The minimum volume covering ellipsoid (MVCE) estimation problem arises in many practical areas su... more The minimum volume covering ellipsoid (MVCE) estimation problem arises in many practical areas such as control, system identification, outlier detection, optimal experimental design, and spatial-temporal data mining. The problem of calculating the MVCE becomes ill-posed in a high-dimensional reproducing kernel Hilbert space (RKHS). In many practical cases the dimension of such a RKHS, eg defined by a Gaussian or Matern kernel function, is unknown and even infinite.
Unveiling combinatorial transcriptional regulation using microarray and motif compendia
The integration of heterogeneous but complementary data sources is an important challenge in syst... more The integration of heterogeneous but complementary data sources is an important challenge in systems biology, as it allows gaining holistic insight into the regulatory network. Recently, we introduced “ReMoDiscovery”[De Bie et al., 2005; Lemmens et al., 2006], an integrative method for inference of transcriptional modules from independently acquired heterogeneous data sources.
Correction to “A Normalized Beamforming Algorithm for Broadband Speech Using a Continuous Interleaved Sampling
Maximum Entropy Modelling for Assessing Results on Real-Valued Data
Using online chord databases to enhance chord recognition
Abstract Advances in chord recognition research using machine learning are hampered by two factor... more Abstract Advances in chord recognition research using machine learning are hampered by two factors: the scarcity of annotated training data, and the limited complexity of the features and models used. Both problems are intertwined, as with few training examples, increasing the complexity of the model would inevitably lead to overfitting. In this paper we develop a way to address the first problem by exploiting chord annotations from online chord databases.
HARMONY PROGRESSION ANALYZER FOR MIREX 2011
Knowledge discovery interestingness measures based on unexpectedness
Objective IMs only depend on properties of the data and the pattern. Typically, an objective IM f... more Objective IMs only depend on properties of the data and the pattern. Typically, an objective IM for a pattern p (eg, an itemset, a tile, an association, or a classification rule, see Data and Patterns Considered in This Paper) mined from a dataset D can be represented by a function
MINING THE CORRELATION BETWEEN LYRICAL AND AUDIO FEATURES AND THE EMERGENCE OF MOOD
Condition dependent regulation in Escherichia coli
Adaptation of Principal Component Analysis towards Inherent Incorporation of Spatial Information for Trend Detection in Imaging Mass Spectrometry Data
Abstract We present a new system for the harmonic analysis of popular musical audio. It is focuse... more Abstract We present a new system for the harmonic analysis of popular musical audio. It is focused on chord estimation, although the proposed system additionally estimates the key sequence and bass notes. It is distinct from competing approaches in two main ways. First, it makes use of a new improved chromagram representation of audio that takes the human perception of loudness into account.
Abstract Mining patterns from multi-relational data is a problem attracting increasing interest w... more Abstract Mining patterns from multi-relational data is a problem attracting increasing interest within the data mining community. Traditional data mining approaches are typically developed for highly simplified types of data, such as an attribute-value table or a binary database, such that those methods are not directly applicable to multi-relational data. Nevertheless, multi-relational data is a more truthful and therefore often also a more powerful representation of reality.
ESAT-SCD (SISTA)
Een eerste laconieke reactie zou kunnen zijn: æWaarom ook niet? Æ De veeleer historische naam æEl... more Een eerste laconieke reactie zou kunnen zijn: æWaarom ook niet? Æ De veeleer historische naam æElektrotechniekÆ dekt immers niet langer de lading. Bekijk maar eens de onderzoektopics op de website van ons departement (* HYPERLINK" http://www. esat. kuleuven. ac. be"** www. esat. kuleuven. ac. be*)!
An information theoretic framework for data mining
Abstract We formalize the data mining process as a process of information exchange, defined by th... more Abstract We formalize the data mining process as a process of information exchange, defined by the following key components. The data miner's state of mind is modeled as a probability distribution, called the background distribution, which represents the uncertainty and misconceptions the data miner has about the data. This model initially incorporates any prior (possibly incorrect) beliefs a data miner has about the data.
Negativity and Concurrence of mixed 2X2 states
Abstract: We consider two measures of entanglement of mixed bipartite states of dimension 2X2: co... more Abstract: We consider two measures of entanglement of mixed bipartite states of dimension 2X2: concurrence and negativity. We first prove the conjecture of Eisert and Plenio that concurrence can never be smaller than negativity. We then characterise all states for which concurrence equals negativity and also those states for which the difference between concurrence and negativity is maximal (keeping either the concurrence fixed, or the participation ratio R= 1/trace (rho^ 2)).
Background Complex cellular behavior is mediated by the action of regulatory networks. The recons... more Background Complex cellular behavior is mediated by the action of regulatory networks. The reconstruction of these networks is one of the foremost challenges of current bioinformatics research [1, 2] and requires combining different high throughput'omics' data. With the current accuracy and availability of these high throughput data, the problem of network reconstruction remains highly underdetermined. The amount of independent experimental data is not sufficient to unequivocally estimate all parameters of the models.
Meta-song evaluation for chord recognition
Abstract: We present a new approach to evaluate chord recognition systems on songs which do not h...
Uploads
Papers by Tijl De Bie