Acta Univ. Agric. Silvic. Mendelianae Brun. 2012, 60(2), 69-72 | DOI: 10.11118/actaun201260020069

Time series classification using k-Nearest neighbours, Multilayer Perceptron and Learning Vector Quantization algorithms

Jiří Fejfar, Jiří Šťastný, Miroslav Cepl

Ústav informatiky, Mendelova univerzita v Brně, Zemědělská 1, 613 00 Brno, Česká republika

We are presenting results comparison of three artificial intelligence algorithms in a classification of time series derived from musical excerpts in this paper. Algorithms were chosen to represent different principles of classification - statistic approach, neural networks and competitive learning. The first algorithm is a classical k-Nearest neighbours algorithm, the second algorithm is Multilayer Perceptron (MPL), an example of artificial neural network and the third one is a Learning Vector Quantization (LVQ) algorithm representing supervised counterpart to unsupervised Self Organizing Map (SOM).
After our own former experiments with unlabelled data we moved forward to the data labels utilization, which generally led to a better accuracy of classification results. As we need huge data set of labelled time series (a priori knowledge of correct class which each time series instance belongs to), we used, with a good experience in former studies, musical excerpts as a source of real-world time series. We are using standard deviation of the sound signal as a descriptor of a musical excerpts volume level.
We are describing principle of each algorithm as well as its implementation briefly, giving links for further research. Classification results of each algorithm are presented in a confusion matrix showing numbers of misclassifications and allowing to evaluate overall accuracy of the algorithm. Results are compared and particular misclassifications are discussed for each algorithm. Finally the best solution is chosen and further research goals are given.

Keywords: classification, k-Nearest Neighbours, Multilayer Perceptron, Learning Vector Quantization

Grants and funding:

This paper is supported by IGA project 39/2011.

Received: November 30, 2011; Published: October 3, 2013  Show citation