An immune system inspired clustering and classification method to detect critical areas in electrical power networks

Identifying critical, failure prone areas in a power system network are often a difficult and computationally intensive task. Artificial Immune System (AIS) algorithms have been shown to be capable of generalization and learning to identify previously unseen patterns. In this paper, a method is developed that uses artificial immune system classification and clustering algorithms to identify critical areas in the network. The algorithm identifies areas of the power system network that are prone to voltage collapse and areas with overloaded lines. The applicability of AIS for this particular task is demonstrated on test electrical power system networks. Its accuracy is compared with an optimised support vector machine (SVM) algorithm and k nearest neighbours algorithm (kNN) across 3 different power system networks.     

A novel approach to ontology classification

Ontology classification–the computation of the subsumption hierarchies for classes and properties–is a core reasoning service provided by all OWL reasoners known to us. A popular algorithm for computing the class hierarchy is the so-called Enhanced Traversal (ET) algorithm. In this paper, we present a new classification algorithm that attempts to address certain shortcomings of ET and improve its performance. Apart from classification of classes, we also consider object and data property classification. Using several simple examples, we show that the algorithms commonly used to implement these tasks are incomplete even for relatively weak ontology languages. Furthermore, we show that property classification can be reduced to class classification, which allows us to classify properties using our optimised algorithm. We implemented all our algorithms in the OWL reasoner HermiT. The results of our performance evaluation show significant performance improvements on several well-known ontologies.     

一种优化Dijkstra算法的研究

阐述传统最短路径算法的优缺点,提出对传统寻路问题的优化算法,旨在解决节点较多网络的最短路径问题。比较优化算法与传统算法的搜索效率,以及优化算法之间的异同,测试表明,优化后的算法在效率方面具有明显的优越性。为了验证算法的有效性,最后给出鲁东大学的一个具体应用。     

A new effective operator for the hybrid algorithm for solving global optimisation problems

Hybrid algorithms have been recently used to solve complex single-objective optimisation problems. The ultimate goal is to find an optimised global solution by using these algorithms. Based on the existing algorithms (HP_CRO, PSO, RCCRO), this study proposes a new hybrid algorithm called MPC (Mean-PSO-CRO), which utilises a new Mean-Search Operator. By employing this new operator, the proposed algorithm improves the search ability on areas of the solution space that the other operators of previous algorithms do not explore. Specifically, the Mean-Search Operator helps find the better solutions in comparison with other algorithms. Moreover, the authors have proposed two parameters for balancing local and global search and between various types of local search, as well. In addition, three versions of this operator, which use different constraints, are introduced. The experimental results on 23 benchmark functions, which are used in previous works, show that our framework can find better optimal or close-to-optimal solutions with faster convergence speed for most of the benchmark functions, especially the high-dimensional functions. Thus, the proposed algorithm is more effective in solving single-objective optimisation problems than the other existing algorithms.     

A multi-objective car sequencing problem on two-sided assembly lines

The car sequencing problem consists of sequencing a given set of cars to be produced in each day. This paper presents an application of the extended coincident algorithm (COIN-E), which is an instance of the estimation of distribution algorithms, to a multi-objective car sequencing problem on a more realistic platform, i.e. two-sided assembly lines. Three conflicting objectives are optimised simultaneously in a Pareto sense including minimise the number of paint colour changes, minimise the total number of ratio constraint violations and minimise the utility work. The performances of COIN-E are compared with COIN (its original version), NSGA II, DPSO and BBO. The results reveal that COIN-E is superior to the other contestant algorithms in both solution quality and diversity.     

Lexicographic bottleneck mixed-model assembly line balancing problem: Artificial bee colony and tabu search approaches with optimised parameters

The lexicographic bottleneck assembly line balancing problem is a recently introduced problem which aims at obtaining a smooth workload distribution among workstations. This is achieved hierarchically. The workload of the most heavily loaded workstation is minimised, followed by the workload of the second most heavily loaded workstation and so on. This study contributes to knowledge by examining the application of the lexicographic bottleneck objective on mixed-model lines, where more than one product model is produced in an inter-mixed sequence. The main characteristics of the lexicographic bottleneck mixed-model assembly line balancing problem are described with numerical examples. Another contribution of the study is the methodology used to deal with the complex structure of the problem. Two effective meta-heuristic approaches, namely artificial bee colony and tabu search, are proposed. The parameters of the proposed meta-heuristics are optimised using response surface methodology, which is a well-known design of experiments technique, as a unique contribution to the expert and intelligent systems literature. Different from the common tendency in the literature (which aims to optimise one parameter at a time), all parameters are optimised simultaneously. Therefore, it is shown how a complex production planning problem can be solved using sophisticated artificial intelligence techniques with optimised parameters. The methodology used for parameter setting can be applied to other metaheuristics for solving complex problems in practice. The performances of both algorithms are assessed using well-known test problems and it is observed that both algorithms find promising solutions. Artificial bee colony algorithm outperforms tabu search in minimising the number of workstations while tabu search shows a better performance in minimising the value of lexicographic bottleneck objective function.     

Deep ensemble learning with non-equivalent costs of fault severities for rolling bearing diagnostics

Effective fault diagnostics on rolling bearings is vital to ensuring safe and reliable operations of industrial equipment. In recent years, enabled by Machine Learning (ML) algorithms, data-based fault diagnostics approaches have been steadily developed as promising solutions to support industries. However, each ML algorithm exhibits some shortcomings limiting its applicability in practice. To tackle this issue, in this paper, Deep Learning (DL) and Ensemble Learning (EL) algorithms are integrated as a novel Deep Ensemble Learning (DEL) approach. In the DEL approach, the training requirements for the DL algorithm are alleviated, and the accuracy for fault condition classifications is enhanced by the EL algorithm. The DEL approach is comprised of the following critical steps: (i) Convolutional Neural Networks (CNNs) are constructed to pre-process vibration signals of rolling bearings to extract fault-related preliminary features efficiently; (ii) decision trees are designed to optimise the extracted features by quantifying their importance contributing to the faults of rolling bearings; (iii) the EL algorithm, which is enabled by a Gradient Boosting Decision Tree (GBDT) algorithm and a Non-equivalent Cost Logistic Regression (NCLR) algorithm, is developed for fault condition classifications with optimised non-equivalent costs assigned to different fault severities. Case studies demonstrate that the DEL approach is superior to some other comparative ML approaches. The industrial applicability of the DEL approach is showcased via the case studies and analyses.     

Computing performance requirements for web service compositions

In order to produce service compositions, modern web applications now combine both in-house and third-party web services. Therefore, their performance depends on the performance of the services that they integrate. At early stages, it may be hard to quantify the performance demanded from the services to meet the requirements of the application, as some services may not be available or may not provide performance guarantees. The authors present several algorithms that compute the required performance for each service from a model of a service composition at an early stage of development. This is also helpful when testing service compositions and selecting candidate web services, enabling performance-driven recommendation systems for web services that could be integrated into service discovery. Domain experts can annotate the model to include partial knowledge on the expected performance of the services. We develop a throughput computation algorithm and two time limit computation algorithms operating on such a model: a baseline algorithm, based on linear programming, and an optimised graph-based algorithm. We conduct theoretical and empirical evaluations of their performance and capabilities on a large sample of models of several classes. Results show that the algorithms can provide an estimation of the performance required by each service, and that the throughput computation algorithm and the graph-based time limit computation algorithm show good performance even in models with many paths.     

Reinforcement learning for parameter estimation in statistical spoken dialogue systems

Reinforcement techniques have been successfully used to maximise the expected cumulative reward of statistical dialogue systems. Typically, reinforcement learning is used to estimate the parameters of a dialogue policy which selects the system's responses based on the inferred dialogue state. However, the inference of the dialogue state itself depends on a dialogue model which describes the expected behaviour of a user when interacting with the system. Ideally the parameters of this dialogue model should be also optimised to maximise the expected cumulative reward.This article presents two novel reinforcement algorithms for learning the parameters of a dialogue model. First, the Natural Belief Critic algorithm is designed to optimise the model parameters while the policy is kept fixed. This algorithm is suitable, for example, in systems using a handcrafted policy, perhaps prescribed by other design considerations. Second, the Natural Actor and Belief Critic algorithm jointly optimises both the model and the policy parameters. The algorithms are evaluated on a statistical dialogue system modelled as a Partially Observable Markov Decision Process in a tourist information domain. The evaluation is performed with a user simulator and with real users. The experiments indicate that model parameters estimated to maximise the expected reward function provide improved performance compared to the baseline handcrafted parameters.     

Genetic algorithm design of neural network and fuzzy logic controllers

This paper discusses the design of neural network and fuzzy logic controllers using genetic algorithms, for real-time control of flows in sewerage networks. The soft controllers operate in a critical control range, with a simple set-point strategy governing “easy” cases. The genetic algorithm designs controllers and set-points by repeated application of a simulator. A comparison between neural network, fuzzy logic and benchmark controller performance is presented. Global and local control strategies are compared. Methods to reduce execution time of the genetic algorithm, including the use of a Tabu algorithm for training data selection, are also discussed. The results indicate that local control is superior to global control, and that the genetic algorithm design of soft controllers is feasible even for complex flow systems of a realistic scale. Neural network and fuzzy logic controllers have comparable performance, although neural networks can be successfully optimised more consistently.     

A Java Card CAP converter in PVS

The Java Card language is a trimmed down dialect of Java aimed at programming smart cards. Java Card specifies its own class file format (the Java Card Converted APplet (CAP) format) that is optimised with respect to the limited space resources of smart cards. This paper deals with the certified development of algorithms necessary for the conversion of ordinary Java class files into the CAP format. More precisely, these algorithms are concerned with constructing and compressing method tables and constant pools. The main contribution of this paper is to specify and prove the correctness of these algorithms using the theorem prover PVS.     

Landmark-based music recognition system optimisation using genetic algorithms

Audio fingerprinting allows us to label an unidentified music fragment within a previously generated database. The use of spectral landmarks aims to obtain a robustness that lets a certain level of noise be present in the audio query. This group of audio identification algorithms holds several configuration parameters whose values are usually chosen based upon the researcher’s knowledge, previous published experimentation or just trial and error methods. In this paper we describe the whole optimisation process of a Landmark-based Music Recognition System using genetic algorithms. We define the actual structure of the algorithm as a chromosome by transforming its high relevant parameters into various genes and building up an appropriate fitness evaluation method. The optimised output parameters are used to set up a complete system that is compared with a non-optimised one by designing an unbiased evaluation model.     

A Pareto biogeography-based optimisation for multi-objective two-sided assembly line sequencing problems with a learning effect

This research presents a Pareto biogeography-based optimisation (BBO) approach to mixed-model sequencing problems on a two-sided assembly line where a learning effect is also taken into consideration. Three objectives which typically conflict with each other are optimised simultaneously comprising minimising the variance of production rate, minimising the total utility work and minimising the total sequence-dependent setup time. In order to enhance the exploration and exploitation capabilities of the algorithm, an adaptive mechanism is embedded into the structure of the original BBO, called the adaptive BBO algorithm (A-BBO). A-BBO monitors a progressive convergence metric in every certain generation and then based on this data it will decide whether to adjust its adaptive parameters to be used in the next certain generations or not. The results demonstrate that A-BBO outperforms all comparative algorithms in terms of solution quality with indifferent solution diversification.     

基于IBEA的低轨区域覆盖星座优化设计

将一款收敛性能优越的多目标优化算法IBEA应用到低轨区域覆盖星座优化设计中,并利用STK对优化出的星座方案进行了仿真验证。结果表明IBEA对于求解低轨区域覆盖星座的优化设计问题是有效的,它可以优化出覆盖性能良好的星座方案。     

基于优化Daugman算法的出租车标志定位

针对传统的Hough变换算法定位圆状目标时易受到干扰,效果不佳,导致定位出现较大偏差的问题,提出了一种基于优化的Daugman算法的定位方法来实现对于出租车标志定位.该算法引进一种优化的Daugnum算子并使用阈值经验以提高出租车标志判断与定位的精确度.实验表明,使用该算法判断与定位出租车标志准确且抗干扰性强,从而能有效地定位出租车标志.     

Empirical analysis of five nature-inspired algorithms on real parameter optimization problems

In the past few years nature-inspired algorithms are seen as potential tools to solve computationally hard problems. Tremendous success of these algorithms in providing near optimal solutions has inspired the researchers to develop new algorithms. However, very limited efforts have been made to identify the best algorithms for diverse classes of problems. This work attempts to assess the efficacy of five contemporary nature-inspired algorithms i.e. bat algorithm (BA), artificial bee colony algorithm (ABC), cuckoo search algorithm (CS), firefly algorithm (FA) and flower pollination algorithm (FPA). The work evaluates the performance of these algorithms on CEC2014 30 benchmark functions which include unimodal, multimodal, hybrid and composite problems over 10, 30, 50 and 100 dimensions. Control parameters of all algorithms are self-adapted so as to obtain best results over benchmark functions. The algorithms have been evaluated along three perspectives (a) statistical significance using Wilcoxon rank sum test (b) computational time complexity (c) convergence rate of algorithms. Experimental results and analysis revealed that ABC algorithm perform best for majority of the problems on high dimension, while on small dimension, CS is the best choice. FPA attain the next best position follow by BA and FA for all kinds of functions. Self adaptation of above algorithms also revealed the best values of input parameters for various algorithms. This study may aid experts and scientists of computational intelligence to solve intricate optimization problems.     

Which algorithm should I choose: An evolutionary algorithm portfolio approach

Many good evolutionary algorithms have been proposed in the past. However, frequently, the question arises that given a problem, one is at a loss of which algorithm to choose. In this paper, we propose a novel algorithm portfolio approach to address the above problem for single objective optimization. A portfolio of evolutionary algorithms is first formed. Covariance Matrix Adaptation Evolution Strategy (CMA-ES), History driven Evolutionary Algorithm (HdEA), Particle Swarm Optimization (PSO2011) and Self adaptive Differential Evolution (SaDE) are chosen as component algorithms. Each algorithm runs independently with no information exchange. At any point in time, the algorithm with the best predicted performance is run for one generation, after which the performance is predicted again. The best algorithm runs for the next generation, and the process goes on. In this way, algorithms switch automatically as a function of the computational budget. This novel algorithm is named Multiple Evolutionary Algorithm (MultiEA). The predictor we introduced has the nice property of being parameter-less, and algorithms switch automatically as a function of budget. The following contributions are made: (1) experimental results on 24 benchmark functions show that MultiEA outperforms (i) Multialgorithm Genetically Adaptive Method for Single Objective Optimization (AMALGAM-SO); (ii) Population-based Algorithm Portfolio (PAP); (iii) a multiple algorithm approach which chooses an algorithm randomly (RandEA); and (iv) a multiple algorithm approach which divides the computational budget evenly and execute all algorithms in parallel (ExhEA). This shows that it outperforms existing portfolio approaches and the predictor is functioning well. (2) Moreover, a neck to neck comparison of MultiEA with CMA-ES, HdEA, PSO2011, and SaDE is also made. Experimental results show that the performance of MultiEA is very competitive. In particular, MultiEA, being a portfolio algorithm, is sometimes even better than all its individual algorithms, and has more robust performance. (3) Furthermore, a positive synergic effect is discovered, namely, MultiEA can sometimes perform better than the sum of its individual EAs. This gives interesting insights into why an algorithm portfolio is a good approach. (4) It is found that MultiEA scales as well as the best algorithm in the portfolio. This suggests that MultiEA scales up nicely, which is a desirable algorithmic feature. (5) Finally, the performance of MultiEA is investigated on a real world problem. It is found that MultiEA can select the most suitable algorithm for the problem and is much better than choosing algorithms randomly.     

Explicit nonlinear dynamic finite element analysis on homogeneous/heterogeneous parallel computing environment

This paper presents parallel computational strategies to implement explicit nonlinear finite element analysis code onto distributed memory parallel computers for solving large-scale problems in structural dynamics. Implementation details on both homogeneous and heterogeneous parallel processing environments are considered in detail in this paper. Implementation of an explicit nonlinear finite element dynamic analysis code on homogeneous systems is discussed first and this is later moved onto heterogeneous systems. Domain decomposition with explicit message passing is preferred for parallel implementation. The message passing implementation in the parallel algorithm is based on MPI (Message Passing Interface) libraries. Implementation aspects of overlapped, non-overlapped domain decomposition techniques, Dynamic Task Allocation (DTA) and clustering techniques for DTA and their relative merits are presented. The interprocessor communications are optimised by overlapping with computations to improve the performance of the domain decomposition based explicit dynamic analysis finite element code.The issues related to implementation of finite element code for nonlinear dynamic analysis on heterogeneous parallel computing environment are later presented. A new dynamic load-balancing algorithm is developed for this purpose and it is integrated with the domain decomposition based parallel explicit finite element code to test our algorithms on a coarse grain heterogeneous cluster of workstations. Numerical experiments have been carried out on PARAM-10000, an Indian parallel computer and also on cluster of Unix workstations.     

面向龙芯平台的快速DCT算法及其实现

针对龙芯2E平台不能流畅播放视频文件的问题,对视频变换过程进行优化,采用一种新的离散余弦变换（DCT）算法,基于龙芯2E多媒体指令集对其进行实现,用该算法替代FFmpeg软件中的DCT算法。测试结果表明,新的DCT算法性能比传统DCT算法提高近11倍,优化后的FFmpeg软件编码速度提高10％左右。     

A combined heuristic optimization technique

Realistic problems of structural optimization are characterized by non-linearity, non-convexity and by continuous and/or discrete design variables. There are non-linear dependencies between the optimised parameters. Real-world problems are rarely decomposable or separable. In this contribution a combined heuristic algorithm is described which is well suited for problems, for which the application-requirements of gradient-based algorithms are not fulfilled. The present contribution describes a combination of the Threshold Accepting Algorithm with Differential Evolution with particular emphasis on structural optimization, it can be classified as a Hybrid Evolutionary Algorithm. The Threshold Accepting Algorithm is similar to Simulated Annealing. Differential Evolution is based on Genetic Algorithms.