An interconnection network is an inevitable component for constructing parallel computers. It connects computation nodes so that the nodes can communicate with each other. As a parallel computation essentially requires inter-node communication according to a parallel algorithm, the interconnection network plays an important role in terms of communication performance. This paper focuses on the collective communication that is frequently performed in parallel computation and this paper addresses the Cup-Stacking method that is proposed in our preceding work. The key issues of the method are splitting a large packet into slices, re-shaping the slice, and stacking the slices, in a genetic algorithm (GA) manner. This paper discusses extending the Cup-Stacking method by introducing additional items (genes) and proposes the extended Cup-Stacking method. Furthermore, this paper places comprehensive discussions on the drawbacks and further optimization of the method. Evaluation results reveal the effectiveness of the extended method, where the proposed method achieves at most seven percent improvement in duration time over the former Cup-Stacking method.

Inter-node communication is essential in parallel computation. The performance of parallel processing depends on the efficiencies in both computation and communication, thus, the communication cost is not negligible. A parallel application program involves a logical communication structure that is determined by the interchange of data between computation nodes. Sometimes the logical communication structure mismatches to that in a real parallel machine. This mismatch results in large communication costs. This paper addresses the node-mapping problem that rearranges logical position of node so that the degree of mismatch is decreased. This paper assumes that parallel programs execute one or more collective communications that follow specific traffic patterns. An appropriate node-mapping achieves high communication performance. This paper proposes a strong heuristic method for solving the node-mapping problem and adapts the method to a genetic algorithm. Evaluation results reveal that the proposed method achieves considerably high performance; it achieves 8.9 (4.9) times speed-up on average in single-(two-)traffic-pattern cases in 32×32 torus networks. Specifically, for some traffic patterns in small-scale networks, the proposed method finds theoretically optimized solutions. Furthermore, this paper discusses in deep about various issues in the proposed method that employs genetic algorithm, such as population of genes, number of generations, and traffic patterns. This paper also discusses applicability to large-scale systems for future practical use.

This paper studies the simple dynamic binary neural network characterized by the signum activation function, ternary weighting parameters and integer threshold parameters. The network can be regarded as a digital version of the recurrent neural network and can output a variety of binary periodic orbits. The network dynamics can be simplified into a return map, from a set of lattice points, to itself. In order to store a desired periodic orbit, we present two learning algorithms based on the correlation learning and the genetic algorithm. The algorithms are applied to three examples: a periodic orbit corresponding to the switching signal of the dc-ac inverter and artificial periodic orbit. Using the return map, we have investigated the storage of the periodic orbits and stability of the stored periodic orbits.

This letter studies learning of the binary neural network and its relation to the logical synthesis. The network has the signum activation function and can approximate a desired Boolean function if parameters are selected suitably. In a parameter subspace the network is equivalent to the disjoint canonical form of the Boolean functions. Outside of the subspace, the network can have simpler structure than the canonical form where the simplicity is measured by the number of hidden neurons. In order to realize effective parameter setting, we present a learning algorithm based on the genetic algorithm. The algorithm uses the teacher signals as the initial kernel and tolerates a level of learning error. Performing basic numerical experiments, the algorithm efficiency is confirmed.

In ubiquitous sensor networks, extra energy savings can be achieved by selecting the filtering solution to counter the attack. This adaptive selection process employs a fuzzy rule-based system for selecting the best solution, as there is uncertainty in the reasoning processes as well as imprecision in the data. In order to maximize the performance of the fuzzy system the membership functions should be optimized. However, the efforts required to perform this optimization manually can be impractical for commonly used applications. This paper presents a GA-based membership function optimizer for fuzzy adaptive filtering (GAOFF) in ubiquitous sensor networks, in which the efficiency of the membership functions is measured based on simulation results and optimized by GA. The proposed optimization consists of three units; the first performs a simulation using a set of membership functions, the second evaluates the performance of the membership functions based on the simulation results, and the third constructs a population representing the membership functions by GA. The proposed method can optimize the membership functions automatically while utilizing minimal human expertise.

This paper develops planar circuit filters consisting of arbitrarily-shaped conductor patches and slots on a conductor-backed dielectric substrate, which are designed by an optimization technique based on the genetic algorithm. The developed filter has multiple resonators and their mutual couplings in the limited space by using both sides of the substrate, so that its compactness is realized. We first demonstrate the effectiveness of the present filter structure from some design samples numerically and experimentally. Then as a practical application, we design compact UWB filters, and their filter characteristics are verified from the measurements.

In this paper, a new algorithm called TGA is introduced which defines the concept of time more naturally for the first time. A parameter called TimeToLive is considered for each chromosome, which is a time duration in which it could participate in the process of the algorithm. This will lead to keeping the dynamism of algorithm in addition to maintaining its convergence sufficiently and stably. Thus, the TGA guarantees not to result in premature convergence or stagnation providing necessary convergence to achieve optimal answer. Moreover, the mutation operator is used more meaningfully in the TGA. Mutation probability has direct relation with parent similarity. This kind of mutation will decrease ineffective mating percent which does not make any improvement in offspring individuals and also it is more natural. Simulation results show that one run of the TGA is enough to reach the optimum answer and the TGA outperforms the standard genetic algorithm.

A two-dimensional filter for photonic label recognition system using time-to-space conversion and delay compensation was designed using Genetic-Algorithms (GA). For four-bit Binary Phase Shift Keying (BPSK) labels at 160 Gbit/s, contrast ratio of the output for eight different labels was improved by optimization of two-dimentional filtering. The contrast ratio of auto-correlation to cross-correlation larger than 2.16 was obtained by computer simulation. This value is 22% larger than the value of 1.77 with the previously reported system using matched filters.

In this paper, an evolutionary approach is proposed to obtain a discrete-time state-space interval model for uncertain continuous-time systems having interval uncertainties. Based on a worst-case analysis, the problem to derive the discrete interval model is first formulated as multiple mono-objective optimization problems for matrix-value functions associated with the discrete system matrices, and subsequently optimized via a proposed genetic algorithm (GA) to obtain the lower and upper bounds of the entries in the system matrices. To show the effectiveness of the proposed approach, roots clustering of the characteristic equation of the obtained discrete interval model is illustrated for comparison with those obtained via existing methods.

A new structure learning approach for Bayesian networks (BNs) based on dual genetic algorithm (DGA) is proposed in this paper. An individual of the population is represented as a dual chromosome composed of two chromosomes. The first chromosome represents the ordering among the BN nodes and the second represents the conditional dependencies among the ordered BN nodes. It is rigorously shown that there is no BN structure that cannot be encoded by the proposed dual genetic encoding and the proposed encoding explores the entire solution space of the BN structures. In contrast with existing GA-based structure learning methods, the proposed method learns not only the topology of the BN nodes, but also the ordering among the BN nodes, thereby, exploring the wider solution space of a given problem than the existing method. The dual genetic operators are closed in the set of the admissible individuals. The proposed method is applied to real-world and benchmark applications, while its effectiveness is demonstrated through computer simulation.

This paper proposes a new type of compact waveguide directional coupler, which is constructed from two crossed E-plane rectangular waveguide with two metallic posts in the square junction and one metallic post at each port. The metallic posts in the square junction are set symmetrically along a diagonal line to obtain the directivity properties. The metallic post inserted at each input/output waveguide port can realize a matched state. Tight-coupling properties 0.79-6 dB are realized by optimizing the dimension of the junction and the positions/radii of the posts. The design results are verified by an em-simulator (Ansoft HFSS) and experiments.

In recent years, network analysis has revealed that some real networks have the properties of small-world and/or scale-free networks. In this study, a simple Genetic Algorithm (GA) is regarded as a network where each node and each edge respectively represent a population and the possibility of the transition between two nodes. The characteristic path length (CPL), which is one of the most popular criteria in small-world networks, is derived analytically and shows how much the crossover operation affects the path length between two populations. As a result, the crossover operation is not so useful for shortening the CPL.

Design of optimal controllers satisfying performance criteria of minimum tracking error and disturbance level for an interval system using a multi-objective evolutionary approach is proposed in this paper. Based on a worst-case design philosophy, the design problem is formulated as a minimax optimization problem, subsequently solved by a proposed two-phase multi-objective genetic algorithm (MOGA). By using two sets of interactive genetic algorithms where the first one determines the maximum (worst-case) cost function values for a given set of controller parameters while the other one minimizes the maximum cost function values passed from the first genetic algorithm, the proposed approach evolutionarily derives the optimal controllers for the interval system. To suitably assess chromosomes for their fitness in a population, root locations of the 32 generalized Kharitonov polynomials will be used to establish a constraints handling mechanism, based on which a fitness function can be constructed for effective evaluation of the chromosomes. Because of the time-consuming process that genetic algorithms generally exhibit, particularly the problem nature of minimax optimization, a parallel computation scheme for the evolutionary approach in the MATLAB-based working environment is also proposed to accelerate the design process.

This paper deals with questions concerning the supply of building-blocks (BBs) in the initial population of real-coded genetic algorithms (rGAs). Drawing upon the methodology of existing BB supply studies for finite alphabets, facetwise models for the supply of a single schema as well as for the supply of all the schemata in a partition are proposed. A model for the initial population size necessary to ensure the presence of all the raw BBs with a given supply error has also been developed using the partition success model. Experimental results show the effectiveness of the facetwise models and the initial population sizing model. Finally, an adaptation approach is suggested for practical use of the BB supply.

Genetic algorithms are a general problem-solving technique that has been widely used in computational biology. In this paper, we present a framework to map hierarchical parallel genetic algorithms for protein folding problems onto computational grids. By using this framework, the two level communication parts of hierarchical parallel genetic algorithms are separated. Thus both parts of the algorithm can evolve independently. This permits users to experiment with alternative communication models on different levels conveniently. The underlying programming techniques are based on generic programming, a programming technique suited for the generic representation of abstract concepts. This allows the framework to be built in a generic way at application level and thus provides good extensibility and flexibility. Experiments show that it can lead to significant runtime savings on PC clusters and computational grids.

This paper proposes a genetically inspired adaptive clustering algorithm for numerical and categorical data sets. To this end, unique encoding method and fitness functions are developed. The algorithm automatically discovers the actual number of clusters and efficiently performs clustering without unduly compromising cluster-purity. Moreover, it outperforms existing clustering algorithms.

This paper proposes an efficient two-phase optimization approach for a compact W-band double-plane stepped rectangular waveguide filter design, which combines genetic algorithms (GAs) with the simplified transmission-line model and full-wave analysis. Being more efficient and robust than the gradient-based method, the approach can lead to a compact waveguide filter design. Numerical results show that the resultant waveguide filter design with 4 sections (total length 19.6 mm) is sufficient to meet the design goal and provides comparable performance to that with 8 sections (total length 35.6 mm) by the Chebyshev synthesis approach. Based on the present approach, nineteen compact high-pass waveguide filters have been implemented and measured at the W-band with satisfactory performance.

In spatial multiplexing systems using multiple antennas, the error-rate performance is heavily dependent on the residual channel estimation error. In this letter, we propose a design method that uses the genetic algorithms to optimize training sequences for accurate channel estimation.

The facility layout problem is one of the most fundamental quadratic assignment problems in operations research. In this paper, we present an improved genetic algorithm for solving the facility layout problem. In our computational model, we propose several improvements to the basic genetic procedures including conditional crossover and mutation. The performance of the proposed method is evaluated on some benchmark problems. Computational results showed that the improved genetic algorithm is capable of producing high-quality solutions.

In this paper, an adaptive bound reduced-form genetic algorithm (ABRGA) to tune the control points of B-spline neural networks is proposed. It is developed not only to search for the optimal control points but also to adaptively tune the bounds of the control points of the B-spline neural networks by enlarging the search space of the control points. To improve the searching speed of the reduced-form genetic algorithm (RGA), the ABRGA is derived, in which better bounds of control points of B-spline neural networks are determined and paralleled with the optimal control points searched. It is shown that better efficiency is obtained if the bounds of control points are adjusted properly for the RGA-based B-spline neural networks.