Data Science Institute

Most Recent
Most Downloaded

Hybrid variational autoencoder for time series forecasting

Cai, B Yang, S Gao, L Xiang, Y

Variational autoencoders (VAE) are powerful generative models that learn the latent representations of input data as random variables. Recent studies show that VAE can flexibly learn the complex te...

Continue Reading
Assessing the role of global food commodity prices in achieving the 2030 agenda for SDGs.

Shen, Y Chen, Y Shi, X An, Y Yang, M Qi, Y

Food plays a vital role in human sustenance and well-being, and the fluctuations in its price exert a significant impact on the attainment of the Sustainable Development Goals (SDGs) from social, e...

Continue Reading
A Bi-Level Optimization Model for Inter-Provincial Energy Consumption Transfer Tax in China

Zeng, L Zhang, W Yang, M

The serious energy crisis and environmental problems resulting from fossil energy excessive consumption have caused severe challenges to the control of energy consumption and intensity (dual contro...

Continue Reading
Are People with Cyber Security Training Worse at Checking Phishing Email Addresses? Testing the Automaticity of Verifying the Sender’s Address

Conway, D Butavicius, M Yu, K Chen, F

Continue Reading
Incident duration prediction using a bi-level machine learning framework with outlier removal and intra-extra joint optimisation

Grigorev, A Mihaita, A-S Lee, S Chen, F

Continue Reading
Using machine learning and deep learning for traffic congestion prediction: A review

Mihaita, AS Li, Z Singh, H Sharma, N Tuo, M Ou, Y

Continue Reading
Metro Ridership Forecasting using Inter-Station-Aware Transformer Networks

Saleh, K Mihaita, A-S Ou, Y

Continue Reading
Traffic Accident Risk Forecasting using Contextual Vision Transformers with Static Map Generation and Coarse-Fine-Coarse Transformers

Grigorev, A Saleh, K Mihaita, A-S

Continue Reading
Automatic Accident Detection, Segmentation and Duration Prediction Using Machine Learning

Grigorev, A Mihăiţă, A-S Saleh, K Chen, F

Continue Reading
Training Physics- Informed Neural Networks via Multi-Task Optimization for Traffic Density Prediction

Wang, B Qin, AK Shafiei, S Dia, H Mihaita, A-S Grzybowska, H

Physics-informed neural networks (PINN s) are a newly emerging research frontier in machine learning, which incorporate certain physical laws that govern a given data set, e.g., those described by ...

Continue Reading