检索结果-内蒙古大学图书馆

Delayed Combination of Adaptive Filters in Colored Noise

IEEE TRANSACTIONS ON SIGNAL PROCESSING 2022年 70卷 1918-1931页

作者： Zhang, Sheng Zhao, Haiquan So, Hing Cheung Southwest Jiaotong Univ Sch Informat Sci & Technol Chengdu 611756 Sichuan Peoples R China Southwest Jiaotong Univ Sch Elect Engn Chengdu 610031 Sichuan Peoples R China City Univ Hong Kong Dept Elect Engn Hong Kong Peoples R China

In this work, we study the combination of adaptive filters in colored noise environments. First, a combination framework using delayed weights is introduced to tackle the colored noise. Based on this, delayed convex and affine combinations of two LMS filters are developed, resulting in the so-called Dcvx-LMS and Daff-LMS algorithms. Then, the convergence behaviors of the two algorithms are investigated using standard mean-square deviation analysis. In addition, to speed up the convergence and reduce the computational complexity, we propose delayed combination with periodic feedback, delayed combined-step-size and block implementation methods. Finally, simulation results demonstrate the superiority of our algorithms over previously reported techniques in the presence of colored noise.

关键词： Adaptive filters Colored noise Signal processing algorithms filtering algorithms Steady-state Convergence Noise measurement Adaptive filter combination with delayed weights colored noise mean-square analysis

来源：评论

学校读者我要写书评

暂无评论

Robust and Least Complex Online Secondary Path Estimation in Broadband Feed-Forward Active Control of Impulsive Noise Using FxLMAT Family

引用

IEEE ACCESS 2022年 10卷 58667-58676页

作者： Khan, Hashir Ali Mirza, Alina Wakeel, Abdul Umair, Mir Yasir Jabeen, Fareeha Afzal, Farkhanda Natl Univ Sci & Technol Mil Coll Signals MCS Dept Elect Engn Islamabad 44000 Pakistan Natl Univ Sci & Technol Mil Coll Signals MCS Dept Humanities & Basic Sci Islamabad 44000 Pakistan

Active noise control (ANC) systems operating on adaptive algorithms endure instability in the presence of impulsive noise (IN). Therefore, this manuscript investigates the performance of such adaptive algorithms with online secondary path modeling (OSPM) in the presence of impulsive noise in non-stationary acoustic paths. Herein, we propose three new solutions based on the filtered x least mean absolute third (FxLMAT) algorithm for OSPM with IN. Our first solution utilizes the FxLMAT algorithm in the control filter of ANC, achieving improved modeling accuracy, good convergence, and better stability than the already existing variants of the filtered x least mean square (FxLMS) solutions. However, our proposed FxLMAT based solution exhibit slow convergence and is not robust in time-varying acoustic paths. Therefore, we propose a modified FxLMAT (MFxLMAT) algorithm to enhance the robustness of the FxLMAT solution. However, the proposed MFxLMAT still lacks good convergence. Henceforth, we introduce our third solution, i.e., a variable step size filtered x robust normalized LMAT (VSSFxRNLMAT) algorithm that almost acquires the same performance as that of the already existing filtered x recursive least square (FxRLS) family-based solutions. Simulation results are provided which show that our proposed VSSFxRNLMAT solution outperforms the already existing algorithms in terms of noise and vibration reduction, robustness, and convergence. Moreover, a comparative analysis based on the computational complexity of some well known existing as well as our proposed solutions is provided, which shows that our proposed VSSFxRNLMAT has almost the same complexity as that of the existing techniques.

关键词： filtering algorithms Adaptive filters Convergence Finite impulse response filters Robustness Stability analysis System performance Adaptive filters impulsive noise LMS LMAT noise cancellation

来源：评论

学校读者我要写书评

暂无评论

Time-Shift Modeling-Based Hear-Through System for In-Ear Headphones

引用

IEEE TRANSACTIONS ON CONSUMER ELECTRONICS 2022年第3期68卷 273-280页

作者： Huang, Chong-Rui Chang, Cheng-Yuan Kuo, Sen M. Chung Yuan Christian Univ Dept Elect Engn Taoyuan 32023 Taiwan

The hear-through (HT) technique was developed actively to compensate for passive isolation by enhancing the perception of ambient sound by wearers of headphones. The passive material in headphones reduces the high-frequency components of sound above 500 Hz. The HT algorithm compensates for the loss of ambient sound by generating an artificial sound, derived using a relative transfer function (RTF) between a microphone and the user's ears. Conventionally, HT performance depends on the direction of arrival (DOA) of the ambient sound. This work develops a time-shift scheme for identifying the RTF and an active equalization algorithm to calculate accurately the compensating sound. A shaping filter is also developed to prevent acoustical interference by the artificial sound at low frequency. Finally, the proposed approach is integrated into in-ear headphones and its HT performance is compared with that of a commercial product to verify the effectiveness of the proposed algorithm.

关键词： Headphones Microphones Ear Coherence Acoustics Transfer functions filtering algorithms Adaptive system direction of arrival hear-through in-ear headphones passive isolation relative transfer function

来源：评论

学校读者我要写书评

暂无评论

A Computationally Efficient EK-PMBM Filter for Bistatic mmWave Radio SLAM

引用

IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS 2022年第7期40卷 2179-2192页

作者： Ge, Yu Kaltiokallio, Ossi Kim, Hyowon Jiang, Fan Talvitie, Jukka Valkama, Mikko Svensson, Lennart Kim, Sunwoo Wymeersch, Henk Chalmers Univ Technol Dept Elect Engn S-41296 Gothenburg Sweden Tampere Univ Unit Elect Engn Tampere 33100 Finland Hanyang Univ Dept Elect Engn Seoul 04763 South Korea

Millimeter wave (mmWave) signals are useful for simultaneous localization and mapping (SLAM), due to their inherent geometric connection to the propagation environment and the propagation channel. To solve the SLAM problem, existing approaches rely on sigma-point or particle-based approximations, leading to high computational complexity, precluding real-time execution. We propose a novel low-complexity SLAM filter, based on the Poisson multi-Bernoulli mixture (PMBM) filter. It utilizes the extended Kalman (EK) first-order Taylor series based Gaussian approximation of the filtering distribution, and applies the track-oriented marginal multi-Bernoulli/Poisson (TOMB/P) algorithm to approximate the resulting PMBM as a Poisson multi-Bernoulli (PMB). The filter can account for different landmark types in radio SLAM and multiple data association hypotheses. Hence, it has an adjustable complexity/performance trade-off. Simulation results show that the developed SLAM filter can greatly reduce the computational cost, while it keeps the good performance of mapping and user state estimation.

关键词： Simultaneous localization and mapping Sensors filtering algorithms Complexity theory Receivers Kalman filters Computational modeling Bistatic sensing extended Kalman filter mmWave sensing poisson multi-Bernoulli mixture filter simultaneous localization and mapping

来源：评论

学校读者我要写书评

暂无评论

Exploiting Feature Selection in Human Activity Recognition: Methodological Insights and Empirical Results Using Mobile Sensor Data

引用

IEEE ACCESS 2022年 10卷 64043-64058页

作者： Manca, Marco Manolo Pes, Barbara Riboni, Daniele Univ Cagliari Dipartimento Matemat & Informat I-09124 Cagliari Italy

Human Activity Recognition (HAR) using mobile sensor data has gained increasing attention over the last few years, with a fast-growing number of reported applications. The central role of machine learning in this field has been discussed by a vast amount of research works, with several strategies proposed for processing raw data, extracting suitable features, and inducing predictive models capable of recognizing multiple types of daily activities. Since many HAR systems are implemented in resource-constrained mobile devices, the efficiency of the induced models is a crucial aspect to consider. This paper highlights the importance of exploiting dimensionality reduction techniques that can simplify the model and increase efficiency by identifying and retaining only the most informative and predictive features for activity recognition. More in detail, a large experimental study is presented that encompasses different feature selection algorithms as well as multiple HAR benchmarks containing mobile sensor data. Such a comparative evaluation relies on a methodological framework that is meant to assess not only the extent to which each selection method is effective in identifying the most predictive features but also the overall stability of the selection process, i.e., its robustness to changes in the input data. Although often neglected, in fact, the stability of the selected feature sets is important for a wider exploitability of the induced models. Our experimental results give an interesting insight into which selection algorithms may be most suited in the HAR domain, complementing and significantly extending the studies currently available in this field.

关键词： Feature extraction filtering algorithms Computational efficiency Classification algorithms Predictive models Prediction algorithms Activity recognition Feature selection methods human activity recognition machine learning algorithms mobile sensor data

来源：评论

学校读者我要写书评

暂无评论

On-Camera Content filtering for Real-Time Video Analytics 23

On-Camera Content Filtering for Real-Time Video Analytics

引用

23rd IEEE International Conference on High Performance Computing and Communications, 7th IEEE International Conference on Data Science and Systems, 19th IEEE International Conference on Smart City and 7th IEEE International Conference on Dependability in Sensor, Cloud and Big Data Systems and Applications, HPCC-DSS-SmartCity-DependSys 2021

作者： Chen, Fahao Li, Peng Wu, Celimuge School of Computer Science and Engineering The University of Aizu Japan Graduate School of Informatics and Engineering The University of Electro-Communications Japan

ISBN: (纸本)9781665494571

In the past several years, pervasive surveillance cameras have generated massive video records continually, and the video records can be used for several applications (e.g., tracking and object detection). Machine Learning (ML), especially Deep Learning, is a powerful method extensively used for video analytics. Typically, cameras do not have enough computational power to analyze videos locally. A commonly used strategy is gathering videos from cameras and processing them in the cloud or edge server. However, limited bandwidth between cameras and the server results in the inefficiency of existing central-based video analytics systems. In this paper, we effectively reduce the bandwidth demands by proposing a novel object filtering method while keeping the resolution of the video. Specifically, we adopt the moving object detection algorithm on the camera side to find regions in the video and encode these regions into high-resolution video. Through extensive experiments, our system can reduce the bandwidth demands of the video to be analyzed by at least 36.2% without losing analysis for main objects. © 2021 IEEE.

关键词： filtering Visual analytics Surveillance Object detection Bandwidth Streaming media filtering algorithms

来源：评论

学校读者我要写书评

暂无评论

Improved MM-MADRL Algorithm for Automatic Tuning of Multiparameter Control Systems

引用

IEEE ACCESS 2022年 10卷 64729-64740页

作者： Zhang, Hongming Assawinchaichote, Wudhichai Shi, Yan King Mongkuts Univ Technol Thonburi Fac Engn Dept Elect & Telecommun Engn Bangkok 10140 Thailand Tokai Univ Grad Sch Sci & Technol Kumamoto 8628652 Japan

Control systems are widely used in our lives, and good control can be achieved by obtaining the optimal tuning parameters of the control system. The number of parameters that need to be adjusted for different control systems varies. With an increase in tuning parameters, the difficulty of tuning grows. Therefore, this paper proposes an improved monkey multiagent DRL (IMM-MADRL) algorithm and selects 3 test functions to test the setting environment of 2-7 parameters. Thus, these parameters are adjusted. The IMM-MADRL algorithm is based on the modified monkey-multiagent DRL (MM-MADRL) algorithm, and its initialization method, position update method and somersault operation are further improved so that it can perform good parameter tuning for a control system with many parameters. The simulation part of this paper proves the advantage of the IMM-MADRL algorithm in a multiparameter control system.

关键词： PI control PD control Licenses Optimization Reinforcement learning Low-pass filters filtering algorithms Incomplete differential PID controller modified monkey-multiagent DRL (MM-MADRL) algorithm improved modified monkey-multiagent DRL (IMM-MADRL) algorithm optimization

来源：评论

学校读者我要写书评

暂无评论

The Strong Tracking Innovation Filter

引用

IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS 2022年第4期58卷 3261-3270页

作者： Kiani, Maryam Ahmadvand, Reza Sharif Univ Technol Dept Aerosp Engn Tehran *** Iran

Sliding innovation filter (SIF) has recently been introduced as a robust strategy for estimation of linear systems. The SIF has been extended to nonlinear systems via analytical linearization. However, as the performance of the extended SIF (ESIF) degrades in the presence of severe nonlinearities, this article has initially developed a derivative-free cubature SIF (CSIF) that uses statistical linearization for the error propagation. In addition, the SIF gain has been reformed to incorporate the innovation covariance matrix, thus reducing the estimation error. Furthermore, the adaptive fading factor has been employed to strengthen the robustness and convergence properties of the CSIF against abrupt changes of state variables. Simulation results of the proposed estimation algorithm named the strong tracking innovation filter (STIF) have been compared to those of the ESIF and the CSIF in different conditions of the modeling error in the dynamic system and statistical characteristics of the system inputs. This comparison has demonstrated the superior performance of the STIF in terms of the convergence rate, estimation accuracy, and the chattering elimination. Integration of the STIF into a sliding mode controller for the concurrent estimation and control of a Mars lander has reconfirmed the robustness and accuracy of the proposed STIF.

关键词： Estimation filtering theory Technological innovation Uncertainty filtering algorithms Robustness Jacobian matrices Cubature kalman filter fading factor robust estimation sliding innovation filter strong tracking filter

来源：评论

学校读者我要写书评

暂无评论

Tracking Multiple Spawning Targets Using Poisson Multi-Bernoulli Mixtures on Sets of Tree Trajectories

引用

IEEE TRANSACTIONS ON SIGNAL PROCESSING 2022年 70卷 1987-1999页

作者： Garcia-Fernandez, Angel F. Svensson, Lennart Univ Liverpool Dept Elect Engn & Elect Liverpool L69 3GJ Merseyside England Univ Antonio Nebrija ARIES Res Ctr Madrid Spain Chalmers Univ Technol Dept Elect Engn SE-41296 Gothenburg Sweden

This paper proposes a Poisson multi-Bernoulli mixture (PMBM) filter on the space of sets of tree trajectories for multiple target tracking with spawning targets. A tree trajectory contains all trajectory information of a target and its descendants, which appear due to the spawning process. Each tree contains a set of branches, where each branch has trajectory information of a target or one of the descendants and its genealogy. For the standard dynamic and measurement models with multi-Bernoulli spawning, the posterior is a PMBM density, with each Bernoulli having information on a potential tree trajectory. To enable a computationally efficient implementation, we derive an approximate PMBM filter in which each Bernoulli tree trajectory has multi-Bernoulli branches, obtained by minimising the Kullback-Leibler divergence. The resulting filter improves tracking performance of state-of-the-art algorithms in a simulated scenario.

关键词： Trajectory Information filters filtering algorithms Time measurement Target tracking Density measurement Standards Multiple target tracking spawning Poisson multi-Bernoulli mixture sets of tree trajectories

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Character Embedding Correction and Candidate Word Denoising

引用

IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING 2022年 30卷 76-86页

作者： Zheng, Kengtao Lin, Nankai Shengyi, Jiang Guangdong Univ Foreign Studies Key Lab Guangzhou Multilingual Intelligent Proc L Guangzhou 510006 Guangdong Peoples R China Guangdong Univ Foreign Studies Sch Informat Sci & Technol Guangzhou 510006 Guangdong Peoples R China

Inthis paper, we take Indonesian as the research object, and propose a multiple filter correction framework (MFCF). The main idea of MFCF is to remove noise from candidate words to increase the probability of correct words being selected. In MFCF, we use window search algorithm (WSA) to filter the candidate words in the dictionary. When searching for candidate words whose Levenshtein distance is 1, WSA reduces the candidate word search space by an average of 71%. When searching for candidate words whose Levenshtein distance is 2, the search space is reduced by an average of 55%. The reduction in search space has brought about an increase in search speed. When WSA searches for candidate words with Levenshtein distance equal to 1 and 2, the speed exceeds the current advanced search algorithm. A character vector-based candidate word scoring model (CWSM-CV) is also introduced in this paper. CWSM-CV is a simple but unsupervised method. In MFCF, we use CWSM-CV to filter the correct word in the candidate word list. Through exploring the feasibility of using word vector-based candidate word scoring model to score candidate words (CWSM-WV), we find the necessity of denoising the candidate word list and verified it with experiments. In order to apply this finding to the text correction, a new set of evaluation indicators are proposed to replace accuracy. Finally, we recommend that researchers who correct text in low-resource languages make the model an open system and publish it for users to use. The system receives user feedback as new data to gradually reduce the negative impact of data volume.

关键词： Dictionaries filtering algorithms Noise reduction Training Speech processing Neural networks Statistical analysis Non-word correction low-resource language search space candidate word score candidate word denoising

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：