Multi-criteria expertness based cooperative Q-learning

One of the most influential points in cooperative learning is the type of exchanging information. If the content of exchanging information among agents is rich, cooperation gives rise to better results. To extract proper knowledge of agents during the cooperation process, some expertness measures that assign expertness levels to the other agents are used. In this paper, a new method named Multi-Criteria Expertness based cooperative Q-learning (MCE) is proposed that utilizes all of the expertness measures and attempts to enrich the exchanging information more efficiently. In MCE, all expertness measures are considered simultaneously and collective knowledge is equal to the combination of learned knowledge by each of expertness measures. The experimental results confirm outstanding performance of the proposed method on a sample maze world and a hunter-prey problem.     

Qualitative vision-based navigation based on sloped funnel lane concept

Intelligent Service Robotics - Funnel lane is a map-less visual navigation technique that tries qualitatively to follow a path that has been recorded before by a camera. Unlike some other methods,...     

Efficiency improvement of genetic network programming by tasks decomposition in different types of environments

Genetic Programming and Evolvable Machines - Genetic Network Programming (GNP) is a relatively recently proposed evolutionary algorithm which is an extension of Genetic Programming (GP). However,...     

LADPSO: using fuzzy logic to conduct PSO algorithm

Optimization plays a critical role in human modern life. Nowadays, optimization is used in many aspects of human modern life including engineering, medicine, agriculture and economy. Due to the growing number of optimization problems and their growing complexity, we need to improve and develop theoretical and practical optimization methods. Stochastic population based optimization algorithms like genetic algorithms and particle swarm optimization are good candidates for solving complex problems efficiently. Particle swarm optimization (PSO) is an optimization algorithm that has received much attention in recent years. PSO is a simple and computationally inexpensive algorithm inspired by the social behavior of bird flocks and fish schools. However, PSO suffers from premature convergence, especially in high dimensional multi-modal functions. In this paper, a new method for improving PSO has been introduced. The Proposed method which has been named Light Adaptive Particle Swarm Optimization is a novel method that uses a fuzzy control system to conduct the standard algorithm. The suggested method uses two adjunct operators along with the fuzzy system in order to improve the base algorithm on global optimization problems. Our approach is validated using a number of common complex uni-modal/multi-modal benchmark functions and results have been compared with the results of Standard PSO (SPSO2011) and some other methods. The simulation results demonstrate that results of the proposed approach is promising for improving the standard PSO algorithm on global optimization problems and also improving performance of the algorithm.     

Generalization performance of support vector machines and neural networks in runoff modeling

Effective one-day lead runoff prediction is one of the significant aspects of successful water resources management in arid region. For instance, reservoir and hydropower systems call for real-time or on-line site-specific forecasting of the runoff. In this research, we present a new data-driven model called support vector machines (SVMs) based on structural risk minimization principle, which minimizes a bound on a generalized risk (error), as opposed to the empirical risk minimization principle exploited by conventional regression techniques (e.g. ANNs). Thus, this stat-of-the-art methodology for prediction combines excellent generalization property and sparse representation that lead SVMs to be a very promising forecasting method. Further, SVM makes use of a convex quadratic optimization problem; hence, the solution is always unique and globally optimal. To demonstrate the aforementioned forecasting capability of SVM, one-day lead stream flow of Bakhtiyari River in Iran was predicted using the local climate and rainfall data. Moreover, the results were compared with those of ANN and ANN integrated with genetic algorithms (ANN-GA) models. The improvements in root mean squared error (RMSE) and squared correlation coefficient (R²) by SVM over both ANN models indicate that the prediction accuracy of SVM is at least as good as that of those models, yet in some cases actually better, as well as forecasting of high-value discharges.     

Wood–high‐density polyethylene composites: Water absorption and mechanical properties

In this research, the effect of water absorption on the mechanical properties of wood/high‐density polyethylene (HDPE) composites were investigated. HDPE (44005ARPC) was used as the polymer matrix, and spruce sawdust was used as the filler at a maximum loading of 50 wt % of the total weight of each compound. All compounds contained 5 wt % magnesium stearate as a lubricant and 0.5 wt % Irgafos 168 as a heat stabilizer. Four factors in two levels were chosen [talc (filler) at levels of 5 and 15 wt %, zinc borate (fungicide) at levels of 0 and 1 wt %, maleic anhydride polyethylene (coupling agent) at levels of 4 and 6 wt %, and method of mixing (one‐step vs. two‐step mixing)], and eight compounds were prepared with an L8 Taguchi orthogonal array which has 8 combinations of levels. The effects of each factor at two levels on the diffusion constant and the tensile and bending strengths (under wet and dry conditions) were investigated by the analysis of variance of means with 90% confidence. The optimum level for each factor is reported. The results show that there was a linear correlation between the diffusion constant and tensile and bending strengths when the samples were immersed in distilled water. A higher diffusion constant resulted in much lower tensile and bending strengths with immersion in distilled water until saturation was reached. Scanning electron microscopy images confirmed good mixing when two‐steps mixing was used. © 2010 Wiley Periodicals, Inc. J Appl Polym Sci, 2011     

A new approach to solve SLAM challenges by relative map filter

In this paper we propose a new approach to solve some challenges in the simultaneous localization and mapping (SLAM) problem based on the relative map filter (RMF). This method assumes that the relative distances between the landmarks of relative map are estimated fully independently. This considerably reduces the computational complexity to average number of landmarks observed in each scan. To solve the ambiguity that may happen in finding the absolute locations of robot and landmarks, we have proposed two separate methods, the lowest position error (LPE) and minimum variance position estimator (MVPE). Another challenge in RMF is data association problem where we also propose an algorithm which works by using motion sensors without engaging in their cumulative error. To apply these methods, we switch successively between the absolute and relative positions of landmarks. Having a sufficient number of landmarks in the environment, our algorithm estimates the positions of robot and landmarks without using motion sensors and kinematics of robot. Motion sensors are only used for data association. The empirical studies on the proposed RMF-SLAM algorithm with the LPE or MVPE methods show a better accuracy in localization of robot and landmarks in comparison with the absolute map filter SLAM.