Estimating Construction Material Indices with ARIMA and Optimized NARNETs

Construction Industry operates relying on various key economic indicators. One of these indicators is material prices. On the other hand, cost is a key concern in all operations of the construction industry. In the uncertain conditions, reliable cost forecasts become an important source of information. Material cost is one of the key components of the overall cost of construction. In addition, cost overrun is a common problem in the construction industry, where nine out of ten construction projects face cost overrun. In order to carry out a successful cost management strategy and prevent cost overruns, it is very important to find reliable methods for the estimation of construction material prices. Material prices have a time dependent nature. In order to increase the foreseeability of the costs of construction materials, this study focuses on estimation of construction material indices through time series analysis. Two different types of analysis are implemented for estimation of the future values of construction material indices. The first method implemented was Autoregressive Integrated Moving Average (ARIMA), which is known to be successful in estimation of time series having a linear nature. The second method implemented was Non-Linear Autoregressive Neural Network (NARNET) which is known to be successful in modeling and estimating of series with non-linear components. The results have shown that depending on the nature of the series, both these methods can successfully and accurately estimate the future values of the indices. In addition, we found out that Optimal NARNET architectures which provide better accuracy in estimation of the series can be identified/discovered as result of grid search on NARNET hyperparameters.     

Effect of magnetic field and temperature on the voltage-current characteristics of YBCO superconductor

Voltage-current characteristics of YBCO superconductor was studied under magnetic field up to 0.4 T at different temperatures below T_c. The critical temperature decreases and the transition width broadens under magnetic field. V-I data below T_c were fitted to a power law expression V I^(T,B) in which (T,B) is found to decrease with increase of magnetic field and temperature, gradually approaching unity as T approaches T_c, being independent of magnetic field. Similarly, (T,B) approaches unity as magnetic field increases being independent of temperature.     

Preserving spatial information and overcoming variations in appearance for face recognition

Local feature-based approaches mainly aim to achieve robustness to variations in facial images by assuming that only some parts of the facial images may be affected. However, such approaches may lose spatial information. In this study, a compromise feature extraction scheme is studied which extracts local features while preserving spatial information. The proposed scheme exploits an ensemble of classifiers where each member is constructed using randomly selected design parameters including the size, number and location of sub-images for local feature extraction. Experiments conducted on FERET and ORL databases have shown that proposed scheme surpasses the local feature-based reference systems which focus on either local information or preserving spatial information.     

Rule extraction from artificial neural networks to discover causes of quality defects in fabric production

In this paper, a novel classification rule extraction algorithm which has been recently proposed by authors is employed to determine the causes of quality defects in a fabric production facility in terms of predetermined parameters like machine type, warp type etc. The proposed rule extraction algorithm works on the trained artificial neural networks in order to discover the hidden information which is available in the form of connection weights in them. The proposed algorithm is mainly based on a swarm intelligence metaheuristic which is known as Touring Ant Colony Optimization (TACO). The algorithm has a hierarchical structure with two levels. In the first level, a multilayer perceptron type neural network is trained and its weights are extracted. After obtaining the weights, in the second level, the TACO-based algorithm is applied to extract classification rules. The main purpose of the present work is to determine and analyze the most effective parameters on the quality defects in fabric production. The parameters and their levels which give the best quality results are tried to be discovered and evaluated by making use of the proposed algorithm. It is also aimed to compare the accuracy of proposed algorithm with several other rule-based algorithms in order to present its competitiveness.     

Investigation of Ant System parameter interactions by using design of experiments for job-shop scheduling problems

In recent years, one of the most important and promising research fields has been metaheuristics to find optimal or near-optimal solutions for NP-hard combinatorial optimization problems. Improving the quality of the solution or the solution time is basic research area on metaheuristics. Modifications of the existing ones or creation of hybrid approaches are the focus of these efforts. Another area of improving the solution quality of metaheuristics is finding the optimal combination of algorithm control parameters. This is usually done by design of experiments or one-at-a-time approach in genetic algorithms, simulated annealing and similar metaheuristics. We observe that, in studies which use Ant Colonies Optimization (ACO) as an optimization technique; the levels of control parameters are determined by some non-systematic initial experiments and the interactions of the parameters are not studied yet.In this study, the parameters of Ant System have been investigated on different sized and randomly generated job-shop scheduling problems by using design of experiments. The effects and interactions of the parameters have been interpreted with the outputs of the experiments. Referring to the statistical analysis it is observed that none of the interactions between the Ant System parameters has a significant effect on makespan value. A specific fractional experimental design is suggested instead of the full factorial design. Depending on the findings from the benchmark problems it will be a reliable approach to use the suggested design for saving time and effort in experiments without sacrificing the solution quality.     

End-to-end epidemic multicast loss recovery: Analysis of scalability and robustness

For ensuring reliability at the transport level end-to-end multicasting, an efficient loss recovery mechanism is indispensable. We consider scalability, topology independence and robustness as the significant features that such a mechanism should offer, and demonstrate that an epidemic loss recovery approach is superior in all these aspects. We also show that the epidemic approach transparently handles network link failures by using pair-wise propagation of information, and compare it with feedback controlled loss recovery on identical network settings. The contribution of this work is the simulative analysis of recovery overhead distribution on multicast group members in the case of various link failures on the network, the impact of group size, randomized system-wide noise and message rate on scalability, and examination of various scenarios modeling the overlay networks. We investigate the important features of epidemic multicast loss recovery extensively together and reach concrete results on realistic network scenarios.     

Sharing in teams of heterogeneous,collaborative learning agents

This paper is focused on the effects of sharing knowledge and collaboration of multiple heterogeneous, intelligent agents (hardware or software) which work together to learn a task. As each agent employs a different machine learning technique, the system consists of multiple knowledge sources and their respective heterogeneous knowledge representations. Collaboration between agents involves sharing knowledge to both speed up team learning, as well as refine the team's overall performance and group behavior. Experiments have been performed that vary the team composition in terms of machine learning algorithms, learning strategies employed by the agents, and sharing frequency for a predator‐prey cooperative pursuit task. For lifelong learning, heterogeneous learning teams were more successful than homogeneous learning counterparts. Interestingly, sharing increased the learning rate, but sharing with higher frequency showed diminishing results. Lastly, knowledge conflicts are reduced over time the more sharing takes place. These results support further investigation of the merits of heterogeneous learning. © 2008 Wiley Periodicals, Inc.     

Geno-mathematical identification of the multi-layer perceptron

In this paper, we will focus on the use of the three-layer backpropagation network in vector-valued time series estimation problems. The neural network provides a framework for noncomplex calculations to solve the estimation problem, yet the search for optimal or even feasible neural networks for stochastic processes is both time consuming and uncertain. The backpropagation algorithm—written in strict ANSI C—has been implemented as a standalone support library for the genetic hybrid algorithm (GHA) running on any sequential or parallel main frame computer. In order to cope with ill-conditioned time series problems, we extended the original backpropagation algorithm to a K nearest neighbors algorithm (K-NARX), where the number K is determined genetically along with a set of key parameters. In the K-NARX algorithm, the terminal solution at instant t can be used as a starting point for the next t, which tends to stabilize the optimization process when dealing with autocorrelated time series vectors. This possibility has proved to be especially useful in difficult time series problems. Following the prevailing research directions, we use a genetic algorithm to determine optimal parameterizations for the network, including the lag structure for the nonlinear vector time series system, the net structure with one or two hidden layers and the corresponding number of nodes, type of activation function (currently the standard logistic sigmoid, a bipolar transformation, the hyperbolic tangent, an exponential function and the sine function), the type of minimization algorithm, the number K of nearest neighbors in the K-NARX procedure, the initial value of the Levenberg–Marquardt damping parameter and the value of the neural learning (stabilization) coefficient α. We have focused on a flexible structure allowing addition of, e.g., new minimization algorithms and activation functions in the future. We demonstrate the power of the genetically trimmed K-NARX algorithm on a representative data set.