Search

Preparation of high-quality datasets for the urban scene understanding is a labor-intensive task, especially, for datasets designed for the autonomous driving applications. The application of the coarse ground truth (GT) annotations of these datasets without detriment to the accuracy of semantic image segmentation (by the mean intersection over union - mIoU) could simplify and speedup the dataset preparation and model fine tuning before its practical application. Here the results of the comparative analysis for semantic segmentation accuracy obtained by PSPNet deep learning architecture are presented for fine and coarse annotated images from Cityscapes dataset. Two scenarios were investigated: scenario 1 - the fine GT images for training and prediction, and scenario 2 - the fine GT images for training and the coarse GT images for prediction. The obtained results demonstrated that for the most important classes the mean accuracy values of semantic image segmentation for coarse GT annotations are higher than for the fine GT ones, and the standard deviation values are vice versa. It means that for some applications some unimportant classes can be excluded and the model can be tuned further for some classes and specific regions on the coarse GT dataset without loss of the accuracy even. Moreover, this opens the perspectives to use deep neural networks for the preparation of such coarse GT datasets., Comment: 10 pages, 6 figures, 2 tables, The Second International Conference on Computer Science, Engineering and Education Applications (ICCSEEA2019) 26-27 January 2019, Kiev, Ukraine

Several statistical and machine learning methods are proposed to estimate the type and intensity of physical load and accumulated fatigue . They are based on the statistical analysis of accumulated and moving window data subsets with construction of a kurtosis-skewness diagram. This approach was applied to the data gathered by the wearable heart monitor for various types and levels of physical activities, and for people with various physical conditions. The different levels of physical activities, loads, and fitness can be distinguished from the kurtosis-skewness diagram, and their evolution can be monitored. Several metrics for estimation of the instant effect and accumulated effect (physical fatigue) of physical loads were proposed. The data and results presented allow to extend application of these methods for modeling and characterization of complex human activity patterns, for example, to estimate the actual and accumulated physical load and fatigue, model the potential dangerous development, and give cautions and advice in real time., Comment: 15 pages, 8 figures, accepted for 18th International Conference on Algorithms and Architectures for Parallel Processing (ICA3PP) 15-17 November, 2018 (Guangzhou, China)

The new method is proposed to monitor the level of current physical load and accumulated fatigue by several objective and subjective characteristics. It was applied to the dataset targeted to estimate the physical load and fatigue by several statistical and machine learning methods. The data from peripheral sensors (accelerometer, GPS, gyroscope, magnetometer) and brain-computing interface (electroencephalography) were collected, integrated, and analyzed by several statistical and machine learning methods (moment analysis, cluster analysis, principal component analysis, etc.). The hypothesis 1 was presented and proved that physical activity can be classified not only by objective parameters, but by subjective parameters also. The hypothesis 2 (experienced physical load and subsequent restoration as fatigue level can be estimated quantitatively and distinctive patterns can be recognized) was presented and some ways to prove it were demonstrated. Several "physical load" and "fatigue" metrics were proposed. The results presented allow to extend application of the machine learning methods for characterization of complex human activity patterns (for example, to estimate their actual physical load and fatigue, and give cautions and advice)., Comment: 12 pages, 10 figures, 1 table; presented at XXIX IUPAP Conference in Computational Physics (CCP2017) July 9-13, 2017, Paris, University Pierre et Marie Curie - Sorbonne (https://ccp2017.sciencesconf.org/program)

Machine learning techniques are presented for automatic recognition of the historical letters (XI-XVIII centuries) carved on the stoned walls of St.Sophia cathedral in Kyiv (Ukraine). A new image dataset of these carved Glagolitic and Cyrillic letters (CGCL) was assembled and pre-processed for recognition and prediction by machine learning methods. The dataset consists of more than 4000 images for 34 types of letters. The explanatory data analysis of CGCL and notMNIST datasets shown that the carved letters can hardly be differentiated by dimensionality reduction methods, for example, by t-distributed stochastic neighbor embedding (tSNE) due to the worse letter representation by stone carving in comparison to hand writing. The multinomial logistic regression (MLR) and a 2D convolutional neural network (CNN) models were applied. The MLR model demonstrated the area under curve (AUC) values for receiver operating characteristic (ROC) are not lower than 0.92 and 0.60 for notMNIST and CGCL, respectively. The CNN model gave AUC values close to 0.99 for both notMNIST and CGCL (despite the much smaller size and quality of CGCL in comparison to notMNIST) under condition of the high lossy data augmentation. CGCL dataset was published to be available for the data science community as an open source resource., Comment: 11 pages, 9 figures, accepted for 25th International Conference on Neural Information Processing (ICONIP 2018), 14-16 December, 2018 (Siem Reap, Cambodia)

The current tendency of human learning and teaching is targeted to development and integration of digital technologies (like cloud solutions, mobile technology, learning analytics, big data, augmented reality, natural interaction technologies, etc.). Our Science Gateway (http://scigate.imp.kiev.ua) in collaboration with High Performance Computing Center (http://hpcc.kpi.ua) is aimed on the close cooperation among the main actors in learning and researching world (teachers, students, scientists, supporting personnel, volunteers, etc.) with industry and academia to propose the new frameworks and interoperability requirements for the building blocks of a digital ecosystem for learning (including informal learning) that develops and integrates the current and new tools and systems. It is the portal for management of distributed courses (workflows), tools, resources, and users, which is constructed on the basis of the Liferay framework and gUSE/WS-PGRADE technology. It is based on development of multi-level approach (as to methods/algorithms) for effective study and research through flexible selection and combination of unified modules ("gaming" with modules as with LEGO-bricks). It allows us to provide the flexible and adjustable framework with direct involvement in real-world and scientific use cases motivated by the educational aims of students and real scientific aims in labs., Comment: 6 pages, 4 figures, 2 tables. 38th International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO 2015); Distributed Computing, Visualization and Biomedical Engineering (DC VIS) May 25-29, 2015 (Opatija, Croatia)

The "IMP Science Gateway Portal" (http://scigate.imp.kiev.ua) for complex workflow management and integration of distributed computing resources (like clusters, service grids, desktop grids, clouds) is presented. It is created on the basis of WS-PGRADE and gUSE technologies, where WS-PGRADE is designed for science workflow operation and gUSE - for smooth integration of available resources for parallel and distributed computing in various heterogeneous distributed computing infrastructures (DCI). The typical scientific workflow with possible scenarios of its preparation and usage is considered. Several typical science applications (scientific workflows) are considered for molecular dynamics (MD) simulations of complex behavior of various nanostructures (nanoindentation of graphene layers, defect system relaxation in metal nanocrystals, thermal stability of boron nitride nanotubes, etc.). The advantages and drawbacks of the solution are shortly analyzed in the context of its practical applications for MD simulations in materials science, physics and nanotechnologies with available heterogeneous DCIs., Comment: 8 pages, 8 figures; Proc. of Third International Conference "High Performance Computing" HPC-UA 2013 (Ukraine, Kyiv, October 7-11, 2013) (http://hpc-ua.org/hpc-ua-13/proceedings). ISBN 978-966-7690-16-8 (2013)