Germán Sanchis-Trilles and Jesús Andrés-Ferrer and Guillem Gascó Jesús González-Rubio and Pascual Martı́nez-Gómez and Martha-Alicia Rocha Joan-Andreu Sánchez and Francisco Casacuberta Instituto Tecnológico de Informática Departamento de Sistemas Informáticos y Computación Universidad Politécnica de Valencia {gsanchis|jandres|fcn}@dsic.upv.es {ggasco|jegonzalez|pmartinez}@dsic.upv.es {mrocha|jand...

The distribution of adipose tissue thickness, fat cell weight (FCW), and number (FCN) were studied in four regions in randomly selected middle-aged men and women and in 930 obese individuals. Both the obese and the randomly selected men were found to have the largest adipose tissue thickness in the abdominal region. Women, however, showed a relative preponderance for the gluteal and femoral reg...

We present a new convolutional neural network-based time-series model. Typical convolutional neural network (CNN) architectures rely on the use of max-pooling operators in between layers, which leads to reduced resolution at the top layers. Instead, in this work we consider a fully convolutional network (FCN) architecture that uses causal filtering operations, and allows for the rate of the out...

OBJECTIVE Executive dysfunction might be an important determinant for response to pharmacotherapy in obsessive-compulsive disorder (OCD), and could be sustained independently of symptom relief. The anterior cingulate cortex (ACC) has been indicated as a potential neural correlate of executive functioning in OCD. The present study examined the brain-executive function relationships in OCD from t...

We propose a hybrid architecture composed of fully convolutional network (FCN) and Dempster-Shafer layer for image semantic segmentation. In the so-called evidential FCN (E-FCN), an encoder-decoder first extracts pixel-wise feature maps from input image. A then computes mass functions at each pixel location based on distances to prototypes. Finally, utility performs segmentation allows imprecis...

Deep fully convolutional neural network (FCN) based architectures have shown great potential in medical image segmentation. However, such architectures usually have millions of parameters and inadequate number of training samples leading to over-fitting and poor generalization. In this paper, we present a novel highly parameter and memory efficient FCN based architecture for medical image analy...

A novel anionic water-soluble pillar[5]arene (4C-WP5A) was synthesized via a convenient synthetic strategy of the direct cyclization of a functionalized hydroquinone monomer. The alkyl chain dependent affinities of ferrocenyl aminiums (FCn(+), n: carbon number) with 4C-WP5A are driven by hydrophobic interactions and desolvations with assisted C-H···π interactions and electrostatic interactions.

Deep learning based methods, such as Convolution Neural Network (CNN), have demonstrated their efficiency in hyperspectral image (HSI) classification. These methods can automatically learn spectral-spatial discriminative features within local patches. However, for each pixel an HSI, it is not only related to its nearby pixels but also has connections far away from itself. Therefore, incorporate...