Classification of oximetry signals using Bayesian neural networks to assist in the detection of obstructive sleep apnoea syndrome

In the present study, multilayer perceptron (MLP) neural networks were applied to help in the diagnosis of obstructive sleep apnoea syndrome (OSAS). Oxygen saturation (SaO2) recordings from nocturnal pulse oximetry were used for this purpose. We performed time and spectral analysis of these signals to extract 14 features related to OSAS. The performance of two different MLP classifiers was compared: maximum likelihood (ML) and Bayesian (BY) MLP networks. A total of 187 subjects suspected of suffering from OSAS took part in the study. Their SaO2 signals were divided into a training set with 74 recordings and a test set with 113 recordings. BY-MLP networks achieved the best performance on the test set with 85.58% accuracy (87.76% sensitivity and 82.39% specificity). These results were substantially better than those provided by ML-MLP networks, which were affected by overfitting and achieved an accuracy of 76.81% (86.42% sensitivity and 62.83% specificity). Our results suggest that the Bayesian framework is preferred to implement our MLP classifiers. The proposed BY-MLP networks could be used for early OSAS detection. They could contribute to overcome the difficulties of nocturnal polysomnography (PSG) and thus reduce the demand for these studies.

The application of artificial neural networks to the interpretation and classification of freshwater benthic invertebrate communities

This thesis presents a thorough and principled investigation into the application of artificial neural networks to the biological monitoring of freshwater. It contains original ideas on the classification and interpretation of benthic macroinvertebrates, and aims to demonstrate their superiority over the biotic systems currently used in the UK to report river water quality. The conceptual basis of a new biological classification system is described, and a full review and analysis of a number of river data sets is presented. The biological classification is compared to the common biotic systems using data from the Upper Trent catchment. This data contained 292 expertly classified invertebrate samples identified to mixed taxonomic levels. The neural network experimental work concentrates on the classification of the invertebrate samples into biological class, where only a subset of the sample is used to form the classification. Other experimentation is conducted into the identification of novel input samples, the classification of samples from different biotopes and the use of prior information in the neural network models. The biological classification is shown to provide an intuitive interpretation of a graphical representation, generated without reference to the class labels, of the Upper Trent data. The selection of key indicator taxa is considered using three different approaches; one novel, one from information theory and one from classical statistical methods. Good indicators of quality class based on these analyses are found to be in good agreement with those chosen by a domain expert. The change in information associated with different levels of identification and enumeration of taxa is quantified. The feasibility of using neural network classifiers and predictors to develop numeric criteria for the biological assessment of sediment contamination in the Great Lakes is also investigated.

Classification of Data to Extract Knowledge from Neural Networks

A major drawback of artificial neural networks is their black-box character. Therefore, the rule extraction algorithm is becoming more and more important in explaining the extracted rules from the neural networks. In this paper, we use a method that can be used for symbolic knowledge extraction from neural networks, once they have been trained with desired function. The basis of this method is the weights of the neural network trained. This method allows knowledge extraction from neural networks with continuous inputs and output as well as rule extraction. An example of the application is showed. This example is based on the extraction of average load demand of a power plant.

Adverse drug reaction classification with deep neural networks

We study the problem of detecting sentences describing adverse drug reactions (ADRs) and frame the problem as binary classification. We investigate different neural network (NN) architectures for ADR classification. In particular, we propose two new neural network models, Convolutional Recurrent Neural Network (CRNN) by concatenating convolutional neural networks with recurrent neural networks, and Convolutional Neural Network with Attention (CNNA) by adding attention weights into convolutional neural networks. We evaluate various NN architectures on a Twitter dataset containing informal language and an Adverse Drug Effects (ADE) dataset constructed by sampling from MEDLINE case reports. Experimental results show that all the NN architectures outperform the traditional maximum entropy classifiers trained from n-grams with different weighting strategies considerably on both datasets. On the Twitter dataset, all the NN architectures perform similarly. But on the ADE dataset, CNN performs better than other more complex CNN variants. Nevertheless, CNNA allows the visualisation of attention weights of words when making classification decisions and hence is more appropriate for the extraction of word subsequences describing ADRs.

Evaluation of follicular lymphoid depletion in the Bursa of Fabricius: an alternative methodology using digital image analysis and artificial neural networks

Fifty Bursa of Fabricius (BF) were examined by conventional optical microscopy and digital images were acquired and processed using Matlab® 6.5 software. The Artificial Neuronal Network (ANN) was generated using Neuroshell® Classifier software and the optical and digital data were compared. The ANN was able to make a comparable classification of digital and optical scores. The use of ANN was able to classify correctly the majority of the follicles, reaching sensibility and specificity of 89% and 96%, respectively. When the follicles were scored and grouped in a binary fashion the sensibility increased to 90% and obtained the maximum value for the specificity of 92%. These results demonstrate that the use of digital image analysis and ANN is a useful tool for the pathological classification of the BF lymphoid depletion. In addition it provides objective results that allow measuring the dimension of the error in the diagnosis and classification therefore making comparison between databases feasible.

Kernel machines for epilepsy diagnosis via EEG signal classification: A comparative study

Objective: We carry out a systematic assessment on a suite of kernel-based learning machines while coping with the task of epilepsy diagnosis through automatic electroencephalogram (EEG) signal classification. Methods and materials: The kernel machines investigated include the standard support vector machine (SVM), the least squares SVM, the Lagrangian SVM, the smooth SVM, the proximal SVM, and the relevance vector machine. An extensive series of experiments was conducted on publicly available data, whose clinical EEG recordings were obtained from five normal subjects and five epileptic patients. The performance levels delivered by the different kernel machines are contrasted in terms of the criteria of predictive accuracy, sensitivity to the kernel function/parameter value, and sensitivity to the type of features extracted from the signal. For this purpose, 26 values for the kernel parameter (radius) of two well-known kernel functions (namely. Gaussian and exponential radial basis functions) were considered as well as 21 types of features extracted from the EEG signal, including statistical values derived from the discrete wavelet transform, Lyapunov exponents, and combinations thereof. Results: We first quantitatively assess the impact of the choice of the wavelet basis on the quality of the features extracted. Four wavelet basis functions were considered in this study. Then, we provide the average accuracy (i.e., cross-validation error) values delivered by 252 kernel machine configurations; in particular, 40%/35% of the best-calibrated models of the standard and least squares SVMs reached 100% accuracy rate for the two kernel functions considered. Moreover, we show the sensitivity profiles exhibited by a large sample of the configurations whereby one can visually inspect their levels of sensitiveness to the type of feature and to the kernel function/parameter value. Conclusions: Overall, the results evidence that all kernel machines are competitive in terms of accuracy, with the standard and least squares SVMs prevailing more consistently. Moreover, the choice of the kernel function and parameter value as well as the choice of the feature extractor are critical decisions to be taken, albeit the choice of the wavelet family seems not to be so relevant. Also, the statistical values calculated over the Lyapunov exponents were good sources of signal representation, but not as informative as their wavelet counterparts. Finally, a typical sensitivity profile has emerged among all types of machines, involving some regions of stability separated by zones of sharp variation, with some kernel parameter values clearly associated with better accuracy rates (zones of optimality). (C) 2011 Elsevier B.V. All rights reserved.

Self-Organizing Maps as a New Tool for Classification of Plants at Lower Hierarchical Levels

A chemotaxonomic analysis is described of a database containing various types of compounds from the Heliantheae tribe (Asteraceae) using Self-Organizing Maps (SOM). The numbers of occurrences of 9 chemical classes in different taxa of the tribe were used as variables. The study shows that SOM applied to chemical data can contribute to differentiate genera, subtribes, and groups of subtribes (subtribe branches), as well as to tribal and subtribal classifications of Heliantheae, exhibiting a high hit percentage comparable to that of an expert performance, and in agreement with the previous tribe classification proposed by Stuessy.

Prediction of MHC class II-binding peptides using an evolutionary algorithm and artificial neural network

Motivation: Prediction methods for identifying binding peptides could minimize the number of peptides required to be synthesized and assayed, and thereby facilitate the identification of potential T-cell epitopes. We developed a bioinformatic method for the prediction of peptide binding to MHC class II molecules. Results: Experimental binding data and expert knowledge of anchor positions and binding motifs were combined with an evolutionary algorithm (EA) and an artificial neural network (ANN): binding data extraction --> peptide alignment --> ANN training and classification. This method, termed PERUN, was implemented for the prediction of peptides that bind to HLA-DR4(B1*0401). The respective positive predictive values of PERUN predictions of high-, moderate-, low- and zero-affinity binder-a were assessed as 0.8, 0.7, 0.5 and 0.8 by cross-validation, and 1.0, 0.8, 0.3 and 0.7 by experimental binding. This illustrates the synergy between experimentation and computer modeling, and its application to the identification of potential immunotheraaeutic peptides.

Normal and anomalous classification of category exemplars in schizophrenia

Background Schizophrenia has been associated with semantic memory impairment and previous studies report a difficulty in accessing semantic category exemplars (Moelter et al. 2005 Schizophr Res 78:209–217). The anterior temporal cortex (ATC) has been implicated in the representation of semantic knowledge (Rogers et al. 2004 Psychol Rev 111(1):205–235). We conducted a high-field (4T) fMRI study with the Category Judgment and Substitution Task (CJAST), an analogue of the Hayling test. We hypothesised that differential activation of the temporal lobe would be observed in schizophrenia patients versus controls. Methods Eight schizophrenia patients (7M : 1F) and eight matched controls performed the CJAST, involving a randomised series of 55 common nouns (from five semantic categories) across three conditions: semantic categorisation, anomalous categorisation and word reading. High-resolution 3D T1-weighted images and GE EPI with BOLD contrast and sparse temporal sampling were acquired on a 4T Bruker MedSpec system. Image processing and analyses were performed with SPM2. Results Differential activation in the left ATC was found for anomalous categorisation relative to category judgment, in patients versus controls. Conclusions We examined semantic memory deficits in schizophrenia using a novel fMRI task. Since the ATC corresponds to an area involved in accessing abstract semantic representations (Moelter et al. 2005), these results suggest schizophrenia patients utilise the same neural network as healthy controls, however it is compromised in the patients and the different ATC activity might be attributable to weakening of category-to-category associations.

Automatic learning for the classification of chemical reactions and in statistical thermodynamics

This Thesis describes the application of automatic learning methods for a) the classification of organic and metabolic reactions, and b) the mapping of Potential Energy Surfaces(PES). The classification of reactions was approached with two distinct methodologies: a representation of chemical reactions based on NMR data, and a representation of chemical reactions from the reaction equation based on the physico-chemical and topological features of chemical bonds. NMR-based classification of photochemical and enzymatic reactions. Photochemical and metabolic reactions were classified by Kohonen Self-Organizing Maps (Kohonen SOMs) and Random Forests (RFs) taking as input the difference between the 1H NMR spectra of the products and the reactants. The development of such a representation can be applied in automatic analysis of changes in the 1H NMR spectrum of a mixture and their interpretation in terms of the chemical reactions taking place. Examples of possible applications are the monitoring of reaction processes, evaluation of the stability of chemicals, or even the interpretation of metabonomic data. A Kohonen SOM trained with a data set of metabolic reactions catalysed by transferases was able to correctly classify 75% of an independent test set in terms of the EC number subclass. Random Forests improved the correct predictions to 79%. With photochemical reactions classified into 7 groups, an independent test set was classified with 86-93% accuracy. The data set of photochemical reactions was also used to simulate mixtures with two reactions occurring simultaneously. Kohonen SOMs and Feed-Forward Neural Networks (FFNNs) were trained to classify the reactions occurring in a mixture based on the 1H NMR spectra of the products and reactants. Kohonen SOMs allowed the correct assignment of 53-63% of the mixtures (in a test set). Counter-Propagation Neural Networks (CPNNs) gave origin to similar results. The use of supervised learning techniques allowed an improvement in the results. They were improved to 77% of correct assignments when an ensemble of ten FFNNs were used and to 80% when Random Forests were used. This study was performed with NMR data simulated from the molecular structure by the SPINUS program. In the design of one test set, simulated data was combined with experimental data. The results support the proposal of linking databases of chemical reactions to experimental or simulated NMR data for automatic classification of reactions and mixtures of reactions. Genome-scale classification of enzymatic reactions from their reaction equation. The MOLMAP descriptor relies on a Kohonen SOM that defines types of bonds on the basis of their physico-chemical and topological properties. The MOLMAP descriptor of a molecule represents the types of bonds available in that molecule. The MOLMAP descriptor of a reaction is defined as the difference between the MOLMAPs of the products and the reactants, and numerically encodes the pattern of bonds that are broken, changed, and made during a chemical reaction. The automatic perception of chemical similarities between metabolic reactions is required for a variety of applications ranging from the computer validation of classification systems, genome-scale reconstruction (or comparison) of metabolic pathways, to the classification of enzymatic mechanisms. Catalytic functions of proteins are generally described by the EC numbers that are simultaneously employed as identifiers of reactions, enzymes, and enzyme genes, thus linking metabolic and genomic information. Different methods should be available to automatically compare metabolic reactions and for the automatic assignment of EC numbers to reactions still not officially classified. In this study, the genome-scale data set of enzymatic reactions available in the KEGG database was encoded by the MOLMAP descriptors, and was submitted to Kohonen SOMs to compare the resulting map with the official EC number classification, to explore the possibility of predicting EC numbers from the reaction equation, and to assess the internal consistency of the EC classification at the class level. A general agreement with the EC classification was observed, i.e. a relationship between the similarity of MOLMAPs and the similarity of EC numbers. At the same time, MOLMAPs were able to discriminate between EC sub-subclasses. EC numbers could be assigned at the class, subclass, and sub-subclass levels with accuracies up to 92%, 80%, and 70% for independent test sets. The correspondence between chemical similarity of metabolic reactions and their MOLMAP descriptors was applied to the identification of a number of reactions mapped into the same neuron but belonging to different EC classes, which demonstrated the ability of the MOLMAP/SOM approach to verify the internal consistency of classifications in databases of metabolic reactions. RFs were also used to assign the four levels of the EC hierarchy from the reaction equation. EC numbers were correctly assigned in 95%, 90%, 85% and 86% of the cases (for independent test sets) at the class, subclass, sub-subclass and full EC number level,respectively. Experiments for the classification of reactions from the main reactants and products were performed with RFs - EC numbers were assigned at the class, subclass and sub-subclass level with accuracies of 78%, 74% and 63%, respectively. In the course of the experiments with metabolic reactions we suggested that the MOLMAP / SOM concept could be extended to the representation of other levels of metabolic information such as metabolic pathways. Following the MOLMAP idea, the pattern of neurons activated by the reactions of a metabolic pathway is a representation of the reactions involved in that pathway - a descriptor of the metabolic pathway. This reasoning enabled the comparison of different pathways, the automatic classification of pathways, and a classification of organisms based on their biochemical machinery. The three levels of classification (from bonds to metabolic pathways) allowed to map and perceive chemical similarities between metabolic pathways even for pathways of different types of metabolism and pathways that do not share similarities in terms of EC numbers. Mapping of PES by neural networks (NNs). In a first series of experiments, ensembles of Feed-Forward NNs (EnsFFNNs) and Associative Neural Networks (ASNNs) were trained to reproduce PES represented by the Lennard-Jones (LJ) analytical potential function. The accuracy of the method was assessed by comparing the results of molecular dynamics simulations (thermal, structural, and dynamic properties) obtained from the NNs-PES and from the LJ function. The results indicated that for LJ-type potentials, NNs can be trained to generate accurate PES to be used in molecular simulations. EnsFFNNs and ASNNs gave better results than single FFNNs. A remarkable ability of the NNs models to interpolate between distant curves and accurately reproduce potentials to be used in molecular simulations is shown. The purpose of the first study was to systematically analyse the accuracy of different NNs. Our main motivation, however, is reflected in the next study: the mapping of multidimensional PES by NNs to simulate, by Molecular Dynamics or Monte Carlo, the adsorption and self-assembly of solvated organic molecules on noble-metal electrodes. Indeed, for such complex and heterogeneous systems the development of suitable analytical functions that fit quantum mechanical interaction energies is a non-trivial or even impossible task. The data consisted of energy values, from Density Functional Theory (DFT) calculations, at different distances, for several molecular orientations and three electrode adsorption sites. The results indicate that NNs require a data set large enough to cover well the diversity of possible interaction sites, distances, and orientations. NNs trained with such data sets can perform equally well or even better than analytical functions. Therefore, they can be used in molecular simulations, particularly for the ethanol/Au (111) interface which is the case studied in the present Thesis. Once properly trained, the networks are able to produce, as output, any required number of energy points for accurate interpolations.

A sensor classification strategy for robotic manipulators

In practice the robotic manipulators present some degree of unwanted vibrations. The advent of lightweight arm manipulators, mainly in the aerospace industry, where weight is an important issue, leads to the problem of intense vibrations. On the other hand, robots interacting with the environment often generate impacts that propagate through the mechanical structure and produce also vibrations. In order to analyze these phenomena a robot signal acquisition system was developed. The manipulator motion produces vibrations, either from the structural modes or from endeffector impacts. The instrumentation system acquires signals from several sensors that capture the joint positions, mass accelerations, forces and moments, and electrical currents in the motors. Afterwards, an analysis package, running off-line, reads the data recorded by the acquisition system and extracts the signal characteristics. Due to the multiplicity of sensors, the data obtained can be redundant because the same type of information may be seen by two or more sensors. Because of the price of the sensors, this aspect can be considered in order to reduce the cost of the system. On the other hand, the placement of the sensors is an important issue in order to obtain the suitable signals of the vibration phenomenon. Moreover, the study of these issues can help in the design optimization of the acquisition system. In this line of thought a sensor classification scheme is presented. Several authors have addressed the subject of the sensor classification scheme. White (White, 1987) presents a flexible and comprehensive categorizing scheme that is useful for describing and comparing sensors. The author organizes the sensors according to several aspects: measurands, technological aspects, detection means, conversion phenomena, sensor materials and fields of application. Michahelles and Schiele (Michahelles & Schiele, 2003) systematize the use of sensor technology. They identified several dimensions of sensing that represent the sensing goals for physical interaction. A conceptual framework is introduced that allows categorizing existing sensors and evaluates their utility in various applications. This framework not only guides application designers for choosing meaningful sensor subsets, but also can inspire new systems and leads to the evaluation of existing applications. Today’s technology offers a wide variety of sensors. In order to use all the data from the diversity of sensors a framework of integration is needed. Sensor fusion, fuzzy logic, and neural networks are often mentioned when dealing with problem of combing information from several sensors to get a more general picture of a given situation. The study of data fusion has been receiving considerable attention (Esteban et al., 2005; Luo & Kay, 1990). A survey of the state of the art in sensor fusion for robotics can be found in (Hackett & Shah, 1990). Henderson and Shilcrat (Henderson & Shilcrat, 1984) introduced the concept of logic sensor that defines an abstract specification of the sensors to integrate in a multisensor system. The recent developments of micro electro mechanical sensors (MEMS) with unwired communication capabilities allow a sensor network with interesting capacity. This technology was applied in several applications (Arampatzis & Manesis, 2005), including robotics. Cheekiralla and Engels (Cheekiralla & Engels, 2005) propose a classification of the unwired sensor networks according to its functionalities and properties. This paper presents a development of a sensor classification scheme based on the frequency spectrum of the signals and on a statistical metrics. Bearing these ideas in mind, this paper is organized as follows. Section 2 describes briefly the robotic system enhanced with the instrumentation setup. Section 3 presents the experimental results. Finally, section 4 draws the main conclusions and points out future work.

Classification Performance of Multilayer Perceptrons with Different Risk Functionals

In the present paper we assess the performance of information-theoretic inspired risks functionals in multilayer perceptrons with reference to the two most popular ones, Mean Square Error and Cross-Entropy. The information-theoretic inspired risks, recently proposed, are: HS and HR2 are, respectively, the Shannon and quadratic Rényi entropies of the error; ZED is a risk reflecting the error density at zero errors; EXP is a generalized exponential risk, able to mimic a wide variety of risk functionals, including the information-thoeretic ones. The experiments were carried out with multilayer perceptrons on 35 public real-world datasets. All experiments were performed according to the same protocol. The statistical tests applied to the experimental results showed that the ubiquitous mean square error was the less interesting risk functional to be used by multilayer perceptrons. Namely, mean square error never achieved a significantly better classification performance than competing risks. Cross-entropy and EXP were the risks found by several tests to be significantly better than their competitors. Counts of significantly better and worse risks have also shown the usefulness of HS and HR2 for some datasets.

Decision fusion for the classification of hyperspectral data: Outcome of the 2008 GRS-S data fusion contest

The 2008 Data Fusion Contest organized by the IEEE Geoscience and Remote Sensing Data Fusion Technical Committee deals with the classification of high-resolution hyperspectral data from an urban area. Unlike in the previous issues of the contest, the goal was not only to identify the best algorithm but also to provide a collaborative effort: The decision fusion of the best individual algorithms was aiming at further improving the classification performances, and the best algorithms were ranked according to their relative contribution to the decision fusion. This paper presents the five awarded algorithms and the conclusions of the contest, stressing the importance of decision fusion, dimension reduction, and supervised classification methods, such as neural networks and support vector machines.

Morphometric shape analysis using learning vector quantization neural networks - an example distinguishing two microtine vole species

Closely related species may be very difficult to distinguish morphologically, yet sometimes morphology is the only reasonable possibility for taxonomic classification. Here we present learning-vector-quantization artificial neural networks as a powerful tool to classify specimens on the basis of geometric morphometric shape measurements. As an example, we trained a neural network to distinguish between field and root voles from Procrustes transformed landmark coordinates on the dorsal side of the skull, which is so similar in these two species that the human eye cannot make this distinction. Properly trained neural networks misclassified only 3% of specimens. Therefore, we conclude that the capacity of learning vector quantization neural networks to analyse spatial coordinates is a powerful tool among the range of pattern recognition procedures that is available to employ the information content of geometric morphometrics.