Evolutionary model trees for handling continuous classes in machine learning

Model trees are a particular case of decision trees employed to solve regression problems. They have the advantage of presenting an interpretable output, helping the end-user to get more confidence in the prediction and providing the basis for the end-user to have new insight about the data, confirming or rejecting hypotheses previously formed. Moreover, model trees present an acceptable level of predictive performance in comparison to most techniques used for solving regression problems. Since generating the optimal model tree is an NP-Complete problem, traditional model tree induction algorithms make use of a greedy top-down divide-and-conquer strategy, which may not converge to the global optimal solution. In this paper, we propose a novel algorithm based on the use of the evolutionary algorithms paradigm as an alternate heuristic to generate model trees in order to improve the convergence to globally near-optimal solutions. We call our new approach evolutionary model tree induction (E-Motion). We test its predictive performance using public UCI data sets, and we compare the results to traditional greedy regression/model trees induction algorithms, as well as to other evolutionary approaches. Results show that our method presents a good trade-off between predictive performance and model comprehensibility, which may be crucial in many machine learning applications. (C) 2010 Elsevier Inc. All rights reserved.

An Information Theory framework for two-stage binary image operator design

The design of translation invariant and locally defined binary image operators over large windows is made difficult by decreased statistical precision and increased training time. We present a complete framework for the application of stacked design, a recently proposed technique to create two-stage operators that circumvents that difficulty. We propose a novel algorithm, based on Information Theory, to find groups of pixels that should be used together to predict the Output Value. We employ this algorithm to automate the process of creating a set of first-level operators that are later combined in a global operator. We also propose a principled way to guide this combination, by using feature selection and model comparison. Experimental results Show that the proposed framework leads to better results than single stage design. (C) 2009 Elsevier B.V. All rights reserved.

ó-SCLOPE : clustering categorical streams using attribute selection

Clustering is a difficult problem especially when we consider the task in the context of a data stream of categorical attributes. In this paper, we propose σ-SCLOPE, a novel algorithm based on SCLOPE’s intuitive observation about cluster histograms. Unlike SCLOPE however, our algorithm consumes less memory per window and has a better clustering runtime for the same data stream in a given window. This positions σ-SCLOPE as a more attractive option over SCLOPE if a minor lost of clustering accuracy is insignificant in the application.

Using autonomous mobile agents for efficient data collection in sensor networks

Sensor networks are emerging as the new frontier in sensing technology, however there are still issues that need to be addressed. Two such issues are data collection and energy conservation. We consider a mobile robot, or a mobile agent, traveling the network collecting information from the sensors themselves before their onboard memory storage buffers are full. A novel algorithm is presented that is an adaptation of a local search algorithm for a special case of the Asymmetric Traveling Salesman Problem with Time-windows (ATSPTW) for solving the dynamic scheduling problem of what nodes are to be visited so that the information collected is not lost. Our algorithms are given and compared to other work.

An effective non-parametric method for globally clustering genes from expression profiles

Clustering is widely used in bioinformatics to find gene correlation patterns. Although many algorithms have been proposed, these are usually confronted with difficulties in meeting the requirements of both automation and high quality. In this paper, we propose a novel algorithm for clustering genes from their expression profiles. The unique features of the proposed algorithm are twofold: it takes into consideration global, rather than local, gene correlation information in clustering processes; and it incorporates clustering quality measurement into the clustering processes to implement non-parametric, automatic and global optimal gene clustering. The evaluation on simulated and real gene data sets demonstrates the effectiveness of the algorithm.

EStream: online mining of frequent sets with precise error guarantee

In data stream applications, a good approximation obtained in a timely  manner is often better than the exact answer that’s delayed beyond the window of opportunity. Of course, the quality of the approximate is as important as its timely delivery. Unfortunately, algorithms capable of online processing do not conform strictly to a precise error guarantee. Since online processing is essential and so is the precision of the error, it is necessary that stream algorithms meet both criteria. Yet, this is not the case for mining frequent sets in data streams. We present EStream, a novel algorithm that allows online processing while producing results strictly within the error bound. Our theoretical and experimental results show that EStream is a better candidate for finding frequent sets in data streams, when both constraints need to be satisfied.

Multiple camera coordination in a surveillance system

We present a distributed surveillance system that uses multiple cheap static cameras to track multiple people in indoor environments. The system has a set of Camera Processing Modules and a Central Module to coordinate the tracking tasks among the cameras. Since each object in the scene can be tracked by a number of cameras, the problem is how to choose the most appropriate camera for each object. This is important given the need to deal with limited resources (CPU, power etc.). We propose a novel algorithm to allocate objects to cameras using the object-to-camera distance while taking into account occlusion. The algorithm attempts to assign objects in the overlapping field of views to the nearest camera, which can see the object without occlusion. Experimental results show that the system can coordinate cameras to track people and can deal well with occlusion.

Ridge regression for two dimensional locality preserving projection

Two Dimensional Locality Preserving Projection (2D-LPP) is a recent extension of LPP, a popular face recognition algorithm. It has been shown that 2D-LPP performs better than PCA, 2D-PCA and LPP. However, the computational cost of 2D-LPP is high. This paper proposes a novel algorithm called Ridge Regression for Two Dimensional Locality Preserving Projection (RR- 2DLPP), which is an extension of 2D-LPP with the use of ridge regression. RR-2DLPP is comparable to 2DLPP in performance whilst having a lower computational cost. The experimental results on three benchmark face data sets - the ORL, Yale and FERET databases - demonstrate the effectiveness and efficiency of RR-2DLPP compared with other face recognition algorithms such as PCA, LPP, SR, 2D-PCA and 2D-LPP.

Coordination of multiple cameras to track multiple people

In this paper, we present a distributed surveillance system that uses multiple cheap static cameras to track multiple people in indoor environments. The system has a set of Camera Processing Modules and a Central Module to coordinate the tracking tasks among the cameras. Since each object in the scene can be tracked by a number of cameras, the problem is how to choose the most appropriate camera for each object. We propose a novel algorithm to allocate objects to cameras using the object-to-camera distance while taking into account occlusion. The algorithm attempts to assign objects in the overlapping fields of view to the nearest camera which can see the object without occlusion. Experimental results show that the system can coordinate cameras to track people properly and can deal well with occlusion.

Extracting 3D mesh skeletons using antipodal points locations

Finding the skeleton of a 3D mesh is an essential task for many applications such as mesh animation, tracking, and 3D registeration. In recent years, new technologies in computer vision such as Microsoft Kinect have proven that a mesh skeleton can be useful such as in the case of human machine interactions. To calculate the 3D mesh skeleton, the mesh properties such as topology and its components relations are utilized. In this paper, we propose the usage of a novel algorithm that can efficiently calculate a vertex antipodal point. A vertex antipodal point is the diametrically opposite point that belongs to the same mesh. The set of centers of the connecting lines between each vertex and its antipodal point represents the 3D mesh desired skeleton. Post processing is completed for smoothing and fitting centers into optimized skeleton parts. The algorithm is tested on different classes of 3D objects and produced efficient results that are comparable with the literature. The algorithm has the advantages of producing high quality skeletons as it preserves details. This is suitable for applications where the mesh skeleton mapping is required to be kept as much as possible.

Automatic cast listing in feature-length films with Anisotropic Manifold Space

Our goal is to automatically determine the cast of a feature-length film. This is challenging because the cast size is not known, with appearance changes of faces caused by extrinsic imaging factors (illumination, pose, expression) often greater than due to differing identities. The main contribution of this paper is an algorithm for clustering over face appearance manifolds. Specifically: (i) we develop a novel algorithm for exploiting coherence of dissimilarities between manifolds, (ii) we show how to estimate the optimal dataset-specific discriminant manifold starting from a generic one, and (iii) we describe a fully automatic, practical system based on the proposed algorithm. The performance of the system is evaluated on well-known featurelength films and situation comedies on which it is shown to produce good results.

Pseudoconvex proximal splitting for L∞problems in multiview geometry

In this paper we study optimization methods for minimizing large-scale pseudoconvex L∞problems in multiview geometry. We present a novel algorithm for solving this class of problem based on proximal splitting methods. We provide a brief derivation of the proposed method along with a general convergence analysis. The resulting meta-algorithm requires very little effort in terms of implementation and instead makes use of existing advanced solvers for non-linear optimization. Preliminary experiments on a number of real image datasets indicate that the proposed method experimentally matches or outperforms current state-of-the-art solvers for this class of problems.

Autoregressive decomposition and pole tracking applied to vocal fold nodule signals

This letter describes a novel algorithm that is based on autoregressive decomposition and pole tracking used to recognize two patterns of speech data: normal voice and disphonic voice caused by nodules. The presented method relates the poles and the peaks of the signal spectrum which represent the periodic components of the voice. The results show that the perturbation contained in the signal is clearly depicted by pole's positions. Their variability is related to jitter and shimmer. The pole dispersion for pathological voices is about 20% higher than for normal voices, therefore, the proposed approach is a more trustworthy measure than the classical ones. © 2007.

Multidimensional analysis of complex networks

Complex Networks analysis turn out to be a very promising field of research, testified by many research projects and works that span different fields. Those analysis have been usually focused on characterize a single aspect of the system and a study that considers many informative axes along with a network evolve is lacking. We propose a new multidimensional analysis that is able to inspect networks in the two most important dimensions, space and time. To achieve this goal, we studied them singularly and investigated how the variation of the constituting parameters drives changes to the network as a whole. By focusing on space dimension, we characterized spatial alteration in terms of abstraction levels. We proposed a novel algorithm that, by applying a fuzziness function, can reconstruct networks under different level of details. We verified that statistical indicators depend strongly on the granularity with which a system is described and on the class of networks. We keep fixed the space axes and we isolated the dynamics behind networks evolution process. We detected new instincts that trigger social networks utilization and spread the adoption of novel communities. We formalized this enhanced social network evolution by adopting special nodes (called sirens) that, thanks to their ability to attract new links, were able to construct efficient connection patterns. We simulated the dynamics of the system by considering three well-known growth models. Applying this framework to real and synthetic networks, we showed that the sirens, even when used for a limited time span, effectively shrink the time needed to get a network in mature state. In order to provide a concrete context of our findings, we formalized the cost of setting up such enhancement and provided the best combinations of system's parameters, such as number of sirens, time span of utilization and attractiveness.

Scale bridging concepts in molecular simulation : coarse-graining and thermodynamic coupling

In dieser Arbeit wurden Simulation von Flüssigkeiten auf molekularer Ebene durchgeführt, wobei unterschiedliche Multi-Skalen Techniken verwendet wurden. Diese erlauben eine effektive Beschreibung der Flüssigkeit, die weniger Rechenzeit im Computer benötigt und somit Phänomene auf längeren Zeit- und Längenskalen beschreiben kann.rnrnEin wesentlicher Aspekt ist dabei ein vereinfachtes (“coarse-grained”) Modell, welches in einem systematischen Verfahren aus Simulationen des detaillierten Modells gewonnen wird. Dabei werden ausgewählte Eigenschaften des detaillierten Modells (z.B. Paar-Korrelationsfunktion, Druck, etc) reproduziert.rnrnEs wurden Algorithmen untersucht, die eine gleichzeitige Kopplung von detaillierten und vereinfachten Modell erlauben (“Adaptive Resolution Scheme”, AdResS). Dabei wird das detaillierte Modell in einem vordefinierten Teilvolumen der Flüssigkeit (z.B. nahe einer Oberfläche) verwendet, während der Rest mithilfe des vereinfachten Modells beschrieben wird.rnrnHierzu wurde eine Methode (“Thermodynamische Kraft”) entwickelt um die Kopplung auch dann zu ermöglichen, wenn die Modelle in verschiedenen thermodynamischen Zuständen befinden. Zudem wurde ein neuartiger Algorithmus der Kopplung beschrieben (H-AdResS) der die Kopplung mittels einer Hamilton-Funktion beschreibt. In diesem Algorithmus ist eine zur Thermodynamischen Kraft analoge Korrektur mit weniger Rechenaufwand möglich.rnrnAls Anwendung dieser grundlegenden Techniken wurden Pfadintegral Molekulardynamik (MD) Simulationen von Wasser untersucht. Mithilfe dieser Methode ist es möglich, quantenmechanische Effekte der Kerne (Delokalisation, Nullpunktsenergie) in die Simulation einzubeziehen. Hierbei wurde zuerst eine Multi-Skalen Technik (“Force-matching”) verwendet um eine effektive Wechselwirkung aus einer detaillierten Simulation auf Basis der Dichtefunktionaltheorie zu extrahieren. Die Pfadintegral MD Simulation verbessert die Beschreibung der intra-molekularen Struktur im Vergleich mit experimentellen Daten. Das Modell eignet sich auch zur gleichzeitigen Kopplung in einer Simulation, wobei ein Wassermolekül (beschrieben durch 48 Punktteilchen im Pfadintegral-MD Modell) mit einem vereinfachten Modell (ein Punktteilchen) gekoppelt wird. Auf diese Weise konnte eine Wasser-Vakuum Grenzfläche simuliert werden, wobei nur die Oberfläche im Pfadintegral Modell und der Rest im vereinfachten Modell beschrieben wird.