检索结果-内蒙古大学图书馆

arXiv 2024年

作者： He, Xilin Hu, Jingyu Lin, Qinliang Luo, Cheng Xie, Weicheng Song, Siyang Khan, Muhammad Haris Shen, Linlin Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence and Robotics for Society China Guangdong Provincial Key Laboratory of Intelligent Information Processing China University of Exeter United Kingdom Mohamed bin Zayed University of Artificial Intelligence United Arab Emirates

Domain generalization methods aim to learn transferable knowledge from source domains that can generalize well to unseen target domains. Recent studies show that neural networks frequently suffer from a simplicity-biased learning behavior which leads to over-reliance on specific frequency sets, namely as frequency shortcuts, instead of semantic information, resulting in poor generalization performance. Despite previous data augmentation techniques successfully enhancing generalization performances, they intend to apply more frequency shortcuts, thereby causing hallucinations of generalization improvement. In this paper, we aim to prevent such learning behavior of applying frequency shortcuts from a data-driven perspective. Given the theoretical justification of models’ biased learning behavior on different spatial frequency components, which is based on the dataset frequency properties, we argue that the learning behavior on various frequency components could be manipulated by changing the dataset statistical structure in the Fourier domain. Intuitively, as frequency shortcuts are hidden in the dominant and highly dependent frequencies of dataset structure, dynamically perturbating the over-reliance frequency components could prevent the application of frequency shortcuts. To this end, we propose two effective data augmentation modules designed to collaboratively and adaptively adjust the frequency characteristic of the dataset, aiming to dynamically influence the learning behavior of the model and ultimately serving as a strategy to mitigate shortcut learning. Code is available at AdvFrequency. © 2024, CC BY.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Heavy tails and pruning in programmable photonic circuits

arXiv

引用

arXiv 2022年

作者： Yu, Sunkyu Park, Namkyoo Intelligent Wave Systems Laboratory Department of Electrical and Computer Engineering Seoul National University Seoul08826 Korea Republic of Photonic Systems Laboratory Department of Electrical and Computer Engineering Seoul National University Seoul08826 Korea Republic of

Developing hardware for high-dimensional unitary operators plays a vital role in implementing quantum computations and deep learning accelerations. Programmable photonic circuits are singularly promising candidates for universal unitaries owing to intrinsic unitarity, ultrafast tunability, and energy efficiency of photonic platforms. Nonetheless, when the scale of a photonic circuit increases, the effects of noise on the fidelity of quantum operators and deep learning weight matrices become more severe. Here we demonstrate a nontrivial stochastic nature of large-scale programmable photonic circuits—heavy-tailed distributions of rotation operators—that enables the development of high-fidelity universal unitaries through designed pruning of superfluous rotations. The power law and the Pareto principle for the conventional architecture of programmable photonic circuits are revealed with the presence of hub phase shifters, allowing for the application of network pruning to the design of photonic hardware. We extract a universal architecture for pruning random unitary matrices and prove that "the bad is sometimes better to be removed" to achieve high fidelity and energy efficiency. This result lowers the hurdle for high fidelity in large-scale quantum computing and photonic deep learning accelerators. © 2022, CC BY.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Analyzing the Impact of Lossy Data Reduction on Volume Rendering of Cosmology Data 8

Analyzing the Impact of Lossy Data Reduction on Volume Rende...

引用

8th IEEE/ACM International Workshop on Data Analysis and Reduction for Big Scientific Data, DRBSD-8 2022

作者： Wang, Jinzhen Grosset, Pascal Turton, Terece L. Ahrens, James New Jersey Institute of Technology Department of Electrical and Computer Engineering NJ United States Information Sciences Los Alamos National Laboratory Los Alamos United States Information Science & Technology Institute Los Alamos National Laboratory Los Alamos United States

ISBN: (纸本)9781665463379

Cosmology simulations are among some of the largest simulations currently run on supercomputers, generating terabytes to petabytes of data for each run. Consequently, scien-tists are seeking to reduce the amount of storage needed while preserving enough quality for analysis and visualization of the data. One of the most commonly used visualization techniques for cosmology simulations is volume rendering. Here, we investigate how different types of lossy error-bound compression algorithms affect the quality of volume-rendered images generated from reconstructed datasets. We also compute a number of image quality assessment metrics to determine which ones are the most effective at identifying artifacts in the visualizations. © 2022 IEEE.

关键词： Data reduction

来源：评论

学校读者我要写书评

暂无评论

A Dual-Inductor Quad-Path Hybrid Buck (2L4PHB) Converter With Reduced Inductor Current

引用

IEEE Journal of Solid-State Circuits 2025年

作者： Zeng, Wen-Liang Cai, Guigang Lu, Yan Sin, Sai-Weng Martins, Rui P. Lam, Chi-Seng State Key Laboratory of Analog and Mixed-Signal Vlsi University of Macau Macau999078 China Institute of Microelectronics University of Macau Macau999078 China Department of Electrical and Computer Engineering Princeton University PrincetonNJ08544 United States Guangzhou510530 China Department of Electrical and Computer Engineering Faculty of Science and Technology University of Macau Macau999078 China Department of Electronic Engineering Tsinghua University Beijing100084 China Instituto Superior Tecnico Universidade de Lisboa Lisbon1049-001 Portugal

In high-efficiency 12-to-1-1.8-V applications, the small duty ratio (D ≈ 0.1) and high voltage stress on power switches of the conventional buck converter bring significant efficiency penalty. This article proposes a dual-inductor quad-path hybrid buck (2L4PHB) converter that addresses these issues, achieving both high power conversion efficiency and power density. Compared to the widely used double step-down (DSD) converter, the proposed 2L4PHB converter reduces the average inductor current by 30% and the inductor current ripple by 18% at a voltage conversion ratio (VCR) of 0.15. In addition to continuous conduction mode (CCM), this design incorporates a discontinuous conduction mode (DCM) calibration loop to improve efficiency at light loads. The proposed 2L4PHB converter, fabricated in a 180-nm BCD process, achieves a maximum current density of 0.18 A/mm2 and 256 A/cm3 and a peak efficiency of 93.7% and maintains efficiencies above 85% across load currents ranging from 0.6 to 4 A, all while using a compact inductor with dimensions of 2.5 × 2.0 × 1.0 mm3 and a DCR of 48 mΩ. © 2025 IEEE.

关键词： Buck converter

来源：评论

学校读者我要写书评

暂无评论

Analytical Model for Device Currents in 5-Level Active Neutral Point Clamped Converter

Analytical Model for Device Currents in 5-Level Active Neutr...

引用

International Conference on electrical Systems for Aircraft, Railway, Ship Propulsion and Road Vehicles & International Transportation Electrification Conference (ESARS-ITEC)

作者： Daniel Zakzewski Rakesh Resalayyan Apurv Kumar Yadav Alireza Khaligh Department of Electrical and Computer Engineering Maryland Power Electronics Laboratory The Institute for Systems Research University of Maryland College Park United States Department of Electrical Engineering Indian Institute of Technology Roorkee Uttrakhand India

This paper presents a closed form analytical model for semiconductor and capacitor currents in a 5-Level Active Neutral Point Clamped Converter (5L-ANPC) topology. This model enables device selection, performance prediction, and design optimization of the topology. Models for the switch and FC currents are derived based on the topology's switching states. A model for input capacitor current is derived by analyzing the interaction of three phase legs of the topology. The model is verified using conventional time-domain switching simulation of the topology.

关键词： Semiconductor device modeling Analytical models Capacitors Transportation Stars Switches Predictive models

来源：评论

学校读者我要写书评

暂无评论

GenFace: A Large-Scale Fine-Grained Face Forgery Benchmark and Cross Appearance-Edge Learning

arXiv

引用

arXiv 2024年

作者： Zhang, Yaning Yu, Zitong Wang, Tianyi Huang, Xiaobin Shen, Linlin Gao, Zan Ren, Jianfeng Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China School of Computing and Information Technology Great Bay University Dongguan523000 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China Nanyang Technological University 50 Nanyang Ave Block N 4 639798 Singapore Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518129 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University China Jinan250014 China Key Laboratory of Computer Vision and System Ministry of Education Tianjin University of Technology Tianjin300384 China School of Computer Science University of Nottingham Ningbo China

The rapid advancement of photorealistic generators has reached a critical juncture where the discrepancy between authentic and manipulated images is increasingly indistinguishable. Thus, benchmarking and advancing techniques detecting digital manipulation become an urgent issue. Although there have been a number of publicly available face forgery datasets, the forgery faces are mostly generated using GAN-based synthesis technology, which does not involve the most recent technologies like diffusion. The diversity and quality of images generated by diffusion models have been significantly improved and thus a much more challenging face forgery dataset shall be used to evaluate SOTA forgery detection literature. In this paper, we propose a large-scale, diverse, and fine-grained high-fidelity dataset, namely GenFace, to facilitate the advancement of deepfake detection, which contains a large number of forgery faces generated by advanced generators such as the diffusion-based model and more detailed labels about the manipulation approaches and adopted generators. In addition to evaluating SOTA approaches on our benchmark, we design an innovative Cross Appearance-Edge Learning (CAEL) detector to capture multi-grained appearance and edge global representations, and detect discriminative and general forgery traces. Moreover, we devise an Appearance-Edge Cross-Attention (AECA) module to explore the various integrations across two domains. Extensive experiment results and visualizations show that our detection model outperforms the state of the arts on different settings like cross-generator, cross-forgery, and cross-dataset evaluations. Code and datasets will be available at https://***/Jenine-321/GenFace. Copyright © 2024, The Authors. All rights reserved.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Estimation of Arterial Stiffness from PPG Spectrograms: A Novel Approach for Non-Invasive Cardiovascular Diagnostics

Deep Learning-Based Estimation of Arterial Stiffness from PP...

引用

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

作者： Kiana Pilevar Abrisham Khalil Alipour Bahram Tarvirdizadeh Mohammad Ghamari Department of Mechatronics Engineering School of Intelligent Systems Engineering College of Interdisciplinary Science and Technology Advanced Service Robots (ASR) Laboratory University of Tehran Tehran Iran Department of Electrical and Computer Engineering Kettering University Flint Michigan USA

ISBN: (数字)9798350371499

ISBN: (纸本)9798350371505

Cardiovascular diseases (CVDs), a leading cause of global mortality, are intricately linked to arterial stiffness, a key factor in cardiovascular health. Non-invasive assessment of arterial stiffness, particularly through Carotid-to-femoral Pulse Wave Velocity (cf-PWV) – the gold standard in this field – is vital for early detection and management of CVDs. This study introduces a novel approach, utilizing photoplethysmogram (PPG) signal spectrograms as inputs for deep learning models to estimate cf-PWV, a significant advancement over traditional methods. Employing a modified ResNet-18 architecture, we analyze PPG signals from digital, radial, and brachial arteries of a simulated dataset of 4374 healthy adults. Our methodology's innovation lies in its direct use of finely tuned spectrogram images, bypassing the complex feature extraction processes. This approach achieved R 2 (correlation coefficient) values of up to 0.9902 for the digital artery, 0.9898 for the radial artery, and 0.9825 for the brachial artery, coupled with significantly lower Mean Absolute Percentage Errors (MAPE) of approximately 1.61% for the digital, 1.87% for the radial, and 2.08% for the brachial artery. These findings highlight the efficacy of PPG spectrograms, especially from the digital artery, in providing an accurate, user-friendly, and non-invasive method for cf-PWV estimation, thereby enhancing the capabilities of non-invasive cardiovascular diagnostics.

关键词： Accuracy Noise Estimation Predictive models Feature extraction Brachytherapy Data models Arteries Spectrogram Monitoring

来源：评论

学校读者我要写书评

暂无评论

Safe Reinforcement Learning-Based Resilient Proactive Scheduling for a Commercial Building Considering Correlated Demand Response

IEEE Open Access Journal of Power and Energy

引用

IEEE Open Access Journal of Power and Energy 2021年 8卷 85-96页

作者： Liang, Zheming Huang, Can Su, Wencong Duan, Nan Donde, Vaibhav Wang, Bin Zhao, Xianbo Department of Electrical and Computer Engineering University of Michigan-Dearborn DearbornMI United States Lawrence Livermore National Laboratory LivermoreCA United States Lawrence Berkeley National Laboratory BerkeleyCA United States School of Engineering and Technology Central Queensland University SydneyNSW Australia

It is a crucial yet challenging task to ensure commercial load resilience during high-impact, low-frequency extreme events. In this paper, a novel safe reinforcement learning (SRL)-based resilient proactive scheduling strategy is proposed for commercial buildings (CBs) subject to extreme weather events. It deploys the correlation between different CB components with demand response capabilities to maximize the customer comfort levels while minimizing the energy reserve cost. It also develops an SRL-based algorithm by combining deep-Q-network and conditional-value-at-risk methods to handle the uncertainties in the extreme weather events such that the impact from extreme epochs in the learning process is greatly mitigated. As a result, an optimum control decision can be derived that targets proactive scheduling goals, where exploration and exploitation are considered simultaneously. Extensive simulation results show that the proposed SRL-based proactive scheduling decisions can ensure the resilience of a commercial building while maintaining comprehensive comfort levels for the occupants. © 2020 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Speed Master: Quick or Slow Play to Attack Speaker Recognition 39

Speed Master: Quick or Slow Play to Attack Speaker Recogniti...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Ye, Zhe Zhang, Wenjie Ren, Ying Kang, Xiangui Yan, Diqun Ma, Bin Wang, Shiqi Guangdong Key Lab of Information Security School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Faculty of Electrical Engineering and Computer Science Ningbo University Ningbo China Key Laboratory of Computing Power Network and Information Security Ministry of Education Qilu University of Technology Shandong Academy of Sciences Jinan China Department of Computer Science City University of Hong Kong Hong Kong

ISBN: (纸本)157735897X

Backdoor attacks pose a significant threat during the model’s training phase. Attackers craft pre-defined triggers to break deep neural networks, ensuring the model accurately classifies clean samples during inference yet erroneously classifies samples added with these triggers. Recent studies have shown that speaker recognition systems trained on large-scale data are susceptible to backdoor attacks. Existing attackers employ unnoticed ambient sounds as triggers. However, these sounds are not inherently part of the training samples themselves. In essence, triggers can be designed to maintain an intrinsic connection with the original speech to enhance stealthiness. Our paper presents a novel attack methodology named Speed Master, which undermines deep neural networks by manipulating the speed of speech samples. Specifically, we execute poison-only backdoor attacks using speed or tempo adjustment. Changes in speech rate have become a common occurrence, as seen on platforms that allow users to adjust playback speed. In real-world scenarios, people naturally adjust their speaking rate depending on the context. As a result, changes in a speaker’s speech rate are typically perceived as normal and are unlikely to raise suspicion. Furthermore, detecting such subtle adjustments becomes challenging for users without reference speech. Our comprehensive experiments demonstrate that Speed Master can achieve an ASR over 99% in the digital domain, with only a 0.6% poisoning rate. Additionally, we validate the feasibility of Speed Master in the real world and its resistance to typical defensive measures. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

A Survey of Graph-Based Resource Management in Wireless Networks -Part II: Learning Approaches

引用

IEEE Transactions on Cognitive Communications and Networking 2024年

作者： Dai, Yanpeng Lyu, Ling Cheng, Nan Sheng, Min Liu, Junyu Wang, Xiucheng Cui, Shuguang Cai, Lin Shen, Xuemin Dalian Maritime University School of Information Science and Technology Dalian116026 China Xidian University State Key Laboratory of ISN the School of Telecommunications Engineering Xian710071 China the Guangdong Provincial Key Laboratory of Future Networks of Intelligence Shenzhen518066 China University of Victoria Department of Electrical and Computer Engineering VictoriaBCV8P 5C2 Canada University of Waterloo Department of Electrical and Computer Engineering WaterlooONN2L 3G1 Canada

This two-part survey provides a comprehensive review of graph optimization and learning for resource management in wireless networks. In Part I, we introduced the fundamentals of graph optimization and provided a recent literature review of graph optimization for resource management in various wireless communication scenarios. In this part, we first present an overview of graph learning and introduce several modern graph neural network models. Then, a state-of-the-art literature review of graph learning for different resource management issues in wireless networks is provided, which covers power control, spectrum management, beamforming design, task scheduling, and aerial coverage planning. Furthermore, we discuss current technical challenges and future research directions of graph optimization and learning for resource management in future wireless networks. © 2024 IEEE.

关键词： Graph neural networks

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：