DeepVM: RNN-Based Vehicle Mobility Prediction to Support Intelligent Vehicle Applications

Liu, Wei; Shoji, Yozo

doi:10.1109/tii.2019.2936507

Cited by 47 publications

(5 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The employed hybrid architecture that combines a convolutional neural network (CNN) and a recurrent neural network (RNN) makes use of disaggregated historical grid occupation values, which are available for each individual vehicle; the resulting scheme improves the quality of vehicle mobility prediction, especially for those vehicles that have a strong individual mobility preference. In [3], the same authors consider a similar scenario to address individual mobility prediction to support intelligent vehicle applications; they propose a deep RNN-based algorithm whose results match the theoretical analysis and improve state-of-the-art previous results. In [5], a deep RNN making use of a long short-term memory (LSTM) architecture is proposed to predict individual vehicle mobility on a grid, based on individual sensor data; the prediction step is followed by a vehicle recruiting algorithm to optimize crowdsensing; the results improve the quantity of collected sensing data versus existing algorithms.…”

Section: State-of-the-art Literature Reviewmentioning

confidence: 60%

“…and smart vehicle applications (e.g., transportation systems, communications, etc.) [1][2][3][4][5][6].…”

Section: Introductionmentioning

confidence: 99%

“…A set of predictors based on a GNN according to (3), where several parameters can be adjusted. First, different number of characteristics W, whether the one-hot representation of the node id has been used (using the Id suffix in the model name) and whether the number of time steps is included in the feature vector (using the T suffix in the model name).…”

mentioning

confidence: 99%

See 2 more Smart Citations

Predicting the Aggregate Mobility of a Vehicle Fleet within a City Graph

Sánchez-Rada,

Vila-Rodríguez,

Montes

et al. 2024

Algorithms

View full text Add to dashboard Cite

Predicting vehicle mobility is crucial in domains such as ride-hailing, where the balance between offer and demand is paramount. Since city road networks can be easily represented as graphs, recent works have exploited graph neural networks (GNNs) to produce more accurate predictions on real traffic data. However, a better understanding of the characteristics and limitations of this approach is needed. In this work, we compare several GNN aggregated mobility prediction schemes to a selection of other approaches in a very restricted and controlled simulation scenario. The city graph employed represents roads as directed edges and road intersections as nodes. Individual vehicle mobility is modeled as transitions between nodes in the graph. A time series of aggregated mobility is computed by counting vehicles in each node at any given time. Three main approaches are employed to construct the aggregated mobility predictors. First, the behavior of the moving individuals is assumed to follow a Markov chain (MC) model whose transition matrix is inferred via a least squares estimation procedure; the recurrent application of this MC provides the aggregated mobility prediction values. Second, a multilayer perceptron (MLP) is trained so that—given the node occupation at a given time—it can recursively provide predictions for the next values of the time series. Third, we train a GNN (according to the city graph) with the time series data via a supervised learning formulation that computes—through an embedding construction for each node in the graph—the aggregated mobility predictions. Some mobility patterns are simulated in the city to generate different time series for testing purposes. The proposed schemes are comparatively assessed compared to different baseline prediction procedures. The comparison illustrates several limitations of the GNN approaches in the selected scenario and uncovers future lines of investigation.

show abstract

Section: State-of-the-art Literature Reviewmentioning

confidence: 60%

“…and smart vehicle applications (e.g., transportation systems, communications, etc.) [1][2][3][4][5][6].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Predicting the Aggregate Mobility of a Vehicle Fleet within a City Graph

Sánchez-Rada,

Vila-Rodríguez,

Montes

et al. 2024

Algorithms

View full text Add to dashboard Cite

show abstract

“…The KNN technique is used to predict short-term traffic flow and describes the parameters that affect the port's short-term traffic flow as a state vector [31]. To predict future vehicle mobility for tens of minutes, RNN based technique is used [32]. A theoretical analysis is performed to quantify the predictability of motion.…”

Section: Related Workmentioning

confidence: 99%

Internet of Intelligent Vehicles (IoIV): An Intelligent VANET Based Computing via Predictive Modeling

2023

View full text Add to dashboard Cite

With the significant research and advancements in technologies, arose new applications such as autonomous driving and augmented/virtual reality. These applications required massive computational resources for the execution of various tasks. Utilizing vehicles resources in a distributed manner and collectively with the help of volunteer computing for various computational tasks is an emerging research area. The appropriate and intelligent decision in selecting a volunteer vehicle is crucial in this opportunistic network where information is exchanged between vehicles. In this paper, we propose Intelligent Volunteer Computing-based VANETs architecture to fulfill the computational requirements of vehicles applications intelligently. We propose selection criteria to select volunteers' vehicles capable of the execution of the computationally intensive task. In this study to rightly identify the volunteer vehicle for task execution, we use a machine learning approach that predicts the capability of certain vehicles in completing the task. Extensive experimentation is conducted for the prediction of the computing capability of optimal volunteer vehicles. We used nine different regression techniques on publicly available datasets. The results show these techniques can efficiently predict the capability of volunteers. By comparing the regression techniques, the results indicate that the ridge regression and support vector regression can significantly reduce the mean square error, relative absolute error, and root mean square errors. Simulations are conducted to compare the proposed scheme with existing one.

show abstract

“…With the development of deep learning, the use of the recurrent neural network (RNN), long shortterm memory (LSTM), and gated recurrent unit (GRU) have shown to improve prediction results. Liu et al [5] proposed an RNN-based model for vehicle mobility prediction and a rolling subway passenger flow prediction model, while Wang et al [6] used the LSTM model to solve traffic forecasting problems. While the traditional statistical method has limitations with periodic data, deep learning methods have more accurate predictions but face complexity in training and parameter adjustment.…”

Section: E-commerce Sales Predictionmentioning

confidence: 99%

Hyperparameter Adaptive Neural Network Model for E-Commerce Sales Prediction

Zhao,

Tian,

Wang

2023

Fuzzy Systems and Data Mining IX

View full text Add to dashboard Cite

Sales forecasting plays a vital role in the daily operations of e-commerce companies, impacting market assessment, operational planning, and supply chain management. As the market is constantly changing, accurately predicting sales is a critical challenge that e-commerce companies need to urgently address. However, traditional statistical forecasting methods have disadvantages such as long run times, low accuracy, weak generalization, and strong data periodicity, which lead to unnecessary losses for companies. We propose the QLBiGRU model that utilizes the reinforcement learning Q-Learning algorithm combined with BiGRU to improve forecasting accuracy. Automatic parameter optimization technology is also used to reduce training time and demand for hardware resources, thereby enabling enterprices to accurately analyze the market and make informed decisions.

show abstract

DeepVM: RNN-Based Vehicle Mobility Prediction to Support Intelligent Vehicle Applications

Cited by 47 publications

References 26 publications

Predicting the Aggregate Mobility of a Vehicle Fleet within a City Graph

Predicting the Aggregate Mobility of a Vehicle Fleet within a City Graph

Internet of Intelligent Vehicles (IoIV): An Intelligent VANET Based Computing via Predictive Modeling

Hyperparameter Adaptive Neural Network Model for E-Commerce Sales Prediction

Contact Info

Product

Resources

About