Drago Torkar

Research areas
  • Computer vision
  • Pattern recognition
  • Image processing
  • Machine vision

  • Projects
  • Distributed Artificial Intelligent Systems (2021-2024)
  • Computer structures and systems (2019-2024)
  • Intelligent Secure Trustable Things (2020-2023)
  • Supporting Active Ageing through Multimodal coaching (2017-2021)
  • Advanced recognition (2020)
  • Machine vision quality control of molded plastic parts (2019-2020)
  • Resource Efficient Food and dRink for the Entire Supply cHain (2015-2019)
  • iNet - The Impact of Net Height in Table Tennis (2017-2018)
  • Computer structures and systems (2015-2018)
  • Computer structures and systems (2009-2014)

  •  
    Computer structures and systems[X]
    • acronym: ARRS program
    • type: ARRS program
    • duration: 2009-2014
    • content:
      New silicon technologies allow implementation of complex devices composed of heterogeneous cores, massive memory, communication networks, electro-mechanical sub-assemblies and intelligent sensors, which requires new multidisciplinary design approaches and introduces numerous problems in design and test. The proposed research programme addresses these problems and is primarily focused on the subjects in which we have gained experience in our earlier research work. A processor core is one of the basic blocks of a modern system-on-chip (SoC), therefore the basic knowledge of processor architectures is imperative for the proposed research programme. Following the progress in this field for a number of years, we concentrate on the problem of task scheduling and resource allocation in multithreaded systems. In the area of embedded systems we address problems of dynamic reconfiguration in real-time. We aim to explore the potential for rapid embedded reconfiguration in terms of predictability, reliability and power consumption searching for adequate technologies, such as real-time operating systems, programming languages, hardware platforms for experimental work and prototyping. High-level systhesis faces complex combinatorial problems including parameters that are mutually dependent. Consequently, optimization of the design is often subject to analysis of extensive space of possible solutions. A typical example is concurrent resource allocation of the computing structure synthesized for a given target algorithm. Conventional approaches are often non-adequate, therefore we investigate alternative approaches based on metaheuristic algorithms.

  • Mobile application for food ingredients informing (2009-2010)
  • Development and implementation of a new PIM binder system using advanced methods (2008-2010)
  • The role of Luka Koper in logistic support of the Slovenian Armed Forces and allies (2006-2008)
  • Adaptive Robots for Flexible Manufacturing Systems (2005-2008)
  • Computing structures and systems (2004-2008)
  • Upgrade of light armoured wheeled vehicles VALUK 6x6 (2006-2007)
  • Vision interface for ABB robots (2006)
  • Secure data storage unit based on new ferroelectric semiconductor memory devices (2004-2006)
  • 2D and 3D digital map system for land, aerial and sea orientation (2004-2005)
  • Modeling rheological properties of ceramic-paraffine suspensions for low-pressure injection-moulding (2003-2004)
  • Computing structures and systems (1999-2003)
  • High performance evolutionary techniques in hardware-software codesign (1999-2001)
  • PEMCAS: personal monitor for capability supervision (1997-1998)
  • Architectural synthesis of computer systems with testability issues (1995-1998)
  • Publications
    Journal articles
  • Biomarkers of pre-existing risk of torsade de pointes under Sotalol treatment, J. ELECTROCARDIOL. (2020)
  • Dynamic features of cardiac vector as alternative markers of drug-induced spatial dispersion, J PHARMACOL TOX MET (2020)
  • Knee stiffness and viscosity of human cadaver - Wartenberg test, BJBMS (2017)
  • Cell counting tool parameters optimization approach for electroporation efficiency determination of attached cells in phase contrast images, J.Microsc. (2011)
  • Identification of radon anomalies in soil gas using decision trees and neural networks, Nukleonika (2010)
  • Application of artificial neural networks in simulating radon levels in soil gas, ChemGe (2010)
  • Visual control of an industrial robot manipulator: Accuracy Estimation, Stroj. vestn. (2009)
  • Robot Vision Accuracy Estimation, Elektroteh. vest. (2009)
  • Apparent viscosity prediction of alumina-paraffin suspensions using artificial neural networks, J. mater. process. technol. (2008)
  • Evaluation of accuracy in a 3D reconstruction system, WSEAS Trans. Syst. Control (2007)
  • Control of a robotic manipulator by visual and speech information, Eng. rev. (2002)
  • An uncalibrated robot system for reaching and grasping objects in unpredictable physical environment, J. Electr. Eng. (2001)
  • GPS positioning and digital map processing in 2D and 3D terrain environment, J. Comput. Inf. Technol. (1994)
  • Computer processing of hard-copy maps and their application in satelite positioning, J. Commun. (1994)
  • Reflection on light distribution measurement, Sens. Rev. (1992)
  • Conference papers
  • Food Waste Ontology: A Formal Description of Knowledge from the Domain of Food Waste, BFNDMA 2019 at IEEE BigData 2019
  • Analysis of an Electrocardiographic Multilead System using Artificial Neural Networks - A Study of the Dispersion during Premature Ventricular Stimulation, Biosignals 2016
  • Accuracy of a 3D reconstruction system, ISPRA 2007
  • Robot TCP positioning with vision : accuracy estimation of a robot visual control system, ICINCO 2007
  • Estimation of accuracy for robot vision control, SHR2007
  • Radon in soil gas : application of neuron networks to identify anomalies caused by earthquakes, Hazards 2006
  • Dynamic viscosity prediction of alumina-paraffin suspensions using artificial neural networks, AERC 2005
  • The use of numerical simulation for the study of low-pressure injection moulding of alumina-paraffin suspensions, AERC 2003
  • Books & Chapters in Books
  • Optimal lead selection for evaluation ventricular premature beats using machine learning approach, (2017)
  • Radon as Earthquake Precursor - Methods for Detecting Anomalies, InTech - Open Access Publisher (2011)