Novel approaches for classification based on Cuckoo Search Strategy

Abstract

This paper introduces a novel bio inspired clustering algorithm called Cuckoo Search Clustering Algorithm (CSCA). This algorithm is based on the recently proposed Cuckoo Search Optimization technique which mimics the breeding strategy of the parasitic bird-cuckoo. The algorithm is further extended to a classification method, Biogeography Based Cuckoo Search Classification Algorithm (BCSCA), which is a hybrid approach of the two nature inspired metaheuristic techniques. The proposed algorithms are validated with real time remote sensing satellite image datasets. The CSCA was first tested with benchmark dataset, which yields good results. Inspired by the results, it was applied on two real time remote sensing satellite image datasets for extraction of the water body, which itself is a quite complex problem. A new method for the generation of new cuckoos has been proposed, which is used in the algorithms. The resulting algorithm is conceptually simpler, takes less parameter than other nature inspired algorithms, and, after some parameter tuning, yields very good results. The extended algorithm BCSCA is also tested on the same satellite image for identifying different land covers by classifying the image in various classes. The algorithm was successful in classifying other land cover regions like rocky, barren, urban and vegetation. We strongly feel that results can be further improved by finer tuning of the parameters. Both the algorithms use Davies-Bouldin index (DBI) as fitness function. Further exploration of suggested algorithms CSCA and BCSCA may prove them to be strong entrants in the pool of nature inspired techniques.

A novel animal migration algorithm for global numerical optimization

“…Biogeography-based optimization is a recently proposed evolutionary algorithm, inspired by the migration behavior of island species [15]. Cuckoo search algorithm is inspired by the obligate brood parasitic behavior of some cuckoo species in combination with the Lévy flight behavior of some birds and fruit flies [16], and applied to classification problem [17], constrained global optimization [18], and various modification version cuckoo algorithm. Bat Algorithm (BA) is a novel meta-heuristic optimization algorithm based on the echolocation behavior of micro-bats, which was proposed by Xin-she Yang in 2010 [2].…”

Cuckoo Search Based Decision Fusion Techniques for Natural Terrain Understanding

“…While exploring nature inspired meta-heuristics we developed four nature inspired techniques for natural terrain understanding (Panchal, 2009;Goel 2013). Experimental results for these techniques demonstrated that the attained accuracies for widely varying terrains in a given region vary greatly.…”

“…• Terrain Analyzers: Different analyzers can be used at this step which provides crisp information about the terrains present in the study region. Here four nature inspired terrain analyzers proposed by us (Panchal, 2009;Goel, 2013) have been used for terrain identification. Different color codes are used to represent each terrain type in the output image.…”

“…For maintaining the diversity among these analyzers, two of the algorithms used are based on the hybridization of nature inspired techniques with the approximate reasoning techniques -RBBO (Rough Set + Biogeography Based Optimization) (Panchal, 2009) and FBBO (Fuzzy C means + Biogeography Based Optimization) . The remaining two algorithms are the result of the hybridization of nature inspired techniques -PBBO (Particle Swarm Optimization + Biogeography Based Optimization) and CBBO (Cuckoo Search + Biogeography Based Optimization) (Goel, 2013)…”

Single and multi-objective ant programming for mining interesting rare association rules

“…Representative types of SI are particle swarm optimisation [15,16], which deals with the movement of flocks of birds or schools of fish; ant colony optimisation (ACO) [17,18], which takes inspiration from the behaviour and self-organisation capabilities of ant colonies; or bee swarm intelligence [19], which models some of the features of honey bees. The SI field is in continuous development, and new optimisation algorithms are being devised from the biological behaviours of bats [20], mosquitoes [21], cuckoos [22] and other organisms.…”