检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2025年第6期6卷 1651-1663页

作者： Zhang, Li Garg, Bhanu Sridhara, Pradyumna Hosseini, Ramtin Xie, Pengtao University of California Department of Electrical and Computer Engineering San DiegoCA92093 United States

Bi-level optimization methods in machine learning are popularly effective in subdomains of neural architecture search, data reweighting, etc. However, most of these methods do not factor in variations in learning difficulty, which limits their performance in real-world applications. To address the above problems, we propose a framework that imitates the learning process of humans. In human learning, learners usually focus more on the topics where mistakes have been made in the past to deepen their understanding and master the knowledge. Inspired by this effective human learning technique, we propose a multilevel optimization framework, learning from mistakes (LFM), for machine learning. We formulate LFM as a threestage optimization problem: 1) the learner learns, 2) the learner relearns based on the mistakes made before, and 3) the learner validates his learning. We develop an efficient algorithm to solve the optimization problem. We further apply our method to differentiable neural architecture search and data reweighting. Extensive experiments on CIFAR-10, CIFAR-100, ImageNet, and other related datasets powerfully demonstrate the effectiveness of our approach. © 2020 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Fundamentals of LEO Based Localization

引用

IEEE Transactions on Information Theory 2025年第7期71卷 5277-5311页

作者： Emenonye, Don-Roberts Dhillon, Harpreet S. Buehrer, R. Michael Virginia Tech Bradley Department of Electrical and Computer Engineering BlacksburgVA24061 United States

In this paper, we derive the fundamental limits of low earth orbit (LEO) enabled localization by analyzing the available information in signals from multiple LEOs during different transmission time slots received on a multiple antennas and evaluate the utility of these signals for 9D localization (3D position, 3D orientation, and 3D velocity estimation). We start by deriving the Fisher Information Matrix (FIM) for the channel parameters that are present in the signals received from LEOs in the same or multiple constellations during multiple transmission time slots. To accomplish this, we define a system model that captures i) time offset between LEOs caused by having relatively cheap clocks, ii) frequency offset between LEOs, iii) the unknown Doppler rate caused by high mobility LEOs, and iv) multiple transmission time slots from a particular LEO. We transform the FIM for the channel parameters to the FIM for the location parameters and determine the required conditions for localization. To do this, we start with the 3D localization cases: i) 3D positioning with known velocity and orientation, ii) 3D orientation estimation with known position and velocity, and iii) 3D velocity estimation with known position and orientation. Subsequently, we derive the FIM for the full 9D localization case (3D position, 3D orientation, and 3D velocity estimation) in terms of the FIM for the 3D localization. Using these results, we determine the number of LEOs, the operating frequency, the number of transmission time slots, and the number of receive antennas that allow for different levels of location estimation. We then provide insights into the interaction between the number of LEOs, the operating frequency, the number of transmission time slots, and the number of receive antennas. One key result is that in the presence of time and frequency offsets and Doppler rate, it is possible to perform 9D localization (3D position, 3D velocity, and 3D orientation estimation) of a receiver by

关键词： Fisher information matrix

来源：评论

学校读者我要写书评

暂无评论

IC Backside Tamper Detection using Impedance Sensing

引用

IEEE Access 2025年 13卷 90706-90725页

作者： Mosavirik, Tahoura Tajik, Shahin Worcester Polytechnic Institute Electrical and Computer Engineering Department WorcesterMA01609 United States

The expansion of flip-chip technologies and lack of backside protection made integrated circuits (ICs) vulnerable to certain classes of physical attacks mounted from the IC’s backside, including laser-assisted probing, electromagnetic side-channel analysis, body biasing injection (BBI), and focused ion beam (FIB) editing. Existing countermeasures are expensive, incompatible with standard IC fabrication, and unsuitable for legacy systems such as field-programmable gate arrays (FPGAs), which are widely used in industrial and defense systems. In this paper, we demonstrate how impedance monitoring of the printed circuit board (PCB) and the IC package’s power distribution network (PDN) using on-chip circuit-based network analyzers can detect IC backside tampering. Our method is based on the fact that any attempt to expose the backside silicon substrate, such as the removal of the fan and heatsinks, or polishing it, leads to changes in the equivalent impedance of the package’s PDN, and hence scanning the package impedance will reveal if the package integrity has been violated. To validate our claims, we deployed an on-FPGA network analyzer on an AMD Zynq UltraScale+ MPSoC (16 nm), which is part of a multi-PCB *** performed a series of backside tamper attacks, including the removal of cooling components and IC backside silicon milling/polishing, across different temperatures, and evaluated detection effectiveness leveraging the difference of means as the statistical metric. © 2013 IEEE.

关键词： Focused ion beams

来源：评论

学校读者我要写书评

暂无评论

Ensemble based unsupervised anomaly detection with concept drift adaptation for time series data 10

Ensemble based unsupervised anomaly detection with concept d...

引用

10th IEEE Smart World Congress, SWC 2024

作者： Li, Danlei Nair, Nirmal Wang, Kevin I-Kai Sakurai, Kouichi University of Auckland Department of Electrical Computer and Software Engineering Auckland New Zealand Kyushu University Department of Informatics Faculty of Information Science and Electrical Engineering Fukuoka Japan

ISBN: (纸本)9798331520861

Anomaly detection is the identification of instances that substantially deviate from the majority of the data and do not conform to a well-defined normal behavior. Investigating time series anomalies has become increasingly popular in recent years due to widely deployed IoT devices and sensors. Although most existing methods apply image anomaly detection algorithms directly on time series and commonly assume the data is IID (independent and identically distributed). However, in most realworld applications, the underlying data distribution alters over time. Changes in data over time are referred to as concept drift and can significantly degrade the efficacy of an anomaly detection model. Existing research also indicates that the majority of anomaly detection frameworks ignored concept drift, resulting in poor long-term model performance. This paper presents an ensemble-based, unsupervised anomaly detection framework that is adaptive to the concept drift in time series data. Both distribution and performance-based techniques are used to detect concept drift and update the model to ensure the framework's longterm performance reliability. The proposed method is evaluated using a real-world univariate time series data that captures sea surface temperature data over a 2 -year period. By comparing our proposed framework to other state-of-the-art algorithms, we demonstrate our proposed method has obvious benefits in accuracy and long-term stability. © 2024 IEEE.

关键词： Anomaly detection Concept drift adaptation Ensemble method Time series Unsupervised method

来源：评论

学校读者我要写书评

暂无评论

A Highly-Parallel and Scalable Hardware Accelerator for the NTest Othello Game Engine

引用

IEEE Transactions on Parallel and Distributed Systems 2025年第8期36卷 1620-1633页

作者： Popa, Stefan Petric, Vlad Ivanovici, Mihai Transilvania University of Brasov Electronics and Computers Department Faculty of Electrical Engineering and Computer Science Romania

Othello is a two-player combinatorial game with 1E+28 legal positions and 1E+58 game tree complexity. We propose a HIghly PArallel, Scalable and configurable hardware accelerator for evaluating the middle and endgame Othello positions. We base HIPAS on NTest - a leading software Othello engine that uses the minimax algorithm with a quality pattern-based evaluation function, alpha-beta pruning, and heuristic mobility sorting. We describe its architecture and Field Programmable Gate Array implementation, measure its performance, and compare it with prior solutions. HIPAS achieves the highest quality evaluation, the highest performance with speed-ups up to several hundreds, and the best energy efficiency. The main novelty is the algorithm implementation as a circular pipeline and a Finite State Machine with pseudo-parallel processing. Although Othello was recently claimed to be weakly solved, the game remains unsolved in a stronger sense. A weak solution only shows how to force a draw. It does not guarantee a win if the opponent makes a mistake. HIPAS can validate the weak solution faster and more efficiently. A multi-threaded NTest software component evaluating the beginning and part of the middle game, combined with one or more instances of HIPAS for handling the remainder can provide a stronger solution. © 1990-2012 IEEE.

关键词： Middleware

来源：评论

学校读者我要写书评

暂无评论

electrical System Planning of Large-scale Offshore Wind Farm Based on N+ Design Considering Optimization of Upper Power Limits of Wind Turbines

引用

Journal of Modern Power Systems and Clean Energy 2023年第6期11卷 1784-1794页

作者： Shurong Wei Hao Wang Yang Fu Fangxing Li Lingling Huang IEEE Department of Electrical Power Engineering Shanghai University of Electric PowerShanghai 200090China Department of Electrical Engineering and Computer Science The University of TennesseeKnoxvilleTN 37996USA

electrical system planning of the large-scale offshore wind farm is usually based on N-1 security for equipment lectotype. However, in this method, owing to the aggregation effect in large-scale offshore wind farms, offshore electrical equipment operates under low load for long periods, thus wasting resources. In this paper, we propose a method for electrical system planning of the large-scale offshore wind farm based on the N+ design. A planning model based on the power-limited operation of wind turbines under the N+ design is constructed, and a solution is derived with the optimization of the upper power limits of wind turbines. A comprehensive evaluation and game analysis of the economy, risk of wind abandonment, and environmental sustainability of the planned offshore electrical systems have been conducted. Moreover, the planning of an infield collector system, substation, and transmission system of an offshore electrical system based on the N+ design is integrated. For a domestic offshore wind farm, evaluation results show that the proposed planning method can improve the efficiency of wind energy utilization while greatly reducing the investment cost of the electrical system.

关键词： electrical system N+design offshore wind farm planning optimization

来源：评论

学校读者我要写书评

暂无评论

Ephemeris and Timing Error Disambiguation Enabling Precise LEO PNT

引用

IEEE Transactions on Aerospace and Electronic Systems 2025年第3期61卷 6138-6153页

作者： Saroufim, Joe Kassas, Zaher M. The Ohio State University Department of Electrical and Computer Engineering ColumbusOH43210 United States

The ephemeris and timing errors of low Earth orbit (LEO) satellites are modeled, leading to an approach to disambiguate these errors from pseudorange-type measurements. First, a model is derived describing the ephemeris error's impact on ranging measurements from LEO space vehicles (SVs) with imprecise ephemerides. A simulation study is presented comparing the impact of ephemeris error on ranging error for five LEO constellations (Statlink, OneWeb, Orbcomm, Iridium, and Globalstar) and five medium Earth orbit (MEO) constellations (GPS, GLONASS, Galileo, BeiDou-3, and O3B). Second, it is shown that for a particular SV position, the ephemeris error has no effect on range measurements. Next, the ephemeris and timing errors are parametrized by the 3-D ephemeris error magnitude and its direction angle from the in-track axis. This parametrization is exploited in a proposed algorithm to disambiguate the ephemeris and timing errors from the LEO SVs' pseudorange measurements at a reference receiver. The two parameters can be communicated to any unknown receiver listening to the same LEO SVs to correct for ephemerides ranging error, leading to improved positioning, navigation, and timing precision. Monte Carlo simulation results are presented demonstrating the efficacy of the proposed algorithm. The simulations considered a reference receiver tracking via pseudorange measurements 22 Starlink and 4 OneWeb LEO SVs with poorly known ephemerides [obtained from two-line element (TLE) files, propagated with SGP4]. The proposed algorithm reduced the 3-D position error of all SVs from a few kilometers to less than 120 m. The parameters were communicated to an unknown receiver to correct the LEO ephemerides, after which the receiver estimated its position by fusing its LEO pseudoranges via an extended Kalman filter, resulting in a horizontal position error of 0.91 m, as compared to 213 m utilizing TLE+SGP4 ephemerides. Two sets of experimental results are presented where the ephemeris

关键词： Extended Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Generalized Implicit Transmission (GIT)

IEEE Open Journal of the Communications Society

引用

IEEE Open Journal of the Communications Society 2025年 6卷 4731-4741页

作者： Hewawaduge, Dhanushki Fonseka, John P. The University of Texas at Dallas Department of Electrical and Computer Engineering RichardsonTX75080 United States

In [1], two implicit transmission techniques, namely, implicit transmission with bit flipping (ITBF) and implicit transmission with collection decoding (ITCD) have been introduced to transmit an independent second coded sequence implicitly while transmitting a first coded sequence explicitly over the channel. In this study, a novel generalized implicit transmission (GIT) technique that can transmit any number of independent implicit sequences implicitly while transmitting a single explicit sequence over the channel is introduced. The GIT technique, its encoding and decoding are explained in detail. It is numerically demonstrated using the LDPC codes employed in the WiFi and 5G standards that GIT with multiple implicit sequences can increase the transmission rate significantly higher than those that can be achieved with a single implicit sequence reported in [1]. © 2020 IEEE.

关键词： Multiplexing

来源：评论

学校读者我要写书评

暂无评论

Intent-driven network automation through sustainable multimodal generative AI

引用

Eurasip Journal on Wireless Communications and Networking 2025年第1期2025卷 1-17页

作者： Trantzas, Kostis Brodimas, Dimitrios Agko, Besiana Tziavas, Georgios Christos Tranoris, Christos Denazis, Spyros Birbas, Alexios Department of Electrical and Computer Engineering University of Patras Rio Campus Achaia Patras26504 Greece

The concept of Network-as-a-Service involves deploying and reconfiguring next-generation networks, in a flexible and dynamic manner, to always cater to the needs of the respective stakeholders. It presents a complex challenge to manage and orchestrate computational and telecommunication resources across the cloud-edge continuum, especially with the growing focus on cost efficiency and energy consumption. To address this complexity, several technology enablers are considered, but the recent advancements in Large Language Models research have inevitably brought Intent-Based Networking to the forefront. This paper explores the architecture and implementation of an intent-based automation framework that adheres to contemporary industry standards, while also considering sustainability. To achieve this, a translation pipeline is introduced, based on emerging multimodal Generative Artificial Intelligence models, which transforms a high-level description of desired network capabilities and supplementary deployment files into machine-consumable information digested by the network itself. Therefore, several state-of-the-art online and locally deployed models are compared. The ultimate motivation of this work is to validate the feasibility and accuracy of the proposed framework, promoting sustainability through minimal resource consumption and cost efficiency. Additionally, the framework ensures compatibility with modern orchestrators and next-generation Operational Support System that follow the same industry standards. © The Author(s) 2025.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

BreastCNet: Breast Cancer Detection, Classification, and Localization Convolutional Neural Network With Advanced Optimization Techniques

引用

IEEE Access 2025年 13卷 87386-87400页

作者： Mahichi, Hassan Ghods, Vahid Sohrabi, Mohammad Karim Sabbaghi, Arash Islamic Azad University Department of Electrical and Computer Engineering Se.C. Semnan Iran

Breast cancer remains a significant global health issue, primarily affecting females and requiring advanced detection methods to improve patient outcomes. While computer-aided diagnostic methods have progressed, limitations in accuracy persist. This study introduced BreastCNet, a Convolutional Neural Network (CNN) with hyperparameter optimization and a multi-task learning framework, enhancing classification and lesion localization. The BreastCNet integrated CNNs with the Grey Wolf Optimizer (GWO) and Parrot Optimizer (PO) in a dual-optimization approach. GWO fine-tuned neuron counts in dense layers to enhance feature learning, while PO dynamically adjusted the learning rate to improve convergence. Specifically, the parrot optimizer adjusted the learning rate from 0.001 to 0.00156, resulting in a 1.5% improvement in accuracy, and the grey wolf optimizer fine-tuned neuron numbers (Dense_1: 6, Dense_2: 866), contributing to a 2.3% increase in validation accuracy. These optimizations mitigated overfitting, accelerated convergence, and improved generalization, making the BreastCNet computationally efficient and clinically viable. The multi-task learning framework simultaneously performed breast ultrasound image classification (benign/malignant) and lesion localization via bounding box regression. The model achieved 98.10% validation accuracy, an AUC of 0.995, an F1-score of 0.98, and an IoU score of 0.96 for lesion localization on the Breast Ultrasound Images (BUSI) dataset, with comparable improvements on the BUSI, Digital Database for Screening Mammography (DDSM), and INbreast datasets. The BreastCNet is highly likely to advance breast cancer detection and lesion localization, providing precise localization and improved generalization, making it a promising tool for clinical applications. © 2013 IEEE.

关键词： Mammography

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：