Search results for " Informatica"
showing 10 items of 978 documents
Comparing model-free and model-based transfer entropy estimators in cardiovascular variability
2013
Information flow between heart period (T), systolic pressure (S) and respiration (R) variability in a head-up tilt (HUT) protocol is assessed by transfer entropy (TE). Two estimates of TE are compared: the model-based (MB) approach using linear regression under the Gaussian assumption, and the model-free (MF) approach combining binning estimates of entropy and non-uniform delay embedding. The approaches were applied to 300-beats series of T, S, R measured in the supine (su) and upright (up) positions during HUT. Both MB and MF approaches detected a unidirectional information transfer from R to T and from R to S, and a significant decrease of the TE from R to T, as well as a significant incr…
Separating respiratory influences from the tachogram: Methods and their sensitivity to the type of respiratory signal
2014
Respiration is one of the main modulators causing heart rate variability (HRV). However, when interpreting studies of HRV, the effect of respiration is largely ignored. We, therefore, previously proposed to take respiratory influences into account by separating the tachogram in a component that is related to respiration and one that contains all residual variations. In this study, we aim to investigate the sensitivity of two of such separation methods, i.e. one based on an ARMAX model and another one based on orthogonal subspace projection (OSP), towards different respiratory signal types, such as nasal airflow (the reference), thoracic and abdominal efforts, and three ECG-derived respirato…
Fuzzy Clustering of Histopathological Images Using Deep Learning Embeddings
2021
Metric learning is a machine learning approach that aims to learn a new distance metric by increas- ing (reducing) the similarity of examples belonging to the same (different) classes. The output of these approaches are embeddings, where the input data are mapped to improve a crisp or fuzzy classifica- tion process. The deep metric learning approaches regard metric learning, implemented by using deep neural networks. Such models have the advantage to discover very representative nonlinear embed- dings. In this work, we propose a triplet network deep metric learning approach, based on ResNet50, to find a representative embedding for the unsupervised fuzzy classification of benign and maligna…
Estimation of confidence limits for descriptive indexes derived from autoregressive analysis of time series: Methods and application to heart rate va…
2017
The growing interest in personalized medicine requires making inferences from descriptive indexes estimated from individual recordings of physiological signals, with statistical analyses focused on individual differences between/within subjects, rather than comparing supposedly homogeneous cohorts. To this end, methods to compute confidence limits of individual estimates of descriptive indexes are needed. This study introduces numerical methods to compute such confidence limits and perform statistical comparisons between indexes derived from autoregressive (AR) modeling of individual time series. Analytical approaches are generally not viable, because the indexes are usually nonlinear funct…
Touch or touchless?:Evaluating usability of interactive displays for persons with autistic spectrum disorders
2019
Interactive public displays have been exploited and studied for engaging interaction in several previous studies. In this context, applications have been focused on supporting learning or entertainment activities, specifically designed for people with special needs. This includes, for example, those with Autism Spectrum Disorders (ASD). In this paper, we present a comparison study aimed at understanding the difference in terms of usability, effectiveness, and enjoyment perceived by users with ASD between two interaction modalities usually supported by interactive displays: touch-based and touchless gestural interaction. We present the outcomes of a within-subject setup involving 8 ASD users…
Automated prostate gland segmentation based on an unsupervised fuzzy C-means clustering technique using multispectral T1w and T2w MR imaging
2017
Prostate imaging analysis is difficult in diagnosis, therapy, and staging of prostate cancer. In clinical practice, Magnetic Resonance Imaging (MRI) is increasingly used thanks to its morphologic and functional capabilities. However, manual detection and delineation of prostate gland on multispectral MRI data is currently a time-expensive and operator-dependent procedure. Efficient computer-assisted segmentation approaches are not yet able to address these issues, but rather have the potential to do so. In this paper, a novel automatic prostate MR image segmentation method based on the Fuzzy C-Means (FCM) clustering algorithm, which enables multispectral T1-weighted (T1w) and T2-weighted (T…
CORENup: a combination of convolutional and recurrent deep neural networks for nucleosome positioning identification
2020
Abstract Background Nucleosomes wrap the DNA into the nucleus of the Eukaryote cell and regulate its transcription phase. Several studies indicate that nucleosomes are determined by the combined effects of several factors, including DNA sequence organization. Interestingly, the identification of nucleosomes on a genomic scale has been successfully performed by computational methods using DNA sequence as input data. Results In this work, we propose CORENup, a deep learning model for nucleosome identification. CORENup processes a DNA sequence as input using one-hot representation and combines in a parallel fashion a fully convolutional neural network and a recurrent layer. These two parallel …
Single neuron binding properties and the magical number 7
2008
When we observe a scene, we can almost instantly recognize a familiar object or can quickly distinguish among objects differing by apparently minor details. Individual neurons in the medial temporal lobe of humans have been shown to be crucial for the recognition process, and they are selectively activated by different views of known individuals or objects. However, how single neurons could implement such a sparse and explicit code is unknown and almost impossible to investigate experimentally. Hippocampal CA1 pyramidal neurons could be instrumental in this process. Here, in an extensive series of simulations with realistic morphologies and active properties, we demonstrate how n radial (ob…
Logical Key Hierarchy for Group Management in Distributed Online Social Networks
2016
Distributed Online Social Networks (DOSNs) have recently been proposed to shift the control over user data from a unique entity to the users of the DOSN themselves. In this paper, we focus our attention on the problem of privacy preserving content sharing to a large group of users of the DOSNs. Several solutions, based on cryptographic techniques, have been recently proposed. The main challenge here is the definition of a scalable and decentralized approach that: i) minimizes the re-encryption of the contents published in a group when the composition of the group changes and ii) enables a fast distribution of the cryptographic keys to all the members (n) of a group, each time a new user is …
A Wavelet approach to extract main features from indirect immunofluorescence images
2019
A number of previous studies have shown that IIF image analysis requires complex and sometimes heterogeneous and diversified methods. Robust solutions can be proposed but they need to orchestrate several methods from low-level analysis up to more complex neural networks or SVM for data classification. The contribution intends to highlight the versatility of Wavelet Transform (WT) and their use in various levels of analysis for the classification of IIF images in order to develop a system capable of performing: image enhancement, ROI segmentation and object classification. Therefore, WT was adopted in the de-noise section, segmentation and classification. This analysis allows frequencies cha…