IEEE Transactions on Knowledge and Data Engineering

IEEE Transactions on Knowledge and Data Engineering - October 2008 (Vol. 20, No. 10)

PrePrint: Evaluating the Effectiveness of Personalized Web Search

Although personalized web search has been under way for many years and many personalization algorithms have been investigated, it is still unclear whether personalization is consistently effective on different queries for different users, and under different search contexts. In this paper, we study this problem and provide some findings. We present a large-scale evaluation framework for personalized search based on query logs, and then evaluate five personalized search algorithms (including two click-based ones and three topical interest-based ones) using 12-day query logs of Windows Live Search. By analyzing the results, we reveal that personalized Web search does not work equally well under various situations. It represents a significant improvement over generic Web search for some queries while it has little effect and even harms query performance under some situations. We propose click entropy as a simple measurement on whether a query should be personalized. We further propose several features to automatically predict when a query will benefit from a specific personalization algorithm. Experimental results show that using a personalization algorithm for queries selected by our prediction model is better than using it simply for all queries.

PrePrint: A Pure Nash Equilibrium Based Game Theoretical Method for Data Replication Across Multiple Servers

This paper proposes a non-cooperative game based technique to replicate data objects across a distributed system of multiple servers in order to reduce user perceived Web access delays. In the proposed technique computational agents represent servers and compete with each other to optimize the performance of their servers. The optimality of a non-cooperative game is typically described by Nash equilibrium, which is based on spontaneous and non-deterministic strategies. However, Nash equilibrium may or may not guarantee system-wide performance. Furthermore, there can be multiple Nash equilibria, making it difficult to decide which one is the best. In contrast, the proposed technique uses the notion of pure Nash equilibrium, which if achieved, guarantees stable optimal performance. In the proposed technique, agents use deterministic strategies that work in conjunction with their self-interested nature but ensure system-wide performance enhancement. In general, the existence of a pure Nash equilibrium is hard to achieve, but we prove the existence of such equilibrium in the proposed technique. The proposed technique is also experimentally compared against some well-known conventional replica allocation methods, such as branch and bound, greedy, and genetic algorithms.

PrePrint: A Generic Local Algorithm for Mining Data Streams in Large Distributed Systems

In a large network of computers or wireless sensors, each of the components (henceforth, peers) has some data about the global state of the system. Much of the system's functionality such as message routing, information retrieval and load sharing relies on modeling the global state. We refer to the outcome of the function (e.g., the load experienced by each peer) as the \emph{model} of the system. Since the state of the system is constantly changing, it is necessary to keep the models up-to-date. Computing global data mining models e.g. decision trees, $k$-means clustering in large distributed systems may be very costly due to the scale of the system and due to communication cost, which may be high. The cost further increases in a dynamic scenario when the data changes rapidly. In this paper we describe a two step approach for dealing with these costs. First, we describe a highly efficient \emph{local} algorithm which can be used to monitor a wide class of data mining models. Then, we use this algorithm as a feedback loop for the monitoring of complex functions of the data such as its $k$-means clustering. The theoretical claims are corroborated with a thorough experimental analysis.

PrePrint: Effective and Efficient Query Processing for Video Subsequence Identification

Content-based video retrieval has been well investigated. However, despite the importance, few studies on video subsequence identification, which is to find the similar content to a short query clip from a long video sequence, have been published. This paper presents a graph transformation and matching approach to this problem, with extension to identify the occurrence of potentially different ordering, alignment or length due to content editing. With a batch query algorithm to retrieve similar frames, the mapping relationship between the query and the database video is first represented by a bipartite graph. The densely matched parts along the long sequence are then extracted, followed by a filter-and-refine search strategy to prune some irrelevant subsequences. During the filtering stage, Maximum Size Matching (MSM) is deployed for each subgraph constructed by the query and candidate subsequence to obtain a smaller set of candidates. During the refinement stage, Sub-Maximum Similarity Matching (SMSM) is devised to identify the subsequence, according to a robust video similarity model which incorporates visual content, temporal order, frame alignment and length information. The performance studies conducted on a long and diverse video recording validate our approach is promising in terms of both search accuracy and speed.

PrePrint: Privacy-Preserving Kth Element Score over Vertically Partitioned Data

Given a large integer dataset shared vertically by two parties, we consider the problem of securely computing a score separating the kth and the k+1st element. An efficient secure protocol is developed to compute such a score while revealing little additional information. The proposed protocol is implemented using the Fairplay system and experimental results are reported. We show a real application of this protocol as a component used in the secure processing of top-k queries over vertically partitioned data.

PrePrint: Distributional Features for Text Categorization

Text categorization is the task of assigning predefined categories to natural language text. With the widely used 'bag of words' representation, previous researches usually assign a word with values such that whether this word appears in the document concerned or how frequently this word appears. Although these values are useful for text categorization, they have not fully expressed the abundant information contained in the document. This paper explores the effect of other types of values, which express the distribution of a word in the document. These novel values assigned to a word are called {\it distributional features}, which include the compactness of the appearances of the word and the position of the first appearance of the word. The proposed distributional features are exploited by a {\it tfidf} style equation and different features are combined using ensemble learning techniques. Experiments show that the distributional features are useful for text categorization. In contrast to using the traditional term frequency values solely, including the distributional features requires only a little additional cost, while the categorization performance can be significantly improved. Further analysis shows that the distributional features are especially useful when documents are long and the writing style is casual.

PrePrint: On the Effect of Location Uncertainty in Spatial Querying

An emerging topic in the field of spatial data management is the handling of location uncertainty of spatial objects, mainly due to inaccurate measurements. The literature on location uncertainty so far has focused on modifying traditional spatial search algorithms in order to handle the impact of objects' location uncertainty in query results. In this paper, we present the first, to the best of our knowledge, theoretical analysis that estimates the average number of false hits introduced in the results of rectangular range queries in the case of data points uniformly distributed in 2D space. Then, we relax the original distribution assumptions showing how to deal with arbitrarily distributed data points and more realistic location uncertainty distributions. The accuracy of the results of our analytical approach is demonstrated through an extensive experimental study using various synthetic and real datasets. Our proposal can be directly employed in spatial database systems in order to provide users with the accuracy of spatial query results based only on known dataset and query parameters.

PrePrint: Improving Personalization Solutions through Optimal Segmentation of Customer Bases

On the Web, where the search costs are low and the competition is just a mouse click away, it is crucial to segment the customers intelligently in order to offer more personalized products and services to them. Traditionally, customer segmentation is achieved using statistics-based methods that compute a set of statistics from the customer data and group customers into segments by applying distance-based clustering algorithms in the space of these statistics. In this paper, we present a direct grouping based approach to computing customer segments that groups customers in terms of optimally combining transactional data of several customers to build a predictive model of customer behavior for each group. We consider customer segmentation as a combinatorial optimization problem of finding the best partitioning of the customer base into disjoint groups and show that finding an optimal customer partition is NP-hard. We propose several suboptimal direct grouping segmentation methods, empirically compares them against traditional statistics-based hierarchical and affinity propagation based segmentation, and 1-to-1 methods across multiple experimental conditions. We show that the best direct grouping method builds mostly small sized customer segments and significantly dominates the statistics-based and 1-to-1 approaches across most of the experimental conditions, while still being computationally tractable.

PrePrint: Mining Projected Clusters in High-Dimensional Spaces

Clustering high-dimensional data has been a major challenge due to the inherent sparsity of the points. Most existing clustering algorithms become substantially inefficient if the required similarity measure is computed between data points in the full-dimensional space. To address this problem, a number of projected clustering algorithms have been proposed. However, most of them encounter difficulties when clusters hide in subspaces with very low dimensionality. These challenges motivate our effort to propose a robust partitional distance-based projected clustering algorithm. The algorithm consists of three phases. The first phase performs attribute relevance analysis by detecting dense and sparse regions and their location in each attribute. Starting from the results of the first phase, the goal of the second phase is to eliminate outliers, while the third phase aims to discover clusters in different subspaces. The clustering process is based on the K-means algorithm, with the computation of distance restricted to subsets of attributes where object values are dense. Our algorithm is capable of detecting projected clusters of low dimensionality embedded in a high-dimensional space and avoids the computation of the distance in the full-dimensional space. The suitability of our proposal has been demonstrated through an empirical study using synthetic and real datasets.

PrePrint: Progressive Parametric Query Optimization

Commercial applications usually rely on pre-compiled parameterized procedures to interact with a database. Unfortunately, executing a procedure with a set of parameters different from those used at compilation time may be arbitrarily sub-optimal. Parametric query optimization (PQO) attempts to solve this problem by exhaustively determining the optimal plans at each point of the parameter space at compile time. However, PQO is likely not cost-effective if the query is executed infrequently or if it is executed with values only within a subset of the parameter space. In this paper we propose instead to progressively explore the parameter space and build a parametric plan during several executions of the same query. We introduce algorithms that, as parametric plans are populated, are able to frequently bypass the optimizer but still execute optimal or near-optimal plans.

PrePrint: Cost-Based Predictive Spatio-Temporal Join

A predictive spatio-temporal join finds all pairs of moving objects satisfying a join condition on future time and space. In this paper we present CoPST, the first and foremost algorithm for such a join using two spatio-temporal indexes. In a predictive spatio-temporal join, the bounding boxes of the outer index are used to perform window searches on the inner index, and these bounding boxes enclose objects with increasing laxity over time. CoPST constructs globally tightened bounding boxes "on the fly" to perform window searches during join processing, thus significantly minimizing overlap and improving the join performance. CoPST adapts gracefully to large scale databases, by dynamically switching between main-memory buffering and disk-based buffering, through a novel probabilistic cost model. Our extensive experiments validate the cost model and show its accuracy for realistic data sets. We also showcase the superiority of CoPST over algorithms adapted from state of the art spatial join algorithms, by a speedup of up to an order of magnitude.

PrePrint: Semantic Access to Multi-Channel M-Services

To support wireless-oriented services, a new generation of Web services called Mobile services (M-services) has emerged. M-services provide mobile users access to services through wireless networks. We present a novel mechanism for effectively delivering M-services and wireless data to mobile users in wireless broadcast environments. We propose a semantics based approach for efficiently accessing composite services from multiple broadcast channels. We also discuss different channel organizations and study their impact on access efficiency.

PrePrint: Learning Image-Text Associations

Web information fusion can be defined as the problem of collating and tracking information related to specific topics on the World Wide Web. Whereas most existing work on web information fusion has focused on text-based multi-document summarization, this paper concerns the topic of image and text association, a cornerstone of cross-media web information fusion. Specifically, we present two learning methods for discovering the underlying associations between images and texts based on small training data sets. The first method based on vague transformation measures the information similarity between the visual features and the textual features through a set of predefined domain-specific information categories. Another method uses a neural network to learn direct mapping between the visual and textual features by automatically and incrementally summarizing the associated features into a set of information templates. Despite their distinct approaches, our experimental results on a terrorist domain document set show that both methods are capable of learning associations between images and texts from a small training data set.

Presented By:

Ads by Pheedo

PrePrint: Detecting, Assessing and Monitoring Relevant Topics in Virtual Information Environments

The ability to assess the relevance of topics and related sources in information-rich environments is a key to success when scanning business environments. This paper introduces a hybrid system to support managerial information gathering. The system is made up of three components: (1) a hierarchical hyperbolic SOM for structuring the information environment and visualizing the intensity of news activity with respect to identified topics, (2) a spreading activation network for the selection of the most relevant information sources with respect to an already existing knowledge infrastructure, and (3) measures of interestingness for association rules as well as statistical testing facilitates the monitoring of already identified topics. Embedding the system by a framework describing three modes of human information seeking behavior endorses an active organization, exploration and selection of information that matches the needs of decision makers in all stages of the information gathering process. By applying our system in the domain of the hotel industry we demonstrate how typical information gathering tasks are supported. Moreover, we present an empirical study investigating the effectiveness and efficiency of the visualization framework of our system.

PrePrint: On-Line Scheduling Sequential Objects with Periodicity for Dynamic Information Dissemination

The scalability of data broadcasting has been manifested by prior studies on the base of the traditional data management systems where data objects, mapped to a pair of state and value in the database, are independent, persistent, and static against simple queries. However, many modern information applications spread dynamic data objects and process complex queries for retrieving multiple data objects. Particularly, the information servers dynamically generate data objects that are dependent and can be associated into a complete response against complex queries. Accordingly, the study in this paper considers the problem of scheduling dynamic broadcast data objects in a clients-providers-servers system from the standpoint of data association, dependency, and dynamics. Since the data broadcast problem is NP-Hard, we derive the lower and the upper bounds of mean service access time. In light of the theoretical analyses, we further devise a deterministic algorithm with several gain measure functions for the approximation of schedule optimization. The experimental results show that the proposed algorithm is able to generate a dynamic broadcast schedule and also minimize the mean service access time to the extent of being very close to the theoretical optimum.

PrePrint: The Development of Fuzzy Rough Sets with the Use of Structures and Algebras of Axiomatic Fuzzy Sets

The notion of a rough set was originally proposed by Pawlak underwent a number of extensions and generalizations. Dubois and Prade (1990) introduced fuzzy rough sets which involve the use of rough sets and fuzzy sets within a single framework. Radzikowska and Kerre (2002) proposed a broad family of fuzzy rough sets, referred to as ( t)-fuzzy rough sets which are determined by some implication operator (implicator), and a certain t-norm. In order to describe the linguistically represented concepts coming from data available in some information system, the concept of fuzzy rough sets are redefined and further studied in the setting of the Axiomatic Fuzzy Set (AFS) theory. Compared with the ( t)-fuzzy rough sets, the advantages of AFS fuzzy rough sets are twofold. They can be directly applied to data analysis present in any information system without resorting to the details concerning the choice of the implication, t-norm and a similarity relation S. Furthermore such rough approximations of fuzzy concepts come with a well-defined semantics and therefore offer a sound interpretation. Some examples are included to illustrate the effectiveness of the proposed construct. It is shown that the AFS fuzzy rough sets provide a far higher flexibility and effectiveness in comparison with rough sets and some of their generalizations.

PrePrint: Efficient Processing of Metric Skyline Queries

Skyline query is of great importance in many applications, such as multi-criteria decision making and business planning. In particular, a skyline point is a data object in the database whose attribute vector is not dominated by that of any other objects. Previous methods to retrieve skyline points usually assume static data objects in the database (i.e. their attribute vectors are fixed), whereas several recent work focus on skyline queries with dynamic attributes. In this paper, we propose a novel variant of skyline queries, namely metric skyline, whose dynamic attributes are defined in the metric space (i.e. not limited to the Euclidean space). We illustrate an efficient and effective pruning mechanism to answer metric skyline queries through a metric index. Most importantly, we formalize the query performance of the metric skyline query in terms of the pruning power, by a cost model, in light of which we construct an optimized metric index aiming to maximize the pruning power of metric skyline queries. Extensive experiments have demonstrated the efficiency and effectiveness of our proposed pruning techniques as well as the constructed index in answering metric skyline queries.

PrePrint: Optimal Lot Sizing Policies For Sequential Online Auctions

This study proposes methods for determining the optimal lot sizes for sequential auctions that are conducted to sell sizable quantities of an item. These auctions are fairly common in business to consumer (B2C) auctions. In these auctions, the tradeoff for the auctioneer is between the alacrity with which funds are received, and the amount of funds collected by the faster clearing of inventory using larger lot sizes. Observed bids in these auctions impact the auctioneer's decision on lot sizes in future auctions. We first present a goal programming approach for estimating the bid distribution for the bidder population from the observed bids, readily available in these auctions. We then develop models to compute optimal lot sizes for both stationary and non-stationary bid distributions. For stationary bid distribution, we present closed form solutions and structural results. Our findings show that the optimal lot size increases with inventory holding costs and number of bidders. Our model for non-stationary bid distribution captures the inter-auction dynamics such as the number of bidders, their bids, past winning bids, and lot size. We use simulated data to test the robustness of our model.

PrePrint: Interactive Correction and Recommendation for Computer Language Learning and Training

Active learning and training is a particularly effective form of education. In various domains, skills are equally important to knowledge. We present an automated learning and skills training system for a database programming environment that promotes procedural knowledge acquisition and skills training. The system provides meaningful, knowledge-level feedback such as correction of student solutions and personalised guidance through recommendations. Specifically, we address automated synchronous feedback and recommendations based on personalised performance assessment. At the core of the tutoring system is a pattern-based error classification and correction component that analyses student input in order to provide immediate feedback and in order to diagnose student weaknesses and suggest further study material. A syntax-driven approach based on grammars and syntax trees provides the solution for a semantic analysis technique. Syntax tree abstractions and comparison techniques based on equivalence rules and pattern matching are specific approaches.

PrePrint: Learning in an Ambient Intelligent World: Enabling Technologies and Practices

The rapid evolution of information and communication technology opens a wide spectrum of opportunities to change our surroundings into an Ambient Intelligent (AmI) world. AmI is a vision of future information society, where people are surrounded by a digital environment which is sensitive to their needs, personalized to their requirements, anticipatory of their behavior, and responsive to their presence. It emphasizes on greater user-friendliness, user-empowerment, and more effective service support, with an aim to bring information and communication technology to everyone, every home, every business, and every school, thus improving the quality of human life. AmI unprecedentedly enhances learning experiences by endowing the users with the opportunities of learning in context, a breakthrough from the traditional educational settings. In this survey paper, we examine some major characteristics of an AmI learning environment. To deliver a feasible and effective solution to ambient learning, we overview a few latest developed enabling-technologies in context-awareness, and interactive learning. Associated practices are meanwhile reported. We also describe our experience in designing and implementing a smart class prototype, which allows teachers to simultaneously instruct both local and remote students in a context-aware and natural way.

PrePrint: Distributed Skyline Retrieval with Low Bandwidth Consumption

We consider skyline computation when the underlying dataset is horizontally partitioned onto geographically distant servers \color{red} that are connected to the Internet. \color{black} The existing solutions are not suitable for our problem, because they have at least one of the following drawbacks: (i) applicable only to distributed systems adopting vertical partitioning or restricted horizontal partitioning, (ii) effective only when each server has limited computing and communication abilities, and (iii) optimized only for skyline search in subspaces but inefficient in the full space. This paper proposes an algorithm, called {\em feedback-based distributed skyline} (FDS), to support arbitrary horizontal partitioning. \color{red} FDS aims at minimizing the network bandwidth, measured in the number of tuples transmitted over the network. \color{black} The core of FDS is a novel feedback-driven mechanism, where the coordinator iteratively transmits certain feedback to each participant. Participants can leverage such information to prune a large amount of local data, which otherwise would need to be sent to the coordinator. Extensive experimentation confirms that FDS significantly outperforms alternative approaches in both effectiveness and progressiveness.

PrePrint: Communities and Emerging Semantics in Semantic Link Network: Discovery and Learning

The World Wide Web contains plentiful Web resources, but hyperlinks connect Web resources for browsing freely rather than for effective learning. To support in-depth learning, e-learning systems should be able to discover and make use of semantic communities and emerging semantic relations in dynamic complex network of learning resources. Previous graph-based community discovery approaches are limited in semantic ability to discover semantic communities. This paper firstly proposes the Semantic Link Network SLN, a loosely coupled semantic data model that can semantically link resources with each other and derive out implicit semantic links according to a set of relational reasoning rules. Then, it proposes two approaches to discover semantic communities in SLN: the decomposition approach and the construction approach. By studying the intrinsic relationship between semantic communities in SLN and semantic closures in reasoning rules, an approach is proposed to discover and manage semantic communities in large SLN. Further, the approach to discover emerging semantic relations in dynamic SLN is proposed. An e-learning environment incorporating the proposed approaches is introduced to support effective discovery and learning.

PrePrint: BMQ-Processor: A High-Performance Border-Crossing Event Detection Framework for Large-scale Monitoring Applications

In this paper, we present BMQ-Processor, a high-performance border-crossing event detection framework for largescale monitoring applications. We first characterize a new query semantics, namely, Border Monitoring Query (BMQ), which is useful for border-crossing event detection in many monitoring applications. It monitors the values of data streams and reports them only when data streams cross the borders of its range. We then propose BMQ-Processor to efficiently handle a large number of BMQs over a high volume of data streams. BMQ-Processor efficiently processes BMQs in a shared and incremental manner. It develops and operates over a novel stateful query index, achieving a high level of scalability over continuous data updates. Also, it utilizes the locality embedded in data streams and greatly accelerates successive BMQ evaluations. We present data structures and algorithms to support one-dimensional as well as multi-dimensional BMQs. We show that the semantics of border monitoring can be extended toward more advanced ones and build region transition monitoring as a sample case. Lastly, we demonstrate excellent processing performance and low storage cost of BMQ-Processor through extensive analysis and experiments.

PrePrint: Storing and Indexing Spatial Data in P2P Systems

he P2P paradigm has become very popular for storing and sharing information in a totally decentralized manner. At first, research focused on P2P systems that host one-dimensional data. Nowadays, the need for P2P applications with multi-dimensional data has emerged motivating research on P2P systems that manage such data. The majority of the proposed techniques are based either on the distribution of centralized indexes or on the reduction of multi-dimensional data to one dimension. Our goal is to create from scratch a technique that is inherently distributed and also maintains the multi-dimensionality of data. Our focus is on structured P2P systems that share spatial information. We present SpatialP2P, a totally decentralized indexing and searching framework that is suitable for spatial data. SpatialP2P supports P2P applications in which spatial information of various sizes can be dynamically inserted or deleted, and peers can join or leave. The proposed technique preserves well locality and directionality of space.

PrePrint: Clustering and Sequential Pattern Mining of Online Collaborative Learning Data

Group work is widespread in education. The growing use of online tools supporting group work generates huge amounts of data. We aim to exploit this data to support mirroring: presenting useful high-level views of information about the group, together with desired patterns characterizing the behaviour of strong groups. The goal is to enable the groups and their facilitators to see relevant aspects of the group's operation and provide feedback if these are more likely to be associated with positive or negative outcomes and where the problems are. We explore how useful mirror information can be extracted via a theory-driven approach and a range of clustering and sequential pattern mining. The context is a senior software development project where students use the collaboration tool TRAC. We extract patterns distinguishing the better from the weaker groups and get insights in the success factors. The results point to the importance of leadership and group interaction, and give promising indications if they are occurring. Patterns indicating good individual practices were also identified. We found that some key measures can be mined from early data. The results are promising for advising groups at the start and early identification of effective/poor practices, in time for remediation.

PrePrint: Towards A Fuzzy Domain Ontology Extraction Method for Adaptive e-Learning

With the wide spread applications of e-Learning technologies to education at all levels, increasing number of online educational resources and messages are generated from the corresponding e-Learning environments. Accordingly, instructors are often overwhelmed by the huge number of messages created by students through online discussion forums. It is quite difficult, if not totally impossible, for instructors to read through and analyze these messages to understand the progress of their students on the fly. As a result, adaptive teaching for a large class is handicapped. The main contribution of this paper is the illustration of a novel concept map generation mechanism which is underpinned by a fuzzy domain ontology extraction algorithm. The proposed mechanism can automatically construct concept maps based on the messages posted to online discussion forums. Our initial experimental results reveal that the accuracy and the quality of the automatically generated concept maps are promising. Our research work opens the door to the development and application of intelligent software tools to enhance e-Learning. To our best knowledge, the work presented in this paper demonstrates the first application of fuzzy domain ontology extraction method to facilitate adaptive e-Learning.

PrePrint: NNexus: An Automatic Linker for Collaborative Web-Based Corpora

In this paper, we introduce NNexus, a generalization of the automatic linking engine of Noosphere (at PlanetMath.org) and the first system that automates the process of linking disparate "encyclopedia" entries into a fully-connected conceptual network. The main challenges of this problem space include: 1) linking quality (correctly identifying which terms to link and which entry to link to with minimal effort on the part of users), 2) efficiency and scalability, and 3) generalization to multiple knowledge bases and web-based information environment. We present the NNexus approach that utilizes subject classification and other metadata to address these challenges. We also present evaluation results demonstrating the effectiveness and efficiency of the approach and discuss ongoing and future directions of research.

PrePrint: Efficient Evaluation of Probabilistic Advanced Spatial Queries on Existentially Uncertain Data

We study the problem of answering spatial queries in databases where objects exist with some uncertainty and they are associated with an existential probability. The goal of a thresholding probabilistic spatial query is to retrieve the objects that qualify the spatial predicates with probability that exceeds a threshold. Accordingly, a ranking probabilistic spatial query selects the objects with the highest probabilities to qualify the spatial predicates. We propose adaptations of spatial access methods and search algorithms for probabilistic versions of range queries, nearest neighbors, spatial skylines, and reverse nearest neighbors and conduct an extensive experimental study, which evaluates the effectiveness of proposed solutions.

PrePrint: Providing Flexible Process Support to Project-Centered Learning

While business process definition is becoming more and more popular as an instrument for describing human activities, there is a growing need for software tools supporting business process abstractions to help users organize and monitor their desktop work. Tools must be light-weight and flexible, so as to enable users to create or change the process as soon as there is a new need. In this article, we first describe an application-independent approach to flexible process support by discussing the abstractions required for modeling, creating, enacting, and modifying flexible processes. Then, we show our approach at work in the context of project-centered learning. Often, students are geographically dispersed or under severe timing constraints, because these activities intertwine with their normal university activity. As a result, they need communication technology in order to interact and workflow technology in order to organize their work. The platform provides a comprehensible, e-learning-specific set of activities and process templates, which can be combined through a simple Web interface into project-centered collaboration processes. We discuss how the general paradigm of flexible processes was adapted to the learning concept, implemented, and experienced by students.

PrePrint: Monitoring Online Tests Through Data Visualization

We present an approach and a system to let tutors monitor several important aspects related to on-line tests, such as learner behaviour and test quality. The approach includes the logging of important data related to learner interaction with the system during the execution of online tests, and exploits data visualization to highlight information useful to let tutors review and improve the whole assessment process. In particular, we have focused on the discovery of behavioural patterns of learners, and conceptual relationships among test items. We have led several experiments in our faculty in order to assess the whole approach. In particular, by analyzing the data visualization charts we have detected several previously unknown test strategies used by the learners. Further, we have detected several correlations among questions, which gave us useful feedbacks on the test quality.

PrePrint: Effective Collaboration with Information Sharing in Virtual Universities

A global education system, as a key area in future IT, has fostered developers providing various learning systems with low cost. While a variety of E-learning advantages have been recognized for a long time and many advances in E-learning systems have been implemented, the needs for effective information sharing in a secure manner have to date been largely ignored, especially for virtual university collaborative environments. Information sharing of virtual universities usually occurs in broad, highly dynamic network-based environments, and formally accessing the resources in a secure manner poses a difficult and vital challenge. This paper aims to build a new rule-based framework to identify and address issues of sharing in virtual university environments through role-based access control management (\textsl{RBAC}). The framework includes a role-based group delegation granting model, group delegation revocation model, authorization granting and authorization revocation. We analyze various revocations and the impact of revocations on role hierarchies. The implementation with \textsl{XML} - based tools demonstrates the feasibility of the framework and authorization methods. Finally, the current proposal is compared with other related work.

PrePrint: Decompositional Rule Extraction from Support Vector Machines by Active Learning

Support vector machines (SVMs) are currently state-of-the-art for the classification task and generally speaking exhibit good predictive performance, due to their ability to model non-linearities. However, their strength is also their main weakness, as the generated non-linear models are typically regarded as incomprehensible black-box models. In this paper, we propose a new Active Learning Based Approach (ALBA) to extract comprehensible rules from opaque SVM models. Through rule extraction, some insight is provided into the logics of the SVM model. ALBA extracts rules from the trained SVM model by explicitly making use of key concepts of the SVM: the support vectors, and the observation that these are typically close to the decision boundary. Active learning implies the focus on apparent problem areas, which for rule induction techniques are the regions close to the SVM decision boundary where most of the noise is found. By generating extra data close to these support vectors, that are provided with a class label by the trained SVM model, rule induction techniques are better able to discover suitable discrimination rules. This performance increase, both in terms of predictive accuracy as comprehensibility, is confirmed in our experiments where we apply ALBA on several publicly available datasets.

PrePrint: An Implementation of the CORDRA Architecture Enhanced for Systematic Reuse of Learning Objects

Abstract¡XThe SCORM (Sharable Content Object Reference Model) specification defines metadata of learning objects, which are used as the elementary reusable components in distance learning. The CORDRA (Content Object Repository Discovery and Registration/Resolution Architecture) specification provides a common architecture for the resolution, discovery, and sharing of these learning objects. These two specifications together define standardized ways in which learning objects can be discovered and reused by content designers. However, the current CORDRA and the definition of objects in SCORM only allow an object to be copied, updated, and re-organized in a new content aggregation, which is used as a delivery package to end users. This paper proposes a revised CORDRA architecture and a reusability mechanism to make instruction design easier. In particular, it proposes a structure called a reusability tree for tracking the history of reuse of learning objects in CORDRA. This paper also defines the notions of similarity, diversity, and relevancy of learning objects to make it easier for users to precisely search for and reuse learning objects.

PrePrint: $k$-Anonymization with Minimal Loss of Information

The technique of $k$-anonymization allows the releasing of databases that contain personal information while ensuring some degree of individual privacy. Anonymization is usually performed by generalizing database entries. We formally study the concept of generalization, and propose three information-theoretic measures for capturing the amount of information that is lost during the anonymization process. The proposed measures are more general and more accurate than those that were proposed by Meyerson and Williams~\cite{MW} and Aggarwal et al.\ \cite{AFK}. We study the problem of achieving $k$-anonymity with minimal loss of information. We prove that it is NP-hard and study polynomial approximations for the optimal solution. Our first algorithm gives an approximation guarantee of $O(\ln k)$ for two of our measures as well as for the previously studied measures. This improves the best-known $O(k)$-approximation of \cite{AFK}. While the previous approximation algorithms relied on the {\em graph representation} framework, our algorithm relies on a novel {\em hypergraph representation} that enables the improvement in the approximation ratio from $O(k)$ to $O(\ln k)$. As the running time of the algorithm is $O(n^{2k})$, we also show how to adapt the algorithm of \cite{AFK} in order to obtain an $O(k)$-approximation algorithm that is polynomial in both $n$ and $k$.

PrePrint: Multiclass MTS for Simultaneous Feature Selection and Classification

Multi-class Mahalanobis-Taguchi system (MMTS), the extension of MTS, is developed for simultaneous multi-class classification and feature selection. In MMTS, the multi-class measurement scale for is constructed by establishing an individual Mahalanobis space for each class. To increase the validity of the measurement scale, the Gram-Schmidt process is performed to mutually orthogonalize the features and eliminate the multicollinearity. The important features are identified using the orthogonal arrays and the signal-to-noise ratio, and are then used to construct a reduced model measurement scale. The contribution of each important feature to classification is also derived according to the effect gain to develop a weighted Mahalanobis distance which is finally used as the distance metric for the classification of MMTS. Using the reduced model measurement scale, an unknown example will be classified into the class with minimum weighted Mahalanobis distance considering only the important features. For evaluating the effectiveness of MMTS, a numerical experiment is implemented, and the results show that MMTS outperforms other well-known algorithms not only on classification accuracy but also on feature selection efficiency. Finally, a real case about gestational diabetes mellitus is studied, and the results indicate the practicality of MMTS in real world applications.

PrePrint: Sub-Ontology Based Resource Management for Web-Based E-Learning

Recent advances in Web and information technologies have resulted in many e-Learning resources. There is an emerging requirement to manage and reuse relevant resources together to achieve on-demand e-Learning in the Web. Ontologies have become a key technology for enabling semantics-driven resource management. We argue that to meet the requirements of semantic-based resource management for Web-based e-Learning, one should go beyond using domain ontologies statically. In this paper, we provide a semantic mapping mechanism to integrate e-Learning databases by using ontology semantics. Heterogeneous e-Learning databases can be integrated under a mediated ontology. Taking into account the locality of resource reuse, we propose to represent context-specific portions from the whole ontology as sub-ontologies. We propose a sub-ontology based approach for resource reuse based on an evolutionary algorithm. We also conduct simulation experiments to evaluate the proposed approach with a traditional Chinese medicine e-Learning scenario and obtain promising results.

PrePrint: Open Smart Classroom : Extensible and Scalable Learning System in Smart Space using Web Service Technology

Real-time interactive virtual classroom with tele-education experience is an important approach in distance learning. However, most current systems fail to meet new challenges in extensibility and scalability, which mainly lie on three issues. First, an open system architecture is required to better support the integration of increasing human-computer interfaces and personal mobile devices in classroom. Second, the learning system should facilitate opening its interfaces, which will help easy deployment coping with different circumstances and other learning systems to talk to each other. Third, the problems emerge on binding existing systems of classrooms together in different places or even different countries, such as tackling systems intercommunication and distant intercultural learning in different languages. To address these issues, we build a prototype application called Open Smart Classroom, built on our software infrastructure based on the multi-agent system architecture using Web Service technology in Smart Space. Besides the evaluation on the extensibility and scalability of the system, an experiment connecting two Open Smart Classrooms deployed in different countries is also undertaken, which focuses on the influence of these new features on the educational effect. Interesting and optimistic results obtained show a significant research prospect for developing future distant learning systems.

PrePrint: Self-Learning Disk Scheduling

Performance of disk I/O schedulers is affected by many factors, such as workloads, file systems, and disk systems. Disk scheduling performance can be improved by tuning scheduler parameters, such as the length of read timers. Scheduler performance tuning is mostly done manually. To automate this process, we propose four self-learning disk scheduling schemes: Change-sensing Round-Robin, Feedback Learning, Per-request Learning, and Two-layer Learning. Experiments show that the novel Two-layer Learning Scheme performs best. It integrates the workload-level and request-level learning algorithms. It employs feedback learning techniques to analyze workloads, change scheduling policy, and tune scheduling parameters automatically. We discuss schemes to choose features for workload learning, divide and recognize workloads, generate training data, and integrate machine learning algorithms into the Two-layer Learning Scheme. We conducted experiments to compare the accuracy, performance, and overhead of five machine learning algorithms: Decision Tree, Logistic Regression, Na�ve Bayes, Neural Network, and Support Vector Machine Algorithms. Experiments with real-world and synthetic workloads show that self-learning disk scheduling can adapt to a wide variety of workloads, file systems, disk systems, and user preferences. It outperforms existing disk schedulers by as much as 15.8% while consuming less than 3%-5% of CPU time.

PrePrint: Online Skyline Analysis with Dynamic Preferences on Nominal Attributes

The importance of skyline analysis has been well recognized in multi-criteria decision making applications. All of the previous studies assume a fixed order on the attributes in question. However, in some applications, users may be interested in skylines with respect to various total or partial orders on nominal attributes. In this paper, we identify and tackle the problem of online skyline analysis with dynamic preferences on nominal attributes. We investigate how changes of orders in attributes lead to changes of skylines. We address two novel types of interesting queries: a viewpoint query returns with respect to which orders a point is (or is not) in the skylines and an order-based skyline query retrieves the skyline with respect to a specific order. We develop two methods systematically and report an extensive performance study using both synthetic and real data sets to verify their effectiveness and efficiency.

PrePrint: A Relation-Based Page Rank Algorithm for Semantic Web Search Engines

With the tremendous growth of information available to end users through the Web, search engines come to play ever a more critical role. Nevertheless, because of their general purpose approach, it is always less uncommon that obtained result sets provide a burden of useless pages. Next generation Web architecture, represented by Semantic Web, provides the layered architecture possibly allowing to overcome this limitation. Several search engines have been proposed, which allow to increase information retrieval accuracy by exploiting a key content of Semantic Web resources, that is relations. However, in order to rank results, most of the existing solutions need to work on the whole annotated knowledge base. In this paper we propose a relation-based page rank algorithm to be used in conjunction with Semantic Web search engines that simply relies on information which could be extracted from user query and annotated resource. Relevance is measured as the probability that retrieved resource actually contains those relations whose existence was assumed by the user at the time of query definition.

PrePrint: Unsupervised Multiway Data Analysis: A Literature Survey

Two-way arrays or matrices are often not enough to represent all the information in the data and standard two-way analysis techniques commonly applied on matrices may fail to find the underlying structures in multi-modal datasets. Multiway data analysis has recently become popular as an exploratory analysis tool in discovering the structures in higher-order datasets, where data have more than two modes. We provide a review of significant contributions in the literature on multiway models, algorithms as well as their applications in diverse disciplines including chemometrics, neuroscience, social network analysis, text mining and computer vision.

PrePrint: Comparing Scores Intended for Ranking

Often ranking is performed on the the basis of some scores available for each item. The existing practice for comparing scoring functions is to compare the induced rankings by one of the multitude of rank comparison methods available in the literature. We suggest that it may be better to compare the underlying scores themselves. To this end, a generalized Kendall distance is defined, which takes into consideration not only the final ordering that the two schemes produce, but also at the spacing between pairs of scores. This is shown to be equivalent to comparing the scores after fusing with another set of scores, making it theoretically interesting. A top k version of the score comparison methodology is also provided. Experimental results clearly show the advantages score comparison has over rank comparison.

PrePrint: Using Context to Improve Predictive Modeling of Customers in Personalization Applications

The idea that context is important when predicting customer behavior has been maintained by scholars in marketing and data mining. However, no systematic study measuring how much the contextual information really matters in building customer models in personalization applications have been done before. In this paper we study how important the contextual information is when predicting customer behavior and how to use it when building customer models. It is done by conducting an empirical study across a wide range of experimental conditions. The experimental results show that context does matter when modeling the behavior of individual customers and that it is possible to infer the context from the existing data with reasonable accuracy in certain cases. It is also shown that significant performance improvements can be achieved if the context is "cleverly" modeled, as described in the paper. These findings have significant implications for data miners and marketers. They show that contextual information does matter in personalization applications and companies have different opportunities to both make context valuable for improving predictive performance of customers' behavior and decreasing the costs of gathering contextual information.

PrePrint: A Virtual Ring Method for Building Small-World Structured P2P Overlays

This paper presents a general virtual ring method to design and analyze small-world structured P2P networks on the base topologies embedded in ID spaces with distance metric. Its basic idea is to abstract a virtual ring from the base topology according to the distance metric, then build small-world long links in the virtual ring and map the links back onto the real network to construct the small-world routing tables for achieving logarithmic greedy routing efficiency. Four properties are proposed to characterize the base topologies that can be turned into small-world by the virtual ring method. The virtual ring method is applied to the base topologies of d-torus with Manhattan distance, high dimensional d-torus base topologies, and other base topologies including the unbalanced d-torus and the ring topology with tree distance. Theoretical analysis and simulation experiments demonstrate the efficiency and the resilience of the proposed overlays.

PrePrint: Efficient Range Query Processing in Peer-to-Peer Systems

With the increasing popularity of the peer-to-peer (P2P) computing paradigm, many general range query schemes for distributed hash table (DHT)-based P2P systems have been proposed in recent years. Although those schemes can provide range query capability without modifying the underlying DHTs, they have the query delay depending on both the scale of the system and the size of the query space or the specific query, and thus cannot guarantee to return the query results in a bounded delay. In this paper, we propose Armada, an efficient range query processing scheme to support delay-bounded single-attribute and multiple-attribute range queries. It is the first delay-bounded general range query scheme on constant-degree DHTs, and can return the results for any range query within 2logN hops in a P2P system with N peers. Results of analysis and simulations show that the average delay in Armada is less than logN, and the average message cost of single-attribute range queries is about logN+2n 2 (n is the number of peers that intersect with the query). These results are very close to the lower bounds on delay and message cost of range queries over constant-degree DHTs.

PrePrint: Discriminative Training of the Hidden Vector State Model for Semantic Parsing

In this paper, we discuss how discriminative training can be applied to the Hidden Vector State (HVS) model in different task domains. The HVS model is a discrete Hidden Markov Model (HMM) in which each HMM state represents the state of a push-down automaton with a finite stack size. In previous applications, Maximum Likelihood estimation (MLE) is used to derive the parameters of the HVS model. However, MLE makes a number of assumptions and unfortunately some of these assumptions do not hold. Discriminative training, without making such assumptions, can improve the performance of the HVS model. Experiments have been conducted in two domains: the travel domain for the semantic parsing task using the DARPA Communicator data and the ATIS data, and the bioinformatics domain for the information extraction task using the GENIA corpus. The results demonstrate modest improvements of the performance of the HVS model using discriminative training. In the travel domain, discriminative training of the HVS model gives a relative error reduction rate of 31% in F-measure when compared with MLE on the DARPA Communicator data and 9% on the ATIS data. In the bioinformatics domain, a relative error reduction rate of 4% in F-measure is achieved on the GENIA corpus.

PrePrint: SPOT Databases: Efficient Consistency Checking and Optimistic Selection in Probabilistic Spatial Databases

Spatial PrObabilistic Temporal (SPOT) databases are a paradigm for reasoning with probabilistic statements about where objects are now or in the future. They express statements of the form "Object O is in spatial region R at time t with some probability in the interval [L,U]." Past work on SPOT databases uses selection operators returning SPOT atoms entailed by the SPOT database - we call this "cautious" selection. In this paper, we study several problems. First, we introduce the notion of "optimistic" selection queries that return sets of SPOT atoms consistent with, rather than entailed by, the SPOT database. We then develop an approach to scaling SPOT databases that has three main contributions: (i) We substantially reduce the size of past work's linear programs via variable elimination. (ii) We rigorously prove how one can prune the space searched in optimistic selection. (iii) We build an efficient index to execute optimistic selection queries over SPOT databases. Our approach is superior to past work in two major respects: first, it makes fewer assumptions than all past works on this topic except [30]. Second, the experiments - some using real world ship movement data - show substantially better performance than achieved in [30].

PrePrint: CDNs Content Outsourcing via Generalized Communities

Content Distribution Networks (CDNs) balance costs and quality in services related to content delivery. Devising an efficient content outsourcing policy is crucial since, based on such policies, CDN providers can provide client-tailored content, improve performance, and result in significant economical gains. Earlier content outsourcing approaches may often prove ineffective since they drive prefetching decisions by assuming knowledge of content popularity statistics, which are not always available and are extremely volatile. This work addresses this issue, by proposing a novel self-adaptive technique under a CDN framework on which outsourced content is identified with no a-priori knowledge of (earlier) request statistics. This is employed by using a structure-based approach identifying coherent clusters of "correlated" Web server content objects, the so-called Web page communities. These communities are the core outsourcing unit and in this paper a detailed simulation experimentation has shown that the proposed technique is robust and effective in reducing user-perceived latency as compared with competing approaches, i.e., two communities-based approaches, Web caching, and non-CDN.

PrePrint: semQA: SPARQL with Idempotent Disjunction

The SPARQL LeftJoin abstract operator is not distributive over Union; this limits the algebraic manipulation of graph patterns, which in turn restricts the ability to create query plans for distributed processing or query optimization. In this paper, we present semQA, an algebraic extension for the SPARQL query language for RDF, which overcomes this issue by transforming graph patterns through the use of an idempotent disjunction operator Or as a substitute for Union. This permits the application of a set of equivalences that transform a query into distinct forms. We further present an algorithm to derive the solution set of the original query from the solution set of a query where Union has been substituted by Or. We also analyze the combined complexity of SPARQL, proving it to be NP-complete. It is also shown that the SPARQL query language is not, in the general case, fixed-parameter tractable. Experimental results are presented to validate the query evaluation methodology presented in this paper against the SPARQL standard, to corroborate the complexity analysis, and to illustrate the gains in processing cost reduction that can be obtained through the application of semQA.