Skip to main content
main-content

Über dieses Buch

The two-volume set (LNCS 6728 and 6729) constitutes the refereed
proceedings of the International Conference on Swarm Intelligence, ICSI
2011, held in Chongqing, China, in June 2011.

The 143 revised full papers presented were carefully reviewed and selected from 298 submissions. The papers are organized in topical sections on theoretical analysis of swarm intelligence algorithms, particle swarm optimization, applications of pso algorithms, ant colony optimization algorithms, bee colony algorithms, novel swarm-based optimization algorithms, artificial immune system, differential evolution, neural networks, genetic algorithms, evolutionary computation, fuzzy methods, and hybrid algorithms - for part I.

Topics addressed in part II are such as multi-objective optimization algorithms, multi-robot, swarm-robot, and multi-agent systems, data mining methods, machine learning methods, feature selection algorithms, pattern recognition methods, intelligent control, other optimization algorithms and applications, data fusion and swarm intelligence, as well as fish school search - foundations and applications.

Inhaltsverzeichnis

Frontmatter

Multi-Objective Optimization Algorithms

Multi-Objective Optimization for Dynamic Single-Machine Scheduling

In this paper, a multi-objective evolutionary algorithm based on gene expression programming (MOGEP) is proposed to construct scheduling rules (SRs) for dynamic single-machine scheduling problem (DSMSP) with job release dates. In MOGEP a fitness assignment scheme, diversity maintaining strategy and elitist strategy are incorporated on the basis of original GEP. Results of simulation experiments show that the MOGEP can construct effective SRs which contribute to optimizing multiple scheduling measures simultaneously.

Li Nie, Liang Gao, Peigen Li, Xiaojuan Wang

Research of Pareto-Based Multi-Objective Optimization for Multi-Vehicle Assignment Problem Based on MOPSO

The purpose of a multi-vehicle assignment problem is to allocate vehicles to complete various missions at different destinations, meanwhile it is required to satisfy all constrains and optimize overall criteria. Combined with MOPSO algorithm, a Pareto-based multi-objective model is proposed, which includes not only the time-cost tradeoff, but also a “Constraint-First-Objective-Next” strategy which handles constraints as an additional objective. Numerical experimental results illustrate that it can efficiently achieve the Pareto front and demonstrate the effectiveness.

Ai Di-Ming, Zhang Zhe, Zhang Rui, Pan Feng

Correlative Particle Swarm Optimization for Multi-objective Problems

Particle swarm optimization (PSO) has been applied to multi-objective problems. However, PSO may easily get trapped in the local optima when solving complex problems. In order to improve convergence and diversity of solutions, a correlative particle swarm optimization (CPSO) with disturbance operation is proposed, named MO-CPSO, for dealing with multi-objective problems. MO-CPSO adopts the correlative processing strategy to maintain population diversity, and introduces a disturbance operation to the non-dominated particles for improving convergence accuracy of solutions. Experiments were conducted on multi-objective benchmark problems. The experimental results showed that MO-CPSO operates better in convergence metric and diversity metric than three other related works.

Yuanxia Shen, Guoyin Wang, Qun Liu

A PSO-Based Hybrid Multi-Objective Algorithm for Multi-Objective Optimization Problems

This paper proposes a PSO-based hybrid multi-objective algorithm (HMOPSO) with the following three main features. First, the HMOPSO takes the crossover operator of the genetic algorithm as the particle updating strategy. Second, a propagating mechanism is adopted to propagate the non-dominated archive. Third, a local search heuristic based on scatter search is applied to improve the non-dominated solutions. Computational study shows that the HMOPSO is competitive with previous multi-objective algorithms in literature.

Xianpeng Wang, Lixin Tang

The Properties of Birandom Multiobjective Programming Problems

This paper is devoted to the multiobjective programming problem based on the birandom theory. We first propose the birandom multiobjective programming (BRMOP) problem and its expected value model. Then we present the concepts of non-inferior solution, called expected-value efficient solutions and expected-value wake efficient solutions, and their properties are also discussed. The results obtained in this paper can provide theoretical basis for designing algorithms to solve the BRMOP problem.

Yongguo Zhang, Yayi Xu, Mingfa Zheng, Liu Ningning

A Modified Multi-objective Binary Particle Swarm Optimization Algorithm

In recent years a number of works have been done to extend Particle Swarm Optimization (PSO) to solve multi-objective optimization problems, but a few of them can be used to tackle binary-coded problems. In this paper, a novel modified multi-objective binary PSO (MMBPSO) algorithm is proposed for the better multi-objective optimization performance. A modified updating strategy is developed which is simpler and easier to implement compared with standard discrete binary PSO. The mutation operator and dissipation operator are introduced to improve the search ability and keep the diversity of algorithm. The experimental results on a set of multi-objective benchmark functions demonstrate that the proposed MBBPSO is a competitive multi-objective optimizer and outperforms the standard binary PSO algorithm in terms of convergence and diversity.

Ling Wang, Wei Ye, Xiping Fu, Muhammad Ilyas Menhas

Improved Multiobjective Particle Swarm Optimization for Environmental/Economic Dispatch Problem in Power System

An improved particle swarm optimization based on cultural algorithm is proposed to solve environmental/economic dispatch (EED) problem in power system. Population space evolves with the improved particle swarm optimization strategy. Three kinds of knowledge in belief space, named situational, normative and history knowledge are redefined respectively to accordance with the solution of multi-objective problem. The results of standard test systems demonstrate the superiority of the proposed algorithm in terms of the diversity and uniformity of the Pareto-optimal solutions obtained.

Yali Wu, Liqing Xu, Jingqian Xue

A New Multi-Objective Particle Swarm Optimization Algorithm for Strategic Planning of Equipment Maintenance

Maintenance planning plays a key role in equipment operational management, and strategic equipment maintenance planning (SEML) is an integrated and complicated optimization problem consisting of more than one objectives and constraints. In this paper we present a new multi-objective particle swarm optimization (PSO) algorithm for effectively solving the SEML problem model whose objectives include minimizing maintenance cost and maximizing expected mission capability of military equipment systems. Our algorithm employs an objective leverage function for global best selection, and preserves the diversity of non-dominated solutions based on the measurement of minimum pairwise distance. Experimental results show that our approach can achieve good solution quality with low computational costs to support effective decision-making.

Haifeng Ling, Yujun Zheng, Ziqiu Zhang, Xianzhong Zhou

Multiobjective Optimization for Nurse Scheduling

It is laborious to determine nurse scheduling using human-involved manner in order to account for administrative operations, business benefits, and nurse requests. To solve this problem, a mathematical formulation is proposed where the hospital administrators can set multiple objectives and stipulate a set of scheduling constraints. We then present a multiobjective optimization method based on the cyber swarm algorithm (CSA) to solve the nurse scheduling problem. The proposed method incorporates salient features from particle swarm optimization, adaptive memory programming, and scatter search to create benefit from synergy. Two simulation problems are used to evaluate the performance of the proposed method. The experimental results manifest that the proposed method outperforms NSGA II and MOPSO in terms of convergence and diversity performance measures of the produced results.

Peng-Yeng Yin, Chih-Chiang Chao, Ya-Tzu Chiang

A Multi-Objective Binary Harmony Search Algorithm

Harmony Search (HS) is an emerging meta-heuristic optimization method and has been used to tackle various optimization problems successfully. However, the research of multi-objectives HS just begins and no work on binary multi-objectives HS has been reported. This paper presents a multi-objective binary harmony search algorithm (MBHS) for tackling binary-coded multi-objective optimization problems. A modified pitch adjustment operator is used to improve the search ability of MBHS. In addition, the non-dominated sorting based crowding distance is adopted to evaluate the solution and update the harmony memory to maintain the diversity of algorithm. Finally the performance of the proposed MBHS was compared with NSGA-II on multi-objective benchmark functions. The experimental results show that MBHS outperform NSGA-II in terms of the convergence metric and the diversity metric.

Ling Wang, Yunfei Mao, Qun Niu, Minrui Fei

Multi-robot, Swarm-robot, and Multi-agent Systems

A Self-organized Approach to Collaborative Handling of Multi-robot Systems

The purpose of this paper is to develop a general self-organized approach to multi-robot’s collaborative handling problem. Firstly, an autonomous motion planning graph (AMP-graph) is described for individual movement representations. An individual autonomous motion rule (IAM-rule) based on “free-loose” and “well-distributed load-bearing” preferences is presented. By establishing the simple and effective individual rule model, an ideal handling formation can be formed by each robot moving autonomously under their respective preferences. Finally, the simulations show that both the AMP-graph and the IAM-rule are valid and feasible. On this basis, the self-organized approach to collaborative hunting and handling with obstacle avoidance of multi-robot systems can be further analyzed effectively.

Tian-yun Huang, Xue-bo Chen, Wang-bao Xu, Wei Wang

An Enhanced Formation of Multi-robot Based on A* Algorithm for Data Relay Transmission

This paper presents a formation control method of multi-robot based on A* algorithm for data relay transmission. In our system, we choose Nanotron sensor and compass sensor to execute the tasks of distance measurement, communication and obtaining moving direction. Since there exists data disturbance from Nanotron sensor when there is an obstacle between two robots. Therefore, we embed path planning algorithm information control. The leader robot (LR) knows the whole information of environment, and sends its moving information and corner information as a node to FRs. The FRs regard the node information which received from LR as temporary target to increase the efficiency of multi-robot formation by optimal path. From the simulations and experiments, we will show desirable results of our method.

Zhiguang Xu, Kyung-Sik Choi, Yoon-Gu Kim, Jinung An, Suk-Gyu Lee

WPAN Communication Distance Expansion Method Based on Multi-robot Cooperation Navigation

Over the past decade, an increasing number of researches and developments for personal or professional service robots are attracting considerable attention and interest in industry and academia. Furthermore, the development of intelligent robots is strongly promoted as a strategic industry. To date, most of the practical and commercial service robots are controlled remotely. The most important technical issue of remote control is wireless communication, especially in indoor and unstructured environments where communication infrastructure may be hampered. Therefore, we propose a multi-robot cooperation navigation method for securing the communication distance extension of the remote control based on wireless personal area networks (WPANs). The concept and implementation of following navigation are introduced, and performance verification is carried out through navigation experiments in real or test-bed environments.

Yoon-Gu Kim, Jinung An, Kyoung-Dong Kim, Zhi-Guang Xu, Suk-Gyu Lee

Relative State Modeling Based Distributed Receding Horizon Formation Control of Multiple Robot Systems

Receding horizon control has been shown as a good method in multiple robot formation control problem. However, there are still two disadvantages in almost all receding horizon formation control (RHFC) algorithms. One of them is the huge computational burden due to the complicated nonlinear dynamical optimization, and the other is that most RHFC algorithms use the absolute states directly while relative states between two robots are more accurate and easier to be measured in many applications. Thus, in this paper, a new relative state modeling based distributed RHFC algorithm is designed to solve the two problems referred to above. Firstly, a simple strategy to modeling the dynamical process of the relative states is given; Subsequently, the distributed RHFC algorithm is introduced and the convergence is ensured by some extra constraints; Finally, formation control simulation with respect to three ground robots is conducted and the results show the improvement of the new given algorithm in the real time capability and the insensitiveness to the measurement noise.

Wang Zheng, He Yuqing, Han Jianda

Simulation and Experiments of the Simultaneous Self-assembly for Modular Swarm Robots

In our previous work, we have proposed a distributed self-assembly method based on Sambot platform. But there have interference of the infrared sensors between multiple Sambots. In this paper, two interference problems with multiple DSAs are solved and a novel simultaneous self-assembly method is proposed to enhance the efficiency of the self-assembly of modular swarm robots. Meanwhile, the simulation platform is established; some simulation experiments for various configurations are made and the results are analyzed for finding out evidence for further improvement. The simulation and physical experiment results verify the effectiveness and scalability of the simultaneous self-assembly algorithm which is more effective to shorten the assembly time.

Hongxing Wei, Yizhou Huang, Haiyuan Li, Jindong Tan

Impulsive Consensus in Networks of Multi-agent Systems with Any Communication Delays

This paper considers consensus problem in directed networks of dynamic agents having communication delays. Based on impulsive control theory on delayed dynamical systems, a simple impulsive consensus protocol for such networks is proposed, and a generic criterion for solving the average consensus problem is analytically derived. Compared with some existing works, a distinctive feature of this work is to address average consensus problem for networks with any communication delays. It is shown that the impulsive gain matrix in the proposed protocol play a key role in seeking average consensus problems. Simulations are presented that are consistent with our theoretical results.

Quanjun Wu, Li Xu, Hua Zhang, Jin Zhou

Data Mining Methods

FDClust: A New Bio-Inspired Divisive Clustering Algorithm

Clustering with bio-inspired algorithms is emerging as an alternative to more conventional clustering techniques. In this paper, we propose a new bio-inspired divisive clustering algorithm FDClust (Artificial Fish based Divisive Clustering algorithm). FDClust takes inspiration from the social organization and the encounters of fish shoals. In this algorithm, each artificial fish (agents) is identified with one object to be clustered. Agents move randomly on the clustering environment and interact with neighboring agents in order to adjust their movement directions. Two Groups of similar objects will appear through the movement of agents in the same direction. The algorithm is tested and evaluated on several real benchmark databases. The obtained results are very interesting in comparison with Kmeans, Slink, Alink, Clink and Diana algorithms.

Besma Khereddine, Mariem Gzara

Mining Class Association Rules from Dynamic Class Coupling Data to Measure Class Reusability Pattern

The increasing use of reusable components during the process of software development in the recent times has motivated the researchers to pay more attention to the measurement of reusability. There is a tremendous scope of using various data mining techniques in identifying set of software components having more dependency amongst each other, making each of them less reusable in isolation. For object-oriented development paradigm, class coupling has been already identified as the most important parameter affecting reusability. In this paper an attempt has been made to identify the group of classes having dependency amongst each other and also being independent from rest of the classes existing in the same repository. The concepts of data mining have been used to discover patterns of reusable classes in a particular application. The paper proposes a three step approach to discover class associations rules for Java applications to identify set of classes that should be reused in combination. Firstly dynamic analysis of the Java application under consideration is performed using UML diagrams to compute class import coupling measure. Then in the second step, for each class these collected measures are represented as Class_Set & binary Class_Vector. Finally the third step uses apriori (association rule mining) algorithm to generate Class Associations Rules (CAR’s) between classes. The proposed approach has been applied on sample Java programs and our study indicates that these CAR’s can assist the developers in the proper identification of reusable classes by discovering frequent class association patterns.

Anshu Parashar, Jitender Kumar Chhabra

An Algorithm of Constraint Frequent Neighboring Class Sets Mining Based on Separating Support Items

For the reasons that present constraint frequent neighboring class sets mining algorithms need generate candidate frequent neighboring class sets and have a lot of repeated computing, and so this paper proposes an algorithm of constraint frequent neighboring class sets mining based on separating support items, which is suitable for mining frequent neighboring class sets with constraint class set in large spatial database. The algorithm uses the method of separating support items to gain support of neighboring class sets, and uses up search to extract frequent neighboring class sets with constraint class set. In the course of mining frequent neighboring class sets, the algorithm only need scan once database, and it need not generate candidate frequent neighboring class sets with constraint class set. By these methods the algorithm reduces more repeated computing to improve mining efficiency. The result of experiment indicates that the algorithm is faster and more efficient than present mining algorithms when extracting frequent neighboring class sets with constraint class set in large spatial database.

Gang Fang, Jiang Xiong, Hong Ying, Yong-jian Zhao

A Multi-period Stochastic Production Planning and Sourcing Problem with Discrete Demand Distribution

This paper studies a new class of multi-period stochastic production planning and sourcing problem with minimum risk criteria, in which a manufacturer has a number of plants or subcontractors and has to meet the product demands according to the service levels set by its customers. In the proposed problem, demands are characterized by stochastic variables with known probability distributions. The objective of the problem is to minimize the probability that the total cost exceeds a predetermined maximum allowable cost, where the total cost includes the sum of the inventory holding, setup and production costs in the planning horizon. For general demand distributions, the proposed problem is very complex, so we cannot solve it by conventional optimization methods. To avoid this difficulty, we assume the demands have finite discrete distributions, and derive the crisp equivalent forms of both probability objective function and the probability level constraints. As a consequence, we turn the original stochastic production planning problem into its equivalent integer programming one so that the branch-and-bound method can be used to solve it. Finally, to demonstrate the developed modeling idea, we perform some numerical experiments via one 3-product source, 8-period production planning problem.

Weili Chen, Yankui Liu, Xiaoli Wu

Exploration of Rough Sets Analysis in Real-World Examination Timetabling Problem Instances

The examination timetabling problem is widely studied and a major activity for academic institutions. In real world cases, an increasing number of student enrolments, variety of courses throw in the growing challenge in the research with a wider range of constraints. Many optimization problems are concerned with the best feasible solution with minimum execution time of algorithms. The aim of this paper is to propose rough sets methods to investigate the Carter datasets. Two rough sets (RS) approaches are used for the data analysis. Firstly, the discretization process

(DP)

returns a partition of the value sets into intervals. Secondly the rough sets Boolean reasoning

(RSBR)

achieves the best decision table on the large data instances. The rough sets classified datasets are experimented with an examination scheduler. The improvements of the solutions on Car-s-91 and Car-f-91 datasets are reported.

J. Joshua Thomas, Ahamad Tajudin Khader, Bahari Belaton, Amy Leow

Community Detection in Sample Networks Generated from Gaussian Mixture Model

Detecting communities in complex networks is of great importance in sociology, biology and computer science, disciplines where systems are often represented as networks. In this paper, we use the coarse-grained-diffusion-distance based agglomerative algorithm to uncover the community structure exhibited by sample networks generated from Gaussian mixture model, in which the connectivity of the network is induced by a metric. The present algorithm can identify the community structure in a high degree of efficiency and accuracy. An appropriate number of communities can be automatically determined without any prior knowledge about the community structure. The computational results on three artificial networks confirm the capability of the algorithm.

Ling Zhao, Tingzhan Liu, Jian Liu

Efficient Reduction of the Number of Associations Rules Using Fuzzy Clustering on the Data

In this paper, we are interested in the knowledge discovery methods. The major inconveniences of these methods are: i) the generation of a big number of association rules that are not easily assimilated by the human brain ii) the space memory and the time execution necessary for the management of their data structures. To cure this problem, we propose to build rules (meta-rules) between groups (or clusters) resulting from a preliminary fuzzy clustering on the data. We prove that we can easily deduce knowledge about the initial data set if we want more details. This solution reduced considerably the number of generated rules, offered a better interpretation of the data and optimized both the space memory and the execution time. This approach is extensible; the user is able to choose the fuzzy clustering or the extraction rules algorithm according to the domain of his data and his needs.

Amel Grissa Touzi, Aicha Thabet, Minyar Sassi

A Localization Algorithm in Wireless Sensor Networks Based on PSO

Node localization is a fundamental and important technology in wireless sensor networks. In this paper, a localization algorithm in wireless sensor networks based on PSO is proposed. Unlike most of the existing location algorithm, the proposed algorithm figures out the rectangular estimation range of unknown node by bounding box algorithm and takes one value as the estimated coordinates of this node, then it has been optimized by PSO, so got the more precise location of unknown nodes. Simulation results show that this optimized algorithm outperforms traditional bounding box on the positioning accuracy and localization error.

Hui Li, Shengwu Xiong, Yi Liu, Jialiang Kou, Pengfei Duan

Game Theoretic Approach in Routing Protocol for Cooperative Wireless Sensor Networks

A game theoretic method, called the first price sealed auction game, was introduced to control routing overhead in wireless sensor networks in this paper. The players of the game are the wireless nodes with set of strategies (forward or not). The game is played whenever an arbitrary node in the network forwards packets. In order for the game to function, a multi-stage pricing game model is established, this provides the probability that the wireless nodes forward the receiving packets, and the payoff of all nodes can be optimize through choosing the best neighbour node. The simulations in NS2 showed that the pricing routing game model improves performance, not only decreasing the energy consumption, but also prolonging network life time. Finally the numerical analysis about nodes’ payoff is given through Matlab.

Qun Liu, Xingping Xian, Tao Wu

Machine Learning Methods

A New Collaborative Filtering Recommendation Approach Based on Naive Bayesian Method

Recommendation is a popular and hot problem in e-commerce. Recommendation systems are realized in many ways such as content-based recommendation, collaborative filtering recommendation, and hybrid approach recommendation. In this article, a new collaborative filtering recommendation algorithm based on naive Bayesian method is proposed. Unlike original naive Bayesian method, the new algorithm can be applied to instances where conditional independence assumption is not obeyed strictly. According to our experiment, the new recommendation algorithm has a better performance than many existing algorithms including the popular k-NN algorithm used by Amazon.com especially at long length recommendation.

Kebin Wang, Ying Tan

Statistical Approach for Calculating the Energy Consumption by Cell Phones

Energy consumption by cell phones has great effect on energy crisis. Calculating and optimizing the method of service that provided by the cell phone is essential. In our solution, we build up three main models. Transition model reflects the relationship between the change of energy and time; next we give the function of energy consumption during the steady state. Optimization approach structures the function of energy consumption and constructs the function with convenience degree to emphasize the convenience of cell phones. Using waste model we obtain the waste functions under different situations and get the total waste energy.

Shanchen Pang, Zhonglei Yu

Comparison of Ensemble Classifiers in Extracting Synonymous Chinese Transliteration Pairs from Web

There is no transliteration standard across all Chinese language regions, including China, Hong Kong, and Taiwan, and variations in Chinese transliteration have thus arisen in the process of transliterating foreign languages (English, for instance) into the Chinese language. In this paper, we compare several ensemble classifiers in confirminga pair, that is, a transliteration and another term, whether it is synonymous. We construct a new confirmation framework to confirm whether a pair of a Chinese transliteration and another Chinese term is synonymous. The presented framework is applied to extract synonymous transliteration pairs from a real-world Web corpus; this is valuable to build a new database of synonymous transliterations or support search engines so that they can return much more complete documents as Web search results to increase the usages in practice.Experiments show that our integrated confirmation framework is effective and robust in confirming and extracting pairs of Chinese transliteration following the collection of synonymous transliterations from the Web corpus.

Chien-Hsing Chen, Chung-Chian Hsu

Combining Classifiers by Particle Swarms with Local Search

Weighted combination model with appropriate weight vector is very effective in multiple classifier systems. We presented a method for determining the weight vector by particle swarm optimization in our previous work, which called PSO-WCM. A weighted combination model, PSO-LS-WCM, was proposed in this paper to improve the classification performance further, which obtained the weighted vector by particle swarm optimization with local search. We describe the algorithm of PSO-LS-WCM in detail. Seven real-world problems from UCI Machine Learning Repository were used in experiments to justify the validity of the approach. It was shown that PSO-LS-WCM is better than PSO-WCM and the other six combination methods in literature.

Liying Yang

An Expert System Based on Analytical Hierarchy Process for Diabetes Risk Assessment (DIABRA)

DIABRA (DIABetes Risk Assessment) is a knowledge-based expert system developed to aid individuals to assess their chance for getting Type 2 diabetes. The system core is a quantitative model, implemented by Analytical Hierarchy Process (AHP) mechanism, to evaluate the developed scenarios. The acquired knowledge as scenarios are scored by AHP mechanism and represented in the DIABRA. The validation results show the expert system gives a highly satisfactory performance when compared to human experts. In addition, the computerized system shows additional advantages which can be used as helpful tool to reduce the chance of getting Type 2 diabetes.

Mohammad Reza Amin-Naseri, Najmeh Neshat

Practice of Crowd Evacuating Process Model with Cellular Automata Based on Safety Training

To solve the problem that the crowd evacuating process model with cellular automata is quite different from the reality crowd evacuating process, the crowd evacuating process model with cellular automata based on safety training is addressed. The crowd evacuating process based on safety training is simulated and predicted, and the result is very close to the reality. Using the vertical way to place the shelves gets both a higher escaping rate and a larger shelf area that the total area is up to 216m

2

, and the average death number is 4.2 by safety training when the fire level being 2.

Shi Xi Tang, Ke Ming Tang

Feature Selection Algorithms

Feature Selectionfor Unlabeled Data

Feature selection has been explored extensively for several real-world applications. In this paper, we address a new solution of selecting a subset of original features for unlabeled data. The concept of our feature selection method is referred to a basic characteristic of clustering in thata data instance usually belongs in the same cluster with its geometrically nearest neighbors and belongs to different clusters with its geometrically farthest neighbors. In particular, our method uses instance-based learning for quantifying features in the context of the nearest and the farthest neighbors of every instance, such that using salient features can raise this characteristic. Experiments on several datasets demonstrated the effectiveness of our presented feature selection method.

Chien-Hsing Chen

Feature Selection Algorithm Based on Least Squares Support Vector Machine and Particle Swarm Optimization

A hybrid feature selection algorithm based on least squares support vector machine (LSSVM) and discrete particle swarm optimization is proposed in this paper. The proposed algorithm takes advantage of the easy solving of LSSVM, adopts LSSVM to construct classifier, and use accuracy as the main part of fitness function on the process of particle swarm optimization. The simulation results show that the proposed algorithm could obtain the features which contribute a lot to classifier. Therefore the dimension of data is decreased and the efficiency of classifier is improved.

Song Chuyi, Jiang Jingqing, Wu Chunguo, Liang Yanchun

Unsupervised Local and Global Weighting for Feature Selection

In this paper we will describe a process for selecting relevant features in unsupervised learning paradigms using a new weighted approachs: local weight observation “OBS-SOM”, and global weight observation “GObs-SOM” This new methods are based on the self organizing map (SOM) model and feature weighting. These learning algorithms provide cluster characterization by determining the feature weights within each cluster. We will describe extensive testing using a novel statistical method for unsupervised feature selection. Our approach demonstrates the efficiency and effectiveness of this method in dealing with high dimensional data for simultaneous clustering and weighting. These models are tested on a wide variety of datasets, showing a better performance for new algorithms or classical SOM algorithm. We can also show that through deferent means of visualization, OBS-SOM, and GObs-SOM algorithms provide various pieces of information that could be used in practical applications.

Nadia Mesghouni, Khaled Ghedira, Moncef Temani

Graph-Based Feature Recognition of Line-Like Topographic Map Symbols

Paper-based raster maps are primarily for human consumption. Todays computer services in geoinformatics usually require vectorized topographic maps, while the usual method of the conversion has been an error-prone, manual process.

The system in development separates the recognition of point-like, line-like and surface-like objects, and the most successful approach appears to be the recognition of these objects in a reversed order with respect to their printing. During the recongition of surfaces, homogeneous and textured surfaces must be distinguished. The most diverse and complicated group constitute the line-like objects.

In this article, a possible method of the conversion is discussed for line-like topographic map objects. The results described here are partially implemented in the IRIS project, but further work remains. This emphasizes the tools of digital image processing and knowledge-based approach.

Rudolf Szendrei, István Elek, Mátyás Márton

Automatic Recognition of Topographic Map Symbols Based on Their Textures

The authors’ research goal is to automatize the raster-vector conversion of topographic maps. To accomplish this goal, a software system is currently, under development. It separates the recognition of point-like, line-like and surface-like objects. The first of these three topics is discussed in details in this paper. It is assumed that a topographic map and its vectorized form (possibly in rough form) are given.

In this paper a method is introduced that is able to recognize the point-like symbols of the map and to assign them as attributes to the corresponding polygon of the vectorized map. It means that point-like symbols should not appear as polygons in the vectorized data model. Instead, symbols appear as polygon attributes. The method presented here is also able to “clean” unnecessary polygons of symbols from vectorized map.

This method is implemented by optimized pattern matching on the raster image source of the map, where the symbols are handled as special textures. This method will be improved by using a raw vector model and a set of kernel symbols.

Rudolf Szendrei, István Elek, István Fekete

Using Population Based Algorithms for Initializing Nonnegative Matrix Factorization

The nonnegative matrix factorization (NMF) is a bound-constrained low-rank approximation technique for nonnegative multivariate data. NMF has been studied extensively over the last years, but an important aspect which only has received little attention so far is a proper initialization of the NMF factors in order to achieve a faster error reduction. Since the NMF objective function is usually non-differentiable, discontinuous, and may possess many local minima, heuristic search algorithms are a promising choice as initialization enhancers for NMF.

In this paper we investigate the application of five population based algorithms (genetic algorithms, particle swarm optimization, fish school search, differential evolution, and fireworks algorithm) as new initialization variants for NMF. Experimental evaluation shows that some of them are well suited as initialization enhancers and can reduce the number of NMF iterations needed to achieve a given accuracy. Moreover, we compare the general applicability of these five optimization algorithms for continuous optimization problems, such as the NMF objective function.

Andreas Janecek, Ying Tan

A Kind of Object Level Measuring Method Based on Image Processing

In order to accurately measure level from object to image acquisition devices, this paper put forward a kind of new non-contact level measuring method based on image process and its prototype equipment. Through a series of image preprocessing for captured image such as difference, grayness, binarization and thinness, original image is preferable to measure than before. The relation between image pixel value and tilt angle is acquired via mathematical derivation, as well as the distance formula is gained through fitting function. A large amount of data is gathered in the experiment while error analysis of these results is also offered, in which testified that the measuring method for object distance achieved expected effect.

Xiaoying Wang, Yingge Chen

Pattern Recognition Methods

Fast Human Detection Using a Cascade of United Hogs

Accurate and efficient human detection has become an important area for research in computer vision. In order to solve problems in the past human detection algorithms such as features with fixed sizes, fixed positions and fixed number, we propose the human detection based on united Hogs algorithm. Through intersection tests and feature integration, the algorithm can dynamically generate the features closer to human body contours. Basically maintaining the detection speed, the detection accuracy is improved by our algorithm.

Wenhui Li, Yifeng Lin, Bo Fu

The Analysis of Parameters t and k of LPP on Several Famous Face Databases

The subspace transformation plays an important role in the face recognition. LPP, which is so-called the

Laplacianfaces

, is a very popular manifold subspace transformation for face recognition, and it aims to preserve the local structure of the samples. Recently, many variants of LPP are proposed. LPP is a baseline in their experiments. LPP uses the adjacent graph to preserve the local structure of the samples. In the original version of LPP, the local structure is determined by the parameters

t

(the heat kernel) and

k

(k-nearest neighbors) and directly influences on the performance of LPP. To the best of our knowledge, there is no report on the relation between the performance and these two parameters. The objective of this paper is to reveal this relation on several famous face databases, i.e. ORL, Yale and YaleB.

Sujing Wang, Na Zhang, Mingfang Sun, Chunguang Zhou

Local Block Representation for Face Recognition

Face expression analysis and recognition play an important role in human face emotion perception and social interaction and have therefore attracted much attention in recent years. Semi-Supervised manifold learning has been successfully applied to facial expression recognition by modeling different expressions as a smooth manifold embedded in a high dimensional space. However, the best classification accuracy does not necessarily guarantee as the assumption of double manifold is still arguable. In this paper, we study a family of semi-supervised learning algorithms for aligning different data sets that are characterzied by the same underlying manifold. The generalized framework for modeling and recognizing facial expressions on multiple manifolds is presented. First, we introduce an assumption of one expression one manifold for facial expression recognition. Second, we propose a feasible algorithm for multiple manifold based facial expression recognition. Extensive experiments show the effectiveness of the proposed approach.

Liyuan Jia, Li Huang, Lei Li

Feature Level Fusion of Fingerprint and Finger Vein Biometrics

The aim is to study the fusion at feature extraction level for fingerprint and finger vein biometrics. A novel dynamic weighting matching algorithm based on quality evaluation of interest features is proposed. First, fingerprint and finger vein images are preprocessed by filtering, enhancement, gray-scale normalization and etc. The effective feature point-sets are extracted from two model sources. To handle the problem of curse of dimension, neighborhood elimination and reservation of points belonging to specific regions are implemented, prior and after the feature point-sets fusion. Then, according to the results of features evaluation, dynamic weighting strategy is introduction for the fusion biometrics. Finally, the fused feature point-sets for the database and the query images are matched using point pattern matching and the proposed weight matching algorithm. Experimental results based on FVC2000 and self-constructed finger vein databases show that our scheme can improve verification performance and security significantly.

Kunming Lin, Fengling Han, Yongming Yang, Zulong Zhang

A Research of Reduction Algorithm for Support Vector Machine

Support vector machine is a new field of machine learning. Generalization accuracy and response time are two important criterions of support vector machine used in practical application. It is hoped that it will minimum the number of training dataset and support vectors, simplify the algorithm realization on the condition of keeping classification accuracy. Based on the above consideration, a reduction algorithm combined SVM with KNN algorithm is presented. The experiment results show that the algorithm can reduce the number of training dataset and support vectors on the condition of keeping the classification accuracy of the original training dataset.

Susu Liu, Limin Sun

Fast Support Vector Regression Based on Cut

In general, the similar input data have the similar output target values. A novel Fast Support Vector Regression (FSVR) is proposed on the reduced training set. Firstly, the improved learning machine divides the training data into blocks by using the traditional clustering methods, such as K-mean and FCM clustering techniques. Secondly, the membership function on each block is defined by the corresponding target values of the training data, all the training data have the membership degree falling into the interval [0, 1], which can vary the penalty coefficient by multiplying C. Thirdly, the reduced training set is used to training FSVR, which consists of the data with the membership degrees, which are greater than or equal to the selected suitable parameter

λ

. The experimental results on the traditional machine learning data sets show that the FSVR can not only achieve the better or acceptable performance but also downsize the number of training data and speed up training.

Wenyong Zhou, Yan Xiong, Chang-an Wu, Hongbing Liu

Intelligent Control

Using Genetic Algorithm for Parameter Tuning ON ILC Controller Design

In this project we use the ILC control method to manipulate the robotic arms of a robot with two degrees of freedom. First we implement the dynamic equations of robot according to the Schillings book of robotic. The aforementioned implementation was done in MATLAB SIMULINK environment. The Genetic Algorithm was used for tuning the coefficients of PD Controllers (proportional and derivative gains). Also we use Multi objective genetic Algorithm to attain the coefficients of ILC PD Controllers.

Alireza rezaee, Mohammad jafarpour jalali

Controller Design for a Heat Exchanger in Waste Heat Utilizing Systems

This paper presents a method of designing self-tuning PID controller based on genetic algorithm for an evaporator in an Organic Rankine Cycle system for waste heat recovery. Compared with Ziegler-Nichols PID controller, the self-tuning PID controller can achieve better control performance.

Jianhua Zhang, Wenfang Zhang, Ying Li, Guolian Hou

Test Research on Radiated Susceptibility of Automobile Electronic Control System

Research into the influences of electromagnetic radiation on automobile electronic control system (ECS) is of great significance to improve and enhance its performance under adverse electromagnetic environment. Therefore, an analog device of an ECS of a certain typed automotive engine is devised, a radiated susceptibility (RS) test is conducted, and the results are then analyzed. The test results indicate that the sensitive frequency of this ECS are HF (high frequency) and VHF (very high frequency), and when the field strength of electromagnetic radiation within the sensitive bandwidth grows to a certain degree, there will be signal derangement, signal loss and even damage to the electronic components of the ECS.

Shenghui Yang, Xiangkai Liu, Xiaoyun Yang, Yu Xiao

Forgeability Attack of Two DLP-Base Proxy Blind Signature Schemes

Proxy blind signature is a cryptographical technique and allows a proxy signer to produce a proxy blind signature on behalf of original signer, in such a way that the authority learns nothing about the message that is being signed. The

unforgeability

is an important property of digital signature. In this work, we analyze security of two DLP-based proxy blind signature schemes , and show that the two schemes are insecure. They are universally forgeable, in other words, anyone is able to forge a proxy blind signature on arbitrary a message. And we also analyze the reason to produce such attack. Finally, the corresponding attack is given.

Jianhong Zhang, Fenhong Guo, Zhibin Sun, Jilin Wang

Other Optimization Algorithms and Applications

Key Cutting Algorithm and Its Variants for Unconstrained Optimization Problems

This paper presents the key cutting algorithm and its variants. This algorithm emulates the work of locksmiths to defeat the lock. The best key that matches a given lock is pretended to be an optimal solution of a relevant optimization problem. The basic structure of the key cutting algorithm is as simple as that of genetic algorithms in which a string of binary numbers is employed as a key to open the lock. In this paper, four variants of the predecessor are proposed. The modification is mainly in the key cutting selection. Various criteria of the key cutting probability are added in order to improve the searching speed and the solution convergence. To evaluate their use, four standard test functions are challenged and therefore which satisfactory best solutions obtained from the key cutting variants are compared with those obtained from genetic algorithms. The results confirm the effectiveness of the key cutting and its variants to solve the unconstrained optimization problems.

Uthen Leeton, Thanatchai Kulworawanichpong

Transmitter-Receiver Collaborative-Relay Beamforming by Simulated Annealing

This paper considers the collaborative-relay beamforming (CRBF) design for a three-hop multi-relay network with one transmitter, one receiver and two clusters of relay nodes. It is assumed that, all the relay nodes work synchronously with perfect channel state information (CSI). Optimization on the relay weights is carried out to improve the signal-to-noise ratio (SNR) at the receiver under aggregate power constraints of each cluster. Two different design approaches are proposed in this study. In the first approach, a simulated annealing (SA) based CRBF method is presented, and a stochastic global optimum is obtained. However, the SA algorithm is quite computational demanding. In order to speed up the heuristic searching process, a suboptimal but efficient closed-form solution is provided in the second approach, which helps to generate the initial state of the SA algorithm. Simulation results show that both approaches outperform the fixed power allocation strategy.

Dong Zheng, Ju Liu, Lei Chen, Yuxi Liu, Weidong Guo

Calculation of Quantities of Spare Parts and the Estimation of Availability in the Repaired as Old Models

In this paper, based on the repair as old model under the same storage condition, the quantities of spare parts M for N identical systems is derived on the condition that failures are repaired with probability

P

0

, a special example is given to prove the feasibility. Besides, availability function expression is provided at the same time, and taking system which follows Weibull distribution as the case, the validity of system is shown through calculation.

Zhe Yin, Feng Lin, Yun-fei Guo, Mao-sheng Lai

The Design of the Algorithm of Creating Sudoku Puzzle

Sudoku puzzle is a well-known and logical-based game. To generate some puzzles of varying difficulty with “unique solution” is not so easy. We make a standard of difficulty based on the player’s position, that is, difficulty of solving methods. Then we develop an algorithm to generate puzzles satisfied the requirement. For the complexity of our algorithm, we divide it into two parts. One is the complexity of the algorithm to generate the complete grid. We discover the randomness of generating complete grid increases when the complexity increases, that is, the randomness higher and the complexity greater. We have developed an algorithm which guarantees the most important premise “unique solution” and ensures the complexity is low enough.

Jixian Meng, Xinzhong Lu

Research and Validation of the Smart Power Two-Way Interactive System Based on Unified Communication Technology

Smart power is an important part of smart grid construction, and it directly to the user. The construction of the smart power two-way interactive system related to the realization of intelligent electricity. In this paper, the intelligent electricity network business needs have been analysed first, then the existing communication technologies and the networking architecture have been compared and researched. Following the unified communication technology and selecting the appropriate communication technology, a fused, flexible and reliable communication network architecture program which is based on the OPLC, including power line communications, wireless communications and other communications, has been formed. The program is the basis and guarantee of the system. And the system advances the ability of exchanging information between the user and the grid and promotes the development of intelligent grid.

Jianming Liu, Jiye Wang, Ning Li, Zhenmin Chen

A Micro Wireless Video Transmission System

The paper introduces a micro embedded wireless video transmission system based on WIFI. The system communication is based on C/S structure. Server takes the TI DaVinci technology to process video and uses H.264 for video compression before transmission. Realization of four modules for the server is introduced. All the hardware were designed and made into a micro wireless video transmission server. Furthermore, it realized server and client software. Finally, an experiment was done to test the system. The results show that the system can support real-time wireless video transmission service well.

Yong-ming Yang, Xue-jun Chen, Wei He, Yu-xing Mao

Inclusion Principle for Dynamic Graphs

From the point of view of graph, complex systems can be described by using dynamic graphs. Thus, the correlative theory of dynamic graphs is introduced, and inclusion principle for dynamic graphs is provided. Based on the inclusion principle and permuted transformation, a decomposition method for dynamic graphs is proposed. By using the approach, the graph can be decomposed as a series of pair-wise subgraphs with desired recurrent reverse order in the expanded space of graph. These decoupling pair-wise subgraphs may be designed to have respective controllers or coordinators. It provides us a theoretic framework for decomposition of complex system, and is also convenient for the decentralized control or coordination of complex systems.

Xin-yu Ouyang, Xue-bo Chen

Lie Triple Derivations for the Parabolic Subalgebras of gl(n,R)

Let

R

be a commutative ring with identity,

$\mbox{gl}(n,R)$

the general linear Lie algebra over

R

,

P

a parabolic subalgebra of

$\mbox{gl}(n,R)$

. In this paper, we give an explicit description of Lie triple derivations for the parabolic subalgebra

P

of

$\mbox{gl}(n,R)$

.

Jing Zhao, Hailing Li, Lijing Fang

Non-contact Icing Detection on Helicopter and Experiments Research

The paper puts forward a new non-contact icing detection approach. In this approach, an infra-red laser directly radiates on the frozen surface. Because there are great differences between the absorption rate on the ice and the detected surface, the energy reflected using the photoelectric detector was totally different. The received energy is disposed by the signal process circuit, so that the icing information along the chord of the rotor can be achieved. The method is validated by the experiments using the infrared laser with the wavelength of 1450nm, the influence of the flapping and torque movement of the rotor to the signal amplitude is discussed, and the corresponding measures to reduce the influence of the flapping and torque movement of the rotor is put forward to the icing detection system according to the changing rule of the signal amplitude.

Jie Zhang, Lingyan Li, Wei Chen, Hong Zhang

Research on Decision-Making Simulation of "Gambler’s Fallacy" and "Hot Hand"

The "gambler’s fallacy" and the "hot hand" are considered as typical examples of misunderstanding random chronological events. People have two different expectations on the same historical information: gambler’s fallacy and hot hand. This paper analyzes the occurring numbers of the four effects which are "gambler’s fallacy", "hot hand", "hot outcome" and "stock of luck" and their revenues in a series of random chronological events by describing the decision-making preferences of heterogeneous individuals with the method of computer simulation. We can conclude from the simulation process of coin flips that there are no differences among the occurring numbers and the revenues of these four effects mentioned above. However, they are different when a single period is focused on, which conforms to the beliefs and behavior in the real decision-making situation.

Jianbiao Li, Chaoyang Li, Sai Xu, Xue Ren

An Integration Process Model of Enterprise Information System Families Based on System of Systems

Based on the theory of system of systems (SoS), an integration process model of an enterprise information system family is discussed. The model is stratified into two levels, the top-level sub-processes of SoS and the bottom-level sub-processes of component systems, and the mapping relations between activities in sub-processes are classified as horizontal and vertical, which all contribute to better internal consistency. To support the dynamic integration environment of an enterprise information system family, the model is also designed to be an iterative process. Finally, based on the proposed model, we present an example of an enterprise information system family integration process in an auto industry chain.

Yingbo Wu, Xu Wang, Yun Lin

Special Session on Data Fusion and Swarm Intelligence

A Linear Multisensor PHD Filter Using the Measurement Dimension Extension Approach

The common probability hypothesis density (PHD) fiter is derived under the single sensor condition. The multisensor PHD (MPHD) filter is remarkably complex and thus is impractical to use. Mahler proposed a MPHD filter under the assumption of independence of all senors. This paper studies the linear multisensor-multitarget system. We propose a linear multisensor probability hypothesis density (LMPHD) filter. By combining measurement dimension extension (MDE) approach, we consider linear correlation of all sensors. A simulation is finally proposed to verify the effective of the L-MPHD filter.

Weifeng Liu, Chenglin Wen

An Improved Particle Swarm Optimization for Uncertain Information Fusion

Multi-sensor information fusion is used to carry on synthesizing excellently to the multi-source information, make verdict of people more accurate and credible. But the influences of uncertainties on the safety/failure of the system and on the warranty costs exist. The new method to deal with the uncertain information fusion based on improved Dempster-Shafer (D-S) evidence theory has been proposed, and set up the concept of weight of sensor evidence itself and evidence distance based on a quantification of the similarity between sets to acquire the reliability weight of the relationship between evidences. Next an improved particle swarm optimization (PSO) is used to computer sensor weight to modify D-S evidence theory. Finally, numerical experiments are adopted to prove its effectiveness.

Peiyi Zhu, Benlian Xu, Baoguo Xu

Three-Primary-Color Pheromone for Track Initiation

We propose a novel ant system with a “subtractive” color mixing model of three-primary-color for jointly estimating the number of tracks to be initiated and their individual tracks in the multi-sensor multi-target system. In our algorithm, each ant deposits cyan, magenta, or yellow pheromone all the time, and ant’s decision depends on the colored pheromone similarity comparison with candidates to be visited. On the basis of it, a mixture optimization function on a three dimensional parameter space is proposed to exploit best solutions by the following ants. Simulation results are presented to support obtained favorable performance of our algorithm.

Benlian Xu, Qinglan Chen, Jihong Zhu

Visual Tracking of Multiple Targets by Multi-Bernoulli Filtering of Background Subtracted Image Data

Most visual multi-target tracking techniques in the literature employ a detection routine to map the image data to point measurements that are usually further processed by a filter. In this paper, we present a visual tracking technique based on a multi-target filtering algorithm that operates directly on the image observations and does not require any detection nor training patterns. Instead, we use the recent history of image data for non-parametric background subtraction and apply an efficient multi-target filtering technique, known as the multi-Bernoulli filter, on the resulting grey scale image data. In our experiments, we applied our method to track multiple people in three video sequences from the CAVIAR dataset. The results show that our method can automatically track multiple interacting targets and quickly finds targets entering or leaving the scene.

Reza Hoseinnezhad, Ba-Ngu Vo, Truong Nguyen Vu

Mobile Robotics in a Random Finite Set Framework

This paper describes the Random Finite Set approach to Bayesian mobile robotics, which is based on a natural multi-object filtering framework, making it well suited to both single and swarm-based mobile robotic applications. By modeling the measurements and feature map as random finite sets (RFSs), joint estimates the number and location of the objects (features) in the map can be generated. In addition, it is shown how the path of each robot can be estimated if required. The framework differs dramatically from existing approaches since both data association and feature management routines are integrated into a single recursion. This makes the framework well suited to multi-robot scenarios due to the ease of fusing multiple map estimates from swarm members, as well as mapping robustness in the presence of other mobile robots which may induce false map measurements. An overview of developments thus far is presented, with implementations demonstrating the merits of the framework on simulated and experimental datasets.

John Mullane, Ba-Ngu Vo, Martin Adams, Ba-Tuong Vo

IMM Algorithm for a 3D High Maneuvering Target Tracking

A major challenge posed by target tracking problems is the target flying at high speeds and performing “high-g” turns in the 3D space. In this situation, horizontally or decoupled models may lead to an unacceptable accuracy. To address this problem an IMM algorithm that includes a 3D constant velocity model (CV), a 3D “current” statistic model (CSM), and 3D constant speed coordinated turn model (3DCSCT) with the kinematic constant for constant speed targets is proposed. The tracking performance of the proposed IMM algorithm is compared with that of an IMM algorithm utilizing CV, 3DCSCT, and constant acceleration model (CA) or singer model. Simulation results that demonstrate the algorithm is feasible and practical for a 3D high maneuvering target tracking.

Dong-liang Peng, Yu Gu

A New Method Based on Ant Colony Optimization for the Probability Hypothesis Density Filter

A new approximating estimate method based on ant colony optimization algorithm for probability hypothesis density (PHD) filter is investigated and applied to estimate the time-varying number of targets and their states in clutter environment. Four key process phases are included: generation of candidates, initiation, extremum search and state extraction. Numerical simulations show the performance of the proposed method is closed to the sequence Monte Carlo PHD method.

Jihong Zhu, Benlian Xu, Fei Wang, Qiquan Wang

Special Session on Fish School Search - Foundations and Application

A Hybrid Algorithm Based on Fish School Search and Particle Swarm Optimization for Dynamic Problems

Swarm Intelligence algorithms have been extensively applied to solve optimization problems. However, some of them, such as Particle Swarm Optimization, may not present the ability to generate diversity after environmental changes. In this paper we propose a hybrid algorithm to overcome this problem by applying a very interesting feature of the Fish School Search algorithm to the Particle Swarm Optimization algorithm, the collective volitive operator. We demonstrated that our proposal presents a better performance when compared to the FSS algorithm and some PSO variations in dynamic environments.

George M. Cavalcanti-Júnior, Carmelo J. A. Bastos-Filho, Fernando B. Lima-Neto, Rodrigo M. C. S. Castro

Feeding the Fish – Weight Update Strategies for the Fish School Search Algorithm

Choosing optimal parameter settings and update strategies is a key issue for almost all population based optimization algorithms based on swarm intelligence. For state-of-the-art optimization algorithms the optimal parameter settings and update strategies for different problem sizes are well known.

In this paper we investigate and compare different newly developed weight update strategies for the recently developed Fish School Search (FSS) algorithm. For this algorithm the optimal update strategies have not been investigated so far. We introduce a new dilation multiplier as well as different weight update steps where fish in poor regions loose weight more quickly than fish in regions with a lot of food. Moreover, we show how a simple non-linear decrease of the individual and volitive step parameters is able to significantly speed up the convergence of FSS.

Andreas Janecek, Ying Tan

Density as the Segregation Mechanism in Fish School Search for Multimodal Optimization Problems

Methods to deal with Multimodal Optimization Problems (MMOP) can be classified in three main approaches, regarding the number and the type of desired solutions. In general, methods can be applied to find: (1) only one global solution; (2) all global solutions; and (3) all local solutions of a given MMOP. The simultaneous capture of several solutions of MMOPs without parameter adjustment is still an open question in optimization problems. In this article, we discuss a density segregation mechanism for Fish School Search to enable simultaneous capture of multiple optimal solutions of MMOPs with one single parameter. The new proposal is based on vanilla version of Fish School Search (FSS) algorithm, which is inspired on actual fish school behavior. The performance of the new algorithm is evaluated and compared to the performance of other methods such as NichePSO and Glowworm Swarm Optimization (GSO) for seven well-known benchmark functions of two dimensions. According to the obtained results, presented in this article, the new approach outperforms the algorithms NichePSO and GSO for all benchmark functions.

Salomão Sampaio Madeiro, Fernando Buarque de Lima-Neto, Carmelo José Albanez Bastos-Filho, Elliackin Messias do Nascimento Figueiredo

Mining Coherent Biclusters with Fish School Search

Fish School Search (FSS) is a recently-proposed metaheuristic inspired by the collective behavior of fish schools. In this paper, we provide a preliminary assessment of FSS while coping with the task of mining coherent and sizeable biclusters from gene expression and collaborative filtering data. For this purpose, experiments were conducted on two real-world datasets whereby the performance of FSS was compared with that exhibited by two other population-based metaheuristics, namely, Genetic Algorithm (GA) and Particle Swarm Optimization (PSO). The results achieved demonstrate the usefulness of FSS while tackling the biclustering problem.

Lara Menezes, André L. V. Coelho

Backmatter

Weitere Informationen

Premium Partner

BranchenIndex Online

Die B2B-Firmensuche für Industrie und Wirtschaft: Kostenfrei in Firmenprofilen nach Lieferanten, Herstellern, Dienstleistern und Händlern recherchieren.

Whitepaper

- ANZEIGE -

Best Practices für die Mitarbeiter-Partizipation in der Produktentwicklung

Unternehmen haben das Innovationspotenzial der eigenen Mitarbeiter auch außerhalb der F&E-Abteilung erkannt. Viele Initiativen zur Partizipation scheitern in der Praxis jedoch häufig. Lesen Sie hier  - basierend auf einer qualitativ-explorativen Expertenstudie - mehr über die wesentlichen Problemfelder der mitarbeiterzentrierten Produktentwicklung und profitieren Sie von konkreten Handlungsempfehlungen aus der Praxis.
Jetzt gratis downloaden!

Bildnachweise