The topical question studied in this paper is how many receptive fields (filters) a convolutional layer of a convolutional neural network should have. The goal is to find a rule for choosing the most appropriate numbers of filters. The benchmark datasets are principally diverse CIFAR-10 and EEACL26 to use a common network architecture with three convolutional layers whose numbers of filters are changeable. Heterogeneity and sensitiveness of CIFAR-10 with infiniteness and scalability of EEACL26 are believed to be relevant enough for generalization and spreading of the appropriateness of filter numbers. The appropriateness rule is drawn from top accuracies obtained on 10 × 20 × 21 parallelepipeds for three image sizes. They show, knowing that the number of filters of the first convolutional layer should be set greater for the more complex dataset, the rest of appropriate numbers of filters are set at integers, which are multiples of that number. The multipliers make a sequence similar to a progression, e.g., it may be 1, 3, 9, 15 or 1, 2, 8, 16, etc. With only those multipliers, such a rule-of-progression does not give the number of filters for the first convolutional layer.
Petra Roupcová, Karel Klouda, Markéta Weisheitelová and Bohdan Filipi
By reducing potassium permanganate using various methods (microwave radiation, HCl, ethanol, ascorbic acid) in a biochar environment, we have prepared composites of manganese oxides and biochar as an electrode material for elements or supercapacitors. Once identified, the prepared products were tested for thermal stability and phytotoxicity as a safety parameter in case they get in contact with the natural environment. The publication had also discussed progression of thermal decomposition of the composite. The process was exo-thermal with mutual oxidation-reduction reaction between the manganese oxides and biochar carbon. In the article there are also described the adsorption capabilities of prepared products. The manganese oxide content had also influenced the phytotoxicity test results. The biochar itself had stimulating effects on all tested seeds, while composites had shown both stimulating and inhibiting effects, depending on the kind of tested seeds.
Understanding gait parameters of patients with limited mobility help specialists monitor, predict, and even control the progression of patient specific pathologies. Accurately determining gait parameters such as joint range of motion (ROM) often involves expensive equipment that typically requires a clinical setting and specially trained personnel. Added to this limitation is the psychological effects of patients that are required to perform in a clinical setting, which may not always reflect their actual day to day gait. The presented article implements accelerometers and gyroscopes, also known as inertial measuring units (IMU), mounted at key anatomical locations of the lower limbs to determine knee ROM. Measurements were performed in tandem with optical motion capture (OMC) which is considered the gold standard for gait analysis. The results show that IMU’s have comparable accuracy to OMC measurements providing an economical alternative to expensive clinical gait analysis that is not restricted to a clinical setting.
Mehmet Atlar, Kwangcheol Seo, Roderick Sampson and Devrim Bulent Danisman
While displacement type Deep-V mono hulls have superior seakeeping behaviour at speed, catamarans typically have modest behaviour in rough seas. It is therefore a logical progression to combine the superior seakeeping performance of a displacement type Deep-V mono-hull with the high-speed benefits of a catamaran to take the advantages of both hull forms. The displacement Deep-V catamaran concept was developed in Newcastle University and Newcastle University’s own multi-purpose research vessel, which was launched in 2011, pushed the design envelope still further with the successful adoption of a novel anti-slamming bulbous bow and tunnel stern for improved efficiency. This paper presents the hullform development of this unique vessel to understand the contribution of the novel bow and stern features on the performance of the Deep-V catamaran. The study is also a further validation of the hull resistance by using advanced numerical analysis methods in conjunction with the model test. An assessment of the numerical predictions of the hull resistance is also made against physical model test results and shows a good agreement between them.
This research has been inspired by security concerns due to the recent increase in the terrorist threat to gas and crude oil transportation around the world, especially in regions that are of significant value for the energy supplies. Computational mechanics methods will be used in this research to apply shock wave analysis for possible damage assessment of the affected pipelines. These methods may be also used for pipelines at power plants, which are usually placed high on the homeland security priority list. This study is primarily focused on the behaviour of some type of pipeline elements existing in gas pipeline system which can be subjected to the shock wave produced by the detonation of highly explosive (HE) materials. In this kind of studies the numerical coupling procedure describing interaction between gas and solid domain was implemented. Outcomes of this research are very important in preventing damage progression of pipelines under the blast loading.
Tomáš Petřík, Eva Hrubešová, Martin Stolárik and Miroslav Pinka
 ČAJKA, R., KŘIVÝ, V. a SEKANINA, D. Design and Development of a Testing Device for Experimental Measurements of Foundation Slabs on the Subsoil. Transactions of the VŠB -Technical University of Ostrava: Construction Series, No.1, 2011, Vol. XI, DOI: 10.2478/v10160-01 1-0002-2. Publisher Versita, Warsaw, ISSN 1213-1962 (Print) 1804-4824 (Online).
 KREJSA, M. PROBABILISTIC CALCULATION OF FATIGUE CRACK PROGRESSION USING FCPROBCALC CODE. Transactions of the VŠB - Technical University of Ostrava
, Cesar. (2001). Transport Sector Restructuring in the Baltic States. In Proceedings of a Seminar held in Riga on November 16-17, 2000. Turku, Finland: Turku School of Economics and World Bank.
29. Laisi, Milla & Poikolainen, Tiina. (2011). Progression of the Deregulation in the North European Railway Passenger Markets - Building Insights via Customer Satisfaction Survey and Expert Interviews , 15/2011. Helsinki, Finland: Finnish Transport Agency.
30. Terk, Erik, Tapaninen, Ulla, Hilmola, Olli-Pekka & Hunt, Tonis. (2007). Oil Transit in
Henryk Borowczyk, Józef Błachnio and Jarosław Spychała
 Abbas, M. and G.J. Vachtsevanos. A system-level approach to fault progression analysis in complex engineering systems . in Annual Conference of the Prognostics and Health Management Society, PHM 2009 . 2009.
 Bano, N., A. Fahim, and M. Nganbe. Fatigue crack initiation life prediction of IN738 using artificial neural network . 2010.
 Blachnio, J. and M. Bogdan, A non-destructive method to assess condition of gas turbine blades, based on the analysis of blade-surface images. Russian Journal of Nondestructive Testing
Science and Technology, 25, 183-196.
Boehrer, B., Tibke, M., Suhr, U., 2004. Frontal progression of a juxtaposed ice cover on the Elbe river. Journal of Hydrology, 288, 258-263, doi: 10.1016/j.jhydrol.2003.10.009.
Cyberski, J., Grześ, M., Gutry-Korycka, M., Nachlik, E., Kundzewicz, Z.W., 2006. History of floods on the River Vistula. Hydrological Sciences Journal, 51:5, 799-817, doi: 10.1623/hysj.51.5.799.
Gołek, J., 1964. Ice phenomena on the Polish rivers. Works of State Hydrological-Meteorological Institute, 63. (In