Catálogo de publicaciones - libros

Breast cancer relapse prediction is an important step in the complex decision-making process of deciding the type of treatment to be applied to patients after surgery. Some non-linear models, like neural networks, have been successfully applied to this task but they suffer from the problem of extracting the underlying rules, and knowing how the methods operate can help to a better understanding of the cancer relapse problem. A recently introduced constructive algorithm (DASG) that creates compact neural network architectures is applied to a dataset of early breast cancer patients with the aim of testing the predictive ability of the new method. The DASG method works with Boolean input data and for that reason a transformation procedure was applied to the original data. The degradation in the predictive performance due to the transformation of the data is also analyzed using the new method and other standard algorithms.

The incorporation of new biomedical technologies in the diagnosis and prognosis of cancer is changing medicine to an evidence-based diagnosis. We summarize some studies related to brain tumour research in Europe, based on the metabolic information provided by in vivo Magnetic Resonance Spectroscopy (MRS) and transcriptomic profiling observed by DNA microarrays. The first result presents the improvement in brain tumour diagnosis by combining Long TE and Short TE single voxel MR Spectra. Afterwards, a mixture model for binned and truncated data to characterize and classify MRS is reviewed. The classification of Glioblastomas Multiforme and Meningothelial Meningiomas using single-labeling cDNA-based microarrays was studied as proof of principle in the incorporation of genomic information to clinical diagnosis. Finally, we present a Decision Support System for in-vivo classification of brain tumours were the best inferred classifiers are deployed for their clinical use.

Unsupervised neural networks are used for constructing virtual reality spaces for visual data mining of gene expression cancer data. Datasets representative of three of the most important types of cancer considered in modern medicine (liver, lung and stomach) are considered in the study. They are composed of samples from normal and tumor tissues, described in terms of tens of thousands of variables, which are the corresponding gene expression intensities measured in microarray experiments. Despite the very high dimensionality of the studied patterns, high quality visual representations in the form of structure-preserving virtual spaces are obtained using SAMANN neural networks, which enables the differentiation of cancerous and noncancerous tissues. The same networks could be used as nonlinear feature generators in a preprocessing step for other data mining procedures.

This paper introduces a multi-objective optimization approach to the problem of computing virtual reality spaces for the visual representation of relational structures (e.g. databases), symbolic knowledge and others, in the context of visual data mining and knowledge discovery. Procedures based on evolutionary computation are discussed. In particular, the NSGA-II algorithm is used as a framework for an instance of this methodology; simultaneously minimizing Sammon’s error for dissimilarity measures, and mean cross-validation error on a k-nn pattern classifier. The proposed approach is illustrated with an example from cancer genomics data (e.g. lung cancer) by constructing virtual reality spaces resulting from multi-objective optimization. Selected solutions along the Pareto front approximation are used as nonlinearly transformed features for new spaces that compromise similarity structure preservation (from an unsupervised perspective) and class separability (from a supervised pattern recognition perspective), simultaneously. The possibility of spanning a range of solutions between these two important goals, is a benefit for the knowledge discovery and data understanding process. The quality of the set of discovered solutions is superior to the ones obtained separately, from the point of view of visual data mining.

The analysis of functional data, is a common task in bioinformatics. Spectral data as obtained from mass spectrometric measurements in clinical proteomics are such functional data leading to new challenges for an appropriate analysis. Here we focus on the determination of classification models for such data. In general the available approaches for this task initially transform the spectra into a vector space followed by training a classifier. Hereby the functional nature of the data is typically lost, which may lead to suboptimal classifier models. Taking this into account a wavelet encoding is applied onto the spectral data leading to a compact representation. Further the Supervised Neural Gas classifier is extended by a functional metric. This allows the classifier to utilize the functional nature of the data in the modeling process. The presented method is applied to clinical proteom data showing good results.

This paper is about the key role of Personalization through Ambient Intelligence in the development of Assistive Technologies for the elders. Ambient Intelligence implies three relatively new technologies: Ubiquitous Computation, Ubiquitous Communication, and Intelligent User Interfaces. We also present our own ideas about the integration of intelligent agent technology with other technologies to build specific assistive tools for the people with disabilities and for the new generation of senior citizens

This paper presents a three degrees of freedom orientation tracker as suitable controlling equipment for an automated wheelchair. Mounted at the back of an operator’s head by the help of an easy to wear frontlet, the device permanently outputs the user’s head posture which can be used as a joystick-like signal. Within an experimental evaluation we demonstrate the applicability of the proposed control interface even for untrained users.

The global trend of increasing longevity of modern societies is causing a growing attention to the elderly citizens. The world elderly population’s needs create the conditions for deploying new types of services to sustain independence and preserve quality of life. The main effort is to achieve e-tools capable of supplying different levels of disability and of satisfying the needs of each user. We focused on one of the most common problems: mobility limitations and their correlates, with particular attention to cognition. This paper presents a real case study on the impact of mobility assistance technology in patients presenting physical and/or cognitive disabilities.

We present our ideas about the integration of agent technology with other technologies to build specific assistive tools for the people with disabilities and for the new generation of senior citizens. We aim to explore the benefits of these tools to enhance the autonomy of the target user group in their daily life, and in particular in those cases where this autonomy should be shared between the human and the device that is assisting them.

Wireless sensor networks are being intensely used in health care environments to collect biometric signals from patients. This paper presents an augmented reality visual interface based on artificial markers intended to be used by medical staff, to monitor real time information from different kind of sensors attached to the patients in care centers in a fast and flexible way. The system can be applied for any kind of information source. In this work, it has been tested with temperature and humidity sensors.