Vehicle speed prediction using a cooperative method of fuzzy Markov model and auto-regressive model

Dual-loop online intelligent programming for driver-oriented predict energy management of plug-in hybrid electric vehicles

“…Considering the computation efficiency and prediction accuracy, 5layer Markov-chain model is reliable for training purpose as has been proved by Ref. [21]. In this paper, the AR model coefficient sets are classified into 5 clusters representing different acceleration states to label the estimated AR models to some specific driver states.…”

“…The auto-regression (AR) model is a proven tool for generalizing the signal's average time regressive pattern and predicting by following the dynamic. The AR model used in this study follows the structure described in [21]:…”

“…[18] driven by neural networks are employed to identify driving patterns in real time. Other types of artificial intelligence-based predictive model contain Bayesian algorithms [19], fuzzy cognitive maps [20], and auto-regressive models [21,22]: these algorithms can be used for modelling, learning, and predicting. If the driving behaviours exhibit dramatic changes, however, the prediction will become poor so that online updates need to be considered.…”

Predicting Fine-Grained Traffic Conditions via Spatio-Temporal LSTM

“…Finally, the individual vehicle speed is predicted by forward-backward algorithm. Another mechanism proposed in [15] is a cooperative method which combines with fuzzy markov model and auto-regressive model. These machine learning approaches for vehicle speed prediction do not care about the basic data sources, and focus more on the accuracy of prediction algorithms rather than the accuracy of segmentbased traffic prediction.…”

Back-to-Back Competitive Learning Mechanism for Fuzzy Logic Based Supervisory Control System of Hybrid Electric Vehicles

“…In the work of Zhang and Xiong [9], a hierarchical control strategy is simulated for multiple energy sources, in which a driving pattern recognition method is developed using fuzzy logic controllers (FLCs). Jing et al [10] proposes a cooperative method for vehicle speed prediction that uses a fuzzy C-mean algorithm with an unsupervised learning process to classify acceleration states. In the work of Filev and Kolmanovsky [11], a fuzzy encoding technology is presented to develop conventional Markov chain models with a continuous range, (also applied in the research of Li et al [12]).…”