N
Nebojsa Bacanin
Researcher at Singidunum University
Publications - 207
Citations - 4041
Nebojsa Bacanin is an academic researcher from Singidunum University. The author has contributed to research in topics: Computer science & Metaheuristic. The author has an hindex of 25, co-authored 121 publications receiving 1740 citations. Previous affiliations of Nebojsa Bacanin include Megatrend University.
Papers
More filters
Proceedings ArticleDOI
Tuning Artificial Neural Network for Healthcare 4.0. by Sine Cosine Algorithm
Nemanja Milutinovic,S. Čabarkapa,Miodrag Zivkovic,Milos Antonijevic,Djordje Mladenovic,Nebojsa Bacanin +5 more
TL;DR: In this article , the sine cosine algorithm (SCA) was used to generate initial random candidate solutions with the goal of fluctuation outwards or towards the ideal answer.
Book ChapterDOI
Feature Selection and Extreme Learning Machine Tuning by Hybrid Sand Cat Optimization Algorithm for Diabetes Classification
Marko Stanković,Nebojsa Bacanin,Miodrag Zivkovic,Dijana Jovanović,Milos Antonijevic,Milos Bukmira,Ivana Strumberger +6 more
TL;DR: In this article , the authors proposed a novel framework for feature selection and extreme learning machine (ELM) hyper-parameter optimization applied to diabetes diagnostics applied to diagnose diabetes.
Journal ArticleDOI
Addressing feature selection and extreme learning machine tuning by diversity-oriented social network search: an application for phishing websites detection
Nebojsa Bacanin,Miodrag Zivkovic,Milos Antonijevic,K. Venkatachalam,Jinseok Lee,Yunyoung Nam,Marina Marjanovic,Ivana Strumberger,Mohamed Abouhawwash +8 more
TL;DR: In this article , a novel diversity-oriented social network search algorithm has been developed and incorporated into a two-level cooperative framework to improve phishing website detection by tuning extreme learning model that utilizes the most relevant subset of phishing websites data sets features.
Book ChapterDOI
An Improved BAT Algorithm for Solving Job Scheduling Problems in Hotels and Restaurants
Tarik A. Rashid,Chra I. Shekho Toghramchi,Heja Sindi,Abeer Alsadoon,Nebojsa Bacanin,Shahla U. Umar,Ahmed S. Shamsaldin,Mokhtar Mohammadi +7 more
TL;DR: An improvement on the original Bat algorithm has been made to speed up convergence and make the method more practical for large applications, and the proposed MBA establishes better global search ability and convergence than the original BA and other approaches.
Proceedings ArticleDOI
Predicting Credit Card Churn: Application of XGBoost Tuned by Modified Sine Cosine Algorithm
TL;DR: In this paper , a new model for forecasting customer churn and determining the contribution of variables that could lead to losing a customer was proposed, and a novel metaheuristic algorithm is proposed and tasked with selecting optimal hyperparameters for the XGBoost algorithm.