Based on the high affinity of folic acid (FA) for folate receptor (FR) that is overexpressed on the surface of many human cancer cells, we have developed a simple fluorescence nanoprobe (1) with multiple capability (fluorescence off-on response and cell-targeting ability) for imaging of FR-positive cells by covalently linking both FA and Rhodamine B (RB) to graphene oxide (GO) through disulfide bonds. The nanoprobe shows a weak fluorescence due to the electron transfer from GO to RB. However, the specific binding of FA to FR-positive cells leads to the internalization of the nanoprobe into the cells. As a result, the disulfide bonds of 1 are cleaved by intracellular glutathione, causing the release of the RB moiety from GO and thereby the generation of fluorescence. Compared to most of the reported fluorescence always-on nanoprobes for imaging FR-positive cells, the present fluorescence off-on nanoprobe can not only produce a high signal/background ratio but also avoid the false positive results often caused by nonspecific adsorption of the always-on nanoprobes on the surface of nontarget cells. Notably, the proposed off-on nanoprobe has been demonstrated to distinguish the cells with different expression levels of FR by culturing and analyzing different cell mixtures (Hela/NIH-3T3 and Hela/MCF-7 cells). Moreover, the nanoprobe is capable of discriminating FR-positive from FR-negative cells even with similar morphology. This method is simple and selective for fluorescence imaging of FR-positive cells.
A new cresyl violet-based ratiometric fluorescence probe is developed and applied to fluorescence imaging of H(2)S in living cells and zebrafish in vivo.
The problem of adaptive traffic signal control in the multi-intersection system has attracted the attention of researchers. Among the existing methods, reinforcement learning has shown to be effective. However, the complex intersection features, heterogeneous intersection structures, and dynamic coordination for multiple intersections pose challenges for reinforcement learning-based algorithms. This paper proposes a cooperative deep Q-network with Q-value transfer (QT-CDQN) for adaptive multi-intersection signal control. In QT-CDQN, a multi-intersection traffic network in a region is modeled as a multi-agent reinforcement learning system. Each agent searches the optimal strategy to control an intersection by a deep Q-network that takes the discrete state encoding of traffic information as the network inputs. To work cooperatively, the agent considers the influence of the latest actions of its adjacencies in the process of policy learning. Especially, the optimal Q-values of the neighbor agents at the latest time step are transferred to the loss function of the Q-network. Moreover, the strategy of the target network and the mechanism of experience replay are used to improve the stability of the algorithm. The advantages of QT-CDQN lie not only in the effectiveness and scalability for the multi-intersection system but also in the versatility to deal with the heterogeneous intersection structures. The experimental studies under different road structures show that the QT-CDQN is competitive in terms of average queue length, average speed, and average waiting time when compared with the state-of-the-art algorithms. Furthermore, the experiments of recurring congestion and occasional congestion validate the adaptability of the QT-CDQN to dynamic traffic environments.INDEX TERMS Deep reinforcement learning, multi-intersection signal control, Q-learning, Q-value transfer, cooperative.
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.