Search Results

Driving style and skill classification are of great significance in human-oriented advanced driver-assistance system (ADAS) development. In this paper, we propose Fully-Connected Deep Neural Networks (FC-DNN) to classify drivers’ styles and skills with naturalistic driving data. Followed by the data collection and pre-processing, FC-DNN with a series of deep learning optimization algorithms are applied. In the experimental part, the proposed model is validated and compared with other commonly used supervised learning methods including the k-nearest neighbors (KNN), support vector machine (SVM), decision tree (DT), random forest (RF), and multilayer perceptron (MLP). The results show that the proposed model has a higher Macro F1 score than other methods. In addition, we discussed the effect of different time window sizes on experimental results. The results show that the driving information of 1s can improve the final evaluation score of the model.

The poor low-temperature behavior of Li-ion batteries has limited its application in the field of electric vehicles and hybrid electric vehicles. Many previous studies concentrate on developing new type of electrolyte to solve this problem. However, according to recent research, the key limitation at low temperature is the low diffusivity of lithium ion in the anode electrodes. Hence, it is potential to study anode materials to improve low-temperature behavior of LIBs. ZnFe2O4 with higher theoretical capacity is low toxicity and abundance, contributing to its commercial application. Different ZnFe2O4 crystalline shapes have different particle sizes. Among them, the cubic ZnFe2O4 with smaller particle size will increase its own electronic and ionic conductance at lower temperature. In this regard, we evaluated low-temperature performance of LIBs with ZnFe2O4 cubes as anode materials at -25°C.