Auxiliadora Sarmiento

Blind Separation of Dependent Sources With a Bounded Component Analysis Deflationary Algorithm

The problem of blind source separation of complex-valued sources from a linear mixture is addressed. We propose a deflationary algorithm for the sequential recovery of a set of communication signals, where each source is extracted by performing a Bounded Component Analysis of the linear mixture. The contribution of each recovered source to the observations is removed by minimizing its convex perimeter, without using second-order statistics. This implies to run a gradient descent algorithm several times. In order to accelerate the convergence, we have derived a fast step size that exploits the second-order information of the cost function by means of the augmented Hessian matrix. Computer simulations show that the proposed method is able to blindly separate even dependent sources, as long as they satisfy the BCA separability conditions. Also, the speed of convergence of this novel step size is compared with other classical approaches.

Bounded Component Analysis of linear mixtures

The blind decomposition of the observations, as a set of additive components of simpler structure, is a problem with many applications in scientific and practical fields. Our study assumes that the component signals are of bounded nature, and relies on the geometric decomposition of the convex set that supports the observations as a Minkowski direct sum of the convex sets that support the components. This last property, which is weaker than the mutual independence of the additive components of the observations, is sufficient for the essential identifiability of the bounded and indecomposable components. In practice, it is usual that the components lie in one-dimensional complex subspaces. Therefore, for this case, we describe a sequential method for their recovery.

Automatic optic cup segmentation algorithm for retinal fundus images based on random forest classifier

Glaucoma is an eye disease that constitutes the second cause of blindness over the world. Although it cannot be cured, its progression may be prevented if it is early detected. Expert ophthalmologists use as a sign of suffering from the disease, the evaluation of the relationship between optic disc and cup areas in retinal fundus images and, therefore, image processing techniques applied to glaucoma has become an emerging research line. This paper presents a novel technique for the detection of the optic cup in retinal fundus images, which may be included in a glaucoma computer aided diagnosis tool. The method, based on a color space related to human perception and adapted to surrounding conditions, JCh from CIECAM 02 (International Commission on Illumination Color Appearance Model), utilizes a random forest classifier to obtain cup edge pixels. As vessels tend to bend in the edge of the cup, the classifier does not consider all the pixels in the image. In fact, only those belonging to vessels and possessing the highest curvature among their neighbors are taken into account. Another prior knowledge used in the proposed method is the fact that cup area usually posses a bright yellow color. Therefore the feature vector serving as an input for the classifier is made with the curvature, the color of the candidate pixel and its location relative to the OD center. Finally, a basic post processing is performed to join the selected pixels with a smooth curve. The method has been tested in a publicly available database, GlaucomaRepo, from where we used 35 images for training and 55 for test. Five numerical parameters were calculated and a comparison against three color spaces was performed. The results obtained indicate the effectiveness of the approach.

Principales Problemas de los Profesores Principiantes en la Enseñanza Universitaria

Some reflections on the main problems that novice university instructors face in higher education are presented and discussed. Such difficulties are classified and analyzed in three aspects: that of teaching, that of interpersonal relationships and that of management or institutional context. The importance of an adequate pedagogical training of the novice teacher and the role of the tutorial action are emphasized. The challenges that the novice instructor must face in the present reform of the Spanish university model according to the European Space for Higher Education and the research-teaching conflict are reviewed. This because research activity is not only indispensable for the constant scientific evolution of the university professor, but it is also an aspect that may guarantee continuity of the professor in the university career. Such activity is usually difficult to combine with the purely educational, especially for novice instructors.

A contrast function based on generalized divergences for solving the permutation problem in convolved speech mixtures

In this paper, we propose a method for solving the permutation problem that is inherent in the separation of convolved mixtures of speech signals in the time-frequency domain. The proposed method obtains the solution through maximization of a contrast function that exploits the similarity of the temporal envelope of the speech spectrum. For this purpose, the contrast calculation uses a global measure of similarity based on the recently developed family of generalized Alpha-Beta divergences, which depend on two tuning parameters, alpha and beta. This parameterization is exploited to best measure the similarity of the speech spectrum and to obtain solutions that are robust against noise and outliers. The ability of this contrast function to solve the permutation problem is supported by a theoretical study that shows that for a simple time-frequency speech model, the contrast value reaches its maximum when the estimated components are properly aligned. Several performance studies demonstrate that the proposed method maintains a high level of permutation correction accuracy in a wide variety of acoustic environments. Moreover, it produces better results than other state-of-the-art methods for solving permutations in highly reverberant environments.

Automatic recognition of severity level for diagnosis of diabetic retinopathy using deep visual features

Diabetic retinopathy (DR) is leading cause of blindness among diabetic patients. Recognition of severity level is required by ophthalmologists to early detect and diagnose the DR. However, it is a challenging task for both medical experts and computer-aided diagnosis systems due to requiring extensive domain expert knowledge. In this article, a novel automatic recognition system for the five severity level of diabetic retinopathy (SLDR) is developed without performing any pre- and post-processing steps on retinal fundus images through learning of deep visual features (DVFs). These DVF features are extracted from each image by using color dense in scale-invariant and gradient location-orientation histogram techniques. To learn these DVF features, a semi-supervised multilayer deep-learning algorithm is utilized along with a new compressed layer and fine-tuning steps. This SLDR system was evaluated and compared with state-of-the-art techniques using the measures of sensitivity (SE), specificity (SP) and area under the receiving operating curves (AUC). On 750 fundus images (150 per category), the SE of 92.18%, SP of 94.50% and AUC of 0.924 values were obtained on average. These results demonstrate that the SLDR system is appropriate for early detection of DR and provide an effective treatment for prediction type of diabetes.

Automatic classification of tissue malignancy for breast carcinoma diagnosis

Breast cancer is the second leading cause of cancer death among women. Its early diagnosis is extremely important to prevent avoidable deaths. However, malignancy assessment of tissue biopsies is complex and dependent on observer subjectivity. Moreover, hematoxylin and eosin (H&E)-stained histological images exhibit a highly variable appearance, even within the same malignancy level. In this paper, we propose a computer-aided diagnosis (CAD) tool for automated malignancy assessment of breast tissue samples based on the processing of histological images. We provide four malignancy levels as the output of the system: normal, benign, in situ and invasive. The method is based on the calculation of three sets of features related to nuclei, colour regions and textures considering local characteristics and global image properties. By taking advantage of well-established image processing techniques, we build a feature vector for each image that serves as an input to an SVM (Support Vector Machine) classifier with a quadratic kernel. The method has been rigorously evaluated, first with a 5-fold cross-validation within an initial set of 120 images, second with an external set of 30 different images and third with images with artefacts included. Accuracy levels range from 75.8% when the 5-fold cross-validation was performed to 75% with the external set of new images and 61.11% when the extremely difficult images were added to the classification experiment. The experimental results indicate that the proposed method is capable of distinguishing between four malignancy levels with high accuracy. Our results are close to those obtained with recent deep learning-based methods. Moreover, it performs better than other state-of-the-art methods based on feature extraction, and it can help improve the CAD of breast cancer.

Initialization method for speech separation algorithms that work in the time-frequency domain

This article addresses the problem of the unsupervised separation of speech signals in realistic scenarios. An initialization procedure is proposed for independent component analysis (ICA) algorithms that work in the time-frequency domain and require the prewhitening of the observations. It is shown that the proposed method drastically reduces the permuted solutions in that domain and helps to reduce the execution time of the algorithms. Simulations confirm these advantages for several ICA instantaneous algorithms and the effectiveness of the proposed technique in emulated reverberant environments.

An Improved Segmentation Method for Non-melanoma Skin Lesions Using Active Contour Model

Computer-Aided Diagnosis (CAD) systems are widely used to classify skin lesions in dermoscopic images. The segmentation of the lesion area is the initial and key step to automate this process using a CAD system. In this paper, an improved segmentation algorithm is developed based on the following steps: (1) color space transform to the perception-oriented CIECAM02 color model, (2) preprocessing step to correct specular reflection, (3) contrast enhancement using an homomorphic transform filter (HTF) and nonlinear sigmoidal function (NSF) and (4) segmentation with relative entropy (RE) and active contours model (ACM). To validate the proposed technique, comparisons with other three state-of-the-art segmentation algorithms were performed for 210 non-melanoma lesions. From these experiments, an average true detection rate of 91.01, false positive rate of 6.35 and an error probability of 7.8 were obtained. These experimental results indicate that the proposed technique is useful for CAD systems to detect non-melanoma skin lesions in dermoscopy images.

A Study of Methods for Initialization and Permutation Alignment for Time-Frequency Domain Blind Source Separation

The problem of the blind signal separation (BSS) consists of estimating the latent component signals in a linear mixture, referred to as the sources, starting from several observed signals, without relying on any specific knowledge of the sources. In particular, when the sources are audible, this problem is known as to the cocktail-party problem, making reference to the ability of the human ear to isolate the conversation of our interest among several conversations immersed in a noisy environment with many people talking at the same time.