Young Researchers Day
Agenda

July 3, 2018
Venue: Faculty of Electrical Engineering, 1108 hall
Patre 5, Banja Luka

Time Speaker Affilation
09:00-09:05 Prof. Dr Gordana Gardašević Faculty of Electrical Engineering
University of Banja Luka
Opening Talk
09:05-10:05 Prof. Dr Danilo P. Mandić Imperial College London
London, United Kingdom
Title. Tensor Decompositions for Big Data Analytics: Blessing of Dimensionality
Multidimensional arrays, also known as tensors, are data structures which are routinely recorded from many modern sensors such as RGB images, multichannel Electroencephalogram, or even communication network traffic data. Yet, standard algorithms for the analysis of such data are typicaly based on matrices, and assume a "flat-view" stracture of the multidimenional world. We show that by tensor representations and the associated tensor decompositions (TD) are an excellent match for the high dimensionality of modern data, whereby the associated super-compression ability of tensor decompositions not only makes the problem computationally tractable, but also preserves physical meaning and interpretability of the so derived latent components in data. A link between tensors and deep learning is also highlighted, with a special emphasis on the link with tensor networks, an arrangement of very high order tensors into lower order cores which are easier to compute on and can be stored in a distributed way or even on different computers. Applications in computer vision, biosignal processing and multimodal learning support the analysis.Multidimensional arrays, also known as tensors, are data structures which are routinely recorded from many modern sensors such as RGB images, multichannel Electroencephalogram, or even communication network traffic data. Yet, standard algorithms for the analysis of such data are typicaly based on matrices, and assume a "flat-view" stracture of the multidimenional world. We show that by tensor representations and the associated tensor decompositions (TD) are an excellent match for the high dimensionality of modern data, whereby the associated super-compression ability of tensor decompositions not only makes the problem computationally tractable, but also preserves physical meaning and interpretability of the so derived latent components in data. A link between tensors and deep learning is also highlighted, with a special emphasis on the link with tensor networks, an arrangement of very high order tensors into lower order cores which are easier to compute on and can be stored in a distributed way or even on different computers. Applications in computer vision, biosignal processing and multimodal learning support the analysis.
10:05-10:35 Aleksandar Mastilović, MSc IEEE Publications Services and Products Board / Communications Regulatory Agency
Bosnia and Herzegovina
Title. 5G: Key Enabler for Internet of Things, Smart Cities and Industry 4.0
Modern challenges in telecommunications are defined with new applications as Internet of Things set of services, Smart Cities, Smart Grid and many other smart solutions but also there is a need for additional automatization of the industry processes, what is defined as Industry 4.0. All these appolications and many others are based on the system of massive number of sensors. Sensors collect the data and send them to nodes for storage and analytics. Current achitecture of telecommunications systems including modern mobile/cellular system 4G (LTE) are not ready to serve for massive and critical Machine-to-Machine communications. 5G is a key enabler for new generation of services and 5G has strictly defined technical parameters and different architecture to be able to reach predefined performances and realibility. New algorithms and new approach for mobile systems will be presented.
10:35-11:20 Dr Darko Aničić Siemens AG
Munich, Germany
Title. Semantics for Interoperable IoT Applications
The Internet of Things (IoT) is fragmented today as it lacks the interoperability across diverse platforms, ecosystems, and domains. As a result, IoT devices and applications are not interoperable. They operate with data silos, and the development of new business applications are faced with high costs and limited market potential. The World Wide Web Consortium (W3C) has recently started a standardization activity called Web of Things (WoT) to encounter this problem. The upcoming standard introduces a Web layer to IoT with the goal of reducing IoT fragmentation. WoT provides rich metadata that describes capabilities of Things, data they exchange, communication and security related information, as well as an API needed to interact with Things. In order to enable applications and platforms to share the same meaning when they exchange data, a semantic interoperability layer at the application level is needed. Applications that are tightly coupled to IoT devices will make up a smaller fraction of delivered value of connected Things over time. There will be more value in interoperable applications that can orchestrate behavior across diverse devices and device ecosystems. This is the reason why iot.schema.org has recently started to work on semantic models that describe common affordances of connected Things (e.g., What does a Thing do? What can I control with it?). Further on, iot.schema.org provides semantics needed for interactions with connected Things from different device ecosystems, i.e., Things that use similar protocols but diverse data models. In this talk, an overview of both activities, W3C WoT and iot.schema.org, will be provided.
11:20-11:50 Vladimir Lekić, MSc Daimler AG, Group Research & Mercedes-Benz Cars Development
Ulm, Germany
Title. Semantic Segmentation of Ranging Sensor Data
Ranging sensors, such as radar and lidar, on-board the vehicle are considered to be very robust under changing environment conditions. Largely owing to this reputation, they have found a broad applicability in driver assistance, and consequently in autonomous driving systems. On the other hand, they lack precision. This makes classification tasks of the measurement data rather difficult. A method for semantic segmentation of the ranging sensors data using the generative adversarial networks will be presented. Utilizing the fully unsupervised learning algorithm sensor data is converted into artificial, camera-like, environmental images that are further used as input for semantic image segmentation algorithms.
11:50-12:05 Coffee break
12:05-12:50 Kemal Hajvazović Daimler AG, Group Research & Mercedes-Benz Cars Development
Sindelfingen, Germany
Title. 48V System Made by Mercedes
In modern vehicles the number of the electrical consumers and the energy demand is constantly increasing. Equipment such as fast seat heaters, armrest heaters, massage function or Thermo-Cupholder improve comfort, but at the same time put additional performance requirements on the electrical system. The base of the energy supply for today’s passenger cars is the 12V electrical system. This system is established and did not change significantly for decades. The operating voltage range is from 11 to 15 volts. This limited voltage range leads, with increasing power requirement, to a steady increase of the occurring currents. Higher currents lead to bigger lead acid batteries and heavier vehicle harness, which directly influences the fuel economy. Therefore present 12V system does not offer enough reserves for future applications. In order to tackle this problem Mercedes-Benz uses a combination of 48 V and 12 V electrical systems in the new S-Class. The 48 V electrical system solves the above stated conflict without the disadvantages of a costly high-voltage electrical system. Additionally it brings many of the well-known hybrid functions and opens potentials for the reduction of the fuel consumption. This presentation will show you current state of the implementation of the 48V system in the new S-Class and highlight future development directions.
12:50-13:20 Ratko Pilipović, ma Faculty of Computer and Information Science
University of Ljubljana, Slovenia
Title. HYLO - HYbrid LOgarithmic Multiplier
Much attention is devoted to the design of multipliers as one of the most important arithmetic circuit. By allowing small but controllable computational error a efficient design of multiplier can be achieved. Although much work is done, leading inexact multiplier design strategies, truncated and logarithm multipliers, fail to meet requirements for chip area efficiency and computational error. Presentation introduces a novel design paradigm for inexact multiplier which combines the advantages of leading design strategies. On the top level, proposed strategy employs decomposed multiplier, where the least significant partial product is obtained by utilizing logarithm multiplier. This allows design of power efficient multiplier which characterize with small error performance. Error performance of proposed method is evaluated by conducting error analysis and comparing it with state-of-the-art multipliers. The results show potential for further development and application of a multiplier in neuro-computing hardware.
13:20-13:40 Dr Aleksandar Pajkanović Faculty of Electrical Engineering
University of Banja Luka
Title. Design and Characterization of an Inductor and a Low-Noise Amplifier in Monolithic Integrated Circuit Technology for Wideband Operation
A passive inductive component and a low-noise amplifier are designed, fabricated in standard monolithic CMOS technology and characterized, both intended for wideband operation. For the design of the inductor, meander topology is chosen. Along with the integrated circuit design tools, electromagnetic field simulator is used. Besides the standard parameter characterization, special attention is dedicated to the analysis of process and temperature variations. Furthermore, mechanical characterization of the material that comprises the protection layer has been undertaken. Low-noise amplifier is designed as the first stage of an ultra wideband receiver and the results show that the circuit is successfully designed.
13:40-14:20 Lunch break
14:20-14:40 Tijana Delić, ma Faculty of Technical Sciences
University of Novi Sad, Serbia
Title. Expressive Speech Synthesis Based on Deep Neural Networks
Studies have shown that people already perceive the interaction with computers, robots and media in the same way as they perceive social communication with other people. For that reason it is critical for a high-quality text-to-speech system (TTS) to sound as human-like as possible. Even though synthetic voices are now intelligible and natural enough, they lack expression. Recent development of software and hardware increased the popularity of using artificial neural networks in many areas, including speech processing. One of the advantages of such methods in speech synthesis is the possibility to easily change speaker characteristics and speaking styles. The main approaches in the area will be presented, putting the accent on having a small amount of data which is typical for scarce languages.
14:40-15:00 Jovan Galić, ma Faculty of Electrical Engineering
University of Banja Luka
Title. ASR Recognition of Whispered Speech Based on Hidden Markov Models
Due to the lack of sufficient amount of whisper data for training, whispered speech recognition is a serious challenge for state-of-the-art Automatic Speech Recognition (ASR) systems. Because of great acoustic mismatch between neutral and whispered speech, ASR systems are faced with significant drop of performance when applied to whisper. In this presentation, an analysis of neutral and whispered speech recognition based on Hidden Markov Models (HMM) framework, in a Speaker Dependent (SD) and Speaker Independent (SI) cases will be given. Special attention is paid to the neutral-trained recognition of whispered speech (N/W scenario). As well, advantages and disadvantages related to recognition based on SVM (Support Vector Machines), ANN (Artificial Neural Networks) and DTW (Dynamic Time Warping) techniques will be discussed.
15:00-15:20 Boris Malčić, ma Faculty of Electrical Engineering
University of Banja Luka
Title. Algorithmic Optimization of Transmission Parameters in IEEE 802.11
The main purpose of this research is to achieve a transmission optimization in real conditions of a dynamic environment. The optimization is based on an idea of mathematical modeling of data flow changes and spatial scheduling of clients in IEEE 802.11 WLAN. In order of existing state optimization in terms of reducing channel interference with energy-efficient work of WAPs in WLAN, new algorithms are proposed. Both algorithms (DCA and TCRFFA) make a unique proposal of the algorithm for the optimization. Also, an algorithm based solution for smart WLAN antenna is modelled in Matlab with a simple option of radio-localization in WLAN. Performed simulations have shown, that proposed solutions could lead to a decrease in EVM, improvements in QoS and transmissions at higher bit rates.
15:20-15:40 Dragan Vasiljević, MSc Faculty of Electrical Engineering
University of Banja Luka
Title. Data Aggregation for Advanced Communications in IEEE802.15.4e TSCH Wireless Sensor Networks
Wireless Sensor Networks – WSNs have a wide range of applications. One of them are industrial applications. This field is of particular interest because it requires WSNs to have a high performance in terms of reliability, throughput and data transmission delay. The usage of frequency hopping technique, which increases resilience to interference and multi path fading, enables IEEE802.15.4e TSCH protocol to have potential to satisfy the criteria of industrial applications. OpenWSN is an open software platform which implements IEEE802.15.4e TSCH protocol together with other standardized protocols for WSN thus making entire protocol stack for WSN. Previous researches using OpenWSN platform showed that the key factor for performance of IEEE802.15.4e TSCH WSNs is timeslot scheduling at MAC (Medium Access Control) layer. For a certain scheduling, additional performance increase can be achieved using the technique of data aggregation at WSN nodes. This technique is applicable in conditions where an average packet size in WSN is significantly smaller than maximum possible packet size. Data aggregation technique provides higher throughput, congestion avoidance and decreases packet losses.
15:40-15:50 Coffee break
15:50-17:50 Panel

ComTrade: Industrial IoT – Cloud solutions (ComTrade experience & use cases in different industries)

Faculty of Technical Sciences, University of Novi Sad, Serbia – presentation

Faculty of Architecture, Civil Engineering and Geodesy, Banja Luka – presentation

Young Researchers Networking – Carrier Opportunities

Speakers

Tensor Decompositions for Big Data Analytics: Blessing of Dimensionality

Prof. Dr Danilo P. Mandić

Imperial College London
London, United Kingdom
d.mandic@imperial.ac.uk
Homepage Biography

Fellow of the IEEE, member of the Board of Governors of International Neural Networks Society (INNS), member of the Big Data Chapter within INNS and member of the IEEE SPS Technical Committee on Signal Processing Theory and Methods. He has received five best paper awards in Brain Computer Interface, runs the Smart Environments Lab at Imperial College, and has about 500 publications in international journals and conferences. He has authored two research monographs on neural networks, Recurrent Neural Networks for Prediction (Wiley, 2001) and Complex Valued Nonlinear Adaptive Filters: Nonlinearity, Widely Linear and Neural Models (Wiley, 2009). He has also co-authored a two volume monograph Tensor Networks for Dimensionality Reduction and Large Scale Optimisation (Now Publishers, 2016, 2017). Prof. Mandić has given a number of keynote speaches and tutorials at foremost international conferences (IJCNN, ICASSP), and has received the President Award for Excellence in Postgraduate Supervision at Imperial. In terms of the applications of his work, he is a pioneer of Hearables, a radically new in-the-ear-canal system for the recording of the Electroencephalogram (EEG) and vital signs. This work appeared in IEEE Spectrum, MIT Technology Review and has won several awards. Prof. Mandić is an author of the two-volume monograph "Tensor Networks for Dimensionality Reduction and Large Scale Optimization", Now Publishers, 2016 and 2017.

Abstract. Multidimensional arrays, also known as tensors, are data structures which are routinely recorded from many modern sensors such as RGB images, multichannel Electroencephalogram, or even communication network traffic data. Yet, standard algorithms for the analysis of such data are typicaly based on matrices, and assume a "flat-view" stracture of the multidimenional world. We show that by tensor representations and the associated tensor decompositions (TD) are an excellent match for the high dimensionality of modern data, whereby the associated super-compression ability of tensor decompositions not only makes the problem computationally tractable, but also preserves physical meaning and interpretability of the so derived latent components in data. A link between tensors and deep learning is also highlighted, with a special emphasis on the link with tensor networks, an arrangement of very high order tensors into lower order cores which are easier to compute on and can be stored in a distributed way or even on different computers. Applications in computer vision, biosignal processing and multimodal learning support the analysis.Multidimensional arrays, also known as tensors, are data structures which are routinely recorded from many modern sensors such as RGB images, multichannel Electroencephalogram, or even communication network traffic data. Yet, standard algorithms for the analysis of such data are typicaly based on matrices, and assume a "flat-view" stracture of the multidimenional world. We show that by tensor representations and the associated tensor decompositions (TD) are an excellent match for the high dimensionality of modern data, whereby the associated super-compression ability of tensor decompositions not only makes the problem computationally tractable, but also preserves physical meaning and interpretability of the so derived latent components in data. A link between tensors and deep learning is also highlighted, with a special emphasis on the link with tensor networks, an arrangement of very high order tensors into lower order cores which are easier to compute on and can be stored in a distributed way or even on different computers. Applications in computer vision, biosignal processing and multimodal learning support the analysis.

5G: Key Enabler for Internet of Things, Smart Cities and Industry 4.0

Aleksandar Mastilović, MSc

IEEE Publications Services and Products Board / Communications Regulatory Agency
Bosnia and Herzegovina
amastilovic@rak.ba
Linkedin Biography

Aleksandar is currently employed as the Expert Advisor to the Director of the Communications Regulatory Agency Bosnia and Herzegovina, from December 2017. He moved back to the Bosnia and Herzegovina as the part of an initiative for creating an expert group of the regulatory authority competent for the implementation of 4G, Digital TV and other relevant projects in Bosnia and Herzegovina. Besides, in January 2017, Aleksandar joined IEEE as an executive board member. IEEE is a renowned representing electrical engineering community with 600.000 members and the budget approx. 1 billion$ US. He is IEEE active volunteer for more than 16 years and nowadays he is the member of a few working groups and executive committees on a global level: IEEE Publications Services and Products Board, IEEE Young Professionals Committee, IEEE Platform Guidance Group, IEEE Internet of Things Standards Steering Committee and many others OUs. He is very active in promoting smart technologies for improving quality of life and building a smart society at all. Aleksandar has strong international experience in technical, business, education and regulation/legal side of smart technologies. He was awarded a grant from IEEE Communications Society for 1st Summer School for 30 best Ph.D. students in Telecommunications worldwide in 2015, and is the author is the author of 8 papers on IEEE conferences and workshops. Furthermore, he was one of 19 members in the international expert group in IEEE for creating the trend/survey paper „Artificial Intelligence and Machine Learning Applied in Cybersecurity“, describing expecting movement in the technology world (https://www.ieee.org/about/industry/confluence/feedback.html). His research interest is Cellular Mobile System 4G/5G with focus on Internet of Things applications and services and especially for Smart Cities and their initiatives, but also Computer Networks Design, Routing and Switching and Communications Security including Applied Mathematics methods and algorithms in Cryptography. In years before, Aleksandar graduated BSc in 2009 and MSc in 2016 at University of Sarajevo (Bosnia and Herzegovina). In the period between 2009 and 2014, Aleksandar was employed in University of Sarajevo, Faculty of Electrical Engineering (Bosnia and Herzegovina) as research and teaching assistant in the field of computer sciences, computer networks and cybersecurity. In 2014, he received Maria Curie Fellowship from EU for Ph.D. studies and is working on the FP7 ADVANTAGE ITN Project in Working Package 1 team for Smart Home design at University of Novi Sad, Faculty of Technical Sciences (Serbia). The primary research topic is Architecture Design for 5G Cellular System, with focus on optimizing uplink Communications and Power Control in Small Cells and Uncoordinated Random Access Control for Massive and Critical Machine-to-Machine communications. Aleksandar is also a Distinguished Lecturer of Friedrich Naumann Foundation on Smart Technologies, Smart and Responsive Cities topics. He is also co-founder of Smart Cities Education Initiative in Western Balkans region from IEEE side, together with a representative of Friedrich Naumann Foundation. Aleksandar is also an external expert of G20 Global Solutions for smart technologies and sustainable development.

Abstract. Modern challenges in telecommunications are defined with new applications as Internet of Things set of services, Smart Cities, Smart Grid and many other smart solutions but also there is a need for additional automatization of the industry processes, what is defined as Industry 4.0. All these appolications and many others are based on the system of massive number of sensors. Sensors collect the data and send them to nodes for storage and analytics. Current achitecture of telecommunications systems including modern mobile/cellular system 4G (LTE) are not ready to serve for massive and critical Machine-to-Machine communications. 5G is a key enabler for new generation of services and 5G has strictly defined technical parameters and different architecture to be able to reach predefined performances and realibility. New algorithms and new approach for mobile systems will be presented.

Semantics for Interoperable IoT Applications

Dr Darko Aničić

Siemens AG
Munich, Germany
darko.anicic@siemens.com
Homepage Biography

Dr. Darko Anicic is a research scientist at Siemens AG, Corporate Technology, Germany. He conducts research in the areas of Internet of Things, Web of Things in Automation Systems, Semantic Web Technologies applied to constrained devices, Complex Event Processing and rule-based reasoning over streaming data. Darko Anicic is involved in the W3C Web of Things standardization activity and the community standardization work on iot.schema.org. He authored more than 30 publications in conferences, book chapters and journals. Darko Anicic is also inventor of few patents, and is responsible for several internal and publicly funded research projects. He received PhD from Karlsruhe Institute of Technology (Germany). Before joining Siemens, Darko Anicic was a researcher at the FZI – Research Center for Information Technology in Karlsruhe (Germany), and the Semantic Technology Institute Innsbruck (Austria).

Abstract. The Internet of Things (IoT) is fragmented today as it lacks the interoperability across diverse platforms, ecosystems, and domains. As a result, IoT devices and applications are not interoperable. They operate with data silos, and the development of new business applications are faced with high costs and limited market potential. The World Wide Web Consortium (W3C) has recently started a standardization activity called Web of Things (WoT) to encounter this problem. The upcoming standard introduces a Web layer to IoT with the goal of reducing IoT fragmentation. WoT provides rich metadata that describes capabilities of Things, data they exchange, communication and security related information, as well as an API needed to interact with Things. In order to enable applications and platforms to share the same meaning when they exchange data, a semantic interoperability layer at the application level is needed. Applications that are tightly coupled to IoT devices will make up a smaller fraction of delivered value of connected Things over time. There will be more value in interoperable applications that can orchestrate behavior across diverse devices and device ecosystems. This is the reason why iot.schema.org has recently started to work on semantic models that describe common affordances of connected Things (e.g., What does a Thing do? What can I control with it?). Further on, iot.schema.org provides semantics needed for interactions with connected Things from different device ecosystems, i.e., Things that use similar protocols but diverse data models. In this talk, an overview of both activities, W3C WoT and iot.schema.org, will be provided.

Semantic Segmentation of Ranging Sensor Data

Vladimir Lekić, MSc

Daimler AG, Group Research & Mercedes-Benz Cars Development
Ulm, Germany
vladimir.lekic@daimler.com
Linkedin Biography

Vladimir Lekić is a Research and Development Engineer at Daimler AG Group Research & Mercedes-Benz Cars Development, Ulm, Germany. He has been designing and developing sensor signal processing and machine learning algorithms for driver assistance systems and for self-driving vehicles for premium vehicle manufacturers. Vladimir is also a doctoral candidate at the Faculty of Electrical Engineering, University of Banja Luka, Bosnia and Herzegovina. The main areas of his research include unsupervised learning, generative models, computer vision and radar signal processing. He authored several conference papers related to computer vision and machine learning.

Abstract. Ranging sensors, such as radar and lidar, on-board the vehicle are considered to be very robust under changing environment conditions. Largely owing to this reputation, they have found a broad applicability in driver assistance, and consequently in autonomous driving systems. On the other hand, they lack precision. This makes classification tasks of the measurement data rather difficult. A method for semantic segmentation of the ranging sensors data using the generative adversarial networks will be presented. Utilizing the fully unsupervised learning algorithm sensor data is converted into artificial, camera-like, environmental images that are further used as input for semantic image segmentation algorithms.

48V System Made by Mercedes

Kemal Hajvazović

Daimler AG, Group Research & Mercedes-Benz Cars Development
Sindelfingen, Germany
kemal.hajvazovic@daimler.com
Biography

Kemal Hajvazovic is born in Teslic (BiH). After finishing the studies of electrical engineering in Banja Luka in 2005, he took his first position as requirements and test engineer in General Motors Powertrain Development at Opel AG in Rüsselsheim (Germany). 2008 he started working as a development engineer in Mercedes Benz Cars at Daimler AG in Stuttgart. Main areas of his work are research and series development of 12V/48V/HV energy systems. He is also actively involved in the development of software functions for predictive distribution of electrical energy in vehicles with classical or alternative powertrains.

Abstract. In modern vehicles the number of the electrical consumers and the energy demand is constantly increasing. Equipment such as fast seat heaters, armrest heaters, massage function or Thermo-Cupholder improve comfort, but at the same time put additional performance requirements on the electrical system. The base of the energy supply for today’s passenger cars is the 12V electrical system. This system is established and did not change significantly for decades. The operating voltage range is from 11 to 15 volts. This limited voltage range leads, with increasing power requirement, to a steady increase of the occurring currents. Higher currents lead to bigger lead acid batteries and heavier vehicle harness, which directly influences the fuel economy. Therefore present 12V system does not offer enough reserves for future applications. In order to tackle this problem Mercedes-Benz uses a combination of 48 V and 12 V electrical systems in the new S-Class. The 48 V electrical system solves the above stated conflict without the disadvantages of a costly high-voltage electrical system. Additionally it brings many of the well-known hybrid functions and opens potentials for the reduction of the fuel consumption. This presentation will show you current state of the implementation of the 48V system in the new S-Class and highlight future development directions.

HYLO – HYbrid LOgarithmic Multiplier

Ratko Pilipović, ma

Faculty of Computer and Information Science
University of Ljubljana, Slovenia
ratko.pilipovic@fri.uni-lj.si
Linkedin Biography

Ratko Pilipović received the Master degree in Electronics and Telecommunication from the Faculty of Electrical Engineering, University in Banja Luka, Bosnia and Herzegovina in 2017 . He is currently working toward the Ph.D. degree at University of Ljubljana, Faculty of Computer and Information Science, Ljubljana, Slovenia. His research interests include approximate computing, low-power VLSI designs, arithmetic circuits designs, FPGA designs, digital signal processing, and image processing.

Abstract. Much attention is devoted to the design of multipliers as one of the most important arithmetic circuit. By allowing small but controllable computational error a efficient design of multiplier can be achieved. Although much work is done, leading inexact multiplier design strategies, truncated and logarithm multipliers, fail to meet requirements for chip area efficiency and computational error. Presentation introduces a novel design paradigm for inexact multiplier which combines the advantages of leading design strategies. On the top level, proposed strategy employs decomposed multiplier, where the least significant partial product is obtained by utilizing logarithm multiplier. This allows design of power efficient multiplier which characterize with small error performance. Error performance of proposed method is evaluated by conducting error analysis and comparing it with state-of-the-art multipliers. The results show potential for further development and application of a multiplier in neuro-computing hardware.

Design and Characterization of an Inductor and a Low-Noise Amplifier in Monolithic Integrated Circuit Technology for Wideband Operation

Dr Aleksandar Pajkanović

Faculty of Electrical Engineering
University of Banja Luka
aleksandar.pajkanovic@etf.unibl.org
Biography

Aleksandar Pajkanovic obtained his BSc (2009) and MSc (2012) at the Faculty of Electrical Engineering, University of Banja Luka and his PhD (2018) at the Faculty of Technical Sciences, University of Novi Sad. Over the eight years long career he worked both in industrial and academic environments in several countries. Currently he is employed as a teaching assistant at the Faculty of Electrical Engineering in Banja Luka, where he teaches several courses in electronics. His main area of research are design and analysis of RF/analog integrated circuits. He authored several papers in peer-review journals and dozens of conference papers.

Abstract. A passive inductive component and a low-noise amplifier are designed, fabricated in standard monolithic CMOS technology and characterized, both intended for wideband operation. For the design of the inductor, meander topology is chosen. Along with the integrated circuit design tools, electromagnetic field simulator is used. Besides the standard parameter characterization, special attention is dedicated to the analysis of process and temperature variations. Furthermore, mechanical characterization of the material that comprises the protection layer has been undertaken. Low-noise amplifier is designed as the first stage of an ultra wideband receiver and the results show that the circuit is successfully designed.

Expressive Speech Synthesis Based on Deep Neural Networks

Tijana Delić, ma

Faculty of Technical Sciences
University of Novi Sad, Serbia
tijanadelic@uns.ac.rs
Linkedin Biography

Tijana Delić is currently employed as a teaching assistant at the Faculty of Technical Sciences, University of Novi Sad, Serbia at the Chair of telecommunications and signal processing. She also cooperates closely with AlfaNum, a leading company in speech technologies in the region. Tijana is also a doctoral candidate at the Faculty of Technical Sciences, University of Novi Sad, Serbia. The main area of her research is speech synthesis based on neural networks with an accent on expressive speech. She authored several conference papers related to speech processing.

Abstract. Studies have shown that people already perceive the interaction with computers, robots and media in the same way as they perceive social communication with other people. For that reason it is critical for a high-quality text-to-speech system (TTS) to sound as human-like as possible. Even though synthetic voices are now intelligible and natural enough, they lack expression. Recent development of software and hardware increased the popularity of using artificial neural networks in many areas, including speech processing. One of the advantages of such methods in speech synthesis is the possibility to easily change speaker characteristics and speaking styles. The main approaches in the area will be presented, putting the accent on having a small amount of data which is typical for scarce languages.

ASR Recognition of Whispered Speech Based on Hidden Markov Models

Jovan Galić, ma

Faculty of Electrical Engineering
University of Banja Luka
jovan.galic@etf.unibl.org
Linkedin Biography

Jovan Galić is Ph.D. candidate in electrical engineering from School of Electrical Engineering, University of Belgrade, Serbia. He received his B.Sc. and M.Sc. degrees in electrical engineering from the Faculty of Electrical Engineering, University of Banja Luka, Bosnia and Herzegovina, in 2007. His research interests are focused in the areas of speech processing, speech enhancement, robust automatic speech recognition and compression of audio signals. He participated in a number of research projects supported by Ministry of Science and Technology of Republic of Srpska, Bosnia and Herzegovina.

Abstract. Due to the lack of sufficient amount of whisper data for training, whispered speech recognition is a serious challenge for state-of-the-art Automatic Speech Recognition (ASR) systems. Because of great acoustic mismatch between neutral and whispered speech, ASR systems are faced with significant drop of performance when applied to whisper. In this presentation, an analysis of neutral and whispered speech recognition based on Hidden Markov Models (HMM) framework, in a Speaker Dependent (SD) and Speaker Independent (SI) cases will be given. Special attention is paid to the neutral-trained recognition of whispered speech (N/W scenario). As well, advantages and disadvantages related to recognition based on SVM (Support Vector Machines), ANN (Artificial Neural Networks) and DTW (Dynamic Time Warping) techniques will be discussed.

Algorithmic Optimization of Transmission Parameters in IEEE 802.11 WLAN

Boris Malčić, ma

Faculty of Electrical Engineering
University of Banja Luka
boris.malcic@etf.unibl.org
Linkedin Biography

Boris Malčić was born in Banja Luka where he finished his BSc. and MSc. studies in the field of electronics and telecommunications at the Faculty of Electrical Engineering, University of Banja Luka. He is currently doing research in the field of radio communications, designs of new antennas, microwave techniques, design of PCB, and research in the field of IoT smart-city solutions.

Abstract. The main purpose of this research is to achieve a transmission optimization in real conditions of a dynamic environment. The optimization is based on an idea of mathematical modeling of data flow changes and spatial scheduling of clients in IEEE 802.11 WLAN. In order of existing state optimization in terms of reducing channel interference with energy-efficient work of WAPs in WLAN, new algorithms are proposed. Both algorithms (DCA and TCRFFA) make a unique proposal of the algorithm for the optimization. Also, an algorithm based solution for smart WLAN antenna is modelled in Matlab with a simple option of radio-localization in WLAN. Performed simulations have shown, that proposed solutions could lead to a decrease in EVM, improvements in QoS and transmissions at higher bit rates.

Data Aggregation for Advanced Communications in IEEE802.15.4e TSCH Wireless Sensor Networks

Dragan Vasiljević, MSc

Faculty of Electrical Engineering
University of Banja Luka
dragan.vasiljevic@mtel.ba
Biography

Dragan Vasiljević graduated at the Faculty of Electrical Engineering, Banja Luka, Bosnia and Herzegovina in 2002. In 2017. he received Master of Science degree at the same faculty. Since 2002. he is employee of Telecommunications of Republic of Srpska. He worked at various projects in area of mobile messaging services. Currently, he is doctoral student in telecommunications at Faculty of Electrical Engineering, Banja Luka. His research interests are Internet of Things applications, Wireless Sensor Network protocols and routing and embedded systems.

Abstract. Wireless Sensor Networks – WSNs have a wide range of applications. One of them are industrial applications. This field is of particular interest because it requires WSNs to have a high performance in terms of reliability, throughput and data transmission delay. The usage of frequency hopping technique, which increases resilience to interference and multi path fading, enables IEEE802.15.4e TSCH protocol to have potential to satisfy the criteria of industrial applications. OpenWSN is an open software platform which implements IEEE802.15.4e TSCH protocol together with other standardized protocols for WSN thus making entire protocol stack for WSN. Previous researches using OpenWSN platform showed that the key factor for performance of IEEE802.15.4e TSCH WSNs is timeslot scheduling at MAC (Medium Access Control) layer. For a certain scheduling, additional performance increase can be achieved using the technique of data aggregation at WSN nodes. This technique is applicable in conditions where an average packet size in WSN is significantly smaller than maximum possible packet size. Data aggregation technique provides higher throughput, congestion avoidance and decreases packet losses.