检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Shan, Hongming de Barros Vimieiro, Rodrigo Borges, Lucas Rodrigues da Costa Vieira, Marcelo Andrade Wang, Ge Dept. of Biomedical Engineering Rensselaer Polytechnic Institute New York United States Dept. of Electrical and Computer Engineering São Carlos School of Engineering University of São Paulo São Carlos Brazil Dept. of Medical Imaging Hematology and Clinical Oncology Ribeirão Preto School of Medicine University of São Paulo Ribeirão Preto Brazil Institute of Science and Technology for Brain-Inspired Intelligence Fudan University Shanghai China Shanghai Center for Brain Science and Brain-Inspired Technology Shanghai China

Digital mammography is still the most common imaging tool for breast cancer screening. Although the benefits of using digital mammography for cancer screening outweigh the risks associated with the x-ray exposure, the radiation dose must be kept as low as possible while maintaining the diagnostic utility of the generated images, thus minimizing patient risks. Many studies investigated the feasibility of dose reduction by restoring low-dose images using deep neural networks. In these cases, choosing the appropriate training database and loss function is crucial and impacts the quality of the results. In this work, a modification of the ResNet architecture, with hierarchical skip connections, is proposed to restore low-dose digital mammography. We compared the restored images to the standard full-dose images. Moreover, we evaluated the performance of several loss functions for this task. For training purposes, we extracted 256,000 image patches from a dataset of 400 images of retrospective clinical mammography exams, where different dose levels were simulated to generate low and standard-dose pairs. To validate the network in a real scenario, a physical anthropomorphic breast phantom was used to acquire real low-dose and standard full-dose images in a commercially avaliable mammography system, which were then processed through our trained model. An analytical restoration model for low-dose digital mammography, previously presented, was used as a benchmark in this work. Objective assessment was performed through the signal-to-noise ratio (SNR) and mean normalized squared error (MNSE), decomposed into residual noise and bias. Results showed that the perceptual loss function (PL4) is able to achieve virtually the same noise levels of a full-dose acquisition, while resulting in smaller signal bias compared to other loss functions. The source code for our deep neural network is available at https://***/WANG-AXIS/LdDMDenoising. © 2021, CC BY.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

5.2dB sensitivity enhancement in 25Gbps APD-based optical receiver using dynamic biasing

5.2dB sensitivity enhancement in 25Gbps APD-based optical re...

引用

Optical Fiber Communication Conference, OFC 2020

作者： Zarkesh-Ha, Payman Efroymson, Robert Fuller, Earl Campbell, Joe C. Hayat, Majeed M. Dynamic Photonics Inc. 1275 Kinnear Rd ColumbusOH43212 United States Center for High Technology Materials and ECE Dept. University of New Mexico 1313 Goddard Street SE AlbuquerqueNM87106-4343 United States Department of Electrical and Computer Engineering University of Virginia PO Box 400743 CharlottesvilleVA22904-4743 United States Department of Electrical and Computer Engineering Marquette University 1515 W. Wisconsin Avenue MilwaukeeWI53233 United States

ISBN: (数字)9781943580712

ISBN: (纸本)9781943580712

First demonstration of dynamically biased 25Gbps avalanche photodiode-based receiver operating at 1.55 µm is reported. A 5.2dB improvement in receiver sensitivity and 10,000-fold reduction in bit-error-rate 25-Gbps are experimentally demonstrated using a commercially available InGaAs-InP APD. OFC 2020 © OSA 2020 © 2020 The Author(s)

关键词： Bit error rate

来源：评论

学校读者我要写书评

暂无评论

Neuromorphic processing at 11 Tera-OPs with soliton crystal Kerr microcombs

Neuromorphic processing at 11 Tera-OPs with soliton crystal ...

引用

2021 IEEE Photonics Society Summer Topicals Meeting Series, SUM 2021

作者： Tan, M. Xu, X. Wu, J. Boes, A. Corcoran, B. Nguyen, T. Chu, S.T. Little, B.E. Morandotti, R. Mitchell, A. Moss, D.J. Optical Sciences Centre Swinburne University of Technology HawthornVIC3122 Australia Dept. of Electrical and Computer Systems Engineering Monash University ClaytonVIC3800 Australia School of Engineering RMIT University MelbourneVIC3001 Australia Department of Physics and Material Science City University of Hong Kong Tat Chee Avenue Hong Kong Xi'an Institute of Optics and Precision Mechanics Precision Mechanics of CAS Xi'an China INRS-Énergie Matériaux et Télécommunications 1650 Boulevard Lionel-Boulet VarennesQCJ3X 1S2 Canada

ISBN: (纸本)9781665416009

We report a new approach to ONNs based on integrated Kerr micro-combs that is programmable, highly scalable and capable of reaching ultra-high speeds. We demonstrate a single neuron perceptron at 11.9 Giga-OPS at 8 bits per OP, or 95.2 Gbps. We then demonstrate a convolutional accelerator operating beyond 11 TeraOPs/s (TOPs). We test the perceptron on handwritten-digit recognition and cancer-cell detection - achieving over 90% and 85% accuracy, respectively. © 2021 IEEE.

关键词： Character recognition

来源：评论

学校读者我要写书评

暂无评论

Optical data transmissionwith high spectral efficiency at44Terabits/s with a soliton crystal micro-comb

Optical data transmissionwith high spectral efficiency at44T...

引用

Signal Processing in Photonic Communications, SPPCom 2021 - Part of OSA Advanced Photonics Congress 2021

作者： Tan, M. Corcoran, B. Xu, X. Wu, J. Boes, A. Nguyen, T. Chu, S. Little, B. Morandotti, R. Mitchell, A. Moss, D.J. Optical Sciences Centre Swinburne University of Technology HawthornVIC3122 Australia Dept. of Electrical and Computer Systems Engineering Monash University ClaytonVIC3800 Australia School of Engineering Rmit University MelbourneVIC3001 Australia Department of Physics and Material Science City University of Hong Kong Tat Chee Avenue Hong Kong Xi'an Institute of Optics and Precision Mechanics Precision Mechanics of Cas Xi'an China INRS-Énergie Matériaux et Télécommunications 1650 Boulevard Lionel-Boulet VarennesQCJ3X 1S2 Canada Institute of Fundamental and Frontier Sciences University of Electronic Science and Technology Chengdu China

We report data transmission over 75km in the lab and a field trial, at 44.2 Tb/s over standard optical fibre using a single integrated chip source, reaching a spectral efficiency of 10.4 bits/s/Hz. © 2021 OSA - T...

ISBN: (纸本)9781557528209

关键词：

来源：评论

学校读者我要写书评

暂无评论

Physics-informed neural networks for securing water distribution systems

arXiv

引用

arXiv 2020年

作者： Falas, Solon Konstantinou, Charalambos Michael, Maria K. Dept. of Electrical and Computer Engineering KIOS Research and Innovation Centre of Excellence University of Cyprus Cyprus FAMU-FSU College of Engineering Center for Advanced Power Systems Florida State University United States

Physics-informed neural networks (PINNs) is an emerging category of neural networks which can be trained to solve supervised learning tasks while taking into consideration given laws of physics described by general nonlinear partial differential equations. PINNs demonstrate promising characteristics such as performance and accuracy using minimal amount of data for training, utilized to accurately represent the physical properties of a system’s dynamic environment. In this work, we employ the emerging paradigm of PINNs to demonstrate their potential in enhancing the security of intelligent cyberphysical systems. In particular, we present a proof-of-concept scenario using the use case of water distribution networks, which involves an attack on a controller in charge of regulating a liquid pump through liquid flow sensor measurements. PINNs are used to mitigate the effects of the attack while demonstrating the applicability and challenges of the approach. Copyright © 2020, The Authors. All rights reserved.

关键词： Embedded systems

来源：评论

学校读者我要写书评

暂无评论

Fully-Passive Quantum Key Distribution

arXiv

引用

arXiv 2022年

作者： Wang, Wenyuan Wang, Rong Zapatero, Victor Qian, Li Qi, Bing Curty, Marcos Lo, Hoi-Kwong Department of Physics University of Hong Kong Pokfulam Road Hong Kong Escuela de Ingeniería de Telecomunicación Department of Signal Theory and Communications University of Vigo Vigo Spain atlanTTic Research Center University of Vigo VigoE-36310 Spain Dept. of Electrical & Computer Engineering University of Toronto TorontoONM5S 3G4 Canada Cisco Systems San JoseCA95134 United States Dept. of Physics University of Toronto TorontoONM5S 3G4 Canada

Passive implementations of quantum key distribution (QKD) sources are highly desirable as they eliminate side-channels that active modulators might introduce. Up till now, passive decoy-state and passive encoding BB84 schemes have both been proposed. Nonetheless, passive decoy-state generation and passive encoding have never been simultaneously implemented with linear optical elements before, which greatly limits the practicality of such passive QKD schemes. In this work, we overcome this limitation and propose a fully-passive QKD source with linear optics that eliminates active modulators for both decoy-state choice and encoding. This allows for highly practical QKD systems that avoid side-channels from the source modulators. The passive source we propose (combined with the decoy-state analysis) can create any arbitrary state on a qubit system and is protocol-independent. That is, it can be used for various protocols such as BB84, reference-frame-independent QKD, or the six-state protocol. It can also in principle be combined with e.g. measurement-device-independent QKD, to build a system without side-channels in either detectors or modulators. Copyright © 2022, The Authors. All rights reserved.

关键词： Quantum cryptography

来源：评论

学校读者我要写书评

暂无评论

Visual object tracking with discriminative filters and siamese networks: A survey and outlook

arXiv

引用

arXiv 2021年

作者： Javed, Sajid Danelljan, Martin Khan, Fahad Shahbaz Khan, Muhammad Haris Felsberg, Michael Matas, Jiri The EECS Department Khalifa University of Science and Technology P.O Box: 127788 Abu Dhabi United Arab Emirates The Computer Vision Lab Dept. of Information Technology and Electrical Engineering ETH Zürich Switzerland Computer Vision Department MBZUAI Abu Dhabi United Arab Emirates Computer Vision Laboratory Linköping University Sweden Center for Machine Perception Czech Technical University Prague Czech Republic

Accurate and robust visual object tracking is one of the most challenging and fundamental computer vision problems. It entails estimating the trajectory of the target in an image sequence, given only its initial location, and segmentation, or its rough approximation in the form of a bounding box. Discriminative Correlation Filters (DCFs) and deep Siamese Networks (SNs) have emerged as dominating tracking paradigms, which have led to significant progress. Following the rapid evolution of visual object tracking in the last decade, this survey presents a systematic and thorough review of more than 90 DCFs and Siamese trackers, based on results in nine tracking benchmarks. First, we present the background theory of both the DCF and Siamese tracking core formulations. Then, we distinguish and comprehensively review the shared as well as specific open research challenges in both these tracking paradigms. Furthermore, we thoroughly analyze the performance of DCF and Siamese trackers on nine benchmarks, covering different experimental aspects of visual tracking: datasets, evaluation metrics, performance, and speed comparisons. We finish the survey by presenting recommendations and suggestions for distinguished open challenges based on our analysis. © 2021, CC BY-SA.

关键词： Surveys

来源：评论

学校读者我要写书评

暂无评论

Variable frame rate-based data augmentation to handle speaking-style variability for automatic speaker verification

arXiv

引用

arXiv 2020年

作者： Afshan, Amber Guo, Jinxi Park, Soo Jin Ravi, Vijay McCree, Alan Alwan, Abeer Dept. of Electrical and Computer Engineering University of California Los Angeles United States Human Language Technology Center of Excellence Johns Hopkins University Baltimore United States

The effects of speaking-style variability on automatic speaker verification were investigated using the UCLA Speaker Variability database which comprises multiple speaking styles per speaker. An x-vector/PLDA (probabilistic linear discriminant analysis) system was trained with the SRE and Switchboard databases with standard augmentation techniques and evaluated with utterances from the UCLA database. The equal error rate (EER) was low when enrollment and test utterances were of the same style (e.g., 0.98% and 0.57% for read and conversational speech, respectively), but it increased substantially when styles were mismatched between enrollment and test utterances. For instance, when enrolled with conversation utterances, the EER increased to 3.03%, 2.96% and 22.12% when tested on read, narrative, and pet-directed speech, respectively. To reduce the effect of style mismatch, we propose an entropy-based variable frame rate technique to artificially generate style-normalized representations for PLDA adaptation. The proposed system significantly improved performance. In the aforementioned conditions, the EERs improved to 2.69% (conversation – read), 2.27% (conversation – narrative), and 18.75% (pet-directed – read). Overall, the proposed technique performed comparably to multi-style PLDA adaptation without the need for training data in different speaking styles per speaker. Copyright © 2020, The Authors. All rights reserved.

关键词： Database systems

来源：评论

学校读者我要写书评

暂无评论

AITIA: Embedded AI Techniques for Embedded Industrial Applications

AITIA: Embedded AI Techniques for Embedded Industrial Applic...

引用

2020 International Conference on Omni-layer Intelligent systems (COINS)

作者： Marcelo Brandalero Muhammad Ali Laurens Le Jeune Hector Gerardo Muñoz Hernandez Mitko Veleski Bruno da Silva Jan Lemeire Kristof Van Beeck Abdellah Touhafi Toon Goedemé Nele Mentens Diana Göhringer Michael Hübner Chair of Computer Engineering Brandenburg University of Technology Cottbus-Senftenberg Germany Chair of Adaptive Dynamic Systems Technical University Dresden Germany Dept. of Electrical Engineering (ESAT) at KU Leuven Belgium Dept. of Industrial Sciences (INDI) VUB Brussels Belgium

ISBN: (数字)9781728163710

ISBN: (纸本)9781728163727

New achievements in Artificial Intelligence (AI) and Machine Learning (ML) are reported almost daily by the big companies. While those achievements are accomplished by fast and massive data processing techniques, the potential of embedded machine learning, where intelligent algorithms run in resource-constrained devices rather than in the cloud, is still not understood well by the majority of the industrial players and Small and Medium Entereprises (SMEs). Nevertheless, the potential embedded machine learning for processing high-performance algorithms without relying on expensive cloud solutions is perceived as very high. This potential has led to a broad demand by industry and SMEs for a practical and application-oriented feasibility study, which helps them to understand the potential benefits, but also the limitations of embedded AI. To address these needs, this paper presents the approach of the AITIA project, a consortium of four Universities which aims at developing and demonstrating best practices for embedded AI by means of four industrial case studies of high-relevance to the European industry and SMEs: sensors, security, automotive and industry 4.0.

关键词： Machine learning Sensor arrays Intrusion detection Machine learning algorithms Industries

来源：评论

学校读者我要写书评

暂无评论

A Local Characterization for Wyner Common Information

A Local Characterization for Wyner Common Information

引用

IEEE International Symposium on Information Theory

作者： Shao-Lun Huang Xiangxiang Xu Lizhong Zheng Gregory W. Wornell DSIT Research Center Tsinghua-Berkeley Shenzhen Institute Shenzhen China Dept. of Electronic Engineering Tsinghua University Beijing China Dept. of Electrical & Computer Eng. Massachusetts Institute of Technology Cambridge MA

ISBN: (数字)9781728164328

ISBN: (纸本)9781728164335

While the Hirschfeld-Gebelein-Rényi (HGR) maximal correlation and the Wyner common information share similar information processing purposes of extracting common knowledge structures between random variables, the relationships between these approaches are generally unclear. In this paper, we demonstrate such relationships by considering the Wyner common information in the weakly dependent regime, called ε-common information. We show that the HGR maximal correlation functions coincide with the relative likelihood functions of estimating the auxiliary random variables in ε-common information, which establishes the fundamental connections these approaches. Moreover, we extend the ε-common information to multiple random variables, and derive a novel algorithm for extracting feature functions of data variables regarding their common information. Our approach is validated by the MNIST problem, and can potentially be useful in multi-modal data analyses.

关键词：

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：