Search

To produce realistic synthetic images, it is important to shade objects based on real illumination conditions of a scene. Estimating the direction of the light source of the scene is a key factor to achieve this. Properly estimating this source under noisy conditions is very challenging, and it is a subject of intense research. Computational intelligence techniques offer promising way of tackling this problem. This paper presents a novel neural network-based approach for recovering light source direction in relation to the viewpoint direction of a graphical image in noisy environments. The estimated light source direction can be used for the generation of 3D images from 2D ones. Experiments are performed using both synthetic and real images in noisy scenes. Four synthetic surfaces where generated with varying light source directions for a total of 12 images. Three real images were also used with varying degrees of noise. The experimental results show that the proposed approach is robust and provides a good level of accuracy. [ABSTRACT FROM AUTHOR]

Highlights: [•] Multilayer perceptrons are used to simulate the I–V curve of thin-film PV modules. [•] APE from the spectral irradiance was added as an input variable to the network. [•] A self-organised map is used to select the curves used for training the network. [•] Curve error and maximum power error decrease when using this technique. [•] This method could provide accurate estimation of the output of a PV plant. [ABSTRACT FROM AUTHOR]

The recursive deterministic perceptron (RDP) is a generalization of the single layer perceptron neural network. This neural network can separate, in a deterministic manner, any classification problem (linearly separable or not). It relies on the principle that in any nonlinearly separable (NLS) two-class classification problem, a linearly separable (LS) subset of one or more points belonging to one of the two classes can always be found. Small network topologies can be obtained when the LS subsets are of maximum cardinality. This is referred to as the problem of maximum separability and has been proven to be NP-Complete. Evolutionary computing techniques are applied to handle this problem in a more efficient way than the standard approaches in terms of complexity. These techniques enhance the RDP training in terms of speed of conversion and level of generalization. They provide an alternative to tackle large classification problems which is otherwise not feasible with the algorithmic versions of the RDP training methods. [ABSTRACT FROM AUTHOR]

Abstract: This paper studies the reliability of geometric features for the identification of users based on hand biometrics. Our methodology is based on genetic algorithms and mutual information. The aim is to provide a system for user identification rather than a classification. Additionally, a robust hand segmentation method to extract the hand silhouette and a set of geometric features in hard and complex environments is described. This paper focuses on studying how important and discriminating the hand geometric features are, and if they are suitable in developing a robust and reliable biometric identification. Several public databases have been used to test our method. As a result, the number of required features have been drastically reduced from datasets with more than 400 features. In fact, good classification rates with about 50 features on average are achieved, with a 100% accuracy using the GA–LDA strategy for the GPDS database and 97% for the CASIA and IITD databases, approximately. For these last contact-less databases, reasonable EER rates are also obtained. [Copyright &y& Elsevier]

Abstract: We study the relationship between linear separability and the level of complexity of classification data sets. Linearly separable classification problems are generally easier to solve than non linearly separable ones. This suggests a strong correlation between linear separability and classification complexity. We propose a novel and simple method for quantifying the complexity of the classification problem. The method, which is shown below, reduces any two class classification problem to a sequence of linearly separable steps. The number of such reduction steps could be viewed as measuring the degree of non-separability and hence the complexity of the problem. This quantification in turn can be used as a measure for the complexity of classification data sets. Results obtained using several benchmarks are provided. [Copyright &y& Elsevier]

Abstract: Several algorithms exist for testing linear separability. The choice of a particular testing algorithm has effects on the performance of constructive neural network algorithms that are based on the transformation of a nonlinear separability classification problem into a linearly separable one. This paper presents an empirical study of these effects in terms of the topology size, the convergence time, and generalisation level of the neural networks. Six different methods for testing linear separability were used in this study. Four out of the six methods are exact methods and the remaining two are approximative ones. A total of nine machine learning benchmarks were used for this study. [ABSTRACT FROM AUTHOR]

We will try to study the aesthetic quality of the representation of an object as an operation related to an explication of the world through which we can more properly give a meaning to the world than know it. This action, that we understand as an aesthetic projection of the world, will be used to explain certain religious phenomena, namely we will try to explain faith and, as well, will make an approach to prayer. [ABSTRACT FROM AUTHOR]

Abstract: The Recursive Deterministic Perceptron (RDP) feed-forward multilayer neural network is a generalisation of the single layer perceptron topology. This model is capable of solving any two-class classification problem as opposed to the single layer perceptron which can only solve classification problems dealing with linearly separable sets. For all classification problems, the construction of an RDP is done automatically and convergence is always guaranteed. Three methods for constructing RDP neural networks exist: Batch, Incremental, and Modular. The Batch method has been extensively tested and it has been shown to produce results comparable with those obtained with other neural network methods such as Back Propagation, Cascade Correlation, Rulex, and Ruleneg. However, no testing has been done before on the Incremental and Modular methods. Contrary to the Batch method, the complexity of these two methods is not NP-Complete. For the first time, a study on the three methods is presented. This study will allow the highlighting of the main advantages and disadvantages of each of these methods by comparing the results obtained while building RDP neural networks with the three methods in terms of the convergence time, the level of generalisation, and the topology size. The networks were trained and tested using the following standard benchmark classification datasets: IRIS, SOYBEAN, and Wisconsin Breast Cancer. The results obtained show the effectiveness of the Incremental and the Modular methods which are as good as that of the NP-Complete Batch method but with a much lower complexity level. The results obtained with the RDP are comparable to those obtained with the backpropagation and the Cascade Correlation algorithms. [Copyright &y& Elsevier]

• Most of foreground detection methods are pixel-based which implies higher complexity. • Several effective methods hardly reach real time execution for 320 × 240 pixels videos. • The rise of low cost devices requires lighter foreground detection algorithms. • Each scene has been represented with a set of tilings. • The final foreground mask consists of a combination of the masks of this set. In this work a novel region-based approach for the detection of foreground in video sequences is presented. The model consists of an ensemble of layers or tilings, where each tiling represents, by means of randomly chosen parallelogram regions, the background of the scene. Currently, the image size of video surveillance cameras far exceeds one megapixel (more than 1024 × 768), and pixel-based proposals are poorly suited for near real-time ratios. Therefore, the analysis by pixel is replaced by an analysis by region, improving the final resolution by overlapping regions or parallelograms with different shapes and sizes. Thus, for each frame, each region estimates the probability of belonging to the foreground or background, to finally compute the consensus foreground mask among all the tilings. With this proposal, it is possible to detect the foreground in high resolution sequences, a process that is not feasible using pixel-level techniques. Several experiments have been carried out by employing a wide range of videos. A qualitative and quantitative comparison with the state-of-the-art algorithms is performed by using a well-known video dataset benchmark. The results show the feasibility of our proposal compared with higher resolution methods. [ABSTRACT FROM AUTHOR]

• Unsupervised clustering algorithms can be used for crop type identification on remote images. • Results of performance of clustering algorithms and distance measures are analysed. • 26 datasets built with all the combination of 5 crops and more than 45000 parcels. • Best performances are obtained for Spectral clustering method. • Manhattan and Euclidean are in general the best distance measures. With the current challenges in population growth and scarceness of food, new technologies are emerging. Remote sensing in general and satellite imagery more specifically are part of these technologies which can help provide accurate monitoring and classification of cultivars. Part of the increase in the use of these technologies has to do with the ongoing increment on the spatial–temporal resolution together with the free availability of some of these services. Typically time series are used as a pre-processing technique and combined with supervised learning techniques in order to build models for crop type identification in remote images. However, these models suffer from the lack of labelled data sets needed to train them. Unsupervised classification can overcome this limitation but has been less frequently used in this research field. This paper proposes to test and analyse the performance of several unsupervised clustering algorithms towards crop type identification on remote images. In this manner combinations of clustering algorithms and distance measures, a key element in the behaviour of these algorithms, are studied using an experimental design with more than twenty datasets built from the combinations of five crops and more than 45000 parcels. Results highlight better clustering methods and distance measures to create accurate and novel crop mapping models for remote sensing images. [ABSTRACT FROM AUTHOR]

In the area of medical imaging, one of the factors that can negatively influence the performance of prediction algorithms is the limited number of observations for each class within a labeled dataset. Usually, in order to increase the samples, a second set of unlabeled images is used. However, this set adds two new problems (i) finding patient observations with different pathologies than those observed in the labeled data set and (ii) finding images belonging to a different distribution from the dataset used in the model training process. This way, merging datasets from different sources can have an adverse effect on the distribution of features. Encountering this type of data (better known as out-of-distribution data) within the deployment environments may also lead to varying degrees of performance degradation as can be seen in the different experimental results obtained. In this research, a study of the behavior of Feature Density is made, as a mathematical model for the estimation of predictive uncertainty in supervised classification algorithms, in order to improve the behavior when out-of-distribution data are presented in the dataset. The Feature Density method is based on the estimation of feature density by means of histogram calculation (or Probability Density Function). The advantage of this method over the baseline approach (Mahalanobis distance) is that it does not assume a Gaussian-type distribution of sample characteristics and serves to estimate the uncertainty. This work focuses on the binary classification of mammography X-ray images from three different datasets simulating the condition of a different degree of contamination with out-of-distribution sample. According to the obtained results, the performance of the proposed method depends directly on the architecture of the implemented neural network. [ABSTRACT FROM AUTHOR]

Nowadays, regression is a very demanded predictive task to solve a wide range of problems belonging to different research and society areas. Examples of applications include industry, economic, medical and energy fields. Ensemble methodology works by merging the output obtained from a set of base methods (learners), achieving successful results in both classification and regression tasks. Traditional ensembles use the output of the whole set of base methods, in a static way, to obtain the result of the ensemble. However, latest studies show that dynamic selection of learners or even dynamic aggregation of their outputs produce better results. Methodologies that integrate these techniques are called dynamic ensembles or dynamic ensemble selection. Although the literature and tools to work with dynamic ensembles for classification tasks is abundant, for regression tasks these resources are scarcer. This paper aims to mitigate these shortcomings by presenting a library for the design, development and execution of dynamic ensembles for regression problems. Specifically, the Python software package DESReg is presented. This library allows us to access to the latest dynamic ensemble techniques in the field, standing out for its high configurability, its support for extending it with user-defined functions or its parallel computation capabilities. [ABSTRACT FROM AUTHOR]

The implementation of deep learning-based computer-aided diagnosis systems for the classification of mammogram images can help in improving the accuracy, reliability, and cost of diagnosing patients. However, training a deep learning model requires a considerable amount of labelled images, which can be expensive to obtain as time and effort from clinical practitioners are required. To address this, a number of publicly available datasets have been built with data from different hospitals and clinics, which can be used to pre-train the model. However, using models trained on these datasets for later transfer learning and model fine-tuning with images sampled from a different hospital or clinic might result in lower performance. This is due to the distribution mismatch of the datasets, which include different patient populations and image acquisition protocols. In this work, a real-world scenario is evaluated where a novel target dataset sampled from a private Costa Rican clinic is used, with few labels and heavily imbalanced data. The use of two popular and publicly available datasets (INbreast and CBIS-DDSM) as source data, to train and test the models on the novel target dataset, is evaluated. A common approach to further improve the model's performance under such small labelled target dataset setting is data augmentation. However, often cheaper unlabelled data is available from the target clinic. Therefore, semi-supervised deep learning, which leverages both labelled and unlabelled data, can be used in such conditions. In this work, we evaluate the semi-supervised deep learning approach known as MixMatch, to take advantage of unlabelled data from the target dataset, for whole mammogram image classification. We compare the usage of semi-supervised learning on its own, and combined with transfer learning (from a source mammogram dataset) with data augmentation, as also against regular supervised learning with transfer learning and data augmentation from source datasets. It is shown that the use of a semi-supervised deep learning combined with transfer learning and data augmentation can provide a meaningful advantage when using scarce labelled observations. Also, we found a strong influence of the source dataset, which suggests a more data-centric approach needed to tackle the challenge of scarcely labelled data. We used several different metrics to assess the performance gain of using semi-supervised learning, when dealing with very imbalanced test datasets (such as the G-mean and the F2-score), as mammogram datasets are often very imbalanced. [ABSTRACT FROM AUTHOR]

Abstract: Fault detection and diagnosis (FDD) is an important issue in building energy conservation. This paper proposes a new option for solving this problem at the building level by using a recursive deterministic perceptron (RDP) neural network. Results show a higher than 97% level of generalization in all the designed experiments. Based on this high detection ability of RDP model, a new diagnostic architecture is proposed. Our experiments demonstrate that it is able to not only report correct source of faults but also sort sources in the order of degradation likelihood. [Copyright &y& Elsevier]

In this paper, a cooperative-competitive multi-objective evolutionary fuzzy system called E2PAMEA is presented for the extraction of emerging patterns in big data environments. E2PAMEA follows an adaptive schema to automatically employ different genetic operators according to the learning needs, which avoid the tuning of some parameters. It also employs a token-competition-based procedure for updating an elite population where the best set of patterns found so far is stored. In addition, a novel MapReduce procedure for an efficient computation of the evaluation function employed for guiding the search process is proposed. The method, called Bit-LUT employs a pre-evaluation stage where data is represented as a look-up table made of bit sets. This look-up table can be employed later in the chromosome evaluation by means of bitwise operations, reducing the computational complexity of the process. The experimental study carried out shows that E2PAMEA is a promising alternative for the extraction of high-quality emerging patterns in big data. In addition, the proposed Bit-LUT evaluation shows a significant improvement on efficiency with a great scalability capacity on both dimensions of data, which enables the processing of massive datasets faster than other alternatives. [ABSTRACT FROM AUTHOR]

Purpose To describe the dynamic changes of the intraocular pressure (IOP) and intracranial pressure (ICP) with normal or pathological values (intracranial hypertension) in nonglaucomatous neurological patients during lumbar punction ( LP). Methods Case-control study, prospective measurement of tonometry in both groups referred for LP. Intraocular pressure, ICP and translaminar pressure difference ( TPD) were compared pre- and post- LP. Results Thirty-six patients (72 eyes) with mean age of 38.5 (16-64) years and BMI of 26.81 kg/m2 were analysed. The initial mean ICP was 12.81 (± 6.6) mmHg. The mean TPD before and after the LP was 1.48 mmHg and 0.65 mmHg, respectively. The mean IOP of both eyes decreased to 0.8 mmHg post- LP in patients with pathological ICP (p = 0.0193) and normal ICP (p = 0.006). Conclusions We found a statistically significant decrease of the IOP post- LP compared to the pre- LP in both groups, being higher in patients with pathological ICP. There were no significant differences of the IOP in patients with normal versus pathological ICP pre- LP/post- LP; neither was found a correlation between ICP and IOP. [ABSTRACT FROM AUTHOR]

El síndrome del vértice orbitario se caracteriza por involucro de los nervios craneales III, IV y VI, la rama oftálmica del trigémino (VI) y asociado con alteración del nervio óptico. Enumerándose entre las causas: inflamatoria, Infecciosa. Neoplásica, traumática, latrogénica y procesos vascularas. De las causas infecoiosas se refieran los hongos, baterías, espiroquetas y virus; y de las bacterias hay escasos reportes en la literatura médica por mycobacterium tuberculosis. Hay reportes de casos de síndrome del seno cavernosos uní o bilateral, que ocurre en presencia o ausencia de otro hallazgo del sistema nervioso, y algunos reportes del 2001, refieran que un tuberculoma del seno cavernoso puede presentarse en ausencia de hallazgos pulmonares Caso clínico: presentamos el caso de un paciente del sexo femenino de 41 años, sin antecedentes de importancia para padecimiento actual, y que inicia el 29 de septiembre del 2007; con cefalea progresiva en hemicráneo izquierdo y de predominio frontal, de carácter pulsátil, de intensidad de 10/10 y de predominio vespertino, acompañado de náusea sin Ilegar al vómito, exacerbándose con maniobras de valsalva y aumentado con la flexión del cuello, siendo tratada con complejo B intramuscular y medicamento por via oral no especificado, sin mejoría de su sintomatología. El 01 de octubre del 2007, se agrega diplopía, y posteriormente disminución de la agudeza visual de ojo izquierdo, endodesviacion y ptosis, la cefalea se intensifica a 10/10, sin mejoría con AINES. El 23 de noviembre del 2007, es atendida por el servicio de neuro-oftalmología, y continúa con cefalea progresiva de predominio frontal con vértigo y náusea, presentando diplopía vertical y horizontal con ptosis y oftalmoplegía total del ojo izquierdo. Exploración oftalmológica (23 noviembre de 2007). Agudeza visual: ojo derecho 20/20, ojo izquierdo: no percibe luz. Sensibilidad cromática: ojo derecho 8/8, ojo izquierdo 0/8. Sensibilidad comeal: ojo derecho conservado ojo izquierdo: hipoestesia. Reflejos pupilares: ojo derecho: fotomotor presente y normal, ojo izquierdo: midríasis, arrefléctica Movilidad: endotropia de más de 30 Dp, de ojo izquierdo, con limitación de dicho ojo, a la abducción de -4, a la aducción de -2, a la supraduccion de -3 y a la infraducción de -2. Campo visual: ojo derecho: completo, ojo izquierdo: amaurótico Fondo de ojo: ojo derecho e izquierdo: pápila normal, coloración naranja, bordes regulares, vasos centrales, retina aplicada. Se realiza el diagnóstico de síndrome del vértice orbitario izquierdo, paciente que tenía afectación del II, III, IV, VI y VI. Requirió hospitalización en noviembre del 2007, la imagen de resonancia magnética reporta proceso ocupativo en el vértice de la orbita, el 12 de diciembre del 2007; se le realiza PPD la cual es positivo. Y en líquido cefalorraquídeo se obtiene PCR para tuberculosis positivo, por lo que inicia tratamiento con antifílmicos. En 3 meses la visión de estar en no percepción de luz de ojo izquierdo queda en cuenta dedos con recuperación de la movilidad ocular y con una atrofía óptica izquierda secundario a síndrome de vértice de la órbita por tuberculosis. [ABSTRACT FROM AUTHOR]

DeMontfort University's (DMU) Centre for Computational Intelligence (CCI) is engaged in a range of programmes applying modern Computational Intelligence (CI) techniques to provide superior analysis of complex real-time data sets that arise within transport systems. Better use of existing transport infrastructures can achieve positive sustainable outcomes, reducing congestion, improving air quality, providing real-time travel information and supporting low carbon vehicles. This is exemplified by the following examples: * ITRAQ, an integrated CI system that uses live feeds to determine the optimum use of the road system to reduce congestion and to improve air quality. * Sustainable Airport development Decision Support Systems. A CI based model that interfaces with a GIS system to model the environmental impact of flight paths. * The application of CI to solve multi-variable systems, logistics and passenger information. * VenusSim. The use of CI to model the dynamics of customer flows in transport terminals. [ABSTRACT FROM AUTHOR]

Introduction: Multiple Sclerosis represents a diagnostic and therapeutic challenge in developing countries since treatment delay is associated to disability while the costs of the approved pharmacological agents have a great economic impact. This Mexican consensus was developed with the aim to analyse the necessary procedures and requirements for the comprehensive care of the disease. Material and methods: A meeting consensus was carried out with the attendance of 21 physicians from seven states of the country, specialists in neurology, neuropediatrics, neuroepidemiology and neuroophthalmology, as well as professionals in areas of administration and teaching. The principal health institutions, both public and private, were represented. Results: The necessary diagnostic and therapeutic procedures were analysed according to scientific evidence; commentaries on availability in the country and guidelines and algorithms for their application were elaborated. Discussion: It is recommended that health institutions provide all the approved medications to allow physicians to choose the adequate treatment, according to the patient's condition. Authorization of ‘generic’ interferons (biosimilars) for sale or institutional use is a matter of concern for Mexican neurologists, since regulatory agencies with international impact (i.e. FDA, EMEA) have not approved these products because there is not evidence on their efficacy and safety, neither represent any economic advantage. The present guidelines constitute a medical proposal to develope Official Mexican Norms for the therapeutic management of multiple sclerosis. [ABSTRACT FROM AUTHOR]

Las malformacionas de Chiari son defectos estructurales del cerebelo, ubicándose este por debajo del foramen magno, y se puede dar cuando el espacio óseo es más pequeño que lo normal, ocasionando que el cerebelo y el tallo cerebral sean empujados hacia abajo, dentro del foramen magno y del canal espinal superior. La presión ejercida puede afectar las funciones controladas por esas aéreas y bloquear el flujo del líquido cefalorraquídeo La etiología es aún desconocida, siendo resultado de un defecto estructural que se produce durante el desarrollo fetal, y teniendo como factores de riesgo: las genétices, exposición a tóxicos, carencia vitamínica e infecciones entre otras. Se clasifican en 4 tipos: Tipo I: involucra la extensión de las amígdalas cerebelosas dentro del foramen magno, sin involucrar al tallo cerebral. Normalmente, sólo la médula espinal pasa por este orificio. No da sintomatología y es la presentación más común, observándose por primera vez en la adolescencia o en la edad adulta y sólo como un hallazgo. Tipo II: (malformación clásica): se caracteriza porque el cerebelo y tallo cerebral se encuentran dentro del foramen magno, el vermis puede estar completo, parcial o ausente. Se acompaña de mielomeningocele. Tipo III: es la forma más seria, el cerebelo y tallo cerebral sobresalen o se hernian a través del foramen magno hacia la médula espinal. Parte del cuarto ventrículo puede sobresalir por el orificio y dentro de la médula espinal, en raras ocasiones, el tejido herniado puede causar un encefalocele occipital, causando graves defectos neurológicos.… [ABSTRACT FROM AUTHOR]