检索结果-内蒙古大学图书馆

A Directional Particle Filter-Based Multi-Floor Indoor Positioning System

IEEE ACCESS 2022年 10卷 116317-116325页

作者： Huang, Shao-Yung Huang, Hsin-Yang Chong, Hua Yuan Jiang, Jun-Bang Leu, Jenq-Shiou Vitek, Stanislav Natl Taiwan Univ Sci & Technol Dept Elect & Comp Engn Taipei 10607 Taiwan Czech Tech Univ Fac Elect Engn Dept Radio Engn Prague 16627 Czech Republic

In recent years, extensive research and applications have demonstrated that a more accurate and stable indoor positioning system (IPS) can be realized through the complementarity of different technologies. However, improving the accuracy of a single positioning technology would significantly impact the subsequent fusion. In this paper, we proposed a smartphone positioning system based on pedestrian dead reckoning (PDR) fusing with a floor estimation module (FEM) and a directional particle filter (PF) extracted by the idea of a regular PF to improve positioning accuracy. Generally, particles are generated by circle-shaped distribution by a regular PF, leading to producing some useless particles that waste computing resources. To tackle this issue, our proposed directional PF uses the particle more effectively by adjusting the distribution shape of particles with an estimated moving direction. Comprehensive experiments are conducted to verify the positioning accuracy and robustness of the proposed method. The experimental data show that the positioning error of our proposed method is only 1.53 m in a multi-floor path with a total length of 306 m.

关键词： Quaternions filtering algorithms IP networks Smart phones Low-pass filters Buildings Gyroscopes Dead reckoning Indoor communication Directional particle filtering indoor positioning system pedestrian dead reckoning smartphone-based

来源：评论

学校读者我要写书评

暂无评论

Short-Term Power Load Prediction Based on VMD-SG-LSTM

引用

IEEE ACCESS 2022年 10卷 102396-102405页

作者： Sun, Qiu Cai, Huafeng Hubei Univ Technol Sch Elect & Elect Engn Wuhan 430068 Peoples R China Hubei Univ Technol Xiangyang Ind Inst Xiangyang 210023 Peoples R China

Power load prediction plays an important role in the safety and stability of national power system. However, due to the nonlinear and multi-frequency characteristics of the power system itself, power load prediction is difficult. To address this problem, we propose a short-term power load prediction model based on variational mode decomposition (VMD). First, original data are decomposed into intrinsic mode function (IMF) of different frequencies using the VMD algorithm, and the decomposed sub-functions are reconstructed. After smoothing the reconstructed data by Savitzky-Golay (S-G) filtering algorithm, the change trend of raw data (CTRD) is obtained. Then, IMF, CTRD and raw data are used as inputs to predict short-term power load by long short-term memory network (LSTM). Finally, the proposed prediction model is compared with the other two groups of prediction models. The results show that the proposed VMD-SG-LSTM prediction model has high fitting ability and high prediction accuracy, and is an effective method for short-term power load prediction.

关键词： Predictive models Load modeling Data models Memory management filtering algorithms Neural networks Time series analysis Power load prediction variational mode decomposition intrinsic mode function S-G filtering long short-term memory network

来源：评论

学校读者我要写书评

暂无评论

Total Least Squares Normalized Subband Adaptive Filter Algorithm for Noisy Input

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS 2022年第3期69卷 1977-1981页

作者： Zhao, Haiquan Chen, Yida Liu, Jun Zhu, Yingying Southwest Jiaotong Univ Key Lab Magnet Suspens Technol & Maglev Vehicle Minist Educ Chengdu 610031 Peoples R China Southwest Jiaotong Univ Sch Elect Engn Chengdu 610031 Peoples R China Chengdu Jiaoda Guangmang Technol Co Ltd Chengdu 610041 Peoples R China

Subband adaptive filter has been widely applied to process correlated input signals due to its decorrelation property. However, the performance of the subband adaptive filter algorithm will be drastically degraded in the case of both the input and output signals are contaminated with noise. To tackle this problem, this brief proposes a total least squares normalized subband adaptive filter (TLS-NSAF) algorithm,which is different from bias-compensated schemes. The proposed algorithm is derived by employing the Rayleigh quotient as the cost function and the gradient steepest descent method. The local mean stability and computational complexity of the proposed algorithm are also analyzed. Simulation results demonstrate that the TLS-NSAF algorithm has better performance in comparison with previous algorithms.

关键词： Signal processing algorithms Convergence filtering algorithms Adaptive filters Adaptation models Computational modeling Computational complexity Correlated input errors-in-variables model subband adaptive filter total least squares

来源：评论

学校读者我要写书评

暂无评论

Variable Kernel Width Algorithm of Generalized Maximum Correntropy Criteria for Censored Regression

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS 2022年第3期69卷 1877-1881页

作者： Zhao, Haiquan Chen, Bing Zhu, Yingying He, Xiaoqiong Shu, Zeliang Southwest Jiaotong Univ Minist Educ Key Lab Magnet Suspens Technol & Maglev Vehicle Chengdu 610031 Peoples R China Southwest Jiaotong Univ Sch Elect Engn Chengdu 610031 Peoples R China

The constant kernel width of generalized maximum correntropy criteria (GMCC) has arisen that the steady-state error and convergence speed can be mutually exclusive. To solve this problem, this brief proposes the variable kernel width (VKW) GMCC algorithm. Actually, due to the censored problem, the output data value beyond the limit of the recording device can not be well observed. In this case, we further developed a variable kernel width GMCC algorithm based on censored regression (CR-VKWGMCC). Simulation results show that the proposed CR-VKWGMCC algorithm has excellent performance in both Gaussian and non Gaussian noise.

关键词： Signal processing algorithms Kernel Steady-state filtering algorithms Convergence Adaptive filters Optimized production technology Generalized maximum correntropy criteria variable kernel width censored regression adaptive filtering

来源：评论

学校读者我要写书评

暂无评论

Stop or Forward: Dynamic Layer Skipping for Efficient Action Recognition 23

Stop or Forward: Dynamic Layer Skipping for Efficient Action...

引用

23rd IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

作者： Seon, Jonghyeon Hwang, Jaedong Mun, Jonghwan Han, Bohyung Seoul Natl Univ Seoul South Korea MIT Cambridge MA 02139 USA Kakao Brain Seongnam South Korea

ISBN: (纸本)9781665493468

One of the challenges for analyzing video contents (e.g., actions) is high computational cost, especially for the tasks that require processing densely sampled frames in a long video. We present a novel efficient action recognition algorithm, which allocates computational resources adaptively to individual frames depending on their relevance and significance. Specifically, our algorithm adopts LSTM-based policy modules and sequentially estimates the usefulness of each frame based on their intermediate representations. If a certain frame is unlikely to be helpful for recognizing actions, our model stops forwarding the features to the rest of the layers and starts to consider the next sampled frame. We further reduce the computational cost of our approach by introducing a simple yet effective early termination strategy during the inference procedure. We evaluate the proposed algorithm on three public benchmarks: ActivityNet-v1.3, Mini-Kinetics, and THUMOS'14. Our experiments show that the proposed approach achieves outstanding trade-off between accuracy and efficiency in action recognition.

关键词： Location awareness Knowledge engineering Heuristic algorithms Semantics Memory management Termination of employment filtering algorithms

来源：评论

学校读者我要写书评

暂无评论

Automated Filter Pruning Based on High-Dimensional Bayesian Optimization

引用

IEEE ACCESS 2022年 10卷 22547-22555页

作者： Kim, Taehyeon Choi, Heungjun Choe, Yoonsik Yonsei Univ Dept Elect & Elect Engn Seoul 03722 South Korea

Filter pruning is necessary to efficiently deploy convolutional neural networks on edge devices that have limited computational resources and power budgets. With conventional filter pruning techniques, the same pruning rate is manually specified for different convolutional layers, which is suboptimal and time-consuming. To extract the features from the coarse level to the fine level, the number of filters in each layer has various distributions. Therefore, it is unsuitable to utilize the same pruning rate for different functional layers. To address this issue, we propose a high-dimensional Bayesian optimization-based filter pruning (HDBOFP) algorithm, which aims to automatically determine the most appropriate pruning rate for each convolutional layer. In addition, the proposed method can automatically identify optimal pruning-rate combinations without a time-consuming retraining phase. Compared with conventional filter pruning methods, this automated filter pruning technique exhibits a higher efficiency, which improves accuracy and reduces the required human labor. The effectiveness of our automated filter pruning algorithm is validated through two major computer vision applications, namely image classification and object detection. Specifically, when used in combination with ResNet-110 to classify the CIFAR-10 dataset, HDBOFP reduces the required number of float point operations (FLOPs) by more than 62% without affecting accuracy. Similarly, when HDBOFP is added to the YOLOv5l framework to run detection experiments on the MS-COCO 2017 dataset, FLOPs decrease by more than 43% with only a 1.2% loss in mean average precision, which has advanced the previous studies.

关键词： filtering algorithms Bayes methods Optimization Information filters Linear programming Degradation Convolutional neural networks Bayesian optimization convolutional neural network acceleration dimensionality reduction filter pruning hyper-parameter optimization

来源：评论

学校读者我要写书评

暂无评论

Improved Robust Total Least Squares Adaptive Filter algorithms Using Hyperbolic Secant Function

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS 2022年第9期69卷 3944-3948页

作者： Chen, Yida Zhao, Haiquan Southwest Jiaotong Univ Minist Educ Key Lab Magnet Suspens Technol & Maglev Vehicle Chengdu 610031 Peoples R China Southwest Jiaotong Univ Sch Elect Engn Chengdu 610031 Peoples R China

In the errors-in-variables (EIV) model, the total least squares (TLS) algorithm has shown good convergence performance. In this model, the input and output signals are simultaneously infected with noise. However, when the output signal is contaminated with impulse noise, the convergence performance of TLS will decrease or even diverge. In order to settle this problem, we propose a hyperbolic secant total least squares (HSTLS) algorithm through adopting the hyperbolic secant function as the cost function. The HSTLS algorithm shows better performance in non-Gaussian noise environment. At the same time, in order to deal with the contradiction between the algorithm's convergence speed and steady-state deviation with the fixed step size, this brief also provides a new variable step size strategy. The improved variable step size HSTLS (VHSTLS) algorithm shows better performance in simulation. Furthermore, to reduce steady-state deviation of the HSTLS algorithm in sparse systems, a series of improved HSTLS algorithms based on the sparse criterion have also been proposed, and they also have excellent convergence performance.

关键词： Convergence Steady-state Software algorithms Mathematical models filtering algorithms Adaptive systems Adaptation models Errors-in-variables model hyperbolic secant impulsive noise total least squares variable step size sparse system

来源：评论

学校读者我要写书评

暂无评论

A Hybrid SFANC-FxNLMS Algorithm for Active Noise Control Based on Deep Learning

引用

IEEE SIGNAL PROCESSING LETTERS 2022年 29卷 1102-1106页

作者： Luo, Zhengding Shi, Dongyuan Gan, Woon-Seng Nanyang Technol Univ Sch Elect & Elect Engn Singapore 639798 Singapore

The selective fixed-filter active noise control (SFANC) method selecting the best pre-trained control filters for various types of noise can achieve a fast response time. However, it may lead to large steady-state errors due to inaccurate filter selection and the lack of adaptability. In comparison, the filtered-X normalized least-mean-square (FxNLMS) algorithm can obtain lower steady-state errors through adaptive optimization. Nonetheless, its slow convergence has a detrimental effect on dynamic noise attenuation. Therefore, this paper proposes a hybrid SFANC-FxNLMS approach to overcome the adaptive algorithm's slow convergence and provide a better noise reduction level than the SFANC method. A lightweight one-dimensional convolutional neural network (1D CNN) is designed to automatically select the most suitable pre-trained control filter for each frame of the primary noise. Meanwhile, the FxNLMS algorithm continues to update the coefficients of the chosen pre-trained control filter at the sampling rate. Owing to the effective combination of the two algorithms, experimental results show that the hybrid SFANC-FxNLMS algorithm can achieve a rapid response time, a low noise reduction error, and a high degree of robustness.

关键词： filtering algorithms Signal processing algorithms Band-pass filters Noise reduction Classification algorithms Training Process control Active noise control selective fixed-filter ANC deep learning hearables

来源：评论

学校读者我要写书评

暂无评论

An M-Estimation-Based Improved Interacting Multiple Model for INS/DVL Navigation Method

引用

IEEE SENSORS JOURNAL 2022年第13期22卷 13375-13386页

作者： Hou, Lanhua Xu, Xiaosu Yao, Yiqing Wang, Di Southeast Univ Key Lab Microinertial Instrument & Adv Nav Techno Minist Educ Sch Instrument Sci & Engn Nanjing 210096 Peoples R China

This paper presents an M-estimation-based Improved Interacting Multiple Model (IIMM) algorithm for inertial navigation system (INS)/Doppler velocity logs (D VL) integrated method to directly apply in complex underwater environment without empirical parameters. Considering the time-varying measurement noise covariance, a variable model structure based on Bayesian estimation law is proposed to adapt to the environment and an adaptive state transition probability matrix is generated to promote the model adaption. Meanwhile, M-estimation-based filter is employed as primary model to save IIMM from the effect of outliers. The performance of the IIMM algorithm is evaluated on simulation, land vehicle, and Yangtze River test, where the state-of-the-art is compared adequately. The robustness simulation test is also performed. It is highlighted that IIMM approach can adapt to actual model rapidly and can resist outliers efficiently. The proposed IIMM method can improve the accuracy and robustness of the navigation system in a severe and unknown environment without increasing the computational load.

关键词： Adaptation models Navigation Hidden Markov models Kalman filters Sensors Noise measurement filtering algorithms Interacting multiple model robust Kalman filter INS DVL integrated navigation system

来源：评论

学校读者我要写书评

暂无评论

A 2-Stage EM Algorithm for Online Peak Detection, an Application to TCSPC Data

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS 2022年第9期69卷 3625-3629页

作者： Poisson, Valentin Guicquero, William Coriat, David Sicard, Gilles Univ Grenoble Alpes CEA LIST LETI F-38054 Grenoble France

Time-Correlated Single Photon Counting (TCSPC) sensors based on the combination of Single Photon Avalanche Diodes (SPADs), Time to Digital Converters (TDCs) and histogram-builders have become a standard for depth imaging using direct Time of Flight (D-ToF). However, one of the main current issue of this working mode is intrinsically due to the large amount of data required to generate pixelwise ToF histograms. To overcome this limitation, a 2-stage Expectation Maximization (EM) algorithm for online peak detection with its Register Transfer Level hardware implementation is proposed. The online estimator consists in sequentially computing the statistical parameters that directly encode the latent spatial distance and intensity information of the illuminated scene. The evaluation on synthetic data demonstrates that with a compression ratio of 0.4%, our approach can efficiently reduce the pixel pitch by around 40% without sacrificing timing resolution.

关键词： Histograms Single-photon avalanche diodes Photonics Hardware filtering algorithms Classification algorithms Mixture models Time-correlated single photon counting ToF imaging online expectation maximization SPAD sensors

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：