K-Means Cluster Using Rainfall and Storm Prediction in Machine Learning Technique

Abstract

Data Mining involves extracting meaningful information from the available data in a user understandable manner. Its role is to analyze voluminous data that is being often assembled. Using the approach of Data mining techniques various business related queries can be attended which formerly were extremely time-consuming to answer. There exist uncontrollable natural disasters that critically hampers and costs human life, environment and revenue material. Natural calamities like heavy rainfall and floods cannot be well predicted until it happens, also it’s beyond one’s power to control them. The aftereffect or destruction caused by these calamities prevails for many years. The term disaster is a result of a vulnerable condition caused by heavy rainfall, flood or storm that can have intense effect at a smaller scale such as a village or at a larger scale such as city or state. Clustering model that was developed before confronted the issue of time complexity, low processing speed and were inappropriate for huge datasets. The current research work proposes the approach of K means clustering that is a subset of ML (machine learning) techniques that are capable to process huge datasets and performs quick computation compared to rest of the clustering model. Various stages in this proposed system include Dataset Collection, Pre-processing, Feature selection, K-means clustering. Among these, the K-means clustering tool which is actually a subset of data-mining and ML approach is employed to cluster observations in the form of groups. It’s a form of unsupervised learning that rectifies the clustering problem. The results reveal that the K-means clustering tool performs clustering faster than the other existing technique.

Abordagem de árvore de regressão para análise de dados de distribuição pluviométrica na cidade de São Carlos – SP

“…Em seu trabalho, Yovan Felix et al (2019) dispõe do algoritmo K-means de aprendizado de máquina. Como resultado, a abordagem foi descrita seguindo um fluxo de etapas sequenciais como: coleção de conjunto de dados, pré-processamento, filtragem, seleção de recursos, e por último o cluster K-means.…”

Research on the Identification of Typical Terrain Patterns in Yunnan Province Based on the K-Means Technology

“…The method we used to identify typical terrain is the K-means clustering technique, which is mainly based on the Euclidean distance between different data and regards them as belonging to the same category by calculating the minimum Euclidean distance [10]. Currently, the K-means clustering technique is widely used in the fields of machine learning [11], image processing [12], climate change [13] and market analysis [14]. For example, in market analysis, K-means can be used to classify customers in order to better understand their needs and behavioral patterns; in the field of image processing, K-means can be used for image segmentation, clustering similar pixels together to form objects.…”

Typical Modes of the Wind Speed Diurnal Variation in Beijing Based on the Clustering Method

“…The clustering method is unsupervised learning, which does not rely on predefined samples and can automatically learn and label samples through iteration [13]. At present, it is widely used in fields such as machine learning [14], image recognition [15,16], speech recognition [17], and climate change [18]. Because the K-means clustering method is based on calculating the spatial distance, it is generally used in numerical samples.…”