A granular sigmoid extreme learning machine and its application in a weather forecast

Extreme Learning Machine (ELM) is a class of machine learning systems or methods based on feedforward neural networks, which are suitable for supervised learning problems. The ELM is regarded as a special kind of FNN in the research, which is characterized by the fact that the weights of hidden layer nodes are randomly or artificially given. As a result, the ELM feature mapping is random. The generic approximation theorem states that any nonlinear piecewise continuous function may be used as the feature map. By introducing the theory of granular computing, this paper proposes a new granulation method of random sigmoid function. The Granular Sigmoid Extreme Learning Machine (GSELM) algorithm was proposed by combining the random sigmoid function with the extreme learning machine algorithm. After granulated data sets are processed by GSELM, the granulated multi-feature data will form granular vectors. The granular vector is processed in parallel, which makes the granular sigmoid extreme learning machine parallel computing. The GSELM is utilized to address the fundamental real-time issue of weather forecasting. The GSELM algorithm can predict whether the next day will be sunny or rainy more accurately and quickly, which is crucial to the field of meteorology. Several UCI data sets are used to test the feasibility of the GSELM algorithm. The verified GSELM algorithm is applied to the Australian weather forecast data set. According to the experimental findings, the GSELM algorithm can predict whether the next day will be sunny or rainy more accurately and quickly.