Redirigiendo al acceso original de articulo en 19 segundos...
Inicio  /  Applied Sciences  /  Vol: 10 Par: 18 (2020)  /  Artículo
ARTÍCULO
TITULO

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

Alket Cecaj    
Marco Lippi    
Marco Mamei and Franco Zambonelli    

Resumen

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.

 Artículos similares

       
 
I.A. Lozhkin,M.E. Dunaev,K.S. Zaytsev,A.A. Garmash     Pág. 109 - 117
The purpose of this work is to study the effectiveness of augmentation methods of image sets when they are insufficient in training sample of neural networks for solving semantic segmentation problems. For this purpose, the main groups of augmentation me... ver más

 
William Villegas-Ch and Jaime Govea    
This article addresses the need for early emergency detection and safety monitoring in public spaces using deep learning techniques. The problem of discerning relevant sound events in urban environments is identified, which is essential to respond quickl... ver más

 
Md Ishtyaq Mahmud, Muntasir Mamun and Ahmed Abdelgawad    
Creating machines that behave and work in a way similar to humans is the objective of artificial intelligence (AI). In addition to pattern recognition, planning, and problem-solving, computer activities with artificial intelligence include other activiti... ver más
Revista: Algorithms

 
Querriel Arvy Mendoza, Lester Pordesimo, Mitchell Neilsen, Paul Armstrong, James Campbell and Princess Tiffany Mendoza    
In this study, a basic insect detection system consisting of a manual-focus camera, a Jetson Nano?a low-cost, low-power single-board computer, and a trained deep learning model was developed. The model was validated through a live visual feed. Detecting,... ver más
Revista: AI

 
Victor Bacu, Constantin Nandra, Adrian Sabou, Teodor Stefanut and Dorian Gorgan    
Near-Earth Asteroids represent potential threats to human life because their trajectories may bring them in the proximity of the Earth. Monitoring these objects could help predict future impact events, but such efforts are hindered by the large numbers o... ver más
Revista: Aerospace