Using multiple windows to track concept drift

In this paper we present a multiple window incremental learning algorithm that distinguishes between virtual concept drift and real concept drift. The algorithm is unsupervised and uses a novel approach to tracking concept drift that involves the use of competing windows to interpret the data. Unlike previous methods which use a single window to determine the drift in the data, our algorithm uses three windows of different sizes to estimate the change in the data. The advantage of this approach is that it allows the system to progressively adapt and predict the change thus enabling it to deal more effectively with different types of drift. We give a detailed description of the algorithm and present the results obtained from its application to two real world problems: background image processing and sound recognition. We also compare its performance with FLORA, an existing concept drift tracking algorithm.

Using selective memory to track concept drift effectively

In this paper we describe a supervised learning algorithm that uses selective memory to track concept drift. Unlike previous methods to track concept drift that use window heuristics to adapt to changes, we present an improved approach that discriminates between the instances observed. The advantage of this method is that it allows the system to both adapt to and track drift more accurately as well as filter the noise in the data more effectively. We present the algorithm and compare its performance with FLORA a well known concept drift tracking algorithm.

Machine learning for user modeling

At first blush, user modeling appears to be a prime candidate for straightforward application of standard machine learning techniques. Observations of the user's behavior can provide training examples that a machine learning system can use to form a model designed to predict future actions. However, user modeling poses a number of challenges for machine learning that have hindered its application in user modeling, including: the need for large data sets; the need for labeled data; concept drift; and computational complexity. This paper examines each of these issues and reviews approaches to resolving them.

Learning about dynamic scenes

Incremental learning allows modification of developed concepts without the need for prior knowledge of all data. An incremental algorithm is developed to focus on the problems of memory size, forgetting and concept drift. The evidence based forgetting procedure minimizes the concept size and maintains its consistency with respect to the incoming data. An age value associated with the data determines its reinforcement or removal from a concept.

Anomaly detection in wireless sensor networks in a non-stationary environment

Anomaly detection in a WSN is an important aspect of data analysis in order to identify data items that significantly differ from normal data. A characteristic of the data generated by a WSN is that the data distribution may alter over the lifetime of the network due to the changing nature of the phenomenon being observed. Anomaly detection techniques must be able to adapt to a non-stationary data distribution in order to perform optimally. In this survey, we provide a comprehensive overview of approaches to anomaly detection in a WSN and their operation in a non-stationary environment.

Polanyi's presagement of the incommensurability concept

Kuhn and Feyerabend have little to say about the thought of Michael Polanyi, and the secondary literature on Polanyi's relation to them is meagre. I argue that Polanyi's view, in Personal knowledge and in other writings, of conceptual frameworks ‘segregated’ by a ‘logical gap’ as giving rise to controversies in science foreshadowed Kuhn and Feyerabend's theme of incommensurability. The similarity between the thinkers is, I suggest, no coincidence.

Application of the fair-value concept : evidence from Australian legal decisions

The concept of "fair value" is increasingly being incorporated into Australian and international accounting standards and pronouncements. The fair-value concept has also been established and developed in Australian legal cases, and an examination of pertinent court decisions is of interest to accountants. By examining and analysing relevant cases, the paper highlights some of the principles and difficulties involved in operationalising the fair-value concept for accounting and legal purposes, particularly in situations where the asset being valued is subject to imperfect or incomplete markets.

Intra-organisational marketing culture and market orientation: a case study of the implementation of the marketing concept in a public library

The measurement of both marketing culture and behaviour provides the opportunity to gain more insight into the overall market focus of organisations. This article seeks to determine the market orientation and marketing culture of all staff within organisations, to ascertain to what extent other members of an organisation support or create barriers to the successful implementation of the marketing concept. This paper will provide a brief overview of the existing literature in the field of market orientation and marketing culture. After detailing the research design and methodology, a summary developed from 11 focus group sessions - consisting of all staff in one public library service in Victoria, Australia - is presented. The findings indicate that while all areas within this organisation are committed to marketing, there are various interpretations of marketing and how it should be implemented. In addition, the research finds a number of factors that could be instrumental in the successful implementation of the marketing concept in public libraries.

Combining extension matrix and integer programming for optimal concept learning

This paper proposes two integer programming models and their GA-based solutions for optimal concept learning. The models are built to obtain the optimal concept description in the form of propositional logic formulas from examples based on completeness, consistency and simplicity. The simplicity of the propositional rules is selected as the objective function of the integer programming models, and the completeness and consistency of the concept are used as the constraints. Considering the real-world problems that certain level of noise is contained in data set, the constraints in model 11 are slacked by adding slack-variables. To solve the integer programming models, genetic algorithm is employed to search the global solution space. We call our approach IP-AE. Its effectiveness is verified by comparing the experimental results with other well- known concept learning algorithms: AQ15 and C4.5.

Integrated health impact assessment into the triple bottom line concept

This theoretical study explores the links between the Triple Bottom Line (TBL) concept and the principles of HIA and considers the potential role of HIA to provide a mechanism for integrating health concerns within a broader agenda of government and business. TBL is a framework linked to the broader sustainability agenda that underpins and reviews environmental, economic and social performance of organizations. In its simplest form, TBL acts as a tool for reporting to stakeholders/shareholders organizational performance and the nature of the impacts on the community. The links to HIA are clear as both seek to determine the impact (potential and actual) on the health and well-being of the population.

The study found that TBL can operate at four levels within organizations ranging from reporting through to full integration with the organization's goals and practices. Health is narrowly defined and there are tensions about how to undertake the social accountability functions. The study shows the potential role for HIA within the broader policy and accountability agenda. As health is one of the main outcomes of an organization's activities it needs to be taken into account at all levels of activity.

Financial reporting for environmental and social responsibility: a normative strategic concept

Corporate responsibility demands that firms address environmental and social values in their firms' policy and key performance indicators. These are integrated through strategic planning and require firms to merge the long-term environmental and social values with short-term economic objectives and performance measures. Each firm's strategy will differ. This paper provides a normative reporting concept to connect the financial implications associated with long-term planning for environmental and social values, with short-term accounting reports. Reporting variants adapted from total cost assessment, life cycle costing and variable costing are integrated to offer upstream information based on a product segment view.

Development of a cooling fabric from conducting polymer coated fibres: proof of concept

It is supposed that there should be a thermal electric effect if a dc current is applied across two dissimilar conducting polymers, similar to so called “Peltier effect” in metals or semiconductors. However, this hypothesis has not been tested on conducting polymers and using these materials to make cooling fabrics has never been attempted before. Polypyrrole coated fabrics were used to test the hypothesis in this preliminary study. Seebeck and the Peltier effects were proven to exist. However, thermoelectricity effect between two conducting polymer coated fabric samples was only about 10 μV/°C. Cooling effect by conductive polymer powder was achieved but performance was unsteady due to electrical degradation of the conducting polymer. Nevertheless, the concept was demonstrated and the development of a cooling fabric is possible.