Peter Lacko

• PhD
• Professor (Assistant) at Slovak University of Technology in Bratislava

In this paper, we present neural models submitted to Shared Task on Implicit Emotion Recognition, organized as part of WASSA 2018. We propose a Bi-LSTM architecture with regularization through dropout and Gaussian noise. Our models use three different embedding layers: GloVe word embeddings trained on Twitter dataset, ELMo embeddings and also sente...

The prediction of electricity consumption has become an important part of managing the smart grid. Smart grid management involves energy production (from traditional and renewable sources), transportation and measurements (smart meters). Storing large amounts of electrical energy is not possible, therefore it is necessary to precisely predict energ...

Deep neural networks are intensively researched field of artificial intelligence. Big companies like Google, Microsoft, Baidu or Facebook are supporting research and development in this field. The recent victory over human player in the game of Go points to a huge potential of this approach. Machine learning approaches based on deep learning techni...

The main goal of the paper is to present the method of design pattern support based on principles of model driven development: the abstraction, semantics and model transformations. More specifically, the method is based on the principle of suggestion of design pattern instances via the semantic marking of model elements or source code fragments and...

Ensemble learning is one of the machine learning approaches, which can be described as the process of combining diverse models to solve a particular computational intelligence problem. We can find the analogy to this approach in human behavior (e.g. consulting more experts before taking an important decision). Ensemble learning is advantageously us...

The complexity of certain problems causes that classical methods for finding exact solutions have some limitations. In this paper we propose an incremental heterogeneous ensemble model for time series prediction where biologically inspired algorithms offer a suitable alternative. Ensemble learning techniques are advantageously used for improving pe...

The efforts of the European Union (EU) in the energy supply domain aim to introduce intelligent grid management across the whole of the EU. The target intelligent grid is planned to contain 80% of all meters to be smart meters generating data every 15 minutes. Thus, the energy data of EU will grow rapidly in the very near future. Smart meters are s...

Human behavior simulation is a challenging task because its nature and the variables affecting it are still unknown. However such simulations play important role in various fields, including army, police training, architecture, emergency exits design etc. In this paper we present a complex simulation of crowd based on the PECS psychological model....

With the increase in the amount of data processing the importance of distributed computational systems is rising. The efficiency of the task scheduling algorithms used in distributed computational systems is one of the major challenges for the architecture of such systems. This paper presents and introduces a new task scheduling algorithm suggested...

Many of software engineering tools and systems are focused to monitoring source code quality and optimizing software development. Many of them use similar source code metrics to solve different kinds of problems. This inspired us to propose an environment for platform independent code monitoring, which supports employment of multiple software devel...

Simulation of human behavior in various situations is nowadays heavily used in miscellaneous research fields (e.g. emergency exits design, psychology, riot or humanitarian help simulation). The Holy Grail is to identify key elements of human beings that drive our behavior and be able to sufficiently simulate them and replicate in artificial compute...

The paper proposes an approach for predicting application upgrade time that is being upgraded from one version to another. The focus is primarily concentrated on applications with upgrades consisting mainly of upgrading the relational database. Chosen application databases have the same schema but the content of tables varies. Data from the upgrade...

Transactional memory is a rather novel approach to concurrency control in parallel computing, that has just recently found its way into distributed systems research. However, the research concentrates mainly on single processor solutions or cluster environment. In this paper we argue, that peer-to-peer systems would require a different design of tr...

In this paper, we study an emergence of game strategy in multiagent systems. Symbolic and subsymbolic approaches are compared. Symbolic approach is represented by abacktrack algorithm with specified search depth, whereas the subsymbolic approach is represented by feed-forward neural networks that are adapted by reinforcement temporal difference TD(...

Several authors have reported interesting results ob- tained by using untrained randomly initialized recurrent part of an recurrent neural network (RNN). Instead of long, difficult and often unnecessary adaptation process, dynam- ics based on fixed point attractors can be rich enough for further exploitation for some tasks. The principle explain -...

In this paper, we study an emergence of game strategy in multiagent systems. Symbolic and subsymbolic approaches are compared. Symbolic approach is represented by a backtrack algorithm with specified search depth, whereas the subsymbolic approach is represented by feedforward neural networks that are adapted by reinforcement temporal difference TD(...

In health-care, it is very important to have simultaneous access to dierent data on the patient, such as his/her case history, medical history or undergone surgeries. The data is usually stored in the hospital information system. This paper describes design of a system called BlueMedica, which provides the mobile access to data stored in the hospit...