Traffic Flow Forecasting on Data-Scarce Environments Using ARIMA and LSTM Networks

Fernandes, Bruno; Silva, Fábio; Aláiz‐Moretón, Héctor; Nováis, Paulo; Analide, César; Neves, José

doi:10.1007/978-3-030-16181-1_26

Cited by 15 publications

(10 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the other hand, recent times come with very promising results in regard to the use of RNNs (Ma et al, 2015;Fernandes et al, 2019). As opposed to classical Artificial Neural Networks (ANNs), RNNs allow information to persist due to its recurrence and chain-like nature, i.e.…”

Section: Arima Models and Lstm Networkmentioning

confidence: 99%

“…Traffic forecasting is yet another domain where LSTMs have been applied successfully (Tian and Pan, 2015;Fu et al, 2016;Cui et al, 2018). Indeed, many studies have already engaged on comparing the performance and accuracy of ARIMA and LSTM models for traffic flow forecasting, with LSTMs outperforming ARIMA models (Ma et al, 2015;Fu et al, 2016;Zhao et al, 2017), even in the presence of data-scarce environments (Fernandes et al, 2019). In Fu et al (2016), the authors conceived a LSTM model over the PeMS dataset to predict short-term traffic flow, showing that LSTM had a slightly better performance when compared to ARIMA.…”

Section: Arima Models and Lstm Networkmentioning

confidence: 99%

“…Until recently, the main focus was on using statistical-based models such as the AutoRegressive Integrated Moving Average (ARIMA) or ARIMA with Explanatory Variable (ARIMAX) to forecast future points (Babu and Reddy, 2012;Cortez et al, 2004). However, the results produced by such models have now been superseded by those produced by deep learning ones, in particular by Recurrent Neural Networks (RNNs) (Fernandes et al, 2019;Fu et al, 2016;Zhao et al, 2017). The promise of RNNs is that the temporal dependence and contextual information in the input data can be learned and generalized to produce reliable forecasts.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Long Short-Term Memory Networks for Traffic Flow Forecasting: Exploring Input Variables, Time Frames and Multi-Step Approaches

Fernandes¹,

Silva²,

Aláiz‐Moretón³

et al. 2020

Informatica

Self Cite

View full text Add to dashboard Cite

Traffic flow forecasting is an acknowledged time series problem whose solutions have been essentially grounded on statistical-based models. Recent times came, however, with promising results regarding the use of Recurrent Neural Networks (RNNs), such as Long Short-Term Memory networks (LSTMs), to accurately address time series problems. Literature is, however, evasive in regard to several aspects of the conceived models and often exhibits misconceptions that may lead to important pitfalls. This study aims to conceive and find the best possible LSTM model for traffic flow forecasting while addressing several important aspects of such models such as the multitude of input features, the time frames used by the model and the employed approach for multi-step forecasting. To overcome the spatial problem of open source datasets, this study presents and describes a new dataset collected by the authors of this work. After several weeks of model fitting, Recursive Multi-Step Multi-Variate models were the ones showing better performance, strengthening the perception that LSTMs can be used to accurately forecast the traffic flow for several future timesteps.

show abstract

Section: Arima Models and Lstm Networkmentioning

confidence: 99%

Section: Arima Models and Lstm Networkmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Long Short-Term Memory Networks for Traffic Flow Forecasting: Exploring Input Variables, Time Frames and Multi-Step Approaches

Fernandes¹,

Silva²,

Aláiz‐Moretón³

et al. 2020

Informatica

Self Cite

View full text Add to dashboard Cite

show abstract

“…Some applications areas of RNN and its variants include for example music composition [55], handwriting recognition [56], speech synthesis [57], and video captioning [58], to name a few. LSTMs are often used for time-series problems such as predicting stock market price movement [59], weather [60], traffic flow [61], and passenger flow [62].…”

Section: Rnn and Its Variantsmentioning

confidence: 99%

Short-Term Forecasting of Land Use Change Using Recurrent Neural Network Models

Cao

Dragićević

2019

Sustainability

View full text Add to dashboard Cite

Land use change (LUC) is a dynamic process that significantly affects the environment, and various approaches have been proposed to analyze and model LUC for sustainable land use management and decision making. Recurrent neural network (RNN) models are part of deep learning (DL) approaches, which have the capability to capture spatial and temporal features from time-series data and sequential data. The main objective of this study was to examine variants of the RNN models by applying and comparing them when forecasting LUC in short time periods. Historical land use data for the City of Surrey, British Columbia, Canada were used to implement the several variants of the RNN models. The land use (LU) data for years 1996, 2001, 2006, and 2011 were used to train the DL models to enable the short-term forecast for the year 2016. For the 2011 to 2016 period, only 4.5% of the land use in the study area had changed. The results indicate that an overall accuracy of 86.9% was achieved, while actual changes in each LU type were forecasted with a relatively lower accuracy. However, only 25% of changed raster cells correctly forecasted the land use change. This research study demonstrates that RNN models provide a suite of valuable tools for short-term LUC forecast that can inform and complement the traditional long-term planning process; however, further additional geospatial data layers and considerations of driving factors of LUC need to be incorporated for model improvements.

show abstract

“…ARIMA is a time-series model which is one of the most popular methods used in infectious disease prediction, such as hemorrhagic fever, [ 4 ] Coronavirus disease 2019, [ 5 ] brucellosis, [ 6 ] hepatitis, [ 7 , 8 ] syphilis, [ 9 ] in uenza, [ 10 , 11 ] tuberculosis, [12,13] HIV, [ 14 ] as well as blood glucose concentrations and hypoglycemia, [ 15 ] hospital daily outpatient visits, [ 16 ] and so on. LSTM is a special case of Recurrent Neural Networks (RNN) which is in the increase of use in recent years in domains such as tra c ow prediction, [ 17 ] speech recognition [ 18 ] and as well as disease prediction. [ 14 , 19 , 20 ] Both ARIMA and LSTM are suitable for time series prediction and forecasting.…”

Section: Introductionmentioning

confidence: 99%

Comparison of ARIMA and LSTM for Prediction of Hemorrhagic Fever at Different Time Scales in China

Zhang

Chen

Meng

et al. 2021

Preprint

View full text Add to dashboard Cite

ObjectivesThis study intends to build and compare two kinds of forecasting models at different time scales for hemorrhagic fever incidence in China.MethodsARIMA and LSTM model were adopted to fit monthly, weekly and daily incidence of hemorrhagic fever in China from 2013 to 2018. The two models, combined and uncombined with rolling forecast, were used to predict the incidence in 2019 to identify its stability and availability. ResultsARIMA (2, 1, 1) (0, 1, 1)12, ARIMA (1, 1, 3) (1, 1, 1)52 and ARIMA (5, 0, 1) was selected as the best fitted ARIMA model for monthly, weekly and daily incidence series respectively. The model with 64 neurons and SGDM for monthly incidence, 8 neurons and Adam for weekly incidence, and 64 neurons and RMSprop for daily incidence were selected as the best fitted LSTM models. The values of root mean square error (RMSE), mean absolute error (MAE) and mean absolute percentage error (MAPE) of the models combined with rolling forecast in 2019 were lower than those of the direct forecast models for both ARIMA and LSTM. It was shown from the forecasting performance in 2019 that ARIMA was better than LSTM for monthly and weekly forecasting while the LSTM was better than ARIMA for daily forecasting in rolling models.ConclusionsBoth ARIMA and LSTM could be used to build a prediction model for the incidence of hemorrhagic fever meanwhile different models might be more suitable for the incidence prediction at different time scales.

show abstract

Traffic Flow Forecasting on Data-Scarce Environments Using ARIMA and LSTM Networks

Cited by 15 publications

References 8 publications

Long Short-Term Memory Networks for Traffic Flow Forecasting: Exploring Input Variables, Time Frames and Multi-Step Approaches

Long Short-Term Memory Networks for Traffic Flow Forecasting: Exploring Input Variables, Time Frames and Multi-Step Approaches

Short-Term Forecasting of Land Use Change Using Recurrent Neural Network Models

Comparison of ARIMA and LSTM for Prediction of Hemorrhagic Fever at Different Time Scales in China

Contact Info

Product

Resources

About