A low-complexity fuzzy activation function for artificial neural networks

A novel fuzzy-based activation function for artificial neural networks is proposed. This approach provides easy hardware implementation and straightforward interpretability in the basis of IF-THEN rules. Backpropagation learning with the new activation function also has low computational complexity. Several application examples ( XOR gate, chaotic time-series prediction, channel equalization, and independent component analysis) support the potential of the proposed scheme.     

An easy demonstration of the optimum value of the adaptationconstant in the LMS algorithm [FIR filter theory]

The least mean squares (LMS) is the most widely used algorithm among those proposed to adapt the coefficients of an FIR filter in order to minimize the mean-square error (MSE) between its output and the desired signal. Since the introduction of the LMS algorithm, many variants have been proposed to improve its performance. Doubtless, the most popular is the normalized LMS algorithm, which uses a value for the adaptation constant that assures the fastest convergence. This correspondence shows a new demonstration of the algorithm based on a mathematical approach easier than that usually proposed     

Self-Organising Maps: A new way to screen the level of satisfaction of dialysis patients

Evaluation of patient satisfaction has become an important indicator for assessing health care quality. Fresenius Medical Care (FME) as a global provider of dialysis services through its NephroCare network has a strong interest in monitoring patient satisfaction.The aim of the paper is to test and validate a methodology for detecting a residual area of low satisfaction in dialysis patients.The FME Patient Satisfaction Programme questionnaire was distributed to haemodialysis (HD) patients treated in 335 centers of its network. It contained 79 questions covering various satisfaction aspects regarding Dialysis Unit, Dialysis Arrangement, Nurses, Doctors, etc.To analyse the data provided by the questionnaire, the Self-Organising Map (SOM) method was used. SOM is a neural network model for clustering and projecting high-dimensional data into a low-dimensional space, preserving topological relationships of original high-dimensional data spaces.10,632 HD patients completed the questionnaire. Mean age was 63.05 ± 14.93 years with 56.69% males. Response rate was 66%. Overall level of satisfaction was 1.99 (range from ?3 to +3). On average patients were very satisfied with all issues. Nevertheless, a group of patients, around 60 years old, balanced gender ratio, whose level of satisfaction was lower than 1, were highlighted.In the NephroCare clinics patient satisfaction with service is rather high. While traditional analysis usually stops here, the SOM method allows identification of areas of potential improvement for specific patient groups.     

Dosage individualization of erythropoietin using a profile-dependent support vector regression

The external administration of recombinant human erythropoietin is the chosen treatment for those patients with secondary anemia due to chronic renal failure in periodic hemodialysis. The objective of this paper is to carry out an individualized prediction of the EPO dosage to be administered to those patients. The high cost of this medication, its side-effects and the phenomenon of potential resistance which some individuals suffer all justify the need for a model which is capable of optimizing dosage individualization. A group of 110 patients and several patient factors were used to develop the models. The support vector regressor (SVR) is benchmarked with the classical multilayer perceptron (MLP) and the Autoregressive Conditional Heteroskedasticity (ARCH) model. We introduce a priori knowledge by relaxing or tightening the epsilon-insensitive region and the penalization parameter depending on the time period of the patients' follow-up. The so-called profile-dependent SVR (PD-SVR) improves results of the standard SVR method and the MLP. We perform sensitivity analysis on the MLP and inspect the distribution of the support vectors in the input and feature spaces in order to gain knowledge about the problem.     

Detecting rottenness caused by Penicillium genus fungi in citrus fruits using machine learning techniques

Penicillium fungi are among the main defects that may affect the commercialization of citrus fruits. Economic losses in fruit production may become enormous if an early detection of that kind of fungi is not carried out. That early detection is usually based either on UltraViolet light carried out manually. This work presents a new approach based on hyperspectral imagery for defect segmentation. Both the physical device and the data processing (geometric corrections and band selection) are presented. Achieved results using classifiers based on Artificial Neural Networks and Decision Trees show an accuracy around 98%; it shows up the suitability of the proposed approach.     

Web mining based on Growing Hierarchical Self-Organizing Maps: Analysis of a real citizen web portal

This work is focused on the usage analysis of a citizen web portal, Infoville XXI (http://www.infoville.es) by means of Self-Organizing Maps (SOM). In this paper, a variant of the classical SOM has been used, the so-called Growing Hierarchical SOM (GHSOM). The GHSOM is able to find an optimal architecture of the SOM in a few iterations. There are also other variants which allow to find an optimal architecture, but they tend to need a long time for training, especially in the case of complex data sets. Another relevant contribution of the paper is the new visualization of the patterns in the hierarchical structure. Results show that GHSOM is a powerful and versatile tool to extract relevant and straightforward knowledge from the vast amount of information involved in a real citizen web portal.     

Development of a Hyperspectral Computer Vision System Based on Two Liquid Crystal Tuneable Filters for Fruit Inspection. Application to Detect Citrus Fruits Decay

Hyperspectral systems are characterised by offering the possibility of acquiring a large number of images at different consecutive wavebands. To ensure reliable and repeatable results using this kind of optical sensors, the intensity shown by the objects in the different spectral images must be independent from the differences in sensitivity of the system for the different wavelengths. The spectral efficiency of the acquisition devices and the spectral emission of the lighting system vary across the spectrum and the images, and therefore the results can reproduce these variations if the system is not properly calibrated and corrected. This is particularly complex, when several LCTF devices are used to obtain large spectral ranges. This work presents the development of a hyperspectral system based on two liquid crystal tuneable filters for the acquisition of images of spherical fruits. It also proposes a methodology for acquiring and segmenting images of citrus fruits aimed at detecting decay in citrus fruits that has been capable of correctly classifying 98 % of pixels as rotten or non-rotten and 95 % of fruit.     

Robust support vector method for hyperspectral data classification and knowledge discovery

We propose the use of support vector machines (SVMs) for automatic hyperspectral data classification and knowledge discovery. In the first stage of the study, we use SVMs for crop classification and analyze their performance in terms of efficiency and robustness, as compared to extensively used neural and fuzzy methods. Efficiency is assessed by evaluating accuracy and statistical differences in several scenes. Robustness is analyzed in terms of: (1) suitability to working conditions when a feature selection stage is not possible and (2) performance when different levels of Gaussian noise are introduced at their inputs. In the second stage of this work, we analyze the distribution of the support vectors (SVs) and perform sensitivity analysis on the best classifier in order to analyze the significance of the input spectral bands. For classification purposes, six hyperspectral images acquired with the 128-band HyMAP spectrometer during the DAISEX-1999 campaign are used. Six crop classes were labeled for each image. A reduced set of labeled samples is used to train the models, and the entire images are used to assess their performance. Several conclusions are drawn: (1) SVMs yield better outcomes than neural networks regarding accuracy, simplicity, and robustness; (2) training neural and neurofuzzy models is unfeasible when working with high-dimensional input spaces and great amounts of training data; (3) SVMs perform similarly for different training subsets with varying input dimension, which indicates that noisy bands are successfully detected; and (4) a valuable ranking of bands through sensitivity analysis is achieved.     

Application of adaptive signal processing for determining thelimits of P and T waves in an ECG

A new algorithm for the determination of the limits of P and T waves is proposed, and its foundations are mathematically analyzed. The algorithm performs an adaptive filtering so that the searched point corresponds to a minimum. Crucial properties of its performance are discussed, i.e., immunity to base line drifts and full adaptation to any cardiological criteria. A series of tests are made involving real registers with different morphologies for P and T-waves     

Machine learning methods to forecast temperature in buildings

Efficient management of energy in buildings saves a very important amount of resources (both economic and technological). As a consequence, there is a very active research in this field. One of the keys of energy management is the prediction of the variables that directly affect building energy consumption and personal comfort. Among these variables, one can highlight the temperature in each room of a building. In this work we apply different machine learning techniques along with other classical ones for predicting the temperatures in different rooms. The obtained results demonstrate the validity of these techniques for predicting temperatures and, therefore, for the establishment of optimal policies of energy consumption.