Efficient genetic based topological mapping using analytical models for on-chip networks

Image can be dividing into different Segmentation. In image processing , the important task is Segmentation process methods. This method involves such as K-means clustering, watershed segmentation, Fuzzy c-Means, Iterative Self Organizing Data. Clustering methods depends powerfully on the selection of the primary spectral signatures which represents initial cluster centers. Normally, this is either done physically or erratically based on statistical operations. In this case the outcome is random and sometime inaccurate. In base paper an unsupervised method based on Multi-Objective Genetic Algorithm (MO-GA) for the selection of spectral signature from satellite images is implemented. The goal is to make greatest cluster centers as an initial population for any segmentation technique. Experimental results are conducted using high-resolution SPOT V satellite image and the verification of the segmentation results is based on a very elevated resolution satellite image of kind Quickbird. The spectral signatures method to Fuzzy c-means and K-means by MO-GA method increased the speed of the clustering algorithm to approximately4 times the speed of the random based selection of signatures. In this paper unsupervised method is comparative with Multi-Objective Messy Genetic Algorithm(MOMGA) with existing MO-GA methods for the selection of spectral signature using satellite images.

In this article, an optimum range for increasing transport coefficients with respect to the laminar flow condition in the channel of a three-way catalyst is introduced. A mathematical model of a three-way catalyst was first developed. The model is a one-dimensional plug flow model which involves mass and energy equations in gas and solid phases. To save numerical time, the three-way catalyst model was replaced with a neural network model used in optimization which was solved by using a multi-objective genetic algorithm method. The results of optimization introduce a range in which the desirable objectives will be satisfied. The objectives are to achieve minimum light-off time and maximum increase in catalyst efficiency during different operating conditions of engine. © 2014 American Institute of Chemical Engineers Environ Prog, 34: 368–379, 2015

Modelling and evaluation of adaptive routing in high-performance n-D tori networks

Optimal design of hysteretic dampers connecting adjacent structures using multi-objective genetic algorithm and stochastic linearization method

This paper introduces a new deadlock-free routing algorithm with fewer virtual channels than the known algorithm for a generalized de Bruijn digraph of m virtual channels, where m is the maximum message path length and r is a radix. Our new algorithm requires maximum m-[/sup m-1///sub r/] virtual channels per physical channel. Extension to this algorithm for a generalized de Bruijn graph and a dBCube graph is introduced, and virtual channel requirements have also been identified. In most of dBCube graphs, maximum m-[/sup m-1///sub r/] virtual channels are required for the outcluster channels, and maximum m+1-[/sup m///sub r/] virtual channels for the incluster channels, where m is the maximum length of the cluster-to-cluster path. >

A non dominated ranking Multi Objective Genetic Algorithm and electre method for unequal area facility layout problems

In recent years, multi-objective evolutionary optimization algorithms have shown success in different areas of research. Due to their efficiency and power, many researchers have concentrated on adapting evolutionary algorithms to generate Pareto solutions. This paper proposes a new memetic adaptive multi-objective evolutionary algorithm that is based on a three-term backpropagation network (MAMOT). This algorithm is an automatic search method for optimizing the parameters and performance of neural networks, and it relies on the use of the adaptive non-dominated sorting genetic algorithm-II integrated with the backpropagation algorithm, being used as a local search method. The presented MAMOT employs a self-adaptive mechanism toward improving the performance of the proposed algorithm and a local optimizer improving all the individuals in a population in order to obtain better accuracy and connection weights. In addition, it selects an appropriate number of hidden nodes simultaneously. The proposed method was applied to 11 datasets representing pattern classification problems, including two-class, multi-class and complex data reflecting real problems. Experiments were performed, and the results indicated that the proposed method is viable in pattern classification tasks compared to a multi-objective genetic algorithm based on a three-term backpropagation network (MOGAT) and some of the methods mentioned in the literature. The statistical analysis results of the t test and Wilcoxon signed-ranks test also show that the performance of the proposed method is significantly better than MOGAT.

This paper presents a novel application of a Method of Inequality-based Multi-objective Genetic Algorithm (MMGA) to generate an efficient time-effective multi-fleet aircraft routing algorithm in response to the schedule disruption of short-haul flights. It attempts to optimize objective functions involving ground turn-around times, flight connections, flight swaps, total flight delay time and a 30-minute maximum delay time of original schedules. The MMGA approach, which combines a traditional Genetic Algorithm (GA) with a multi-objective optimization method, can address multiple objectives at the same time, then explore the optimal solution. The airline schedule disruption management problem is traditionally solved by Operations Research (OR) techniques that always require a precise mathematical model. However, airline operations involve too many factors that must be considered dynamically, making a precise mathematical model difficult to define. Experimental results based on a real airline flight schedule demonstrate that the proposed method, Multi-objective Optimization Airline Disruption Management by GA, can recover the perturbation efficiently within a very short time. Our results further demonstrate that the application can yield high quality solutions quickly and, consequently, has potential to be employed as a real-time decision support tool for practical complex airline operations.

Synchronous Reluctance Machine has attracted increasing attention for high performance applications. However, they can be vulnerable to high torque ripple if they are not properly designed. In this paper, it is analyzed how the rotor geometry has a high influence on its performance. A rotor structure with two flux barriers per pole is optimized using a Multi-Objective Genetic Algorithm and Finite Element Method. The different conditions imposed in the optimization lead to two final models, one symmetrical and one asymmetrical of the rotor flux barriers. When comparing the performance indexes of the final models, a considerable improvement is observed in the asymmetric model, which achieves a reduction of more than 40% in the ripple torque without sacrificing the average torque, the power factor also improves and the harmonic distortion in the flux density decreases.

This paper describes the crashworthiness optimization of an intumescent energy-absorbing anti-crawler, which was applied to anti-crawling devices for rail vehicles. The energy absorption characteristics of the expansion-type energy-absorbing anti-crawler were studied experimentally, a finite element model (FEM) was established, and the finite element simulation results were verified with the experimental results. In this paper, the response of the expansion structure was predicted using a validated finite element model. Then, the effects of the variables (expansion tube thickness (T), friction coefficient (μ), and slope angle of conical mandrel (α)) on the response were sampled using the design-of-experiments (DOE) method, including a full factorial design and a central composite. Based on these samples, an alternative model was developed using the moving least-squares method (MLSM). Using the results from the full factorial design for main effects analysis, T was found to have the most significant effect on the average force (Favg), while α had the greatest effect on the specific energy absorption (SEA). The Favg, fracture strain, thickness, taper, and friction coefficient of the structure were used as constraints, and the multiobjective genetic algorithm (MOGA) method was used for parameter optimization to obtain a higher SEA. Finally, the best parameters (T = 5.76 mm, μ = 0.178, α = 25°) with an SEA value of 36.52 kJ/kg were obtained. The SEA value was increased by 31.70% compared to the initial results.

With rapid development of urban rail transit, maglev trains, benefiting from its comfortable, energy-saving and environmentally friendly merits, have gradually entered people's horizons. In this paper, aiming at improving the aerodynamic performance of an urban maglev train, the aerodynamic optimization design has been performed. An improved two-point infill criterion has been adopted to construct the cross-validated Kriging model. Meanwhile, the multi-objective genetic algorithm and complex three-dimensional geometric parametrization method have been used, to optimize the streamlined head of the train. Several optimal shapes have been obtained. Results reveal that the optimization strategy used in this paper is sufficiently accurate and time-efficient for the optimization of the urban maglev train, and can be applied in practical engineering. Compared to the prototype of the train, optimal shape benefits from higher lift of the leading car and smaller drag of the whole train. Sensitivity analysis reveals that the length and height of the streamlined head have a great influence on the aerodynamic performance of the train, and strong nonlinear relationships exist between these design variables and aerodynamic performance. The conclusions drawn in this study offer the chance to derive critical reference values for the optimization of the aerodynamic characteristics of urban maglev trains.Graphic abstract

This paper presents new analytical models for computing the blocking performance of translucent optical networks with sparsely located optical-electrical-optical regeneration nodes. Due to physical layer impairments such as noise and crosstalk, there is a maximum distance [called the transmission reach (TR)] that optical signals can travel before they have to be regenerated. Regeneration nodes that are allocated to a lightpath can also be used for wavelength conversion besides mitigating PLIs. The quality of transmission of a lightpath is satisfied if the length of each segment between two allocated regeneration nodes is less than the TR. We develop analytical models to estimate the call blocking probability for two typical regeneration node allocation policies. The first policy allocates regeneration nodes when the lightpath needs either regeneration or wavelength conversion, while the other allocation policy allocates regenerators only for signal regeneration. The analytical models strike a balance between computational complexity and prediction accuracy. The models are validated using extensive simulation results for a variety of network topologies and parameters.

Networks---on---Chip (NoCs) have been proposed as a promising solution to the complex on-chip communication problems derived from the increasing number of processor cores. The design of NoCs involves several key issues, being the topological mapping (the mapping of the Intellectual Properties (IPs) to network nodes) one of them. Several proposals have been focused on topological mapping last years, but they require the experimental validation of each mapping considered. In this paper, we propose a communication-aware topological mapping technique for NoCs. This technique is based on the experimental correlation of the network model with the actual network performance, thus avoiding the need to experimentally evaluate each mapping explored. The evaluation results show that the proposed technique can provide better performance than the currently existing techniques (in terms of both network latency and energy consumption). Additionally, it can be used for both regular and irregular topologies.

A new general method to compute virtual channels occupancy probabilities in wormhole networks

Analytical method for modal analysis of submerged electric motor stator