Velocity forecasts using a combined deep learning model in hybrid electric vehicles with V2V and V2I communication
SCIENCE CHINA-TECHNOLOGICAL SCIENCES
Authors: Pei, JiaZheng; Su, YiXin; Zhang, DanHong; Qi, Yue; Leng, ZhiWen
Vehicle velocity forecast is an important clue in improving the performance of energy management in hybrid electric vehicles (HEV). This paper presents a new combined model for predicting vehicle's velocity time series. The main features of the model are to combine the feature extraction capability of deep restricted Boltzmann machines (DBM) and sequence pattern predicting capability of bidirectional long short-term memory (BLSTM). Hence, the model is named as DBMBLSTM. In addition, the DRMBLSTM model utilizes the vehicle driving information and roadside infrastructure information provided respectively through vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communication channels to predict vehicle velocity at various length of prediction horizon. Furthermore, the predictions results of this study are compared with the state of the art of vehicle velocity forecasts. The root mean square error (RMSE) is used as an evaluation criteria of predictions accuracy. Finally, these compared prediction model are applied in model predictive control (MPC) energy management strategy for the verifications of fuel economy improvement of a HEV. Simulation results confirm that the proposed combined deep learning model performs better than other five prediction methods. Therefore, it is a means of arriving at a reliable forecast model for HEV.
Hepatitis E Virus Cysteine Protease Has Papain Like Properties Validated by in silico Modeling and Cell-Free Inhibition Assays
FRONTIERS IN CELLULAR AND INFECTION MICROBIOLOGY
Authors: Saraswat, Shweta; Chaudhary, Meenakshi; Sehgal, Deepak
Hepatitis E virus (HEV) has emerged as a global health concern during the last decade. In spite of a high mortality rate in pregnant women with fulminant hepatitis, no antiviral drugs or licensed vaccine is available in India. HEV-protease is a pivotal enzyme responsible for ORF1 polyprotein processing leading to cleavage of the non-structural enzymes involved in virus replication. HEV-protease region encoding 432-592 amino acids of Genotype-1 was amplified, expressed in Sf21 cells and purified in its native form. The recombinant enzyme was biochemically characterized using SDS-PAGE, Western blotting and Immunofluorescence. The enzyme activity and the inhibition studies were conducted using Zymography, FTC-casein based protease assay and ORF1 polyprotein digestion. To conduct ORF1 digestion assay, the polyprotein, natural substrate of HEV-protease, was expressed in E. coli and purified. Cleavage of 186 kDa ORF1 polyprotein by the recombinant HEV-protease lead to appearance of non-structural proteins viz. Methyltransferase, Protease, Helicase and RNA dependent RNA polymerase which were confirmed through immunoblotting using antibodies generated against specific epitopes of the enzymes. FTC-casein substrate was used for kinetic studies to determine Km and Vmax of the enzyme and also the effect of different metal ions and other protease inhibitors. A 95% inhibition was observed with E-64 which was validated through in silico analysis. The correlation coefficient between inhibition and docking score of Inhibitors was found to have a significant value of r(2) = 0.75. The predicted 3D model showed two domain architecture structures similar to Papain like cysteine protease though they differed in arrangements of alpha helices and beta sheets. Hence, we propose that HEV-protease has characteristics of "Papain-like cysteine protease," as determined through structural homology, active site residues and class-specific inhibition. However, conclusive nature of the enzyme remains to be established.