Effect of Data Representation for Time Series Classification—A Comparative Study and a New Proposal

Abstract

Time series classification (TSC) is becoming very important in the area of pattern recognition with the increased availability of time series data in various natural and real life phenomena. TSC is a challenging problem because, due to the attributes being ordered, traditional machine learning algorithms for static data are not quite suitable for processing temporal data. Due to the gradual increase of computing power, a large number of TSC algorithms have been developed recently. In addition to traditional feature-based, model-based or distance-based algorithms, ensemble and deep networks have recently become popular for time series classification. Time series are essentially huge, and classifying raw data is computationally expensive in terms of both processing and storage. Representation techniques for data reduction and ease of visualization are needed for accurate classification. In this work a recurrence plot-based data representation is proposed and time series classification in conjunction with a deep neural network-based classifier has been studied. A simulation experiment with 85 benchmark data sets from UCR repository has been undertaken with several state of the art algorithms for time series classification in addition to our proposed scheme of classification for comparative study. It was found that, among non-ensemble algorithms, the proposed algorithm produces the highest classification accuracy for most of the data sets.

Improved Recurrence Plots Compression Distance by Learning Parameter for Video Compression Quality

“…Furthermore, qRPCD works comparably to RP1+ResNet [ 20 ]. RP1+ResNet is a CNN-based method developed in 2019.…”

“…RP1+ResNet is a CNN-based method developed in 2019. According to [ 20 ], its average accuracy for the 27 dataset equals 78.8%, which is smaller than qRPCD. This result is astonishing, since qRPCD needs only one parameter, i.e., much fewer parameters to learn than the CNN.…”

“…Hatami et al [ 19 ] attempted to classify the RP images on the CNN architecture early on. Nakano et al [ 20 ] paid attention to the symmetric nature of RP and embedded different information to the half of RPs. Zhang et al [ 21 ] proposed multi-scale signed recurrence plots that retain upward/downward trends and the scale of images.…”

Enhancing Inference on Physiological and Kinematic Periodic Signals via Phase-Based Interpretability and Multi-Task Learning

“…These dynamics are the key to successfully understanding how those signals behave. There are some studies that have tried to tackle some of these issues for different tasks (e.g., classification, and forecasting) by leveraging deep neural networks to model the signals [6][7][8][9]. Some authors use recurrent neural networks (RNNs) and convolutional neural networks (CNNs) for long-term and short-term prediction [6][7][8][9].…”

“…There are some studies that have tried to tackle some of these issues for different tasks (e.g., classification, and forecasting) by leveraging deep neural networks to model the signals [6][7][8][9]. Some authors use recurrent neural networks (RNNs) and convolutional neural networks (CNNs) for long-term and short-term prediction [6][7][8][9]. Prior work has also used attention mechanisms and transformers [10,11] to extract relevant information for forecasting.…”