A Robust Multi-Sensor Data Fusion Clustering Algorithm Based on Density Peaks

Abstract

In this paper, a novel multi-sensor clustering algorithm, based on the density peaks clustering (DPC) algorithm, is proposed to address the multi-sensor data fusion (MSDF) problem. The MSDF problem is raised in the multi-sensor target detection (MSTD) context and corresponds to clustering observations of multiple sensors, without prior information on clutter. During the clustering process, the data points from the same sensor cannot be grouped into the same cluster, which is called the cannot link (CL) constraint; the size of each cluster should be within a certain range; and overlapping clusters (if any) must be divided into multiple clusters to satisfy the CL constraint. The simulation results confirm the validity and reliability of the proposed algorithm.

Impact of the Validity Analysis Model and Multirelational Data Clustering Based on the Trust Probability

“…e experiments suggest that the method described in this research is successful, has a broad application potential, and is adaptable. Interval midpoint method [1,4] 0.868 0.655 0.735 0.435 [1,8] 0.878 0.635 0.728 0.455 [1,12] 0.865 0.603 0.655 0.429 [1,16] 0.792 0.598 0.539 0.421 [1,20] 0.768 0.568 0.435 0.386…”

“…. ., n) the greater the correlation degree of the data sequence, r (z 0 , z i ), the greater the correlation degree between the relevant factor s and the system behavior, and the greater the impact on the system [20]. erefore, the order relationship between the correlation degree of the relevant factor and the behavior factor is determined.…”

An Energy Effectual Swarm Based Hierarchical Density Peak Clustering (HDPCS) Method for Multi-sensor Data Fusion Strategy

“…The main drawback was it needs the number of clusters in advance. Jiande (2019) [12] have presented the clustering algorithm includes calculate the cluster for each data point and determine whether there was an overlapping cluster in dataset according to filter out clutter and obtain for k-means clustering. The disadvantage of such method was local minima and slow convergence.…”

On Sparsity Measures In Deep Subspace Clustering

“…Besides, the distance measures become ineffective for high-dimensional data like video, facial image datasets, multisensor data, due to the so-called curse of dimensionality phenomenon. Hence, subspace clustering plays an imperative role in applications which involve high-dimensional data such as-face recognition [3], hyperspectral image processing, [4] , multisensor data [5] etc. These shortcomings mentioned above motivated the researchers to look beyond the traditional similarity measures in the clustering task.…”