Lane-changing (LC) is a critical task for autonomous driving, especially in complex dynamic environments. Numerous automatic LC algorithms have been proposed. This topic, however, has not been sufficiently addressed in existing on-road manoeuvre decision methods. Therefore, this paper presents a novel LC decision (LCD) model that gives autonomous vehicles the ability to make human-like decisions. This method combines a deep autoencoder (DAE) network with the XGBoost algorithm. First, a DAE is utilized to build a robust multivariate reconstruction model using time series data from multiple sensors; then, the reconstruction error of the DAE trained with normal data is analysed for LC identification (LCI) and training data extraction. Then, to address the multi-parametric and nonlinear problem of the autonomous LC decision-making process, an XGBoost algorithm with Bayesian parameter optimization is adopted. Meanwhile, to fully train our learning model with large-scale datasets, we proposed an online training strategy that updates the model parameters with data batches. The experimental results illustrate that the DAE-based LCI model is able to accurately identify the LC behaviour of vehicles. Furthermore, with the same input features, the proposed XGBoost-based LCD model achieves better performance than other popular approaches. Moreover, a simulation experiment is performed to verify the effectiveness of the decision model. INDEX TERMS Autonomous vehicle, lane-changing identification, lane-changing decision-making, deep autoencoder network, XGBoost.
Domesticated microalgae hold great promise for the sustainable provision of various bioresources for human domestic and industrial consumption. Efforts to exploit their potential are far from being fully realized due to limitations in the know-how of microalgal engineering. The associated technologies are not as well developed as those for heterotrophic microbes, cyanobacteria, and plants. However, recent studies on microalgal metabolic engineering, genome editing, and synthetic biology have immensely helped to enhance transformation efficiencies and are bringing new insights into this field. Therefore, this article, summarizes recent developments in microalgal biotechnology and examines the prospects for generating specialty and commodity products through the processes of metabolic engineering and synthetic biology. After a brief examination of empirical engineering methods and vector design, this article focuses on quantitative transformation cassette design, elaborates on target editing methods and emerging digital design of algal cellular metabolism to arrive at high yields of valuable products. These advances have enabled a transition of manners in microalgal engineering from single-gene and enzyme-based metabolic engineering to systems-level precision engineering, from cells created with genetically modified (GM) tags to that without GM tags, and ultimately from proof of concept to tangible industrial applications. Finally, future trends are proposed in microalgal engineering, aiming to establish individualized transformation systems in newly identified species for strain-specific specialty and commodity products, while developing sophisticated universal toolkits in model algal species.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.