Nikola Ivković

ORCID: 0000-0003-1730-2518
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Metaheuristic Optimization Algorithms Research
  • Vehicle Routing Optimization Methods
  • Advanced Multi-Objective Optimization Algorithms
  • Distributed and Parallel Computing Systems
  • Multi-Agent Systems and Negotiation
  • Ombudsman and Human Rights
  • Peer-to-Peer Network Technologies
  • Parallel Computing and Optimization Techniques
  • Advanced MIMO Systems Optimization
  • Evolutionary Algorithms and Applications
  • Education, Law, and Society
  • Petri Nets in System Modeling
  • IoT and Edge/Fog Computing
  • Real-Time Systems Scheduling
  • European and International Law Studies
  • European Criminal Justice and Data Protection
  • Network Security and Intrusion Detection
  • Information and Cyber Security
  • Cloud Computing and Resource Management
  • Privacy-Preserving Technologies in Data
  • Robotic Path Planning Algorithms
  • Energy Efficient Wireless Sensor Networks
  • AI in cancer detection
  • Formal Methods in Verification
  • Mobile Agent-Based Network Management

University of Zagreb
2011-2025

Opća Bolnica Varaždin
2015-2016

Unmanned aerial vehicles (UAVs) are increasingly being deployed in crucial missions for the armed forces, law enforcement, industrial control monitoring, and other sectors. However, these hostile operating circumstances, along with UAVs' dependence on wireless protocols, pose substantial security threats, limiting their mainstream application. With network such a major issue UAV networks, machine learning-based intrusion detection system (IDS) has been determined to be an effective strategy...

10.1109/access.2024.3349469 article EN cc-by-nc-nd IEEE Access 2024-01-01

In this paper, a task scheduling problem for cloud computing environment is formulated by using the M/M/n queuing model. A priority assignment algorithm designed to employ new data structure named waiting time matrix assign individual tasks upon arrival. addition this, queue implements unique concept based on principle of Fibonacci heap extracting with highest priority. This work introduces parallel in which and building executed respect non-preemptive preemptive nature tasks. The proposed...

10.1109/access.2023.3255781 article EN cc-by-nc-nd IEEE Access 2023-01-01

Channel estimation poses a main challenge in intelligent reflecting surface (IRS)-assisted millimeter wave (mmWave) multi-user multiple-input multiple-output (MIMO) systems due to the substantial number of antennas at base station (BS) and passive reflective elements within IRS lacking sufficient signal processing capabilities. This article addresses this by proposing channel technique for IRS-assisted mmWave MIMO systems. The problem is normally taken as compressed sensing (CS) problem,...

10.7717/peerj-cs.2582 article EN cc-by PeerJ Computer Science 2025-01-03

In the era of big data, managing dynamic data flows efficiently is crucial as traditional storage models struggle with real-time regulation and risk overflow. This paper introduces Data Dams, a novel framework designed to optimize inflow, storage, outflow by dynamically adjusting flow rates prevent congestion while maximizing resource utilization. Inspired physical dam mechanisms, employs intelligent sluice controls predictive analytics regulate based on system conditions such bandwidth...

10.48550/arxiv.2502.03218 preprint EN arXiv (Cornell University) 2025-02-05

Objective This paper aims to address the need for real-time malaria disease detection that integrates a faster prediction model with robust underlying network. The study first proposes 5G network-based healthcare system and then develops an automated capable of providing accurate diagnosis, particularly in areas limited diagnostic resources. Methods proposed leverages deep learning-based YOLOv5x algorithm detect parasites thick thin blood smear samples. network architecture was modified by...

10.1177/20552076251321540 article EN cc-by-nc-nd Digital Health 2025-02-01

The security of Internet Medical Things (IoMT) devices is crucial for ensuring the integrity and reliability patients' medical data. These devices, operating over TCP ICMP protocols, are highly susceptible to cyberattacks. While machine learning models can detect these attacks with acceptable accuracy, their operational mechanisms remain unclear, leaving decision-making process undefined. Moreover, accuracy training time more questionable when datasets has large number sparse features class...

10.1038/s41598-025-93404-8 article EN cc-by-nc-nd Scientific Reports 2025-03-13

Reporting the results of optimization algorithms in evolutionary computation is a challenging task with many potential pitfalls.The source problems their stochastic nature and inability to guarantee an optimal solution polynomial time.One basic questions that often not addressed concerns method summarizing entire distribution solutions into single value.Although mean value used by default for purpose, best obtained also occasionally addition or instead it.Based on our analysis different...

10.18178/ijmlc.2016.6.3.593 article EN International Journal of Machine Learning and Computing 2016-06-01

Reporting the empirical results of swarm and evolutionary computation algorithms is a challenging task with many possible difficulties. These difficulties stem from stochastic nature such algorithms, as well their inability to guarantee an optimal solution in polynomial time. This research deals measuring performance optimization confidence intervals empirically obtained statistics. Traditionally, arithmetic mean used for average performance, but we propose quantiles average, peak bad-case...

10.3390/math10224364 article EN cc-by Mathematics 2022-11-20

Ant colony optimization (ACO) is a well-known class of swarm intelligence algorithms suitable for solving many NP-hard problems. An important component such record pheromone trails that reflect colonies’ experiences with previously constructed solutions the problem instance being solved. By using pheromones, algorithm builds probabilistic model exploited constructing new and, hopefully, better solutions. Traditionally, there are two different strategies updating trails. The best-so-far...

10.3390/a16050251 article EN cc-by Algorithms 2023-05-12

10.1016/j.eswa.2018.12.021 article EN Expert Systems with Applications 2018-12-31

Modern programming paradigms have brought many different challenges for visually impaired programmers. Graphical interfaces become one of the biggest obstacles professionals. The same problems that relate to programmers also apply education in which it is very challenging make educational accessible and other students with disabilities. In order more suitable visual impairment an system enables voice-based control its elements has been developed purpose their education. results using this...

10.1109/mipro.2016.7522265 article EN 2016-05-01

The performance of Wireless Sensor Networks (WSNs) is an important fragment the Internet Things (IoT), where current WSNbuilt IoT network’s sensor hubs are enticing due to their critical resources. By grouping hubs, a clustering convention offers useful solution for ensuring energy-saving and Hybrid Media Access Control (HMAC) during course organization. Nevertheless, standards suffer from issues with structure that impacts exhibition these conventions negatively. In this investigation, we...

10.32604/cmc.2023.036275 article EN Computers, materials & continua/Computers, materials & continua (Print) 2023-01-01

Modern automobiles have many built-in sensors and electronic control units responsible for increasing safety, optimizing performance improving occupant comfort.Along with this well-established uses of computing devices inside automobiles, there are two main research directions in further computerization automobiles.One direction is aimed at creating vehicles that communicate road infrastructure other ad hoc manner forming vehicular network (VANET).The expected to produce self-driving can...

10.18178/ijfcc.2016.5.6.475 article EN International Journal of Future Computer and Communication 2016-01-01

The sensorimotor system is a crucial mechanism that enables organisms to categorize information in their environment, skill necessary for survival. According cognitive scientist Steven Harnad's "To Cognize Categorize: Cognition Categorization all living things are essentially systems. This approach proposed serve as novel concept the development of algorithms inspired by swarm intelligence. Many authors such have drawn inspiration from animal species, attempting emulate abilities interact...

10.23919/mipro57284.2023.10159646 article EN 2023-05-22

Business systems as well corresponding websites are constantly growing in their complexity and it is harder to use them find desired functionality or information. Intelligent assistants can be used a mean of enabling users information they seek get the answers require way that quicker more suited for wider types compared traditional approach because not required know system detail but rather communicate with appropriate intelligent assistant natural language which similar talking colleagues....

10.1109/mipro.2015.7160441 article EN 2015-05-01
Coming Soon ...