A5023873971- Regional Development and Management Studies
- Neural Networks and Applications
- Acute Myeloid Leukemia Research
- Sarcoma Diagnosis and Treatment
- Viral-associated cancers and disorders
- Stock Market Forecasting Methods
- Chronic Myeloid Leukemia Treatments
- Neutropenia and Cancer Infections
- Chronic Lymphocytic Leukemia Research
- Fault Detection and Control Systems
- Myeloproliferative Neoplasms: Diagnosis and Treatment
- Lung Cancer Treatments and Mutations
- Lymphoma Diagnosis and Treatment
- Regional Development and Policy
- Neuroethics, Human Enhancement, Biomedical Innovations
- Economic Analysis and Policy
- Dermatologic Treatments and Research
- Chromatin Remodeling and Cancer
- CCD and CMOS Imaging Sensors
- CNS Lymphoma Diagnosis and Treatment
- Electric Power System Optimization
- Immunodeficiency and Autoimmune Disorders
- Energy Load and Power Forecasting
- Spreadsheets and End-User Computing
- Connective tissue disorders research
College of Slavonski Brod
2008-2025
Klinička bolnica Merkur
2015-2025
Catholic University of Croatia
2025
Wind energy is an important renewable source, and artificial intelligence (AI) plays role in improving its efficiency, reliability cost-effectiveness while minimizing environmental impact. Based on analysis of the latest scientific literature, this article examines AI applications for entire life cycle wind turbines, including planning, operation decommissioning. A key focus AI-driven maintenance, which reduces downtime, improves extends lifetime turbines. also optimizes design particularly...
Predicting innovation outcomes at the firm level continues to be an important but challenging goal for researchers and practitioners alike. In this study, multiple machine learning models, encompassing both ensemble-based single-model approaches, were applied data from Community Innovation Survey. Methods included random forests, gradient boosting frameworks, support vector machines, neural networks, logistic regression, each with hyperparameters optimized through Bayesian search routines...
Background/Objectives: In hematological patients receiving treatment for lymphomas, febrile neutropenia (FN) is a serious complication associated with significant morbidity and mortality. This prospective study aimed to evaluate the diagnostic prognostic value of novel biomarker presepsin (PSP) in episodes FN this specific cohort patients. Methods: The enrolled 37 18 without fever as control group. Patients were divided into two groups: those confirmed infections them. Various clinical...
In the last few years, microcontrollers became more and powerful, many authors have started to use them for different machine learning projects. One of most popular frameworks is TensorFlow, their began develop this framework microcontrollers. The goal paper analyses full connected neural networks inference speed depending on number neurons one microcontroller (Arduino Nano 33 BLE Sense) with simple implementation, as well impact network weights quantisation. We expected a reduction in size...
Processors with multiple cores have enabled machine learning to achieve the great success it has. In last few years System on Chip devices became powerful enough be used for tasks, and some of them cores. this paper propagation speed ESP32 SoC two feed-forward part neural network tasks considering number will analysed.
This paper presents an algorithmic conversion process of data written on a weekly basis in the format monthly basis, including all specifics. The aim is to graphically and numerically display results size errors that time running. main method used for averaging average value. Research shows error, ie. loss original value below 2.5%.
This paper analyses the Austrian Traded Index (ATX) of Vienna Stock Exchange (Wiener Börse) in period from 2009 to 2017, using method artificial neural network (ANN).Sampling data are taken web page Wiener Börse and filtered on weekly basis comply with seasonality eight years range.The aim is construct several AAN models that meet certain criteria evaluate them holdout subsample.Furthermore, goal find best model can predict new upcoming yet unseen high accuracy.A frame for testing...