Results 1  10
of
18
MultiDimensional Relational Sequence Mining
, 2008
"... The issue addressed in this paper concerns the discovery of frequent multidimensional patterns from relational sequences. The great variety of applications of sequential pattern mining, such as user profiling, medicine, local weather forecast and bioinformatics, makes this problem one of the centr ..."
Abstract

Cited by 13 (10 self)
 Add to MetaCart
The issue addressed in this paper concerns the discovery of frequent multidimensional patterns from relational sequences. The great variety of applications of sequential pattern mining, such as user profiling, medicine, local weather forecast and bioinformatics, makes this problem one of the central topics in data mining. Nevertheless, sequential information may concern data on multiple dimensions and, hence, the mining of sequential patterns from multidimensional information results very important. In a multidimensional sequence each event depends on more than one dimension, such as in spatiotemporal sequences where an event may be spatially or temporally related to other events. In literature, the multirelational data mining approach has been successfully applied to knowledge discovery from complex data. However, there exists no contribution to manage the general case of multidimensional data in which, for example, spatial and temporal information may coexist. This work takes into account the possibility to mine complex patterns, expressed in a firstorder language, in which events may occur along different dimensions. Specifically, multidimensional patterns are defined as a set of atomic firstorder formulae in which events are explicitly represented by a variable and the relations between events are represented by a set of dimensional predicates. A complete framework and an Inductive Logic Programming algorithm to tackle this problem are presented along with some experiments on artificial and real multidimensional sequences proving its effectiveness.
The Design and Evaluation of Web Prefetching and Caching Techniques
, 2002
"... Userperceived retrieval latencies in the World Wide Web can be improved by preloading a local cache with resources likely to be accessed. A user requesting content that can be served by the cache is able to avoid the delays inherent in the Web, such as congested networks and slow servers. The diff ..."
Abstract

Cited by 13 (2 self)
 Add to MetaCart
Userperceived retrieval latencies in the World Wide Web can be improved by preloading a local cache with resources likely to be accessed. A user requesting content that can be served by the cache is able to avoid the delays inherent in the Web, such as congested networks and slow servers. The difficulty, then, is to determine what content to prefetch into the cache. This work explores machine learning algorithms for user sequence prediction, both in general and specifically for sequences of Web requests. We also consider information retrieval techniques to allow the use of the content of Web pages to help predict future requests. Although historybased mechanisms can provide strong performance in predicting future requests, performance can be improved by including predictions from additional sources. While past researchers have used a variety of techniques for evaluating caching algorithms and systems, most of those methods were not applicable to the evaluation of prefetching algorithms or systems. Therefore, two new mechanisms for evaluation are introduced. The first is a detailed tracebased simulator, built from scratch,
Constraint based mining of first order sequences in SeqLog
 In Database Support for Data Mining Applications: Discovering Knowledge with Inductive Queries
, 2004
"... Abstract. A logical language, SeqLog, for mining and querying sequential data and databases is presented. In SeqLog, data takes the form of a sequence of logical atoms, background knowledge can be specified using DataLog style clauses and sequential queries or patterns correspond to subsequences of ..."
Abstract

Cited by 11 (0 self)
 Add to MetaCart
Abstract. A logical language, SeqLog, for mining and querying sequential data and databases is presented. In SeqLog, data takes the form of a sequence of logical atoms, background knowledge can be specified using DataLog style clauses and sequential queries or patterns correspond to subsequences of logical atoms. SeqLog is then used as the representation language for the inductive database mining system MineSeqLog. Inductive queries in MineSeqLog take the form of a conjunction of a monotonic and an antimonotonic constraint on sequential patterns. Given such an inductive query, MineSeqLog will efficiently compute the borders of the solution space. MineSeqLog uses variants of the famous levelwise algorithm together with ideas from version spaces to realize this. Finally, we report on a number of experiments in the domains of usermodeling that validate of the approach. 1 Introduction Data mining has been a hot research topic in recent years, and the mining ofknowledge from data of various models has been studied. One popular data model that has attracted a lot of attention concerns sequential data [2, 20, 13,6, 21, 22]. Many of these approaches are extensions of the classical levelwise itemset discovery algorithm "Apriori"[1]. However, the data models that havebeen used so far for modeling sequential patterns are not very expressive and often based on some form of propositional logic. The need for more expressivekind of patterns arises e.g. when modeling Unixusers [9]. E.g. the command sequence 1. ls 2. vi paper.tex 3. latex paper.tex 4. dvips paper.dvi 5. lpr paper.ps
Firstorder temporal pattern mining with regular expression constraints
 In 20th Brazilian Symposium on Databases
, 2005
"... Previous studies on mining sequential patterns have focused on temporal patterns specified by some form of propositional temporal logic. However, there are some interesting sequential patterns whose specification needs a more expressive formalism, the firstorder temporal logic. Multisequential pat ..."
Abstract

Cited by 8 (2 self)
 Add to MetaCart
(Show Context)
Previous studies on mining sequential patterns have focused on temporal patterns specified by some form of propositional temporal logic. However, there are some interesting sequential patterns whose specification needs a more expressive formalism, the firstorder temporal logic. Multisequential patterns are firstorder temporal patterns and aim at representing the behaviour of individuals related to each other by some criteria, throughout time. They appear in many application domains, like financial market and retailing. In this paper, we extend a wellknown usercontrolled tool, based on regular expressions constraints, to the multisequential pattern context. This specification tool enables the incorporation of user focus into the multisequential patterns mining process. We present MSPMiner, an Aprioribased algorithm to discover all frequent multisequential patterns satisfying a userspecified regular expression constraint. We perform detailed experiments on synthetic data to study the performance of MSPMiner.
Milprit: Mining interval logic patterns with regular expression constraints
 In 1st Brazilian Workshop on Data Mining Algorithms
, 2005
"... Abstract. Most methods for temporal pattern mining assume that time is pontual, that is, represented by points in a straight line beginning at some initial instant. In this paper, we consider a new temporal pattern, where time is explicitly represented by intervals. We present the algorithm MILPRI ..."
Abstract

Cited by 4 (2 self)
 Add to MetaCart
(Show Context)
Abstract. Most methods for temporal pattern mining assume that time is pontual, that is, represented by points in a straight line beginning at some initial instant. In this paper, we consider a new temporal pattern, where time is explicitly represented by intervals. We present the algorithm MILPRIT for mining these kind of temporal patterns, which uses variants of the classical levelwise search algorithms. We also present some preliminary experimental results and discuss further applications.
Relational Temporal Data Mining for Wireless Sensor Networks
"... Abstract. Wireless sensor networks (WSNs) represent a typical domain where there are complex temporal sequences of events. In this paper we propose a relational framework to model and analyse the data observed by sensor nodes of a wireless sensor network. In particular, we extend a general purpose r ..."
Abstract

Cited by 3 (1 self)
 Add to MetaCart
(Show Context)
Abstract. Wireless sensor networks (WSNs) represent a typical domain where there are complex temporal sequences of events. In this paper we propose a relational framework to model and analyse the data observed by sensor nodes of a wireless sensor network. In particular, we extend a general purpose relational sequence mining algorithm to tackle into account temporal intervalbased relations. Realvalued time series are discretized into similar subsequences and described by using a relational language. Preliminary experimental results prove the applicability of the relational learning framework to complex real world temporal data.
Mining Temporal Relational Patterns over Databases with Hybrid Time Domains
 XXII SIMPÓSIO BRASILEIRO DE BANCO DE DADOS
, 2007
"... Most methods for temporal pattern mining assume that time is represented by points in a straight line starting at some initial instant. Discovering sequential patterns in customer’s transactions is a wellknown application where such data mining methods have been used successfully. In this paper, we ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
(Show Context)
Most methods for temporal pattern mining assume that time is represented by points in a straight line starting at some initial instant. Discovering sequential patterns in customer’s transactions is a wellknown application where such data mining methods have been used successfully. In this paper, we consider a new kind of temporal pattern where both interval and punctual time representation are considered. These patterns, which we call temporal pointinterval patterns aim at capturing how events taking place during different time periods or at different time instants relate to each other. The datasets where these kind of patterns may appear are temporal relational databases whose relations contain point or interval timestamps. We use a simple extension of Allen’s Temporal Interval Logic as a formalism for specifying these temporal patterns. We also present the algorithm MILPRIT∗ for mining temporal pointinterval patterns, which uses variants of the classical levelwise search algorithms. Besides, MILPRIT∗ allows a broad spectrum of constraints to be incorporated into the mining process. These constraints aim at restricting the search space (and so, improving the algorithm perfomance) as well as returning patterns closer to user interest. Finally, we present an extensive set of experiments of MILPRIT∗ executed over synthetic and real data and analyse its results.
P.: Mining FirstOrder Temporal Interval Patterns with Regular Expression Constraints
 in: Proceedings of the 9th International Conference on Data Warehousing and Knowledge Discovery
"... Abstract. Most methods for temporal pattern mining assume that time is represented by points in a straight line starting at some initial instant. In this paper, we consider a new kind of first order temporal pattern, specified in Allen’s Temporal Interval Logic, where time is explicitly represented ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
(Show Context)
Abstract. Most methods for temporal pattern mining assume that time is represented by points in a straight line starting at some initial instant. In this paper, we consider a new kind of first order temporal pattern, specified in Allen’s Temporal Interval Logic, where time is explicitly represented by intervals. We present the algorithm MILPRIT for mining temporal interval patterns, which uses variants of the classical levelwise search algorithms. MILPRIT allows a broad spectrum of constraints over temporal patterns to be incorporated in the mining process. Some experimental results over synthetic and real data are presented.
Dynamic Website Mining
"... Web servers log how a user interacts with a website. This can provide the website author with valuable information about the `audience' of the site. However with dynamically generated pages, such an analysis has become more difficult. In this paper we present some ideas about how machine learni ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
Web servers log how a user interacts with a website. This can provide the website author with valuable information about the `audience' of the site. However with dynamically generated pages, such an analysis has become more difficult. In this paper we present some ideas about how machine learning techniques can be used to analyse these data. We apply these techniques to real world data and present preliminary results.
Relational Sequence Clustering for Aggregating Similar Agents
"... Abstract. Many clustering methods are based on flat descriptions, while data regarding realworld domains include heterogeneous objects related to each other in multiple ways. For instance, in the field of MultiAgent System, multiple agents interact with the environment and with other agents. In th ..."
Abstract
 Add to MetaCart
(Show Context)
Abstract. Many clustering methods are based on flat descriptions, while data regarding realworld domains include heterogeneous objects related to each other in multiple ways. For instance, in the field of MultiAgent System, multiple agents interact with the environment and with other agents. In this case, in order to act effectively an agent should be able to recognise the behaviours adopted by other agents. Actions taken by an agent are sequential, and thus its behaviour can be expressed as a sequence of actions. Inferring knowledge about competing and/or companion agents by observing their actions is very beneficial to construct a behavioural model of the agent population. In this paper we propose a clustering method for relational sequences able to aggregate companion agent behaviours. The algorithm has been tested on a real world dataset proving its validity.