面向数据流结构的指令映射优化方法

在高性能计算领域,数据流是一类重要的计算结构,也在很多实际场景表现出很好的性能和适用性。在数据流计算模式中,程序是以数据流图来表示的,数据流计算中一个关键的问题是如何将数据流图映射到多个执行单元上。通过分析现有数据流结构的指令映射方法及其不足,提出了基于数据流结构的新型指令映射优化方法。主要是根据多地址共享数据包的特性对指令映射方法进行优化,延迟多地址共享数据路由包的拆分,减少网络拥堵。     

一种人工情绪模型及其电商计算实验应用

针对电子商务顾客购物人工系统的计算实验研究，提出一种基于状态类比假说的人工情绪模型，给出了情绪的产生、增强、衰落和消失过程的描述方法，研究了外部刺激、情感强度和内部驱动力的计算方法，并进行了模拟分析。基于此人工情绪模型，构建了电商顾客购物的情绪-行为影响关系模型；将其应用于电商顾客购物的计算实验分析。结果表明，该人工情绪模型能较好地应用于电商复杂人工系统顾客购物的计算实验。     

Analog active filter design using a multi objective genetic algorithm

The selection of the correct values for passive elements, resistors, and capacitors, is an important task in analog active filter design. The classic method of choosing passive elements is a difficult task and can lead to errors. To reduce the incidence of error and human effort evolutionary optimization techniques are used to select the values of capacitors and resistors. However, due to the single objective optimization technique, these are not well suited to optimize different filter parameters. For this reason, the performance of a multi-objective genetic algorithm named non-dominated sorting genetic algorithm II (NSGA-II) against the different single objective algorithms is evaluated. Two analog active filters: A fourth order Butterworth and a second order state variable filter with the operational amplifiers in their cores are used for testing purposes. In both cases two different objects are chosen along with eight components as variables to be optimized. The component values are compatible with the E12, E24 and E96 series using NSGA-II. The computation results are better in terms of design error and allow for better resistor and capacitor choice. To reach the same or better results the NSGA-II needs fewer generations compared with other genetic algorithms for this problem.     

Quantum computation based bundling optimization for combinatorial auction in freight service procurements

Combinatorial auction is a useful trade manner for transportation service procurements in e-marketplaces. To enhance the competition of combinatorial auction, a novel auction mechanism of two-round bidding with bundling optimization is proposed. As the recommended the auction mechanism, the shipper/auctioneer integrates the objects into several bundles based on the bidding results of first round auction. Then, carriers/bidders bid for the object bundles in second round. The bundling optimization is described as a multi-objective model with two criteria on price complementation and combination consistency. A Quantum Evolutionary Algorithm (QEA) with β-based rotation gate and the encoding scheme based on non-zero elements in complementary coefficient matrix is developed for the model solution. Comparing with a Contrast Genetic Algorithm, QEA can achieve better computational performances for small and middle size problems.     

Lagrangian relaxation hybrid with evolutionary algorithm for short-term generation scheduling

Short-term generation scheduling is an important function in daily operational planning of power systems. It is defined as optimal scheduling of power generators over a scheduling period while respecting various generator constraints and system constraints. Objective of the problem includes costs associated with energy production, start-up cost and shut-down cost along with profits. The resulting problem is a large scale nonlinear mixed-integer optimization problem for which there is no exact solution technique available. The solution to the problem can be obtained only by complete enumeration, often at the cost of a prohibitively computation time requirement for realistic power systems. This paper presents a hybrid algorithm which combines Lagrangian Relaxation (LR) together with Evolutionary Algorithm (EA) to solve the problem in cooperative and competitive energy environments. Simulation studies were carried out on different systems containing various numbers of units. The outcomes from different algorithms are compared with that from the proposed hybrid algorithm and the advantages of the proposed algorithm are briefly discussed.     

Evolutionary collective behavior decomposition model for time series data mining

In this research, we propose a novel framework referred to as collective game behavior decomposition where complex collective behavior is assumed to be generated by aggregation of several groups of agents following different strategies and complexity emerges from collaboration and competition of individuals. The strategy of an agent is modeled by certain simple game theory models with limited information. Genetic algorithms are used to obtain the optimal collective behavior decomposition based on history data. The trained model can be used for collective behavior prediction. For modeling individual behavior, two simple games, the minority game and mixed game are investigated in experiments on the real-world stock prices and foreign-exchange rate. Experimental results are presented to show the effectiveness of the new proposed model.     

A stochastic evolutionary coalition game model of secure and dependable virtual service in Sensor-Cloud

Various intrusion detection systems (IDSs) have been proposed in recent years to provide safe and reliable services in cloud computing. However, few of them have considered the existence of service attackers who can adapt their attacking strategies to the topology-varying environment and service providers’ strategies. In this paper, we investigate the security and dependability mechanism when service providers are facing service attacks of software and hardware, and propose a stochastic evolutionary coalition game (SECG) framework for secure and reliable defenses in virtual sensor services. At each stage of the game, service providers observe the resource availability, the quality of service (QoS), and the attackers’ strategies from cloud monitoring systems (CMSs) and IDSs. According to these observations, they will decide how evolutionary coalitions should be dynamically formed for reliable virtual-sensor-service composites to deliver data and how to adaptively defend in the face of uncertain attack strategies. Using the evolutionary coalition game, virtual-sensor-service nodes can form a reliable service composite by a reliability update function. With the Markov chain constructed, virtual-sensor-service nodes can gradually learn the optimal strategy and evolutionary coalition structure through the minimax-Q learning, which maximizes the expected sum of discounted payoffs defined as QoS for virtual-sensor-service composites. The proposed SECG strategy in the virtual-sensor-service attack-defense game is shown to achieve much better performance than strategies obtained from the evolutionary coalition game or stochastic game, which only maximizes each stage's payoff and optimizes a defense strategy of stochastic evolutionary, since it successfully accommodates the environment dynamics and the strategic behavior of the service attackers.     

An experimental study of adaptive control for evolutionary algorithms

In this paper, we investigate how adaptive operator selection techniques are able to efficiently manage the balance between exploration and exploitation in an evolutionary algorithm, when solving combinatorial optimization problems. We introduce new high level reactive search strategies based on a generic algorithm's controller that is able to schedule the basic variation operators of the evolutionary algorithm, according to the observed state of the search. Our experiments on SAT instances show that reactive search strategies improve the performance of the solving algorithm.     

Data-driven placemaking: Public space canopy design through multi-objective optimisation considering shading,structural and social performance

In the context of ongoing densification of cities and aging urban populations, public spaces are a crucial infrastructure to support the physical and mental wellbeing of urban residents. The design of public space furniture elements is often standardised, and not considered in relation to environmental conditions and mechanisms of social interaction. This article presents a digital workflow to generate site-specific designs for shaded public seating, considering the relationships of local public places to their surroundings. A strategy for customised and site-specific design is developed through the use of multiple software tools, employing evolutionary algorithms and multi-objective optimisation. The method is applied to a small public space canopy prototype installed within a public housing estate in Hong Kong, incorporating additional criteria to achieve a low-cost and light-weight structure. Through multiple stages of refinement and optimisation, a material, structural and social performance-driven outcome was achieved that creates a shaded space for public seating, people watching and social interaction. As part of a larger research agenda exploring architectural form-finding and environmental psychology, the project represents potential new applications in the emerging field of socially driven computational design.     

MDA-TOEPGA: A novel method to identify miRNA-disease association based on two-objective evolutionary programming genetic algorithm

The association between miRNA and disease has attracted more and more attention. Until now, existing methods for identifying miRNA related disease mainly rely on top-ranked association model, which may not provide a full landscape of association between miRNA and disease. Hence there is strong need of new computational method to identify the associations from miRNA group view. In this paper, we proposed a framework, MDA-TOEPGA, to identify miRNAdisease association based on two-objective evolutionary programming genetic algorithm, which identifies latent miRNAdisease associations from the view of functional module. To understand the miRNA functional module in diseases, the case study is presented. We have been compared MDA-TOEPGA with several state-of-the-art functional module algorithm. Experimental results showed that our method cannot only outperform classical algorithms, such as K-means, IK-means, MCODE, HC-PIN, and ClusterONE, but can also achieve an ideal overall performance in terms of a composite score consisting of f1, Sensitivity, and Accuracy. Altogether, our study showed that MDA-TOEPGA is a promising method to investigate miRNA-disease association from the landscapes of functional module.