检索结果-内蒙古大学图书馆

Proceedings of the 41st International Conference on Machine Learning

作者： Yunke Wang Minjing Dong Yukun Zhao Bo Du Chang Xu School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence and Wuhan Institute of Data Intelligence Wuhan University China Department of Computer Science City University of Hong Kong China School of Computer Science Faculty of Engineering The University of Sydney Australia

Imitation learning has emerged as a promising approach for addressing sequential decision-making problems, with the assumption that expert demonstrations are optimal. However, in real-world scenarios, most demonstrations are often imperfect, leading to challenges in the effectiveness of imitation learning. While existing research has focused on optimizing with imperfect demonstrations, the training typically requires a certain proportion of optimal demonstrations to guarantee performance. To tackle these problems, we propose to purify the potential noises in imperfect demonstrations first, and subsequently conduct imitation learning from these purified demonstrations. Motivated by the success of diffusion model, we introduce a two-step purification via diffusion process. In the first step, we apply a forward diffusion process to smooth potential noises in imperfect demonstrations by introducing additional noise. Subsequently, a reverse generative process is utilized to recover the optimal demonstration from the diffused ones. We provide theoretical evidence supporting our approach, demonstrating that the distance between the purified and optimal demonstration can be bounded. Empirical results on MuJoCo and RoboSuite demonstrate the effectiveness of our method from different aspects.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Asymptotic Leader-Following With Continuous Control Inputs in Networked Euler-Lagrangian Systems: The Case of Directed Topologies

引用

IEEE Transactions on Control of Network Systems 2025年

作者： Rezaee, Hamed Parisini, Thomas Polycarpou, Marios M. Imperial College London Department of Mechanical Engineering LondonSW7 2AZ United Kingdom Imperial College London Department of Electrical and Electronic Engineering LondonSW7 2AZ United Kingdom Aalborg University Department of Electronic Systems Denmark University of Trieste Department of Engineering and Architecture Italy University of Cyprus KIOS Research and Innovation Center of Excellence Department of Electrical and Computer Engineering NicosiaCY-1678 Cyprus

In most practical dynamic leader-following scenarios, the control input or dynamical model of the neighboring agents are not known to the followers. In such scenarios, asymptotic leader-following requires employing discontinuous robust mechanisms to cope with unknown parts of the neighbors trajectories, leading to chattering in the followers inputs. Few studies already addressed asymptotic leader-following with continuous control inputs;however, they require the communication topology to be undirected, which is a restrictive assumption in leader-following. In this paper, asymptotic dynamic leader-following in Euler-Lagrangian multiagent systems is addressed. We assume that the leader control input is determined by the leader locally and is unknown to the followers. The contribution of this paper is that whereas the unknown input and model of the neighboring agents are compensated by a robust mechanism in the followers control strategy, the continuity in the followers control inputs is guaranteed and the interaction in the network is under directed topologies. Simulation results for a network of manipulator robots illustrate the performance of the proposed control strategy. © 2014 IEEE.

关键词： Lagrange multipliers

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning Approach for Detecting GPS Location Spoofing Attacks in Autonomous Vehicles

A Machine Learning Approach for Detecting GPS Location Spoof...

引用

IEEE Conference on Vehicular Technology (VTC)

作者： S. Filippou A. Achilleos S. Z. Zukhraf C. Laoudias K. Malialis M. K. Michael G. Ellinas KIOS Research and Innovation Center of Excellence University of Cyprus Nicosia Cyprus Department of Electrical and Computer Engineering University of Cyprus Nicosia Cyprus

Connected and Autonomous Vehicles (CAV) depend on satellite systems, such as the Global Positioning System (GPS), for location awareness. Location data are streamed in real-time to the CAV’s perception engine from its onboard GPS receiver for autonomous driving and navigation. However, these receivers are vulnerable to location spoofing attacks that can be easily launched using Commercial-Off-The-Self (COTS) equipment and open-source software. Existing data-driven attack detection solutions typically require data associated with ‘normal’ and ‘attack’ labels. The latter are hard to collect in operational conditions or even in controlled experiments. To this end, we formulate the GPS location spoofing attack detection as an outlier detection problem. The proposed solution based on Machine Learning (ML) relies solely on normal location data for training during attack-free operation. Our solution demonstrates more than 98% detection accuracy according to standard metrics on realistic data produced with the CARLA driving simulator and outperforms by 15% another (non ML-based) state-of-the-art solution.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Metasurface Superstrate for 5G Bandwidth and Gain Enhancement

Metasurface Superstrate for 5G Bandwidth and Gain Enhancemen...

引用

2022 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting, AP-S/URSI 2022

作者： Bilal, Asif Quddious, Abdul Votsi, Haris Kanno, Atsushi Kawanishi, Tetsuya Antoniades, Marco A. Iezekiel, Stavros University of Cyprus EMPHASIS Research Centre Nicosia Cyprus University of Cyprus Department of Electrical and Computer Engineering Nicosia Cyprus University of Cyprus KIOS Research Center for Excellence Nicosia Cyprus National Institute of Information and Communications Technology Tokyo Japan Waseda University Tokyo Japan Ryerson University Department of Electrical Computer & Biomedical Engineering TorontoON Canada

ISBN: (数字)9781665496582

ISBN: (纸本)9781665496582

This paper discusses a dual-layer metasurface (MSF) superstrate, consisting of double split-ring resonator cells in the 28 GHz 5G mm-wave frequency band. The MSF superstrate is added above a conventional patch antenna, and an enhancement in the performance of the patch antenna in terms of bandwidth and gain is achieved. This is due to the negative index metamaterial (NIM) properties of the designed MSF superstrate. In this design, the impedance bandwidth is improved from 2.6 GHz to 3.6 GHz, while the gain of the patch antenna is increased from 6.59 dBi to 12.9 dBi. The simplicity of the design to achieve a higher gain and broader bandwidth makes it a suitable candidate for applications in 5G mm-wave communications. © 2022 IEEE.

关键词： Microstrip antennas

来源：评论

学校读者我要写书评

暂无评论

Model Predictive Control For Multiple Castaway Tracking with an Autonomous Aerial Agent

Model Predictive Control For Multiple Castaway Tracking with...

引用

European Control Conference (ECC)

作者： Andreas Anastasiou Savvas Papaioannou Panayiotis Kolios Christos G. Panayiotou KIOS Research and Innovation Center of Excellence (KIOS CoE) Nicosia Cyprus Department of Electrical and Computer Engineering University of Cyprus Nicosia Cyprus

Over the past few years, a plethora of advancements in Unmanned Areal Vehicle (UAV) technology has paved the way for UAV-based Search and Rescue (SAR) operations with transformative impact to the outcome of critical life-saving missions. This paper dives into the challenging task of multiple castaway tracking using an autonomous UAV agent. Leveraging on the computing power of the modern embedded devices, we propose a Model Predictive Control (MPC) framework for tracking multiple castaways assumed to drift afloat in the aftermath of a maritime accident. We consider a stationary radar sensor that is responsible for signaling the search mission by providing noisy measurements of each castaway’s initial state. The UAV agent aims at detecting and tracking the moving targets with its equipped onboard camera sensor that has limited sensing range. In this work, we also experimentally determine the probability of target detection from real-world data by training and evaluating various Convolutional Neural Networks (CNNs). Extensive qualitative and quantitative evaluations demonstrate the performance of the proposed approach.

关键词：

来源：评论

学校读者我要写书评

暂无评论

60 GHz mmWave Metasurface Superstrate for Gain and Bandwidth Improvement 3

60 GHz mmWave Metasurface Superstrate for Gain and Bandwidth...

引用

3rd URSI Atlantic and Asia Pacific Radio Science Meeting, AT-AP-RASC 2022

作者： Bilal, Asif Quddious, Abdul Kanno, Atsushi Kawanishi, Tetsuya Antoniades, Marco A. Iezekiel, Stavros University of Cyprus Emphasis Research Centre Nicosia Cyprus University of Cyprus Department of Electrical and Computer Engineering Nicosia Cyprus University of Cyprus Kios Research Center for Excellence Nicosia Cyprus National Institute of Information and Communications Technology Tokyo Japan Waseda University Tokyo Japan Ryerson University Department of Electrical Computer & Biomedical Engineering TorontoON Canada

ISBN: (纸本)9789463968058

A multi-layer structure designed for the 60 GHz mm-wave frequency band is presented. The design consists of an antenna element on the substrate and a split ring resonator (SRR) metasurface on the superstrate. With the addition of the metasurface superstrate layer, an improved performance of the antenna in terms of gain and bandwidth is achieved. These enhancements are based on the negative index metamaterial (NIM) properties of the designed metasurface sheet. In this proposed design the bandwidth is improved from 3 GHz to 4.5 GHz, while the gain of the antenna is increased from 7.87 dBi to 13.87 dBi at 60 GHz. © 2022 URSI.

关键词： Millimeter waves

来源：评论

学校读者我要写书评

暂无评论

Triple Simplex Matrix Completion for Expense Forecasting

arXiv

引用

arXiv 2023年

作者： Qian, Cheng Glass, Lucas M. Sidiropoulos, Nicholas D. The Analytics Center of Excellence IQVIA United States The Department of Electrical and Computer Engineering University of Virginia CharlottesvilleVA22904 United States

Forecasting project expenses is a crucial step for businesses to avoid budget overruns and project failures. Traditionally, this has been done by financial analysts or data science techniques such as time-series analysis. However, these approaches can be uncertain and produce results that differ from the planned budget, especially at the start of a project with limited data points. This paper proposes a constrained non-negative matrix completion model that predicts expenses by learning the likelihood of the project correlating with certain expense patterns in the latent space. The model is constrained on three probability simplexes, two of which are on the factor matrices and the third on the missing entries. Additionally, the predicted expense values are guaranteed to meet the budget constraint without the need of post-processing. An inexact alternating optimization algorithm is developed to solve the associated optimization problem and is proven to converge to a stationary point. Results from two real datasets demonstrate the effectiveness of the proposed method in comparison to state-of-the-art algorithms. © 2023, CC BY.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

CIXG: A Comprehensive Approach to Driver Gene Identification and Causal Interpretation

CIXG: A Comprehensive Approach to Driver Gene Identification...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Yawen Liu Yiwen Chen Shanling Nie Hai Yang Department of Computer Science and Engineering East China University of Science and Technology Shanghai China Shanghai Key Laboratory of Computer Software Evaluating and Testing Shanghai China Center for Continuing and Lifelong Education National University of Singapore Faculty of Engineering The University of Sydney Australia

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

With the ongoing advancements in science and technology and the increasing research focus on cancer-related issues, there has been a proliferation of omics-related resources for in-depth analysis and exploration. This burgeoning volume and complexity of biological data have fostered the integration of machine-learning techniques into biology. As a result, numerous machine-learning strategies have been established to identify driver mutations. Yet, many of these strategies produce complex models, complicating comprehension and thereby clouding the impact of input features on the resulting predictions. Our analysis presented the CIXG framework, which integrates a driver gene prediction module using XGBoost with a causality interpretation module anchored on CXPlain. This architecture enables quantifying each input feature’s contribution to the prediction outcome and ensures precise predictions of driver genes. When benchmarked against the state-of-the-art (SOTA) method, CIXG demonstrated superior accuracy in pinpointing driver genes across pan-cancer studies and within the 32 specific cancer types. Importantly, our results underscored that mutation features chiefly influence CIXG’s predictive prowess, with additional support from other omics features.

关键词： Accuracy Biological system modeling Cause effect analysis Machine learning Predictive models Benchmark testing Complexity theory Bioinformatics Cancer

来源：评论

学校读者我要写书评

暂无评论

Editorial

引用

Transportation Research Procedia 2021年 52卷 1-2页

作者： Timotheou, Stelios Panayiotou, Christos G. Kios Research and Innovation Center of Excellence Department of Electrical and Computer Engineering University of Cyprus 1 Panepistimiou Avenue Nicosia 2109 Cyprus

来源：评论

学校读者我要写书评

暂无评论

Federated Learning-Based Intelligent Indoor Smoke and Fire Detection System for Smart Buildings

Federated Learning-Based Intelligent Indoor Smoke and Fire D...

引用

2024 International Conference on Telecommunications and Intelligent Systems, ICTIS 2024

作者： Aymene Berkani, Mohamed Rafik Chouchane, Ammar Himeur, Yassine Abdennebi, Anes Sagiroglu, Seref Amira, Abbes Medea Algeria University Biskra University Center of Barika Laboratory of LI3C Amdoukal Road Barika05001 Algeria University of Dubai College of Engineering and Information Technology Dubai United Arab Emirates École de Technologie Supérieure Software and Information Technology Engineering Montréal Canada Analytics Security R&D Center Gazi University Artificial Intelligence and Big Data Ankara Turkey University of Sharjah Department of Computer Science Sharjah United Arab Emirates

ISBN: (纸本)9798331527396

Ensuring safety in smart buildings is crucial due to the increasing prevalence of smoke and fire hazards in modern environments. This paper introduces a novel privacy-preserving FL approach based on a CNN1D for smoke and fire detection in smart buildings. Our system integrates data from wearable environmental sensors to train a lightweight, edge-deployable DL-CNN1D model, ensuring data privacy while enabling collaborative learning across distributed clients using Federated Averaging (FedAvg) aggregation. Experiments conducted on a comprehensive air measurement dataset for smoke and fire detection demonstrate exceptional performance, with the global model achieving 99.97% accuracy, 99.96% precision, in smoke and fire recognition. Our model demonstrates a low communication cost of 0.4 MB, underscoring its efficiency for real-time applications. Our FL-based approach represents a significant step towards balancing the need for robust safety systems with growing privacy concerns in smart building environments. © 2024 IEEE.

关键词： Federated learning

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：