In this work, a Nadaraya-Watson kernel based learning system which owns general regression neural network topology is adapted to Q learning method to evaluate a quick and efficient action selection policy for reinforcement learning problems. By means of the proposed method Q value function is generalized and learning speed of Q agent is accelerated. The training data of the developed neural network are obtained by a standard Q learning agent on closed-loop simulation system. The efficiency of the proposed method is tested on popular reinforcement learning benchmarks and its performance is compared with other popular regression methods and Q-learning utilized methods. QLRNN increased the learning performance and it learns faster than other methods on selected benchmarks. Test results showed the efficiency and the importance of the proposed network.
This paper deals with two kinds of fuzzy implications: QL and Dishkant implications. That is, those defined through the expressions I(x,y)=S(N(x),T(x,y)) and I(x,y)=S(T(N(x),N(y)),y) respectively, where T is a t-norm, S is a t-conorm and N is a strong negation. Special attention is due to the relation between both kinds of implications. In the continuous case, the study of these implications is focused in some of their properties (mainly the contrapositive symmetry and the exchange principle). Finally, the case of non continuous t-norms or non continuous t-conorms is studied, deriving new implications of both kinds and showing that they remain strongly connected.
The aim of the study was to detect the changes of QT dispersion (QTd) due to cardiotoxicity of tricyclic antidepressant dosulepin. Electrocardiographic and vectorcardiographic recordings were obtained using Cardiag 112.2 diagnostic system from 28 psychiatric outpatients treated with prophylactic doses of dosulepin and compared to those obtained from 37 healthy volunteers. From these recordings following parameters were evaluated: QTd, spatial QRS-STT angle and amplitude of T-wave. The acquired data were correlated with the dosulepin plasma levels using Spearman´s rank order correlation test. The average QTd (±S.D.) in the dosulepin group was significantly higher (70±21 ms) than that in the control group (34±12 ms) (P<0.001). Moreover, the correlation between QTd and the dosulepin plasma levels was highly significant (r = 0.7871, P<0.001). Similar results were obtained when QTc dispersion was used. On the contrary, the QRS-STT space angle did not correlate with the dosulepin plasma levels. Furthermore, the T-wave amplitude was not significantly correlated to the QT-interval. Thus we can conclude that the QT dispersion could be used as a simple marker of the dosulepin effect on the myocardium.
Gestational diabetes mellitus (GDM) represents additional risks to both mother and infant. Moreover it increases a woman's risk of cardiovascular disease in the postpartum. The aim of our study was therefore to detect changes of both the QT dispersion and the electrical heart field that could be typical for GDM. Body surface potential maps were obtained using the Cardiac 112.2 device from 26 young women with GDM and 54 young healthy pregnant women in the 36th week of pregnancy. The same recordings were obtained from 18 healthy women in the same age (19-36 years). The average QT dispersion (±SD) in women suffering from GDM was significantly higher (107±25 ms) both than in those with physiological pregnancy (73±18 ms) and than in the normal subjects (34±12 ms) (P<0.001). Moreover we have found in GDM patients shorter QRS complex 82.0±6.8 ms vs. 89.5±8.2 ms in healthy pregnant women and 90.8±7.9 ms in the control group (p=0.011), more horizontal electrical heart axis [16.4±20.1° vs. 42.4±28.7° and 74.6±39.2° respectively (P<0.05)] and lower some depolarization and repolarization amplitudes on isopotential and isointegral maps. According to these results we suppose that described electrocardiographic changes reflect a deterioration of the complete process of ventricular depolarization and repolarization in GDM., E. Medová, ... [et al.]., and Obsahuje seznam literatury
The aim of the study was to detect changes of both the QT dispersion and T-loop morphology resulting from the changed spatial position of the heart during pregnancy. Electrocardiographic and vectorcardiographic recordings were obtained from 37 healthy women 19-36 years old in the 36th to 40th week of physiological pregnancy and 2 to 6 days after delivery. The same recordings were obtained from 18 healthy women of the same age. The average QT dispersion (±S.D.) in normal subjects was significantly lower (34±12 ms) than in those in late pregnancy (73±18 ms) (P<0.001). The average amplitude of T-loop (Ta) in women in late pregnancy was significantly (P<0.001) smaller (532±98 mV) and the width of T-loop (Tw) was wider (21.24±11.48 deg) than in the control group (793±114 mV and 7.17±3.02 deg, respectively). The partial post-partum restoration of all parameters was not significant. In all groups, the QT dispersion was significantly correlated with Tw but not with Ta. According to these results we can conclude that the QT dispersion is an indirect reflection of the complete process of ventricular repolarization, reflected in the morphology of the T-loop., M. Lechmanová, O. Kittnar, M. Mlček, J. Slavíček, A. Dohnalová, Š. Havránek, J. Kolařík, A. Pařízek., and Obsahuje bibliografii
Riziko náhlé srdeční smrti u pacientů po infarktu myokardu je zvýšeno v přítomnosti abnormalit komorové repolarizace. Cílem studie je hodnocení QT dynamicity ? vztahu QT/RR ? u pacientů po infarktu myokardu a její přínos k rizikové stratifikaci náhlé srdeční smrti. Metody: Soubor tvořili pacienti s diagnózou akutního infarktu, kterým byl 48?72 hod po infarktu myokardu proveden dlouhodobý EKG záznam (MARS Unity Workstation, GE Medical Information Technologies). Vyřazovacími kritérii byla oběhová nestabilita, umělá plicní ventilace, blokáda levého raménka Tawarova, fibrilace síní, stimulovaný rytmus. Analýza QT dynamicity byla prováděna softwarem QT Guard (GE Medical Information Technologies). Závislost QT/RR je vyjádřena lineární regresí jako rovnice přímky QT = aRR + b. Parametr ?a? je označován jako ?slope? (strmost). Výsledky: Holterovský záznam s hodnotitelnou QT dynamicitou byl získán od 215 pacientů. V průběhu 6měsíčního sledování 2 pacienti zemřeli a další byl úspěšně resuscitován pro primární fibrilaci komor. Půlroční mortalita resp. mortalita + resuscitace byla 0,9 %, resp. 1,4 %. Statistické vyhodnocení tedy není možné. Hodnoty parametru ?slope? byly u 3 uvedených jedinců 0,333, 0,249 a 0,342. Závěry: Vzhledem k nízké mortalitě moderně léčených pacientů po infarktu myokardu nelze ve střednědobém sledování zhodnotit přínos QT dynamicity pro rizikovou stratifikaci. Limitací metody je nutnost značné selekce pacientů vhodných k provedení analýzy a závislost na odpovídající přístrojové technice., Tomáš Novotný, M. Šišáková, A. Floriánová, and Lit. 17
Post-editing and MQM annotations produced by the QT21 project. As described in
@InProceedings{specia-etal_MTSummit:2017,
author = {Specia, Lucia and Kim Harris and Frédéric Blain and Aljoscha Burchardt and Viviven Macketanz and Inguna Skadiņa and Matteo Negri and and Marco Turchi},
title = {Translation Quality and Productivity: A Study on Rich Morphology Languages},
booktitle = {Proceedings of Machine Translation Summit XVI},
year = {2017},
pages = {55--71},
address = {Nagoya, Japan},
}
This corpora is part of Deliverable 5.5 of the European Commission project QTLeap FP7-ICT-2013.4.1-610516 (http://qtleap.eu).
The texts are Q&A interactions from the real-user scenario (batches 1 and 2). The interactions in this corpus are available in Basque, Bulgarian, Czech, English, Portuguese and Spanish.
The texts have been automatically annotated with NLP tools, including Word Sense Disambiguation, Named Entity Disambiguation and Coreference resolution. Please check deliverable D5.6 in http://qtleap.eu/deliverables for more information.
We discuss the representability almost everywhere (a.e.) in C of an irreducible algebraic function as the Cauchy transform of a signed measure supported on a finite number of compact semi-analytic curves and a finite number of isolated points. This brings us to the study of trajectories of the particular family of quadratic differentials A(z − a)(z − b)×(z − c)−2 dz2. More precisely, we give a necessary and sufficient condition on the complex numbers a and b for these quadratic differentials to have finite critical trajectories. We also discuss all possible configurations of critical graphs., Mohamed Jalel Atia, Faouzi Thabet., and Obsahuje seznam literatury