检索结果-内蒙古大学图书馆

Exploiting deep learning for secure transmission in an underlay cognitive radio network

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhang, Miao Cumanan, Kanapathippillai Thiyagalingam, Jeyarajan Tang, Yanqun Wang, Wei Ding, Zhiguo Dobre, Octavia A. School of Information Science and Engineering Chongqing Jiaotong University Chongqing China Department of Electronic Engineering University of York YorkYO10 5DD United Kingdom Scientific Computing Department of Rutherford Appleton Laboratory Science and Technology Facilities Council Harwell Campus Ditcot United Kingdom School of Electronics and Communication Engineering Sun Yat-Sen University Shenzhen510006 China School of Information Science and Technology Nantong University Nantong China Nantong Research Institute for Advanced Communication Technologies Nantong China Research Center of Networks and Communications Peng Cheng Laboratory Shenzhen China School of Electrical and Electronic Engineering University of Manchester Manchester United Kingdom Department of Electrical and Computer Engineering Memorial University St. John’sNLA1B 3X5 Canada

This paper investigates a machine learning-based power allocation design for secure transmission in a cognitive radio (CR) network. In particular, a neural network (NN)based approach is proposed to maximize the secrecy rate of the secondary receiver under the constraints of total transmit power of secondary transmitter, and the interference leakage to the primary receiver, within which three different regularization schemes are developed. The key advantage of the proposed algorithm over conventional approaches is the capability to solve the power allocation problem with both perfect and imperfect channel state information. In a conventional setting, two completely different optimization frameworks have to be designed, namely the robust and non-robust designs. Furthermore, conventional algorithms are often based on iterative techniques, and hence, they require a considerable number of iterations, rendering them less suitable in future wireless networks where there are very stringent delay constraints. To meet the unprecedented requirements of future ultra-reliable low-latency networks, we propose an NN-based approach that can determine the power allocation in a CR network with significantly reduced computational time and complexity. As this trained NN only requires a small number of linear operations to yield the required power allocations, the approach can also be extended to different delay sensitive applications and services in future wireless networks. When evaluate the proposed method versus conventional approaches, using a suitable test set, the proposed approach can achieve more than 94% of the secrecy rate performance with less than 1% computation time and more than 93% satisfaction of interference leakage constraints. These results are obtained with significant reduction in computational time, which we believe that it is suitable for future real-time wireless applications. © 2021, CC0.

关键词： Cognitive radio

Fusing Bluetooth with Pedestrian Dead Reckoning: A Floor Plan-Assisted Positioning Approach

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Pan, Wenxuan Yang, Yang Chen, Mingzhe Wei, Dong Guo, Caili Mao, Shiwen Beijing Key Laboratory of Network System Architecture and Convergence School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing100876 China Department of Electrical and Computer Engineering the Institute for Data Science and Computing University of Miami Coral GablesFL33146 United States Institute of Information Engineering Chinese Academy of Sciences Beijing100093 China Beijing Laboratory of Advanced Information Networks School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing100876 China Wireless Engineering Research and Education Center Auburn University AuburnAL36849 United States

Floor plans can provide valuable prior information that helps enhance the accuracy of indoor positioning systems. However, existing research typically faces challenges in efficiently leveraging floor plan information and applying it to complex indoor layouts. To fully exploit information from floor plans for positioning, we propose a floor plan-assisted fusion positioning algorithm (FP-BP) using Bluetooth low energy (BLE) and pedestrian dead reckoning (PDR). In the considered system, a user holding a smartphone walks through a positioning area with BLE beacons installed on the ceiling, and can locate himself in real time. In particular, FP-BP consists of two phases. In the offline phase, FP-BP programmatically extracts map features from a stylized floor plan based on their binary masks, and constructs a mapping function to identify the corresponding map feature of any given position on the map. In the online phase, FP-BP continuously computes BLE positions and PDR results from BLE signals and smartphone sensors, where a novel grid-based maximum likelihood estimation (GML) algorithm is introduced to enhance BLE positioning. Then, a particle filter is used to fuse them and obtain an initial estimate. Finally, FP-BP performs post-position correction to obtain the final position based on its specific map feature. Experimental results show that FP-BP can achieve a real-time mean positioning accuracy of 1.19 m, representing an improvement of over 28% compared to existing floor plan-fused baseline algorithms. Copyright © 2025, The Authors. All rights reserved.

关键词： Photomapping

Channel pruning via automatic structure search

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Lin, Mingbao Ji, Rongrong Zhang, Yuxin Zhang, Baochang Wu, Yongjian Tian, Yonghong Media Analytics and Computing Laboratory Department of Artificial Intelligence School of Informatics Xiamen University China School of Automation Science and Electrical Engineering Beihang University China Co. Ltd China School of Electronics Engineering and Computer Science Peking University Beijing China Peng Cheng Laboratory Shenzhen China

Channel pruning is among the predominant approaches to compress deep neural networks. To this end, most existing pruning methods focus on selecting channels (filters) by importance/ optimization or regularization based on ruleof- thumb designs, which defects in sub-optimal pruning. In this paper, we propose a new channel pruning method based on artificial bee colony algorithm (ABC), dubbed as ABCPruner, which aims to efficiently find optimal pruned structure, i.e., channel number in each layer, rather than selecting "important" channels as previous works did. To solve the intractably huge combinations of pruned structure for deep networks, we first propose to shrink the combinations where the preserved channels are limited to a specific space, thus the combinations of pruned structure can be significantly reduced. And then, we formulate the search of optimal pruned structure as an optimization problem and integrate the ABC algorithm to solve it in an automatic manner to lessen human interference. ABCPruner has been demonstrated to be more effective, which also enables the fine-tuning to be conducted efficiently in an end-to-end manner. Experiments on CIFAR-10 show that ABCPruner reduces 73.68% of FLOPs and 88.68% of parameters with even 0.06% accuracy improvement for VGGNet-16. On ILSVRC-2012, it achieves a reduction of 62.87% FLOPs and removes 60.01% of parameters with negligible accuracy cost for ResNet-152. The source codes can be available at https://***/lmbxmu/ABCPruner. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep neural networks

Vector Symbolic Architectures as a computing Framework for Emerging Hardware

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Kleyko, Denis Davies, Mike Frady, E. Paxon Kanerva, Pentti Kent, Spencer J. Olshausen, Bruno A. Osipov, Evgeny Rabaey, Jan M. Rachkovskij, Dmitri A. Rahimi, Abbas Sommer, Friedrich T. The Redwood Center for Theoretical Neuroscience The University of California BerkeleyCA94720 United States The Intelligent Systems Lab Research Institutes of Sweden Kista16440 Sweden The Neuromorphic Computing Laboratory Intel Labs Santa ClaraCA95054 United States The Department of Computer Science Electrical and Space Engineering Luleå University of Technology Luleå97187 Sweden The Department of Electrical Engineering and Computer Sciences The University of California BerkeleyCA94720 United States International Research and Training Center for Information Technologies and Systems Kyiv03680 Ukraine IBM Research – Zurich Rüschlikon8803 Switzerland

This article reviews recent progress in the development of the computing framework Vector Symbolic Architectures (also known as Hyperdimensional computing). This framework is well suited for implementation in stochastic, emerging hardware and it naturally expresses the types of cognitive operations required for Artificial Intelligence (AI). We demonstrate in this article that the field-like algebraic structure of Vector Symbolic Architectures offers simple but powerful operations on high-dimensional vectors that can support all data structures and manipulations relevant to modern computing. In addition, we illustrate the distinguishing feature of Vector Symbolic Architectures, "computing in superposition," which sets it apart from conventional computing. It also opens the door to efficient solutions to the difficult combinatorial search problems inherent in AI applications. We sketch ways of demonstrating that Vector Symbolic Architectures are computationally universal. We see them acting as a framework for computing with distributed representations that can play a role of an abstraction layer for emerging computing hardware. This article serves as a reference for computer architects by illustrating the philosophy behind Vector Symbolic Architectures, techniques of distributed computing with them, and their relevance to emerging computing hardware, such as neuromorphic computing. Copyright © 2021, The Authors. All rights reserved.

关键词： Vectors

Optimizing for periodicity: a model-independent approach to flux crosstalk calibration for superconducting circuits

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Dai, X. Trappen, R. Yang, R. Disseler, S.M. Basham, J.I. Gibson, J. Melville, A.J. Niedzielski, B.M. Das, R. Kim, D.K. Yoder, J.L. Weber, S.J. Hirjibehedin, C.F. Lidar, D.A. Lupascu, A. Institute for Quantum Computing Department of Physics and Astronomy University of Waterloo WaterlooONN2L 3G1 Canada Lincoln Laboratory Massachusetts Institute of Technology LexingtonMA02421 United States Department of Physics and Astronomy Dartmouth College HanoverNH03755 United States Departments of Electrical & Computer Engineering Chemistry and Physics Center for Quantum Information Science & Technology University of Southern California Los AngelesCA90089 United States Waterloo Institute for Nanotechnology University of Waterloo WaterlooONN2L 3G1 Canada

Flux tunability is an important engineering resource for superconducting circuits. Large-scale quantum computers based on flux-tunable superconducting circuits face the problem of flux crosstalk, which needs to be accurately calibrated to realize high-fidelity quantum operations. Typical calibration methods either assume that circuit elements can be effectively decoupled and simple models can be applied, or require a large amount of data. Such methods become ineffective as the system size increases and circuit interactions become stronger. Here we propose a new method for calibrating flux crosstalk, which is independent of the underlying circuit model. Using the fundamental property that superconducting circuits respond periodically to external fluxes, crosstalk calibration of N flux channels can be treated as N independent optimization problems, with the objective functions being the periodicity of a measured signal depending on the compensation parameters. We demonstrate this method on a small-scale quantum annealing circuit based on superconducting flux qubits, achieving comparable accuracy with previous methods. We also show that the objective function usually has a nearly convex landscape, allowing efficient optimization. Copyright © 2022, The Authors. All rights reserved.

关键词： Crosstalk

Generating Approximate Ground States of Molecules Using Quantum Machine Learning

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Ceroni, Jack Stetina, Torin F. Kieferová, Mária Marrero, Carlos Ortiz Arrazola, Juan Miguel Wiebe, Nathan Xanadu TorontoONM5G 2C8 Canada Department of Mathematics University of Toronto TorontoONM5S 3E1 Canada Simons Institute for the Theory of Computing BerkeleyCA94704 United States Berkeley Quantum Information and Computation Center University of California BerkeleyCA94720 United States Centre for Quantum Computation and Communication Technology Centre for Quantum Software and Information University of Technology SydneyNSW2007 Australia AI & Data Analytics Division Pacific Northwest National Laboratory RichlandWA99354 United States Department of Electrical & Computer Engineering North Carolina State University RaleighNC27607 United States Department of Computer Science University of Toronto ONM5S 1A1 Canada High Performance Computing Group Pacific Northwest National Laboratory RichlandWA99354 United States

The potential energy surface (PES) of molecules with respect to their nuclear positions is a primary tool in understanding chemical reactions from first principles. However, obtaining this information is complicated by the fact that sampling a large number of ground states over a high-dimensional PES can require a vast number of state preparations. In this work, we propose using a generative quantum machine learning model to prepare quantum states at arbitrary points on the PES. The model is trained using quantum data consisting of ground-state wavefunctions associated with different classical nuclear coordinates. Our approach uses a classical neural network to convert the nuclear coordinates of a molecule into quantum parameters of a variational quantum circuit. The model is trained using a fidelity loss function to optimize the neural network parameters. We show that gradient evaluation is efficient and numerically demonstrate our method’s ability to prepare wavefunctions on the PES of hydrogen chains, water, and beryllium hydride. In all cases, we find that a small number of training points are needed to achieve very high overlap with the groundstates in practice. From a theoretical perspective, we further prove limitations on these protocols by showing that if we were able to learn across an avoided crossing using a small number of samples, then we would be able to violate Grover’s lower bound. Additionally, we prove lower bounds on the amount of quantum data needed to learn a locally optimal neural network function using arguments from quantum Fisher information. This work further identifies that quantum chemistry can be an important use case for quantum machine learning. © 2022, CC BY.

关键词： Molecules

FAIR for AI: An interdisciplinary and international community building perspective

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Huerta, E.A. Blaiszik, Ben Brinson, L. Catherine Bouchard, Kristofer E. Diaz, Daniel Doglioni, Caterina Duarte, Javier M. Emani, Murali Foster, Ian Fox, Geoffrey Harris, Philip Heinrich, Lukas Jha, Shantenu Katz, Daniel S. Kindratenko, Volodymyr Kirkpatrick, Christine R. Lassila-Perini, Kati Madduri, Ravi K. Neubauer, Mark S. Psomopoulos, Fotis E. Roy, Avik Rübel, Oliver Zhao, Zhizhen Zhu, Ruike Data Science and Learning Division Argonne National Laboratory LemontIL60439 United States Department of Computer Science University of Chicago ChicagoIL60637 United States Globus University of Chicago ChicagoIL60637 United States Department of Mechanical Engineering and Materials Science Duke University DurhamNC27708 United States Scientific Data Division Lawrence Berkeley National Laboratory BerkeleyCA94720 United States Biological Systems & Engineering Lawrence Berkeley National Laboratory BerkeleyCA94720 United States Helen Wills Neuroscience Institute University of California Berkeley BerkeleyCA94720 United States Department of Physics University of California La Jolla San DiegoCA92093 United States Lund University Department of Physics Box 118 Lund221 00 Sweden School of Physics & Astronomy The University of Manchester ManchesterM13 9PL United Kingdom Leadership Computing Facility Argonne National Laboratory LemontIL60439 United States Biocomplexity Institute Department of Computer Science University of Virginia CharlottesvilleVA22904 United States Department of Physics Massachusetts Institute of Technology CambridgeMA02139 United States Technical University Munich Arcisstraße 21 München80333 Germany Computational Science Initiative Brookhaven National Laboratory UptonNY11973 United States Electrical and Computer Engineering Rutgers The State University of New Jersey PiscatawayNJ08854 United States National Center for Supercomputing Applications University of Illinois Urbana-Champaign UrbanaIL61801 United States Department of Computer Science University of Illinois at Urbana-Champaign UrbanaIL61801 United States Department of Electrical & Computer Engineering University of Illinois at Urbana-Champaign UrbanaIL61801 United States School of Information Sciences University of Illinois at Urbana-Champaign UrbanaIL61801 United States San Diego Supercomputer Center University of California La Jolla San DiegoCA

A foundational set of findable, accessible, interoperable, and reusable (FAIR) principles were proposed in 2016 as prerequisites for proper data management and stewardship, with the goal of enabling the reusability of scholarly data. The principles were also meant to apply to other digital assets, at a high level, and over time, the FAIR guiding principles have been reinterpreted or extended to include the software, tools, algorithms, and workflows that produce data. FAIR principles are now being adapted in the context of AI models and datasets. Here, we present the perspectives, vision, and experiences of researchers from different countries, disciplines, and backgrounds who are leading the definition and adoption of FAIR principles in their communities of practice, and discuss outcomes that may result from pursuing and incentivizing FAIR AI research. The material for this report builds on the FAIR for AI Workshop held at Argonne National laboratory on June 7, 2022. Copyright © 2022, The Authors. All rights reserved.

关键词： Information management

SED-MVS: Segmentation-Driven and Edge-Aligned Deformation Multi-View Stereo with Depth Restoration and Occlusion Constraint

学校读者我要写书评

暂无评论

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Yuan, Zhenlong Yang, Zhidong Cai, Yujun Wu, Kuangxin Liu, Mufan Zhang, Dapeng Jiang, Hao Li, Zhaoxin Wang, Zhaoqi Chinese Academy of Sciences Institute of Computing Technology Beijing100190 China School of Electrical Engineering and Computer Science Australia Hunan Police Academy Information Technology Department Changsha410100 China Shanghai Jiao Tong University Cooperative MediaNet Innovation Center Shanghai200240 China Lanzhou University DSLAB School of Information Science and Engineering 730000 China Ministry of Agriculture and Rural Affairs Agricultural Information Institute Chinese Academy of Agricultural Sciences Key Laboratory of Agricultural Big Data 100081 China

Recently, patch-deformation methods have exhibited significant effectiveness in multi-view stereo owing to the deformable and expandable patches in reconstructing textureless areas. However, existing approaches neglect to address the problem of deformation instability caused by easily overlooked edge-skipping, potentially leading to matching distortions, thus leaving room for further improvement. To fill this gap, we propose SED-MVS, which adopts panoptic segmentation and multi-trajectory diffusion strategy for segmentation-driven and edge-aligned patch deformation. Specifically, to prevent unanticipated edge-skipping, we first employ SAM2 for panoptic segmentation as depth-edge guidance to guide patch deformation, followed by multi-trajectory diffusion strategy to ensure patches are comprehensively aligned with depth edges. Moreover, to avoid potential inaccuracy of random initialization, we combine both sparse points from LoFTR and monocular depth map from DepthAnything V2 to restore reliable and realistic depth map for initialization and supervised guidance. Finally, we integrate the segmentation image with the monocular depth map to exploit inter-instance occlusion relationship, then further regard them as occlusion map to implement two distinct edge constraint, thereby facilitating occlusion-aware patch deformation. Extensive results on ETH3D, Tanks & Temples, BlendedMVS, Strecha and DL3DV-10K datasets validate the state-of-the-art performance and robust generalization capability of our proposed method. © 1991-2012 IEEE.

关键词： Image segmentation

Multistage model for robust face alignment using deep neural networks

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Wang, Huabin Cheng, Rui Zhou, Jian Tao, Liang Kwan, Hon Keung MOE Key Laboratory of Intelligent Computing and Signal Processing School of Computer Science and Technology Anhui University Hefei Anhui230601 China Department of Electrical and Computer Engineering University of Windsor WindsorONN9B 3P4 Canada

An ability to generalize unconstrained conditions such as severe occlusions and large pose variations remains a challenging goal to achieve in face alignment. In this paper, a multistage model based on deep neural networks is proposed which takes advantage of spatial transformer networks, hourglass networks and exemplar-based shape constraints. First, a spatial transformer - generative adversarial network which consists of convolutional layers and residual units is utilized to solve the initialization issues caused by face detectors, such as rotation and scale variations, to obtain improved face bounding boxes for face alignment. Then, stacked hourglass network is employed to obtain preliminary locations of landmarks as well as their corresponding scores. In addition, an exemplar-based shape dictionary is designed to determine landmarks with low scores based on those with high scores. By incorporating face shape constraints, misaligned landmarks caused by occlusions or cluttered backgrounds can be considerably improved. Extensive experiments based on challenging benchmark datasets are performed to demonstrate the superior performance of the proposed method over other state-of-the-art methods. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep neural networks