Forecasting of multivariate time series data, for instance the prediction of electricity consumption, solar power production, and polyphonic piano pieces, has numerous valuable applications. However, complex and non-linear interdependencies between time steps and series complicate this task. To obtain accurate prediction, it is crucial to model long-term dependency in time series data, which can be achieved by recurrent neural networks (RNNs) with an attention mechanism. The typical attention mechanism reviews the information at each previous time step and selects relevant information to help generate the outputs; however, it fails to capture temporal patterns across multiple time steps. In this paper, we propose using a set of filters to extract time-invariant temporal patterns, similar to transforming time series data into its “frequency domain”. Then we propose a novel attention mechanism to select relevant time series, and use its frequency domain information for multivariate forecasting. We apply the proposed model on several real-world tasks and achieve state-of-the-art performance in almost all of cases. Our source code is available at https://github.com/gantheory/TPA-LSTM.
A three‐factor, three‐by‐three‐by‐two‐level factorial designs were used for studying the effects of air pressure, sprayer orifice size and electrostatic charge of a spray gun on pH, oxidation‐reduction potential (ORP), electric conductivity and residual chlorine of electrolysed oxidizing (EO) waters with either low (9 mg L?1) or high concentration (88 mg L?1) of chlorine. Results indicated that a smaller orifice produced higher reduction in ORP and chlorine concentration than larger orifices. Electrostatic charge, in general, did not cause a significant reduction in chlorine concentration. High air pressure spray retained more chlorine and gave a higher ORP than low air pressure. EO water with high initial chlorine concentration achieved at least a 3–4 log10 CFU mL?1 reduction in Listeria monocytogenes populations when sprayed with the spray gun, while spraying with a commercial backpack sprayer or a poly‐tank sprayer eliminated Listeria population (9.4 log10 CFU mL?1 reductions) completely. These results demonstrated that although spraying reduced the chlorine in EO water by 20–97%, application of EO water through spraying has potential for reducing bacteria in food‐processing operations. 相似文献