Ship Track Regression Based on Support Vector Machine

Ban, Bo; Yang, Junjie; Chen, Pengguang; Xiong, Jiang; Wang, Qinruo

doi:10.1109/access.2017.2749260

Cited by 7 publications

(4 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This article research as thrust allocation strategy based on the 2.8 meters ship model, the bow propeller using channel propeller, where installed speed sensor, the stern propeller and other parts use full-revolving propeller, where installed speed sensor and full-revolving angle sensor [17]. The Power plants of each propeller use Yaskawa SGDV-2R8A01A ac servo motor with power 0.4kW, the rated speed is 3000r/min, and the propeller blade diameter D = 95mm.…”

Section: Simulation Resultsmentioning

confidence: 99%

Design and Implementation of Pseudo-Inverse Thrust Allocation Algorithm for Ship Dynamic Positioning

Xiong

Wang

et al. 2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

The pseudo-inverse method cannot optimize the angle and needs to give the azimuth angle artificially, therefore, when the dynamic positioning system has variable vector propellers and rudders, the pseudo-inverse method cannot be applied to the full automatic control and cannot realize the optimal exactly. In this paper, in view of the above problems, considering the propeller and the environment load conditions, a thrust allocation scheme based on the pseudo inverse algorithm with weight is proposed for minimizing the energy consumption. The thrust allocation scheme distributes the thrust after optimizing the angle. It combines the full-revolving propulsion angle optimization with the thrust optimization to realize the ship thrust allocation reasonably and efficiently and achieves the minimum energy consumption and wear. Finally, the experimental results verify the effectiveness of the proposed method. INDEX TERMS Pseudo-inverse method, dynamic positioning, thrust allocation, optimize.

show abstract

Section: Simulation Resultsmentioning

confidence: 99%

Design and Implementation of Pseudo-Inverse Thrust Allocation Algorithm for Ship Dynamic Positioning

Xiong

Wang

et al. 2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…According to Equations (2)–(4), there is a nonlinear relationship between X and boldR˜. Since SVR has a rather strong nonlinear approximation ability and antinoise ability [41], we use SVR to learn the regression function by identifying structures in the mapping of input X to output boldR˜.…”

Section: Detailed Description Of the Proposed Localization Schemementioning

confidence: 99%

“…Firstly, the measured RSSI value contains noise which would cause a large error in the result of the curve matching. Since SVR has a strong ability [41], we use the predicted RSSI curve instead of the measured RSSI curve to perform curve matching.…”

Section: Detailed Description Of the Proposed Localization Schemementioning

confidence: 99%

A Mobile Anchor Node Assisted RSSI Localization Scheme in Underwater Wireless Sensor Networks

Sun

Yuan

et al. 2019

Sensors

View full text Add to dashboard Cite

In this paper, a mobile anchor node assisted RSSI localization scheme in underwater wireless sensor networks (UWSNs) is proposed, which aims to improve location accuracy and shorten location time. First, to improve location accuracy, we design a support vector regression (SVR) based interpolation method to estimate the projection of sensor nodes on the linear trajectory of the mobile anchor node. The proposed method increases the accuracy of the nonlinear regression model of noisy measured data and synchronously decreases the estimation error caused by the discreteness of measured data. Second, to shorten location time, we develop a curve matching method to obtain the perpendicular distance from sensor nodes to the linear trajectory of the mobile anchor node. The location of the sensor node can be calculated based on the projection and the perpendicular distance. Compared with existing schemes that require the anchor node to travel at least two trajectories, the proposed scheme only needs one-time trajectory to locate sensor nodes, and the location time is shortened with the reduction in the number of trajectories. Finally, simulation results prove that the proposed scheme can obtain more accurate sensor node location in less time compared with the existing schemes.

show abstract

“…Kalman Filter (KF)-based techniques for tracking ships using Global Positioning System (GPS) data were introduced in [ 37 ]. Ban et al used a support vector regression (SVR) method for deposing outliers and regressing polluted ship tracks [ 38 ]. Chen et al proposed a novel method based on mean shift for automatic detection and tracking of a ship in the corrected video sequences [ 39 ].…”

Section: Related Workmentioning

confidence: 99%

A Self-Selective Correlation Ship Tracking Method for Smart Ocean Systems

Song

Guo

et al. 2019

Sensors

View full text Add to dashboard Cite

In recent years, with the development of the marine industry, the ship navigation environment has become more complicated. Some artificial intelligence technologies, such as computer vision, can recognize, track and count sailing ships to ensure maritime security and facilitate management for Smart Ocean systems. Aiming at the scaling problem and boundary effect problem of traditional correlation filtering methods, we propose a self-selective correlation filtering method based on box regression (BRCF). The proposed method mainly includes: (1) A self-selective model with a negative samples mining method which effectively reduces the boundary effect in strengthening the classification ability of the classifier at the same time; (2) a bounding box regression method combined with a key points matching method for the scale prediction, leading to a fast and efficient calculation. The experimental results show that the proposed method can effectively deal with the problem of ship size changes and background interference. The success rates and precisions were over 8 % higher than Discriminative Scale Space Tracking (DSST) on the marine traffic dataset of our laboratory. In terms of processing speed, the proposed method is higher than DSST by nearly 22 frames per second (FPS).

show abstract

Ship Track Regression Based on Support Vector Machine

Cited by 7 publications

References 17 publications

Design and Implementation of Pseudo-Inverse Thrust Allocation Algorithm for Ship Dynamic Positioning

Design and Implementation of Pseudo-Inverse Thrust Allocation Algorithm for Ship Dynamic Positioning

A Mobile Anchor Node Assisted RSSI Localization Scheme in Underwater Wireless Sensor Networks

A Self-Selective Correlation Ship Tracking Method for Smart Ocean Systems

Contact Info

Product

Resources

About