0000000000073006
AUTHOR
Antonio J. Serrano
Neural Networks Ensemble for Cyclosporine Concentration Monitoring
This paper proposes the use of neural networks ensemble for predicting the cyclosporine A (CyA)concen tration in kidney transplant patients. In order to optimize clinical outcomes and to reduce the cost associated with patient care, accurate prediction of CyA concentrations is the main objective of therapeutic drug monitoring. Thirty-two renal allograft patients and different factors (age, weight, gender, creatinine and post-transplantation days, together with past dosages and concentrations)w ere studied to obtain the best models. Three kinds of networks (multilayer perceptron, FIR network, Elman recurrent network) and the formation of neural-network ensembles were used. The FIR network, y…
Robust adaptive algorithm with low computational cost
An adaptive algorithm, which is robust to impulsive noise, is proposed. The cost function underlying this algorithm contains a parameter that controls the immunity to impulsive noise and can be easily adapted. Moreover, weight updating involves a nonlinear function, which recently has been shown to have an efficient hardware implementation. The proposed adaptive algorithm has been successfully tested in terms of accuracy and convergence on a system-identification simulation.
Vibration Monitoring of the Mechanical Harvesting of Citrus to Improve Fruit Detachment Efficiency
The introduction of a mechanical harvesting process for oranges can contribute to enhancing farm profitability and reducing labour dependency. The objective of this work is to determine the spread of the vibration in citrus tree canopies to establish recommendations to reach high values of fruit detachment efficiency and eliminate the need for subsequent hand-harvesting processes. Field tests were carried out with a lateral tractor-drawn canopy shaker on four commercial plots of sweet oranges. Canopy vibration during the harvesting process was measured with a set of triaxial accelerometer sensors with a datalogger placed on 90 bearing branches. Monitoring of the vibration process, fruit pro…
Application of machine learning techniques to analyse the effects of physical exercise in ventricular fibrillation
This work presents the application of machine learning techniques to analyse the influence of physical exercise in the physiological properties of the heart, during ventricular fibrillation. To this end, different kinds of classifiers (linear and neural models) are used to classify between trained and sedentary rabbit hearts. The use of those classifiers in combination with a wrapper feature selection algorithm allows to extract knowledge about the most relevant features in the problem. The obtained results show that neural models outperform linear classifiers (better performance indices and a better dimensionality reduction). The most relevant features to describe the benefits of physical …
A Teaching Laboratory in Analog Electronics: Changes to Address the Bologna Requirements
Training new electronics engineers presents several major challenges. This paper proposes a new approach for practical lessons in second-level analog electronics, where students get a closer view of real-world practices in electronic engineering. The authors describe and evaluate a more dynamic way of teaching practical lessons in analog electronics in the first year of an electronic engineering degree. The method consists of creating a virtual company that contracts students to develop prototypes. The design process involves theoretical concepts from the students' lessons, and poses challenges with respect to costs and teamwork. The method brings the students closer to the working environm…
Clinical Decision Support System To Prevent Toxicity In Patients Treated With Digoxin
In this chapter, authors develop a system for prevention and detection of congestive heart failure and fibrillation. Due to its narrow therapeutic range more than 10% of the patients treated with DGX can suffer toxic effects, but it is estimated that half of the cases of digitalis toxicity could be prevented. Two multivariate models were developed to prevent digitalis toxicity.
Design of a Neural Network Model as a Decision Making Aid in Renal Transplant
This paper presents the application of this new tool of data processing in the study of the problem that arises when a renal transplant is indicated for a paediatric patient. Its aim is the development and validation of a neural network based model which can predict the success of the transplant over the short, medium and long term, using pre-operative characteristics of the patient (recipient) and implant organ (donor). When compared to results of logistic regression, the results of the proposed model showed better performance. Once the model is obtained, it will be converted into a tool for predicting the efficiency of the transplant protocol in order to optimise the donor-recipient pair …
Feature selection using ROC curves on classification problems
Feature Selection (FS) is one of the key stages in classification problems. This paper proposes the use of the area under Receiver Operator Characteristic curves to measure the individual importance of every input as well as a method to discover the variables that yield a statistically significant improvement in the discrimination power of the classification model.
Expert system for predicting unstable angina based on Bayesian networks
The use of computer-based clinical decision support (CDS) tools is growing significantly in recent years. These tools help reduce waiting lists, minimise patient risks and, at the same time, optimise the cost health resources. In this paper, we present a CDS application that predicts the probability of having unstable angina based on clinical data. Due to the characteristics of the variables (mostly binary) a Bayesian network model was chosen to support the system. Bayesian-network model was constructed using a population of 1164 patients, and subsequently was validated with a population of 103 patients. The validation results, with a negative predictive value (NPV) of 91%, demonstrate its …
MATLAB-based educational software for exploratory data analysis (EDA toolkit)
This article presents an educational software developed in order to enable engineering students to gain insight into data sets via the exploratory data analysis (EDA). This software has been developed using the MATLAB GUIDE tool. This article shows the program suitability for learning EDA in different engineering courses related to data analysis such as data mining or data processing courses. © 2009 Wiley Periodicals, Inc. Comput Appl Eng Educ 20: 313–320, 2012
BELM: Bayesian Extreme Learning Machine
The theory of extreme learning machine (ELM) has become very popular on the last few years. ELM is a new approach for learning the parameters of the hidden layers of a multilayer neural network (as the multilayer perceptron or the radial basis function neural network). Its main advantage is the lower computational cost, which is especially relevant when dealing with many patterns defined in a high-dimensional space. This brief proposes a bayesian approach to ELM, which presents some advantages over other approaches: it allows the introduction of a priori knowledge; obtains the confidence intervals (CIs) without the need of applying methods that are computationally intensive, e.g., bootstrap…
Adaptive algorithms robust to impulsive noise with low computational cost using order statistic
Abstract In this paper a family of adaptive algorithms robust to impulsive noise and with low computational cost are presented. Unlike other approaches, no cost functions or filtering of the gradient are considered in order to update the filter coefficients. Its initial basis is the basic LMS algorithm and its sign-error variant. The proposed algorithms can be considered as some sign-error variants of the LMS algorithm. The algorithms are successfully tested in terms of accuracy and convergence in a standard system identification simulation in which an impulsive noise is present. Simulations show that they improve the performance of LMS variants that are robust to impulsive noise.
Neural networks as effective techniques in clinical management of patients: some case studies
In this paper, we present four examples of effective implementation of neural systems in the daily clinical practice. There are two main goals in this work; the first one is to show that neural networks are especially well-suited tools for solving different kind of medical/pharmaceutical problems, given the complex input output relationships and the few a priori knowledge about data distribution and variable relations. The second goal is to develop specific software applications, which enclose complex mathematical models, to clinicians; thus, the use of such models as decision support systems is facilitated. Four important pharmaceutical problems are considered in this study: identificatio…
Survival prediction in patients undergoing ischemic cardiopathy
The ischemic cardiopathy is the main cause of death in developed countries. New improved drugs and therapies have appeared last years. However, the interventionist strategy and the most powerful drugs may have complications, and hence, it is very important to know the risk of death associated with patients during their stay in the hospital, or in the next six months. Thus, it is possible to tune the best treatment for each individual patient. In this framework, the use of artificial neural networks is proposed with a double objective: survival prediction and the extraction of the parameters with best predictive capabilities. A cohort of 691 patients treated in the Hospital Clinic, in Barcel…
Some Examples for Solving Clinical Problems Using Neural Networks
In this paper neural networks are presented for solving some pharmaceutical problems. We have predicted and prevented patients with potential risk of post-Chemotherapy Emesis and potentially intoxicated patients treated with Digoxin. Neural networks have been also used for predicting Cyclosporine A concentration and Erythropoietin concentrations. Several neural networks (multilayer perceptron for classification tasks and Elman and FIR networks for prediction) and classical methods have been used. Results show how neural networks are very suitable tools for classification and prediction tasks, outperforming the classical methods. In a neural approach it is not strictly necessary to assume a …
Application of Neural Networks in Animal Science
Stock breeding has been one of the most important sources of food and labour throughout human history. Every advance in this field has always led to important and beneficial impacts on human society. These innovations have mainly taken place in machines or genetics, but data analysis has been somewhat ignored. Most of the published works in data analysis use linear models, and there are few works in the literature that use non-linear methods for data processing in stock breeding where these methods have proven to obtain better results and performance than linear, classical methods. This chapter demonstrates the use of non-linear methods by presenting two practical applications: milk yield p…
Neural networks for animal science applications: Two case studies
Abstract Artificial neural networks have shown to be a powerful tool for system modelling in a wide range of applications. In this paper, we focus on neural network applications to intelligent data analysis in the field of animal science. Two classical applications of neural networks are proposed: time series prediction and clustering. The first task is related to the prediction of weekly milk production in goat flocks, which includes a knowledge discovery stage in order to analyse the relative relevance of the different variables. The second task is the clustering of goat flocks; it is used to analyse different livestock surveys by using self-organizing maps and the adaptive resonance theo…