Anthony Stein

Interpolation-based classifier generation in XCSF

XCSF is a rule-based on-line learning system that makes use of local learning concepts in conjunction with gradient-based approximation techniques. It is mainly used to learn functions, or rather regression problems, by means of dividing the problem space into smaller subspaces and approximate the function values linearly therein. In this paper, we show how local interpolation can be incorporated to improve the approximation speed and thus to decrease the system error. We describe how a novel interpolation component integrates into the algorithmic structure of XCSF and thereby augments the well-established separation into the performance, discovery and reinforcement component. To underpin the validity of our approach, we present and discuss results from experiments on three test functions of different complexity, i.e. we show that by means of the proposed strategies for integrating the locally interpolated values, the overall performance of XCSF can be improved.

Interpolation in the eXtended Classifier System

Sparseness in the input space can be challenging for Learning Classifier Systems.Interpolation is proposed as a solution to tackle this problem.Two approaches to incorporate interpolation in the eXtended Classifier System are introduced.Experimental results promise beneficial effects during the learning process.The presented results improve the observations reported elsewhere. Machine Learning techniques constitute a key factor to make Organic Computing (OC) systems self-adaptive and self-reconfigurable at runtime. OC systems are therefore equipped with a so-called self-learning property enabling them to react appropriately when the environmental demands change and the system is faced possibly unforeseen situations. The eXtended Classifier System (XCS) is a rule-based evolutionary online learning system that has gained plenty attention in the research field of Genetic-based Machine Learning in general and within the OC initiative in particular. In this article, the XCS system is structurally extended to incorporate numerical interpolation. With the presented approaches we pursue the overall goal to overcome the challenge of sparsely distributed samples in the problem space resulting from e.g., non-uniform data distributions. A novel Interpolation Component (IC) is introduced and two architectural integration approaches are discussed. We elaborate on three strategies to integrate interpolated values into various algorithmic steps of XCS. The potential of incorporating interpolation techniques is underpinned by an evaluation on a rather challenging theoretical classification task, called the checkerboard problem.

Dealing with Unforeseen Situations in the Context of Self-Adaptive Urban Traffic Control: How to Bridge the Gap

Autonomously adapting signalling strategies to changing traffic demands in urban areas have been frequently used as application scenario for self-organising systems in general as well as for Autonomic or Organic Computing systems in particular. The Organic Traffic Control (OTC) system is one of the most prominent representatives in this domain. OTC implements a multi-layered Observer/Controller (O/C) architecture and utilises a strongly modified eXtended Classifier System (XCSO/C) for the task of self-adaptation. In this paper, we extend the algorithmic structure of XCS-O/C by a novel interpolation-based approach that incorporates existing knowledge beyond the traditional means. We demonstrate the benefit of the developed approach in terms of reduced delay times for near-to-reality simulations of realistic traffic conditions from Hamburg, Germany.

Ensemble Time Series Forecasting with XCSF

Time series forecasting constitutes an important aspect of any technical system, since the underlying data generating processes vary over time. In order to take system designers out of the loop, efforts for designing self-adaptive, learning systems have extensively been made. By means of forecasting the succeeding system state, the system is enabled to anticipate how to reconfigure itself for satisfying the upcoming conditions. Ensembleforecasting is a specific means of combining the forecasts of multiple independent forecast methods. In this work, we draw a picture of how the eXtended Classifier System for Function approximation (XCSF) can be utilised as a novel self-adaptive weighting approach for ensemble forecasting of univariate time series. We elaborate on the fundamental ideas and evaluate our proposed technique on the basis of several time series.

What about interpolation?: a radial basis function approach to classifier prediction modeling in XCSF

Learning Classifier Systems (LCS) have been strongly investigated in the context of regression tasks and great successes have been achieved by applying the function approximating Extended Classifier System (XCSF) endowed with sophisticated prediction models. In this paper, a novel approach to model a classifiers payoff prediction is proposed. Radial Basis Function (RBF) interpolation is utilized as a new means to capture the underlying function surface complexity. We pose the hypothesis that by the use of a more flexible RBF-based classifier prediction, that alleviates the a priori bias injected via choosing the degree of a polynomial approximation, the classifiers can evolve toward a higher generality by maintaining at least a competitive level of performance compared to the current and probably mostly used state of the art approach - polynomial approximation in combination with the Recursive Least Squares (RLS) technique for incremental coefficient optimization. The presented experimental results underpin our assumptions by revealing that the RBF-based classifier prediction outperforms the n-th order polynomial approximation on several test functions of varying complexity. Additionally, results of experiments with various degrees of noise will be reported to touch upon the proposed approachs applicability in real world situations.

Self-learning Smart Cameras - Harnessing the Generalization Capability of XCS.

In this paper, we show how an evolutionary rule-based machine learning technique can be applied to tackle the task of self-configuration of smart camera networks. More precisely, the Extended Classifier System (XCS) is utilized to learn a configuration strategy for the pan, tilt, and zoom of smart cameras. Thereby, we extend our previous approach, which is based on Q-Learning, by harnessing the generalization capability of Learning Classifier Systems (LCS), i.e. avoiding to separately approximate the quality of each possible (re-)configuration (action) in reaction to a certain situation (state). Instead, situations in which the same reconfiguration is adequate are grouped to one single rule. We demonstrate that our XCS-based approach outperforms the Q-learning method on the basis of empirical evaluations on scenarios of different severity.

Local ensemble weighting in the context of time series forecasting using XCSF

Time series forecasting constitutes an important aspect of any kind of technical system, since the underlying stochastic processes vary over time. Extensive efforts for designing self-adaptive learning systems have been made, to take system designers out of the loop. One goal of such systems is to transfer design-time decisions, e.g. parametrisation, to the run-time. By means of forecasting the succeeding system state, the system itself is enabled to anticipate, how to reconfigure to handle upcoming conditions. Ensemble forecasting is a specific means of combining and weighting the forecasts of multiple independent forecast methods. This concept has proven successful in various domains today. In this work, we present our self-adaptive forecast module for ensemble forecasting of univariate time series and draw a picture of how the eXtended Classifier System for Function approximation (XCSF) can be utilised as a novel weighting approach in this context. We elaborate on the fundamental ideas and evaluate our proposed technique on the basis of several time series with different characteristics.

Distributed resource allocation as co-evolution problem

Distributed self-organising systems often face conflicts if more than one entity tries to access a limited resource. In order to solve this conflict, research focuses on techniques for resource allocation considering different priorities. In this paper, we propose to tackle the decision problem of whom to assign the resource by means of a co-evolutionary approach. We investigate appropriate fitness estimations, representation schemes, and configuration of the underlying genetic operators. We demonstrate the convergence and efficiency of our approach using an exemplary system model.

Task Execution in Distributed Smart Systems

This paper presents a holistic approach to execute tasks in distributed smart systems. This is shown by the example of monitoring tasks in smart camera networks. The proposed approach is general and thus not limited to a specific scenario. A job-resource model is introduced to describe the smart system and the tasks, with as much order as necessary and as few rules as possible. Based on that model, a local algorithm is presented, which is developed to achieve optimization transparency. This means that the optimization on system-wide criteria will not be visible to the participants. To a task, the system-wide optimization is a virtual local single-step optimization. The algorithm is based on proactive quotation broadcasting to the local neighborhood. Additionally, it allows the parallel execution of tasks on resources and includes the optimization of multiple-task-to-resource assignments.

HCI-Patterns for Developing Mobile Apps and Digital Video-Assist-Technology for the Film Set

Digital cinema technology is now widely accepted by directors, directors of photography, producers, film crews, and during the post-production process. On the film set high-resolution digital motion picture cameras have entered the field. In order to exploit the full creative and organizational potential of the advanced digital production technology and to support the whole shooting process, digital video-assist systems are connected to the cameras, monitors, and auxiliary components on the set to form a computer-supported film set CSFS. The CSFS around Vantage Films PSU® family of advanced video-assist systems offers intelligent support for all the roles and tasks on the film set. This paper focuses on the design of the PSU® product generations. Contextual design, agility, and patterns, both for designing control and user interface functionality, have been used extensively in the development process. This is demonstrated for the iPad-based mobile PSU® Satellite and some GUI patterns that were used for different features of the touch-screen based user interface.