Search results for "Pattern recognition"
showing 10 items of 2301 documents
Classification of Heart Sounds Using Convolutional Neural Network
2020
Heart sounds play an important role in the diagnosis of cardiac conditions. Due to the low signal-to-noise ratio (SNR), it is problematic and time-consuming for experts to discriminate different kinds of heart sounds. Thus, objective classification of heart sounds is essential. In this study, we combined a conventional feature engineering method with deep learning algorithms to automatically classify normal and abnormal heart sounds. First, 497 features were extracted from eight domains. Then, we fed these features into the designed convolutional neural network (CNN), in which the fully connected layers that are usually used before the classification layer were replaced with a global averag…
Combining feature extraction and expansion to improve classification based similarity learning
2017
Abstract Metric learning has been shown to outperform standard classification based similarity learning in a number of different contexts. In this paper, we show that the performance of classification similarity learning strongly depends on the data format used to learn the model. We then present an Enriched Classification Similarity Learning method that follows a hybrid approach that combines both feature extraction and feature expansion. In particular, we propose a data transformation and the use of a set of standard distances to supplement the information provided by the feature vectors of the training samples. The method is compared to state-of-the-art feature extraction and metric lear…
Local electrical characterisation of human atrial fibrillation
2002
The rate of success of radio-frequency catheter ablation in the treatment of atrial fibrillation may be significantly improved by evaluating the local electrical properties of the atrial tissue. The aim of this study is the development of an automatic procedure for the characterisation of the local electrical activity during atrial fibrillation and the comparison of its performance with the manual analysis. The adopted procedures were the semi-automatic measurement of the local fibrillation intervals (A-A intervals) and the manual electrogram classification following the criteria suggested by Wells (1978) or Konings (1997). Two methods have been used: Principal Component Analysis and Cluste…
Testing the X-IFU calibration requirements: an example for quantum efficiency and energy resolution
2018
With its array of 3840 Transition Edge Sensors (TESs) operated at 90 mK, the X-Ray Integral Field Unit (X-IFU) on board the ESA L2 mission Athena will provide spatially resolved high-resolution spectroscopy (2.5 eV FWHM up to 7 keV) over the 0.2 to 12 keV bandpass. The in-flight performance of the X-IFU will be strongly affected by the calibration of the instrument. Uncertainties in the knowledge of the overall system, from the filter transmission to the energy scale, may introduce systematic errors in the data, which could potentially compromise science objectives - notably those involving line characterisation e.g. turbulence velocity measurements - if not properly accounted for. Defining…
The performance of the ATHENA X-ray Integral Field Unit
2018
The X-ray Integral Field Unit (X-IFU) is a next generation microcalorimeter planned for launch onboard the Athena observatory. Operating a matrix of 3840 superconducting Transition Edge Sensors at 90 mK, it will provide unprecedented spectro-imaging capabilities (2.5 eV resolution, for a field of view of 5') in the soft X-ray band (0.2 up to 12 keV), enabling breakthrough science. The definition of the instrument evolved along the phase A study and we present here an overview of its predicted performances and their modeling, illustrating how the design of the X-IFU meets its top-level scientific requirements. This article notably covers the energy resolution, count-rate capability, quantum …
A methodology for assessing the effect of correlations among muscle synergy activations on task-discriminating information
2013
Delis, Ioannis | Berret, Bastien | Pozzo, Thierry | Panzeri, Stefano; International audience; ''Muscle synergies have been hypothesized to be the building blocks used by the central nervous system to generate movement. According to this hypothesis, the accomplishment of various motor tasks relies on the ability of the motor system to recruit a small set of synergies on a single-trial basis and combine them in a task-dependent manner. It is conceivable that this requires a fine tuning of the trial-to-trial relationships between the synergy activations. Here we develop an analytical methodology to address the nature and functional role of trial-to-trial correlations between synergy activation…
Performance of Fine-Tuning Convolutional Neural Networks for HEp-2 Image Classification
2020
The search for anti-nucleus antibodies (ANA) represents a fundamental step in the diagnosis of autoimmune diseases. The test considered the gold standard for ANA research is indirect immunofluorescence (IIF). The best substrate for ANA detection is provided by Human Epithelial type 2 (HEp-2) cells. The first phase of HEp-2 type image analysis involves the classification of fluorescence intensity in the positive/negative classes. However, the analysis of IIF images is difficult to perform and particularly dependent on the experience of the immunologist. For this reason, the interest of the scientific community in finding relevant technological solutions to the problem has been high. Deep lea…
Deep Convolutional Neural Networks for Fire Detection in Images
2017
Detecting fire in images using image processing and computer vision techniques has gained a lot of attention from researchers during the past few years. Indeed, with sufficient accuracy, such systems may outperform traditional fire detection equipment. One of the most promising techniques used in this area is Convolutional Neural Networks (CNNs). However, the previous research on fire detection with CNNs has only been evaluated on balanced datasets, which may give misleading information on real-world performance, where fire is a rare event. Actually, as demonstrated in this paper, it turns out that a traditional CNN performs relatively poorly when evaluated on the more realistically balance…
Foetal ECG recovery using dynamic neural networks
2002
Non-invasive electrocardiography has proven to be a very interesting method for obtaining information about the foetus state and thus to assure its well-being during pregnancy. One of the main applications in this field is foetal electrocardiogram (ECG) recovery by means of automatic methods. Evident problems found in the literature are the limited number of available registers, the lack of performance indicators, and the limited use of non-linear adaptive methods. In order to circumvent these problems, we first introduce the generation of synthetic registers and discuss the influence of different kinds of noise to the modelling. Second, a method which is based on numerical (correlation coe…
Ambiguity and complementation in recognizable two-dimensional languages
2008
The theory of one-dimensional (word) languages is well founded and investigated since fifties. From several years, the increasing interest for pattern recognition and image processing motivated the research on two-dimensional or picture languages, and nowadays this is a research field of great interest. A first attempt to formalize the concept of finite state recognizability for two-dimensional languages can be attributed to Blum and Hewitt ([7]) who started in 1967 the study of finite state devices that can define two-dimensional languages, with the aim to finding a counterpart of what regular languages are in one dimension. Since then, many approaches have been presented in the literature…