Examinando por Autor "Mora Jiménez, Inma"

Mostrando 1 - 12 de 12

A New Spread Spectrum Watermarking Method with Self-Synchronization Capabilities
(2009-07-30T09:24:49Z) Mora Jiménez, Inma; Navia Vázquez, Angel
Among the many techniques available for information concealment, those based on spread spectrum modulations have proven to yield improved results when robustness against attack is at a premium. In this paper, we propose a new spread spectrum-based watermarking procedure that combines space and frequency marks to provide good robustness properties against both spatial (affine) and transform-based compression attacks, without needing the original image as a reference (blind detection). It provides a mechanism for N-bit concealment and also improves the detection-of-presence process by gathering all watermark energy into a single value (sufficient statistic for detection). The recovery of every single bit is also improved by taking into account the so-called "watermark-print" or "waterprint" instead of looking at a single correlation value. It additionally provides the means to recover synchronization under affine transformations in the blind detection scenario. These characteristics will be analyzed by means of several practical examples.
A Universal Learning Rule that Minimizes Well-formed Cost Functions
(2009-07-29T13:59:17Z) Mora Jiménez, Inma; Cid Sueiro, Jesús
In this paper, we analyze stochastic gradient learning rules for posterior probability estimation using networks with a single layer of weights and a general nonlinear activation function. We provide necessary and sufficient conditions on the learning rules and the activation function to obtain probability estimates. Also, we extend the concept of well-formed cost function, proposed by Wittner and Denker, to multiclass problems, and we provide theoretical results showing the advantages of this kind of objective functions.
Creating Modular-like Ensembles by Output Clustering
(2009-07-30T09:15:03Z) Mora Jiménez, Inma; Lyhyaoui, Abdelouahid; Arenas García, J.; Figueiras Vidal, Aníbal R
In this paper we consider the possibility of replacing the output layer of Multi- Layer Perceptrons (MLPs) by local schemes when dealing with classification problems. In order to open the possibility of developing LMS-trainable models, and posterior adaptive schemes, we apply a trainable version of the classical k-Nearest Neighbour classifier (kNN) named kNN-Learning Vector Classifier. We develop the corresponding training formulas for the whole resulting structure and apply it to some classification benchmark problems. The experimental results give evidence of the nearly systematic advantage of our proposal with respect to MLPs, as well as of their competitive performance regarding the Modular Neural Networks (MNNs), which have a similar philosophy as our approach.
Growing Support Vector Classifiers with controlled complexity
(2009-07-29T14:43:25Z) Parrado Hernández, E.; Mora Jiménez, Inma; Arenas García, J.; Figueiras Vidal, Aníbal R; Navia Vázquez, Angel
Semiparametric Support Vector Machines have shown to present advantages with respect to nonparametric approaches, in the sense that generalization capability is further improved and the size of the machines is always under control. We propose here an incremental procedure for Growing Support Vector Classifiers, which serves to avoid an a priori architecture estimation or the application of a pruning mechanism after SVM training. The proposed growing approach also opens up new possibilities for dealing with multi-kernel machines, automatic selection of hyperparameters, and fast classification methods. The performance of the proposed algorithm and its extensions is evaluated using several benchmark problems.
Heart Rate Turbulence Denoising Using Support Vector Machines
(2009-02-04T19:17:36Z) Rojo-Álvarez, José Luis; Barquero Pérez, Óscar; Mora Jiménez, Inma; Everss, Estrella; Rodríguez González, Ana Belén; García Alberola, Arcadi
Heart Rate Turbulence (HRT) is the transient acceleration and subsequent deceleration of the heart rate after a premature ventricular complex (PVC), and it has been shown to be a strong risk stratification criterion in patients with cardiac disease. In order to reduce the noise level of the HRT signal, conventional measurements of HRT use a patient-averaged template of post-PVC tachograms (PPT), hence providing with long-term HRT indices. We hypothesize that the reduction of the noise level at each isolated PPT, using signal processing techniques, will allow to estimate short-term HRT indices. Accordingly, its application could be extended to patients with reduced number of available PPT. In this paper, several HRT denoising procedures are proposed and tested, with special attention to Support Vector Machine (SVM) estimation, as this is a robust algorithm that allows us to deal with few available time samples in the PPT. Pacing stimulated HRT during electrophysiological study are used as a low noise gold-standard. Measurements in a 24 hour-Holter patient database reveal a significant reduction in the the bias and in the variance of HRT measurements. We conclude that SVM denoising yields short-term HRT measurements and improves the signal to noise level of long-term HRT measurements.
Improving Performance of Neural Classifiers Via Selective Reduction of Target Levels
(2009-07-29T13:50:22Z) Mora Jiménez, Inma; Figueiras Vidal, Aníbal R
On Problem-Oriented Kernel Refining
(2009-07-29T14:33:24Z) Parrado Hernández, E.; Arenas García, J.; Mora Jiménez, Inma; Navia Vázquez, Angel
Much attention has been recently devoted to those machine learning procedures known as kernel methods, the Support Vector Machines being an instance of them. Their performance heavily depends on the particular 'distance measurement' between patterns, function also known as 'kernel', which represents a dot product in a projection space. Although some attempts are being made to 'a priori' decide which kernel function is more suitable for a problem, no defnite solution for this taskhas been found yet, since choosing the best kernel very often reduces to a selection among diferent possibilities by a cross-validation process. In this paper, we propose a method for solving classification problems relying on the ad hoc determination of a kernel for every problem at hand, i.e., a problem-oriented kernel design method. We iteratively obtain a semiparametric projecting function of the input data into a space which has an appropriately low dimension to avoid both overfitting and complexity explosion of the resulting machine, but being powerful enough to solve the classification problems with good accuracy. The performance of the proposed method is illustrated using standard databases, and we further discuss its suitability for developing problem-oriented feature extraction procedures.
Path Efficiency in Mobile Ad-Hoc Networks
(3rd International Symposium on Wireless Communication Systems, 2006. ISWCS '06, 2006-09) Caamaño, Antonio J.; Vinagre Díaz, Juan José; Mora Jiménez, Inma; Figuera Pozuelo, Carlos; Ramos, Javier
The process of routing in large ad-hoc mobile networks is theoretically analyzed as the capacity of a packet to be directed form a source to a destination. The equivalence between directivity and an effective radius, which represents the actual knowledge of any node of its neighbourhood, is demonstrated. The mobility of the network is modelled as that resulting from the most probable distribution of mobile nodes. The results are conclusive: mobility reduces the throughput and delay performance of any routing algorithm with a finite effective radius.
Real-Time High Density People Counter Using Morphological Tools
(2001-12-04) Albiol Colomer, Antonio; Mora Jiménez, Inma; Naranjo, Valery
This paper deals with an application of image sequence analysis. In particular, it addresses the problem of determining the number of people who get into and out of a train carriage when it's crowded, and background and/or illumination changes. The proposed system analyzes image sequences and processes them using an algorithm based on the use of several morphological tools, which are presented in detail in the paper.
Real-Time High Density People Counter using Morphological Tools
(2009-07-30T09:33:21Z) Albiol Colomer, Antonio; Naranjo, Valery; Mora Jiménez, Inma
This paper deals with an application of image sequence analysis. In particular, it addresses the problem of determining the number of people who get into and out of a train carriage when it's crowded and background and/or illumination might change. The proposed system analyses image sequences and processes them using an algorithm based on the use of several morphological tools and optical flow motion estimation.
Real-Time High Density People Counter Using Morphological Tools
(2009-07-29T14:53:47Z) Albiol Colomer, Antonio; Mora Jiménez, Inma; Naranjo, Valery
This paper deals with an application of image sequence analysis. In particular, it addresses the problem of determining the number of people who get into and out of a train carriage when it's crowded, and background and/or illumination changes. The proposed system analyzes image sequences and processes them using an algorithm based on the use of several morphological tools, which are presented in detail in the paper.
Sample Selection Via Clustering to Construct Support Vector-Like Classifiers
(2009-07-29T15:18:19Z) Lyhyaoui, Abdelouahid; Martínez Ramón, M; Mora Jiménez, Inma; Vázquez Castro, M.A; Sancho Gómez, JL; Figueiras Vidal, Aníbal R
This paper explores the possibility of constructing RBF classifiers which, somewhat like support vector machines, use a reduced number of samples as centroids, by means of selecting samples in a direct way. Because sample selection is viewed as a hard computational problem, this selection is done after a previous vector quantization: this way obtaining also other similar machines using centroids selected from those that are learned in a supervised manner. Several forms of designing these machines are considered, in particular with respect to sample selection; as well as some different criteria to train them. Simulation results for well-known classification problems show very good performance of the corresponding designs, improving that of support vector machines and reducing substantially their number of units. This shows that our interest in selecting samples (or centroids) in an efficient manner is justified. Many new research avenues appear from these experiments and discussions, as suggested in our conclusions.