Milos Ivanovic

• PhD
• Professor (Associate) at University of Kragujevac

This study employs a novel physics-informed neural network (PINN) approach, the standard explicit finite difference method (EFDM) and unconditionally positivity preserving FDM to tackle the one-dimensional Sine-Gordon equation (SGE). Two test problems with known analytical solutions are investigated to demonstrate the effectiveness of these techniq...

This study employs a novel physics-informed neural networks (PINN) approach, standard explicit finite difference method (EFDM) and Chen-Charpentier et al.’s finite difference method (CCFDM) to tackle the one-dimensional Sine-Gordon equation (SGE). Two test problems with known analytical solutions are investigated to demonstrate the effectiveness of...

The paper presents the GeNNsem (Genetic algorithm ANNs ensemble) software framework for the simultaneous optimization of individual neural networks and building their optimal ensemble. The proposed framework employs a genetic algorithm to search for suitable architectures and hyperparameters of the individual neural networks to maximize the weighte...

We employed a novel physics-informed neural networks (PINN) to tackle (1+1) dimensional Sine-Gordon equation (SGE). A test problem with known analytical solution is numerically solved to demonstrate the effectiveness of the PINN, and compared to standard explicit finite difference method (EFDM) and Chen-Charpentier et al.’s finite difference method...

We investigate oxygen diffusion in the soil in one dimension by the finite difference method and the physics-informed neural network. Solving the diffusion equation by either method determines the oxygen concentration profiles inside the soil column at various times. However, while respecting specified Dirichlet and Neumann boundary conditions, the...

The diffusion of oxygen in the soil in one dimension is investigated by the finite difference method and the physics-informed neural network. By solving the diffusion equation by either method, the concentration profiles of the oxygen inside the soil column are determined at various times. However, while respecting specified Dirichlet and Neumann b...

There is a need to develop an integrated computational platform that will contain both datasets and multiscale models related to bone (modelling), cancer, cardiovascular diseases, and tissue engineering. The SGABU platform is a robust information system capable of data integration, information extraction, and knowledge exchange, with the goal of de...

When simulating various physical phenomena, the law of the phenomenon is often known in advance, in the form of a partial differential equation, that needs to be solved. Numerical methods, such as the finite element method, have been developed over decades, and these methods approximate the solution to the partial differential equation. However, th...

The Burgers' equation is solved using the explicit finite difference method (EFDM) and physics-informed neural networks (PINN). We compare our numerical results, obtained using the EFDM and PINN for three test problems with various initial conditions and Dirichlet boundary conditions, with the analytical solutions, and, while both approaches yield...

Supervised deep learning relies heavily on the existence of a huge amount of labelled data, which in many cases is difficult to obtain. Domain adaptation deals with this problem by learning on a labelled dataset and applying that knowledge to another, unlabelled or scarcely labelled dataset, with a related but different probability distribution. He...

Supervised deep learning requires a huge amount of reference data, which is often difficult and expensive to obtain. Domain adaptation helps with this problem—labelled data from one dataset should help in learning on another unlabelled or scarcely labelled dataset. In remote sensing, where a variety of sensors produce images of different modalities...

Biophysical muscle models, also known as Huxley-type models, are appropriate for simulating non-uniform and unsteady contractions. Large-scale simulations can be more challenging to use because this type of model can be computationally intensive. The method of characteristics is typically used to solve Huxley’s muscle equation, which describes the...

The investigation of the bandwidth in multimode graded-index microstructured polymer optical fiber (GI mPOF) with a solid core is proposed using a modal diffusion approach. For a variety of launch radial offsets of multimode GI mPOF, bandwidth is reported by numerically solving the time-dependent power flow equation (TD PFE) using the explicit fini...

The purpose of the SGABU platform is to include various models and datasets in the area of multiscale modelling. The main aspect of SGABU platform are various datasets and multiscale models related to cancer, cardiovascular, bone and tissue disorders. From the point of view of the dataset integration, a task requires implementation of the user inte...

Solving complex real-world optimization problems is a computationally demanding task. To solve it efficiently and effectively, one must possess expert knowledge in various fields (problem domain knowledge, optimization, parallel and distributed computing) and appropriate expensive software and hardware resources. In this regard, we present a cloud-...

The computational requirements of the Huxley-type muscle models are substantially higher than those of Hill-type models, making large-scale simulations impractical or even impossible to use. We constructed a data-driven surrogate model that operates similarly to the original Huxley muscle model but consumes less computational time and memory to ena...

Clinicians can use biomechanical simulations of cardiac functioning to evaluate various real and fictional events. Our present understanding of the molecular processes behind muscle contraction has inspired Huxley-like muscle models. Huxley-type muscle models, unlike Hill-type muscle models, are capable of modeling non-uniform and unstable contract...

Machine learning methods have been widely and successfully applied in hydrological problems. Most of the methods, such as artificial neural networks, have been focused on estimating hydrological data based on observation over time. Even though these models provide good results, it can be observed that results become unreliable when the training dat...

The aim of this research was to facilitate the application of smoothed particle hydrodynamics (SPH) method to computational fluid dynamics analysis of turbulent flow through complex geometry blood vessels, and to compare it with the state-of-the-art finite element method (FEM). SPH offers the possibility to observe motion of fluid fragment or parti...

SGABU platform was created as a computational platform for multiscale modelling in biomedical engineering. This is one of the few proposed integrated platforms that include different areas of bioengineering. The platform includes already developed solutions, various datasets and models related to cancer, cardiovascular, bone disorders, and tissue e...

Biophysical muscle models, often called Huxley-type models, are based on the underlying physiology of muscles, making them suitable for modeling non-uniform and unsteady contractions. This kind of model can be computationally intensive, which makes the usage of large-scale simulations difficult. To enable more efficient usage of the Huxley muscle m...

In this paper, we present a generic, scalable and adaptive load balancing parallel Lagrangian particle tracking approach in Wiener type processes such as Brownian motion. The approach is particularly suitable in problems involving particles with highly variable computation time, like deposition on boundaries that may include decay, when particle li...

Purposes: The aim of the study was to determine optimal threshold of the Prostate Health Index (Phi) for predicting aggressive prostate cancer (PCa), taking into account misclassification costs, prevalence, and plausible risk factors. Methods: This prospective cohort study analyzed patients undergoing prostate biopsy and Phi testing. The primary...

The cloud computing paradigm has gained wide acceptance in the scientific community, taking a significant share from fields previously reserved exclusively for High Performance Computing (HPC). On-demand access to a large amount of computing resources provided by Cloud makes it ideal for executing large-scale optimizations using evolutionary algori...

Since multi-scale models of muscles rely on the integration of physical and biochemical properties across multiple length and time scales, they are highly processor and memory intensive. Consequently, their practical implementation and usage in real-world applications is limited by high computational requirements. There are various reported solutio...

Purpose The purpose of this paper is to improve the accuracy and stability of the existing solutions to 1D Stefan problem with time-dependent Dirichlet boundary conditions. The accuracy improvement should come with respect to both temperature distribution and moving boundary location. Design/methodology/approach The variable space grid method ba...

We propose a novel method of Mean-Capital Requirement portfolio optimization. The optimization is performed using a parallel framework for optimization based on the Nondominated Sorting Genetic Algorithm II. Capital requirements for market risk include an additional stress component introduced by the recent Basel 2.5 regulation. Our optimization wi...

A computer program for studying proton tracks in solid state nuclear track detectors was developed and described in this paper. The program was written in Fortran 90, with an additional tool for visualizing the track appearance as seen under the optical microscope in the transmission mode, which was written in the Python programming language. Measu...

The rapid growth of student demand for flexible education and learning alternatives has caused a significant increase in web-based programming course offerings. In order to ensure easy and enjoyable ways of acquiring knowledge, many web-based solutions have customized the design and content to student needs. This paper introduces a project of the I...

In previous decades a number of computational methods for calculation of very complex physical phenomena with a satisfactory accuracy have been developed. Most of these methods usually model only a single physical phenomenon, while their performance regarding accuracy and efficiency are limited within narrow spatial and temporal domains. However, s...

One of the main activities within the Group for Scientific Computing at the Faculty of Science are methods for efficiently utilizing real parallel architectures, typically clusters of SMP nodes, shared-memory systems, and GPUs. Focus is on design, development and implementation of parallel algorithms and data structures for fundamental scientific a...

We present Mexie, an extensible and scalable software solution for distributed multi-scale muscle simulations in a hybrid MPI–CUDA environment. Since muscle contraction relies on the integration of physical and biochemical properties across multiple length and time scales, these models are highly processor and memory intensive. Existing paralleliza...

Real-world problems often contain nonlinearities, relationships, and uncertainties that are too complex to be modeled analytically. In these scenarios, simulation-based optimization is a powerful tool to determine optimal system parameters. Evolutionary Algorithms (EAs) are robust and powerful techniques for optimization of complex systems that per...

Most of the existing methods for dam behavior modeling require a persistent set of input parameters. In real-world applications, failures of the measuring equipment can lead to a situation in which a selected model becomes unusable because of the volatility of the independent variables set. This paper presents an adaptive system for dam behavior mo...

Objective Assessment of costs matrix and patterns of prescribing of radiology diagnostic, radiation therapy, nuclear medicine, and interventional radiology services. Another aim of the study was insight into drivers of inappropriate resource allocation. Methods An in-depth, retrospective bottom-up trend analysis of services consumption patterns an...

The ABC index is a degree-based molecular structure descriptor, that found chemical applications. Finding the connected graph(s) of a given order whose ABC index is minimal is a hitherto unsolved problem, but it is known that these must be trees. In this paper, by combining mathematical arguments and computer-based modeling we establish the basic s...

If G = (V, E) is a molecular graph, and d(u) is the degree of its vertex u, then the atom-bond connectivity index of G is Mathamatical equation repersented. This molecular structure descriptor, introduced by Estrada et al. in the late 1990s, found recently interesting applications in the study of the thermodynamic stability of acyclic saturated hyd...

The estimation of chemical kinetic rate constants for any non-trivial model is complex due to the nonlinear effects of second order chemical reactions. To accomplish this goal we have developed an algorithm based on genetic algorithms (GA) and then tested the effectiveness of this method on the McKillop-Geeves (MG) model of thin filament regulation...

Atherosclerosis is a progressive disease characterized by inflammation, monocyte-macrophage migration, and lipid accumulation in the vascular wall. Atherosclerosis is initially characterized by endothelial dysfunction, which favors lipid and cell elements crossing inside blood vessel wall. In this study we investigated our three-dimensional compute...

A computer program called Neutron_CR-39.F90 for neutron simulation through a PADC detector and its detection was described and developed. In this work the neutron Am–Be source was considered for simulation. It was shown that the most intensive secondary particles, created in neutron interactions with the detector, are protons. The programming steps...

Advances in e-Infrastructure promise to revolutionize sensing systems and the way in which data are collected and assimilated, and complex water systems are simulated and visualized. According to the EU Infrastructure 2010 work-programme, data and compute infrastructures and their underlying technologies, either oriented to tackle scientific challe...

Cells communicate through shed or secreted ligands that traffic through the interstitium. Force-induced changes in interstitial geometry can initiate mechanotransduction responses through changes in local ligand concentrations. To gain insight into the temporal and spatial evolution of such mechanotransduction responses, we developed a 3-D computat...

Geometrical changes of blood vessels, called aneurysm, occur often in humans with possible catastrophic outcome. Then, the blood flow is enormously affected, as well as the blood hemodynamic interaction forces acting on the arterial wall. These forces are the cause of the wall rupture. A mechanical quantity characteristic for the blood-wall interac...

This paper describes a software system for hemodynamic simulation of the blood flow through an aneurysm with rigid walls. Human health significantly depends on the status of blood vessels, however measuring in vivo the important hemodynamic factors in the arterial blood flow, such as wall shear stress, pressure and velocity in blood vessels, is ver...

Laminar flows through channels, pipes and between two coaxial cylinders are of significant practical interest because they often appear in a wide range of industrial, environmental, and biological processes. Discrete particle modeling has increasingly been used in recent years and in this study we examined two of these methods: dissipative particle...

A trial to find the right reasons of the pathogenesis of the pathological changes on the blood vessels and to prevent the growing of the cardiovascular diseases, includes many different techniques of the Artificial Intelligence (AI). Fuzzy modeling and Neural Network reasoning are shown in this paper as two possible solutions in measuring valuable...

Modern medical image devices provide data which are suitable for computer modeling. Using the data from a multi-slice 64-CT scanner at German Cancer Research Center in Heidelberg, we developed a set of software tools for manipulating FE mesh as well as post-processing. In this work we employed raw data from the CT image device to create a 3D brick...

The objectives of this study were to define the regional and local groundwater flow, and to give quantitative estimates of the groundwater dynamic parameters and of the available groundwater resources. To achieve these objectives, numerical tools are required to quantitatively model flow through porous saturated and unsaturated media. We have devel...

The objectives of this study are to define the regional and local groundwater flow, and to give quantitative estimates of different dynamic parameters for Ranney wells in Belgrade Water Supply Center. To solve these tasks used the numerical tools to quantitatively model flow through porous saturated and unsaturated media. We used finite element (FE...