2020
DOI: 10.1007/978-3-030-38081-6_8
|View full text |Cite
|
Sign up to set email alerts
|

A Neighborhood-Augmented LSTM Model for Taxi-Passenger Demand Prediction

Abstract: Taxi is a convenient means of transportation worldwide. Accurately predicting the taxi-demand is crucial for taxi-companies to effectively allocate their fleet to taxi-stands and reduce the waiting time for passengers thus increasing their overall satisfaction and customer retention. Nowadays precise information about taxi-rides is available and can be used to infer the taxi-passenger demand across different locations and time-points. In this paper, we propose an approach for predicting the pick-demand of a gi… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
4
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
3
2
1

Relationship

0
6

Authors

Journals

citations
Cited by 7 publications
(4 citation statements)
references
References 25 publications
0
4
0
Order By: Relevance
“…The advantage of LSTM is that it is suitable for time series forecasting because LSTM contains a special unit called a memory block in a hidden layer that repeats itself (Goyal A., Kumar R., Kulkarni S., 2016) . Memory blocks contain memory cells with links that store temporary network states in addition to special copying units called information flow control gates (Quy et al, 2020) . LSTM is able to overcome long-term dependencies on its input (Bandara et al, 2019) .…”
Section: Related Workmentioning
confidence: 99%
See 1 more Smart Citation
“…The advantage of LSTM is that it is suitable for time series forecasting because LSTM contains a special unit called a memory block in a hidden layer that repeats itself (Goyal A., Kumar R., Kulkarni S., 2016) . Memory blocks contain memory cells with links that store temporary network states in addition to special copying units called information flow control gates (Quy et al, 2020) . LSTM is able to overcome long-term dependencies on its input (Bandara et al, 2019) .…”
Section: Related Workmentioning
confidence: 99%
“…(Hsieh, 2021) . A model with one input layer is called a sequential model (Quy et al, 2020) . LSTM has one output layer and several hidden layers (Lee et al, 2018) .…”
Section: Proposed Long Short-term Memory Forecasting Architecturementioning
confidence: 99%
“…They established these two spatial relations using a graph CNN, whereas they mapped the temporal characteristics using an LSTM network. Quy and others [18] augmented an LSTM with demand knowledge from neighboring taxi stands, along with historical taxi-demand counts, to forecast the pickup demand for a given taxi stand. Guo [19] proposed a hybrid model, combining a CNN with a bidirectional LSTM and the attention mechanism in order to predict taxi demand.…”
Section: Literature Reviewmentioning
confidence: 99%
“…Recently, there has been much research investigating the correlation between taxi demands and related dependencies. However, taxi demand forecasting is still an open problem, which is mainly affected by several kinds of factors [4][5][6]:…”
Section: Introductionmentioning
confidence: 99%