In this note, we study the stability of the error dynamics of an observer designed to estimate only the slow states of a singularly perturbed system. The observer is designed on the basis of the reduced (slow) model. We have recently reported semi-global practical results for this problem. Our previous work can be used to state local and regional convergence of the estimation error, but we cannot conclude global results from it. We seek to prove a stronger (global) result under stronger (global) assumptions in this manuscript. Moreover, we focus on proving the robustness of an observer with respect to singular perturbations and with respect to the measurement noise.

Many industrial domains are characterized by Multiple-Input-Multiple-Output (MIMO) systems for which an explicit relationship capturing the nontrivial trade-off between the competing objectives is not available. Human experts have the ability to implicitly learn such a relationship, which in turn enables them to tune the corresponding controller to achieve the desirable closed-loop performance. However, as the complexity of the MIMO system and/or the controller increase, so does the tuning time and the associated tuning cost. To reduce the tuning cost, a framework is proposed in which a machine learning method for approximating the human-learned cost function along with an optimization algorithm for optimizing it, and consequently tuning the controller, are employed. In this work the focus is on the tuning of Model Predictive Controllers (MPCs), given both the interest in their implementations across many industrial domains and the associated high degrees of freedom present in the corresponding tuning process. To demonstrate the proposed approach, simulation results for the tuning of an air path MPC controller in a diesel engine are presented.

2Univerzitet of Tuzla, School of Medicine, Tuzla, Bosnia and Herzegovina KeYWORdS: myocardial infarction, exercise training, cardiovascular rehabilitation. citAtiON: Cardiol Croat. 2018;13(11-12):416. | https://doi.org/10.15836/ccar2018.416 *AddReSS fOR cORReSpONdeNce: Emir Bećirović, JZU Univerzitetski klinički centar Tuzla, Klinika za interne bolesti, Prof. dr Ibre Pasica, 75 000 Tuzla, Bosnia i Herzegovina. / Phone: +387-61-876-152 / E-mail: becirovic.emir@live.com ORcid: Emir Becirovic, https://orcid.org/0000-0002-4134-987X • Ammar Brkic, https://orcid.org/0000-0002-5436-3670 Esad Brkic, https://orcid.org/0000-0002-7784-328X • Tarik Brkic, https://orcid.org/0000-0003-2054-2571 Ermina Mujanovic, https://orcid.org/0000-0001-8154-586X • Amir Becirovic, https://orcid.org/0000-0002-7012-8064 Semir Hadzic, https://orcid.org/0000-0002-3308-8331 • Amila Jasarevic, https://orcid.org/0000-0003-4861-6683 Majda Skokic, https://orcid.org/0000-0001-5913-1863 • Esref Becirovic, https://orcid.org/0000-0003-3759-7878

ORcid: Emir Becirovic, http://orcid.org/0000-0002-4134-987X • Ammar Brkic, http://orcid.org/0000-0002-5436-3670 Esad Brkic, http://orcid.org/0000-0002-7784-328X • Amira Kusljugic, http://orcid.org/0000-0003-4537-4615 Edita Sijercic, http://orcid.org/0000-0001-5926-7226 • Hazim Tulumovic, http://orcid.org/0000-0002-0662-5576 Denis Mrsic, http://orcid.org/0000-0002-6736-9561 • Daniela Loncar, http://orcid.org/0000-0001-8186-1766

Accurate and easy to perform high voltage circuit breakers condition assessment is of crucial importance for the reliability of the overall power system. This paper presents the concept of the designed and developed embedded and handheld system for the timing measurement of the high voltage circuit breaker performed in online mode with the focus on the "first-trip" test.

One of the effective strategies for increasing reliability of the distribution networks is to perform a faster fault localization. The common techniques for accelerating the process of finding the faults are based on application of fault locators and fault passage indicators. The goal of this study is to assess the performance of both techniques, either considered separately or in combination with each other. Since the performance of both concepts depends on various stochastic variables, a comprehensive assessment methodology developed in this paper is based on the non-sequential Monte Carlo simulation.

In this paper a methodology for determining proper number and positions of fault passage indicators (FPIs) in medium voltage distribution networks with installed fault locators (FLs) is proposed and discussed. The main goal is to achieve the techno-economic balance, by obtaining maximum improvement of the reliability indices while using the minimum number of FPIs. The method is verified by Monte Carlo simulation on a real combined urban/rural distribution network in Bosnia and Herzegovina. The purpose of the simulation tests is to assess performance of the proposed methodology, as well as to discuss the results and propose potential actions required to improve their reliability for several possible scenarios: the use of FLs only, the use of FPIs only and the combined use of FLs and FPIs.

Clinical diagnosis of early melanoma (Breslow thickness less than 0.8 mm) is crucial to disease-free survival. However, it is subjective and can be exceedingly difficult, leading to missed melanomas, or unnecessary excision of benign pigmented skin lesions. An objective technique is needed to improve the diagnosis of early melanoma. We have developed a method to improve diagnosis of (thin) melanoma, based on Raman spectroscopy. In an ex vivo study in a tertiary referral (pigmented lesions) centre, high-wavenumber Raman spectra were collected from 174 freshly excised melanocytic lesions suspicious for melanoma. Measurements were performed on multiple locations within the lesions. A diagnostic model was developed and validated on an independent data set of 96 lesions. Approximately 60% of the melanomas included in this study were melanomas in situ. The invasive melanomas had an average Breslow thickness of 0.89 mm. The diagnostic model correctly classified all melanomas (including in situ) with a specificity of 43.8%, and showed a potential improvement of the number needed to treat from 6.0 to 2.7, at a sensitivity of 100%. This work signifies an important step towards accurate and objective clinical diagnosis of melanoma and in particular melanoma with Breslow thickness <0.8 mm.

1Sarajevo School of Science and Technology, Sarajevo, Bosnia and Herzegovina 2University Clinical Center Sarajevo, Sarajevo, Bosnia and Herzegovina KeYWORdS: natriuretic peptides, brain natriuretic peptide, biomarker of myocardial infarction, Alzheimer’s disease. citAtiON: Cardiol Croat. 2018;13(11-12):435. | https://doi.org/10.15836/ccar2018.435 *AddReSS fOR cORReSpONdeNce: Edin Begic, Sarajevo School of Science and Technology, Sarajevo Medical School, Department of Pharmacology, Hrasnicka cesta 3a, 71000 Sarajevo, Bosnia and Herzegovina. / Phone: +38761303375 / E-mail: edinbegic90@gmail.com ORcid: Edin Begic, https://orcid.org/0000-0001-6842-262X • Suncica Hadzidedic, https://orcid.org/0000-0001-9026-8737 Ajla Kulaglic, https://orcid.org/0000-0003-3410-7079 • Belma Ramic-Brkic, https://orcid.org/0000-0002-8205-0137 Zijo Begic, https://orcid.org/0000-0002-1863-5755 • Mirsada Causevic, https://orcid.org/0000-0002-6099-6415

The past decade was marked, among other things, by the rapid growth of social networks. These networks collect personal data about their users - their photographs, interests, friends, locations, website visits, clicks, status updates and much more. A large number of users and a big collection of various data collected about the users make social media networks an abundant source of data that can be analyzed and used for targeted marketing, social phenomena analysis, generating different statistics and so on. In this paper we will use the potential of the tool RapidMiner in order to collect data from the social media network Twitter using the AYLIEN extension, preparing the data and applying sentiment analysis, which will give insight into the general atmosphere surrounding the actions of the current USA president Donald Trump

Post-traumatic stress disorder (PTSD) is a common and debilitating disorder. The risk of PTSD following trauma is heritable, but robust common variants have yet to be identified by genome-wide association studies (GWAS). We have collected a multi-ethnic cohort including over 30,000 PTSD cases and 170,000 controls. We first demonstrate significant genetic correlations across 60 PTSD cohorts to evaluate the comparability of these phenotypically heterogeneous studies. In this largest GWAS meta-analysis of PTSD to date we identify a total of 6 genome-wide significant loci, 4 in European and 2 in African-ancestry analyses. Follow-up analyses incorporated local ancestry and sex-specific effects, and functional studies. Along with other novel genes, a non-coding RNA (ncRNA) and a Parkinson’s Disease gene, PARK2, were associated with PTSD. Consistent with previous reports, SNP-based heritability estimates for PTSD range between 10-20%. Despite a significant shared liability between PTSD and major depressive disorder, we show evidence that some of our loci may be specific to PTSD. These results demonstrate the role of genetic variation contributing to the biology of differential risk for PTSD and the necessity of expanding GWAS beyond European ancestry.