This paper presents a fully complex-valued functional link network (CFLN). The CFLN is a single-layered neural network, which introduces nonlinearity in the input layer using nonlinear functions of the original input ...
详细信息
This paper presents a fully complex-valued functional link network (CFLN). The CFLN is a single-layered neural network, which introduces nonlinearity in the input layer using nonlinear functions of the original input variables. In this study, we consider multivariate polynomials as the nonlinear functions. Unlike multilayer neural networks, the CFLN is free from local minima problem, and it offers very fast learning in parameters because of its linear structure. In the complex domain, polynomial based CFLN has an additional advantage of not requiring activation functions, which is a major concern in the complex-valued neural networks. However, it is important to select a smaller subset of polynomial terms (monomials) for faster and better performance, since the number of all possible monomials may be quite large. In this paper, we use the orthogonal least squares method in a constructive fashion (starting from lower degree to higher) for the selection of a parsimonious subset of monomials. Simulation results demonstrate that computing CFLN in purely complex domain is advantageous than in double-dimensional real domain, in terms of number of connection parameters, faster design, and possibly generalization performance. Moreover, our proposed CFLN compares favorably with several other multilayer networks in the complex domain.
We develop an algorithm for two-stage stochastic programming with a convex second stage program and with uncertainty in the right-hand side. The algorithm draws on techniques from bounding and approximation methods as...
详细信息
We develop an algorithm for two-stage stochastic programming with a convex second stage program and with uncertainty in the right-hand side. The algorithm draws on techniques from bounding and approximation methods as well as sampling-based approaches. In particular, we sequentially refine a partition of the support of the random vector and, through Jensen's inequality, generate deterministically valid lower bounds on the optimal objective function value. An upper bound estimator is formed through a stratified Monte Carlo sampling procedure that includes the use of a control variate variance reduction scheme. The algorithm lends itself to a stopping rule theory that ensures an asymptotically valid confidence interval for the quality of the proposed solution. Computational results illustrate our approach.
We have already proposed an idea of simultaneous implementation of population subdivision and training data set subdivision, which leads to significant decrease in computation time of genetics-based machine learning (...
详细信息
We have already proposed an idea of simultaneous implementation of population subdivision and training data set subdivision, which leads to significant decrease in computation time of genetics-based machine learning (GBML) for large data sets. In our idea, a population is subdivided into multiple sub-populations as in island models where subdivided training data are rotated over the sub-populations. In this paper, we focus on the effect of training data rotation on the generalization ability and the computation time of our hybrid fuzzy GBML algorithm. First we show parallel distributed implementation of our hybrid fuzzy GBML algorithm. Then we examine the effect of training data rotation through computational experiments where both single-population (i.e., non-parallel) and multi-population (i.e., parallel) versions of our GBML algorithm are applied to a multi-class high-dimensional problem with a large number of training patterns. Experimental results show that training data rotation improves the generalization ability of our GBML algorithm. It is also shown that the population size is more directly related to the computation time than the training data set size.
The wireless ad hoc network is expected to be used as an alternative of the existing mobile communication network to make users communicate when a large-scale disaster occurs. It is also expected to be deployed to sea...
详细信息
The wireless ad hoc network is expected to be used as an alternative of the existing mobile communication network to make users communicate when a large-scale disaster occurs. It is also expected to be deployed to search robot rescue system in a closed space of disaster struck area. In this paper, we propose two communication models by use of wireless ad hoc network. One is a real city communication model considering the disaster occurs. The other is a search robot communication model in the closed spaces. We analyze and evaluate the communication performance of these two network models by using the network simulator.
In this paper we address the Stochastic Airport Bus Routing Problem (SABRP) where the availability of customers in the meeting points is randomly generated. We solve the problem by utilizing the stochastic programming...
详细信息
In this paper we address the Stochastic Airport Bus Routing Problem (SABRP) where the availability of customers in the meeting points is randomly generated. We solve the problem by utilizing the stochastic programming recourse approach. The objective of our model is to minimize the cost of regular bus tours and the recourse cost when special taxis tours will be sent to specific customers.
Our purpose in this research is to contribute to developing of assistive robot and apparatus. Recently, there is a pressing need to develop a new system which assists and acts for car driving and wheelchair for the el...
详细信息
ISBN:
(纸本)9781457721366
Our purpose in this research is to contribute to developing of assistive robot and apparatus. Recently, there is a pressing need to develop a new system which assists and acts for car driving and wheelchair for the elderly as the population grows older. In terms of developing a new system, it is thought that it is important to examine behaviors as well as spatial recognition. So, experiments were performed for an examination of human spatial perceptions, especially right and left ones, during car driving using NIRS. In previous research, it has been documented that there were significant differences at dorsolateral prefrontal cortex at left hemisphere during virtual driving. In addition, significant differences were seen at similar regions during actual driving. In this time, detailed analysis about ocular motions was reported. The final goal of this study is to find a way to apply this result to new systems with functions that are responsive like human.
The purpose of this paper is to develop an efficient information system to manage all of the procedures in volleyball competitions, including the registration, schedule arrangement, distribution of referees, and score...
详细信息
The purpose of this paper is to develop an efficient information system to manage all of the procedures in volleyball competitions, including the registration, schedule arrangement, distribution of referees, and scores report. We established this system on the website to be applied by University Volleyball League in Taiwan, it not only solved all of the operated problems in traditional and complicated processes to become much easier than ever and to make the information popularized and updated, but also efficiently decreased the consumption in the time and expenses of administrated supports especially in the procedures of arrangement all of the referees to operate their tasks in the competitions. As the results, the usage of the contest management system has improved the quality of the administrated procedures in volleyball competitions. The conclusion shows that it is also innovative and advanced for other sports to prepare and handle the competitive procedures.
Mobile phones come into wide use now and many people usually carry about and are familiar with using them. So, mobile phone becomes a very useful communication tool in large scale disasters. But it often cannot use, b...
详细信息
Mobile phones come into wide use now and many people usually carry about and are familiar with using them. So, mobile phone becomes a very useful communication tool in large scale disasters. But it often cannot use, because congestion occurs owing to large demand of calls by which people wants to know their family with accidents or without accidents, non-functional base stations occur owing to cable cutting or long time power failure. As countermeasures to these issues, we study the holding time limitation and the emergency multi-system access, in the project of researches on network control technologies in disasters. This paper describes the outline of our studies.
In these years, gas engine generators have been much improved to gain higher electrical efficiency by using lean-burn and miller cycle technologies. As on-site power generation, electrical efficiency of over 40%LHV ca...
详细信息
In these years, gas engine generators have been much improved to gain higher electrical efficiency by using lean-burn and miller cycle technologies. As on-site power generation, electrical efficiency of over 40%LHV can be obtained by several hundreds to several thousands kWs units. In addition to obtaining a highly efficient power utilization by interconnected operation, emergency power could be supplied by an islanded operation that is the most distinctive ability of distributed generators to keep social infrastructure from disasters. However, high-efficient gas engines are not suitable for islanded operations because of the instability during load changes. Even though interconnect operation, the limitation of load increment is imposed for the system operation, in which gas engines need several minutes for load increment from 0kW to the rated load. In this study, we describe a highly efficient lean burn gas engine combined with power storage devices, which will establish operation stability during islanding mode. We will demonstrate the design of cooperative control between two power sources to derive better performance by the integration.
Achieving high performance optimization algorithms for embedded applications can be very challenging, particularly when several requirements such as high accuracy computations, short elapsed time, area cost, low power...
详细信息
Achieving high performance optimization algorithms for embedded applications can be very challenging, particularly when several requirements such as high accuracy computations, short elapsed time, area cost, low power consumption and portability must be accomplished. This paper proposes a hardware implementation of the Particle Swarm Optimization algorithm with passive congregation (HPPSOpc), which was developed using several floating-point arithmetic libraries. The passive congregation is a biological behavior which allows the swarm to preserve its integrity, balancing between global and local search. The HPPSOpc architecture was implemented on a Virtex5 FPGA device and validated using two multimodal benchmark problems. Synthesis, simulation and execution time results demonstrates that the passive congregation approach is a low cost solution for solving embedded optimization problems with a high performance.
暂无评论