Genetic Programming and Serial Processing for Time Series Classification

Abstract

This work describes an approach devised by the authors for time series classification. In our approach genetic programming is used in combination with a serial processing of data, where the last output is the result of the classification. The use of genetic programming for classification, although still a field where more research in needed, is not new. However, the application of genetic programming to classification tasks is normally done by considering the input data as a feature vector. That is, to the best of our knowledge, there are not examples in the genetic programming literature of approaches where the time series data are processed serially and the last output is considered as the classification result. The serial processing approach presented here fills a gap in the existing literature. This approach was tested in three different problems. Two of them are real world problems whose data were gathered for online or conference competitions. As there are published results of these two problems this gives us the chance to compare the performance of our approach against top performing methods. The serial processing of data in combination with genetic programming obtained competitive results in both competitions, showing its potential for solving time series classification problems. The main advantage of our serial processing approach is that it can easily handle very large datasets.

Programação genética aplicada no processo de previsão: um estudo de caso aplicado em chamadas de uma central de teleatendimento

“…Alguns trabalhos aplicam computação evolucionária para executar previsão de series temporais [10], [1] e [7]. Estes trabalhos buscam criar um modelo de previsão utilizando a temática de populações através da PG.…”

“…Já em [7] um algoritmo genéticoé aplicado em series temporais para detectar padrões nas séries de dados sobre terremotos. Em [1] a programação genéticaé utilizada para classificar séries temporais. Já em [6] um conjunto de experimentosé realizado para comparação da PG com métodos como ARIMA e alisamento exponencial.…”

“…A programação genéticaé uma técnica automática de programação que propicia a evolução de programas. Alguns trabalhos utilizam o paradigma da programação genética em conjunto com a regressão simbólica para lidar com o tema de previsão de séries temporais [3], [10] e [1]. Este tipo de abordagemé interessante para a automatização do processo de geração de boas soluções e tem mostrado resultados em algumasáreas de aplicação [6] e [15].…”

A hybrid gene expression programming algorithm based on orthogonal design

“…Table 4 presents the descriptive statistics of the input attributes. For simplicity, all the input attributes are then scaled to a range of [1,10] by dividing 10 or 100. Table 5 reports the average approximation accuracy for various algorithms, such as conventional GEP 5 and neural networks 13 , over 30 independent runs.…”

“…Finally the best individual with highest fitness is selected as the final output. Numerical experiments demonstrate that GEP has a significantly better performance compared to genetic algorithm (GA) 27,30 and genetic programming (GP) 1,17 , and surpasses those conventional methods by more than two orders of magnitude 10,11,12 . However, GEP has also been shown to have certain disadvantages, such as slow convergence and low solution accuracy, particularly for problems with a high-dimensional and large space 4,6,24 .…”