License plate detection is a challenging problem due to the large visual variations in complex environments, such as motion blur, occlusion, and lighting changes. An advanced discriminative model is needed to accurately segment license plates from the backgrounds. However, effective models for the problem tend to be computationally prohibitive. To address these two conflicting challenges, we propose to detect license plate based on two CNNs, a shallow CNN and a deep CNN. The shallow CNN is used to quickly remove most of the background regions to reduce the computation cost, and the deep CNN is used to detect license plate in the remaining regions. These two CNNs are trained end to end and are complementary to each other to guarantee the detection precision with low computation cost. Experimental results show that the proposed method is promising for license plate detection.
Combined heat and power economic dispatch (CHPED) problem aims to optimally schedule the output of generating units with minimum fuel cost, which is a highly non-linear, non-convex and large-scale global optimization problem with many practical constraints. The complexity of the problem demands solution methods with powerful search ability, robustness, and computational efficiency. This paper proposes a heterogeneous evolving cuckoo search (HECS) algorithm with a novel constraint-handling mechanism to solve the large-scale CHPED problem considering valve-point effect. Based on the cuckoo search algorithm, we apply a comprehensive learning strategy to enhance the search ability in the highdimensional environment, and a heterogeneous evolving strategy to improve the robustness of the algorithm. Moreover, we develop a novel constraint-handling mechanism that uses strict mathematical methods to repair unfeasible solutions and avoid redundant calculation. 5 tests are conducted on 24-unit, 48-unit, 84-unit, 96-unit, and 192-unit systems and the results are compared with the state-of-the-art algorithms published in the year 2015-2019. The comparisons show that the HECS could annually save millions of dollars in some large-scale systems, which verify its effectiveness. INDEX TERMS Combined heat and power economic dispatch, large-scale global optimization, valve-point effect, cuckoo search, constraint-handling mechanism.
Fe2+ and Zn2+ levels in perilymph of guinea pigs injected with gentamicin (GM) were examined and compared with the corresponding concentrations in CSF, serum and hairs. We observed a preventive and therapeutic action of sea buckthorn oil and injectio gastrodini to hearing loss. The results showed that: (1) the Fe2+ content in GM-injected guinea pigs was increased in perilymph and hairs; it was decreased after prevention and treatment, but there was no obvious change in CSF and serum; (2) the Zn2+ content in perilymph and CSF was increased in GM-injected guinea pigs. It rose further after prevention, but in serum and hairs it decreased. The results indicate that the ototoxic reaction to GM is related to the rise of the Fe2+ content in perilymph. The elevation of Zn2+ is a compensatory reaction. The changes in the chemical composition of perilymph are more important than those in CSF, serum and hairs for pathological changes of the cochlea. Sea buckthorn oil can prevent GM ototoxicity.
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.