Improving Parking Occupancy Prediction in Poor Data Conditions Through Customization and Learning to Learn

Qu, Haohao; Liu, Sheng; Guo, Zihan; You, Linlin; Li, Jun

doi:10.1007/978-3-031-10983-6_13

Cited by 5 publications

(2 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…LSTM is an optimized recurrent neural network (RNN), which can cope with the correlation within time series in both short and long term [32]. LSTM generally defines a recurrent function F L and calculates h t for current time t , as Equation (10).…”

Section: Encoder Modulementioning

confidence: 99%

“…In the current literature, there are two types of methods to extract the change features of parking occupancy to improve the prediction accuracy: 1) data augmentation by generating fake samples that look like original data, introducing extra heterogeneous data, or decomposing patterns [7][8][9][10]; 2) structure optimization by using advanced machine learning or deep learning methods [11,12]. However, these methods still suffer from two major shortages.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A parking occupancy prediction method incorporating time series decomposition and temporal pattern attention mechanism

Ye,

Kuang,

et al. 2023

IET Intelligent Trans Sys

Self Cite

View full text Add to dashboard Cite

Parking occupancy prediction is an important reference for travel decisions and parking management. However, due to various related factors, such as commuting or traffic accidents, parking occupancy has complex change features that are difficult to model accurately, thus making it difficult for parking occupancy to be accurately predicted. Moreover, how to give appropriate weights to these changing features in prediction becomes a new challenge in the era of machine learning. To tackle these challenges, a parking occupancy prediction method called time series decomposition–long and short‐term memory neural network (LSTM)–temporal pattern attention mechanism, which consists of three modules, namely 1) time series decomposition: modelling parking occupancy changes by extracting features such as trend, period, and effect; 2) encoder: extracting temporal correlations of feature sequences with LSTM; 3) temporal pattern attention mechanism: assigning attention to different features, are proposed. The evaluation results of 30 parking lots in Guangzhou city show that the proposed model 1) improves accuracy over the baseline model LSTM by 9.14% on average; 2) performs outstanding in four prediction time intervals and six types of parking lots, proving its validity and generality; 3) demonstrates its rationality and interpretability through ablation experiments and Shapley additive explanation.

show abstract

Section: Encoder Modulementioning

confidence: 99%