Hrčak - Portal of scientific journals of Croatia
Not a member yet
321498 research outputs found
Sort by
Hybrid Black Widow Combined Seagull Optimization with Deep Learning for Efficient Road Classification in UAV-Aided Intelligent Transportation Systems
No full textUnmanned Aerial Vehicles (UAVs) are pivotal in Intelligent Transportation Systems (ITS) for smart cities, enabling interconnected and autonomous vehicle networks. UAVs enhance ground vehicles by establishing efficient wireless connections and aiding in real-time road monitoring. Artificial Intelligence (AI) and Machine Learning (ML) optimize UAV operations, including dynamic control, path planning, and environmental perception. Deep Learning (DL), particularly Convolutional Neural Networks (CNNs), excels in detection tasks, making it ideal for UAV-based road classification.This study proposes a Hybrid Black Widow Combined Seagull Optimization with Deep Learning-based Classification (HBWCSO-DLC) algorithm to improve road classification accuracy. The HBWCSO-DLC integrates Black Widow Optimization (BWO) and Seagull Optimization (SOA) to enhance feature selection and CNN performance. Evaluated on a road image dataset, HBWCSO-DLC achieves 99.48% accuracy, 98.69% sensitivity, 99.67% specificity, and a 98.69% F1-score, outperforming existing methods like MODAE-RCM, Adam, and SGD. The hybrid optimization ensures robust convergence, while the CNN architecture adapts to complex road textures captured by UAVs.The results demonstrate HBWCSO-DLC's superiority in ITS applications, including autonomous driving and safety systems. This work provides a scalable solution for UAV-assisted road classification, combining bio-inspired optimization with deep learning for real-time, high-precision outcomes
Unexpected abnormal flotation of gel separator in tube of post dialysis samples: a case report highlighting the critical role of sampling site selection
No full textProper preanalytical handling of blood samples is critical to ensure the reliability of laboratory results, particularly in patients undergoing hemodialysis, where biochemical monitoring is essential for assessing dialysis adequacy and guiding treatment decision. We reported three cases of abnormal post-dialysis gel separator flotation in blood collection tubes from patients undergoing hemodiafiltration: in each case, the gel migrated to the top of the tube, with plasma trapped below and blood cells remaining at the bottom. Marked hyperproteinemia and hypercalcemia were observed in the plasma, inconsistent with the patient’s clinical status and pre-dialysis values. These findings raised suspicion of a preanalytical error potentially associated with the hemodialysis procedure. On-site investigations conducted in collaboration with the dialysis center for four additional patients, combined with a better understanding of the principles of hemodiafiltration and the potential sampling sites, confirmed that the gel migration anomaly was secondary to unsuitable sampling from the venous line (outflow line) of the dialysis circuit instead of the arterial one (inflow line). In conclusion, we highlighted the critical role of adhering to the appropriate sampling site when performing post-dialysis blood tests: the arterial line was identified as the appropriate site for post-dialysis blood sampling, while the venous line should be reserved exclusively for infusion or reinjection purposes and must never be used for blood collection at the end of dialysis
Performance enhancement of Savonius hydrokinetic turbines: the role of twisted blade profiles
Get PDFSavonius Hydrokinetic Turbines (SHTs) are widely recognized for their simplicity, cost-effectiveness, and adaptability to slow flow conditions. However, conventional SHT designs face limitations, including low efficiency and significant torque fluctuations. The adoption of twisted/helical blade profiles has emerged as a potential solution to enhance turbine performance by reducing torque fluctuations and improving power output. A review of the existing literature reveals that studies focusing on blade twist angles are limited. To address this, the present study systematically investigates the impact of a broader range of blade twist angles (15-90°) on SHT performance using computational fluid dynamics (CFD). Key performance metrics, including the torque coefficient (CT) and power coefficient (CP), were evaluated, and numerical accuracy was ensured through mesh independence and time step independence studies. The developed CFD model was validated against experimental results obtained from the literature to confirm the model’s ability to capture flow dynamics. The results show that the SHT with a 45° blade twist achieves a maximum CP of 0.252, an increase of 3.81 % over the conventional design, and reduces torque fluctuations by 9.38 %. Meanwhile, the 60° blade twist demonstrates comparable CP values but achieves a further 7.28 % reduction in torque fluctuations compared to SHTs with a 45° blade twist.Savonius Hydrokinetic Turbines (SHTs) are widely recognized for their simplicity, cost-effectiveness, and adaptability to slow flow conditions. However, conventional SHT designs face limitations, including low efficiency and significant torque fluctuations. The adoption of twisted/helical blade profiles has emerged as a potential solution to enhance turbine performance by reducing torque fluctuations and improving power output. A review of the existing literature reveals that studies focusing on blade twist angles are limited. To address this, the present study systematically investigates the impact of a broader range of blade twist angles (15-90°) on SHT performance using computational fluid dynamics (CFD). Key performance metrics, including the torque coefficient (CT) and power coefficient (CP), were evaluated, and numerical accuracy was ensured through mesh independence and time step independence studies. The developed CFD model was validated against experimental results obtained from the literature to confirm the model’s ability to capture flow dynamics. The results show that the SHT with a 45° blade twist achieves a maximum CP of 0.252, an increase of 3.81 % over the conventional design, and reduces torque fluctuations by 9.38 %. Meanwhile, the 60° blade twist demonstrates comparable CP values but achieves a further 7.28 % reduction in torque fluctuations compared to SHTs with a 45° blade twist
Robust trajectory tracking of surface vessels in ice floe sea state via discrete integral sliding-mode control and Gaussian process regression
Get PDFBy considering the disturbance caused by ice floes in polar regions, the trajectory tracking control problem for uncertain unmanned surface vessels (USVs) is investigated in this paper. USVs for trajectory tracking missions in polar regions are required to not only overcome common disturbances and perturbations such as model uncertainties and environmental disturbances caused by winds, waves and currents, but it must also consider the stochastic resistance generated by ice floes. However, studies on the stochastic model of ice floes resistance on USVs are insufficient, making it difficult to a design tracking controller. This paper proposes a discrete integral sliding-mode control (DISMC) with a disturbance observer based on Gaussian process regression (GPR) technique, which could steer uncertain USVs to track predefined trajectories under disturbance without knowing its upper bound. Compared to the existing methods for USV control, (1) to the best of our knowledge, this study is among the first to address the trajectory tracking control problem of USVs in ice-floe sea conditions; (2) a novel fully data-driven disturbance observer is proposed that approximates the mean and autocorrelation function of the lumped uncertainties without requiring prior knowledge about the stochastic ice resistance; and (3) a novel DISMC given the autocorrelation function of uncertainties instead of the uncertain upper bound is proposed and proved to be stable with a probability of 1. The proposed method offers a significant approach for controlling USVs in ice-covered sea areas
Sponzorski kutak: Pregled proizvoda/opreme (Ru-Ve – BANDELIN, visokoučinkovite ultrazvučne kupke spulsirajućim vakuumom)
Get PDFOsvrti: Osvrt na okrugli stol “Kemija u doba umjetne inteligencije: inovacije, suradnje i izazovi” održan tijekom konferencije HKD-a
Get PDFWater Harvesting Pits on Forest Roads – Perspectives? A Case Study in the Czech Republic
Get PDFGiven the ongoing climate warming that can lead to water scarcity, water retention has been on the forefront of forest ecosystem services. Water harvesting pits on forest roads are one of the possible engineering measures that can help mitigate some of the negative impacts forest roads have on the hydrological regime of the forest ecosystem. The aim of the research is to inform the scientific and professional public about the function and potential of water harvesting pits under forest road culverts and to offer insight into the significance of expected benefits of these objects for water retention and improvement of forest stand hydrological conditions. In this study, standard engineering methods were used to design and build water harvesting pits connected and not connected to culvert mouths and to equip the whole surrounding area with soil moisture and water level sensors. During the two-year study period, a number of irrigation experiments were also performed. The goal was to observe and evaluate the distribution of water from the pits to the surrounding soil and forest stands. Even though water harvesting pits and similar water retention objects on the forest road network seem very beneficial on paper, data from our research does not fully support it. According to our results, the benefits obtained seem much smaller than originally expected to a point that the viability of such measures is probably very low both from the forest stand and water management standpoint. More research is definitely needed in a wider variety of conditions and with a longer time frame
Comparative assessment of flexible manufacturing systems using the EDAS and Shannon entropy method
Get PDFAs global competition intensifies, most manufacturing companies strive to improve their production methods to gain a competitive edge. One such advancement is the adoption of Flexible Manufacturing Systems (FMS), which enable the efficient production of various products in specified quantities with minimal lead times. These systems offer adaptability and efficiency, allowing manufacturers to leverage modern technologies to improve operational performance. However, evaluating or selecting an appropriate FMS involves considering numerous conflicting criteria. To address this complexity, Multi-criteria Decision Making (MCDM) methods are employed. This study conducts a comparative evaluation of eight FMS alternatives using the Evaluation based on the Distance from the Average Solution (EDAS) method, integrated with Shannon Entropy for objective weight determination. Key performance indicators, including production cost, system flexibility, energy efficiency, and operational reliability, are used in the assessment. The Shannon Entropy method ensures unbiased, data-driven weight assignment, while the EDAS method provides a robust framework for ranking alternatives based on their deviation from an average solution. To test the robustness of the ranking, we compared the ranking with other MCDM methods and also conducted a sensitivity analysis using equal weighting criteria. We found that the first and last rankings remained unchanged when we changed the criteria, although there were slight changes in the rankings of some alternatives. The findings highlight the effectiveness of integrating EDAS with Shannon Entropy in selecting the best flexible manufacturing systems, offering valuable insights for manufacturers and decision-makers
DETERMINANTS AND ACHIEVEMENTS OF KNOWLEDGE TRANSFER AND KNOWLEDGE SHARING IN PUBLIC HEALTH INSTITUTIONS IN THE REPUBLIC OF CROATIA - EMPIRICAL ANALYSIS
No full textIn the post-Covid era, individual health and well-being have become key priorities. The theme of the 2025 HLPF Conference confirms this by prioritizing several UN SDG sustainable development goals, particularly Goal 3 – Ensuring healthy lives and promoting well-being for all at all ages. The Integrated Health Care (IHC) principle provides a forward-thinking, holistic approach that prioritizes the patient as the central point of the healthcare system, emphasizing recovery and overall well-being rather than solely medical treatment. This concept integrates various aspects of patient care, including social, technological, and other relevant health elements, creating a comprehensive framework for improving health outcomes. Implementing IHC principles requires strategic management of partnership networks involving medical institutions, universities, healthy food producers, medical technology developers, and other stakeholders. Knowledge management within these networks is a critical process that ensures instant information, e.g. knowledge transfer. Literature highlights the benefits of these networks, such as reliability, security, scalability, and cost savings.This study investigates the extent of knowledge sharing and knowledge transfer among healthcare professionals working in public health institutions in Croatia. The authors have been using a quantitative method with a smaller sample, surveying healthcare professionals based on Liebowitz's model (2018), which analyzes key institutional factors influencing knowledge transfer in healthcare institutions, such as organizational culture, processes, and management support. The findings identified key opportunities and barriers for improving knowledge transfer in healthcare institutions in Croatia. Based on these results, the authors will propose guidelines for optimizing knowledge transfer processes in healthcare institutions. This research will encourage further scientific discussions and analyses on the topic, initiating strategic guidelines, project initiatives, and best practices in this critical field - global health
Labor Pain Perception: a Narrative Literature Review
No full textAim: Labor pain is one of the most intense and complex painful experiences, yet its perception varies widely among women. Traditional explanations based solely on nociceptive mechanisms are insufficient to account for these interindividual differences. Therefore, this review aims to summarize current evidence on the physiological, psychological, and genetic factors influencing labor pain perception, in order to better understand individual variability. Materials and Methods: A narrative review of the literature was conducted using recent peer-reviewed studies retrieved from PubMed, Scopus, and Web of Science. Articles exploring physiological mechanisms, psychological influences, and genetic polymorphisms associated with labor pain were included. Results: Labor pain arises from the interaction of nociceptive mechanisms, genetic variability (e.g., SERT, OPRM1, COMT polymorphisms), and psychological factors such as trait and state anxiety, fear of childbirth, coping strategies, and expectations. Social determinants, including prenatal education, partner and healthcare support, and cultural context, further modulate pain perception. Evidence supports significant gene–environment interactions, where genetic predispositions are amplified or buffered by psychological states and environmental influences. Conclusion: Labor pain is best understood within a bio-psychosocial framework that integrates biological vulnerability, emotional regulation, and contextual factors. Identifying women at increased risk for heightened pain perception may facilitate personalized obstetric care, combining targeted psychological interventions, structured prenatal education, and, in the future, genetically informed pain management strategies