Search results

In this research, neural network (NN) and genetic algorithm (GA) are used together to design optimal NN structure. The proposed approach combines the characteristics of GA and NN to reduce the computational complexity of artificial intelligence applications in design and manufacturing. Genetic input selection approach is introduced to obtain optimal NN topology. Experimental results are given to evaluate the performance of the proposed system.

Aims to show the potential benefits associated with the application of genetic algorithms (GAs) to the field of marketing management. Describes the background and fundamentals of the technique, and introduces a list of relevant marketing areas to which an optimization technique such as genetic algorithms could be applied. Presents two worked examples (one in site location and the other in market segmentation) to illustrate the power and suitability of using GAs in marketing.

To navigate humanoid robots in complex arenas, a significant level of intelligence is required which needs proper integration of computational intelligence with the robot's controller. This paper describes the use of a combination of genetic algorithm and neural network for navigational control of a humanoid robot in given cluttered environments.

The experimental work involved in the current study has been done by a NAO humanoid robot in laboratory conditions and simulation work has been done by the help of V-REP software. Here, a genetic algorithm controller is first used to generate an initial turning angle for the robot and then the genetic algorithm controller is hybridized with a neural network controller to generate the final turning angle.

From the simulation and experimental results, satisfactory agreements have been observed in terms of navigational parameters with minimal error limits that justify the proper working of the proposed hybrid controller.

With a lack of sufficient literature on humanoid navigation, the proposed hybrid controller is supposed to act as a guiding way towards the design and development of more robust controllers in the near future.

To demonstrate the scalability of the genetic hybrid algorithm (GHA) in monitoring a local neural network algorithm for difficult non‐linear/chaotic time series problems.

GHA is a general‐purpose algorithm, spanning several areas of mathematical problem solving. If needed, GHA invokes an accelerator function at key stages of the solution process, providing it with the current population of solution vectors in the argument list of the function. The user has control over the computational stage (generation of a new population, crossover, mutation etc) and can modify the population of solution vectors, e.g. by invoking special purpose algorithms through the accelerator channel. If needed, the steps of GHA can be partly or completely superseded by the special purpose mathematical/artificial intelligence‐based algorithm. The system can be used as a package for classical mathematical programming with the genetic sub‐block deactivated. On the other hand, the algorithm can be turned into a machinery for stochastic analysis (e.g. for Monte Carlo simulation, time series modelling or neural networks), where the mathematical programming and genetic computing facilities are deactivated or appropropriately adjusted. Finally, pure evolutionary computation may be activated for studying genetic phenomena. GHA contains a flexible generic multi‐computer framework based on MPI, allowing implementations of a wide range of parallel models.

The results indicate that GHA is scalable, yet due to the inherent stochasticity of neural networks and the genetic algorithm, the scalability evidence put forth in this paper is only indicative. The scalability of GHA follows from maximal node intelligence allowing minimal internodal communication in problems with independent computational blocks.

The paper shows that GHA can be effectively run on both sequential and parallel platforms. The multicomputer layout is based on maximizing the intelligence of the nodes – all nodes are provided with the same program and the available computational support libraries – and minimizing internodal communication, hence GHA does not limit the size of the mesh in problems with independent computational tasks.

This mixed-methods study reports on an outreach clinics program designed to deliver genetic services to medically underserved communities in Wisconsin.

We show the geographic distribution, funding patterns, and utilization trends for outreach clinics over a 20-year period. Interviews with program planners and outreach clinic staff show how external and internal constraints limited the program’s capacity. We compare clinic operations to the conceptual models guiding program design.

Our findings show that state health officials had to scale back financial support for outreach clinic activities while healthcare providers faced increasing pressure from administrators to reduce investments in charity care. These external and internal constraints led to a decline in the overall number of patients served. We also find that redistribution of clinics to the Milwaukee area increased utilization among Hispanics but not among African-Americans. Our interviews suggest that these patterns may be a function of shortcomings embedded in the planning models.

Planning models have three shortcomings. First, they do not identify the mitigation of health disparities as a specific goal. Second, they fail to acknowledge that partners face escalating profit-seeking mandates that may limit their capacity to provide charity services. Finally, they underemphasize the importance of seeking trusted partners, especially in working with communities that have been historically marginalized.

There has been little discussion about equitably leveraging genetic advances that improve healthcare quality and efficacy. The role of State Health Agencies in mitigating disparities in access to genetic services has been largely ignored in the sociological literature.

The paper offers an intelligent approach to analyze and determine the design parameters minimizing the total cost and achieving the desired performance measures in the maintenance float systems. The expected total cost in a maintenance float system includes the cost of lost production, the cost of repair persons and the cost of standby machines. The developed design procedure integrates simulation, metamodel and genetic algorithms. Neural networks are able to approximate functions based on a set of sample data, i.e. construct metamodels from simulation results in this study. The objective of metamodels is to predict simulation responses in order to significantly reduce the amount of simulation runs. The predictive performance of neural metamodels comparably outperforms the traditional regression metamodels. The neural metamodels are further extended to formulate a decision model for optimizing the maintenance float systems by using genetic algorithms.

To present research in the area of the applications of modern heuristics and data mining techniques in knowledge discovery.

Applications of data mining for neural networks using NeuralWare Predict^® software, genetic algorithms using Biodiscovery GeneSight^® (2005) software, and regression and discriminant analysis using SPSS^® were selected for bioscience data sets of continuous numerical‐valued Abalone fish data and discrete nominal‐valued mushroom data.

This paper illustrates the useful information that can be obtained using data mining for evolutionary algorithms specifically as those for neural networks, genetic algorithms, regression analysis, and discriminant analysis.

The use of NeuralWare Predict^® was a very effective method of implementing training rules for neural networks to identify the important attributes of numerical and nominal valued data.

The software and algorithms discussed in the paper can be used to visualize and mine microarray data.

The paper contributes to the discussion on the data visualization and data mining of microarray database for bioinformatics and emphasizes new applicability of modern heuristics and software.

This paper presents a new surface reconstruction method based on complex form functions, genetic algorithms and neural networks. Surfaces can be reconstructed in an analytical representation format. This representation is optimal in the sense of least‐square fitting by predefined subsets of data points. The surface representations are achieved by evolution via repetitive application of crossover and mutation operations together with a back‐propagation algorithm until a termination condition is met. The expression is finally classified into specific combinations of basic functions. The proposed method can be used for CAD model reconstruction of 3D objects and free smooth shape modelling. We have implemented the system demonstration with Visual C++ and MatLab to enable real time surface visualisation in the process of design.

The purpose of this paper is to study the electrochemical properties of electrode material on activated carbon double layer capacitors. It also tries to develop a prediction model to evaluate pore size value.

Back-propagation neural network (BPNN) prediction model is used to evaluate pore size value. Also, an improved heuristic approach genetic algorithm (HAGA) is used to search for the optimal relationship between process parameters and electrochemical properties.

A three-layer ANN is found to be optimum with the architecture of three and six neurons in the first and second hidden layer and one neuron in output layer. The simulation results show that the optimized design model based on HAGA can get the suitable process parameters.

HAGA BPNN is proved to be a practical and efficient way for acquiring information and providing optimal parameters about the activated carbon double layer capacitor electrode material.