检索结果-内蒙古大学图书馆

Single UWB Anchor Aided PDR Heading and Step Length Correcting Indoor Localization System

IEEE ACCESS 2021年 9卷 11511-11522页

作者： Long, Keliu Shen, Chong Tian, Chuan Zhang, Kun Bhatti, Uzair Aslam Kong, Darryl Franck Nsalo Feng, Shuo Cheng, Hesen Hainan Univ State Key Lab Marine Resources Utilizat South Chi Haikou 570228 Hainan Peoples R China Hainan Univ Coll Informat Sci & Technol Haikou 570228 Hainan Peoples R China Hainan Trop Ocean Univ Educ Ctr MTA Sanya 572022 Peoples R China Chinese Acad Sci Inst Deep Sea Sci & Engn Sanya 572000 Peoples R China Nanjing Normal Univ Sch Geog Nanjing 210023 Peoples R China

In this paper, we present a simple-structure Pedestrian Dead Reckon (PDR) system based on commercial IMU sensor and UWB ranging system. In PDR system, the accuracy of step and heading angle estimation completely decide the precision of location result. In order to select proper zero-velocity intervals for step and heading estimations in the foot stance/still stage, a modified zero-velocity detection way called Heuristic Step Detection (HSD) has been designed based on zero-velocity update algorithm (ZUPT). Based on the modified zero-velocity detection algorithm, i.e., HSD, an Kalman-type filter is used to get rough heading angle by fusing zero-velocity information and single UWB anchor ranging results. After that, a constrained sigma point based filter is used to further constrain heading angle range. Moreover, the range measures, provided by a UWB localization system with only one reference anchor, are used to correct the pedestrian step length. Trough UWB ranging measures analysis between two consecutive steps, the step length and pedestrian heading direction correcting processes are related to each other, and as a result, a more stable positioning result can be gotten. The corresponding practical experiments are conducted in real indoor environment over 2000 meters, and the results show that, compared with only INS-aided PDR, our scheme can reduce the average position error by more than 80%, and it can achieve long-term high accuracy and robust localization results.

关键词： Location awareness Distance measurement Legged locomotion Estimation Gyroscopes filtering algorithms Kalman filters Pedestrian dead reckon ultra-wide band indoor localization fusion strategy

来源：评论

学校读者我要写书评

暂无评论

A Process-Oriented Method for Rapid Acquisition of Canopy Height Model From RGB Point Cloud in Semiarid Region

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2021年 14卷 12187-12198页

作者： Tian, Yu Bian, Zhengfu Lei, Shaogang Ji, Chuning Zhao, Yibo Zhang, Shubi Duan, Lei Sedlak, Vladimir China Univ Min & Technol Sch Environm Sci & Spatial Informat Xuzhou 221116 Jiangsu Peoples R China Engn Res Ctr Coal Min Subsided Land & Goaf Treatm Jining 272100 Peoples R China Pavol Jozef Safarik Univ Kosice Fac Sci Inst Geog Kosice 04001 Slovakia

This study addressed the problems of difficult parameter selection of ground point filtering algorithm, slow speed, and susceptibility to wrong classification points of the traditional interpolation algorithm in extracting canopy height model from dense point cloud produced by structure from motion. Finding the true ground is vital for canopy height estimation using unmanned aerial vehicle red, green, and blue point cloud, especially for semiarid area where cloud points of short vegetation like shrubs and dwarf trees generally mixed up with the ground points. This article proposes a ground point extraction strategy that combines the advantages of structural and spectral filtering. Specifically, spectral filtering simplifies the threshold selection for structural filtering, whereas structural filtering removes the outliers from spectral filtering. Considering the misclassified points in the ground filtering algorithm, a fast, nonparametric ground point interpolation algorithm was used to suppress the wrong classification points. This novel algorithm is based on the basic idea of least square quadratic fitting and prediction of terrain profile (PF). The quantitative results show that compared to inverse distance weighting (IDW), radial basis function (RBF), and ordinary kriging (OK), it takes less time (PF: 122 s, IDW: 518 s, RBF: 1374 s, OK: 1129 s), and has lower RMSE (PF: 0.301 m, IDW: 0.549 m, RBF: 0.903 m, OK: 0.427 m).

关键词： Interpolation filtering Vegetation mapping Laser radar filtering algorithms Prediction algorithms Ecosystems Canopy height model (CHM) fast extraction algorithm semiarid structure from motion (SfM)

来源：评论

学校读者我要写书评

暂无评论

A GGIW-PHD Filter for Multiple Non-Ellipsoidal Extended Targets Tracking With Varying Number of Sub-Objects

引用

IEEE ACCESS 2021年 9卷 64719-64731页

作者： Gong, Yang Cui, Chen Wu, Biao Natl Univ Def Technol Inst Elect Countermeasure Hefei 230037 Peoples R China Huayin Ordnance Test Ctr Weinan 714000 Peoples R China

When the extension state of the non-ellipsoidal extended target (NET) changes, the performance of traditional multiple target tracking algorithms based on the constant number of sub-objects will decrease. To solve this problem, this paper proposes a gamma Gaussian inverse Wishart probability hypothesis density filter for non-ellipsoidal extended targets with varying number of sub-objects, called VN-NET-GGIW-PHD filter. In the proposed filter, each NET is considered as a combination of multiple spatially close sub-objects, and the label management is introduced to realize the association between the NET and corresponding sub-objects. Then, by target spawning and combination, the number of sub-objects for approximating the extension state of each NET can be adjusted automatically. Furthermore, to obtain the partition of the measurement set, an approach based on the clustering by fast search and find of density peaks (CFSFDP) algorithm and expectation maximization (EM) algorithm is proposed. Simulation results show that the proposed filter can adaptively adjust the number of sub-objects and has better performance when the extension state of the NET changes.

关键词： Target tracking Information filters filtering algorithms Sensors Partitioning algorithms Kinematics Noise measurement Multi-target tracking non-ellipsoidal extended target target spawning target combination measurement set partition

来源：评论

学校读者我要写书评

暂无评论

Improving Relevance in a Recommendation System to Suggest Charities without Explicit User Profiles Using Dual-Autoencoders 7

Improving Relevance in a Recommendation System to Suggest Ch...

引用

7th International Conference on Data Science and Machine Learning Applications (CDMA)

作者： Adames, Pablo Mokhasi, Sourabh Pauchard, Yves Moshirpour, Mohammed Rostoker, Camilo Univ Calgary Calgary AB Canada Benevity Inc Calgary AB Canada

ISBN: (纸本)9781665410144

This work explores the effect of the quality of inferred user profiles on the accuracy of charitable recommendations when using an item-based collaborative filter algorithm. A gap was identified in the literature with respect to the application of charitable recommendation systems in the absence of rich user profiles. This paper introduces an approach to generate relevant recommendations when neither user profiles nor feedback on donation preferences is available. The discovery of user preferences is achieved via the construction of implicit ratings computed from custom feature engineering, while the sparsity of item and user ratings was addressed with a dimension reduction strategy based on dual-autoencoders from a commercial machine learning platform. Our analysis shows the magnitude and sensitivity of the relationship between the relevance of the recommendations and the average number of donations per user. Raw data for this research was provided by a leading online donation platform and contains 24 million anonymous donations to 165 thousand unique causes from over 1.2 million users. We find that the most effective way to increase the relevance of recommendations by a factor of 2 at any top-k value is to train the collaborative filter with users that have at least 50 donations in the data set. As a result, the training set for the collaborative filter is restricted to 8% of the original users, 70% of the companies, 49% of the causes, and 70% of the original countries where users making donations reside.

关键词： Training Dimensionality reduction Sensitivity Machine learning algorithms Density measurement Collaboration filtering algorithms

来源：评论

学校读者我要写书评

暂无评论

Dynamic CNN Accelerator Supporting Efficient Filter Generator with Kernel Enhancement and Online Channel Pruning 22

Dynamic CNN Accelerator Supporting Efficient Filter Generato...

引用

27th Asia and South Pacific Design Automation Conference (ASP-DAC)

作者： Tang, Chen Sun, Wenyu Wang, Wenxun Liu, Yongpan Tsinghua Univ Dept Elect Engn Beijing Peoples R China

ISBN: (纸本)9781665421355

Deep neural network achieves exciting performance in several tasks with heavy storing and computing costs. Previous works adopt pruning-based methods to slim deep network. For traditional pruning, either the convolution kernel or the network inference is static, which cannot fully compress the model parameter and restrains their performance. In this paper, we propose an online pruning algorithm to support dynamic kernel generation and dynamic network inference at the same time. Two novel techniques including the filter generator and the importance-level based channel pruning are proposed. Moreover, we validate the success of the proposed method by the implementation on Ultra96-v2 FPGA. Compared with state-of-art static or dynamic pruning methods, our method can reduce the top-5 accuracy drop by nearly 50% for ResNet model on ImageNet at similar compressing level. It can also achieve better accuracy while up to 50% fewer weights are reduced to be saved on chip.

关键词： Image coding Design automation Heuristic algorithms Neural networks filtering algorithms Generators Inference algorithms

来源：评论

学校读者我要写书评

暂无评论

Fast filtering of Search Results Sorted by Attribute

引用

ACM TRANSACTIONS ON INFORMATION SYSTEMS 2022年第2期40卷 40-40页

作者： Nardini, Franco Maria Trani, Roberto Venturini, Rossano ISTI CNR I-56126 Pisa PI Italy Univ Pisa I-56126 Pisa PI Italy

Modern search services often provide multiple options to rank the search results, e.g., sort "by relevance", "by price" or "by discount" in e-commerce. While the traditional rank by relevance effectively places the relevant results in the top positions of the results list, the rank by attribute could place many marginally relevant results in the head of the results list leading to poor user experience. In the past, this issue has been addressed by investigating the relevance-aware filtering problem, which asks to select the subset of results maximizing the relevance of the attribute-sorted list. Recently, an exact algorithm has been proposed to solve this problem optimally. However, the high computational cost of the algorithm makes it impractical for the Web search scenario, which is characterized by huge lists of results and strict time constraints. For this reason, the problem is often solved using efficient yet inaccurate heuristic algorithms. In this article, we first prove the performance bounds of the existing heuristics. We then propose two efficient and effective algorithms to solve the relevance-aware filtering problem. First, we propose OPT-filtering, a novel exact algorithm that is faster than the existing state-of-the-art optimal algorithm. Second, we propose an approximate and even more efficient algorithm, epsilon-filtering, which, given an allowed approximation error epsilon, finds a (1-epsilon)-optimal filtering, i.e., the relevance of its solution is at least (1-epsilon) times the optimum. We conduct a comprehensive evaluation of the two proposed algorithms against state-of-the-art competitors on two real-world public datasets. Experimental results show that OPT-filtering achieves a significant speedup of up to two orders of magnitude with respect to the existing optimal solution, while epsilon-filtering further improves this result by trading effectiveness for efficiency. In particular, experiments show that epsilon-filtering can achieve quasi-opt

关键词： Relevance-aware filtering filtering algorithms approximation algorithms efficiency-effectiveness trade-offs

来源：评论

学校读者我要写书评

暂无评论

On Unsupervised Uncertainty-Driven Speech Pseudo-Label filtering and Model Calibration

On Unsupervised Uncertainty-Driven Speech Pseudo-Label Filte...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Nauman Dawalatabad Sameer Khurana Antoine Laurent James Glass MIT Computer Science and Artificial Intelligence Laboratory Cambridge MA USA LIUM - Le Mans University France

Pseudo-label (PL) filtering forms a crucial part of Self-Training (ST) methods for unsupervised domain adaptation. Dropout-based Uncertainty-driven Self-Training (DUST) proceeds by first training a teacher model on source domain labeled data. Then, the teacher model is used to provide PLs for the unlabeled target domain data. Finally, we train a student on augmented labeled and pseudo-labeled data. The process is iterative, where the student becomes the teacher for the next DUST iteration. A crucial step that precedes the student model training in each DUST iteration is filtering out noisy PLs that could lead the student model astray. In DUST, we proposed a simple, effective, and theoretically sound PL filtering strategy based on the teacher model’s uncertainty about its predictions on unlabeled speech utterances. We estimate the model’s uncertainty by computing disagreement amongst multiple samples drawn from the teacher model during inference by injecting noise via dropout. In this work, we show that DUST’s PL filtering, as initially used, fail under severe source and target domain mismatch. We suggest several approaches to eliminate or alleviate this issue. Further, we bring insights from the research in neural network model calibration to DUST and show that a well-calibrated model correlates strongly with a positive outcome of the DUST PL filtering step. We demonstrate effectiveness of our methods on target domain GigaSpeech YouTube dataset.

关键词： Training Adaptation models Uncertainty Video on demand filtering Computational modeling filtering algorithms

来源：评论

学校读者我要写书评

暂无评论

Adaptive Frequency-Domain Normalized Implementations of Widely-Linear Complex-Valued Filter

引用

IEEE TRANSACTIONS ON SIGNAL PROCESSING 2021年 69卷 5801-5814页

作者： Zhang, Sheng Zhang, Jiashu Xia, Yili So, Hing Cheung Southwest Jiaotong Univ Sch Informat Sci & Technol Chengdu 611756 Sichuan Peoples R China Southwest Jiaotong Univ Sch Comp & Artificial Intelligence Chengdu 611756 Sichuan Peoples R China Southeast Univ Sch Informat Sci & Engn Nanjing 210096 Peoples R China City Univ Hong Kong Dept Elect Engn Hong Kong 852 Peoples R China

The widely-linear complex-valued least-mean-square (WL-CLMS) algorithm exhibits slow convergence in the presence of non-circular and highly correlated filter input signals. To tackle such an issue with reduced computational complexity, this paper introduces adaptive frequency-domain normalized implementations of widely-linear complex-valued filter. Two normalized algorithms are firstly devised based on the circulant matrices of weight coefficients and the regression vector, respectively. In the design, the normalization matrix using the second-order complementary statistical information of the input signal helps increase the algorithm convergence speed. Then, mean-square and complementary mean-square performance of periodic update frequency-domain widely-linear normalized LMS (P-FDWL-NLMS) algorithm for non-circular complex signals is analyzed. In addition, by introducing a variable-periodic (VP) mechanism, we propose the VP-FDWL-NLMS method that provides faster convergence than the P-FDWL-NLMS scheme. Computer simulation results show the superiority of the proposed approach over the fullband widely-linear complex-valued least-mean-square, augmented affine projection algorithm and its variable step-size version, in terms of both complexity and convergence rate.

关键词： Frequency-domain analysis Signal processing algorithms Adaptive filters Convergence filtering algorithms Adaptation models Information filters Adaptive filter frequency domain widely-linear model mean-square analysis variable-periodic method

来源：评论

学校读者我要写书评

暂无评论

Barrier Forming: Separating Polygonal Sets with Minimum Number of Lines 39

Barrier Forming: Separating Polygonal Sets with Minimum Numb...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Peng, Si Wei Yu, Jingjin Rutgers State Univ Dept Comp Sci Piscataway NJ 08854 USA

ISBN: (纸本)9781728196817

In this work, we carry out structural and algorithmic studies of a problem of barrier forming: selecting the minimum number of straight line segments (barriers) that separate several sets of mutually disjoint objects in the plane. The problem models the optimal placement of line sensors (e.g., infrared laser beams) for isolating many types of regions in a pair-wise manner for practical purposes (e.g., guarding against intrusions). The problem is NP-hard even if we want to find the minimum number of lines to separate two sets of points in the plane. Under the umbrella problem of barrier forming with minimum number of line segments, three settings are examined: barrier forming for point sets, point sets with polygonal obstacles, polygonal sets with polygonal obstacles. We describe methods for computing the optimal solution for the first two settings with the assistance of mathematical programming, and provide a 2-OPT solution for the third. We demonstrate the effectiveness of our methods through extensive simulations.

关键词： NP-hard problem Particle separators Heuristic algorithms filtering algorithms Laser modes Mathematical models Sensors

来源：评论

学校读者我要写书评

暂无评论

VLSI Implementation of a Real-time Modified Decision-based Algorithm for Impulse Noise Removal

VLSI Implementation of a Real-time Modified Decision-based A...

引用

IEEE International IOT, Electronics and Mechatronics Conference (IEMTRONICS)

作者： Sanki, Pradyut Kumar Bevara, Vasudeva Supriya, Medarametla Deepthi Vignesh, Devireddy Harshath, Peram Bhanu Sai Kuchina, Siavya SRM Univ AP UGC Elect & Commun Engn Guntur Andhra Pradesh India

ISBN: (纸本)9781665486842

In this paper, a Real-Time Impulse Noise Removal (RTINR) algorithm and its hardware architecture are proposed for denoising images corrupted with fixed valued impulse noise. A decision-based algorithm is modified in the proposed RTINR algorithm where the corrupted pixel is first detected & is restored with median or previous pixel value depending on the number of corrupted pixels in the image. The proposed RTINR architecture has been designed to reduce the hardware complexity as it requires 21 comparators, 4 adders, and 2 line buffers which in turn improve the execution time. The proposed architecture results better in qualitative and quantitative performance in comparison to different denoising schemes while evaluated based on PSNR, IEF, MSE, EKI, SSIM,& FOM. The proposed architecture has been simulated using the VIRTEX7 FPGA device and the reported maximum post place& route frequency is 360.88 MHz. The proposed RTINR architecture is capable of denoising images of size 512 x 512 at a frame rate of 686. The architecture has also been synthesized using UMC 90 nm technology where 103 mW power is consumed at a clock frequency of 100 MHz with a gate count of 23K (NAND2) including two memory buffers.

关键词： Impulse noise image denoising filtering algorithms image quality PSNR field programmable gate arrays

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：