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

Cecaj, Alket; Lippi, Marco; Mamei, Marco; Zambonelli, Franco

doi:10.3390/app10186580

Cited by 32 publications

(18 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The study in [51] combined Semi-Supervised Classification and Semi-Supervised Clustering machine learning methods for air pollutants prediction and showed how it can be used successfully for time-series prediction problem. The work in [52] compared statistical and deep learning methods in time-series forecasting. However, both statistical and deep learning methods (such as LSTM) are useful to be used in the time-series applications, a comparison between these methods can be investigated with respect to more than one consideration such as time-lag parameter selection.…”

Section: Mae Running Timementioning

confidence: 99%

Time-Lag Selection for Time-Series Forecasting Using Neural Network and Heuristic Algorithm

Surakhi

Zaidan²,

Fung³

et al. 2021

Electronics

View full text Add to dashboard Cite

The time-series forecasting is a vital area that motivates continuous investigate areas of intrigued for different applications. A critical step for the time-series forecasting is the right determination of the number of past observations (lags). This paper investigates the forecasting accuracy based on the selection of an appropriate time-lag value by applying a comparative study between three methods. These methods include a statistical approach using auto correlation function, a well-known machine learning technique namely Long Short-Term Memory (LSTM) along with a heuristic algorithm to optimize the choosing of time-lag value, and a parallel implementation of LSTM that dynamically choose the best prediction based on the optimal time-lag value. The methods were applied to an experimental data set, which consists of five meteorological parameters and aerosol particle number concentration. The performance metrics were: Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE) and R-squared. The investigation demonstrated that the proposed LSTM model with heuristic algorithm is the superior method in identifying the best time-lag value.

show abstract

Section: Mae Running Timementioning

confidence: 99%

Time-Lag Selection for Time-Series Forecasting Using Neural Network and Heuristic Algorithm

Surakhi

Zaidan²,

Fung³

et al. 2021

Electronics

View full text Add to dashboard Cite

show abstract

“…Nevertheless, these statistical approaches are now being overcome by more recent approaches based on deep learning architectures, which will be described in the next subsection. For a detailed experimental comparison between statistical and deep learning approaches for crowd mobility forecasting, the reader may also refer to recent experimental surveys [65,66].…”

Section: Statistical Approaches To Time-series Forecastingmentioning

confidence: 99%

Sensing and Forecasting Crowd Distribution in Smart Cities: Potentials and Approaches

Cecaj

Lippi

Mamei

et al. 2021

IoT

Self Cite

View full text Add to dashboard Cite

The possibility of sensing and predicting the movements of crowds in modern cities is of fundamental importance for improving urban planning, urban mobility, urban safety, and tourism activities. However, it also introduces several challenges at the level of sensing technologies and data analysis. The objective of this survey is to overview: (i) the many potential application areas of crowd sensing and prediction; (ii) the technologies that can be exploited to sense crowd along with their potentials and limitations; (iii) the data analysis techniques that can be effectively used to forecast crowd distribution. Finally, the article tries to identify open and promising research challenges.

show abstract

“…Ketika tujuan peramalan hanya sebatas untuk mengurangi nilai kesalahan, maka pendekatan ML akan lebih tepat digunakan. Sedangkan statistik memiliki keunggulan dalam memberikan hasil peramalan yang lebih tepat, namun memerlukan pengetahuan atas domain data dan teknik komputasi yang lebih besar untuk memilih parameter terbaiknya [16].…”

Section: Pendahuluanunclassified

Penerapan Ensemble Stacking untuk Peramalan Laba Bersih Bank Syariah Indonesia (BSI)

Syamsiah

Purwandani

2021

bits

View full text Add to dashboard Cite

Univariate data prediction has been done by many researchers with various methods used. The research was conducted using one method, several methods to combine several methods. This research uses several methods and simultaneously combines several methods. The method is by applying the Ensemble, namely Stacking. Meanwhile, the univariate data used is the Indonesian Sharia Bank Monthly Profit Data. This study aims to prove the accuracy of ensemble stacking prediction results by applying the SVM, Random Forest, Neural Network, and General Linear Model algorithms. Based on the results of the study, it was found that by applying Stacking the most accurate results were obtained for predicting univariate time series data (Indonesian Islamic Bank profits), where the RMSE generated was 0.534

show abstract

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

Cited by 32 publications

References 28 publications

Time-Lag Selection for Time-Series Forecasting Using Neural Network and Heuristic Algorithm

Time-Lag Selection for Time-Series Forecasting Using Neural Network and Heuristic Algorithm

Sensing and Forecasting Crowd Distribution in Smart Cities: Potentials and Approaches

Penerapan Ensemble Stacking untuk Peramalan Laba Bersih Bank Syariah Indonesia (BSI)

Contact Info

Product

Resources

About