Multivariate time series prediction of lane changing behavior using deep neural network

Many real world pattern classification problems involve the process and analysis of multiple variables in temporal domain. This type of problem is referred to as Multivariate Time Series (MTS) problem. It remains a challenging problem due to the nature of time series data: high dimensionality, large data size and updating continuously. In this paper, we use three types of physiological signals from the driver to predict lane changes before the event actually occurs. These are the electrocardiogram (ECG), galvanic skin response (GSR), and respiration rate (RR) and were determined, in prior studies, to best reflect a driver's response to the driving environment. A novel Group-wise Convolutional Neural Network, MTS-GCNN model is proposed for MTS pattern classification. In our MTS-GCNN model, we present a new structure learning algorithm in training stage. The algorithm exploits the covariance structure over multiple time series to partition input volume into groups, then learns the MTS-GCNN structure explicitly by clustering input sequences with spectral clustering. Different from other feature-based classification approaches, our MTS-GCNN can select and extract the suitable internal structure to generate temporal and spatial features automatically by using convolution and down-sample operations. The experimental results showed that, in comparison to other state-of-the-art models, our MTS-GCNN performs significantly better in terms of prediction accuracy.