With the explosion of healthcare information, there has been a tremendous amount of heterogeneous textual medical knowledge (TMK), which plays an essential role in healthcare information systems. Existing works for integrating and utilizing the TMK mainly focus on straightforward connections establishment and pay less attention to make computers interpret and retrieve knowledge correctly and quickly. In this paper, we explore a novel model to organize and integrate the TMK into conceptual graphs. We then employ a framework to automatically retrieve knowledge in knowledge graphs with a high precision. In order to perform reasonable inference on knowledge graphs, we propose a contextual inference pruning algorithm to achieve efficient chain inference. Our algorithm achieves a better inference result with precision and recall of 92% and 96%, respectively, which can avoid most of the meaningless inferences. In addition, we implement two prototypes and provide services, and the results show our approach is practical and effective.

Sphingomonas melonis TY utilizes nicotine as a sole source of carbon, nitrogen, and energy through a variant of the pyridine and pyrrolidine pathways (VPP). A 31-kb novel nicotine-degrading gene cluster, ndp, in strain TY exhibited a different genetic organization with the vpp cluster in strains Ochrobactrum rhizosphaerae SJY1 and Agrobacterium tumefaciens S33. Genes in vpp were separated by a 20-kb interval sequence, while genes in ndp were localized together. Half of the homolog genes were in different locus in ndp and vpp. Moreover, there was a gene encoding putative transporter of nicotine or other critical metabolite in ndp. Among the putative nicotine-degrading related genes, the nicotine hydroxylase, 6-hydroxy-L-nicotine oxidase, 6-hydroxypseudooxynicotine oxidase, and 6-hydroxy-3-succinyl-pyridine monooxygenase responsible for catalyzing the transformation of nicotine to 2, 5-dihydropyridine in the initial four steps of the VPP were characterized. Hydroxylation at C6 of the pyridine ring and dehydrogenation at the C2–C3 bond of the pyrrolidine ring were the key common reactions in the VPP, pyrrolidine and pyridine pathways. Besides, VPP and pyrrolidine pathway shared the same latter part of metabolic pathway. After analysis of metabolic genes in the pyridine, pyrrolidine, and VPP pathways, we found that both the evolutionary features and metabolic mechanisms of the VPP were more similar to the pyrrolidine pathway. The linked ndpHFEG genes shared by the VPP and pyrrolidine pathways indicated that these two pathways might share the same origin, but variants were observed in some bacteria. And we speculated that the pyridine pathway was distributed in Gram-positive bacteria and the VPP and pyrrolidine pathways were distributed in Gram-negative bacteria by using comprehensive homologs searching and phylogenetic tree construction.

Evolution strategies (ES) have recently raised attention in solving challenging tasks with low computation costs and high scalability. However, it is well-known that evolution strategies reinforcement learning (RL) methods suffer from low stability. Without careful consideration, ES methods are sensitive to local optima and are unstable in learning. Therefore, there is an urgent need for improving the stability of ES methods in solving RL problems. In this paper, we propose a simple yet efficient ES method to stabilize the learning. Specifically, we propose a framework to incorporate the maximum entropy reinforcement learning with evolution strategies and derive an efficient entropy calculation method for linear policies. We further present a practical algorithm called maximum entropy evolution policy search based on the proposed framework, which is efficient and stable for policy search in continuous control. Our algorithm shows high stability across different random seeds and can obtain comparable results in performance against some existing derivative-free RL methods on several of the well-known benchmark MuJoCo robotic control tasks.

Novelty search, which was inspired by the nature that evolves creatures with diversity, has shown great potential in solving reinforcement learning (RL) tasks with sparse and deceptive rewards. However, most of the existing novelty search methods evolve the populations through hybrization and mutation, which is inefficient in diverging populations. In this paper, we propose a method which incorporates deep RL with novelty search to improve the efficiency of diverging the populations for novelty search. We first propose a strategy that improves the novelty of individuals generated by genetic algorithm using reinforcement learning. Based on this strategy, we propose a framework that incorporates deep RL with novelty search, and then derive an algorithm to improve the search efficiency of the novelty search for continuous control tasks. Our experimental results show that our method can improve the search efficiency of novelty search and can also provide a competitive performance compared to some of the existing novelty search methods. The

Recently, the Internet-of-Things technique is believed to play an important role as the foundation of the coming Artificial Intelligence age for its capability to sense and collect real-time context information of the world, and the concept Artificial Intelligence of Things (AIoT) is developed to summarize this vision. However, in typical centralized architecture, the increasing of device links and massive data will bring huge congestion to the network, so that the latency brought by unstable and time-consuming long-distance network transmission limits its development. The multi-access edge computing (MEC) technique is now regarded as the key tool to solve this problem. By establishing a MEC-based AIoT service system at the edge of the network, the latency can be reduced with the help of corresponding AIoT services deployed on nearby edge servers. However, as the edge servers are resource-constrained and energy-intensive, we should be more careful in deploying the related AIoT services, especially when they can be composed to make complex applications. In this paper, we modeled complex AIoT applications using directed acyclic graphs (DAGs), and investigated the relationship between the AIoT application performance and the energy cost in the MEC-based service system by translating it into a multi-objective optimization problem, namely the CA$$^3$$ 3 D problem — the optimization problem was efficiently solved with the help of heuristic algorithm. Besides, with the actual simple or complex workflow data set like the Alibaba Cloud and the Montage project, we conducted comprehensive experiments to evaluate the results of our approach. The results showed that the proposed approach can effectively obtain balanced solutions, and the factors that may impact the results were also adequately explored.