An Introduction to MultiAgent Systems.

해외산업간호정보 - 미국 산업안전보건연구원(National Institute for Occupational Safety and Health) 소개

Though research on the Semantic Web has progressed at a steady pace, its promise has yet to be realized. One major difficulty is that, by its very nature, the Semantic Web is a large, uncensored system to which anyone may contribute. This raises the question of how much credence to give each source. We cannot expect each user to know the trustworthiness of each source, nor would we want to assign top-down or global credibility values due to the subjective nature of trust. We tackle this problem by employing a web of trust, in which each user maintains trusts in a small number of other users. We then compose these trusts into trust values for all other users. The result of our computation is not an agglomerate "trustworthiness" of each user. Instead, each user receives a personalized set of trusts, which may vary widely from person to person. We define properties for combination functions which merge such trusts, and define a class of functions for which merging may be done locally while maintaining these properties. We give examples of specific functions and apply them to data from Epinions and our BibServ bibliography server. Experiments confirm that the methods are robust to noise, and do not put unreasonable expectations on users. We hope that these methods will help move the Semantic Web closer to fulfilling its promise.

Trust management for the Semantic Web

From machine learning to deep learning: progress in machine intelligence for rational drug discovery.

At the core of the analysis task in the development process is information systems requirements modelling. Modelling of requirements has been occurring for many years and the techniques used have progressed from flowcharting through data flow diagrams and entity-relationship diagrams to object-oriented schemas today. Unfortunately, researchers have been able to give little theoretical guidance only to practitioners on which techniques to use and when. In an attempt to address this situation, Wand and Weber have developed a series of models based on the ontological theory of Mario Bunge—the Bunge–Wand–Weber (BWW) models. Two particular criticisms of the models have persisted however—the understandability of the constructs in the BWW models and the difficulty in applying the models to a modelling technique. This paper addresses these issues by presenting a meta model of the BWW constructs using a meta language that is familiar to many IS professionals, more specific than plain English text, but easier to understand than the set-theoretic language of the original BWW models. Such a meta model also facilitates the application of the BWW theory to other modelling techniques that have similar meta models defined. Moreover, this approach supports the identification of patterns of constructs that might be common across meta models for modelling techniques. Such findings are useful in extending and refining the BWW theory.

Developing a meta model for the Bunge–Wand–Weber ontological constructs

Influence maximization problem aims to select a subset of k most influential nodes from a given network such that the spread of influence triggered by the seed set will be maximum. Greedy based algorithms are time-consuming to approximate the expected influence spread of given node set accurately and not well scalable to large-scale networks especially when the propagation probability is large. Conventional heuristics based on network topology or confined diffusion paths tend to suffer from the problem of low solution accuracy or huge memory cost. In this paper an effective discrete shuffled frog-leaping algorithm (DSFLA) is proposed to solve influence maximization problem in a more efficient way. Novel encoding mechanism and discrete evolutionary rules are conceived based on network topology structure for virtual frog population. To facilitate the global exploratory solution, a novel local exploitation mechanism combining deterministic and random walk strategies is put forward to improve the suboptimal meme of each memeplex in the frog population. The experimental results of influence spread in six real-world networks and statistical tests show that DSFLA performs effectively in selecting targeted influential seed nodes for influence maximization and is superior than several state-of-the-art alternatives.

A discrete shuffled frog-leaping algorithm to identify influential nodes for influence maximization in social networks

RuleML is a family of XML languages whose modular system of schemas permits high-precision (Web) rule interchange. The family's top-level distinction is deliberation rules vs. reaction rules. In this paper we address the Reaction RuleML subfamily of RuleML and survey related work. Reaction RuleML is a standardized rule markup/serialization language and semantic interchange format for reaction rules and rule-based event processing. Reaction rules include distributed Complex Event Processing (CEP), Knowledge Representation (KR) calculi, as well as Event-Condition-Action (ECA) rules, Production (CA) rules, and Trigger (EA) rules. Reaction RuleML 1.0 incorporates this reactive spectrum of rules into RuleML employing a system of step-wise extensions of the Deliberation RuleML 1.0 foundation.

Reaction RuleML 1.0: standardized semantic reaction rules

Influence maximization aims to select a small set of k influential nodes to maximize the spread of influence. It is still an open research topic to develop effective and efficient algorithms for the optimization problem. Greedy-based algorithms utilize the property of “submodularity” to provide performance guarantee, but the computational cost is unbearable especially in large-scale networks. Meanwhile, conventional topology-based centrality methods always fail to provide satisfying identification of influential nodes. To identify the k influential nodes effectively, we propose a metaheuristic discrete bat algorithm (DBA) based on the collective intelligence of bat population in this paper. According to the evolutionary rules of the original bat algorithm (BA), a probabilistic greedy-based local search strategy based on network topology is presented and a CandidatesPool is generated according to the contribution of each node to the network topology to enhance the exploitation operation of DBA. The experimental results and statistic tests on five real-world social networks and a synthetic network under independent cascade model demonstrate that DBA outperforms other two metaheuristics and the Stop-and-Stair algorithm, and achieves competitive influence spread to CELF (Cost-Effective Lazy Forward) but has less time computation than CELF.

Maximizing the spread of influence via the collective intelligence of discrete bat algorithm

Influence maximization aims to select a subset of top-k influential nodes to maximize the influence propagation, and it remains an open research topic of viral marketing and social network analysis. Submodularity-based methods including greedy algorithm can provide solutions with performance guarantee, but the time complexity is unbearable especially in large-scale networks. Meanwhile, conventional centrality-based measures cannot provide steady performance for multiple influential nodes identification. In this paper, we propose an improved discrete particle swarm optimization with an enhanced network topology-based strategy for influence maximization. According to the strategy, the k influential nodes in a temporary optimal seed set are recombined firstly in ascending order by degree metric to let the nodes with lower degree centrality exploit more influential neighbors preferentially. Secondly, a local greedy strategy is applied to replace the current node with the most influential node from the direct neighbor set of each node from the temporary seed set. The experimental results conducted in six social networks under independent cascade model show that the proposed algorithm outperforms typical centrality-based heuristics, and achieves comparable results to greedy algorithm but with less time complexity.

Identification of top-k influential nodes based on enhanced discrete particle swarm optimization for influence maximization

Data-driven statistical air quality prediction methods usually build models fast with moderate accuracy and have been studied a lot in recent years. However, due to the complexity of air quality prediction which usually involves multiple factors, such as meteorological, spatial, and temporal properties, it is still a challenge to propose a model with required accuracy. In this paper, we propose a hybrid ensemble model CERL to exploit the merits of both forward neural networks and recurrent neural networks that are designed for handling time serial data to predict air quality hourly. Measured air pollutant factors including Air Quality Index (AQI), PM2.5, PM10, CO, SO2, NO2, and O3 are used as input to predict air quality from 1 to 8 h ahead. Based on the air quality prediction evaluation in Lanzhou and Xi'an, which are two important provincial capitals in Northwest China, CERL provides better performance over other baseline models. Moreover, as the step length increases, CERL has more obvious improvement. For example, the improvements of CERL in the 1-step, 3-step, 5-step, and 8-step prediction for PM2.5 in Lanzhou are 1.82%, 8.01%, 9.98%, and 20.03%, respectively. The superiority of CERL is also proved by a hypothesis Diebold Mariano test with level of significance 5%.

Zhili Zhao

Papers

A discrete shuffled frog-leaping algorithm to identify influential nodes for influence maximization in social networks

Reaction RuleML 1.0: standardized semantic reaction rules

Maximizing the spread of influence via the collective intelligence of discrete bat algorithm

Identification of top-k influential nodes based on enhanced discrete particle swarm optimization for influence maximization

Combining forward with recurrent neural networks for hourly air quality prediction in Northwest of China