A Radial Basis Function Neural Network (RBFNN) based diagnosis system for automatic identification of Cerebral Vascular Accident (CVA) through analysis of Computer Tomographic images (CT) is presented. For the design ...
详细信息
ISBN:
(纸本)9781509024872
A Radial Basis Function Neural Network (RBFNN) based diagnosis system for automatic identification of Cerebral Vascular Accident (CVA) through analysis of Computer Tomographic images (CT) is presented. For the design of a neural network classifier, most published methods just focus on the feature selection aspect and do not consider any approach for determining a model structure that best fits the application at their hand. Moreover, considering the domain of lesion detection from brain tissues, their feature space rarely contains symmetry/asymmetry information with respect to ideal mid-sagittal line. Another issue is how to handle multiple conflicting objectives in the design process, such as the maximization of both specificity and sensitivity, enforcing as well generalization. To deal with these challenges, a multiobjectivegeneticalgorithm (MOGA) based approach is used to determine the architecture of the classifier, its corresponding parameters and input features subject to multiple objectives, as well as their corresponding restrictions and priorities.
This paper discusses the development of strategies in big data context,proposing a multi-drive data mining algorithm based on classification method and solving the investment decision problem when educational charity ...
详细信息
This paper discusses the development of strategies in big data context,proposing a multi-drive data mining algorithm based on classification method and solving the investment decision problem when educational charity Goodgrant is planning to invest in 7900 colleges in the U.S. This paper first classifies all the colleges into to-be funded and to-be eliminated based on cluster analysis. Then, run the Fisher discriminant function parameters of the to-be funded colleges. After determining 52 indices which can influence investment return, select 39 effective indices according to Bayesian discriminant and calculate index weights. In the end,build a multi-objective optimal model based on the maximum of Fisher discriminant function and investment return, apply multi-objective genetic algorithm to compute the optimal investment weights of all the colleges and produce investment priority ranking according to the investment weight. The method in this paper can also be used in other investment area among big data context.
In this paper, the original mooring system is optimized and improved under the condition of considering the water flow and water depth. The whole system is divided into a buoy system and a mooring system. For the buoy...
详细信息
ISBN:
(纸本)9781510845008
In this paper, the original mooring system is optimized and improved under the condition of considering the water flow and water depth. The whole system is divided into a buoy system and a mooring system. For the buoy system, the moment of gravity of the buoy at the mean sea level is analyzed. For mooring system, the anchor cable will appear elastic deformation under the action of water flow force. So the particle spring model is constructed to analyze the force of the catenary segment. Then the new wind speed critical value is obtained. Thus, the state of existence of the chain is determined. A general optimization index is set up. And the optimal solution of the optimization index is calculated according to the multi-objective genetic algorithm. Thus the design of mooring system is completed.
According to the recent demand for materials for use in various displays and solid-state lighting, new phosphors with improved performance have been consistently pursued. multi-objectivegenetic-algorithm-assisted com...
详细信息
According to the recent demand for materials for use in various displays and solid-state lighting, new phosphors with improved performance have been consistently pursued. multi-objectivegenetic-algorithm-assisted combinatorial-material-search (MOGACMS) strategies have been applied to various multi-compositional inorganic systems to search for new phosphors and to optimize the properties of phosphors. In addition, the troublesome, complex problem of high-throughput experimentation (HTE), the inconsistency, which is frequently faced by combinatorial material scientists, is especially emphasized. The luminance and inconsistency was treated as two objective functions in our MOGACMS strategy to pinpoint and optimize promising phosphors with high photoluminance and reliable reproducibility. Using MOGACMS, several multi-dimensional oxide systems were screened in term of the minimization of inconsistency and the maximization of luminance.
Mycobacterium tuberculosis (MTB) and Human immunodeficiency virus (HIV) are two causes of infection which threaten human health over recent decades. There is abundant evidence indicating that these diseases are relate...
详细信息
Accurate prediction of the friction factor and consequently the pressure drop of two-phase flow in small channels is still an issue. Many correlations exist for the determination of the viscosity and the friction fact...
详细信息
Accurate prediction of the friction factor and consequently the pressure drop of two-phase flow in small channels is still an issue. Many correlations exist for the determination of the viscosity and the friction factor that appear in the frictional pressure drop and their combination often determined the degree of disagreements between the experimental data and predicted outcomes. Demands for environmentally friendly refrigerants have further posed a challenge to find compatible alternatives with as good a performance as the current coolants. Despite the many available correlations developed to date, many more are studied in effort to reduce the discrepancies. This paper presents the outcomes of a study comparing the optimized conditions when three different viscosity equations are paired with eight different friction factor correlations to minimize the frictional pressure drop. The approach used multi-objective genetic algorithm (MOGA) to assist in selecting the best pairing. Comparison is then completed with available experimental data. The study showed that the Blasius friction factor paired with the Dukler viscosity produced the least percentage difference for R22, while when paired with the McAdams viscosity produced a lower difference for R290, an environmentally friendly refrigerant being considered to replace R22.
An inverted pendulum system (IPS) is a highly nonlinear dynamical open loop unstable system, typically used as a benchmark to verify the performance of controllers. The IPS emulates the behaviour of an altitude contro...
详细信息
An inverted pendulum system (IPS) is a highly nonlinear dynamical open loop unstable system, typically used as a benchmark to verify the performance of controllers. The IPS emulates the behaviour of an altitude control of a space booster or rocket on take-off. The problem is to develop suitable controllers to maintain the stabilization and swing up of an inverted pendulum on a cart. This paper presents the evolutionary tuning methods of nonlinear PID (NL-PID) controller for IPS with the multi-objective genetic algorithm (MOGA) and adaptive particle swarm optimization (APSO) algorithm. The function of NL-PID controllers is to keep the pendulum in an upright position by maintaining the pendulum at same state and angle at zero degrees. The comparison of responses and performance of MOGA tuned NL-PID and APSO tuned NL-PID controllers for an IPS are described. The mathematical modeling and simulation analysis of the IPS is presented in detail to test the effectiveness of controller tuning algorithm. The APSO based tuning of the NL-PID controller has lesser chattering, noise and fast settling time than MOGA based tuning of the controller.
The multi-objective Job-Shop scheduling problem under multi-resource constrains was investigated and the active heuristic based operation precedence was developed to address the minimization of makespan, the minimizat...
详细信息
The multi-objective Job-Shop scheduling problem under multi-resource constrains was investigated and the active heuristic based operation precedence was developed to address the minimization of makespan, the minimization of total tardiness and the minimization of total idle time of the machines. Then a hybrid procedure was presented by combining the heuristic with multi-objective genetic algorithms and fuzzy evaluation. In the procedure, the representation based operation and the crossover operator based heuristics were adopted, which lead to chromosomes evolve in the active scheduling domain. The weights, which were specified randomly for each fuzzy evaluation, ensured the multidirectional search in the multi-objective genetic algorithm. The results of examples show that the procedure is available and efficient, and superior to the method of Ponnambala.
This paper contains a strategy to minimize energy losses in an electrical distribution network. In order to develop the strategy, a model was constructed to simulate an electrical distribution network, and different p...
详细信息
ISBN:
(纸本)9781629931333
This paper contains a strategy to minimize energy losses in an electrical distribution network. In order to develop the strategy, a model was constructed to simulate an electrical distribution network, and different parameters were included that help in estimation of technical losses in medium voltage (MV) distribution network. The main objective of this paper is to minimize technical and non-technical losses in power systems. There are losses in power systems that cannot be predicted or calculated beforehand, these are the non-technical losses. The bulk of these losses are likely caused by electricity theft, rather than the other possibilities such as poor maintenance of meters, and calculation and accounting mistakes, some power systems may suffer from both. The strategy is applied on a part of real distribution network. The network segments consist of different network busses delivering electrical energy from substation to supply different customers. In this network, the load supplied by one bus is a varying load for different times especially at maximum load conditions.
暂无评论