THE DESIGN AND ANALYSIS OF EXPERIMENTS. By Oscar Kempthorne. New York, John Wiley and Sons, Inc., 1952. 631 pp. $8.50. This book by a teacher of statistics (as well as a consultant for \"experimenters\") is a comprehensive study of the philosophical background for the statistical design of experiment. It is necessary to have some facility with algebraic notation and manipulation to be able to use the volume intelligently. The problems are presented from the theoretical point of view, without such practical examples as would be helpful for those not acquainted with mathematics. The mathematical justification for the techniques is given. As a somewhat advanced treatment of the design and analysis of experiments, this volume will be interesting and helpful for many who approach statistics theoretically as well as practically. With emphasis on the \"why,\" and with description given broadly, the author relates the subject matter to the general theory of statistics and to the general problem of experimental inference. MARGARET J. ROBERTSON

The Design and Analysis of Experiments

An overview of the self-organizing map algorithm, on which the papers in this issue are based, is presented in this article.

The Self-Organizing Map

Learning and evolution are two fundamental forms of adaptation. There has been a great interest in combining learning and evolution with artificial neural networks (ANNs) in recent years. This paper: 1) reviews different combinations between ANNs and evolutionary algorithms (EAs), including using EAs to evolve ANN connection weights, architectures, learning rules, and input features; 2) discusses different search operators which have been used in various EAs; and 3) points out possible future research directions. It is shown, through a considerably large literature review, that combinations between ANNs and EAs can lead to significantly better intelligent systems than relying on ANNs or EAs alone.

/pdf/evolving-artificial-neural-networks-4kzrbu7pkn.pdf

Evolving artificial neural networks

List of Figures. List of Tables. Preface. Contributing Authors. Series Foreword. Part I: Foundations. 1. An Introduction to Evolutionary Algorithms J.A. Lozano. 2. An Introduction to Probabilistic Graphical Models P. Larranaga. 3. A Review on Estimation of Distribution Algorithms P. Larranaga. 4. Benefits of Data Clustering in Multimodal Function Optimization via EDAs J.M. Pena, et al. 5. Parallel Estimation of Distribution Algorithms J.A. Lozano, et al. 6. Mathematical Modeling of Discrete Estimation of Distribution Algorithms C. Gonzalez, et al. Part II: Optimization. 7. An Empiricial Comparison of Discrete Estimation of Distribution Algorithms R. Blanco., J.A. Lozano. 8. Results in Function Optimization with EDAs in Continuous Domain E. Bengoetxea, et al. 9. Solving the 0-1 Knapsack Problem with EDAs R. Sagarna, P. Larranaga. 10. Solving the Traveling Salesman Problem with EDAs V. Robles, et al. 11. EDAs Applied to the Job Shop Scheduling Problem J.A. Lozano, A. Mendiburu. 12. Solving Graph Matching with EDAs Using a Permutation-Based Representation E. Bengoetxea, et al. Part III: Machine Learning. 13. Feature Subset Selection by Estimation of Distribution Algorithms I. Inza, et al. 14. Feature Weighting for Nearest Neighbor by EDAs I. Inza, et al. 15. Rule Induction by Estimation of Distribution Algorithms B. Sierra, et al. 16. Partial Abductive Inference in Bayesian Networks: An Empirical Comparison Between GAs and EDAs L.M. de Campos, et al.17. Comparing K-Means, GAs and EDAs in Partitional Clustering J. Roure, et al. 18. Adjusting Weights in Artificial Neural Networks using Evolutionary Algorithms C. Cotta, et al. Index.

Estimation of Distribution Algorithms: A New Tool for Evolutionary Computation

A scheme is developed for classifying the types of motion perceived by a humanlike robot. It is assumed that the robot receives visual images of the scene using a perspective system model. Equations, theorems, concepts, clues, etc., relating the objects, their positions, and their motion to their images on the focal plane are presented. >

http://ieeexplore.ieee.org/iel2/815/3148/00100651.pdf

Robot vision

In this work we compare some of the freely available parallel Toolboxes for Matlab, which differ in purpose and implementation details: while DP-Toolbox and MultiMatlab offer a higher-level parallel environment, the goals of PVMTB and MPITB, developed by us [7], are to closely adhere to the PVM system and MPI standard, respectively. DP-Toolbox is also based on PVM, and MultiMATLAB on MPI. These Toolboxes allow the user to build a parallel application under the rapid-prototyping Matlab environment. The differences between them are illustrated by means of a performance test and a simple case study frequently found in the literature. Thus, depending on the preferred message-passing software and the performance requirements of the application, the user can either choose a higher-level Toolbox and benefit from easier coding, or directly interface the message-passing routines and benefit from greater control and performance.

Performance of message-passing MATLAB toolboxes

The design of Radial Basis Function Neural Networks (RBFNNs) still remains as a difficult task when they are applied to classification or to regression problems. The difficulty arises when the parameters that define an RBFNN have to be set, these are: the number of RBFs, the position of their centers and the length of their radii. Another issue that has to be faced when applying these models to real world applications is to select the variables that the RBFNN will use as inputs. The literature presents several methodologies to perform these two tasks separately, however, due to the intrinsic parallelism of the genetic algorithms, a parallel implementation will allow the algorithm proposed in this paper to evolve solutions for both problems at the same time. The parallelization of the algorithm not only consists in the evolution of the two problems but in the specialization of the crossover and mutation operators in order to evolve the different elements to be optimized when designing RBFNNs. The subjacent Genetic Algorithm is the Non-Sorting Dominated Genetic Algorithm II (NSGA-II) that helps to keep a balance between the size of the network and its approximation accuracy in order to avoid overtraining networks. Another of the novelties of the proposed algorithm is the incorporation of local search algorithms in three stages of the algorithm: initialization of the population, evolution of the individuals, and final optimization of the Pareto front. The initialization of the individuals is performed hybridizing clustering techniques with the Mutual Information theory (MI) to select the input variables. As the experiment will show, the synergy of the different paradigms and techniques combined by the presented algorithm allow to obtain very accurate models using the most significant input variables.

Parallel multi-objective memetic RBFNNs design and feature selection for function approximation problems

Selective attention to visual-spatial stimuli causes decrements of power in alpha band and increments in beta. For steady-state visual evoked potentials (SSVEP) selective attention affects electroencephalogram (EEG) recordings, modulating the power in the range 8-27 Hz. The same behaviour can be seen for auditory stimuli as well, although for auditory steady-state response (ASSR), it is not fully confirmed yet. The design of selective attention based braincomputer interfaces (BCIs) has two major advantages: First, no much training is needed. Second, if properly designed, a steady-state response corresponding to spectral peaks can be elicited, easy to filter and classify. In this paper we study the behaviour of Kohonen Maps as feature selector for a selective attention to auditory stimuli based BCI system.

Use of Kohonen Maps as Feature Selector for Selective Attention Brain-Computer Interfaces

We present a policy-based approach to managing congestions in short message service (SMS) systems. Congestion situations typically occur on SMS gateways (SMSGs), which route SMS messages between different networks and domains. In our architecture, an SMS operator can dynamically define the maximum acceptable loss of messages of a nonguaranteed SMS service class, thereby controlling the trade-off between minimal message loss and maximum throughput in an SMS system. We present the functional architecture of a manageable SMSG and discuss the realization of the policy decision point (PDP), which applies the congestion policy on the SMSG. An implementation of our architecture on a commercial SMSG, the EMG, is underway.

Policy-based congestion management for an SMS gateway

Critical networked services enable significant revenue for network operators and, in turn, are regulated by Service Level Agreements (SLAs). In order to ensure SLAs are being met, service levels need to be monitored. One technique for this involves active measurements, such as IPSLA. However, active measurements are expensive in terms of CPU consumption on network devices. As a result, active measurements usually can cover only a fraction of what could be measured, which can lead to SLA violations being missed. The definition of which subsets of service paths to measure and to configure corresponding measurement probes is a practice that does not scale well and results in fairly static measurement setups that do not adapt well to shifting networking patterns. We propose a solution to increase the detection rate of SLA violations in which devices in a network autonomously and dynamically determine how to place probes in order to detect service level violations. It does not require human intervention, is adaptive to changes in network conditions, resilient to networking faults, and independent of the underlying active measurement technology. Our solution is based on peer-to-peer principles and is characterized by a high degree of decentralized decision making across a network using a self-organizing overlay. In these experiments it is possible to observe that an increase in the information used in probe placement decisions decreases the number of SLA violations missed.

Alberto Prieto

Papers

Performance of message-passing MATLAB toolboxes

Parallel multi-objective memetic RBFNNs design and feature selection for function approximation problems

Use of Kohonen Maps as Feature Selector for Selective Attention Brain-Computer Interfaces

Policy-based congestion management for an SMS gateway

Decentralized detection of SLA violations using P2P technology