Search

The structured road is a scene with high interaction between vehicles, but due to the high uncertainty of behavior, the prediction of vehicle interaction behavior is still a challenge. This prediction is significant for controlling the ego-vehicle. We propose an interaction behavior prediction model based on vehicle cluster (VC) by self-attention (VC-Attention) to improve the prediction performance. Firstly, a five-vehicle based cluster structure is designed to extract the interactive features between ego-vehicle and target vehicle, such as Deceleration Rate to Avoid a Crash (DRAC) and the lane gap. In addition, the proposed model utilizes the sliding window algorithm to extract VC behavior information. Then the temporal characteristics of the three interactive features mentioned above will be caught by two layers of self-attention encoder with six heads respectively. Finally, target vehicle’s future behavior will be predicted by a sub-network consists of a fully connected layer and SoftMax module. The experimental results show that this method has achieved accuracy, precision, recall, and F1 score of more than 92% and time to event of 2.9 s on a Next Generation Simulation (NGSIM) dataset. It accurately predicts the interactive behaviors in class-imbalance prediction and adapts to various driving scenarios.

Machine learning is a powerful tool to predict user behavior and harness the vast amount of data measured in cellular networks. Predictive resource allocation is a promising approach to take advantage of the prediction for the mobility and traffic load related user behavior. This paper strives to boost the performance of under-utilized networks by predicting behavior-related information from historical data with deep learning. We first propose a hierarchical and multi-timescale radio resource management scheme for non-realtime service that only needs coarse-grained future knowledge, by taking multi-input-multi-output orthogonal frequency multi-access as an example system and high throughput as an example performance metric. Such a scheme allows the decision of resource management to be made in a central processor and base stations in different timescales and allows the knowledge to be predicted with less training samples. Then, we design a deep neural network to learn the future knowledge required for making decision directly from different types of past data with different resolutions observable in cellular networks. Simulation results show that the proposed scheme with the end-to-end knowledge prediction performs closely to the relevant optimal solution with perfect and fine-grained prediction, and provides dramatic gain over non-predictive counterpart in supporting high request arrival rate for the non-realtime service.

The structured road is a scene with high interaction between vehicles, but due to the high uncertainty of behavior, the prediction of vehicle interaction behavior is still a challenge. This prediction is significant for controlling the ego-vehicle. We propose an interaction behavior prediction model based on vehicle cluster (VC) by self-attention (VC-Attention) to improve the prediction performance. Firstly, a five-vehicle based cluster structure is designed to extract the interactive features between ego-vehicle and target vehicle, such as Deceleration Rate to Avoid a Crash (DRAC) and the lane gap. In addition, the proposed model utilizes the sliding window algorithm to extract VC behavior information. Then the temporal characteristics of the three interactive features mentioned above will be caught by two layers of self-attention encoder with six heads respectively. Finally, target vehicle's future behavior will be predicted by a sub-network consists of a fully connected layer and SoftMax module. The experimental results show that this method has achieved accuracy, precision, recall, and F1 score of more than 92% and time to event of 2.9 s on a Next Generation Simulation (NGSIM) dataset. It accurately predicts the interactive behaviors in class-imbalance prediction and adapts to various driving scenarios. [ABSTRACT FROM AUTHOR]

• RUL of ultracapacitors can be predicted only using data from 5 consecutive cycles. • Prediction does not require specific domain knowledge or manual feature extraction. • The proposed method enables early prediction. Accurate and rapid prediction of the lifetime is essential for accelerating the application of ultracapacitors. To overcome the large inconsistencies in the lifetime of ultracapacitors, an end-to-end remaining useful life (RUL) prediction method based on the convolutional neural network (CNN) is proposed. It directly establishes the mapping between the charging and discharging data collected within a few consecutive cycles and the corresponding remaining useful life. It learns many ageing features from limited raw data without any expert knowledge. While improving the prediction accuracy of the RUL, the required test time drops greatly. Validation results based on 113 ultracapacitors demonstrate that our method can accurately predict RUL by using the data within 5 consecutive cycles collected at any ageing stage, and the root mean square error is 501 cycles. Our method demonstrates higher accuracy compared with conventional feature-based prediction methods, while required input data are sharply reduced. Such 5-cycle testing can be conducted within 15 min to collect enough data for RUL prediction. Our work highlights the promise of data-driven approaches to predict the degradation of energy storage devices. [ABSTRACT FROM AUTHOR]