检索结果-内蒙古大学图书馆

DSPU: An Efficient Deep Learning-Based Dense RGB-D Data Acquisition With Sensor Fusion and 3-D Perception SoC

IEEE JOURNAL OF SOLID-STATE CIRCUITS 2022年第1期58卷 177页

作者： Im, Dongseok Park, Gwangtae Ryu, Junha Li, Zhiyong Kang, Sanghoon Han, Donghyeon Lee, Jinsu Park, Wonhoon Kwon, Hankyul Yoo, Hoi-Jun Korea Adv Inst Sci & Technol KAIST Sch Elect Engn Daejeon 34141 South Korea

3-D red, green, blue, and depth (RGB-D) and 3-D perception are essential information for 3-D applications such as autonomous driving and augmented reality (AR)/virtual reality (VR) systems. However, battery-and resource-limited mobile devices face difficulties in obtaining dense RGB-D data and 3-D perception information in low-power (LP) and real-time. Specifically, an RGB-D sensor is used to acquire 3-D RGB-D data, but it consumes high power and produces sparse depth data. Moreover, preprocessing for RGB-D data requires a long execution time. Previous 3-D perception accelerators also have limited reconfigurability, making them incapable of executing diverse 3-D perception tasks. In this article, an LP and real-time depth signal processing system-on-chip (SoC), depth signal processing unit (DSPU), is presented. The DSPU produces accurate dense RGB-D data using a convolutional neural network (CNN)-based monocular depth estimation (MDE) and a sensor fusion with an LP ToF sensor. Then, the DSPU performs 3-D perception inferring a point cloud-based neural network (PNN). The DSPU executes the depth signal processing system with the following features: 1) a unified point processing unit (UPPU) with a flexible window based-search algorithm for simplifying the complexity of point processing algorithms and saving the arithmetic units and buffers;2) a unified matrix processing unit (UMPU) with bit-slice-level sparsity exploitation to accelerate various matrix processing algorithms;3) a band matrix encoder and decoder to decrease the data transactions in the conjugate-gradient (C-Grad) method;and 4) a point feature (PF) reuse method with a pipelined architecture for low-latency and LP PNN inference. Finally, the DSPU achieves real-time implementation with 281.6 mW of the end-to-end 3-D B-box extraction system.

关键词： signal processing algorithms Sensor fusion signal processing Sparse matrices Real-time systems Decoding Convolution 3-D perception conjugated-gradient (C-Grad) convolutional neural network (CNN) deep neural network depth estimation point cloud-based neural network (PNN) red green blue and depth (RGB-D) data sensor fusion system-on-chip (SoC)

来源：评论

学校读者我要写书评

暂无评论

Mc2g: An Efficient Algorithm for Matrix Completion With Social and Item Similarity Graphs

引用

IEEE TRANSACTIONS ON signal processing 2022年 70卷 2681-2697页

作者： Zhang, Qiaosheng Suh, Geewon Suh, Changho Tan, Vincent Y. F. Shanghai Artificial Intelligence Lab Shanghai 200232 Peoples R China Korea Adv Inst Sci & Technol Sch Elect Engn Daejeon 34141 South Korea Natl Univ Singapore Dept Elect & Comp Engn Singapore 117583 Singapore Natl Univ Singapore Dept Math Singapore 117583 Singapore

In this paper, we design and analyze Mc2g (Matrix Completion with 2 Graphs), an efficient algorithm that performs matrix completion in the presence of social and item similarity graphs. Mc2g runs in quasilinear time and is parameter free. It is based on spectral clustering and local refinement steps. For the matrix completion problem which possesses additional block structures in its rows and columns, we derive the expected number of sampled entries required for Mc2g to succeed, and further show that it matches an information-theoretic lower bound up to a constant factor for a wide range of parameters. We perform extensive experiments on both synthetic datasets and a semi-real dataset inspired by real graphs. The experimental results show that Mc2g outperforms other state-of-the-art matrix completion algorithms.

关键词： Clustering algorithms signal processing algorithms Computational efficiency Social networking (online) Recommender systems Maximum likelihood estimation Prediction algorithms Matrix completion community detection stochastic block model graph side information

来源：评论

学校读者我要写书评

暂无评论

Multivariate Fast Iterative Filtering for the Decomposition of Nonstationary signals

引用

IEEE TRANSACTIONS ON signal processing 2022年 70卷 1521-1531页

作者： Cicone, Antonio Pellegrino, Enza Univ Aquila DISIM I-67100 Laquila Italy INAF Ist Astrofis & Planetol Spaziali I-00133 Rome Italy Ist Nazl Geofis & Vulcanol I-00143 Rome Italy Univ Aquila DIIIE I-67040 Laquila Italy

In this work, we present a new technique for the decomposition of multivariate data, which we call Multivariate Fast Iterative Filtering (MvFIF) algorithm. We study its properties, proving rigorously that it converges in finite time when applied to the decomposition of any kind of multivariate signal. We test MvFIF performance using a wide variety of artificial and real multivariate signals, showing its ability to: separate multivariate modulated oscillations;align frequencies along different channels;produce a quasi-dyadic filterbank when decomposing white Gaussian noise;decompose the signal in a quasi-orthogonal set of components;being robust to noise perturbation, even when the number of channels is increased considerably. Finally, we compare it and its performance with the main methods developed so far in the literature, proving that MvFIF produces, without any a priori assumption on the signal under investigation and in a fast and reliable manner, a uniquely defined decomposition of any multivariate signal.

关键词： signal processing algorithms Filtering Iterative algorithms Optimization Frequency modulation Convergence Wavelet transforms Adaptive signal processing filtering algorithms array signal processing iterative methods

来源：评论

学校读者我要写书评

暂无评论

Optimal Transmission Strategy and Time Allocation for RIS-Enhanced Partially WPSNs

引用

IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS 2022年第9期21卷 7207-7221页

作者： Liu, Heng Zhang, Yan Gong, Shiqi Shen, Wenqian Xing, Chengwen An, Jianping Beijing Inst Technol Sch Informat & Elect Beijing 100081 Peoples R China Univ Macau State Key Lab Internet Things Smart City Taipa Macao Peoples R China Univ Macau Dept Elect & Comp Engn Taipa Macao Peoples R China

Wireless powered sensor networks (WPSNs) have evolved as a promising paradigm for energy-efficient communications. Recently, the proliferation of reconfigurable intelligent surface (RIS) has further been envisioned as a cost-effective solution for improving wireless power transfer (WPT) efficiency. In this paper, from the practical perspective of balancing the network sustainability and reliability, we consider a RIS-enhanced partially WPSN that composed of wireless-powered energy receivers (ERs) and battery-powered information receivers (IRs). Assuming the partially WPSN operates in time division multiple access (TDMA) mode, the joint optimization of covariance matrices, downlink/uplink (DL/UL) time allocation and RIS reflecting coefficients are investigated under the minimum DL rate constraint among all IRs for maximizing the achievable UL sum rate. Specifically, the single-IR single-ER (SISE) case is first studied based on the assumption of separate DL/UL RIS reflecting coefficients, in which an alternating optimization algorithm is proposed with semi-closed-form optimal solutions. In order to reduce the hardware overhead and signal processing complexity, we also investigate the case of identical DL/UL RIS reflecting coefficients, in which an iterative optimization algorithm is developed to tackle the coupled DL/UL transmissions. Then, we extend our work to the multiple-IRs multiple-ERs (MIME) case, where both the optimization problems corresponding to separate and identical DL/UL RIS reflecting schemes become more challenging to solve. To circumvent this intractability, we propose a successive convex relaxation (SCA) based alternating optimization algorithm and a low-complexity two-step algorithm. Finally, numerical results demonstrate the superior UL sum rate performance of our proposed algorithms over the adopted benchmarks.

关键词： Wireless communication Optimization Wireless sensor networks Resource management Time division multiple access signal processing algorithms Receivers Wireless powered sensor networks simultaneous wireless information and power transfer reconfigurable intelligent surface TDMA

来源：评论

学校读者我要写书评

暂无评论

A Brief Review of signal processing for EEG-based BCI: Approaches and Opportunities

A Brief Review of Signal Processing for EEG-based BCI: Appro...

引用

IEEE International Conference on Electro Information Technology (EIT)

作者： Haider, Ali Cent Michigan Univ Sch Engn & Technol Mt Pleasant MI 48859 USA

ISBN: (纸本)9781665418461

In every society, people with disabilities need to communicate with others. However, their economic and educational status are predominantly limited by the unavailability of tools and technologies to satisfy their special needs. There is a necessity for technological solutions to constantly increase to overcome their difficulties with everyday activities. Recent days, Brain-computer Interface (BCI) has drawn attention of many researchers as a hands-free tool which can help motion impaired people to control devices, express their opinions and ideas, and communicate with others. The real-time control of sensors and actuators can be implemented using BCI at the expense of high computational resources. In fact, the evolution of brain technology has offered limitless opportunities and possibilities for impaired as well as healthy members to contribute and participate in the society. With the help of human brain signals or an electroencephalogram (EEG), brain activity in the neocortex is measured as voltage differences over the scalp. Information on subjects' intentions and thoughts is encompassed by EEG electrical patterns, which is decoded as important signatures of brain activity. The status quo BCI technology and associated signal processing schemes are advancing fast. It will also improve control of devices in space, people's lives in e-home, or communication in novel ways. This manuscript presents the EEG signal processing and classification techniques to design BCI system as a control or communication device.

关键词： Brain Voltage measurement Scalp signal processing algorithms signal processing Tools Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Robust Tensor Tracking With Missing Data and Outliers: Novel Adaptive CP Decomposition and Convergence Analysis

引用

IEEE TRANSACTIONS ON signal processing 2022年 70卷 4305-4320页

作者： Le Trung Thanh Abed-Meraim, Karim Nguyen Linh Trung Hafiane, Adel Univ Orleans INSA CVL PRISME F-45100 Orleans France Vietnam Natl Univ VNU Univ Engn & Technol AVITECH Hanoi 100000 Vietnam

Canonical Polyadic (CP) decomposition is a powerful multilinear algebra tool for analyzing multiway (a.k.a. tensor) data and has been used for various signal processing and machine learning applications. When the underlying tensor is derived from data streams, adaptive CP decomposition is required. In this paper, we propose a novel method called robust adaptive CP decomposition (RACP) for dealing with high-order incomplete streaming tensors that are corrupted by outliers. At each time instant, RACP first performs online outlier rejection to accurately detect and remove sparse outliers, and then performs tensor factor tracking to efficiently update the tensor basis. A unified convergence analysis of RACP is also established in that the sequence of generated solutions converges asymptotically to a stationary point of the objective function. Extensive experiments were conducted on both synthetic and real data to demonstrate the effectiveness of RACP in comparison with state-of-the-art adaptive CP algorithms.

关键词： Tensors Convergence signal processing algorithms Adaptation models Loading Linear programming Data models CANDECOMP PARAFAC (CP) decomposition adaptive algorithm streaming tensor missing data outlier

来源：评论

学校读者我要写书评

暂无评论

FDA-Based Space-Time-Frequency Deceptive Jamming Against SAR Imaging

引用

IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS 2022年第3期58卷 2127-2140页

作者： Bang, Huang Wang, Wen-Qin Zhang, Shunsheng Liao, Yi Univ Elect Sci & Technol China Sch Informat & Commun Engn Chengdu 611731 Peoples R China Univ Elect Sci & Technol China Yangtze Delta Reg Inst Huzhou 313001 Peoples R China Univ Elect Sci & Technol China Res Inst Elect Sci & Technol Chengdu 611731 Peoples R China

Due to the employment of frequency increment across the array elements, frequency-diverse array (FDA) produces a jointly range-angle-time-dependent beampattern, which finds wide applicability in improving the target detection performance and imaging resolution capability. By the exploitation of the multifrequency transmission across elements, this article proposes an FDA-based space-time-frequency deceptive jamming approach against spaceborne synthetic aperture radar (SAR) by using the range-Doppler algorithm (RDA) for high-resolution imaging process. We analyze the range-azimuth distribution of false targets generated by the FDA jammer and then reveal the controllability of the number and locations of false targets by adjusting the frequency increment and the number of FDA elements. In order to set the FDA jammer parameters properly, we derive the minimum/maximum allowable frequency increment, the maximum number of elements and maximum azimuth offset by the ambiguity function, and Doppler frequency analysis. The effectiveness of the proposed approach is validated by extensive numerical results.

关键词： Jamming Synthetic aperture radar Azimuth Spaceborne radar Radar polarimetry signal processing algorithms Imaging Ambiguity function deceptive jamming false target frequency-diverse array (FDA) range-Doppler algorithm (RDA) synthetic aperture radar (SAR)

来源：评论

学校读者我要写书评

暂无评论

Soft Channel Estimation and Localization for Millimeter Wave Systems With Multiple Receivers

引用

IEEE TRANSACTIONS ON signal processing 2022年 70卷 4897-4911页

作者： Yang, Xi Wen, Chao-Kai Han, Yu Jin, Shi Swindlehurst, A. Lee Southeast Univ Natl Mobile Commun Res Lab Nanjing 210018 Peoples R China Natl Sun Yat Sen Univ Inst Commun Engn Kaohsiung 804 Taiwan Univ Calif Irvine Ctr Pervas Commun & Comp Irvine CA 92697 USA

In millimeter wave (mmWave) communications, user position information can enable various position-based communication services, such as resource allocation, beam tracking and alignment, interference control, and synchronization. Classical localization methods focus on hard localization information, but soft localization provides the confidence levels in position estimates and thus enables the information to be efficiently fused with different measurements and application layers to realize integrated communication and localization. In this study, we propose a soft channel estimation and localization algorithm for an mmWave systems with multiple base stations. We present the Newtonized variational inference spectral estimation algorithm to extract soft information of position-related channel parameters. The soft localization algorithm estimates user position by using soft channel parameters from the expectation propagation simultaneous localization and mapping algorithm framework. The proposed algorithms realize channel estimation and localization in the communication process and refine the channel estimation through the localization information. Numerical results show that the proposed algorithms approach the Cramer-Rao lower bound for channel estimation and localization, and are thus verified to be effective.

关键词： Location awareness Channel estimation signal processing algorithms Inference algorithms Estimation Delays Synchronization Channel estimation localization mmWave system soft information

来源：评论

学校读者我要写书评

暂无评论

Robust Decentralized Learning Using ADMM With Unreliable Agents

引用

IEEE TRANSACTIONS ON signal processing 2022年 70卷 2743-2757页

作者： Li, Qunwei Kailkhura, Bhavya Goldhahn, Ryan Ray, Priyadip Varshney, Pramod K. Lawrence Livermore Natl Lab Livermore CA 94550 USA Ant Grp Hangzhou 310000 Zhejiang Peoples R China Syracuse Univ EECS Dept Syracuse NY 13244 USA

Many signal processing and machine learning problems can be formulated as consensus optimization problems which can be solved efficiently via a cooperative multi-agent system. However, the agents in the system can be unreliable due to a variety of reasons: noise, faults and attacks. Providing erroneous updates leads the optimization process in a wrong direction, and degrades the performance of distributed machine learning algorithms. This paper considers the problem of decentralized learning using ADMM in the presence of unreliable agents. First, we rigorously analyze the effect of erroneous updates (in ADMM learning iterations) on the convergence behavior of the multi-agent system. We show that the algorithm linearly converges to a neighborhood of the optimal solution under certain conditions and characterize the neighborhood size analytically. Next, we provide guidelines for network design to achieve a faster convergence to the neighborhood. We also provide conditions on the erroneous updates for exact convergence to the optimal solution. Finally, to mitigate the influence of unreliable agents, we propose ROAD, a robust variant of ADMM, and show its resilience to unreliable agents with an exact convergence to the optimum.

关键词： Convergence Optimization signal processing algorithms Convex functions Peer-to-peer computing Training Neural networks Decentralized learning ADMM unreliable

来源：评论

学校读者我要写书评

暂无评论

A Practical Deceptive Jamming Method Based on Vulnerable Location Awareness Adversarial Attack for Radar HRRP Target Recognition

引用

IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 2022年 17卷 2410-2424页

作者： Du, Chuan Cong, Yulai Zhang, Lei Guo, Dandan Wei, Song Nanjing Univ Informat Sci & Technol Sch Elect & Informat Engn Nanjing 210044 Peoples R China Sun Yat Sen Univ Sch Elect & Commun Engn Shenzhen 510275 Peoples R China Chinese Univ Hong Kong Inst Robot & Intelligent Mfg Shenzhen 518172 Peoples R China

In recent years, deep neural networks are increasingly popular in the field of radar high-resolution range profiles (HRRPs) target recognition. Unfortunately, recent researches have revealed that a deep-learning classifier can be easily fooled by adding small perturbations to the input, named adversarial attack. This provides us an inspiration for radar deceptive jamming signal generation in electronic countermeasures (ECMs). However, the perturbations generated by these adversarial attacks are usually of complex envelopes and quite low power, making it challenging for jammers to generate such actual jamming signals. To solve that issue, we propose a practical deceptive jamming generation method that learns the vulnerable range cells in an HRRP sample and injects several jamming pulses with specific amplitudes into these range cells. Such jamming signals are easy to generate and can deceive the radar automatic target recognition (RATR) model to output the wrong target category prediction with high confidence. To avoid the requirement of the recognition network structure information, we leverage the differential evolution optimization algorithm (non-gradientbased). Further, to provide the potential of real-time jamming signal generation during the test, an encoder is constructed not only to learn the separable features but also to find the vulnerable range cells and the specific amplitudes of the jamming pulses. In the experiments, we apply the proposed attack algorithms to fool the one-dimensional convolutional neural network-based HRRPRATR models. The extensive experimental results on measured aircraft HRRP dataset prove that the proposed algorithms achieve a promising attack performance and serve as a practical and fast deceptive jamming generation method.

关键词： Jamming Radar Target recognition Perturbation methods Radar imaging signal processing algorithms Real-time systems Adversarial attack high-resolution range profiles radar automatic target recognition electronic countermeasures deceptive jamming black-box attack

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：