Search

This paper analyzes and compares the sensitivity and suitability of several artificial intelligence techniques applied to the Morgan&ndash, Keenan (MK) system for the classification of stars. The MK system is based on a sequence of spectral prototypes that allows classifying stars according to their effective temperature and luminosity through the study of their optical stellar spectra. Here, we include the method description and the results achieved by the different intelligent models developed thus far in our ongoing stellar classification project: fuzzy knowledge-based systems, backpropagation, radial basis function (RBF) and Kohonen artificial neural networks. Since one of today&rsquo, s major challenges in this area of astrophysics is the exploitation of large terrestrial and space databases, we propose a final hybrid system that integrates the best intelligent techniques, automatically collects the most important spectral features, and determines the spectral type and luminosity level of the stars according to the MK standard system. This hybrid approach truly emulates the behavior of human experts in this area, resulting in higher success rates than any of the individual implemented techniques. In the final classification system, the most suitable methods are selected for each individual spectrum, which implies a remarkable contribution to the automatic classification process.

Lung modules are an initial indicator as to whether or not a patient will develop lung carcinoma which has a significant mortality rate if it is not detected at an early stage. The detection of these lung nodules is a complex task and is time-consuming for the radiologist. For these reasons, CAD systems have been developed and employed for the detection of lung nodules. In this article, we present a CAD system that uses a hybrid strategy: techniques for the analysis of medical images and soft computing (fuzzy clustering, SVM and ANN) with a description of the main stages: preprocessing, identification of ROIs (region of interest), creation of VOIs (volume interests) and ROI classifications. Remarkable elements of the system are: detection automation, a new phase to reduce the ROIs false positives and a new algorithm to build the VOIs in order to improve the location and a better detection. For its development, helical CT studies proceeding from the LIDC public database have been used. The system achieves similar and even better results to other CADs for the same purpose with a sensitivity of 82% and a number of false positives of 7.3 per study.

0, info:eu-repo/semantics/published

Graphical abstractDisplay Omitted HighlightsSelf-Organizing Maps (SOMs) are powerful tools with many applications. Nevertheless, they cannot deal directly with categorical variables.In order to present categorical variables to SOMs, they are usually transformed by binarization. This increases dramatically the dataset dimensionality.NCSOM has been presented in order to cope with categorical or mixed data. However, it presents some drawbacks: categorical and numerical variables are not equally balanced and the method is not convergent.A novel SOM variant, called FMSOM, is presented which is able to deal with numerical and categorical variables, giving the same weight to them and ensuring convergence. A scalable implementation of the method is fully described.FMSOM is applied to a benchmark of well known datasets, composed of categorical and mixed data. The results show the potential of the method to analyze this kind of datasets. Even though Self-Organizing Maps (SOMs) constitute a powerful and essential tool for pattern recognition and data mining, the common SOM algorithm is not apt for processing categorical data, which is present in many real datasets. It is for this reason that the categorical values are commonly converted into a binary code, a solution that unfortunately distorts the network training and the posterior analysis. The present work proposes a SOM architecture that directly processes the categorical values, without the need of any previous transformation. This architecture is also capable of properly mixing numerical and categorical data, in such a manner that all the features adopt the same weight. The proposed implementation is scalable and the corresponding learning algorithm is described in detail. Finally, we demonstrate the effectiveness of the presented algorithm by applying it to several well-known datasets.

Geographic Information Systems (GIS) have gained popularity in recent years because they provide spatial data management and access through the Web. This article gives a detailed description of a tool that offers an integrated framework for the detection and localization of marine spills using remote sensing, GIS, and cloud computing. Advanced segmentation algorithms are presented in order to isolate dark areas in SAR images, including fuzzy clustering and wavelets. In addition, cloud computing is used for scaling up the algorithms and providing communication between users.

Synthetic aperture radar (SAR) images are a valuable source of information for the detection of marine oil spills. For their effective analysis, it is important to have segmentation algorithms that can delimit possible oil spill areas. This article addresses the application of clustering, logistic regression and convolutional neural network algorithms for the detection of oil spills in Envisat and Sentinel-1 satellite images. Large oil spills do not occur frequently so that the identification of a pixel as oil is relatively uncommon. Metrics based on Precision–Recall curves have been employed because they are useful for problems with an imbalance in the number of samples from the classes. Although logistic regression and clustering algorithms can be considered useful for oil spill segmentation, the combination of convolutional techniques and neural networks achieves the best results with low computing time. A convolutional neural network has been integrated into a decision support system in order to facilitate decision-making and data analysis of possible oil spill events.

Gaia is an ESA cornerstone astronomical mission that will observe with unprecedented precision positions, distances, space motions, and many physical properties of more than one billion objects in our Galaxy and beyond. It will observe all objects in the sky in the visible magnitude range from 6 to 20, up to approximately 10^9 sources. An international scientific consortium, the Gaia Data Processing and Analysis Consortium (Gaia DPAC), has organized itself in several coordination units, with the aim, among others, of addressing the work of classifying the observed astronomical sources, using both supervised and unsupervised classification algorithms. This work focuses on the analysis of classification outliers by means of unsupervised classification. We present a novel method to combine SOMs trained with independent features that are calculated from spectrophotometry. The method as described here can help to improve the models used for the supervised classification of astronomical sources. Furthermore, it allows for data exploration and knowledge discovery in huge astronomical databases such as the upcoming Gaia mission.

The detection of pulmonary nodules is one of the most studied problems in the field of medical image analysis due to the great difficulty in the early detection of such nodules and their social impact. The traditional approach involves the development of a multistage CAD system capable of informing the radiologist of the presence or absence of nodules. One stage in such systems is the detection of ROI (regions of interest) that may be nodules in order to reduce the space of the problem. This paper evaluates fuzzy clustering algorithms that employ different classification strategies to achieve this goal. After characterising these algorithms, the authors propose a new algorithm and different variations to improve the results obtained initially. Finally it is shown as the most recent developments in fuzzy clustering are able to detect regions that may be nodules in CT studies. The algorithms were evaluated using helical thoracic CT scans obtained from the database of the LIDC (Lung Image Database Consortium).

This work presents a strategy for the classification of astronomical objects based on spectrophotometric data and the use of unsupervised neural networks and statistical classification algorithms. Our strategy constitutes an essential part of the preparation phase of the automatic classification and parameterization algorithms for the data that are to be collected by the Gaia satellite of the European Space Agency (ESA), whose launch is foreseen for the spring of 2012. The proposed algorithm is based on a hierarchical structure of neural networks composed of various tree-structured SOM networks. The classification of possible astronomical objects (stars, galaxies, quasars, multiple objects, etc.) basically consists in the iterative segmentation of the inputs space and the ensuing generation of initial classifications and increase in classification precision by means of a refining process. Apart from providing a classification, our technique also measures the quality and precision of the classifications and segments the objects for which it cannot determine whether or not they belong to a pre-established class of astronomical objects (outliers).

Gaia is the next astrometric ESA mission, conceived to extend the Hipparcos legacy by producing what has been called the first stereoscopic census of the Galaxy. The spacecraft will be launched by spring of 2012 and will measure astrometry with unprecedented accuracy for a significant 1% of the objects in the Milky Way. Additionally, two spectrophotometers will determine the spectral energy distributions (SEDs) of the objects in the region of 0.3-1 μm, and a radial velocity spectrograph (RVS) will measure the kinematics of the brightest objects (down to 17 mag). The Gaia RVS will provide spectra in the near-IR Ca II triplet region with an expected signal-to- noise ratio (S/N) between 100 and 20 for FGK stars with visual magnitude between 8 and 15. In order to deal with the enormous volume of data that the mission will generate, automated specialized analysis tools are being devel- oped by the mission scientific Data Analysis and Processing Consortium (Gaia DPAC). In particular, we have been testing several analysis techniques in order to be prepared to extract all possible astrophysical information from RVS stellar spectra. A combination of data processing in transformed domains (Fourier analysis and wavelet multilevel decomposition) and connectionist systems (artificial neural networks, ANNs) has proven to be a good approach to derive the fundamental stellar parameters, Teff, log g, ½Fe=H� , and ½α=Fe� , on the basis of RVS synthetic spectra blurred with noise at different S/N. Signal-processing techniques allowed us to estimate and categorize the S/N, which in turn is found to be essential since the optimal algorithm for parameterization is highly dependent on S/N. In the case of low S/N (5-25) spectra, it is found that the wavelet transform provides a competitive approach for parameterization. The derivation of the stellar parameters is performed by the use of ANNs trained with the error backpropagation algorithm. The accuracy of the parameters' derivation is presented for typical Galaxy populations.

One of the upcoming cornerstone missions of the European Space Agency (ESA) is Gaia, a spacecraft that will be launched in 2011 and will carry out a stereoscopic census of our Galaxy and its environment by measuring with unprecedented exactitude the astrometry (distance and movements), the photometric distribution from ultraviolet to the infrared of its components, and, in the case of the brightest objects (mainly stars), the spectrum with intermediate resolution in the region of the infrared CaII triplet, with a spectrograph known as Radial Velocity Spectrometer (RVS). Stars are the basic constituents of our Galaxy, and they can be characterized if we can estimate their principal atmospheric parameters: effective temperature, gravity, metal content (general abundance of elements other than H and He), and their abundance of alpha elements (elements with Z>22, [@a/Fe]), which provide information on the physical environment in which the star was born. This work presents our results for the parameterization of stellar spectra with simulated data (synthetic spectra) in the spectral region of the RVS and with the application of Artificial Intelligence Techniques based on ANNs. Our work has two main purposes: to determine the optimal domain for the ANNs performance, and to develop an adequate noise detection and filtering algorithm.

Astrophysics is evolving toward a more rational use of costly observational data by intelligently exploiting the large terrestrial and spatial astronomical databases. In this paper, we present a study showing the suitability of an expert system to perform the classification of stellar spectra in the Morgan and Keenan (MK) system. Using the formalism of artificial intelligence for the development of such a system, we propose a rules' base that contains classification criteria and confidence grades, all integrated in an inference engine that emulates human reasoning by means of a hierarchical decision rules tree that also considers the uncertainty factors associated with rules. Our main objective is to illustrate the formulation and development of such a system for an astrophysical classification problem. An extensive spectral database of MK standard spectra has been collected and used as a reference to determine the spectral indexes that are suitable for classification in the MK system. It is shown that by considering 30 spectral indexes and associating them with uncertainty factors, we can find an accurate diagnose in MK types of a particular spectrum. The system was evaluated against the NOAO-INDO-US spectral catalog.

Estimating the presence and size of fishing banks has significant ecological and economic advantages: it contributes to a rational exploitation of the available marine resources, to the reduction of fuel costs, and to a general decrease in required fishing time. This work presents the integration of remote sensing techniques and connectionist models for the prediction of fishing banks. We have developed and implemented an information system that stores and processes the data from various satellites and visualizes them by generating a geographic forecasting map.

Since its launch in December 2013, the Gaia space mission has collected and continues to collect tremendous amounts of information concerning the objects that populate our Galaxy and beyond. The international Gaia Data and Analysis Consortium (DPAC) is in charge of developing computer algorithms that extract and process astrophysical information from these objects. It organizes its work by means of work packages; one of these packages, Outlier Analysis, is dedicated to the exploration of vast amounts of outlier objects detected during the main classification of the observations. We present a method that is based on Self-Organizing Maps (SOM) and parallelized by means of the Hadoop framework so as to improve its performance. We also compare the execution times of both the sequential and the distributed versions of the algorithm.

This article presents the application of various Artificial Intelligence techniques to images that proceed from Remote Sensing and serve to predict Prionace Glauca captures (the Prionace Glauca is a type of shark). Our data proceed from remote sensors whose spectral signature allows us to calculate products that are useful for ecological modelling. After digitally processing the Remote Sensing images, we created a database from which to extract the necessary patterns for the training of the artificial neural networks (Backpropagation network, RBF, functional separability network) and the neuro-diffuse networks (ANFIS). These data are used for the training of our system with the aforementioned algorithms. The results show that for this type of problems the generalisation capacity of the functional networks is reduced, which is probably due to the absence of a subjacent mathematical model. Finally, the implementation was carried out with a multilayer perceptron that was trained with a Backpropagation algorithm (error backpropagation); a method that is less complicated than the ANFIS and RBF networks.

This paper presents the application of artificial intelligence techniques to optical spectroscopy, a specific field of Astrophysics. We propose the analysis, design and implementation of an intelligent system for the analysis and classification of the low-resolution optical spectra of supergiant, giant and dwarf stars, with luminosity levels I, III and V, respectively. The developed system automatically and objectively collects the most important spectral features, and determines the temperature and luminosity of the stars according to the current standard system. The system development combines signal processing, expert systems and fuzzy logic techniques, and integrates them through the use of a relational database, which allows us to structure the collected astronomical data and to contrast the results of the different classification methods. As an additional research, we have designed and implemented several models of artificial neural networks, including them as an alternative method for the classification of spectra.

In recent years, functional networks have emerged as an extension of artificial neural networks (ANNs). In this article, we apply both network techniques to predict the catches of the Prionace Glauca (a class of shark) and the Katsowonus Pelamis (a variety of tuna, more commonly known as the Skipjack). We have developed an application that will help reduce the search time for good fishing zones and thereby increase the fleet’s competitivity. Our results show that, thanks to their superior learning and generalisation capacities, functional networks are more efficient than ANNs. Our data proceeds from remote sensors. Their spectral signatures allow us to calculate products that are useful for ecological modelling. After an initial phase of digital image processing, we created a database that provides all the necessary patterns to train both network types.

This paper describes the design and implementation of an intelligent system by means of which multiple anaerobic systems for wastewater treatment are controlled individually by local controllers which are linked to a common remote central supervisor via wide area networks in a client/server network architecture. The local control systems have a hybrid structure, comprising both algorithmic routines for data acquisition, signal preprocessing, calculation of plant operation parameters, etc., and an expert system based on production rules embodying non-mathematical or semiquantitative knowledge of the unit’s operation. The system shows a modular structure, which allows for easy modification or updating with improved versions. The expert system starts up faster than a human operator and maintains the stability of the biological process by modifications in the operating conditions of the plants, reporting warnings and alarms to the central system. The central supervisor acquires, analyses, interprets and stores the data sent by the on-site bioreactor control systems in a relational database, allowing remote specification of plant operating setpoints and continual development of the system. The database is linked with the expert system in order to extend the working memory to the database, allowing its use as an information source. The client/server architecture has been analysed using two different aspects. Firstly, different operating systems were under consideration in the local equipment, in order to determine the networking, multitasking and temporal behaviour. Secondly, different implementations of the network communication were taken into account to make it more flexible, and to allow better adaptation to the communication infrastructure.

This paper describes the design and implementation of an intelligent real-time supervision system for the monitoring and control of wastewater treatment plants. The system presents a hybrid structure which integrates knowledge engineering techniques and methodologies (an expert system based on production rules embodying non-mathematical or semiquantitative knowledge of unit operation) and algorithmic process-related methods (data acquisition, signal preprocessing, calculation of plant operation parameters etc.). The fundamental design aspects consist of temporal information treatment, artifact detection and a client- server structure which allows the telesupervision of various plants by a central system.

The complexity of the monitored data available in modern intensive care units (ICUs) means that they are best processed, for presentation to medical staff, by expert system techniques. This article describes an expert system that has an appropriately designed inference engine, handling the temporal considerations inherent in monitoring and manages data acquisition via a Medical Information Bus. Also, we will describe how we extended our monitoring system in ICUs by writing an interface allowing communication in dynamic SQL with a relational database management system. The extended system facilitates both permanent filing of case data and the use of filed data by the rules of the expert system, and allows automatic intelligent screening of data prior to permanent filing so as to ensure data reliability.

Because of the complexity of monitored data in modern intensive care units (ICUs), and the risk of information being overlooked if medical staff have to pay attention to a multiplicity of monitoring apparatuses and alarm signals, the data for each patient may well be best presented on a single bedside screen after digestion by expert system techniques. Such central units should be able to deal with data from any monitoring apparatus, not just a predefined set. Furthermore, relay of the information from each bed to a central control station (one per ICU) is desirable for the purposes of permanent storage and for in-depth analysis. The paper describes a comprehensive system for ICU monitoring management and patient data analysis that integrates multiple expert systems and computers. The basic difficulties in applying expert system techniques to monitoring are overcome with the shell OPS/83, which allows calls to sequential C routines and allows time-driven reasoning through appropriate design of the inference engine and rules. Flexibility as regards connectable monitoring apparatus is afforded by basing data acquisition mainly, though not exclusively, on the IEEE Medical Information Bus.