Next Article in Journal
Fluoride Risk Assessment from Consumption of Different Foods Commercialized in a European Region
Next Article in Special Issue
World-Models for Bitrate Streaming
Previous Article in Journal
Grousers Effect in Tracked Vehicle Multibody Dynamics with Deformable Terrain Contact Model
Previous Article in Special Issue
Can We Exploit Machine Learning to Predict Congestion over mmWave 5G Channels?
Article

Comparing Deep Learning and Statistical Methods in Forecasting Crowd Distribution from Aggregated Mobile Phone Data

1
Dipartimento di Scienze e Metodi dell’Ingegneria, University of Modena and Reggio Emilia, 42122 Reggio Emilia, Italy
2
Artificial Intelligence Research and Innovation Center (AIRI), University of Modena and Reggio Emilia, 41125 Modena, Italy
*
Author to whom correspondence should be addressed.
Appl. Sci. 2020, 10(18), 6580; https://doi.org/10.3390/app10186580
Received: 12 August 2020 / Revised: 10 September 2020 / Accepted: 16 September 2020 / Published: 21 September 2020
(This article belongs to the Special Issue AI in Mobile Networks)
Accurately forecasting how crowds of people are distributed in urban areas during daily activities is of key importance for the smart city vision and related applications. In this work we forecast the crowd density and distribution in an urban area by analyzing an aggregated mobile phone dataset. By comparing the forecasting performance of statistical and deep learning methods on the aggregated mobile data we show that each class of methods has its advantages and disadvantages depending on the forecasting scenario. However, for our time-series forecasting problem, deep learning methods are preferable when it comes to simplicity and immediacy of use, since they do not require a time-consuming model selection for each different cell. Deep learning approaches are also appropriate when aiming to reduce the maximum forecasting error. Statistical methods instead show their superiority in providing more precise forecasting results, but they require data domain knowledge and computationally expensive techniques in order to select the best parameters. View Full-Text
Keywords: forecasting; time series; crowd distribution; aggregated mobile phone data; deep neural networks forecasting; time series; crowd distribution; aggregated mobile phone data; deep neural networks
Show Figures

Figure 1

MDPI and ACS Style

Cecaj, A.; Lippi, M.; Mamei, M.; Zambonelli, F. Comparing Deep Learning and Statistical Methods in Forecasting Crowd Distribution from Aggregated Mobile Phone Data. Appl. Sci. 2020, 10, 6580. https://doi.org/10.3390/app10186580

AMA Style

Cecaj A, Lippi M, Mamei M, Zambonelli F. Comparing Deep Learning and Statistical Methods in Forecasting Crowd Distribution from Aggregated Mobile Phone Data. Applied Sciences. 2020; 10(18):6580. https://doi.org/10.3390/app10186580

Chicago/Turabian Style

Cecaj, Alket, Marco Lippi, Marco Mamei, and Franco Zambonelli. 2020. "Comparing Deep Learning and Statistical Methods in Forecasting Crowd Distribution from Aggregated Mobile Phone Data" Applied Sciences 10, no. 18: 6580. https://doi.org/10.3390/app10186580

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop