Spatiotemporal Data Mining: A Survey on Challenges and Open Problems

no code implementations • 31 Mar 2021 • Ali Hamdi, Khaled Shaban, Abdelkarim Erradi, Amr Mohamed, Shakila Khan Rumi, Flora Salim

Specifically, we investigate the challenging issues in regards to spatiotemporal relationships, interdisciplinarity, discretisation, and data characteristics.

Clustering Epidemiology +1

Spatiotemporal Tensor Completion for Improved Urban Traffic Imputation

no code implementations • 12 Mar 2021 • Ahmed Ben Said, Abdelkarim Erradi

To recover the missing data, we propose an enhanced CANDECOMP/PARAFAC (CP) completion approach that considers the urban and temporal aspects of the traffic.

Imputation Management +1

Predicting COVID-19 cases using Bidirectional LSTM on multivariate time series

no code implementations • 10 Sep 2020 • Ahmed Ben Said, Abdelkarim Erradi, Hussein Aly, Abdelmonem Mohamed

Conclusion: Using data of multiple countries in addition to lockdown measures improve accuracy of the forecast of daily cumulative COVID-19 cases.

Clustering Time Series +1

Deep-Gap: A deep learning framework for forecasting crowdsourcing supply-demand gap based on imaging time series and residual learning

no code implementations • 2 Nov 2019 • Ahmed Ben Said, Abdelkarim Erradi

This allows anticipating the supply-demand gap and redirecting crowdsourced service providers towards target areas.

Time Series Time Series Analysis

A Deep Learning Spatiotemporal Prediction Framework for Mobile Crowdsourced Services

no code implementations • 4 Sep 2018 • Ahmed Ben Said, Abdelkarim Erradi, Azadeh Ghari Neiat, Athman Bouguettaya

This papers presents a deep learning-based framework to predict crowdsourced service availability spatially and temporally.

General Classification Time Series +1