With the development of society and the continuous advancement of urbanization, motor vehicles have increased rapidly, which exacerbates the imbalance between parking supply and demand. Therefore, it is very important to excavate knowledge from historical parking data and forecast the parking volume in different time periods so as to optimize parking resource utilization and improve traffic conditions. This paper proposes a new hybrid model that stacks gated recurrent unit (GRU) and long-short term memory (LSTM). The proposed stacked GRU-LSTM model combines LSTM's advantage in prediction accuracy and GRU's advantage in prediction efficiency, and uses multi factors, including occupancy, weather conditions and holiday, as input to predict parking availability. When compared against other predictive models such as stacked simple RNN, stacked LSTM-RNN, and stacked LSTM-Bi-LSTM, our experimental results indicate that the stacked GRU-LSTM model has better performance for parking occupancy prediction as it not only improves prediction accuracy, but also reduces prediction time.
In this paper, a method for estimating the autoregressive parameters from a signal segment is proposed. The method is based on a deep neural network (DNN) in combination with the classical Levinson-Durbin recursion (LDR). The DNN acts as a pre-processor for the LDR and can be trained on different metrics commonly encountered in speech processing using a generalized analysis-by-synthesis (GABS) structure where the LDR acts as the encoder. Unlike end-to-end datadriven approaches, this structure ensures that the DNN is easy to train and initialize since the DNN only has to learn a simple mapping. The results confirm this and show that the proposed method produces an AR-spectrum that efficiently represents the speech spectrum in terms of the Itakura-Saito divergence, Kullback-Leibler divergence, log-spectral distortion, and speech distortion.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.