All issues

The reconstruction of charged particle trajectories in tracking detectors is a key problem in the analysis of experimental data for high energy and nuclear physics.

The amount of data in modern experiments is so large that classical tracking methods such as Kalman filter can not process them fast enough. To solve this problem, we have developed two neural network algorithms of track recognition, based on deep learning architectures, for local (track by track) and global (all tracks in an event) tracking in the GEM tracker of the BM@N experiment at JINR (Dubna). The advantage of deep neural networks is the ability to detect hidden nonlinear dependencies in data and the capability of parallel execution of underlying linear algebra operations.

In this work we generalize these algorithms to the cylindrical GEM inner tracker of BESIII experiment. The neural network model RDGraphNet for global track finding, based on the reverse directed graph, has been successfully adapted. After training on Monte Carlo data, testing showed encouraging results: recall of 98% and precision of 86% for track finding.

The local neural network model TrackNETv2 was also adapted to BESIII CGEM successfully. Since the tracker has only three detecting layers, an additional neuro-classifier to filter out false tracks have been introduced. Preliminary tests demonstrated the recall value at the first stage of 99%. After applying the neuro-classifier, the precision was 77% with a slight decrease of the recall to 94%. This result can be improved after the further model optimization.

We suggested some approaches for solving image processing tasks in the decision support system (DSS) of the Center for Automated Recording of Administrative Offenses of the Road Traffic (CARAO). The main task of this system is to assist the operator in obtaining accurate information about the vehicle registration plate and the vehicle brand/model based on images obtained from the photo and video recording systems. We suggested the approach for vehicle registration plate recognition and brand/model classification on the images based on modern neural network models. LPRNet neural network model supplemented by Spatial Transformer Layer was used to recognize the vehicle registration plate. The ResNeXt-101-32x8d neural network model was used to classify for vehicle brand/model. We suggested the approach to construct the training set for the neural network of vehicle registration plate recognition. The approach is based on computer vision methods and machine learning algorithms. The SIFT algorithm was used to detect and describe local features on images with the vehicle registration plate. DBSCAN clustering was used to detect and delete outliers in such local features. The accuracy of vehicle registration plate recognition was 96% on the testing set. We suggested the approach to improve the efficiency of using the ResNeXt-101-32x8d model at additional training and classification stages. The approach is based on the new architecture of convolutional neural networks with “freezing” weight coefficients of convolutional layers, an additional convolutional layer for parallelizing the classification process, and a set of binary classifiers at the output. This approach significantly reduced the time of additional training of neural network when new vehicle brand/model classification was needed. The final accuracy of vehicle brand/model classification was 99% on the testing set. The proposed approaches were tested and implemented in the DSS of the CARAO of the Republic of Tatarstan.

The numerical methods used to simulate the evolution of hydrodynamic systems require the considerable use of computational resources thus limiting the number of possible simulations. The data-driven simulation technique is one promising approach to the development of heuristic models, which may speed up the study of such models. In this approach, machine learning methods are used to tune the weights of an artificial neural network that predicts the state of a physical system at a given point in time based on initial conditions. This article describes an original neural network architecture and a novel multi-stage training procedure which create a heuristic model of a two-phase flow in a heterogeneous porous medium. The neural network-based model predicts the states of the grid cells at an arbitrary timestep (within the known constraints), taking in only the initial conditions: the properties of the heterogeneous permeability of the medium and the location of sources and sinks. The proposed model requires orders of magnitude less processor time in comparison with the classical numerical method, which served as a criterion for evaluating the effectiveness of the trained model. The proposed architecture includes a number of subnets trained in various combinations on several datasets. The techniques of adversarial training and weight transfer are utilized.

When modeling turbulent flows in practical applications, it is often necessary to carry out a series of calculations of bodies of similar topology. For example, bodies that differ in the shape of the fairing. The use of convolutional neural networks allows to reduce the number of calculations in a series, restoring some of them based on calculations already performed. The paper proposes a method that allows to apply a convolutional neural network regardless of the method of constructing a computational mesh. To do this, the flow field is reinterpolated to a uniform mesh along with the body itself. The geometry of the body is set using the signed distance function and masking. The restoration of the flow field based on part of the calculations for similar geometries is carried out using a neural network of the UNet type with a spatial attention mechanism. The resolution of the nearwall region, which is a critical condition for turbulent modeling, is based on the equations obtained in the nearwall domain decomposition method.

A demonstration of the method is given for the case of a flow around a rounded plate by a turbulent air flow with different rounding at fixed parameters of the incoming flow with the Reynolds number $Re = 10^5$ and the Mach number $M = 0.15$. Since flows with such parameters of the incoming flow can be considered incompressible, only the velocity components are studied directly. The flow fields, velocity and friction profiles obtained by the surrogate model and numerically are compared. The analysis is carried out both on the plate and on the rounding. The simulation results confirm the prospects of the proposed approach. In particular, it was shown that even if the model is used at the maximum permissible limits of its applicability, friction can be obtained with an accuracy of up to 90%. The work also analyzes the constructed architecture of the neural network. The obtained surrogate model is compared with alternative models based on a variational autoencoder or the principal component analysis using radial basis functions. Based on this comparison, the advantages of the proposed method are demonstrated.

A hybrid cluster implies the use of computational devices with radically different architectures. Usually, these are conventional CPU architecture (e.g. x86_64) and GPU architecture (e. g. NVIDIA CUDA). Creating and exploiting such a cluster requires some experience: in order to harness all computational power of the described system and get substantial speedup for computational tasks many factors should be taken into account. These factors consist of hardware characteristics (e.g. network infrastructure, a type of data storage, GPU architecture) as well as software stack (e.g. MPI implementation, GPGPU libraries). So, in order to run scientific applications GPU capabilities, software features, task size and other factors should be considered.

This report discusses opportunities and problems of hybrid computations. Some statistics from tests programs and applications runs will be demonstrated. The main focus of interest is open source applications (e. g. OpenFOAM) that support GPGPU (with some parts rewritten to use GPGPU directly or by replacing libraries).

There are several approaches to organize heterogeneous computations for different GPU architectures out of which CUDA library and OpenCL framework are compared. CUDA library is becoming quite typical for hybrid systems with NVIDIA cards, but OpenCL offers portability opportunities which can be a determinant factor when choosing framework for development. We also put emphasis on multi-GPU systems that are often used to build hybrid clusters. Calculations were performed on a hybrid cluster of SPbU computing center.

One of the important direction of cloud technologies development nowadays is a creation of methods for integration of various cloud infrastructures. An actuality of such direction in academic field is caused by a frequent lack of own computing resources and a necessity to attract additional ones. This article is dedicated to existing approaches to cloud infrastructures integration with each other: federations and so called ‘cloud bursting’. A ‘federation’ in terms of OpenNebula cloud platform is built on a ‘one master zone and several slave ones’ schema. A term ‘zone’ means a separate cloud infrastructure in the federation. All zones in such kind of integration have a common database of users and the whole federation is managed via master zone only. Such approach is most suitable for a case when cloud infrastructures of geographically distributed branches of a single organization need to be integrated. But due to its high centralization it's not appropriate when one needs to join cloud infrastructures of different organizations. Moreover it's not acceptable at all in case of clouds based on different software platforms. A model of federative integration implemented in EGI Federated Cloud allows to connect clouds based on different software platforms but it requires a deployment of sufficient amount of additional services which are specific for EGI Federated Cloud only. It makes such approach is one-purpose and uncommon one. A ‘cloud bursting’ model has no limitations listed above but in case of OpenNebula platform what the Laboratory of Information Technologies of Joint Institute for Nuclear Research (LIT JINR) cloud infrastructure is based on such model was implemented for an integration with a certain set of commercial cloud resources providers. Taking into account an article authors’ experience in joining clouds of organizations they represent as well as with EGI Federation Cloud a ‘cloud bursting’ driver was developed by LIT JINR cloud team for OpenNebula-based clouds integration with each other as well as with OpenStack-based ones. The driver's architecture, technologies and protocols it relies on and an experience of its usage are described in the article.

This article considers the task of multiclass classification of coniferous trees with varying degrees of damage by insect pests on images obtained using unmanned aerial vehicles (UAVs). We propose the use of convolutional neural networks (CNNs) for the classification of fir trees Abies sibirica and Siberian pine trees Pinus sibirica in unmanned aerial vehicles (UAV) imagery. In our approach, we develop three CNN models based on the classical U-Net architecture, designed for pixel-wise classification of images (semantic segmentation). The first model, Mo-U-Net, incorporates several changes to the classical U-Net model. The second and third models, MSC-U-Net and MSC-Res-U-Net, respectively, form ensembles of three Mo-U-Net models, each varying in depth and input image sizes. Additionally, the MSC-Res-U-Net model includes the integration of residual blocks. To validate our approach, we have created two datasets of UAV images depicting trees affected by pests, specifically Abies sibirica and Pinus sibirica, and trained the proposed three CNN models utilizing mIoULoss and Focal Loss as loss functions. Subsequent evaluation focused on the effectiveness of each trained model in classifying damaged trees. The results obtained indicate that when mIoULoss served as the loss function, the proposed models fell short of practical applicability in the forestry industry, failing to achieve classification accuracy above the threshold value of 0.5 for individual classes of both tree species according to the IoU metric. However, under Focal Loss, the MSC-Res-U-Net and Mo-U-Net models, in contrast to the third proposed model MSC-U-Net, exhibited high classification accuracy (surpassing the threshold value of 0.5) for all classes of Abies sibirica and Pinus sibirica trees. Thus, these results underscore the practical significance of the MSC-Res-U-Net and Mo-U-Net models for forestry professionals, enabling accurate classification and early detection of pest outbreaks in coniferous trees.

Storage is the essential and expensive part of cloud computation both from the point of view of network requirements and data access organization. So the choice of storage architecture can be crucial for any application. In this article we can look at the types of cloud architectures for data processing and data storage based on the proven technology of enterprise storage. The advantage of cloud computing is the ability to virtualize and share resources among different applications for better server utilization. We are discussing and evaluating distributed data processing, database architectures for cloud computing and database query in the local network and for real time conditions.

Methods for modeling blood flow and its rheological properties are reviewed. Blood is considered as a particle suspencion. The methods are boundary integral equation method (BIEM), lattice Boltzmann (LBM), finite elements on dynamic mesh, dissipative particle dynamics (DPD) and agent based modeling. The analysis of these methods’ applications on high-performance systems with various architectures is presented.

Although each task of recreating artifacts is truly unique, the modeling process for façades, foundations and building elements can be parametrized. This paper is focused on a complex of the existing programming libraries and solutions that need to be united into a single computer system to solve such a task. An algorithm of generating 3D filling of objects under reconstruction is presented. The solution architecture necessary for the system's adaptation for a cloud environment is studied.