检索结果-内蒙古大学图书馆

IEEE Workshop on Machine Learning for Signal Processing

作者： Marcelo Ramos Romano Leonardo Tomazeli Duarte Leonardo Abdala Elias Neural Engineering Research Laboratory Center for Biomedical Engineering University of Campinas Campinas SP Brazil School of Applied Sciences University of Campinas Limeira SP Brazil Department of Electronics and Biomedical Engineering School of Electrical and Computer Engineering University of Campinas Campinas SP Brazil

A recent approach to address the blind source separation (BSS) problem relies on autoencoders with a discriminator as a generative adversarial network (GAN). However, this model is difficult to train due to the lack of metrics that ensure the convergence of a GAN. In this study, we try to provide an alternative solution by replacing the discriminator with appropriate regularization functions based on prior information on the sources. We tested this solution in the high-density electromyogram (HD-EMG) separation problem for a scenario with synthetic but realistic data and compared it with a classic algorithm from the literature. An interesting feature of the proposal is that it can be easily adapted for other source separation problems. Moreover, although the performance is slightly worse than the state-of the-art HD-EMG algorithm, which considers very detailed information on the problem, our proposal provides good results with a mean rate of agreement of 91.88% between the true and estimated spikes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Pulmonary X-Ray Image Classification Using Deep Learning with Coordinate Attention and Meta-ACON Activation Function 13

Pulmonary X-Ray Image Classification Using Deep Learning wit...

引用

13th International Conference on Information Technology in Medicine and Education, ITME 2023

作者： Chen, Hongkang Lu, Huijuan Chai, Zhuijun Zhu, Wenjie Huo, Wanli Yao, Yudong College of Information Engineering China Jiliang University Zhejiang Province Hangzhou China College of Information Engineering China Jiliang University China Drore Information and Technology Co. LTD. Zhejiang Province Hangzhou China Zhejiang Fangyuan Testing Group Co. Ltd. Zhejiang Province Hangzhou China College of Information Engineering Key Laboratory of Electromagnetic Wave Information Technology and Metrology of Zhejiang Province Zhejiang Province Hangzhou China Stevens Institute of Technology Department of Electrical and Computer Engineering HobokenNJ United States

ISBN: (纸本)9798350319156

Pneumonia is a serious health risk that usually examined by lung X-rays. Traditional deep learning models neglect image location information, fail to establish long-range dependencies and the limited ability to handle pneumonia features. In this paper, we propose MCANet model based on ResNet50 architecture by combining coordinate attention module and introducing a new activation function (Meta-ACON). The coordinate attention module in this model is used to capture positional information and establish long-range dependencies on feature maps. Meta-ACON activation function can adaptively select whether each neuron is activated, which contributes to dynamically handling pneumonia features. This paper performs comparison experiments on the public dataset ChestXray2020. Accuracy, Precision, Recall, and F1-score are used as evaluation metrics. Experiment results show that the MCANet improves each metrics compared with the original ResNet50 by 4.14%, 3.63%,4.25% and 3.99% respectively. © 2023 IEEE.

关键词： Health risks

来源：评论

学校读者我要写书评

暂无评论

Code-Aided Channel Estimation in LDPC-Coded MIMO Systems

arXiv

引用

arXiv 2023年

作者： Shi, Binghui Wu, Yongpeng Yuan, Peihong Ng, Derrick Wing Kwan Xia, Xiang-Gen Zhang, Wenjun The Department of Electronic Engineering Shanghai Jiao Tong University Minhang200240 China The Research Laboratory of Electronics Massachusetts Institute of Technology CambridgeMA United States The School of Electrical Engineering and Telecommunications University of New South Wales SydneyNSW Australia The Department of Electrical and Computer Engineering University of Delaware NewarkDE19716 United States

For a multiple-input multiple-output (MIMO) system with unknown channel state information (CSI), a novel low-density parity check (LDPC)-coded transmission (LCT) scheme with joint pilot and data channel estimation is proposed. To fine-tune the CSI, a method based on the constraints introduced by the coded data from an LDPC code is designed such that the MIMO detector exploits the fine-tuned CSI. For reducing the computational burden, a coordinate ascent algorithm is employed along with several approximation methods, effectively reducing the required times of MIMO detection and computational complexity to achieve a satisfying performance. Simulation results utilizing WiMAX standard LDPC codes and quadrature phase-shift keying (QPSK) modulation demonstrate gains of up to 1.3 dB at a frame error rate (FER) of 10−4 compared to pilot-assisted transmission (PAT) over Rayleigh block-fading channels. Copyright © 2023, The Authors. All rights reserved.

关键词： Channel state information

来源：评论

学校读者我要写书评

暂无评论

Affine Frequency Division Multiplexing: Extending OFDM for Scenario-Flexibility and Resilience

arXiv

引用

arXiv 2025年

作者： Yin, Haoran Tang, Yanqun Bemani, Ali Kountouris, Marios Zhou, Yu Zhang, Xingyao Liu, Yuqing Chen, Gaojie Yang, Kai Liu, Fan Masouros, Christos Li, Shuangyang Caire, Giuseppe Xiao, Pei School of Electronics and Communication Engineering Sun Yat-sen University China Mathematical and Algorithmic Sciences Laboratory Huawei France Research and Development France Communication Systems Department EU-RECOM France Department of Computer Science and Artificial Intelligence University of Granada Spain Sun Yat-sen University China School of Information and Electronics Beijing Institute of Technology China National Mobile Communications Research Laboratory Southeast University Bangladesh Department of Electrical and Electronic Engineering University College London United Kingdom Department of Electrical Engineering and Computer Science Technical University of Berlin Germany 5G/6G Innovation Centre University of Surrey United Kingdom

Next-generation wireless networks are conceived to provide reliable and high-data-rate communication services for diverse scenarios, such as vehicle-to-vehicle, unmanned aerial vehicles, and satellite networks. The severe Doppler spreads in the underlying time-varying channels induce destructive inter-carrier interference (ICI) in the extensively adopted orthogonal frequency division multiplexing (OFDM) waveform, leading to severe performance degradation. This calls for a new air interface design that can accommodate the severe delay-Doppler spreads in highly dynamic channels while possessing sufficient flexibility to cater to various applications. This article provides a comprehensive overview of a promising chirp-based waveform named affine frequency division multiplexing (AFDM). It is featured with two tunable parameters and achieves optimal diversity order in doubly dispersive channels (DDC). We study the fundamental principle of AFDM, illustrating its intrinsic suitability for DDC. Based on that, several potential applications of AFDM are explored. Furthermore, the major challenges and the corresponding solutions of AFDM are presented, followed by several future research directions. Finally, we draw some instructive conclusions about AFDM, hoping to provide useful inspiration for its development. Copyright © 2025, The Authors. All rights reserved.

关键词： Orthogonal frequency division multiplexing

来源：评论

学校读者我要写书评

暂无评论

Comparison of using photovoltaic system and diesel generator to feed the desired load 4

Comparison of using photovoltaic system and diesel generator...

引用

4th International Iraqi Conference on engineering Technology and Their Applications, IICETA 2021

作者： Hussain, Ali Nasser Al-Sagar, Zuhair S. Al-Tamimi, Majid Khudair Abbas Abid, Mimouna Hassan, Qusay AL-Abbooda, Karrar Saadoon Baghdad Iraq Baghdad Iraq Department of Electrical Engineering L2GEGI Laboratory University of Tiaret Tiaret Algeria Department of Computer Engineering Al-turath University College Baghdad Iraq College of Technical Engineering The Islamic University Najaf Iraq

ISBN: (纸本)9781665494618

The work in this paper presents techno-economic evolution for two energy systems (conventional and renewable) set with grid connection. The investigation was carried out by using an experimental measurement for the desired load and weather data (solar irradiance and ambient temperature). The simulation process performed using MATLAB and HOMER software at 1-minute time step resolution. The economic optimisation objective presented for two energy systems scenarios (i) photovoltaic/grid and (ii) diesel/grid. The component prices and economic assumptions based on the Iraqi market and regulations. The diesel generator is designed to work at the same period of the photovoltaic system operation (only during day hours), where the annual operation hours recorded 4380 hours/year which can produce 2349 kWh/year and consume diesel fuel by about 1826 letters/year. The results showed that the photovoltaic system based on scenario (A) can generate energy approx. 7895 kWh and the diesel generator based on scenario (B) can generate energy approx. 2346 kWh. The total net present cost and the cost of energy for scenario (A) by about ($1079) and ($0.035/kWh) respectively, and scenario (B) ($12287) and ($0.598/kWh) respectively. Based on the obtained results the used of solar energy is highly recommended than diesel generators due to the lowest cost and participation in grid energy support. © 2021 IEEE.

关键词： Solar energy

来源：评论

学校读者我要写书评

暂无评论

Inverse design of 3D-printable metalenses with complementary dispersion for terahertz imaging

arXiv

引用

arXiv 2025年

作者： Chen, Mo Chan, Ka Fai Hammond, Alec M. Chan, Chi Hou Johnson, Steven G. Department of Mathematics Massachusetts Institute of Technology CambridgeMA02139 United States State Key Laboratory of Terahertz and Millimeter Waves CityU Hong Kong School of Electrical and Computer Engineering Georgia Institute of Technology AtlantaGA30308 United States

This study formulates a volumetric inverse-design methodology to generate a pair of complementary focusing metalenses for terahertz imaging: the two lenses exhibit equal and opposite shifts in focal length with frequency. An asymmetry arises, where we find a focal length that decreases with frequency to be more challenging to achieve (without material dispersion) given fabrication constraints, but it is still possible. We employ topology optimization, coupled with manufacturing constraints, to explore fully freeform designs compatible with 3D printing. Formulating an optimization problem that quantifies the goal of maximal complementary focal shifts, while remaining differentiable and tractable, requires a carefully selected sequence of constraints and approximations. Copyright © 2025, The Authors. All rights reserved.

关键词： Shape optimization

来源：评论

学校读者我要写书评

暂无评论

Do Electric Vehicles Lead to More Severe Crashes? A Doubly Robust-Based Causal Inference Approach

SSRN

引用

SSRN 2025年

作者： Zhai, Guocong Xie, Kun Yang, Di Yang, Hong School of Transportation and Logistics National Engineering Laboratory of Integrated Transportation Big Data Application Technology National Engineering Laboratory of Integrated and Intelligent Transportation Southwest Jiaotong University Chengdu611756 China Department of Civil & Environmental Engineering Old Dominion University NorfolkVA23529 United States Department of Transportation & Urban Infrastructure Studies Morgan State University BaltimoreMD21251 United States Department of Electrical & Computer Engineering Old Dominion University NorfolkVA23529 United States Singapore

Electric vehicles (EVs) possess distinct physical characteristics compared to conventional vehicles, including greater mass, larger torque, higher acceleration rates, and a lower center of gravity. However, the safety implications of these differences remain underexplored in existing literature. This study examines the relationship between vehicle type and crash injury severity by employing a rigorous causal inference framework. We analyzed seven years of police-reported crash data (2017-2023) from Virginia, USA, treating EV crashes as the treatment group and conventional vehicle crashes as the control group. To address potential confounding issues in this high-dimensional covariate space, we implement a doubly robust estimator that integrates Bayesian Additive Regression Trees for matching-based estimation (inverse probability of treatment weighting) with logistic regression for outcome modeling. This approach provides reliable causal estimates even if one component is incorrectly specified. Our findings reveal that EV crashes are associated with a 14% reduction in the odds of severe injury compared to conventional vehicle crashes, with consistent estimates across methodological approaches. This study advances knowledge on EV safety and contributes methodologically by developing a doubly robust framework for binary safety outcomes through log-transformed causal odds ratios. From a practical perspective, our findings can guide transportation agencies in developing EV-related regulations, inform insurance providers in designing premium structures for EVs, and help consumers make informed choices on EV adoptions. © 2025, The Authors. All rights reserved.

关键词： Vehicle safety

来源：评论

学校读者我要写书评

暂无评论

Active Vibration Reduction for the Autonomous Observation Mechanism

Active Vibration Reduction for the Autonomous Observation Me...

引用

Control Technology and Applications (CCTA),

作者： Fatemeh Rekabi-Bana Mahmood Saadat Nahid Kalantaryardebily Martin Stefanec Laurenz A. Fedotoff Honghao Pan Tomáš Krajník Thomas Schmickl Farshad Arvin Department of Computer Science Swarm & Computational Intelligence Laboratory (SwaCIL) Durham University UK Faculty of Engineering Mechanics Virginia Tech Blacksburg Virginia United States of America Artificial Life Lab University of Graz Austria Faculty of Electrical Engineering Czech Technical University Czechia

ISBN: (数字)9798350370942

ISBN: (纸本)9798350370959

This paper presents a method applied for vibration reduction in an autonomous mechanism developed for robot-insect interaction. The mechanism performs continuous data collection of honeybee behaviour within a living honeybee colony. To ensure sufficient quality of the observations, the system has to be installed in proximity to the hive. However, as honeybees are particularly sensitive to vibrations, it is important to keep the vibrations produced by the mechanism below the values that can disturb the natural behaviour of the bees. Furthermore, avoiding vibrations improves the gathered data quality, decreases the maintenance frequency and prolonges the system service life. In this paper, we present the robotic observation mechanism’s development process of vibration control. The subspace identification method is applied to determine a model utilised to design a controller to actively reduce the resulting vibration while preserving the position tracking accuracy. The results of the experiments demonstrate a reduction of about 10dB in the vibration after applying the suggested controller.

关键词： Vibrations Power measurement Mechatronics Process control Vibration measurement Aerospace electronics Position measurement

来源：评论

学校读者我要写书评

暂无评论

Thermal and electric field driven rf breakdown precursor formation on metal surfaces

引用

Physical Review Accelerators and Beams 2024年第5期27卷 053101-053101页

作者： Ryo Shinohara Soumendu Bagchi Evgenya Simakov Sergey V. Baryshev Danny Perez Department of Electrical and Computer Engineering Michigan State University Michigan 48824 USA Department of Physics and Astronomy Michigan State University East Lansing Michigan 48824 USA Theoretical Division Los Alamos National Laboratory Los Alamos New Mexico 87545 USA Accelerator Operations and Technology Division Los Alamos National Laboratory Los Alamos New Mexico 87545 USA Department of Chemical Engineering and Material Science Michigan State University Michigan 48824 USA

The phenomenon of electric breakdown poses serious challenges to the design of devices that operate in high electric field environments. Experimental evidence points toward breakdown events that are accompanied by elevated temperatures and dark current spikes, which is attributed to high-asperity nanostructure formation that enhances the local electric field and triggers a runaway process. However, the exact mechanistic origin of such nanostructures under typical macroscopic operational conditions of electric field and magnetic-field-mediated heating remains poorly understood. In this work, we simulate the evolution of a copper surface under the combined action of the electric fields and elevated temperatures. Using a mesoscale curvature-driven surface evolution model, we show how a copper surface can undergo a type of dynamical instability that naturally leads to the formation of sharp asperities in realistic experimental conditions. Exploring the combined effect of fields and temperature rise, we identify the critical regimes that allow for the formation of breakdown precursors. The results show that thermoelastic stresses, while not essential, can significantly lower the critical electric field required for runaway surface instability, which is consistent with experimental observations that thermal effects can increase breakdown rates.

关键词： Material failure Plastic deformation Room temperature RF Thermal expansion Finite-element method

来源：评论

学校读者我要写书评

暂无评论

The molecular impact of sonoporation: A transcriptomic analysis of gene regulation profile

引用

Ultrasonics Sonochemistry 2024年 111卷 107077页

作者： Duan, Xinxing Wan, Jennifer M.F. Yu, Alfred C.H. Schlegel Research Institute for Aging and Department of Electrical & Computer Engineering University of Waterloo WaterlooONN2L3G1 Canada School of Biological Sciences The University of Hong Kong Hong Kong Pokfulam Hong Kong State Key Laboratory of Ultrasound in Medicine and Engineering College of Biomedical Engineering Chongqing Medical University Chongqing400016 China

Sonoporation has long been known to disrupt intracellular signaling, yet the involved molecules and pathways have not been identified with clarity. In this study, we employed whole transcriptome shotgun sequencing (RNA-seq) to profile sonoporation-induced gene responses after membrane resealing has taken place. Sonoporation was achieved by microbubble-mediated ultrasound (MB-US) exposure in the form of 1 MHz ultrasound pulsing (0.50 MPa peak negative pressure, 10 % duty cycle, 30 s exposure period) in the presence of microbubbles (1:1 cell-to-bubble ratio). Using propidium iodide (PI) and calcein respectively as cell viability and cytoplasmic uptake labels, post-exposure flow cytometry was performed to identify three viable cell populations: 1) unsonoporated cells, 2) sonoporated cells with low uptake, and 3) sonoporated cells with high uptake. Fluorescence-activated cell sorting was then conducted to separate the different groups followed by RNA-seq analysis of the gene expressions in each group of cells. We found that sonoporated cells with low or high calcein uptake showed high similarity in the gene responses, including the activation of multiple heat shock protein (HSP) genes and immediate early response genes mediating apoptosis and transcriptional regulation. In contrast, unsonoporated cells exhibited a more extensive gene expression alteration that included the activation of more HSP genes and the upregulation of diverse apoptotic mediators. Four oxidative stress-related and three immune-related genes were also differentially expressed in unsonoporated cells. Our results provided new information for understanding the intracellular mobilization in response to sonoporation at the molecular level, including the identification of new molecules in the sonoporation-induced apoptosis regulatory network. Our data also shed light on the innovative therapeutic strategy which could potentially leverage the responses of viable unsonoporated cells as a synergistic effect

关键词： Cell death

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：