检索结果-内蒙古大学图书馆

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Hongqiang Du Xiaohai Tian Lei Xie Haizhou Li Audio Speech and Langauge Processing Laboratory School of Computer Science Northwestern Polytechnical University China Department of Electrical and Computer Engineering National University of Singapore Singapore

ISBN: (数字)9781509066315

ISBN: (纸本)9781509066322

WaveNet has shown its great potential as a direct conversion model in voice conversion. However, due to the model complexity, WaveNet always requires a large amount of training data, which has limited its applications in voice conversion, where training data is scarce. In this paper, we propose a WaveNet adaptation method that effectively reduces the need of adaptation data. We first train a speaker independent WaveNet conversion model with multi-speaker dataset. Adaptation is then applied with limited target speaker's data. Specifically, singular value decomposition (SVD) is applied to dilated convolution layers of WaveNet to reduce the number of parameters, which makes adaptation more effective with limited data. Experiments conducted on CMU-ARCTIC and CSTR-VCTK corpus show that the proposed method outperforms baseline methods in terms of both quality and similarity.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient Probabilistic Semantic Communication over Space-Air-Ground Integrated Networks

引用

IEEE Transactions on Wireless Communications 2025年

作者： Zhao, Zhouxiang Yang, Zhaohui Chen, Mingzhe Zhu, Chen Xu, Wei Zhang, Zhaoyang Huang, Kaibin Zhejiang University College of Information Science and Electronic Engineering China Zhejiang Provincial Key Laboratory of Info. Proc. Commun Hangzhou310027 China University of Miami Department of Electrical and Computer Engineering Institute for Data Science and Computing Coral GablesFL33146 United States Zhejiang University Polytechnic Institute Hangzhou310015 China Hangzhou Dianzi University School of Communication Engineering Hangzhou310018 China Southeast University National Mobile Communications Research Laboratory Nanjing211189 China The University of Hong Kong Department of Electrical and Electronic Engineering Hong Kong

Space-air-ground integrated networks (SAGINs) are emerging as a pivotal element in the evolution of future wireless networks. Despite their potential, the joint design of communication and computation within SAGINs remains a formidable challenge. In this paper, the problem of energy efficiency in SAGIN-enabled probabilistic semantic communication (PSCom) system is investigated. In the considered model, a satellite needs to transmit data to multiple ground terminals (GTs) via an unmanned aerial vehicle (UAV) acting as a relay. During transmission, the satellite and the UAV can use PSCom technique to compress the transmitting data, while the GTs can automatically recover the missing information. The PSCom is underpinned by shared probabilistic graphs that serve as a common knowledge base among the transceivers, allowing for resource-saving communication at the expense of increased computation resource. Through analysis, the computation overhead function in PSCom is a piecewise function with respect to the semantic compression ratio. Therefore, it is important to make a balance between communication and computation to achieve optimal energy efficiency. The joint communication and computation problem is formulated as an optimization problem aiming to minimize the total communication and computation energy consumption of the network under latency, power, computation capacity, bandwidth, semantic compression ratio, and UAV location constraints. To solve this non-convex non-smooth problem, we propose an iterative algorithm where the closed-form solutions for computation capacity allocation and UAV altitude are obtained at each iteration. Numerical results show the effectiveness of the proposed algorithm. © 2002-2012 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Classification of Breast cancer lesions in ultrasound images by using attention layer and loss ensembles in deep convolutional neural networks

arXiv

引用

arXiv 2021年

作者： Kalafi, Elham Yousef Jodeiri, Ata Setarehdan, Seyed Kamaledin Lin, Ng Wei Rahman, Kartini Binti Taib, Nur Aishah Dhillon, Sarinder Kaur Data Science & Bioinformatics Laboratory Institute of Biological Sciences Faculty of Science University of Malaya Kuala Lumpur Malaysia School of Electrical and Computer Engineering College of Engineering University of Tehran Tehran Iran Department of Biomedical Imaging Faculty of Medicine University of Malaya Kuala Lumpur50603 Malaysia Department of Surgery Faculty of Medicine University of Malaya Kuala Lumpur Malaysia

Reliable classification of benign and malignant lesions in breast ultrasound images can provide an effective and relatively low cost method for early diagnosis of breast cancer. The accuracy of the diagnosis is however highly dependent on the quality of the ultrasound systems and the experience of the users (radiologists). The leverage in deep convolutional neural network approaches provided solutions in efficient analysis of breast ultrasound images. In this study, we proposed a new framework for classification of breast cancer lesions by use of an attention module in modified VGG16 architecture. We also proposed new ensembled loss function which is the combination of binary cross-entropy and logarithm of the hyperbolic cosine loss to improve the model discrepancy between classified lesions and its labels. Networks trained from pretrained ImageNet weights, and subsequently fine-tuned with ultrasound datasets. The proposed model in this study outperformed other modified VGG16 architectures with the accuracy of 93% and also the results are competitive with other state of the art frameworks for classification of breast cancer lesions. In this study, we employed transfer learning approaches with the pre-trained VGG16 architecture. Different CNN models for classification task were trained to predict benign or malignant lesions in breast ultrasound images. Our Experimental results show that the choice of loss function is highly important in classification task and by adding an attention block we could empower the performance our model. © 2021, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Heralding Single Photons using Photon-number-resolving Superconducting Nanowires

Heralding Single Photons using Photon-number-resolving Super...

引用

Conference on Lasers and Electro-Optics (CLEO)

作者： Samantha I. Davis Andrew Mueller Raju Valivarthi Nikolai Lauk Lautaro Narvaez Boris Korzh Andrew D. Beyer Marco Colangelo Karl K. Berggren Matthew D. Shaw Neil Sinclair Maria Spiropulu Division of Physics Mathematics and Astronomy California Institute of Technology Pasadena CA USA Alliance for Quantum Technologies (AQT) California Institute of Technology Pasadena CA USA Jet Propulsion Laboratory California Institute of Technology Pasadena CA USA Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology Cambridge MA USA John A. Paulson School of Engineering and Applied Sciences Harvard University Cambridge MA USA

ISBN: (数字)9781957171050

ISBN: (纸本)9781665466660

We improve a single photon source based on spontaneous parametric down-conversion by heralding one of the output modes using a photon number resolving superconducting nanowire detector. We measure a reduced magnitude of the second order cross correlation of one of the output modes conditioned on detection of a single photon in the other mode.

关键词： Correlation Measurement by laser beam Detectors Laser modes Electrooptical waveguides Photonics

来源：评论

学校读者我要写书评

暂无评论

Harmonized-Multinational qEEG norms (HarMNqEEG)

引用

NEUROIMAGE 2022年 256卷 119190-119190页

作者： Li, Min Wang, Ying Lopez-Naranjo, Carlos Hu, Shiang Reyes, Ronaldo Cesar Garcia Paz-Linares, Deirel Areces-Gonzalez, Ariosky Hamid, Aini Ismafairus Abd Evans, Alan C. Savostyanov, Alexander N. Calzada-Reyes, Ana Villringer, Arno Tobon-Quintero, Carlos A. Garcia-Agustin, Daysi Yao, Dezhong Dong, Li Aubert-Vazquez, Eduardo Reza, Faruque Razzaq, Fuleah Abdul Omar, Hazim Abdullah, Jafri Malin Galler, Janina R. Ochoa-Gomez, John F. Prichep, Leslie S. Galan-Garcia, Lidice Morales-Chacon, Lilia Valdes-Sosa, Mitchell J. Trondle, Marius Zulkifly, Mohd Faizal Mohd Rahman, Muhammad Riddha Bin Abdul Milakhina, Natalya S. Langer, Nicolas Rudych, Pavel Koenig, Thomas Virues-Alba, Trinidad A. Lei, Xu Bringas-Vega, Maria L. Bosch-Bayard, Jorge F. Valdes-Sosa, Pedro Antonio The Clinical Hospital of Chengdu Brain Science Institute MOE Key Lab for Neuroinformation School of Life Science and Technology University of Electronic Science and Technology of China Chengdu China Brain and Behaviour Cluster School of Medical Sciences Universiti Sains Malaysia Health Campus Kota Bharu Kelantan 16150 Malaysia Anhui Provincial Key Laboratory of Multimodal Cognitive Computation Key Laboratory of Intelligent Computing & Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei 230601 China Cuban Center for Neurocience La Habana Cuba University of Pinar del Río “Hermanos Saiz Montes de Oca” Pinar del Río Cuba Department of Neurosciences School of Medical Sciences Universiti Sains Malaysia Universiti Sains Malaysia Health Campus Kota Bharu Kelantan 16150 Malaysia Hospital Universiti Sains Malaysia Universiti Sains Malaysia Health Campus Kota Bharu Kelantan 16150 Malaysia McGill Centre for Integrative Neuroscience Ludmer Centre for Neuroinformatics and Mental Health Montreal Neurological Institute Canada Humanitarian Institute Novosibirsk State University Novosibirsk 630090 Russia Laboratory of Psychophysiology of Individual Differences Federal State Budgetary Scientific Institution Scientific Research Institute of Neurosciences and Medicine Novosibirsk 630117 Russia Laboratory of Psychological Genetics at the Institute of Cytology and Genetics Siberian Branch of the Russian Academy of Sciences Novosibirsk 630090 Russia Department of Neurology Max Planck Institute for Human Cognitive and Brain Sciences Leipzig Germany Department of Cognitive Neurology University Hospital Leipzig Leipzig Germany Center for Stroke Research Charité-Universitätsmedizin Berlin Berlin Germany Grupo Neuropsicología y Conducta - GRUNECO Faculty of Medicine Universidad de Antioquia Colombia Research Department Institución Prestadora de Servicios de Salud IPS Universitaria Colombia The Cuban center aging longevity and healt

This paper extends frequency domain quantitative electroencephalography (qEEG) methods pursuing higher sensitivity to detect Brain Developmental Disorders. Prior qEEG work lacked integration of cross-spectral information omitting important functional connectivity descriptors. Lack of geographical diversity precluded accounting for site-specific variance, increasing qEEG nuisance variance. We ameliorate these weaknesses. (i) Create lifespan Riemannian multinational qEEG norms for cross-spectral tensors. These norms result from the HarMNqEEG project fostered by the Global Brain Consortium. We calculate the norms with data from 9 countries, 12 devices, and 14 studies, including 1564 subjects. Instead of raw data, only anonymized metadata and EEG cross spectral tensors were shared. After visual and automatic quality control, developmental equations for the mean and standard deviation of qEEG traditional and Riemannian DPs were calculated using additive mixed-effects models. We demonstrate qEEG "batch effects " and provide methods to calculate harmonized z-scores. (ii) We also show that harmonized Riemannian norms produce z-scores with increased diagnostic accuracy predicting brain dysfunction produced by malnutrition in the first year of life and detecting COVID induced brain dysfunction. (iii) We offer open code and data to calculate different individual z-scores from the HarMNqEEG dataset. These results contribute to developing bias-free, low-cost neuroimaging technologies applicable in various health settings.

关键词： Quantitative EEG EEG cross-spectrum Riemannian geometry Batch effects Z-score Harmonization Malnutrition Covid induced brain dysfunction Developmental Brain Chart

来源：评论

学校读者我要写书评

暂无评论

Dynamic Spectrum Aggregation and Access for Rescue Cognitive Networks Using Multi-Agent Actor-Critic Reinforcement Learning

引用

IEEE Transactions on Cognitive Communications and Networking 2025年

作者： Zhang, Wensheng Ding, Wenjiao Wang, Cheng-Xiang Chen, Yunfei Abreu, Giuseppe Liu, Zhi Sun, Jian Han, Zhu Shandong University School of Information Science and Engineering Shandong Key Laboratory of Intelligent Communication and Sensing-Computing Integration Qingdao266237 China Industrial and Commercial Bank Of China Limited Shandong Branch Jinan China Southeast University National Mobile Communications Research Laboratory School of Information Science and Engineering Nanjing211189 China Purple Mountain Laboratories Pervasive Communication Research Center Nanjing211111 China Durham University Department of Engineering DurhamDH1 3LE United Kingdom Constructor University Bremen GGMBH School of Computer Science and Engineering Campus Ring 1 Bremen28757 Germany University of Houston Department of Electrical and Computer Engineering HoustonTX77004 United States Kyung Hee University Department of Computer Science and Engineering Seoul446-701 Korea Republic of

Unmanned aerial vehicles (UAVs) based emergency communication is gaining more attention for disaster rescue, where the UAV can work as an aerial base station to provide spectrum access in areas with power outages or network interruptions. However, UAVs can only provide limited spectrum access for a short period of time due to limited battery energy. Aiming to providing spectrum access to more users under spectrum and energy limitations, a new dynamic spectrum aggregation and access scheme is proposed for rescue cognitive networks (RCNs), in which different kinds of users are modeled as primary users (PUs) and secondary users (SUs). In each time slot, SUs with different spectrum sensing capabilities, spectrum aggregation capabilities, and bandwidth demands need to sense and aggregate multiple spectrum slots that are not occupied by PUs for data transmission. Based on selected channel states, the reward is designed as a function of transmission rates and is fed back to SUs. A maximum entropy based multi-agent actor-critic (ME-MAAC) algorithm is proposed to optimize the action selection policy for SUs. Simulation results show that the proposed ME-MAAC algorithm can effectively achieve higher achievable rate, lower mean collision rate and lower power consumption, than state-of-the-art methods based on Deep Q-Network (DQN) algorithm. The proposed RCNs provide a novel spectrum usage paradigm for emergency communication and rescue networks. © 2015 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Steady-state planning in expected reward multichain MDPs

arXiv

引用

arXiv 2020年

作者： Atia, George K. Beckus, Andre Alkhouri, Ismail Velasquez, Alvaro Department of Electrical and Computer Engineering Department of Computer Science University of Central Florida FL32816 United States Air Force Research Laboratory NY13441 United States

The planning domain has experienced increased interest in the formal synthesis of decision-making policies. This formal synthesis typically entails finding a policy which satisfies formal specifications in the form of some well-defined logic. While many such logics have been proposed with varying degrees of expressiveness and complexity in their capacity to capture desirable agent behavior, their value is limited when deriving decision-making policies which satisfy certain types of asymptotic behavior in general system models. In particular, we are interested in specifying constraints on the steady-state behavior of an agent, which captures the proportion of time an agent spends in each state as it interacts for an indefinite period of time with its environment. This is sometimes called the average or expected behavior of the agent and the associated planning problem is faced with significant challenges unless strong restrictions are imposed on the underlying model in terms of the connectivity of its graph structure. In this paper, we explore this steady-state planning problem that consists of deriving a decision-making policy for an agent such that constraints on its steady-state behavior are satisfied. A linear programming solution for the general case of multichain Markov Decision Processes (MDPs) is proposed and we prove that optimal solutions to the proposed programs yield stationary policies with rigorous guarantees of behavior. Copyright © 2020, The Authors. All rights reserved.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Polychromatic electric field knots

arXiv

引用

arXiv 2021年

作者： Ferrer-Garcia, Manuel F. D’Errico, Alessio Sit, Alicia Laroque, Hugo Karimi, Ebrahim Department of Physics University of Ottawa Advanced Research Complex 25 Templeton OttawaONK1N 6N5 Canada Research Laboratory of Electronics Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology CambridgeMA United States

The polarization of a monochromatic optical beam lies in a plane, and in general, is described by an ellipse, known as the polarization ellipse. The polarization ellipse in the tight focusing (non-paraxial) regime forms non-trivial three-dimensional topologies, such as Möbius and ribbon strips, as well as knots. The latter is formed when the dynamics of specific polarization states, e.g., circular polarization states, is studied upon propagation. However, there is an alternative method to generate optical knots: the electric field’s tip can be made to locally evolve along a knot trajectory in time. We propose an intuitive technique to generate and engineer the path traced by the electric field vector of polychromatic beams to form different knots. In particular, we show examples of how tightly focused beams with at least three frequency components and different spatial modes can cause the tip of the electric field vector to follow, locally, a knotted trajectory. Furthermore, we characterize the generated knots and explore different knot densities upon free-space propagation in the focal volume. Our study may provide insight for designing current densities when structured polychromatic electromagnetic fields interact with materials. © 2021, CC BY.

关键词： Electromagnetic fields

来源：评论

学校读者我要写书评

暂无评论

Charged Defect Healing by N, N'–Di (Naphthalene-1-Yl)-N, N' Diphenyl Benzidine at the Interface of Cuins2 Nanoparticle Hole Transporting Materials in Carbon-Based Halide Perovskite Solar Cells

SSRN

引用

SSRN 2022年

作者： Heydari, Mahsa Mohammadi, Mahdi Baghestani, Elham Tajabadi, Fariba Bowman, Alan R. Roose, Bart Forouzandeh, Mozhdeh Heidariramsheh, Maryam Stranks, Samuel D. Abdi, Yaser Taghavinia, Nima Nanoparticles and Coating Lab Department of Physics Sharif University of Technology Tehran11365-9161 Iran Nanophysics Research Laboratory Department of Physics University of Tehran Tehran*** Iran Department of Electrical and Computer Engineering Tarbiat Modares University Tehran14115-194 Iran Department of Nanotechnology and Advanced Materials Materials and Energy Research Center Karaj*** Iran Station 9 LausanneCH-1015 Switzerland Cavendish Laboratory Department of Chemical Engineering & Biotechnology University of Cambridge CambridgeCB3 0HE United Kingdom Institute for Nano Science and Nanotechnology Sharif University of Technology Tehran14588-89694 Iran

Recently, inorganic nanoparticles have been studied as hole transporting materials (HTM) in perovskite solar cells (PSCs). Inorganic HTMs are believed to provide better stability compared to conventional organic HTMs, such as spiro-OMeTAD. One of the challenges of nanoparticle HTMs is the high density of defects at the interface with the perovskite film, which reduces the device’s fill factor. In this study, we use N, N'–di (naphthalene-1-yl)-N, N' diphenyl benzidine (NPB) small molecules to passivate the surface of perovskite films in carbon-based PSCs with CuInS 2 nanoparticles as the HTM. By applying NPB, trap density decreases from 1.35×10 16 cm -3 to 5.09×10 15 cm -3 . NPB interface passivation results in a power conversion efficiency (PCE) of 16.11% compared to the control device with PCE of 14.92% in carbon-based perovskite solar cells. Moreover, improved contact angle was obtained for NPB surface-treated film (61.9°) compared to the reference film (40.6°), providing better protection against moisture induced degradation. The surface-treated devices maintained 92% of their efficiency after 4,000 hours of storage at ambient condition, while the control device showed a rapid and notable degradation, losing >58% of the initial efficiency under the same condition. © 2022, The Authors. All rights reserved.

关键词： Perovskite solar cells

来源：评论

学校读者我要写书评

暂无评论

Method of moment analysis of carbon nanotubes embedded in a lossy dielectric slab using a multilayer dyadic green’s function

TechRxiv

引用

TechRxiv 2021年

作者： Dey, Sumitra Chatterjee, Deb Garboczi, Edward J. Hassan, Ahmed M. Department of Computer Science and Electrical Engineering University of Missouri–Kansas City Kansas CityMO64110 United States Material Measurement Laboratory Applied Chemicals and Materials Division National Institute of Standards and Technology BoulderCO80305 United States

Modeling the electromagnetic response of carbon nanotube (CNT) reinforced composites is inherently a three-dimensional (3D) multi-scale problem that is challenging to solve in real-time for nondestructive evaluation applications. This article presents a fast and accurate full-wave electromagnetic solver based on a multi-layer dyadic Green’s function approach. In this approach, we account for the effects of the dielectric slab, where the CNTs are embedded, without explicitly discretizing its interfaces. Due to their large aspect ratios, the CNTs are modeled as arbitrary thin wires (ATWs), and the method of moment (MoM) formulation with distributed line impedance is used to solve for their coupled currents. The accuracy of the in-house solver is validated against commercial method of moment (MoM) and finite element method (FEM) solvers over a broad range of frequencies (from 1 GHz to 10 THz) and for a wide range of dielectric slab properties. Examples of 100 nm long vertical and horizontal CNTs embedded in a 1 µm thick lossy dielectric substrate are presented. The in-house solver provides more than 50 × speed up while solving the vertical CNT, and more than 570 × speed up while solving the horizontal CNT than a commercial MoM solver over the GHz to THz frequency range. © 2021, CC BY-NC-SA.

关键词： Method of moments

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：