted, and its results further qualitatively prove the practicability and robustness of KGNet.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Phaseless Imaging via Wirtinger Flow with Decoding Prior

Deep Phaseless Imaging via Wirtinger Flow with Decoding Prio...

引用

Asilomar Conference on Signals, systems & computers

作者： Samia Kazemi Bariscan Yonel Birsen Yazici Department of Electrical Computer and Systems Engineering Rensselaer Polytechnic Institute Troy NY USA

We introduce a deep learning (DL) based network for imaging from intensity-only measurements using low dimensional encoded representations. Phaseless imaging constitutes a non-convex and ill-posed problem that is relevant to a wide range of applications, where accurate measurement of phase information is challenging. State-of-the-art methods solve the original non-convex optimization problem using sophisticated initialization schemes that lead to locally benign loss function topographies. However, these are commonly contingent upon high sample complexity and restrictive conditions on the forward maps, which limit their practical applicability. To circumvent fundamental limitations, we utilize a model-based deep network for phaseless imaging that implements a fixed-step size realization of gradient descent directly on the lower dimensional encoded representation domain. Accordingly, the iterative algorithm is combined with a non-linear encoder-decoder pair that govern the mapping between low dimensional representations and the image manifold of our interest. This results in feasible regimes beyond those dictated by the standard sufficient conditions of the exact recovery theory used in non-convex optimization. We empirically demonstrate the effectiveness of our lower dimensional formulation of signal recovery through numerical simulations on a number of practical deterministic imaging geometries at reduced sample complexities.

关键词： Manifolds Training Sufficient conditions Imaging Surfaces Complexity theory Decoding

来源：评论

学校读者我要写书评

暂无评论

Tree Reconstruction Guarantees from CRISPR-Cas9 Lineage Tracing Data Using Neighbor-Joining 29th

Tree Reconstruction Guarantees from CRISPR-Cas9 Lineage Tra...

引用

29th International Conference on Research in Computational Molecular Biology, RECOMB 2025

作者： Prillo, Sebastian An, Kevin Wu, Wilson Kristanto, Ivan Jones, Matthew G. Song, Yun S. Yosef, Nir Department of Electrical Engineering and Computer Sciences University of California Berkeley BerkeleyCA94720 United States Department of Systems Immunology Weizmann Institute of Science Rehovot7610001 Israel Department of Statistics University of California Berkeley BerkeleyCA94720 United States Department of Molecular and Cell Biology University of California Berkeley BerkeleyCA94720 United States Center for Personal Dynamic Regulomes Stanford University StanfordCA94305 United States

ISBN: (纸本)9783031902512

CRISPR-Cas9 based lineage tracing technologies have enabled the reconstruction of single-cell phylogenies from transcriptional readouts. However, developing tree-reconstruction algorithms with theoretical guarantees in this setting is challenging. In this work, we derive a reconstruction algorithm with theoretical guarantees using Neighbor-Joining (NJ) on distances that are moment-matched to estimate the true tree distances. We develop a series of tools to analyze this algorithm and prove its theoretical guarantees. Empirically, we show on both simulated lineage tracing data and on real data from a mouse model of lung cancer the improved performance of our method as compared to the traditional use of NJ. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AN ADDRESSABLE ELECTROWETTING VALVE FOR CENTRIFUGAL MICROFLUIDICS 26

AN ADDRESSABLE ELECTROWETTING VALVE FOR CENTRIFUGAL MICROFLU...

引用

26th International Conference on Miniaturized systems for Chemistry and Life Sciences, MicroTAS 2022

作者： Xia, Yanming Song, Chao Meng, Yingchao Xue, Peng deMello, Andrew J. Gao, Quan Stavrakis, Stavros Ma, Shenglin Cao, Xiaobao Department of Mechanical & Electrical Engineering Xiamen University Xiamen China Institute for Chemical and Bioengineering ETH Zürich Zürich8093 Switzerland Institute of Robotics and Intelligent Systems ETH Zürich Zürich8006 Switzerland Guangzhou Laboratory Guangdong Guangzhou510320 China

ISBN: (纸本)9781733419048

This paper presents and assesses an addressable electrowetting centrifugal (EWC) valve, which can rapidly and selectively open through (remote) control of the applied electric field. The utility of EWC valves is showcased by the implementation of fluid complexly controlling and CD4 cell antigens detection. © 2022 MicroTAS 2022 - 26th International Conference on Miniaturized systems for Chemistry and Life Sciences. All rights reserved.

关键词： Wetting

来源：评论

学校读者我要写书评

暂无评论

FRAME: Fast and Robust Autonomous 3D Point Cloud Map-Merging for Egocentric Multi-Robot Exploration

FRAME: Fast and Robust Autonomous 3D Point Cloud Map-Merging...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Nikolaos Stathoulopoulos Anton Koval Ali-akbar Agha-mohammadi George Nikolakopoulos Department of Computer Electrical and Space Engineering Robotics and AI Group Luleå University of Technology Luleå Sweden Jet Propulsion Laboratory California Institute of Technology Pasadena CA

This article presents a 3D point cloud map-merging framework for egocentric heterogeneous multi-robot exploration, based on overlap detection and alignment, that is independent of a manual initial guess or prior knowledge of the robots' poses. The novel proposed solution utilizes state-of-the-art place recognition learned descriptors, that through the framework's main pipeline, offer a fast and robust region overlap estimation, hence eliminating the need for the time-consuming global feature extraction and feature matching process that is typically used in 3D map integration. The region overlap estimation provides a homogeneous rigid transform that is applied as an initial condition in the point cloud registration algorithm Fast-GICP, which provides the final and refined alignment. The efficacy of the proposed framework is experimentally evaluated based on multiple field multi-robot exploration missions in underground environments, where both ground and aerial robots are deployed, with different sensor configurations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Development of a UAV-based System for Technical Diagnostics of Overhead Power Lines 24

Development of a UAV-based System for Technical Diagnostics ...

引用

24th International Conference on Computational Problems of electrical engineering, CPEE 2023

作者： Kozlovskyi, Oleksandr Trushakov, Dmitro Rendzinyak, Serhiy Korud, Vasyl Central Ukrainian National Technical University Department of Electrical Systems and Energy Management Kropyvnytskyi Ukraine Central Ukrainian National Technical University Department of Automation and Control in Technical Systems Kropyvnytskyi Ukraine Ivan Franko National University of Lviv Faculty of Electronics and Computer Technologies Lviv Ukraine Lviv Polytechnic National University Institute of Power Engineering and Control System Lviv Ukraine

ISBN: (纸本)9798350330342

The problems associated with the operation of overhead power lines and ways of improving control over their condition with the help of UAVs are considered. A structural diagram of the system of technical diagnostics of overhead lines based on UAVs was developed, for which the necessary diagnostic parameters were selected according to informative criteria. An analysis of types of UAVs was carried out in order to determine their suitability and efficiency of use for diagnosing the condition of overhead lines. © 2023 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Spatio-Temporal Hybrid Fusion of CAE and SWin Transformers for Lung Cancer Malignancy Prediction

Spatio-Temporal Hybrid Fusion of CAE and SWin Transformers f...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Sadaf Khademi Shahin Heidarian Parnian Afshar Farnoosh Naderkhani Anastasia Oikonomou Konstantinos N. Plataniotis Arash Mohammadi Concordia Institute for Information Systems Engineering Concordia University Montreal Canada Department of Electrical and Computer Engineering Concordia University Montreal Canada Department of Medical Imaging Sunnybrook Health Sciences Centre Toronto Canada Department of Electrical and Computer Engineering University of Toronto Toronto Canada

The paper proposes a novel hybrid discovery Radiomics framework that simultaneously integrates temporal and spatial features extracted from non-thin chest Computed Tomography (CT) slices to predict Lung Adenocarcinoma (LUAC) malignancy with minimum expert involvement. Lung cancer is the leading cause of mortality from cancer worldwide and has various histologic types, among which LUAC has recently been the most prevalent. LUACs are classified as pre-invasive, minimally invasive, and invasive adenocarcinomas. Timely and accurate knowledge of the lung nodules malignancy leads to a proper treatment plan and reduces the risk of unnecessary or late surgeries. Currently, chest CT scan is the primary imaging modality to assess and predict the invasiveness of LUACs. However, the radiologists’ analysis based on CT images is subjective and suffers from a low accuracy compared to the ground truth pathological reviews provided after surgical resections. The proposed hybrid framework, referred to as the CAET-SWin, consists of two parallel paths: (i) The Convolutional Auto-Encoder (CAE) Transformer path that extracts and captures informative features related to inter-slice relations via a modified Transformer architecture, and; (ii) The Shifted Window (SWin) Transformer path, which is a hierarchical vision transformer that extracts nodules’ related spatial features from a volumetric CT scan. Extracted temporal (from the CAET path) and spatial (from the SWin path) are then fused through a fusion path to classify LUACs. Experimental results on our in-house dataset of 114 pathologically proven SubSolid Nodules (SSNs) demonstrate that the CAET-SWin significantly improves reliability of the invasiveness prediction task while achieving an accuracy of 82.65%, sensitivity of 83.66%, and specificity of 81.66% using 10-fold cross-validation.

关键词： Sensitivity Three-dimensional displays Computed tomography Lung Lung cancer Feature extraction Transformers

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：