Sandor Szenasi

Óbudai Egyetem · John von Neumann Faculty of Informatics

In this paper, we present a novel parallel algorithm implemented on graphics accelerators to solve the two-dimensional inverse heat conduction problem (estimation of the temporo-spatial heat transfer coefficients without any prior knowledge of the thermal boundary conditions) based on Particle Swarm Optimization method. In the absence of analytical...

Nowadays, processing medical images is increasingly done through using digital imagery and custom software solutions. The distributed algorithm presented in this paper is used to detect special tissue parts, the nuclei on haematoxylin and eosin stained colon tissue sample images. The main aim of this work is the development of a new data-parallel r...

One of the most important road safety interventions is the elimination of accident black spots (places with accident density higher than expected). The first step of this process is the identification of these locations. There are several methods for this purpose, but most of them are now outdated. The primary objective of our five-year project was...

The accurate knowledge of Heat Transfer Coefficients is essential for the design of precise heat transfer operations. The determination of these values requires Inverse Heat Transfer Calculations, which are usually based on heuristic optimisation techniques, like Genetic Algorithms or Particle Swarm Optimisation. The main bottleneck of these heuris...

The use of digital microscopy allows diagnosis through automated quantitative and qualitative analysis of the digital images. Often to evaluate the samples, the first step is determining the number and location of cell nuclei. For this purpose, we have developed a GPGPU based data-parallel region growing algorithm that is equally as accurate as the...

In this paper, a lightweight blockchain simulation and transaction graph visualization application is presented, crafted to augment the identification of pivotal nodes within blockchain networks. Harnessing sophisticated data visualization techniques, this application provides an extensive and easy to use environment for delving into and scrutinizi...

Although current computer vision systems are closer to the human intelligence when it comes to comprehending the visible world than previously, their performance is hindered when objects are partially occluded. Since we live in a dynamic and complex environment, we encounter more occluded objects than fully visible ones. Therefore, instilling the c...

In this contribution the matrix representation of the IMBT is introduced in order to be able to assess its performance next to arbitrary key distribution, compare to other well known data structures and formulate a sufficient condition on the dynamic equilibrium of IMBT.

The motivation behind this contribution was raised during the examination of the boundary value patterns of the Virtual Dictionary Extension (VDE) lossless compression method. During the VDE compression method words are stored in the so called compression dictionary, therefore the base unit of the boundary value pattern is the word. Determination o...

Low-level object matching can be done using projection signatures. In case of a large number of projections, the matching algorithm has to deal with less significant slices. A trivial approach would be to do statistical analysis or apply machine learning to determine the significant features. To take adjacent values of the projection matrices into...

It is expected that most accidents occurring due to human mistakes will be eliminated by autonomous vehicles. Their control is based on real-time data obtained from the various sensors, processed by sophisticated algorithms and the operation of actuators. However, it is worth noting that this process flow cannot handle unexpected accident situation...

The significant power of deep learning networks has led to enormous development in object detection. Over the last few years, object detector frameworks have achieved tremendous success in both accuracy and efficiency. However, their ability is far from that of human beings due to several factors, occlusion being one of them. Since occlusion can ha...

In the field of image processing, there are several difficult issues that do not have exact solutions due to incomplete or imperfect information and limited computation capacity [...]

The heat transfer coefficients reconstruction could be solved using several ways and configurations. The Inverse Heat Transfer Problems (IHCP) collects all kind of algorithms which try to solve the Heat Transfer Problems. These algorithms try to calculate the heat transfer coefficients inversely. There is some solution for solving this numerical me...

This work focuses on Human Computer Interaction (HCI) for multidisciplinary product modeling. Requirement Functional Logical Physical (RFLP) structure has emerged as one of the prominent approaches for modeling the multidisciplinary products. To simplify the HCI of an RFLP structured product model, Information Content (IC) provides effective commun...

Most road accidents are caused by human errors; therefore, the development of self-driving cars could reduce the number, or at least, the severity of accidents. Their control is based on real-time data obtained from the various sensors, processed by sophisticated algorithms. However, this process flow cannot handle several unexpected accident situa...

In this contribution, we provide a detailed analysis of the search operation for the Interval Merging Binary Tree (IMBT), an efficient data structure proposed earlier to handle typical anomalies in the transmission of data packets. A framework is provided to decide under which conditions IMBT outperforms other data structures typically used in the...

An inverse solver for the estimation of the temporospacial heat transfer coefficients (HTCs), without using prior information of the thermal boundary conditions, was used for immersion quenching into a series of vegetable oils and two commercial petroleum oil quenchants. The Particle Swarm Optimization method was used on near-surface temperature-ti...

To achieve the optimal performance of an object to be heat treated, it is necessary to know the value of the Heat Transfer Coefficient (HTC) describing the amount of heat exchange between the work piece and the cooling medium. The prediction of the HTC is a typical Inverse Heat Transfer Problem (IHCP), which cannot be solved by direct numerical met...

Data preprocessing is a crucial task for data scientists working on machine learning projects, as well as lowering the dimensionality of input vectors as possible. While deep learning got popular with big data used in neural networks with a large number of layers and neurons, researchers are also working on methods where accurate predictions can be...

In case of object matching on low-quality images, projection-based similarity measurement is an often used approach. In recent advances, deep convolutional neural networks are used to extract the features from the input data. In this paper, an analysis is done to compare end-to-end methods with projection-based preprocessing methods, including the...

Graphics processing units (GPUs), mainly named as general-purpose computing on graphics processing units (GPGPUs) became a widely used technology for many computer-aided procedures in different research or industry areas that require high algorithmic computation capabilities for parallel computing tasks. In the field of bioinformatics and especiall...

Computer-Aided Design (CAD) is a type of software program used by humans to create 2D and 3D product models of physical components. The complex product model is handled through the interface provided by the vendors of CAD software. This work focuses on the Human Computer Interaction (HCI) of the multidisciplinary product modeling in the CAD systems...

Nowadays, several commercial and open source game engines are available for game developers. These are usually using a monolithic approach as the engines are solely meant to be end-to-end tools for game development without considering their benefits in other areas that may need some of the engine's features but will not be published as a game. This...

A novel algorithm-based method for Neural Architecture Generation is introduced in this paper. Unlike NASNet or AutoML, which outputs one optimal trained model based on a Recurrent Neural Network, the presented method outputs multiple possible architectures, without training. This method is not meant for automatic model generation based on inputs,...

In the course of transmission through networks a particular packet, like a Storm tuple or a performance/fault management (PM/FM) report in XML format of an Operation Support System (OSS) application, data loss/out of order arrival/duplication phenomena may cause the packet not to arrive at the destination, arrive exactly once or to arrive in severa...

The aim of this paper is to present a technique, which uses machine learning to process the short text answers with Hungarian language. The processing is based on a special neural network, the convolutional neural network, which can efficiently process short text answer. To achieve precise classification for training and recall grammatically consis...

Heatmaps are widely used by road safety engineers to visualise accident data (where heat refers to the concentration of accidents). In the subfield of road accident black spot localisation, the high number of similar black spot candidate locations makes this method unreliable and difficult to use. An additional process to convert the clusters of th...

The localisation of road accident hotspots (areas of the public road network, where the number of accidents is higher than expected based on the average values) is one of the main tasks of road safety experts. Analysing these locations can help to avoid further traffic accidents and personal injuries (most of all, fatal accidents). There are severa...

A novel method to measure similarity on images is based on the Siamese architecture of Convolutional Neural Networks. Two identical CNNs extract the significant parts of the inputs, and a single neuron outputs the distance of the two. The aim of this paper is to introduce that the Siamese structure can be applied to match image projection based sig...

The matching of the visual representations of two objects is a very important task in most computer vision applications. In special cases, when all objects look alike and only small differences occur, the difficulty of the task increases. In this paper, a novel method for matching low-quality images of rear-viewed vehicles is proposed, using multi-...

Accurate design of heat treatment operations requires the knowledge of the Heat Transfer Coefficients (HTC), which quantity can be determined by performing Inverse Heat Transfer Calculations. The novel approaches for the estimation of HTC are based on heuristic optimisation methods, but the usage of these techniques raises several questions. In the...

The parallelized particle swarm optimization (PSO) method has been developed to solve inverse heat transfer problems. Temporal- and spatial-dependent heat transfer coefficient functions obtained on the surfaces of axis-symmetrical work pieces are estimated by applying the novel technique. The goal function to be minimized by the PSO approach is def...

The general area of the paper is methods and data structures to efficiently avoid data duplication. In telecommunication networks operation support systems (OSS) process time series of counters related to the behaviour of network elements, such as failed location updates over the last 5 min. In general we may assume time series of key-value pairs w...

The Radon transform and the reverse formulas are mostly used in computer tomography to reconstruct the original shape. The projections of an image could be used in computer vision for object recognition, based on projection matching. By comparing the projections, an effective method could be defined. To understand the projection behavior the basic...

The application of lossless data compression methods may significantly decrease the required storage space or throughput. The quality of the compression ratio is influenced by several factors, like the available space and processing resources and the statistical characteristic of the data to be compressed. In this contribution we will perform the b...

One of the biggest shortcomings of the CUDA environment is the lack of a data structure having effective parallel insert and remove operations. This paper focuses on the insertion. The traditional vector-based lists are not applicable for this kind of addition; however, the well-known linked list data structure has the ability to handle parallel in...

Several real-world applications involve simulation of the heat transfer within a given workpiece when placed into an environment with a different temperature. This requires calculation of the temperature in a particular location and at a given moment in time according to the available input parameters (shape and thermal characteristics of the given...

To simulate the behaviour of cell-level biological interactions, cells can be modeled as individual agents interacting with each other. To identify the effects of parameter perturbation, a massive number of simulations are usually required that are feasible to carry out by parallel computation. In this article, a multiprocessing scheme is defined t...

Lossless data compression is an important topic from both data transmission and storage point of view. A well chosen data compression technique can largely reduce the required throughput or storage need. As a trade-off, data compression always requires some computing resources which are in a correlation with the achieved compression rate. For a par...

In this paper, we present an inverse solver for the estimation of the temporospatial heat transfer coefficients (HTCs) without using prior information of the thermal boundary conditions. The particle swarm optimisation (PSO) method has been introduced to recover the unknown HTC function obtained during immersion quenching. The HTC obtained on the s...

Template matching is a classic technique used in image processing for object detection. It is based on multiple matrix-based calculations, where there are no dependencies on partial results, so parallel solutions could be created. In this article two GPU implemented methods are presented and compared to the CPU-based sequential solution.

Hadoop Distributed File System (HDFS) is the de facto file system in vanilla Hadoop and most of open source Hadoop distributions. However HDFS suffers from the so called Small File Problem. Storm is a parallelized stream processing framework. In this paper we evaluate buffering strategies to mitigate the small file problem. In our evaluations Storm...

Particle swarm optimization was developed in 1995 by Eberhardt and Kennedy \cite{Kennedy1995,Rini2011}. It is a biologically-inspired search and optimization method based on the behaviours of birds flocking or fish schooling. The main idea of the algorithm is the simulation of animal groups without any distinguished leader (such as birds and fishes...

The methodology based on the Particle Swarm Optimization (PSO) method, as a recent stochastic optimization technique to solve complex inverse heat transfer problems is outlined. Temporal and spatial dependent Heat Transfer coefficient obtained on the surfaces of a cylindrical work piece is recovered by solving the inverse heat conduction problem. T...

Generally, template matching methods are very sensible to image orientation, rotation or the size of the template. However, there are known occasions, when they perform better then other keypoint-based techniques. This article demonstrates a massively parallelizable method to multi-scaled template matching. By implementing it sequentially on CPU an...

Nowadays, graphics cards are not only used for processing video data but also suitable for other general purpose operations too. We can use these graphics accelerators in the field of road accident black spot searching. There are several black spot searching methods and most of them are very time and resource consuming; therefore, it is worth imple...