An improved krill herd algorithm with global exploration capability for solving numerical function optimization problems and its application to data clustering

Multi-population Black Hole Algorithm for the problem of data clustering

The retrieval of important information from a dataset requires applying a special data mining technique known as data clustering (DC). DC classifies similar objects into a groups of similar characteristics. Clustering involves grouping the data around k-cluster centres that typically are selected randomly. Recently, the issues behind DC have called for a search for an alternative solution. Recently, a nature-based optimization algorithm named Black Hole Algorithm (BHA) was developed to address the several well-known optimization problems. The BHA is a metaheuristic (population-based) that mimics the event around the natural phenomena of black holes, whereby an individual star represents the potential solutions revolving around the solution space. The original BHA algorithm showed better performance compared to other algorithms when applied to a benchmark dataset, despite its poor exploration capability. Hence, this paper presents a multi-population version of BHA as a generalization of the BHA called MBHA wherein the performance of the algorithm is not dependent on the best-found solution but a set of generated best solutions. The method formulated was subjected to testing using a set of nine widespread and popular benchmark test functions. The ensuing experimental outcomes indicated the highly precise results generated by the method compared to BHA and comparable algorithms in the study, as well as excellent robustness. Furthermore, the proposed MBHA achieved a high rate of convergence on six real datasets (collected from the UCL machine learning lab), making it suitable for DC problems. Lastly, the evaluations conclusively indicated the appropriateness of the proposed algorithm to resolve DC issues.

A novel krill herd algorithm with orthogonality and its application to data clustering

Krill herd algorithm (KHA) is an emerging nature-inspired approach that has been successfully applied to optimization. However, KHA may get stuck into local optima owing to its poor exploitation. In this paper, the orthogonal learning (OL) mechanism is incorporated to enhance the performance of KHA for the first time, then an improved method named orthogonal krill herd algorithm (OKHA) is obtained. Compared with the existing hybridizations of KHA, OKHA could discover more useful information from historical data and construct a more promising solution. The proposed algorithm is applied to solve CEC2017 numerical problems, and its robustness is verified based on the simulation results. Moreover, OKHA is applied to tackle data clustering problems selected from the UCI Machine Learning Repository. The experimental results illustrate that OKHA is superior to or at least competitive with other representative clustering techniques.

An adaptive QoS supportive approach for user based services using Krill Herd Approach over Internet of Things (KHAI)

The demand for a providing QoS adaptive routing over IoT networks is always a challenge among current research community. This research work KHAI proposes a framework for QoS-adaptive routing approach, which incorporates Krill Herd optimization model over IoT network. Variable QoS user preference and handling differential service types over a scalable IoT network shows that challenge for designing an adaptive QoS is a must. Research survey suggest that major works have been carried out on bandwidth appreciable services and route management approaches. Hence QoS adaptive user defined services, which adapt to variable service priority levels based on user demand and network resource utilization is proposed in this research work. The performance analysis of proposed approach shows an improved throughput of 97.51 Mbps and minimal packet loss of 37.29% over a session in comparison to traditional computational approaches. Considering large scale of interconnected IoT devices, proposed approach delivers near optimal solution of throughput and adaptive utilization of network resources.

G. EKEGWO: Enhanced Kernel-Based Exponential Grey Wolf Optimizer for Bi-Objective Data Clustering

The widespread application of clustering in various fields leads to the discovery of different clustering techniques in order to partition multidimensional data into separable clusters. Although there are various clustering approaches used in literature, optimized clustering techniques with multi-objective consideration are rare. This paper proposes a novel data clustering algorithm, Enhanced Kernel-based Exponential Grey Wolf Optimization (EKEGWO), handling two objectives. EKEGWO, which is the extension of KEGWO, adopts weight exponential functions to improve the searching process of clustering. Moreover, the fitness function of the algorithm includes intra-cluster distance and the inter-cluster distance as an objective to provide an optimum selection of cluster centroids. The performance of the proposed technique is evaluated by comparing with the existing approaches PSC, mPSC, GWO, and EGWO for two datasets: banknote authentication and iris. Four metrics, Mean Square Error (MSE), F-measure, rand and jaccord coefficient, estimates the clustering efficiency of the algorithm. The proposed EKEGWO algorithm can attain an MSE of 837, F-measure of 0.9657, rand coefficient of 0.8472, jaccord coefficient of 0.7812, for the banknote dataset.