BUS ROUTE DEMAND PREDICTION WITH DEEP LEARNING

Stevanus Alditian Lai, Yonathan Purbo Santosa

Abstract


bus companies currently have several obstacles in providing their fleets from one city to another because of the highly dynamic demand from passengers, bus companies must be able to analyze which routes will have a lot of demand so that bus companies can provide more fleets on the routes that will have high demand. Deep learning method is relatively new for bus company to predict the bus route demand, this study is try to create and implement LSTM Autoencoder-Bi-LSTM Hybrid Models and Bi-LSTM  to forecast bus route demand to support the decision making process in order to optimize bus fleet deployment each route. The results shows that LSTM Autoencoder-Bi-LSTM Hybrid Models and Bi-LSTM models doesn't differ very much.


Keywords


Autoencoders, deep learning; LSTM; Bi-LSTM; Timeseries

Full Text:

PDF

References


S. A. Krishnaswamy, M. Paul, and Srivatsa Krishnaswamy, “A Comparative Study and Analysis of Time

Series Forecasting Techniques | Enhanced Reader,” 2020. Available:

https://www.researchgate.net/publication/337244936_Comparative_Study_on_Time_Series_Forecasting_M

odels.

K. Yang and C. Shahabi, “A pca-based kernel for kernel pca on multivariate time series,” Proc. ICDM 2005

Work. …, no. June, 2005, [Online]. Available: http://w2.math.bme.hu/kanya/astor/tdm05.pdf.

K. Nazmoon, T. Tahmid, A. Rafi, and M. Ehsanul, “Forecasting COVID-19 cases: A com-parative analysis

between recurrent and convolutional neural networks,” no. January, 2020. Available:

https://www.researchgate.net/publication/350978557_Forecasting_COVID-

_cases_A_comparative_analysis_between_recurrent_and_convolutional_neural_networks.

J. G. Taylor, “Univariate and Multivariate Time Series Predictions,” no. January, pp. 11–22, 2002, doi:

1007/978-1-4471-0151-2_2. Available: https://www.sciencegate.app/app/document/download/10.1007/978-1-

-0151-2_2

I. Sülo, Ş. R. Keskin, G. Doǧan, and T. Brown, “Energy Efficient Smart Buildings: LSTM Neural Networks

for Time Series Prediction,” Proc. - 2019 Int. Conf. Deep Learn. Mach. Learn. Emerg. Appl. Deep. 2019, pp. 18–

, 2019, doi: 10.1109/Deep-ML.2019.00012. Available: https://ieeexplore.ieee.org/document/8876919.

Z. Che, S. Purushotham, K. Cho, D. Sontag, and Y. Liu, “Recurrent Neural Networks for Multivariate Time

Series with Missing Values,” Sci. Rep., vol. 8, no. 1, Dec. 2018, doi: 10.1038/s41598-018-24271-9.

K. Ouyang, Y. Hou, S. Zhou, and Y. Zhang, “Convolutional neural network with an elastic matching

mechanism for time series classification,” Algorithms, vol. 14, no. 7, 2021, doi: 10.3390/a14070192. Available:

https://mdpi-res.com/d_attachment/algorithms/algorithms-14-00192/article_deploy/algorithms-14-00192.pdf

Y. Wen, P. Lin, and X. Nie, “Research of stock price prediction based on PCA-LSTM model,” IOP Conf. Ser.

Mater. Sci. Eng., vol. 790, no. 1, 2020, doi: 10.1088/1757-899X/790/1/012109. Available:

https://www.researchgate.net/publication/340490809_Research_of_Stock_Price_Prediction_Based_on_PC

A-LSTM_Model

Y. Yuan et al., “Bus dynamic travel time prediction: Using a deep feature extraction framework based on

rnn and dnn,” Electron., vol. 9, no. 11, pp. 1–20, 2020, doi: 10.3390/electronics9111876. Available:

https://www.mdpi.com/2079-9292/9/11/1876

L. Badal and S. Franzén, “A Comparative Analysis of RNN and SVM Electricity Price Forecasting in Energy

Management Systems,” DEGREE Proj. Comput. Eng., 2019. Avail-able: http://kth.diva-

portal.org/smash/record.jsf?pid=diva2%3A1353342&dswid=-602




DOI: https://doi.org/10.24167/proxies.v4i2.12439

Copyright (c) 2024 Proxies : Jurnal Informatika



View My Stats