24 November 2020 in IEEE Access
Limited driving range is one of the major obstacles to the widespread application of electric vehicles (EVs). Accurately predicting the remaining driving range can effectively reduce the range anxiety of drivers. In this paper, a blended machine learning model was proposed to predict the remaining driving range of EVs based on real-world historical driving data. The blended model fuses two advanced machine learning algorithms of Extreme Gradient Boosting Regression Tree (XGBoost) and Light Gradient Boosting Regression Tree (LightGBM). The proposed model was trained to “learn” the relationship between the driving distance and the proposed features such as cumulative output energy of the motor and the battery, different driving patterns, and temperature of the battery). In addition, an “anchor (baseline) based” strategy was proposed and was seen to be able to effectively eliminate the unbalance distribution of dataset. The results of experiments suggest that our proposed anchor-based blended model has better performances with a smaller prediction error range of -0.8, 0.8 as compared with previous methods.
27 January 2021 in International Journal of Electrical Engineering & Education
With the advancement of multimedia technology, a series of problems have emerged in the reform of college English teaching. How to use multimedia to assist college students in English learning has become a meaningful study. Multimedia-assisted instruction is a common method of teaching English. The design of multimedia-assisted English teaching resource software determines its development, management, evaluation and other aspects, so the design of multimedia platform plays a vital role in the effect of multimedia teaching. This paper will discuss the design and implementation of multimedia-assisted college English independent education resources from the perspective of knowledge classification. Through the content analysis, some problems exist in the design process of some college English multimedia teaching, and the status quo is analyzed. It also studies the difficulties of college students in the process of multimedia assisted learning, and how college students hope to design multimedia independent learning multimedia platform. Finally, the five knowledge classification learning theories of “listening, speaking, reading, writing and translating” can change the status quo, meet the needs of college students, and develop the knowledge of vocabulary, grammar and listening in college English. The design strategy of self-learning multimedia-assisted instruction and the design of college English self-learning multimedia teaching is briefly written.
25 January 2021 in IEEE Access
Driving cycle is an important indicator to evaluate vehicle performance and to measure fuel consumption. Its impact is not only on pollution emissions but also on asset management. Based on the real life detailed data from the city tour buses in Beijing, this paper proposes to couple a genetic algorithm based GA-K-means clustering with the Hidden Markov Model (HMM) to construct a city tour bus urban road driving cycle in Beijing. Compared to the standard driving cycle C-WTVC used for heavy commercial vehicle fuel consumption certification in China, our driving cycle model can reflect the real life situation more accurately. With our model, the influence of driving state and driving behavior on fuel consumption is also analyzed, and the fuel consumption estimation model under the corresponding driving cycle is constructed. To gain deeper insight and better fuel consumption, we further segment and construct the driving sub-cycles of peak and off-peak periods according to the difference in fuel consumption at different time periods in Beijing in September 2019. Through this fine-grain driving cycle, we can further improve the accuracy of the fuel consumption estimation model.