Auto-adaptive multilayer perceptron for univariate time series classification. (1st November 2021)

• Record Type: Journal Article
• Authors: Arias del Campo, Felipe; Guevara Neri, María Cristina; Vergara Villegas, Osslan Osiris; Cruz Sánchez, Vianey Guadalupe; Ochoa Domínguez, Humberto de Jesús; García Jiménez, Vicente
• Is Part Of: Expert systems with applications. Volume 181(2021)
• Publication Date: 2021-11-01
• Subjects: Time series -- Time series classification -- Multilayer perceptron -- UCR data set; Expert systems (Computer science) -- Periodicals; Systèmes experts (Informatique) -- Périodiques; Electronic journals; 006.33
• DOI: 10.1016/j.eswa.2021.115147
• Languages: English
• ISSNs: 0957-4174

Abstract

Highlights: A novel auto-adaptive MLP for time series classification is proposed. Batch size and number of neurons in the hidden layers auto-adapts according to time series nature. Our model does not need a computer cluster, it runs on standard equipment. Accuracy obtained with our MLP is competitive versus 14 state-of-the-art methods. Experiments on 61 univariate UCR data sets verify effectiveness of our proposal. Abstract: Time Series Classification (TSC) is an intricate problem that has encountered applications in various science fields. Accordingly, many researchers have presented interesting proposals to tackle the TSC problem. Nevertheless, most methods are hand-crafted to classify specific Time Series (TS) and are computationally expensive even for small data sets. In this paper, we propose a new approach to the Multilayer Perceptron (MLP) for TSC. The main novelty is that the hyperparameters related to batch size and the number of neurons in the hidden layers are auto-adapted according to the TS nature. We carried out an empirical study on 61 benchmark data sets from the University of California, Riverside (UCR). The experimental evaluation revealed that our proposal is competitive when we compare the accuracy versus 14 state-of-the-art methods. A non-parametric statistical test verifies that the proposed MLP ranked in fourth place and can be executed on standard computer equipment, making it simple, accessible, and competitive.