Predicting vacant parking space availability zone-wisely: a densely connected ConvLSTM method

Feng, Yajing; Tang, Zhenzhou; Xu, Ying-Ying; Krishnamoorthy, Sujatha; Hu, Qian

doi:10.1109/vppc53923.2021.9699140

Cited by 6 publications

(10 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Two series of experiments, direct single-step prediction and iterative multi-step prediction, are conducted on 8 parking lots in Santa Monica. It should be noted that, unlike our previous work [27,28], the distance between the parking lot St9 and the other 8 parking lots is far away, which will affect the extraction of spatial features, thus affecting the prediction results. Therefore, in this paper, St1-St8 are used to predict the number of VPSs.…”

Section: E Results and Analysismentioning

confidence: 83%

“…Moreover, with the increase of the prediction time step, the prediction advantage of the ST-GBGRU model is greater. Specifically, compared with the ConvLSTM-DCN model in [27], the RMSE of dConvLSTM-DCN framework in 5-/15-/30-/45-/60-min predictions are reduced by 0.77, 0.58, 2.81 and 2.59 and 6.42, respectively.…”

Section: E Results and Analysismentioning

confidence: 99%

“…In our previous work [27,28], we have fully analyzed the temporal and spatial correlation of parking lot. In view of this, the specific analysis is not carried out in this paper, and we simply show the results of the spatiotemporal analysis.…”

Section: A Data Description and Preprocessingmentioning

confidence: 99%

“…The ConvLSTM-DCN model [27] and the GCN+GRU model [37] (i.e. stacked GCN and GRU models) are used as baseline models to evaluate the performance of the ST-GBGRU model.…”

Section: ) Experimental Setupmentioning

confidence: 99%

“…The ratio of training set and test set is 4:1. The settings of the ConvLSTM-DCN model hyperparameters can be found in [27]. The hyperparameter settings for the GCN+GRU model are the same as that of the ST-GBGRU model.…”

Section: ) Experimental Setupmentioning

confidence: 99%

See 4 more Smart Citations

Predicting vacant parking space availability zone-wisely: a hybrid deep learning approach

Feng

et al. 2022

Complex Intell. Syst.

Self Cite

View full text Add to dashboard Cite

Precise prediction on vacant parking space (VPS) information plays a vital role in intelligent transportation systems for it helps drivers to find the parking space quickly to reduce unnecessary waste of time and excessive environmental pollution. By analyzing the historical zone-wise VPS data, we find that for the number of VPSs, there is not only a solid temporal correlation within each parking lot, but also an obvious spatial correlation among different parking lots. Given this, this paper proposes a hybrid deep learning framework, known as the dConvLSTM-DCN (dual Convolutional Long Short-Term Memory with Dense Convolutional Network), to make short-term (within 30 min) and long-term (over 30 min) predictions on the VPS availability zone-wisely. Specifically, the temporal correlations of different time scales, namely the 5-min and daily-wise temporal correlations of each parking lot, and the spatial correlations among different parking lots can be effectively captured by the two parallel ConvLSTM components, and meanwhile, the dense convolutional network is leveraged to further improve the propagation and reuse of features in the prediction process. Besides, a two-layer linear network is used to extract the meta-info features to promote the prediction accuracy. For long-term predictions, two methods, namely the direct and iterative prediction methods, are developed. The performance of the prediction model is extensively evaluated with practical data collected from nine public parking lots in Santa Monica. The results show that the dConvLSTM-DCN framework can achieve considerably high accuracy in both short-term and long-term predictions.

show abstract

Section: E Results and Analysismentioning

confidence: 83%

Section: E Results and Analysismentioning

confidence: 99%

Section: A Data Description and Preprocessingmentioning

confidence: 99%

“…The ConvLSTM-DCN model [27] and the GCN+GRU model [37] (i.e. stacked GCN and GRU models) are used as baseline models to evaluate the performance of the ST-GBGRU model.…”

Section: ) Experimental Setupmentioning

confidence: 99%

Section: ) Experimental Setupmentioning

confidence: 99%

See 3 more Smart Citations

Predicting vacant parking space availability zone-wisely: a hybrid deep learning approach

Feng

et al. 2022

Complex Intell. Syst.

Self Cite

View full text Add to dashboard Cite

show abstract

A review of research on urban parking prediction

Ma,

Huang,

2024

Journal of Traffic and Transportation Engineering (English Edit

View full text Add to dashboard Cite

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

Ye,

Kuang,

et al. 2023

IET Intelligent Trans Sys

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

Predicting vacant parking space availability zone-wisely: a densely connected ConvLSTM method

Cited by 6 publications

References 15 publications

Predicting vacant parking space availability zone-wisely: a hybrid deep learning approach

Predicting vacant parking space availability zone-wisely: a hybrid deep learning approach

A review of research on urban parking prediction

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

Contact Info

Product

Resources

About