检索结果-内蒙古大学图书馆

Meta-ETI: Meta-Reinforcement Learning with Explicit Task Inference for UAV-IoT Coverage

IEEE Internet of Things Journal 2025年第13期12卷 23852-23865页

作者： Huang, Songjun Sun, Chuanneng Pompili, Dario Rutgers University-New Brunswick Department of Electrical and Computer Engineering NJ United States

To better enhance the network service for different user devices in various scenarios, unmanned aerial vehicles (UAVs) are increasingly used as aerial base stations (ABSs). However, optimizing coverage for user devices via UAV team control is an NP-hard problem and escalates exponentially in complexity with the growing number of user devices. To address this challenge, researchers have turned to reinforcement learning (RL) for a more practical solution. With the growing prevalence of the Internet of Things (IoT), the diversity of user devices increases, posing challenges for traditional RL, as i) the spatial distribution of devices becomes more complex;ii) variations in device types and device mobility increase the training latency;iii) the high-speed movement of IoT devices can lead to performance deterioration in widely used RL algorithms with discrete action space;and iv) traditional RL struggles to adapt to new environments. To solve these problems, we propose a new meta-RL framework, Meta-RL with Explicit Task Inference (Meta-ETI). Then, we apply this framework to efficiently train an energy-efficient UAV control policy for fair and effective coverage in 3D dynamic environments. Meta-ETI is evaluated in both theoretical and application-related aspects and demonstrates superior performance compared to the baseline frameworks. The result shows that Meta-ETI demonstrates 2 to 3 times faster adaptation speed and a decent performance in sample efficiency. Furthermore, in the UAV-IoT coverage application, Meta-ETI shows 30% to 50% better in energy efficiency and 40% to 60% more served devices because of the fair coverage. © 2014 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Spin Photonic Topological Metasurface Based on a Kagome Lattice for Use in Leaky-Wave Antenna Application

引用

IEEE Access 2025年 13卷 89811-89818页

作者： Ahmad Abtahi, Sayyed Maddahali, Mohsen Bakhtafrouz, Ahmad Isfahan University of Technology Department of Electrical and Computer Engineering Isfahan84156-83111 Iran

The emerging field of topological metasurfaces offers unique advantages, particularly in robustness against backscattering in low-profile structures. The lattice configuration of these structures significantly influences the ability to achieve sharp turns in the propagation path. One of the most studied lattices in condensed matter physics is the kagome lattice, characterized by its hexagonal Brillouin zone, which displays a Dirac cone in its dispersion diagram. Previous research on kagome lattices in photonic topological insulators has primarily focused on valley types of insulators. This article introduces a spin topological metasurface based on the kagome lattice and its unit cell, enabling a broad range of sharp turns and propagation paths. The unit cell is compared to its hexagonal and 60-degree rhombic counterparts, and a parametric study of its dimensions is conducted. As a result of this research, a new X-band leaky-wave antenna designed in the kagome lattice with an armchair arrangement interface has been developed. This antenna provides two forward and two backward beams, each pair achieving an approximately 50-degree scan within the 8.8 to 11.1 GHz bandwidth. © 2013 IEEE.

关键词： Crystal lattices

来源：评论

学校读者我要写书评

暂无评论

Learning-Based Compress-and-Forward Schemes for the Relay Channel

引用

IEEE Journal on Selected Areas in Communications 2025年第7期43卷 2393-2404页

作者： Ozyilkan, Ezgi Carpi, Fabrizio Garg, Siddharth Erkip, Elza New York University Department of Electrical and Computer Engineering BrooklynNY United States

The relay channel, consisting of a source-destination pair along with a relay, is a fundamental component of cooperative communications. While the capacity of a general relay channel remains unknown, various relaying strategies, including compress-and-forward (CF), have been proposed. In CF, the relay forwards a quantized version of its received signal to the destination. Given the correlated signals at the relay and destination, distributed compression techniques, such as Wyner–Ziv coding, can be harnessed to utilize the relay-to-destination link more efficiently. Leveraging recent advances in neural network-based distributed compression, we revisit the relay channel problem and integrate a learned task-aware Wyner–Ziv compressor into a primitive relay channel with a finite-capacity out-of-band relay-to-destination link. The resulting neural CF scheme demonstrates that our compressor recovers binning of the quantized indices at the relay, mimicking the optimal asymptotic CF strategy, although no structure exploiting the knowledge of source statistics was imposed into the design. The proposed neural CF, employing finite order modulation, operates closely to the rate achievable in a primitive relay channel with a Gaussian codebook. We showcase the advantages of exploiting the correlated destination signal for relay compression through various neural CF architectures that involve end-to-end training of the compressor and the demodulator components. Our learned task-oriented compressors provide the first proof-of-concept work toward interpretable and practical neural CF relaying schemes. © 1983-2012 IEEE.

关键词： Compressors

来源：评论

学校读者我要写书评

暂无评论

A Scalable Unsupervised and Back Propagation Free Learning With SACSOM: A Novel Approach to SOM-Based Architectures

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第4期6卷 955-967页

作者： Hirani, Gaurav R. Wang, Kevin I-Kai Abdulla, Waleed H. The University of Auckland Department of Electrical Computer and Software Engineering Auckland1010 New Zealand

The field of computer vision is predominantly driven by supervised models, which, despite their efficacy, are computationally expensive and often intractable for many applications. Recently, research has expedited alternative avenues such as self-organizing maps (SOM)-based architectures, which offer significant advantages such as tractability, the absence of back-propagation, and feed-forward unsupervised learning. However, these SOM-based approaches frequently suffer from lower accuracy and limited generalization capabilities. To address these shortcomings, we propose a novel model called split and concur SOM (SACSOM). SACSOM overcomes the limitations of closely related SOM-based algorithms by utilizing multiple parallel branches, each equipped with its own SOM modules that process data independently with varying patch sizes. Furthermore, by creating groups of classes and using respective training samples to train independent subbranches in each branch, our approach accommodates datasets with a large number of classes. SACSOM employs a simple yet effective labeling technique requiring minimal labeled samples. The outputs from each branch, filtered by a threshold, contribute to the final prediction. Experimental validation on MNIST-digit, Fashion-MNIST, CIFAR-10, and CIFAR-100 demonstrates that SACSOM achieves competitive accuracy with significantly reduced computation time. Furthermore, it exhibits superior performance and generalization capabilities, even in high-noise scenarios. The weights of the single-layered SACSOM provide meaningful insights into the patch-based learning pattern, enhancing its tractability and making it ideal from the perspective of explainable AI. This study addresses the limitations of current clustering techniques, such as K-means and traditional SOMs, by proposing a lightweight, manageable, and fast architecture that does not require a GPU, making it suitable for low-powered devices. © 2024 IEEE.

关键词： Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning Data Collection for Bayesian Inference of Hidden Markov Models

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第5期6卷 1217-1232页

作者： Alali, Mohammad Imani, Mahdi Northeastern University Department of Electrical and Computer Engineering BostonMA02115 United States

Hidden Markov models (HMMs) are a powerful class of dynamical models for representing complex systems that are partially observed through sensory data. Existing data collection methods for HMMs, typically based on active learning or heuristic approaches, face challenges in terms of efficiency in stochastic domains with costly data. This article introduces a Bayesian lookahead data collection method for inferring HMMs with finite state and parameter spaces. The method optimizes data collection under uncertainty using a belief state that captures the joint distribution of system states and models. Unlike traditional approaches that prioritize short-term gains, this policy accounts for the long-term impact of data collection decisions to improve inference performance over time. We develop a deep reinforcement learning policy that approximates the optimal Bayesian solution by simulating system trajectories offline. This pretrained policy can be executed in real time, dynamically adapting to new conditions as data is collected. The proposed framework supports a wide range of inference objectives, including point based, distribution based, and causal inference. Experimental results across three distinct systems demonstrate significant improvements in inference accuracy and robustness, showcasing the effectiveness of the approach in uncertain and data-limited environments. © 2020 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Theoretical Analysis of Detection of Flying Vehicles Based on the Passive Radiometric Detection of Microwave-Millimeter-Terahertz Wavelength Electromagnetic Emissions from Exhaust Plasma Gases

引用

Progress in Electromagnetics Research C 2025年 154卷 267-275页

作者： Chatziathanasiou, Thomas N. Uzunoglu, Nikolaos Microwave Laboratory Department of Electrical and Computer Engineering National Technical University of Athens Greece

The feasibility of using passive radiometric detection of chaotic electromagnetic signals emanating from low density plasma plumes of the jet exhaust gases to detect low radar cross section aircrafts is analyzed for the frequency band 3.108–3.1012 Hz. The aircraft exhaust plume gas formation is modelled with a number of discrete different dimensions ellipsoids, with each having different electron densities and temperatures. Electromagnetic radiation analysis of emitting signals is computed applying fluctuation-dissipation theorem and geometric considerations. The detection range of characteristic military jet aircraft is computed numerically for the whole frequency band, from UHF to 3 THz. It is shown that high range detection can be achieved at upper microwave frequencies. © 2025, Electromagnetics Academy. All rights reserved.

关键词： Terahertz waves

来源：评论

学校读者我要写书评

暂无评论

Matrix Completion from One-Bit Dither Samples

引用

IEEE Transactions on Signal Processing 2024年 1-14页

作者： Eamaz, Arian Yeganegi, Farhang Soltanalian, Mojtaba Department of Electrical and Computer Engineering University of Illinois Chicago Chicago IL USA

We explore the impact of coarse quantization on matrix completion in the extreme scenario of dithered one-bit sensing, where the matrix entries are compared with random dither levels. In particular, instead of observing a subset of high-resolution entries of a low-rank matrix, we have access to a small number of one-bit samples, generated as a result of these comparisons. In order to recover the low-rank matrix using its coarsely quantized known entries, we begin by transforming the problem of one-bit matrix completion (one-bit MC) with random dithering into a nuclear norm minimization problem. The one-bit sampled information is represented as linear inequality feasibility constraints. We then develop the popular singular value thresholding (SVT) algorithm to accommodate these inequality constraints, resulting in the creation of the One-Bit SVT (OBSVT). Our findings demonstrate that incorporating multiple random dither sequences in one-bit MC can significantly improve the performance of the matrix completion algorithm. In pursuit of achieving this objective, we utilize diverse dithering schemes, namely uniform, Gaussian, and discrete dithers. To accelerate the convergence of our proposed algorithm, we introduce three variants of the OB-SVT algorithm. Among these variants is the randomized sketched OB-SVT, which departs from using the entire information at each iteration, opting instead to utilize sketched data. This approach effectively reduces the dimension of the operational space and accelerates the convergence. We perform numerical evaluations comparing our proposed algorithm with the maximum likelihood estimation method previously employed for one-bit MC, and demonstrate that our approach can achieve a better recovery performance. Authors

关键词： Linear matrix inequalities

来源：评论

学校读者我要写书评

暂无评论

Noninvasive estimation of blood potassium concentration using ECG and FCM-ANFIS model

引用

Research on Biomedical engineering 2024年第3-4期40卷 647-658页

作者： Samandari, Zeynab Molaeezadeh, Seyyedeh Fatemeh Department of Electrical and Computer Engineering Jundi-Shapur University of Technology Dezful Iran

Purpose: Potassium imbalance, often symptomless but potentially fatal, is prevalent in patients with kidney or heart conditions. Traditional laboratory tests for potassium measurement are costly and require skilled technicians. Additionally, phlebotomy is challenging and painful for high-risk patients. To address these issues, this study proposes a noninvasive and bloodless approach that leverages the electrocardiogram (ECG) signal, which may be sensitive to potassium changes. The research introduces a data-driven framework for ECG-based potassium measurement. Methods: The proposed framework comprises five main components: Cohort Selection—Among 461,178 patients in the ECG-ViEW II database, those with simultaneous ECG, Age-adjusted Charlson Comorbidity Index (ACCI), and potassium measurements within a 5-min interval are chosen;Data Labeling—Three labels—hypokalemia, normal, and hyperkalemia—are defined;Feature Extraction—Relevant features such as RR interval, PR interval, QRS duration, QT interval, QTc interval, P axis, QRS axis, T axis, and ACCI are extracted;Feature Selection—The Kruskal–Wallis technique evaluates feature importance and selects discriminative ones;and Model Design—An ANFIS model based on FCM clustering (FCM-ANFIS) is developed using the selected features. Results: Among the 42 patients selected during cohort filtering, T axis demonstrated significant association with potassium levels (P © The Author(s), under exclusive licence to The Brazilian Society of Biomedical engineering 2024.

关键词： Electrocardiograms

来源：评论

学校读者我要写书评

暂无评论

FARVIS: A Facial Attribute Recognizer based on Vision Sensor using Super-Efficient Network Supporting Service Robots

引用

IEEE Sensors Journal 2025年第12期25卷 22696-22706页

作者： Priadana, Adri Nguyen, Duy-Linh Vo, Xuan-Thuy Choi, Jehwan Jo, Kanghyun University of Ulsan Department of Electrical Electronic and Computer Engineering Ulsan44610 Korea Republic of

Service robots have developed into a significant tool in advertising industry and facial attribute recognition is crucial because it allows robots to understand human preferences, intentions, and emotions. Robot machines typically utilize a low-cost device such as a CPU as the primary control unit for efficient implementation. Therefore, efficient facial attribute recognition that does not demand extensive memory and computational resources is required. This work proposes a Super-Efficient Facial Attribute Recognizer (SEFAR) designed specially to support service robots. SEFAR introduces a super-efficient network consisting of a Bottleneck Multi-Perspective Convolution (BMPC) reinforced by an Aggregated Large Kernel Attention (ALKA) module. SEFAR, which has low computation and few parameters, achieves highly competitive performance compared to other networks on the CelebA and LFWA as benchmark datasets. By integrating the proposed SEFAR with face detection as the initial process and a camera as a vision-based sensor, this work proposes FARVIS. It operates in real-time at a maximum speed of 21.63, 51.90, and 86.58 frames per second (FPS) using face input images of a 224 × 224, 112 × 112, and 56 × 56, respectively. FARVIS achieves this performance on a VGA camera resolution using an Intel Core i7-9750H CPU without demanding extensive memory or computational resources. © 2001-2012 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Switching Dynamic State Estimation and Event Detection for Inverter-Based Resources with Multiple Control Modes

引用

IEEE Transactions on Power Systems 2024年第4期40卷 3439-3451页

作者： Huang, Heqing Lin, Yuzhang Department of Electrical and Computer Engineering New York University Brooklyn NY USA

The Dynamic State Estimation (DSE) for Inverter-Based Resources (IBRs) is an emerging topic as IBRs gradually replace synchronous generators (SGs) in power systems. Unlike SGs, the dynamic models of IBRs heavily depend on their control algorithms, and conventional DSE methods for SGs, which assume a unchanged state space and dynamic model, cannot handle IBRs with control mode changes in real time, particularly when the power grid operators are unaware of the current control mode of the IBRs. In response to these challenges, an Expectation-Maximization Sliding-Window Iterated Extended Kalman Filter (EM-SW-IEKF) method is proposed in this paper. It theoretically achieves maximum likelihood estimation under different modes through the EM algorithm, providing the most probable control mode of the system as well as the corresponding state estimate. This method is validated in various IBR systems (battery energy storage systems and solar photovoltaic systems) and under different control mode transitions (switching between grid-following and grid-forming controls and between low voltage ride through and maximum power point tracking controls). © 1969-2012 IEEE.

关键词： Expectation maximization algorithm

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

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

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：