The combination of reinforcement learning and deep learning has shown some remarkable results in many scientific fields. Deep reinforcement learning algorithms are particularly good at understanding and modeling adaptive decision-making in dynamic environments. In recent years, this concept has been successfully applied to smart grids. In this paper, we provide a brief introduction to the concepts of reinforcement and deep reinforcement learning to the power system engineers and present research progress and prospects in the field. Additionally, we identify smart grid engineering domains that need extensive pattern-based modeling as being particularly suitable for deep reinforcement learning.

This paper addresses the use of deep learning techniques in 3D point cloud labeling of environment representations for the task of a semantic visual localization of mobile robots. In contrast to standard problems resolved with Convolutional Neural Networks (CNNs), the paper deals with applying CNNs to segment point clouds that are, unlike images, unordered and unstructured. The used point clouds contain laser measurements of 3D positions (x,y,z) as well as captured RGB camera images from the scanned scene to colorize the point cloud (RGB values). The main focus of the paper is on implementation and evaluation of a hand-crafted convolution layer and the ConvPoint CNN architecture that introduces continuous convolutions for point cloud processing. The solution was implemented in the Python programming language using the PyTorch deep learning framework.

The application of spectral analysis methods to the heart rate (HR) signal is challenging due to the nature of the signal itself, which is non-uniform. Methods for non-uniform signals can be applied directly, whilst the methods designed for uniform signals can be used after the signal is adequately preprocessed beforehand. Preprocessing consists of interpolation and resampling. In this paper, we have implemented a tool for explorative evaluation of various spectral analysis methods applied to HR signal. The tool is based on heat maps used for visualization of frequency metrics for the ECG signals selected from the MIT-BIH Arrhythmia Database. Evaluated methods are the Lomb-Scargle method for nonuniform signal analysis and Welch's method which is applied in conjunction with different interpolation approaches. A set of frequency-domain metrics are evaluated with the proposed tool for exploratory analysis. The evaluation indicates that the Lomb-Scargle method produces a loss of information in certain frequency bands. Furthermore, Welch method better demonstrates the difference in spectral power metrics for frequency bands of interest, irrespective of the type of interpolation used.

Hepatitis C is an inflammatory condition of the liver caused by the hepatitis C virus. Diagnosis of the disease itself is difficult because the incubation period is long, often the disease is initially without some characteristic symptoms, but also due to a lack of laboratory methods. Artificial intelligence is increasingly being used nowadays to make it easier and faster to assess the illness. As hepatitis C is a rising healthcare burden it is of utmost importance to construct effective and reliable screening methods. As AI has already proven useful for diagnosis of a variety of conditions based on clinical parameters, this study focuses on the application of artificial neural network (ANN) for hepatitis C diagnosis. In this study, a database of 1000 respondents divided into two groups was used to develop the ANN: healthy (n = 200) and sick (n = 800). Monitoring parameters were: albumin, alkaline phosphatase, alanine aminotransferase, aspartate aminotransferase, bilirubin, acetylcholinesterase and anti-HCV antibodies. The overall accuracy of the developed ANN was 97,78%, which indicates that the potential of artificial intelligence in diagnosing hepatitis C is enormous, and in the future, attention should be paid to the development of new systems with as much data as possible.

Background: In last 2 decades, there have been substantial changes in the utilization patterns of antihypertensive medicines following new clinical trials and the introduction of new treatment guidelines. The aim of this study was to analyze utilization and prescribing patterns regarding antihypertensive medicines in the Republic of Srpska, Bosnia and Herzegovina during an 11-years follow-up according to national and European treatment guidelines. Methods: In this retrospective, observational study, medicine utilization data were analyzed between 2009–2019 period using the ATC/DDD methodology and expressed as the number of DDD/1,000 inhabitants/day (DID/TID). The medicine utilization 90% (DU90%) method was used for determine the quality of prescribing. Results: During the observed period, the use of antihypertensive medicines increased more than 3-times (125.97 DDD/TID in 2009 vs 414.95 DDD/TID in 2019), corresponding to a rise in the prevalence of hypertensive patients from 91.7/1,000 to 186.3/1,000 in the same period. This was mainly driven by increased use of angiotensin converting enzyme inhibitors with 241.69%, beta blockers with 146.87%, calcium channel blockers with 251.55%, and diuretics with 178.95%. Angiotensin receptor blockers were the fastest growing group of antihypertensive medicines in this period and their utilization increased nearly 40 times. Conclusions: The overall antihypertensive medicines utilization was largely influenced by national and ESH/ESC guidelines and strongly corresponded to the positive medicine list of the national health insurance fund. Antihypertensive medicines utilization is comparable with medicine utilization trends in other countries.

The growing need for autonomous systems in offshore industries has contributed to the increased use of machine learning methods. These systems promise to improve safety in operations. However, the methods as enablers of autonomy are susceptible to various failures while interpreting data and making decisions. Several studies have highlighted the lack of research on the reliability and resilience of autonomous systems powered by these standard methods. Recent research provides sets of data interpretation methods. Despite the popularity of machine learning, there is a significant drop in knowledge when these methods result in failures. These failures further support autonomous systems in making wrong decisions. For autonomous systems, resilience and safety management should be an integrated functionality for recovery from risky situations and reporting of incidents. This research proposes an overview of machine learning methods for interpreting sensor data captured by drones operated manually and autonomously. We apply Isolation Forest for anomaly detection analysis and evaluate the Decision tree, Random forest, kNN, Logistic Regression, SVM, and, Naive Bayes for classification analysis. The methods are chosen based on their adequacy and comparative research prevalence. Comparison between the two drone operation modes contributes to understanding the reliability level for autonomously collected data. This research’s results provide an evaluation of machine learning methods’ performance across sensor data.

The growing penetration of renewable resources such as wind and solar into the electric power grid through power electronic inverters is challenging grid protection. Due to the advanced inverter control algorithms, the inverter-based resources present fault responses different from conventional generators, which can fundamentally affect the way that the power grid is protected. This paper studied solar inverter dynamics focused on negative-sequence quantities during the restoration period following a grid disturbance by using a real-time digital simulator. It was found that solar inverters can act as negative-sequence sources to inject negative-sequence currents into the grid during the restoration period. The negative-sequence current can be affected by different operating conditions such as the number of inverters in service, grid strength, and grid fault types. Such negative-sequence responses can adversely impact the performance of protection schemes based on negative-sequence components and potentially cause relay maloperations during the grid restoration period, thus making system protection less secure and reliable.

The paper analyzes the normative-formative framework that denotes the connection between memory and identity as a crucial origin of conflicts. In addition to concerns about memory politics, historical revisionism and ethnonational identity collectivism, the paper dissolves the connection between phenomena highlighting outcomes of the peace process, transitional justice, and its ethical/moral connotations. The study argues that Western Balkan’s sociopolitical stability depends on declining conflicting and contradictory memory order within radical sociopolitical processes. The revisionist contention memorializes conflicts and wars as the fundamental concept of ethnicity/religion/nation. It overlaps with the neoliberal and neoconservative reduction of all competitive relations, in which only the stronger have the right to existence. Discarding dominant ethnopolitical narratives is essential for conflict transformation and transitional justice for all ethnoreligious communities. The Balkan historical events and conflicting memory (WW2, Yugoslav wars) caused sociopolitical dominion shaping the collective behavior of ethnic groups. The damaging ethnic/religious practice of genocide denial and honoring war crimes within people’s social lives can become a matrix for future conflicts. Placing memory politics with radical populism is a critical condition of collective identity politics in the former Yugoslavia. Scientific rationality can provide a solid path through the anomalies in the form of political ideologies.

A modernidade tem trazido mudanças efetivas na sociedade. Com o advento da globalização e o avanço tecnolígico na área de comunicação as profissões sofrerão fortes mudanças no modus operandi ao longo do tempo e as legislações não tiveram essa mudança brisca respeitando essa mesma velocidade. Dado a isso, na área do transporte de passageiros não se furtou a isso, além dos conhecidos taxis, surgiram várias empresas de transporte de pessoas por aplicativo, onde motoristas disposibilizam seus carros para o transporte terceirizando seu serviço para operadoas desses aplicativos, Dentro desse viés a legislação vigente fala de responsabilidade subsidiada, porém a ausência de uma lei específica, a falta de jurisprudência atua e atualizada deixam lacunas nas leis para a tomada de descisões sobre a relação emprego e prestação de serviços desses motoristas de aplicativos. Sobre essas grandes mudanças não coabitaram com as novas demandas surgidas no campo trabalhista gerando confusão nas decisões e até mesmo trazendo certas dificuldades aos juristas nas decisões da criação de jurisprudência.Portanto, é preciso uma revisão bibliográfica, de forma a percepção de pareceres, um novo olhar legislativo, observando as nuances das escritas a fim de traçar parâmetros interpretativos para estabelecer conceitos sobre essa relação de emprego, onde não está claro o posicionamento de ambos, nem se quer o posicionamento da ordenação jurídica a esse respeito.

The aim of this paper is to analyse the influence of foliar application of a biostimulative fertilizer on some of the elements of raspberry fruit quality of the Polka variety. The research was conducted in 2015, according to the system of controls and treatment. Slavol VVL, a foliar fertilizer with biostimulating effects was applied for treatment. A total of 12 quantitative and qualitative properties were analyzed depending on the influencing factor, namely: total sugar content, reducing sugars, invert sugars, sucrose, water content, dry matter, total acidity, vitamin C, total phenols, total flavonoids and antioxidant capacity, and fruit weight. After the completed analyzes, it can be concluded that raspberry plants treated with Slavol VVL were characterized by the highest values ​​of total acidity (2.07%), dry matter (14.86%), and vitamin C content (25.15 mg/100 g of fresh weight).

The purpose of a network intrusion detection (NID) is to detect intrusions in the network, which plays a critical role in ensuring the security of the Internet of Things (IoT). Recently, deep learning (DL) has achieved a great success in the field of intrusion detection. However, the limited computing capabilities and storage of IoT devices hinder the actual deployment of DL-based high-complexity models. In this article, we propose a novel NID method for IoT based on the lightweight deep neural network (LNN). In the data preprocessing stage, to avoid high-dimensional raw traffic features leading to high model complexity, we use the principal component analysis (PCA) algorithm to achieve feature dimensionality reduction. Besides, our classifier uses the expansion and compression structure, the inverse residual structure, and the channel shuffle operation to achieve effective feature extraction with low computational cost. For the multiclassification task, we adopt the NID loss that acts as a better loss function to replace the standard cross-entropy loss for dealing with the problem of uneven distribution of samples. The results of experiments on two real-world NID data sets demonstrate that our method has excellent classification performance with low model complexity and small model size, and it is suitable for classifying the IoT traffic of normal and attack scenarios.

In this research the aim was to determine differences in morphological characteristics between 11 tomato accessions from the Gene Bank of the Republic of Srpska. The experiment was conducted and analysis was performed during the 2018 and 2019 seasons. A total of 16 morphological characteristics (9 quantitative and 7 qualitative) were analyzed according to International Plant Genetic Resources Institute (IPGRI) descriptors for tomato. The results showed that polymorphism (diversity) was present in all quantitative characteristics and in 6 qualitative characteristics, while only one qualitative characteristic was monomorphic (no differences between accessions). Thereby, polymorphism was present in 93.75% of morphological characteristics. Out of a total of 9 quantitative characteristics, a highly significant difference (p 0.01) was found in all characteristics except for the 1000-seed weight since this characteristic had only one value per accession measured according to the IPGRI tomato descriptors. The accessions from the Gene Bank of the Republic of Srpska have shown high diversity in all qualitative characteristics except in plant growth type, which was indeterminate in all analyzed accessions. This research provides a new insight into the research area of diversity of tomato landraces from the Republic of Srpska, which is important for further promotion and sustainable use of germplasm not only for scientific research purposes but also for national rural farmers, who are the key to preserving traditional knowledge and skills related to the cultivation and use of traditional varieties and tomato landraces.

Abstract Background Specialty training in plastic, reconstructive and aesthetic surgery is a prerequisite for safe and effective provision of care. The aim of this study was to assess and portray similarities and differences in the continuing education and specialization in plastic surgery in Europe. Material and Methods A detailed questionnaire was designed and distributed utilizing an online survey administration software. Questions addressed core items regarding continuing education and specialization in plastic surgery in Europe. Participants were addressed directly via the European Leadership Forum (ELF) of the European Society of Plastic, Reconstructive and Aesthetic Surgery (ESPRAS). All participants had detailed knowledge of the organization and management of plastic surgical training in their respective country. Results The survey was completed by 29 participants from 23 European countries. During specialization, plastic surgeons in Europe are trained in advanced tissue transfer and repair and aesthetic principles in all parts of the human body and within several subspecialties. Moreover, rotations in intensive as well as emergency care are compulsory in most European countries. Board certification is only provided for surgeons who have had multiple years of training regulated by a national board, who provide evidence of individually performed operative procedures in several anatomical regions and subspecialties, and who pass a final oral and/or written examination. Conclusion Board certified plastic surgeons meet the highest degree of qualification, are trained in all parts of the body and in the management of complications. The standard of continuing education and qualification of European plastic surgeons is high, providing an excellent level of plastic surgical care throughout Europe. Zusammenfassung Hintergrund Die Facharzt-Weiterbildung für Plastische und Ästhetische Chirurgie ist eine Grundvoraussetzung für sichere und effektive Patientenversorgung. Ziel der vorliegenden Studie war die Darstellung von Gemeinsamkeiten und Unterschieden in der Weiterbildung für Plastische Chirurgie innerhalb von Europa. Materialien und Methoden Ein internetbasierter Fragebogen wurde mit Hilfe eines kostenlosen Formularerstellungstools erstellt und verteilt. Die Fragen betrafen Kernpunkte der Weiterbildung für Plastische Chirurgie in Europa. Die Teilnehmer wurden direkt über das European Leadership Forum (ELF) der European Society of Plastic, Reconstructive and Aesthetic Surgery (ESPRAS) kontaktiert. Alle Teilnehmer hatten weitreichende Kenntnisse über die Organisation und Struktur der plastisch-chirurgischen Weiterbildung in ihrem jeweiligen Land. Ergebnisse 29 Teilnehmer*innen aus 23 europäischen Ländern nahmen an der Umfrage teil. Die Weiterbildung für Plastische Chirurgie beinhaltet grundlegende Prinzipien und Techniken zur Wiederherstellung von Form und Funktion innerhalb der verschiedenen Säulen der Plastischen Chirurgie, sowie in allen Körperregionen. In den meisten europäischen Ländern ist eine Rotation in der Intensiv- und Notfallmedizin und die Behandlung kritisch kranker Patienten obligatorisch. Voraussetzung für die Facharztbezeichnung ist die mehrjährige, national organisierte Weiterbildung, der Nachweis einer festgelegten Anzahl selbstständig durchgeführter Operationen, sowie die mündliche und/oder schriftliche Abschlussprüfung. Schlussfolgerung Fachärzte für Plastische und Ästhetische Chirurgie sind hochqualifiziert und auch im Umgang mit Komplikationen geschult. Der Standard der Weiterbildung der europäischen Plastischen Chirurgen ist hoch, so dass innerhalb Europas eine hohe Qualität plastisch-chirurgischer Versorgung gewährleistet ist.

Background Pharmacogenomics (PGx) testing can reduce toxicities and improve efficacy of several drugs used to treat cancer and associated symptoms. PGx results can be determined from germline whole-exome sequencing (WES), but somatic mutations may cause discordance between tumor and germline DNA. Since clinical diagnostic sequencing in oncology frequently only includes tumor DNA, there would be clinical value in calling germline PGx genotypes from tumor DNA. Thus, the purpose of this study was to assess the feasibility of using somatic WES data to call germline PGx genotypes. Methods Germline and somatic WES data were obtained as part of the clinical workflow for 64 patients treated at the solid molecular tumor board clinic at Indiana University. Aldy v3.3 was implemented in LifeOmic’s Precision Health Cloud™ to call PGx genotypes from somatic WES. Somatic Aldy calls were compared with previously validated Aldy germline calls for 8 genes: CYP2C9, CYP2C19, CYP2D6, CYP3A4, CYP3A5, CYP4F2, DPYD, and TPMT. Somatic read depth was >100x, except for the intronic CYP3A4*22 variant, which was >30x. Results Somatic and germline Aldy calls were compared for a total of 512 genotypes and 56 (11%) calls were discordant. Discordant calls were most common for CYP2B6 (23.4%), followed by CYP2D6 (14.1%), CYP2C19 (10.9%), CYP2C8 (6.3%), and DPYD (6.3%). In contrast, all Aldy calls were concordant for CYP3A5 and TPMT. 38 out of 64 subjects (59%) had discordant calls for at least one gene. The most common first cancer diagnoses in our cohort were colorectal (9.3%), breast (7.8%), and pancreatic (7.8%), and the rates of discordant Aldy calls did not differ by cancer type (p>0.05 for all cancer types). Based on our analyses of discordant calls, we anticipate that adjusting Aldy’s thresholds for variant calling may allow Aldy to determine genotypes from somatic WES data. Conclusion In most cases, genotype calls of drug metabolism genes from tumor DNA reflected the germline genotypes; however, additional work needs to be done to determine if the remaining discordant calls can be corrected by modifying the informatics tools or if they are due to somatic mutations. Citation Format: Wilberforce A. Osei, Tyler Shugg, Reynold C. Ly, Steven M. Bray, Benjamin A. Salisbury, Ryan R. Ratcliff, Victoria M. Pratt, Ibrahim Numanagić, Todd Skaar. Pharmacogenomics genotyping from clinical somatic whole exome sequencing: Aldy, a computational tool [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr 1151.