Welcome

Overview

The International Conference on Informatics and Information Technologies is the 14th of the series of conferences organized by the
Faculty of Computer Science and Engineering (FCSE) .

 

Date and venue

April 07-09, 2017, Hotel Bistra, Mavrovo, Macedonia

 

Scope

  • Artificial Intelligence, Robotics, Bioinformatics
  • Multimedia, Signal Processing
  • Computer Networks
  • Sensor Networks
  • Distributed Systems
  • Computer Architecture and Parallel Processing
  • Cloud and GRID Computing
  • Wireless and Mobile Computing
  • Security and Cryptography
  • Theoretical Foundations of Informatics
  • Applied Mathematics
  • eWorld-eWork, eCommerce, eBusiness, eLearning
  • Green ICT

Keynote and invited speakers

 

Prof. Smile Markovski, 

retired professor at the Faculty of Computer Science and Engineering, UKIM, Skopje  

  

S. Markovski is a retired professor of FCSE. He has written more than hundred scientific papers published in journals and conference proceedings, and has been a presenter on many conferences. His scientific interest has transformed from universal algebras via quasigroups theory to cryptography and coding theory. The main focus of his latest research is on applications of quasigroup string transformations for building different types of cryptographic primitives and for designing error correcting  and error detecting codes.  

  

Title of talk:  Probabilistic quasigroups 

 

 

Vesna Prchkovska, PhD 

co-founder & CSO of  Mint Labs, Barcelona, Spain

 

V. Prchkovska graduated with honors from the Faculty of Electrical Engineering at Ss. Cyril and Methodius University in Skopje, Macedonia, in 2006. She obtained her PhD at the Eindhoven University of Technology, Netherlands in 2010 on novel diffusion-based MRI medical imaging models, focusing on HARDI and DTI. After being awarded a Marie Curie Intra-European fellowship, she became a postdoctoral research fellow at the IDIBAPS at Hospital Clinic in Barcelona from 2013 to 2015, where she researched neurological disorders, focusing on brain connectomics. She was then a postdoctoral research fellow at the joint Radiology Department of MassGeneral Hospital and Harvard Medical School where she explored network and graph-based theory applied to brain connectivity matrices from diffusion MRIs and fMRIs. She is now the acting CSO of Mint Labs, also a co-founder, responsible for the R&D, relations with the scientific and medical communities, publications, and patenting algorithms.

 

Title of talk:  Seeing the brain: How neuroimaging transforms the diagnosis and treatment of patients with brain disorders 

Abstract: Doctors and scientists once had to wait until autopsy to examine the brain, and psychologists had to deduce from behavior where the brain was injured. Now they can study detailed three-dimensional images of the brain to spot problems, to understand what happens during tasks, thoughts and emotions and to assess the effectiveness of various treatments.

Current neuroimaging techniques reveal both form and function. They reveal the brain's anatomy, including the integrity of brain structures and their interconnections. They elucidate its chemistry, physiology and electrical and metabolic activity. The newest tools show how different regions of the brain connect and communicate. They can even show with split-second timing the sequence of events during a specific process, such as reading or remembering.

In this talk I will explain the developments and utilities of Neuroimaging over the past decade and how we use it to help accelerate the discovery and development of treatments for brain disorders.

 

 

Ognjen Šćekić, PhD 

postdoc researcher at the Distributed Systems Group, Institute of Information Systems, TU Wien 

  

Dr. Ognjen Šćekić is a postdoctoral researcher and lecturer at the Distributed Systems Group, TU Wien, Vienna, Austria. He earned his PhD from the TU Wien, and his Master’s degree from the School of Electrical Engineering, University of Belgrade, Serbia. His research interests include Social Computing, Crowdsourcing, Socio-technical Systems, and Collective Adaptive Distributed Systems, with focus on the direct and indirect programmability aspects of the software and human elements in these systems. Ognjen has co-authored 3 books, and over 20 conference and journal papers. Prior to his academic career, he worked for Microsoft and Cisco Systems as software developer.

  

Title of talk:  Cyber-Human Smart Cities: The Internet of Things, People and Systems  

Abstract: Contemporary view on Smart City is very much static and infrastructure-centric, focusing on installation and subsequent management of Edge devices and analytics of data provided by these devices. While this still allows a more efficient management of the city's  ICT infrastructure, optimizations and savings in different domains, the existing supporting software architectures are currently designed as single-purpose, vertically-siloed solutions. This effectively hinders an active involvement of a variety of stakeholders (e.g., citizens and businesses) who naturally form part of the city's ecosystem and have an inherent interest in jointly coordinating and influencing city-level activities towards a common benefit.

In this talk we present a value-driven architecture and the defining properties of the envisioned Smart City, characterized by complex coordinated activities involving the City's ICT services, stakeholders and their smart/pervasive devices. We look at the existing foundational technologies for provisioning, coordination and controllability of the said activities and discuss the required alignment steps towards the fulfillment of the stated vision.

Guest student speaker

 

Ana Tanevska, M.Sc. 

PhD student at the Robotics, Brain and Cognitive Sciences Unit, Istituto Italiano di Tecnologia (IIT), Italy 

  

A. Tanevska received her her M.Sc. degree in Intelligent Systems Engineering (with particular focus on Robotics) in 2016 from FCSE/FINKI. Since November 2016, Ana has been working as a PhD fellow under a double affiliation. She is enrolled in the Bioengineering and Robotics PhD programme at the University of Genoa in Italy, following the curriculum of Cognitive Sciences, Interactive and Rehabilitation Technologies; while her research work as a PhD fellow is done at the Italian Institute of Technology (IIT) in Genoa, with the Department of Robotics, Brain and Cognitive Sciences (RBCS). Her PhD work is focusing on implementing a self-learning, intelligent agent on the iCub humanoid robot, applying memory, prospection and the robot's emotions as internal evaluation mechanisms with the purpose of creating an autonomous model for cognitive human-robot interaction. Ana's research interests include Cognitive Robotics, Human-Robot Interaction, Socially-Assistive Robotics and Robot-Assisted Therapy.

 

  

Title of talk:  Towards autonomous and cognitive human-robot interaction  

Abstract: Quickly becoming one of the more intriguing topics in social robotics in recent years, cognition is a highly-desired ability for intelligent agents and robots. In the context of robotics, cognition encompasses several skills necessary for any potentially autonomous robot – perceiving the robot’s environment, learning from experience, anticipating the outcome of events, adapting to changing circumstances and ultimately acting with the purpose of achieving some goals. Considering the complexity of cognition, it’s understandable why most of the human-robot interaction (HRI) projects opt for the non-autonomous approach, where the robot is either partially or completely controlled by a human. While this approach (referred to as the Wizard-of-Oz method) is highly effective when applied in assistive therapy or in HRI with unpredictable target groups, autonomous HRI is still the desired endpoint for roboticists. An optimal middle point between the two would be implementing a cognitive agent in the robot responsible solely for HRI.

This talk will include an in-depth view on cognition and its implementation in robotics, as well as discussions about two major projects concerning cognitive agents for autonomous HRI, namely the Self-learning agent in the NAO humanoid robot and the Autonomous cognitive agent in the iCub humanoid robot.

 

 

Title of the talk: Ambient Intelligence (AmI) applications in healthcare domain 

In recent years, people are surrounded by technology which tries to increase their quality of life and facilitate the daily activities. However, sometimes technology is difficult to handle or people have a lack of knowledge to use it. Ambient Intelligence (AmI) is an emerging discipline that brings intelligence to our everyday environments and makes those environments sensitive to us.  The vision of AmI is a global intelligent environment, which is aware of the people and their state, and thus provides intelligent and intuitive interfaces embedded in the everyday objects around them. The basic idea behind AmI is that by enriching an environment with technology (mainly sensors and devices interconnected through a network), a system can be built to take decisions to benefit the users of that environment based on real-time information gathered and historical data accumulated. AmI is a fast-growing multi-disciplinary area which builds upon the advances in multiple well-established areas in computer science, such as: artificial intelligence, sensors, networks, pervasive/ubiquitous computing, and human computer interfaces. 

In this talk, four applications of AmI in healthcare domain will be presented, including: 

§  Human Activity Recognition. This application is about recognizing the activities of a person that is wearing a sensor. It includes all aspects of the creation of a successful application: sensor data acquisition, data processing, machine learning analysis, and finally recognizing the activity of the user. Comparison of several algorithms on several sensor body locations will be presented (chest, thighs, ankles, wrists, etc.). Having an accurate activity recognition system can be beneficial for sportsman (fitness tracking), weight control, management of metabolic disorders (e.g., diabetes), and similar. 

§  Human Fall Detection. This application is about detecting when a person falls. This is achieved by analyzing data provided from wearable sensors, mainly accelerometers. Various algorithms and sensor locations will be discussed and experimental results will be presented. This application is especially useful for elderly people, which have tendency to fall, and sometimes are hurt and cannot call for a help. Having such system, an automatic call can be stablished once a fall is detected. 

§  Human Energy Expenditure Estimation. This application is about automatically estimating the energy expenditure of a person. A system will be presented that analyzes data from several wearable sensors (accelerometer, heart rate, galvanic skin response, etc.) and by using machine learning techniques it estimates the energy expenditure. Energy expenditure directly reflects the intensity of physical activity, which makes the estimation of it, an important component for sports training, weight control, management of metabolic disorders (e.g., diabetes), and other health goals. 

§  Human Stress Detection. A system that continuously detects the stress level of a person will be presented. The system uses machine learning methods to analyze data from a wristband device and to detect the stress level. 



 

Hristijan Gjoreski was born in Prilep, Republic of Macedonia. In 2010 he finished his undergraduate studies at the Faculty of Electrical Engineering and Information Technology in Skopje, Macedonia, under supervision of Prof. Dr. Ivan Chorbev. 

In 2011, he received a Master’s degree at the Jožef Stefan International Postgraduate School in Ljubljana, Slovenia, for the thesis titled "Adaptive human activity recognition and fall detection using wearable sensors", under the supervision of Prof. Dr. Matjaž Gams. 

In 2015 he received his PhD degree at the Jožef Stefan International Postgraduate School, Slovenia, by defending the thesis entitled: “Context-based Reasoning in Ambient Intelligence” supervised by Prof. Dr. Matjaž Gams and co-supervised by Dr. Mitja Luštrek. 

Since 2010, he is a researcher at the Department of Intelligent Systems at the Jožef Stefan Institute. His main research field is artificial intelligence with focus on data mining and machine learning techniques and their application in fields such as intelligent systems, ambient intelligence and wearable sensors computing. Applications on which he has focused in the last several years are: human activity recognition, fall detection, energy expenditure estimation, and stress detection. Currently, he is a technical leader of the European Horizon 2020 IN LIFE project. 

His research work has been presented in more than 30 international conferences and published in more than 10 international journals. He was also part of the team that won the annual international competition in activity recognition − EvAAL 2013. For his work in the ambient intelligence domain he has also received the two best paper awards, at the European Conference Ambient Intelligence (AmI 2015) and at the Jožef Stefan International Postgraduate School Students’ Conference (IPSSC 2014). The majority of his research experience is mainly from four European research projects: IN LIFE, Confidence, Chiron and Commodity12.