IFAC PapersOnLine 52-27 (2019) 520–523 ScienceDirect Available online at www.sciencedirect.com 2405-8963 © 2019, IFAC (International Federation of Automatic Control) Hosting by Elsevier Ltd. All rights reserved. Peer review under responsibility of International Federation of Automatic Control. 10.1016/j.ifacol.2019.12.716 © 2019, IFAC (International Federation of Automatic Control) Hosting by Elsevier Ltd. All rights reserved. 1. INTRODUCTION A part of cognitive disorders does not have a disease entity in ICD (International Classification of Disorders) despite continuous replenishment of ICD. In 2022, ICD-11 will be released World Health Organization (2019). Working memory and short-time memory determine our cognitive abilities and influence the quality of functioning and cognitive tasks. In elderly people this memory is worse, which correlates with age and young people (and children) have the greatest cognitive abilities. Research shows that also pregnant women have decreased cognitive processes. Most likely, it is related to the levels of estrogen and progesterone. Such outcome have been proven by tests on mice during pregnancy CabreraPedraza et al. (2017); Hampson (2018). In addition, the reduction of Alpha frequencies can be used in the Brain Computer Interfaces Wan et al. (2016); Reis et al. (2016). 1.1 EEG Analysis in BCI Systems When using BCI with EEG signals, to obtain a response, it is necessary to have standard patterns to detect changes and anomalies. The analyzed brain waves describing our states should correspond to the Event Related Potential (ERP). The main problems with this connection are: high accuracy, time, noise and values that stick out Lotte et al. (2018); Blankertz et al. (2011). Understanding the pat- terns of ”brainwaves” helps in development of faster, more stable BCI. The learning process of these EEG models is based on the search for characteristic things, such as values or system responses ERP. Therefore, it is very important to develop new methods of signal analysis. Nu- merous publications describing methods of signal analysis and differences between a healthy and pathological EEG signal appear for this purpose Chaudhary et al. (2017); Molla (2018); Wang et al. (2015). 2. MATERIALS AND METHODS For recording of the EEG signal in edf format the first author of this paper decided to use quantitative EEG (QEEG). EEG was placed above the area of the motor cortex on the following locations: Fz, C3, C4 and Cz – in accordance with the 1020 system Homan et al. (1987). Figure 1 shows 10-20 system with marked motor cortex area and the electrodes’ locations. Keywords: EEG, neurofeedback, BCI, algoritms. Abstract: Thanks to the automation of diagnostic processes based on the EEG signal and the creation of classifications of various attention disorders based on the analysis of the EEG signals (as diagnostic markers) – it may be possible to refer patients to appropriate specialists and provide them with appropriate neurofeedback-based treatment. The marker method proposed by the authors of the hereof paper is based on analysis of the EEG, which signal can be widely use in screening diagnostics. The proposed solution in this work may be used for neurofeedback or Brain Computer Interfaces (BCI). In this paper the authors presented implementation of markers for the purpose of analysis of some memory disorders and short-time attention disorder. The study is still in progress. Presented results have initial-study character. * Opole University of Technology – Faculty of Electrical Engineering, Automatic Control and Informatics ul. Proszkowska 76, 45-758 Opole, Poland (e-mail: kawala84@gmail.com, magdazolubak@gmail.com, m.podpora@po.edu.pl) ** West Pomeranian University of Technology in Szczecin – Faculty of Electrical Engineering, ul. Sikorskiego 37, 70-313 Szczecin, Poland (e-mail: Wojciech.Chlewicki@zut.edu.pl, Katarzyna.Cichon@zut.edu.pl). *** University of Greenwich – Department of Computing and Information Systems – Faculty of Architecture, Computing and Humanities Old Royal Naval College, Park Row, SE10 9LS London, UK (e-mail: m.pelc@greenwich.ac.uk) Magda Zolubak * Mariusz Pelc *,*** Michal Podpora * Wojciech Chlewicki ** Katarzyna Cichon ** Aleksandra Kawala-Sterniuk * Application of Cognitive Changes Markers for Diagnostics’ Purposes and in Neurofeedback Therapy