Traffic Flow Forecast Through Time Series Analysis Based on Deep Learning

Abstract

Traffic congestion is a thorny issue to many large and medium-sized cities, posing a serious threat to sustainable urban development. Recently, intelligent traffic system (ITS) has emerged as an effective tool to mitigate urban congestion. The key to the ITS lies in the accurate forecast of traffic flow. However, the existing forecast methods of traffic flow cannot adapt to the stochasticity and sheer length of traffic flow time series. To solve the problem, this paper relies on deep learning (DL) to forecast traffic flow through time series analysis. The authors developed a traffic flow forecast model based on the long shortterm memory (LSTM) network. The proposed model was compared with two classic forecast models, namely, the autoregressive integrated moving average (ARIMA) model and the backpropagation neural network (BPNN) model, through long-term traffic flow forecast experiments, using an actual traffic flow time series from OpenITS. The experimental results show that the proposed LSTM network outperformed the classic models in prediction accuracy. Our research discloses the dynamic evolution law of traffic flow, and facilitates the decision-making of traffic management. INDEX TERMS Traffic flow forecast, time series analysis, deep learning (DL), long short-term memory (LSTM).

Smart Cities: Data-Driven Solutions to Understand Disruptive Problems in Transportation—The Lisbon Case Study

“…Zheng [25] used another LSTM model and compared it with the conventional machinelearning models such as ARIMA and BPNN (back-propagation neural network), and obtained substantially superior results.…”

“…Dimension Application [22] Traffic simulations based on spatially abstracted transportation networks using dependency models derived from real traffic data Identify correlations between the traffic intensity and movement speed on links of a spatially abstracted transportation network [23] Data-driven short-term data processing and LSTM-RNN Forecast urban road network traffic [24] Traffic flow combination forecasting method based on improved LSTM and ARIMA Forecast traffic flow [25] Traffic flow forecast through time series analysis based on deep learning Forecast traffic flow [26] Palm distribution application to analyze road accident risk assessment Identify correlations between traffic, road, and weather conditions in road accidents…”

“…When the traffic level was 5, the Delay column had the value "−1", and this value could not be used for analysis. To surpass this problem without impacting the column values, "−1" was treated like missing data and replaced with a value prediction using a Pearson correlation and linear regression [24,25]. Table 8 shows the Pearson correlation between all variables.…”

Online Bus Speed Prediction With Spatiotemporal Interaction: A Laplace Approximation-Based Bayesian Approach

“…A possible reason is that the ST model and the Type IV model account for structured temporal effects, which is no doubt sensitive to time changing; while the PL model and the Type I model do not account for structured temporal effects (See TABLE 1 for detail about four types of interaction). Aside from the proposed model, three benchmark models are also tested, i.e., autoregressive integrated moving average (ARIMA) model [69], CNN model [70], and the backpropagation neural network (BPNN) model [69]. The hyperparameters for the benchmark models are listed in TABLE 5.…”

A General Traffic Flow Prediction Approach Based on Spatial-Temporal Graph Attention

“…The time-series analysis model uses mathematical formulas to model past behavior, and then uses the obtained model to predict future results. ARIMA [7] is a classic statistical model in time-series analysis, which is widely used in traffic prediction [8]. References [9] and [10] ,extended the spatial domain to the ARIMA time series model to obtain the spatio-temporal autoregressive integrated moving average (STARIMA) models.…”