Secondary decomposition multilevel denoising method of hydro-acoustic signal based on information gain fusion feature DOI
Guohui Li, Haoran Yan, Hong Yang

et al.

Nonlinear Dynamics, Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 10, 2024

Language: Английский

A multi-timescale dynamic graph attention network (MTDGAT) for short-term traffic prediction under special events DOI
Lei Tian, Yuxin Ding,

Jingpeng Wen

et al.

Expert Systems with Applications, Journal Year: 2025, Volume and Issue: unknown, P. 127649 - 127649

Published: April 1, 2025

Language: Английский

Citations

0
A new denoising method of ship-radiated noise: Improved variational mode decomposition coupled with fractional order entropy double threshold criterion DOI
Guohui Li, Liwen Zhang, Hong Yang

et al.

Measurement Science and Technology, Journal Year: 2024, Volume and Issue: 35(12), P. 126112 - 126112

Published: Aug. 2, 2024

Abstract Ship-radiated noise (SRN) contains abundant ship characteristic information. The detection and analysis of SRN is very important for target recognition, positioning tracking. However, complex ocean easily interferes with the propagation in water. To achieve a preferable denoising effect, new method proposed. First, decomposed by an improved variational mode decomposition (DVMD) dung beetle optimizer, complexity each intrinsic function after measured fractional order refined composite multiscale fluctuation dispersion entropy (FRCMFDE). Second, distribution characteristics are analyzed, different adaptive division methods used to determine modes, i.e. it divides all modes into clean mildly noisy moderately highly modes. Then, locally weighted scatterplot smoothing dual-tree wavelet transform (IDTCWT) denoise respectively. Finally, denoised obtained reconstructing two groups proposed Rossler, Chen Lorenz signals, signal-to-noise ratio (SNR) 13.0785, 11.9390 12.3775 dB, Compared DVMD-FRCMFDE, DVMD-FRCMFDE-wavelet soft threshold ( WSTD) DVMD-FRCMFDE-IDTCWT, SNR increased 48%, 45.93% 38.76%, respectively, root mean square error 46.55%, 42.76% 30.04%, applied four types SRN. Based on these findings, enhances clarity smoothness phase space attractor, effectively suppresses marine environmental SRN, which provides solid groundwork subsequent processing

Language: Английский

Citations

2
A novel approach for underwater acoustic signal denoising based on improved time-variant filtered empirical mode decomposition and weighted fusion filtering DOI
Guohui Li,

Yaoyu Han,

Hong Yang

et al.

Ocean Engineering, Journal Year: 2024, Volume and Issue: 313, P. 119550 - 119550

Published: Oct. 23, 2024

Language: Английский

Citations

2
A Study of Mixed Non-Motorized Traffic Flow Characteristics and Capacity Based on Multi-Source Video Data DOI Creative Commons
Guobin Gu, Xin Sun, Benxiao Lou

et al.

Sensors, Journal Year: 2024, Volume and Issue: 24(21), P. 7045 - 7045

Published: Oct. 31, 2024

Mixed non-motorized traffic is largely unaffected by motor vehicle congestion, offering high accessibility and convenience, thus serving as a primary mode of "last-mile" transportation in urban areas. To advance stochastic capacity estimation methods provide reliable assessments roadway capacity, this study proposes model based on power spectral analysis. The treats discrete flow data time-series signal employs parameter to fit patterns. Initially, UAVs video cameras are used capture videos mixed flow. were processed with an image detection algorithm the YOLO convolutional neural network tracking using DeepSORT multi-target model, extracting flow, density, speed, rider characteristics. Then, autocorrelation partial functions employed distinguish among four classical models. parameters optimized minimizing AIC information criterion identify optimal fit. fitted parametric models analyzed transforming them from time domain frequency domain, spectrum then calculated. experimental results show that yields pure EV 2060-3297 bikes/(h·m) bicycle 1538-2460 bikes/(h·m). density-flow calculates 2349-2897 1753-2173 minimal difference between these estimates validates effectiveness proposed model. These findings hold practical significance addressing road congestion.

Language: Английский

Citations

2
Research on tidal energy prediction method based on improved time-varying filter-empirical mode decomposition and confluent double-stream neural network DOI
Yi Huang, Guohui Li

Ocean Engineering, Journal Year: 2024, Volume and Issue: 312, P. 119300 - 119300

Published: Sept. 24, 2024

Language: Английский

Citations

1
An ocean tidal energy point-interval forecasting system based on enhanced auxiliary feature, mode decomposition combined with compressive sensing and attention interaction DOI
Hong Yang, Qingsong Wu, Guohui Li

et al.

Journal of Cleaner Production, Journal Year: 2024, Volume and Issue: unknown, P. 143680 - 143680

Published: Sept. 1, 2024

Language: Английский

Citations

0
Redefining the modified Water Benefit-Based Ecological Index to evaluate the impact of cropland expansion on the ecological environment in an arid area DOI Creative Commons
Chenglong Yao,

Zexian Li,

Yuejian Wang

et al.

Journal of Cleaner Production, Journal Year: 2024, Volume and Issue: unknown, P. 143730 - 143730

Published: Sept. 1, 2024

Language: Английский

Citations

0
Secondary decomposition multilevel denoising method of hydro-acoustic signal based on information gain fusion feature DOI
Guohui Li, Haoran Yan, Hong Yang

et al.

Nonlinear Dynamics, Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 10, 2024

Language: Английский

Citations

0