Fuzzy c‐means clustering‐based smart tracking model for three‐dimensional manoeuvring target including unknown acceleration input

Abstract

This study proposes a smart tracking model with multiple structures. To achieve optimal performance, an ideal tracking system should maintain contact with the target and constantly update its tracking data. One of the major problems to consider arises from the target motion uncertainty. Although the variance of the overall noise is time-varying and may reduce tracking efficiency, it is difficult to adaptively approximate this uncertainty. To solve these computational problems, a variety of techniques have been studied, and the adaptive interacting multiple model has shown the best result. However, predefined sub-models with different conditions for multiple models are required. Moreover, the acceleration intervals for different acceleration levels should be determined in advance. To alleviate these problems, the authors propose a multiple-structured smart tracking algorithm which properly separates the acceleration from the overall noise by fuzzy c-means clustering. The filter in the algorithm recognises the manoeuvring target as if it does not include the acceleration input, and precisely tracks the target with multiple structures. This study focuses on the acceleration causing the uncertainty and three-dimensional (3D) motion of the real target motion in the tracking problem. Finally, a 3D cruise missile example is provided to show the effectiveness of the proposed algorithm.

Reinforced Ultra-Tightly Coupled GPS/INS System for Challenging Environment

“…The proposed algorithms were implemented to real experimental data from Hammerhead AUV and results showed a promising result in improving the estimation of KF and enhancing the overall accuracy of the integrated INS/GPS system. Similar conclusions about the advantages of FLAC were also drawn in [12,13]. Sun proposed a generalized neutral network to implement fuzzy modeling and calibration of membership function was involved.…”

Artificial intelligence‐based short‐circuit fault identifier for MT‐HVDC systems

“…where 'y' is the number of data sets, 's' is the number of classes, μ ik is the membership of the kth data point in the ith class, 'h' is the number of coordinates required to describe the data sample location in the space. The cluster coordinates for each class are formulated as [35,36]…”

Smart tracking algorithm for multi‐static sonar based on expectation maximisation

“…The measurements should also be processed with an appropriate coordinate transformation scheme. Thus, the coordinates of the sensors are transformed into those of the primary system [13, 14]. The false alarm rate can be reduced, though it needs some addition to the computational process.…”