Lorcan Coyle's Home on Tinterweb

Keywords:

Abstract:

Pervasive computing requires the ability to detect user activity in order to provide situation-specific services. Case-based reasoning can be used for activity recognition by using sensor data obtained from the environment. Pervasive computing systems can grow to be very large, containing many users, sensors, objects and situations, thus raising the issue of scalability. This paper presents a case-based reasoning approach to activity recognition in a smart home setting. An analysis is performed on scalability with respect to case storage, and an ontology-based approach is proposed for case base maintenance. We succeeded in reducing the casebase size by a factor of one thousand, while increasing the accuracy in recognising some activities.

• Tagged
• XML
• BibTex

Introduction to CBML

Hayes et al. (1999) describe imposing a standard case-based view on the information system of an application in order to retrieve case-knowledge. They anticipated that a standard way of representing case based reasoning (CBR) information will make this easier to achieve and proposed a case representation language that would facilitate this. Without such a standard means of representing case data it is up to the application developer to shape the case data from the available knowledge base. The manipulation of case data is dependent on the representation format chosen by the developer. This limits transformation of the data into a format suitable for the presentation layer, or its movement to another back-end component or between distributed CBR components. Hayes et al. proposed a standard case representation language called Case-Based Mark-up Language (CBML) in 1998. Our work in the field of CBR representation is a continuation of that work.

Keywords:

Abstract:

Case Based Reasoning has found increasing application on the Internet as a shopping assistant for e-commerce stores. The strength of CBR in this area stems from its reuse of the knowledge base associated with a particular application, thus providing an ideal way to make personalised configuration or technical information available to the Internet user. Since case data may be one aspect of a company's entire knowledge system, it is important to integrate case data easily within a company's IT infrastructure, providing in effect a CBR 'View' on the company knowledge base. We describe CBML, an XML-based Case Mark-Up Language we have developed to facilitate such integration. We will detail the benefits of our system for industry in general in terms of extensibility, ease of reuse and interoperability. The language allows us to make the formal definition of the structure of our cases completely independent of the application code. In this way we allow the structure and definition of our cases to be described and modified easily. Such a language would also allow cases to be exchanged between heterogeneous CBR systems. As an example of how CBML might be used we describe our research on a wireless Case Based assistant for the travel market. In this application user profiles are marked up as sets of cases in CBML.

• Tagged
• XML
• BibTex

Keywords:

Abstract:

Because of the changing nature of spam, a spam filtering system that uses machine learning will need to be dynamic. This suggests that a case-based (memory-based) approach may work well. Case-Based Reasoning (CBR) is a lazy approach to machine learning where induction is delayed to run time. This means that the case base can be updated continuously and new training data is immediately available to the induction process. In this paper we present a detailed description of such a system called ECUE and evaluate design decisions concerning the case representation. We compare its performance with an alternative system that uses Naïve Bayes (NB). We find that there is little to choose between the two alternatives in cross-validation tests on data sets. However, ECUE does appear to have some advantages in tracking concept drift over time.

• Tagged
• XML
• BibTex

Keywords:

Abstract:

Because of the changing nature of spam, a spam filtering system that uses machine learning will need to be dynamic. This suggests that a case-based (memory-based) approach may work well. Case-Based Reasoning (CBR) is a lazy approach to machine learning where induction is delayed to run time. This means that the case base can be updated continuously and new training data is immediately available to the induction process. In this paper we present a detailed description of such a system called ECUE and evaluate design decisions concerning the case representation. We compare its performance with an alternative system that uses Naïve Bayes. We find that there is little to choose between the two alternatives in cross-validation tests on data sets. However, ECUE does appear to have some advantages in tracking concept drift over time.

• Tagged
• XML
• BibTex

Keywords:

Abstract:

Clearly, machine learning techniques can play an important role in filtering spam email because ample training data is available to build a robust classifier. However, spam filtering is a particularly challenging task as the data distribution and concept being learned changes over time. This is a particularly awkward form of concept drift as the change is driven by spammers wishing to circumvent the spam filters. In this paper we show that lazy learning techniques are appropriate for such dynamically changing contexts. We present a case-based system for spam filtering called ECUE that can learn dynamically. We evaluate its performance as the case-base is updated with new cases. We also explore the benefit of periodically redoing the feature selection process to bring new features into play. Our evaluation shows that these two levels of model update are effective in tracking concept drift.

• Tagged
• XML
• BibTex

Keywords:

Abstract:

Spam filtering is a particularly challenging machine learning task as the data distribution and concept being learned changes over time. It exhibits a particularly awkward form of concept drift as the change is driven by spammers wishing to circumvent spam filters. In this paper we show that lazy learning techniques are appropriate for such dynamically changing contexts. We present a case-based system for spam filtering that can learn dynamically. We evaluate its performance as the case-base is updated with new cases. We also explore the benefit of periodically redoing the feature selection process to bring new features into play. Our evaluation shows that these two levels of model update are effective in tracking concept drift.

• Tagged
• XML
• BibTex

Keywords:

Abstract:

We introduce the Fionn framework for developing CBR systems. We outline the evaluation framework that underpins the feature selection and similarity learning process and we present a brief description of the Explanation-Guided Retrieval mechanism in Fionn.

• Tagged
• XML
• BibTex

Keywords:

Abstract:

Conversational recommender systems have recently emerged as useful alternative strategies to their single-shot counterpart, especially given their ability to expose a user's current preferences. These systems use conversational feedback to hone in on the most suitable item for recommendation by improving the mechanism that finds useful collaborators. We propose a novel architecture for performing recommendation that incorporates information about the individual performance of neighbours during a recommendation session, into the neighbour retrieval mechanism. We present our architecture and a set of preliminary evaluation results that suggest there is some merit to our approach. We examine these results and discuss what they mean for future research.

• Tagged
• XML
• BibTex

Keywords:

Abstract:

As e-commerce has become more popular, the problem of information overload has come to the fore. Recommender systems that reduce the information overload problem are becoming more common. However, the problem with many recommender systems is that they are associated with a high cost of learning customer preferences (in terms of cognitive load). We describe the Personal Travel Assistant (PTA), a flight recommender application that uses case-based reasoning (CBR) to overcome these problems.

The PTA allows users to search multiple flights providers concurrently and recommends flights based on their individual travel preferences. These preferences are implicitly learned from observations of user behaviour. When the user purchases a flight, the PTA uses the selection of a preferred flight to discover and refine the user's overall travel preferences. These preferences are stored in a user-model as sets of cases representing their interactions, which are used to provide personalised recommendations.

The PTA makes recommendations taking into account the context in which the flights were offered. It uses features from the request to determine this context, e.g. the duration of the trip. We perform evaluations of contextual recommendations that support our view that user preferences change depending on the context of the session. We further improve recommendation accuracy by storing and personalising similarity measures in the user-model. The PTA alters the relative importance of features in the personal similarity measure based on implicit user feedback, e.g. increasing the importance of price at the cost of stop-over time in a multiple hop flight.

We also investigate cooperative components to extend our recommendation strategies. These allow users to reuse the information learned from other users when they encounter new situations. However, these techniques are not as successful as we had hoped. We discuss these components in relation to other work on collaborative recommendation and suggest that the standard approach is unsuited to the PTA's context-based recommendation strategy.

The strength of CBR in the e-commerce domain stems from its reuse of the knowledge base associated with a particular application. Since case data may be one aspect of a company's entire knowledge system, it is important to integrate case data easily within a company's IT infrastructure, providing in effect a case-based view on relevant portions of the company knowledge base. We describe CBML, an XML-based Case Mark-Up Language we have developed to facilitate such integration.

• Tagged
• XML
• BibTex