Short-term time series forecasting is pivotal in various scientific and industrial fields. Recent advancements in deep learning-based technologies have significantly improved the efficiency and accuracy of short-term time series modeling. Despite advancements, current time short-term series forecasting methods typically emphasize modeling dependencies across time stamps but frequently overlook inter-variable dependencies, which is crucial for multivariate forecasting. We propose a multi patterns memory model discovering various dependency patterns for short-term multivariate time series forecasting to fill the gap. The proposed model is structured around two key components: the short-term memory block and the long-term memory block. These networks are distinctively characterized by their use of asymmetric convolution, each tailored to process the various spatial-temporal dependencies among data. Experimental results show that the proposed model demonstrates competitive performance over the other time series forecasting methods across five benchmark datasets, likely thanks to the asymmetric structure, which can effectively extract the underlying various spatial-temporal dependencies among data.

Multivariate time series prediction is a critical problem that is encountered in many fields, and recurrent neural network (RNN)‐based approaches have been widely used to address this problem. However, traditional RNN‐based approaches for predicting multivariate time series are still facing challenges, as time series are often related to each other and historical observations in real‐world applications. To address this limitation, this paper proposes a spatiotemporal self‐attention mechanism‐based LSTNet, which is a multivariate time series forecasting model. The proposed model leverages two self‐attention strategies, spatial and temporal self‐attention, to focus on the most relevant information among time series. The spatial self‐attention is used to discover the dependences between variables, while temporal attention is employed to capture the relationship among historical observations. Moreover, a standard deviation term is added to the objective function to track multivariate time series effectively. To evaluate the proposed method’s performance, extensive experiments are conducted on multiple benchmarked datasets. The experimental results show that the proposed method outperforms several baseline methods significantly. Therefore, the proposed spatiotemporal self‐attention‐based LSTNet is a promising approach for predicting multivariate time series.

Tactile icons were proposed to convey non-visual information as an abstract approach. Perception of transformational Tactons has been explored, which encode two or more dimensions of information with various vibrotactile parameters. Unlike transformational Tactons, compound Tactons are a sequence of two or more one-element Tactons. However, little has been done on how to design compound Tactons to present non-visual information effectively. This article investigates mean recognition rates and information transfer values of compound Tactons that encode complex navigation information, and evaluates their effectiveness on assisting the participants to navigate in a virtual city. Results of the experiments indicate that overall identification rate for three-parameter Tactons is 92.7% by manipulating different vibrotactile parameters, and 88.7% for four-parameter Tactons by adding an extra thermal parameter; guided by these compound Tactons, all participants were able to reach destinations in the simple virtual urban environment. Therefore, compound tactile icons can be a potential way of conveying multidimensional information.