A hybrid interval type-2 semi-supervised possibilistic fuzzy c-means clustering and particle swarm optimization for satellite image analysis

Abstract

Although satellite images can provide more information about the Earth's surface in a relatively short time and over a large scale, they are affected by observation conditions (e.g., wind, sun, rain, and humidity) and the accuracy of the image acquisition equipment. The objects on the images are often unclear and uncertain, especially at their borders. The fuzzy clustering technique allows each data pattern to belong to many different clusters through membership function (MF) values that can handle data patterns with unclear and uncertain boundaries well. However, this technique is quite sensitive to noise, outliers, and limitations in handling uncertainties. Furthermore, the membership degrees of type-1 fuzzy sets (T1FSs) are crisp, and in many cases, it is difficult to precisely determine the T1FS parameters. To overcome these disadvantages, we propose a hybrid method encompassing interval type-2 semi-supervised possibilistic fuzzy c-means clustering (IT2SPFCM) and particle swarm optimization (PSO) to form the proposed IT2SPFCMPSO. We experimented on several satellite images (Landsat-5 TM, Landsat-7 ETM+, Landsat-8, Sentinel-2A) to prove the effectiveness of the proposed method. Experimental results show that the IT2SPFCM-PSO algorithm achieves accuracies from 98.8% to 99.39%, which are higher than those of other matching algorithms. An analysis of the results by indicators PC-I, CE-I, D-I, XB-I, τ − I, and MSE also showed that the proposed method achieves better results in most experiments.

Optimization Effect Analysis of ACM-PSO Integrating Individual Adjustment and Cross Operation on Microgrid DG Technology

“…Mai et al proposed a hybrid algorithm based on fuzzy c-means clustering and PSO to solve the problem of unclear satellite images at present, and used this algorithm to process the boundaries and fuzzy areas of satellite images. The proposed algorithm's accuracy was 99.2%, which was superior to other comparison algorithms [9]. The automatic recognition system of atmospheric refractive index had low recognition rate.…”

“…On the other hand, the operating state of energy storage is determined. Then the actual load demand at each time in the system is shown in formula (9).…”

Evaluation Model of Youth Basketball Training Performance Based on PSO Algorithm

“…Particle swarm optimization (PSO) is a population-based stochastic optimization technique that mimics the swarm behavior of insects, herds, birds, and schools of fish. These groups search for food in a cooperative way, and each member of the group constantly changes its search mode by learning its own experience and that of other members [21][22][23]. Take the birds as an example.…”

Bio-Inspired Algorithms and Its Applications for Optimization in Fuzzy Clustering

“…Another recent study on this area is shown in [24], where the authors presented a hybrid semi-supervised interval type-2 possibilistic fuzzy c-means clustering and particle swarm optimization for optimizing results in satellite image analysis.…”