Our evaluation on the independent test set showed that most types of feature were beneficial to Chinese NER systems, although the improvements were limited. The system achieved the highest performance by combining word segmentation and section information, indicating that these two types of feature complement each other. When the same types of optimized feature were used, CRF and SSVM outperformed SVM and ME. More specifically, SSVM achieved the highest performance of the four algorithms, with F-measures of 93.51% and 90.01% for admission notes and discharge summaries, respectively.
Robust model predictive control (MPC) is widely applied to batch processes to handle its intrinsic plant-model mismatch by considering the worst-case scenario and thus leads to conservative performance. Identification methods that make use of system repetitiveness have been invented and combined with robust MPC to reduce conservativeness. In this paper, we show that in addition to the repetitiveness, time-wise continuity in system dynamics can also help to improve model accuracy and accelerate the convergence rate. Specifically, we propose a two-dimensional online identification method in the framework of set membership identification. The method is capable of (1) employing time-wise correlation and cycle-wise repetitiveness in system dynamics; (2) identifying both of the nominal value and the corresponding uncertainty set of the unknown parameters, thus being amenable to robust MPC schemes; and (3) guaranteeing convergence to the true parameters under mild conditions. Numerical examples are provided to illustrate its fast convergence and superiority in improving prediction accuracy and control performance.
Repeatability provides an opportunity to learn from historical process data, thus enabling batch processes to produce high-value and batch-improved products. However, industrial batch processes are always constrained. This makes many data-driven learning methods impractical. Therefore, learning within a set of constraints is of great importance in batch processes. In order to optimize tracking problems, iterative learning approaches require pre-established policies and knowledge of the underlying performance evaluation. In this article, we propose a constrained learning algorithm for the problem that is data-efficient, in the sense that it can be used by extracting useful information from historical process data under complex and uncertain conditions. Using historical process data, we create an efficient convex constraint for dynamic optimization problems, making the real-time optimal learning less dependent on model accuracy, which is the main tenet of model-based iterative learning. Our method achieves better control performance and a faster convergence rate than conventional methods. The technique is demonstrated using an injection molding process for tracking control tasks.
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.