No abstract

We report Lobachevsky University Database (LUDB) of ECG signals, an open tool for validating ECG delineation algorithms, that is superior to the existing publicly available data bases in several aspects. LUDB contains 200 recordings of 10-second 12-lead electrocardiograms (ECG) from different subjects, representative of a variety of signal morfologies. The boundaries and peaks of QRS complexes and P and T waves are manually annotated by cardiologists for all recordings and independently for each lead, and all records received an expert classification by abnormalities. We present a case study for the recently proposed wavelet-based algorithm and the broadly used ecg-kit tool, and demonstrate the advantage of multi-lead ECG data analysis. LUDB contributes to the diversity of public databases employed in developing and validating novel ECG analysis algorithms, including the most advanced based on deep learning neural networks.

No abstract

‫ޒ‬ d : Ax ≥ b} can be found by solving a similar problem for the cone {(x, x d + 1 ) ∈ ‫ޒ‬ d + 1: Ax -bx d + 1 ≥ 0, x d + 1 ≥ 0} and, then, setting x d + 1 = 1.These problems arise in many applications, such as computer graphics, physical simulation, image processing, cartography, computational biology, theoretical physicist, and others. The construction of a Abstract-A new modification of the double description method is proposed for constructing the skel eton of a polyhedral cone. Theoretical results and a numerical experiment show that the modification is considerably superior to the original algorithm in terms of speed.

A new algorithm has been developed for delineation of significant points of various electrocardiographic signal (ECG) waves, taking into account information from all available leads and providing similar or higher accuracy in comparison with other modern technologies. The test results for the QT database show a sensitivity above 97% when detecting ECG wave peaks and 96% for their onsets and offsets, as well as better positive predictive value compared to the previously known algorithms. In contrast to the previously published algorithms, the proposed approach also allows one to determine the morphology of waves. The segmentation mean errors of all significant points are below the tolerances defined by the Committee of General Standards for Electrocardiography (CSE).

Abstract. It is known that a minimal teaching set of any threshold function on the twodimensional rectangular grid consists of 3 or 4 points. We derive exact formulae for the numbers of functions corresponding to these values and further refine them in the case of a minimal teaching set of size 3. We also prove that the average cardinality of the minimal teaching sets of threshold functions is asymptotically 7 /2. We further present corollaries of these results concerning some special arrangements of lines in the plane.

We propose a method for generating an electrocardiogram (ECG) signal for one cardiac cycle using a variational autoencoder. Our goal was to encode the original ECG signal using as few features as possible. Using this method we extracted a vector of new 25 features, which in many cases can be interpreted. The generated ECG has quite natural appearance. The low value of the Maximum Mean Discrepancy metric, 3.83 × 10−3, indicates good quality of ECG generation too. The extracted new features will help to improve the quality of automatic diagnostics of cardiovascular diseases. Generating new synthetic ECGs will allow us to solve the issue of the lack of labeled ECG for using them in supervised learning.

No abstract