ABSTRACT
In short-term passenger flow forecasting, thanks to big data analysis, we can obtain a large number of influencing factors describing the change of station passenger flow. Although this information provides a good basis for passenger flow forecasting, statistical use of passenger flow forecasting in the past are not accurate and stable because of the characteristics of timing, space and trend of passenger flow forecasting. In building an automated passenger flow forecasting system, accuracy and stability are the key points we need to pay attention to. this paper use the optimal parameter passenger flow prediction based on ga-lstm model. After selecting the optimal time step and the number of hidden units by using genetic algorithm (GA), LSTM is used for prediction. In the multi station boarding and alighting number prediction experiment on the real subway data provided by Hangzhou, It is proved that ga-lstm is better than the non optimized RNN model in prediction accuracy.
- Jin J, Yang D M. Analysis of Bus Diversity Fare Vote System and Passenger Flow Effect[J]. Journal of Transportation Systems Engineering & Information Technology, 2010, 10(3):115-122.Google Scholar
- Zheng Z, Chen W, Yue H, A novel short-term traffic forecast model based on travel distance estimation and ARIMA[C] Control & Decision Conference. IEEE, 2016.Google Scholar
- Suhartono. Time Series Forecasting by using Seasonal Autoregressive Integrated Moving Average: Subset, Multiplicative or Additive Model[J]. Journal of Mathematics & Statistics, 2011, 7(1):20-27.Google ScholarCross Ref
- MR Costa-Jussà, Allauzen A, Barrault L, Introduction to the special issue on deep learning approaches for machine translation[J]. Computer Speech & Language, 2017, 46(nov.):367-373.Google ScholarDigital Library
- ME Sánchez-Gutiérrez, Albornoz E M, Martinez-Licona F, Deep Learning for Emotional Speech Recognition[C] 6th Mexican Conference on Pattern Recognition MCPR2014. Springer International Publishing, 2014.Google Scholar
- Xing, Junhang, Li, Diagnosing deep learning models for high accuracy age estimation from a single image[J]. Pattern Recognition the Journal of the Pattern Recognition Society, 2017.Google ScholarDigital Library
- Koesdwiady, A., Soua, R., Karray, F. Improving Traffic Flow Prediction With Weather Information in Connected Cars: A Deep Learning Approach[J]. IEEE Transactions on Vehicular Technology, 2016, 65, (12), pp. 9508-9517.Google ScholarCross Ref
- Huang W, Song G, Hong H, Deep Architecture for Traffic Flow Prediction: Deep Belief etworks With Multitask Learning[J]. IEEE Transactions on Intelligent Transportation Systems, 2014, 15(5):2191-2201.Google ScholarCross Ref
- Yu D, Liu Y, Yu X. A Data Grouping CNN Algorithm for Short-Term Traffic Flow Forecasting[M] Web Technologies and Applications. Springer International Publishing, 2016:92-103.Google Scholar
- Zheng Y, Liu Q, Chen E, Exploiting multi-channels deep convolutional neural networks for multivariate time series classification[J]. Frontiers of Computer Science, 2016, 10(1):1-17Google ScholarDigital Library
- Zheng Z, Chen W, Wu X, LSTM network: a deep learning approach for short-term traffic forecast[J]. Iet Intelligent Transport Systems, 2017, 11(2):68-75.Google ScholarCross Ref
- H. Shao and B. Soong, "Traffic flow prediction with Long Short-Term Memory Networks (LSTMs),"2016 IEEE Region 10 Conference (TENCON), 2016, pp. 2986-2989, doi: 10.1109/TENCON.2016.7848593.Google Scholar
- Wu Y, Tan H . Short-term traffic flow forecasting with spatial-temporal correlation in a hybrid deep learning framework[J]. two thousand and sixteenGoogle Scholar
- Graves A . Long Short-Term Memory[J]. Springer Berlin Heidelberg, 2012.Google ScholarCross Ref
- Qing X, Niu Y . Hourly day-ahead solar irradiance prediction using weather forecasts by LSTM[J]. Energy, 2018, 148(APR.1):461-468.Google ScholarCross Ref
- Hüsken, Michael, Stagge, Recurrent neural networks for time series classification.[J]. Neurocomputing, 2003.Google Scholar
- Goldberg D E, Samtani M P . Engineering Optimization via Genetic Algorithm. one thousand nine hundred and eighty-sixGoogle Scholar
Recommendations
An LSTM Approach for Predicting the Short-time Passenger Flow of Urban Bus
AIEE '21: Proceedings of the 2021 2nd International Conference on Artificial Intelligence in Electronics EngineeringThe advantages of LSTM as a deep learning neural network algorithm in time series prediction of passenger flow have gradually emerged. In addition to general passenger flow data that can be used for prediction, other context information can improve ...
Fuzzy temporal logic based railway passenger flow forecast model
Passenger flow forecast is of essential importance to the organization of railway transportation and is one of the most important basics for the decision-making on transportation pattern and train operation planning. Passenger flow of high-speed railway ...
Incorporating CNN-LSTM and SVM with wavelet transform methods for tourist passenger flow prediction
AbstractEffective management of urban rail transit systems increasingly centers on short-term passenger flow prediction which is a key factor in operational scheduling decisions. The critical need to use existing infrastructure efficiently and avoid ...
Comments