2014 International Conference on Data Science and Advanced Analytics (DSAA)

Oct. 30 2014-Nov. 1 2014

Filter Results

Displaying Results 1 - 25 of 104
  • [Front cover]

    Publication Year: 2014, Page(s): c1
    Request permission for commercial reuse | PDF file iconPDF (273 KB)
    Freely Available from IEEE
  • Copyright page

    Publication Year: 2014, Page(s): 1
    Request permission for commercial reuse | PDF file iconPDF (52 KB)
    Freely Available from IEEE
  • Welcome from DSAA 2014 chairs

    Publication Year: 2014, Page(s):9 - 10
    Request permission for commercial reuse | PDF file iconPDF (47 KB) | HTML iconHTML
    Freely Available from IEEE
  • DSAA 2014 organizing committee

    Publication Year: 2014, Page(s): v
    Request permission for commercial reuse | PDF file iconPDF (25 KB)
    Freely Available from IEEE
  • DSAA 2014 program committee

    Publication Year: 2014, Page(s):vi - viii
    Request permission for commercial reuse | PDF file iconPDF (29 KB)
    Freely Available from IEEE
  • DSAA/BESC keynote speeches

    Publication Year: 2014, Page(s):ix - xv
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (377 KB)

    These keynotes speeches discuss the following: Big Data, AIl Data, Old Data: Predictive Analytics in a Changing Data Landscape; Relative thinking; Monte Carlo Methods for Big Data and Big Models; Social Computing and Computational Societies: An ACP based Approach for Smart and Parallel Economic Systems; Some Patterns in Online Behavior. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Panel discussion

    Publication Year: 2014, Page(s): xvi
    Request permission for commercial reuse | PDF file iconPDF (27 KB)
    Freely Available from IEEE
  • DSAA special sessions

    Publication Year: 2014, Page(s):xvii - xxiii
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (70 KB) | HTML iconHTML

    Presents a summary of special sessions held at this conference. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • DSAA trends & controversies & invited talks

    Publication Year: 2014, Page(s):xxiv - xxviii
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (432 KB) | HTML iconHTML

    These invited talks discuss the following: data science; advanced analytics; Big Data; online video; Bayesian network classifier; scalable learning; context awareness; and massive open online course. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • DSAA/BESC tutorials

    Publication Year: 2014, Page(s): xxix
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (88 KB)

    These tutorials discuss the following: Network mining and analysis for social applications; Harvesting, integrating, maintaining and leveraging knowledge graphs. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Technical papers

    Publication Year: 2014, Page(s):xxx - xxxvi
    Request permission for commercial reuse | PDF file iconPDF (6280 KB)
    Freely Available from IEEE
  • Table of contents

    Publication Year: 2014, Page(s):1 - 6
    Request permission for commercial reuse | PDF file iconPDF (6472 KB)
    Freely Available from IEEE
  • Assessing the longevity of online videos: A new insight of a video's quality

    Publication Year: 2014, Page(s):1 - 10
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (498 KB) | HTML iconHTML

    Recommending valuable videos to viewers is always crucial to an online video website and its related third parties. More particularly, what features and methods to be selected to assess the quality of online videos is still an on-going research topic. Unlike previous work attempted to evaluate a video only by its view count (a.k.a. popularity), this article proposes an additional scoring mechanism... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Minimizing expected loss for risk-avoiding reinforcement learning

    Publication Year: 2014, Page(s):11 - 17
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (604 KB) | HTML iconHTML

    This paper considers the design of a reinforcement learning (RL) agent that can strike a balance between return and risk. First, we discuss several favorable properties of an RL risk model, and then propose a definition of risk based on expected negative rewards. We also design a Q-decomposition-based framework that allows a reinforcement learning agent to control the balance between risk and prof... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Large-scale factorization of type-constrained multi-relational data

    Publication Year: 2014, Page(s):18 - 24
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1258 KB) | HTML iconHTML

    The statistical modeling of large multi-relational datasets has increasingly gained attention in recent years. Typical applications involve large knowledge bases like DBpedia, Freebase, YAGO and the recently introduced Google Knowledge Graph that contain millions of entities, hundreds and thousands of relations, and billions of relational tuples. Collective factorization methods have been shown to... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Pseudo labels for imbalanced multi-label learning

    Publication Year: 2014, Page(s):25 - 31
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (300 KB) | HTML iconHTML

    The classification with instances which can be tagged with any of the 2L possible subsets from the predefined L labels is called multi-label classification. Multi-label classification is commonly applied in domains, such as multimedia, text, web and biological data analysis. The main challenge lying in multi-label classification is the dilemma of optimising label correlations over expon... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Proactive learning with multiple class-sensitive labelers

    Publication Year: 2014, Page(s):32 - 38
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1283 KB) | HTML iconHTML

    Proactive learning extends active learning by considering multiple labelers with different accuracies and costs, thus optimizing labeler selection as well as instance selection. In this paper, we propose a novel method to estimate labeler accuracy per class and to select labelers based on both cost and estimated accuracy, combined with an ensemble approach called multi-class information density (M... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Itemset approximation using Constrained Binary Matrix Factorization

    Publication Year: 2014, Page(s):39 - 45
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (298 KB) | HTML iconHTML

    We address in this paper the problem of efficiently finding a few number of representative frequent itemsets in transaction matrices. To do so, we propose to rely on matrix decomposition techniques, and more precisely on Constrained Binary Matrix Factorization (CBMF) which decomposes a given binary matrix into the product of two lower dimensional binary matrices, called factors. We first show, und... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Community detection in social networks: The power of ensemble methods

    Publication Year: 2014, Page(s):46 - 52
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (743 KB) | HTML iconHTML

    In this work, we present an original seed-centric algorithm for community detection. Instead of expanding communities around selected seeds as most of existing seed-centric approaches do, we propose applying an ensemble clustering approach to different network partitions derived from local communities computed for each seed. Local communities are themselves computed applying an ensemble ranking ap... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Semi-randomized hashing for large scale data retrieval

    Publication Year: 2014, Page(s):53 - 58
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (233 KB) | HTML iconHTML

    In information retrieval, efficient accomplishing the nearest neighbor search on large scale database is a great challenge. Hashing based indexing methods represent each data instance as a binary string to retrieve the approximate nearest neighbors. In this paper, we present a semi-randomized hashing approach to preserve the Euclidean distance by binary codes. Euclidean distance preserving is a cl... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Storage efficient graph search by composite dynamic-and-static indexing of a single network

    Publication Year: 2014, Page(s):59 - 65
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (701 KB) | HTML iconHTML

    Nowadays, the surge of complex structured data in the form of single information network puts new challenges for advanced searching and indexing mechanisms. Traditional feature-based indexing no longer works in the new scenario, because the mining deficiency and pattern recurrence curse on the excessive and complicated internal structure prevent index construction and storage from being handled ef... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Indexing and retrieval of human motion data based on a growing self-organizing map

    Publication Year: 2014, Page(s):66 - 71
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (636 KB) | HTML iconHTML

    As low-cost depth cameras are released recently, motion data containing 3D coordinates of skeleton joints during a time period can be directly captured. Nevertheless, analyzing the motion data is usually a challenging problem and requires huge computation costs because of the high-dimensionality. Among several alternatives, the self-organizing map (SOM) is verified to be an effective technique to ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An improved dynamic adaptive multi-tree search anti-collision algorithm based on RFID

    Publication Year: 2014, Page(s):72 - 75
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (260 KB) | HTML iconHTML

    In this letter, we present a dynamic adaptive multi-tree search (DAMS) algorithm which is an improvement of a multi-tree search algorithm (AMS). In order to reduce collisions, the multi-tree search algorithm adjusts the search tree through collision factor (CF). The proposed algorithm puts forward a new CF critical value and stipulates that the length of EPC which tags replied dynamically. The sim... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Exploiting mobility for location promotion in location-based social networks

    Publication Year: 2014, Page(s):76 - 82
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (164 KB) | HTML iconHTML

    In this paper, we target the location promotion problem in location-based social networks (LBSNs). The location promotion problem is given a location, we select a set of users as seeds to influence as many users as possible who are likely to visit a selected location. Specifically, we model the location promotion problem as an influence maximization problem on a graph and explore the independent c... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Investigating sample selection bias in the relevance feedback algorithm of the vector space model for Information Retrieval

    Publication Year: 2014, Page(s):83 - 89
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (238 KB) | HTML iconHTML

    Information Retrieval (IR) is concerned with indexing and retrieving documents including information relevant to a user's information need. Relevance Feedback (RF) is an effective technique for improving IR and it consists of gathering further data representing the user's information need and automatically creating a new query. As RF relies on the ability of an IR system to learn new queries and i... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.