Towards investigation of iterative strategy for data mining of short-term traffic flow with Recurrent Neural Networks

Fandango, Armando; Wiegand, R. Paul

doi:10.1145/3206098.3206112

Cited by 10 publications

(1 citation statement)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To this end, Support Vector Machine (SVM) is proposed to reduce the stepwise prediction errors where its hyper-parameters are tuned for multi-step prediction [27]. More recently, DL models are forged to fit the recursive approach for multi-step prediction, and a study exploits RNN to predict flow patterns of road traffic [28]. Similarly, LSTM is recursively used to improve the detection of abnormal diagnostic signals from electronic health records [29].…”

Section: B Recursive Approach For Multi-step Predictionmentioning

confidence: 99%

Deep Mobile Path Prediction With Shift-and-Join and Carry-Ahead

Yang

Raza

Kim

et al. 2023

IEEE Trans. Cogn. Commun. Netw.

View full text Add to dashboard Cite

Importance of user mobility has rapidly increased in 5G due to reduced cell sizes, management of Multi-access Edge Computing (MEC), and ultra-low latency services. Reactive nature of existing management systems is a bottleneck, and it can be solved by building proactive systems that exploit temporal characteristics of time-series mobility data to predict long-term user movement (i.e., path). However, user mobile path prediction with useable accuracy is a challenging task, particularly for lengthy target trajectories. This paper adopts general approaches to propose two models for predicting mobile path with high accuracy.Step Forward Iteration (SFI) model is based on recursive approach, whereas Encoder-Decoder (ED) model follows multi-output approach, and both the models use Long-Short Term Memory (LSTM) as the learning unit. Training and testing of these models is done on mobility datasets from the wireless network of Pangyo ICT Research Center, Korea and one of the Korean mobile operators. The experiment results show viability of the proposed models for leveraging mobile network management, as they outperform state-of-the-art GRU with attention (GRU-ATTN) and Transformer Network (TN) models. The highest prediction accuracies achieved for 3, 5, and 7 steps of target sequences (i.e., predicted mobile path) in the campus dataset are 96%, 90%, and 87%, respectively.

show abstract

Section: B Recursive Approach For Multi-step Predictionmentioning

confidence: 99%