Martin Sramka

Martin Sramka

Auto-generated profile, based on publicly available information

Martin Sramka

Czech Technical University in Prague, Faculty of Electrical Engineering, Technicka 2, 166 27 Prague 6, Czech Republic

Research Focus & Metrics

Academic Career Length

17Years (2010-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
2 July 2019 in PeerJ
Verified
Journal Article
Open access
PDF file
MSMartin Sramka
Martin Sramka
MSMartin Slovak
Martin Slovak
JTJana Tuckova
Jana Tuckova
PSPavel Stodulka
Pavel Stodulka
Aim: To evaluate the potential of the Support Vector Machine Regression model (SVM-RM) and Multilayer Neural Network Ensemble model (MLNN-EM) to improve the intraocular lens (IOL) power calculation for clinical workflow. Background: Current IOL power calculation methods are limited in their accuracy with the possibility of decreased accuracy especially in eyes with an unusual ocular dimension. In case of an improperly calculated power of the IOL in cataract or refractive lens replacement surgery there is a risk of re-operation or further refractive correction. This may create potential complications and discomfort for the patient. Methods: A dataset containing information about 2,194 eyes was obtained using data mining process from the Electronic Health Record (EHR) system database of the Gemini Eye Clinic. The dataset was optimized and split into the selection set (used in the design for models and training), and the verification set (used in the evaluation). The set of mean prediction errors (PEs) and the distribution of predicted refractive errors were evaluated for both models and clinical results (CR). Results: Both models performed significantly better for the majority of the evaluated parameters compared with the CR. There was no significant difference between both evaluated models. In the ±0.50 D PE category both SVM-RM and MLNN-EM were slightly better than the Barrett Universal II formula, which is often presented as the most accurate calculation formula. Conclusion: In comparison to the current clinical method, both SVM-RM and MLNN-EM have achieved significantly better results in IOL calculations and therefore have a strong potential to improve clinical cataract refractive outcomes.

1 January 2020 in Journal of Cataract & Refractive Surgery
Verified
Journal Article
Closed access
PSPavol Stodulka
Pavol Stodulka
MSMartin Me Sramka
Martin Me Sramka
JPJaroslav Polisensky
Jaroslav Polisensky
KLKarel Msc Liska
Karel Msc Liska
Purpose: To report the initial experience with a new presbyopic phakic intraocular lens (pIOL) in the correction of high myopia and presbyopia. Setting: Gemini Eye Clinic, Zlin, Czech Republic. Design: Prospective cohort study. Methods: Presbyopic eyes with moderate to high myopia were implanted with a presbyopic posterior chamber pIOL (IPCL). The visual acuities at near and distance, endothelial cell density, and ocular condition were examined 1 week, 3 months, 1 year and 2 years postoperatively. Results: The mean uncorrected distance visual acuity improved significantly from 1.25 logarithm of the minimum angle of resolution (logMAR) (1.15 to 1.35 95% confidence interval [CI]) to 0.11 logMAR (95% CI, 0.03 to 0.17) (P < .0001). No eye lost 1 or more lines of corrected distance visual acuity. The mean distance refraction improved significantly from −6.9 diopters (D) (range −8.6 to −5.3 D) preoperatively to −0.35 D (range −0.55 to −0.15 D, P < .0001) with less than −0.5 D residual refraction in 11 of 17 eyes. Fifteen of 17 eyes had improved uncorrected near visual acuity to J1 (Jaeger chart) at the 2-year follow-up. The near addition at the 2-year follow-up decreased from preoperatively +1.26 D (range 0.19 to 2.34 D) to +0.39 D (range 0.18 to 0.60 D). The mean endothelial cell density was reduced from 2552 cells/mm2 (range 2421 to 2682 cells/mm2) to 2299 cells/mm2 (range 2108 to 2490 cells/mm2) after 2 years. All patients were subjectively satisfied with the outcomes. Conclusions: The new pIOL provided good visual outcomes in near and far distances in an initial case series of patients.

1 January 2012 in International Journal of Data Analysis Techniques and Strategies
Verified
Journal Article
Closed access
JTJana Tuckova
Jana Tuckova
MSMartin Sramka
Martin Sramka
In the present text, we deal with the problem of classification of speech emotion. Problems of speech processing are addressed through the use of artificial neural networks (ANNs). The results can be used for two research projects - for prosody modelling and for analysis of disordered speech. The first ANN topology discussed is the multilayer neural network (MLNN) with the BPG learning algorithm, while the supervised SOM (SSOM) is the second ANN topology. Our aim is to combine knowledges from phonetics and ANN but also to try to classify speech signals which are described by music theory. Finally, one solution is given for this problem which is supplemented with a proof.

19 December 2018
Verified
Conference Paper
Closed access
PDF file
MSMartin Sramka
Martin Sramka
AVAlzbeta Vlachynska
Alzbeta Vlachynska
Here is information on how to publish, spread your research, and search for your publications. Most of LiU's research publications are directly imported into DiVA from the Web of Science. Before registering a publication, always check if the publication is already in DiVA!

1 January 2017 in AIP Conference Proceedings
Verified
Conference Paper
Closed access
AVAlzbeta Vlachynska
Alzbeta Vlachynska
ZOZuzana Komínková Oplatková
Zuzana Komínková Oplatková
MSMartin Sramka
Martin Sramka
The aim of the work is to determine the coordinate system of an eye and insert a polar-axis system into images captured by a slip lamp. The image of the eye with the polar axis helps a surgeon accurately implant toric intraocular lens in the required position/rotation during the cataract surgery. In this paper, two common algorithms for pupil detection are compared: the circle Hough transform and Daugman's algorithm. The procedures were tested and analysed on the anonymous data set of 128 eyes captured at Gemini eye clinic in 2015. © 2017 Author(s).Ministry of Education, Youth and Sports of the Czech Republic within the National Sustainability Programme [LO1303 (MSMT-7778/2014)]; European Regional Development Fund under CEBIA-Tech [CZ.1.05/2.1.00/03.0089]; Grant Agency of the Czech Republic-GACR [588 P103/15/06700S]; Internal Grant Agency of Tomas Bata University in Zlin [IGA/CebiaTech/2016/007

1 October 2010
Verified
Conference Paper
Closed access
JTJana Tuckova
Jana Tuckova
MSMartin Sramka
Martin Sramka
In the present text, we deal with the problem of classification of speech emotion. Problems of speech processing are addressed through the use of artificial neural networks (ANN). The results can be use for two research projects - for prosody modelling and for analysis of disordered speech. The first ANN topology discussed is the multilayer neural network (MLNN) with the BPG learning algorithm, while the supervised SOM (SSOM) are the second ANN topology. Our aim is to verify the various of knowledge from phonetics and ANN but also to try to classify speech signals which are described by musical theory. Finally, one solution is given for this problem which is supplemented with a proof.