检索结果-内蒙古大学图书馆

9th IEEE International Conference on Progress in Informatics and Computing, PIC 2024

作者： Yang, Ke Feng, Jingyun Xi, Zhiyu Zheng, Qiuke Zhang, Huan Deng, Wei China Railway Eryuan Engineering Group Co. Ltd. Chengdu China Southern University of Science and Technology Dept. of Statistics Shenzhen China School of Automation Science and Electrical Engineering Beihang University Beijing China School of Computer Science and Artificial Intelligence Southwestern University of Finance and Economics Chengdu China School of Statistics Southwestern University of Finance and Economics Chengdu China Chongqing University of Posts and Telecommunications Chongqing Key Laboratory of Computational Intelligence Chongqing China

ISBN: (纸本)9798350363203

The structure of knowledge graph is basically flat and lack of hierarchies to make knowledge graph too general to deal with concrete reasoning problems. There are few work about hierarchical knowledge graph. In this paper, the entity and relation combined method is proposed to divide the entities into groups based on structure similarity. The hierarchical cluster method is proposed with the entity and relation combined embedding representation to construct a multi-granular knowledge graph. The experimental results show that the hierarchical division relied on combined embedding are significantly better than those based on the existing entity embedding methods in three evaluation indexes. The combined embedding can capture the structure information which is helpful to hierarchical knowledge graph accurately and reasonably. © 2024 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Dynamic Spectrum Access in Non-stationary Environments: A DRL-LSTM Integrated Approach

Dynamic Spectrum Access in Non-stationary Environments: A DR...

引用

International Conference on Computing, Networking and Communications (ICNC)

作者： Mingjie Feng Wenhan Zhang Marwan Krunz Wuhan National Laboratory for Optoelectronics Huazhong University of Science ampersand Technology Wuhan China Dept. Electrical ampersand Computer Engineering The University of Arizona Tucson AZ USA

In this paper, we investigate the problem of dynamic spectrum access (DSA) in non-stationary environments, Where secondary users (SUs) and primary users (PUs) operate over a shared set of orthogonal channels. The non-stationarity is caused by the time-varying PU activity and the coupled channel access strategies of different SUs. Considering such non-stationarity and the channel dynamics, the DSA problem is formulated as a hidden-mode Markov Decision Process (HMMDP), Which can be decomposed into multiple MDPs under different modes. At each time, one of the modes is active, each mode corresponds to a unique MDP. The HMMDP is solved when the active mode is determined and the MDP under this mode is solved. We first propose a deep reinforcement learning (DRL) framework for solving the MDP under a given mode. We then propose a long short-term memory (LSTM)-based approach to predict the active mode at each time slot. Simulation results show that the proposed scheme outperforms benchmark schemes by achieving significantly fewer collisions and improved spectrum utilization.

关键词： Deep learning Simulation Dynamic spectrum access Hidden Markov models Reinforcement learning Markov processes Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

Evaluating NGBoost as a Model for Probabilistic Prediction for V-Band Power Attenuation

Evaluating NGBoost as a Model for Probabilistic Prediction f...

引用

Antennas and Propagation Society International Symposium

作者： Ralph L. Gesner Christos G. Christodoulou Steven A. Lane The Dept. of Electrical & Computer Engineering The University of New Mexico Albuquerque NM USA Airforce Research Laboratory Space Vehicles Directorate Kirtland AFB Albuquerque NM USA

A novel application of probabilistic prediction for estimating mm-wave attenuation due to varying weather conditions is developed. Validation of atmospheric propagation models in the W/V-bands has progressed greatly in past years, but the confidence of their predictions has not been validated. The Natural Gradient Boosting (NGBoost) algorithm is tested against a deep neural network to estimate atmospheric attenuation on a 72 GHz terrestrial link and to demonstrate the ability to produce prediction confidence estimates.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Timely Target Tracking: Distributed Updating in Cognitive Radar Networks

arXiv

引用

arXiv 2023年

作者： Howard, William W. Martone, Anthony F. Buehrer, R. Michael Bradley Dept. of Electrical and Computer Engineering Virginia Tech BlacksburgVA24060 United States DEVCOM Army Research Laboratory AdelphiMD20783 United States

Cognitive radar networks (CRNs) are capable of optimizing operating parameters in order to provide actionable information to an operator or secondary system. CRNs have been proposed to answer the need for low-cost devices tracking potentially large numbers of targets in geographically diverse regions. Networks of small-scale devices have also been shown to outperform legacy, large scale, high price, single-device installations. In this work, we consider a CRN tracking multiple targets with a goal of providing information which is both fresh and accurate to a measurement fusion center (FC). We show that under a constraint on the update rate of each radar node, the network is able to utilize Age of Information (AoI) metrics to maximize the resource utilization and minimize error per track. Since information freshness is critical to decision-making, this structure enables a CRN to provide the highest-quality information possible to a downstream system or operator. We discuss centralized and distributed approaches to solving this problem, taking into account the quality of node observations, the maneuverability of each target, and a limit on the rate at which any node may provide updates to the FC. We present a centralized AoI-inspired node selection metric, where a FC requests updates from specific nodes. We compare this against several alternative techniques. Further, we provide a distributed approach which utilizes the Age of Incorrect Information (AoII) metric, allowing each independent node to provide updates according to the targets it can observe. We provide mathematical analysis of the rate limits defined for the centralized and distributed approaches, showing that they are equivalent. We conclude with numerical simulations demonstrating that the performance of the algorithms exceeds that of alternative approaches, both in resource utilization and in tracking performance. Copyright © 2023, The Authors. All rights reserved.

关键词： Target tracking

来源：评论

学校读者我要写书评

暂无评论

Factorization Machine Learning for Disaggregation of Transmission Load Profiles with High Penetration of Behind-the-Meter Solar

Factorization Machine Learning for Disaggregation of Transmi...

引用

IEEE Energy Conversion Congress and Exposition, ECCE

作者： Zhenyu Zhao Daniel Moscovitz Liang Du Xiaoyuan Fan Dept. of Electrical and Computer Engineering Temple University Philadelphia USA EMS Support Department PJM Interconnection Audubon USA Pacific Northwest National Laboratory Richland USA

The ever-growing high penetration of ubiquitously distributed energy resources, especially behind-the-meter solar (BTM) generations, has significant impacts on nodal load (i.e., net injection) profiles and consequently caused imperative operational challenges to system operators such as regional transmission organizations (RTOs). Illustrated by real-world nodal data and examples at PJM Interconnection, this paper first discusses the application and necessity of effectively extracting daily nodal load profiles in a non-intrusive manner. More importantly, a novel bi-level architecture, including Factorization Machines (FM) learning procedure has been proposed to effectively disaggregate not only one node but every node in an RTO service territory. Specifically, FM leaning is adopted to capture the interconnections between related features to better utilize the correlation between buses in the same region and between a single bus and the zonal load. The proposed bi-level technique is numerically validated using real-world, minute-level, normalized, and anonymized nodal data at PJM service territory.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learning Goal-based Movement via Motivational-based Models in Cognitive Mobile Robots

arXiv

引用

arXiv 2023年

作者： Berto, Letícia Costa, Paula Simões, Alexandre Gudwin, Ricardo Colombini, Esther Laboratory of Robotics and Cognitive Systems Institute of Computing University of Campinas Brazil Dept. of Computer Engineering and Industrial Automation School of Electrical and Computer Engineering University of Campinas Brazil Dept. of Control and Automation Engineering Institute of Science and Technology São Paulo State University Sorocaba Brazil University of Campinas Brazil

Humans have needs motivating their behavior according to intensity and context. However, we also create preferences associated with each action’s perceived pleasure, which is susceptible to changes over time. This makes decision-making more complex, requiring learning to balance needs and preferences according to the context. To understand how this process works and enable the development of robots with a motivational-based learning model, we computationally model a motivation theory proposed by Hull. In this model, the agent (an abstraction of a mobile robot) is motivated to keep itself in a state of homeostasis. We added hedonic dimensions to see how preferences affect decision-making, and we employed reinforcement learning to train our motivated-based agents. We run three agents with energy decay rates representing different metabolisms in two different environments to see the impact on their strategy, movement, and behavior. The results show that the agent learned better strategies in the environment that enables choices more adequate according to its metabolism. The use of pleasure in the motivational mechanism significantly impacted behavior learning, mainly for slow metabolism agents. When survival is at risk, the agent ignores pleasure and equilibrium, hinting at how to behave in harsh scenarios. Copyright © 2023, The Authors. All rights reserved.

关键词： Metabolism

来源：评论

学校读者我要写书评

暂无评论

An Attention-Based Parallel Algorithm for Hyperspectral Skin Cancer Classification on Low-Power GPUs

An Attention-Based Parallel Algorithm for Hyperspectral Skin...

引用

Euromicro Symposium on Digital System Design

作者： Emanuele Torti Marco Gazzoni Elisa Marenzi Raquel Leon Gustavo Marrero Callicò Giovanni Danese Francesco Leporati Dept. of Electrical Computer and Biomedical Engineering University of Pavia Pavia Italy Institute for Applied Microelectronics (IUMA) Universidad de Las Palmas de Gran Canaria Las Palmas de Gran Canaria Spain

Recently, several medical applications have relied on hyperspectral imaging. This technology enables both automated diagnosis and surgeon guidance. The employed algorithms adopt machine and deep learning methods to classify the images. In particular, Vision Transformers are a recent deep architecture that have been used to classify hyperspectral images of skin cancers achieving interesting results. However, deep architectures are computationally intensive and parallel architectures are mandatory to ensure a fast classification (depending on the application type even in real time). In this paper, we propose a parallel Vision Transformer architecture exploiting a low power GPU targeting the development of a portable diagnostic device. The classification time and power consumption of the low power board are compared with the performance of a desktop GPU. The results clearly highlight the suitability of the low power GPU to develop a portable diagnostic system based on hyperspectral imaging.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Non-monolithic fabrication of thin-film microelectrode arrays on PMUT transducers as a bimodal neuroscientific investigation tool*

Non-monolithic fabrication of thin-film microelectrode array...

引用

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

作者： Andrada I. Velea Joshua Wilson Astrid Gollhardt Cyril B. Karuthedath Abhilash S. Thanniyil Vasiliki Giagka Bioelectronics Section Dept. of Microelectronics Faculty of Electrical Engineering Mathematics and Computer Science Delft University of Technology the Netherlands Fraunhofer Institute for Reliability and Microintegration IZM VTT Technical Research Centre of Finland Ltd.

Ultrasound (US)-based neuromodulation has recently emerged as a spatially selective yet non-invasive alternative to conventional electrically-based neural interfaces. However, the fundamental mechanisms of US neuromodulation are not yet clarified. Thus, there is a need for in-vitro bimodal investigation tools that allow us to compare the effect of US versus electrically-induced neural activity in the vicinity of the transducing element. To this end, we propose a MicroElectrode-MicroTransducer Array (MEMTA), where a dense array of electrodes is co-fabricated on top of a similarly dense array of US *** this paper, we test the proof of concept for such co-fabrication using a non-monolithic approach, where, at its most challenging scenario, desired topologies require electrodes to be formed directly on top of fragile piezoelectric micromachined ultrasound transducer (PMUTs) membranes. On top of the PMUTs, a thin-film microelectrode array was developed utilizing microfabrication processes, including metal sputtering, lithography, etching and soft encapsulation. The samples were analysed through focused ion beam–scanning electron microscopy (FIB-SEM), and the results have shown that damage to the membranes does not occur during any of the process steps. This paper proves that the non-monolithic development of a miniaturised bimodal neuroscientific investigation tool can be achieved, thus, opening up a series of possibilities for further understanding and investigation of the nervous system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancement of a 263 GHz EPR Spectrometer with TWT Amplifier

Enhancement of a 263 GHz EPR Spectrometer with TWT Amplifier

引用

International Conference on Vacuum Electronics

作者： Shasha Qiu Yuan Zheng Neville C. Luhmann Paul Stucky David R. Britt Pan Pan Ying Li Jinjun Feng Dept. of Electrical and Computer Engineering University of California Davis Davis CA USA Dept. of Chemistry University of California Davis Davis CA USA National Key Laboratory of Science and Technology on Vacuum Electronics Beijing Vacuum Electronics Research Institute (BVERI) Beijing China

ISBN: (数字)9798350348705

ISBN: (纸本)9798350348712

A compact, broadband 263 GHz TWT amplifier is incorporated into a high-field pulse EPR spectrometer system. The pulsed TWT amplifier, with 10 GHz 3-dB bandwidth, operates at 20.25 kV cathode voltage and provides 25.5 dB gain in saturation. A preliminary experiment has been carried out to examine the performance of the implementation. The wideband and moderate power TWT demonstrates a dramatic improvement on the signal intensity of the nano-second pulse sequence from 200 mW to more than 7 W over 5 GHz bandwidth.

关键词： Vacuum systems Broadband amplifiers Voltage Cavity resonators Vacuum electronics Electron sources Wideband Gain Cathodes

来源：评论

学校读者我要写书评

暂无评论

Effectiveness of L2 Regularization in Privacy-Preserving Machine Learning

arXiv

引用

arXiv 2024年

作者： Chandrinos, Nikolaos Loi, Iliana Zachos, Panagiotis Symeonidis, Ioannis Spiliotis, Aristotelis Panou, Maria Moustakas, Konstantinos Human Factors and Vehicle Technology Hellenic Institute of Transport Centre for Research and Technology Hellas Thermi Greece Wire Communications and Information Technology Laboratory Dept. of Electrical and Computer Engineering University of Patras Patras Greece

Artificial intelligence, machine learning, and deep learning as a service have become the status quo for many industries, leading to the widespread deployment of models that handle sensitive data. Well-performing models, the industry seeks, usually rely on a large volume of training data. However, the use of such data raises serious privacy concerns due to the potential risks of leaks of highly sensitive information. One prominent threat is the Membership Inference Attack, where adversaries attempt to deduce whether a specific data point was used in a model's training process. An adversary's ability to determine an individual's presence represents a significant privacy threat, especially when related to a group of users sharing sensitive information. Hence, well-designed privacy-preserving machine learning solutions are critically needed in the industry. In this work, we compare the effectiveness of L2 regularization and differential privacy in mitigating Membership Inference Attack risks. Even though regularization techniques like L2 regularization are commonly employed to reduce overfitting, a condition that enhances the effectiveness of Membership Inference Attacks, their impact on mitigating these attacks has not been systematically explored. © 2024, CC BY.

关键词： Adversarial machine 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：