CEEMDAN-IPSO-LSTM: A Novel Model for Short-Term Passenger Flow Prediction in Urban Rail Transit Systems.

Urban rail transit (URT) is a key mode of public transport, which serves for greatest user demand. Short-term passenger flow prediction aims to improve management validity and avoid extravagance of public transport resources. In order to anticipate passenger flow for URT, managing nonlinearity, correlation, and periodicity of data series in a single model is difficult. This paper offers a short-term passenger flow prediction combination model based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and long-short term memory neural network (LSTM) in order to more accurately anticipate the short-period passenger flow of URT. In the meantime, the hyperparameters of LSTM were calculated using the improved particle swarm optimization (IPSO). First, CEEMDAN-IPSO-LSTM model performed the CEEMDAN decomposition of passenger flow data and obtained uncoupled intrinsic mode functions and a residual sequence after removing noisy data. Second, we built a CEEMDAN-IPSO-LSTM passenger flow prediction model for each decomposed component and extracted prediction values. Third, the experimental results showed that compared with the single LSTM model, CEEMDAN-IPSO-LSTM model reduced by 40 persons/35 persons, 44 persons/35 persons, 37 persons/31 persons, and 46.89%/35.1% in SD, RMSE, MAE, and MAPE, and increase by 2.32%/3.63% and 2.19%/1.67% in R and R2, respectively. This model can reduce the risks of public health security due to excessive crowding of passengers (especially in the period of COVID-19), as well as reduce the negative impact on the environment through the optimization of traffic flows, and develop low-carbon transportation.

What to Forecast When Forecasting New Covid-19 Cases? Jordan and the United Arab Emirates as Case Studies

Covid-19 has exerted tremendous pressure on countries’ resources, especially the health sector. Thus, it was important for governments to predict the number of new covid-19 cases to face this sudden epidemic. Deep learning techniques have shown success in predicting new covid-19 cases. Researchers have used long-short term memory (LSTM) networks that consider the previous covid-19 numbers to predict new ones. In this work, we use LSTM networks to predict new covid-19 cases in Jordan and the United Arab Emirates (UAE) for six months. The populations of both countries are almost the same;however, they had different arrangements to deal with the epidemic. The UAE was a world leader in terms of the number of covid-19 tests per capita. Thus, we try to find if incorporating covid-19 tests in predicting the LSTM networks would improve the prediction accuracy. Building bi-variate LSTM models that consider the number of tests did not improve uni-variate LSTM models that only consider previous covid-19 cases. However, using a uni-variate LSTM model to predict the ratio of covid-19 cases to the number of covid-19 tests have shown superior results in the case of Jordan. This ratio can be used to forecast the number of new covid-19 cases by multiplying this ratio by the number of conducted tests. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

A Comparison: Prediction of Death and Infected COVID-19 Cases in Indonesia Using Time Series Smoothing and LSTM Neural Network.

COVID-19 is a virus causing pneumonia, also known as Corona Virus Disease. The first outbreak was found in Wuhan, China, in the province of Hubei on December 2019. The objective of this paper is to predict the death and infected COVID-19 in Indonesia using Savitzky Golay Smoothing and Long Short Term Memory Neural Network model (LSTM-NN). The dataset is obtained from Humanitarian Data Exchange (HDX), containing daily information on death and infected due to COVID-19. In Indonesia, the total data collected ranges from 2 March 2020 and by 26 July 2020, with a total of 147 records. The results of these two models are compared to determine the best fitted model. The curve of LSTM-NN shows an increase in death and infected cases and the Time Series also increases, however the smoothing shows a tendency to decrease. In conclusion, LSTM-NN prediction produce better result than the Savitzky Golay Smoothing. The LSTM-NN prediction shows a distinct rise and align with the actual Time Series data.