Building a hybridised meta-heuristic optimisation algorithm for efficient cluster analysis

Nature-inspired algorithms are a relatively recent field of meta-heuristics introduced to optimise the process of clustering unlabelled data. In recent years, hybridisation of these algorithms has been pursued to combine the best of multiple algorithms for more efficient clustering and overcoming their drawbacks. In this paper, we discuss a novel hybridisation concept where we combine the exploration and exploitation processes of the vanilla bat and vanilla whale algorithm to develop a hybrid meta-heuristic algorithm. We test this algorithm against the existing vanilla meta-heuristic algorithms, including the vanilla bat and whale algorithm. These tests are performed on several single objective CEC functions to compare convergence speed to the minima coordinates. Additional tests are performed on several real-life and artificial clustering datasets to compare convergence speeds and clustering quality. Finally, we test the hybrid on real-world cases with unlabelled clustering data, namely a credit card fraud detection dataset, and a COVID-19 diagnosis dataset, and end with a discussion on the significance of the work, its limitations and future scope. © 2023 Inderscience Enterprises Ltd.

Enhanced K-Means ++ Using Probability Theory For Efficient Prediction Of Air Pollution

Increasing concentrations of air pollutants is a global concern as it is a major underlying cause for other serious issues like premature deaths, global warming, increased susceptibility to heart diseases, lung disorders and skin disorders. Exposure to particulate pollutants increases vulnerability to Covid-19 and risk of succumbing to the virus. Air pollution analysis is a widely undertaken study by government officials and research scholars. K-means is a frequently used algorithm to understand the condition of the atmosphere from massive sensor generated data. The algorithm however comes with its drawbacks. Random initialization of the initial centroids can lead to bad clustering, an alternative, K-means++ does away with this, however, takes more execution time and iterations which is not ideal. We propose an advanced K-means++ initialization algorithm which incorporates an oversampling factor for smarter initialization of centroids using probability theory and weight assignment. We also propose a probability based convergence algorithm as opposed to the regular convergence algorithm to smartly select a portion of the data points to recompute the centroids. This will ensure a faster formation of final clusters. Real time Bengaluru, India air pollution data is scraped, pre-processed and clustered using the proposed technique. All the variants of K-means under study are compared over parameters of execution time, iterations and performance metrics. This work is also extended to tackle future air data points using a fast ensemble model. The solution proposed is better in terms of being reliable, fast and helps with better clustering, which leads to better air quality analysis, which leads to better air quality prediction, which leads to taking apt precautions to mitigate and regulate the air pollution.