Article
Computer Science, Artificial Intelligence
Xuanyu Zheng, Changsheng Zhang, Bin Zhang
Summary: This paper presents a novel metaheuristic algorithm based on the Mayfly algorithm to solve the cardinality constrained mean-variance portfolio optimization problem. The experimental results show that the proposed approach achieves competitive performance on datasets of different sizes, demonstrating the feasibility of this approach in solving the problem.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Tunchan Cura
Summary: This study presents a heuristic approach to portfolio optimization problem using artificial bee colony technique. The results show that the proposed artificial bee colony approach is relatively efficient and effective in solving the problem.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Ryan Solgi, Hugo A. Loaiciga
Summary: This study evaluates the performance of seven bee-inspired metaheuristic algorithms in solving continuous optimization problems, ranks them based on convergence efficiency, and identifies ABC, BEGA, and MBO as the most efficient algorithms.
ARTIFICIAL INTELLIGENCE REVIEW
(2021)
Article
Computer Science, Artificial Intelligence
Shan Lu, Ning Zhang, Lifen Jia
Summary: This paper addresses a multiobjective multiperiod portfolio selection problem based on uncertainty theory, proposing a new uncertain portfolio optimization model and a hybrid technique called the MFA-SOS algorithm to solve it. Various constraints are taken into account in the model, and a numerical example demonstrates the effectiveness of the proposed approach.
APPLIED INTELLIGENCE
(2021)
Article
Computer Science, Artificial Intelligence
Asma M. Altabeeb, Abdulqader M. Mohsen, Laith Abualigah, Abdullatif Ghallab
Summary: The study introduces a cooperative hybrid firefly algorithm to solve the capacitated vehicle routing problem (CVRP), which utilizes multiple firefly algorithm populations to collaborate, hybridizes with local search and genetic operators, and exchanges solutions among populations through communication, the results of experiments demonstrate the algorithm's outstanding performance compared to other methods.
APPLIED SOFT COMPUTING
(2021)
Article
Operations Research & Management Science
Christos Konstantinou, Alexandros Tzanetos, Georgios Dounias
Summary: The paper presents a consistent and effective hybrid optimization scheme using nature-inspired algorithms and expert knowledge to tackle cardinality constrained portfolio optimization problems, achieving a new optimal solution in the financial sector. The performance of the proposed hybrid scheme is compared with other schemes applied to the same data and problem, showing higher efficiency.
OPERATIONAL RESEARCH
(2022)
Article
Computer Science, Artificial Intelligence
Deniz Ustun, Abdurrahim Toktas, Ugur Erkan, Ali Akdagli
Summary: This study introduces a modified algorithm, mABC, by incorporating mutation and crossover stages from differential evolution into the artificial bee colony algorithm. By comparing the performance with other algorithms through various statistical evaluations and convergence plots, it is found that mABC outperforms other variants in terms of optimization precision and convergence.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Review
Computer Science, Artificial Intelligence
Zaid Abdi Alkareem Alyasseri, Osama Ahmad Alomari, Mohammed Azmi Al-Betar, Sharif Naser Makhadmeh, Iyad Abu Doush, Mohammed A. Awadallah, Ammar Kamal Abasi, Ashraf Elnagar
Summary: This paper reviews the research conducted using the bat-inspired algorithm (BA) from 2017 to 2021, summarizing its characteristics, development, and applications. The limitations of BA are also analyzed, and suggestions for future directions and improvements are given.
NEURAL COMPUTING & APPLICATIONS
(2022)
Article
Spectroscopy
Mohamed B. El-Zeiny, Hossam M. Zawbaa, Ahmed Serag
Summary: This study introduces the grey wolf optimization (GWO) and antlion optimization (ALO) algorithms as variable selection tools in spectroscopic data analysis for the first time, showing that they select fewer variables than genetic algorithm (GA) and particle swarm optimization (PSO) algorithm in most cases while maintaining almost the same performance.
SPECTROCHIMICA ACTA PART A-MOLECULAR AND BIOMOLECULAR SPECTROSCOPY
(2021)
Review
Automation & Control Systems
Ebubekir Kaya, Beyza Gorkemli, Bahriye Akay, Dervis Karaboga
Summary: The ABC algorithm is a popular optimization algorithm that has been successfully applied to solve real-world problems. This study examines combinatorial optimization approaches based on the ABC algorithm, provides summaries of related studies, and introduces the ABC algorithm-based approaches used. The study also evaluates mechanisms to improve the local search capability of the ABC algorithm and analyzes neighborhood operators, selection schemes, initial populations determination approaches, hybrid approaches, and test instances used in evaluating the performances of ABC algorithms.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2022)
Article
Computer Science, Artificial Intelligence
Mathew Mithra Noel, Venkataraman Muthiah-Nakarajan, Geraldine Bessie Amali, Advait Sanjay Trivedi
Summary: The Firebug Swarm Optimization (FSO) algorithm, inspired by the reproductive swarming behavior of Firebugs, outperforms 17 popular state-of-the-art heuristic global optimization algorithms on benchmark tests, demonstrating its effectiveness in finding optimal solutions.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
Man-Fai Leung, Jun Wang, Hangjun Che
Summary: This paper investigates portfolio selection based on neurodynamic optimization. It formulates the portfolio selection problem as a biconvex optimization problem and addresses the cardinality-constrained portfolio selection problem as well. A two-timescale duplex neurodynamic approach is customized and applied to solve the reformulated portfolio optimization problem. Experimental results demonstrate the superior performance of the neurodynamic optimization approach compared to three baseline methods in terms of risk-adjusted performance and portfolio returns.
Article
Multidisciplinary Sciences
Farouq Zitouni, Saad Harous, Ramdane Maamri
Summary: The proposed quantum firefly algorithm combines the social behavior of fireflies mating in nature, laws of quantum physics, and laws of natural evolution. Tested on mathematical test functions and a structural design problem, the algorithm proves to be very competitive compared to other algorithms.
ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING
(2021)
Article
Engineering, Multidisciplinary
W. Y. Wang, Z. H. Xu, Y. H. Fan, D. D. Pan, P. Lin, X. T. Wang
Summary: This work proposes a novel adaptive global optimization algorithm called Disturbance Inspired Equilibrium Optimizer, which enhances the exploitation ability of Equilibrium Optimizer and solves the issue of getting trapped in local minima. The algorithm introduces a novel disturbance-based hybrid initialization strategy, a new form of time factor, and a new update rule of particle's position, leading to significantly improved exploration and exploitation ability.
APPLIED MATHEMATICAL MODELLING
(2023)
Article
Computer Science, Artificial Intelligence
Changting Zhong, Gang Li, Zeng Meng
Summary: This paper presents a novel swarm-based metaheuristic algorithm called beluga whale optimization (BWO), which is inspired by the behaviors of beluga whales, for solving optimization problems. BWO consists of three phases: exploration, exploitation, and whale fall, corresponding to pair swim, prey, and whale fall behaviors, respectively. The self-adaptive balance factor and probability of whale fall in BWO play significant roles in controlling the exploration and exploitation capabilities. Additionally, Levy flight is introduced to enhance the global convergence in the exploitation phase. The effectiveness of BWO is evaluated using 30 benchmark functions and compared with 15 other metaheuristic algorithms through qualitative, quantitative, and scalability analysis. The results show that BWO is a competitive algorithm for solving unimodal and multimodal optimization problems. Furthermore, BWO achieves the first overall rank in the scalability analysis of benchmark functions among the compared metaheuristic algorithms. Four engineering problems are also solved to demonstrate the merits and potential of BWO in solving complex real-world optimization problems. The source code of BWO is publicly available.
KNOWLEDGE-BASED SYSTEMS
(2022)
Review
Energy & Fuels
Nebojsa Bacanin, Catalin Stoean, Miodrag Zivkovic, Miomir Rakic, Roma Strulak-Wojcikiewicz, Ruxandra Stoean
Summary: An effective energy oversight is a global concern, especially with recent increasing stringency. Machine learning and deep learning approaches have shown high accuracy in energy load and consumption prediction, but few recent methods focus on parameter tuning for better results. This study develops and tunes a long short-term memory (LSTM) DL model for multivariate time-series forecasting of electricity load, using a benchmark dataset from Europe. The results serve as a benchmark for hybrid LSTM-optimization methods in energy time-series forecasting. The study highlights the importance of parameter tuning for improved results using metaheuristics, with the worst-performing metaheuristic still outperforming grid search.
Article
Computer Science, Artificial Intelligence
Luka Jovanovic, Nebojsa Bacanin, Miodrag Zivkovic, Milos Antonijevic, Bojan Jovanovic, Marija Bogicevic Sretenovic, Ivana Strumberger
Summary: The progress of Industrial Revolution 4.0 has been supported by recent advances in multiple domains, particularly the Internet of Things. Smart factories and healthcare have both benefited in terms of improved quality of service and productivity rate. However, security, intrusion, and failure detection pose significant concerns due to high dependence on IoT devices. Artificial intelligence, especially machine learning algorithms, are used to overcome these challenges by providing fault prediction, intrusion detection, and computer-aided diagnostics. However, the efficiency of machine learning models relies heavily on feature selection, predetermined hyper-parameter values, and training.
Article
Computer Science, Artificial Intelligence
K. Venkatachalam, Pavel Trojovsky, Dragan Pamucar, Nebojsa Bacanin, Vladimir Simic
Summary: Weather forecasting plays a crucial role in various aspects of modern society, and this study proposes a deep learning model called LSTM and T-LSTM for accurate weather prediction. Evaluation metrics demonstrate the effectiveness and reliability of the T-LSTM method.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Milos Mravik, Marko Sarac, Nebojsa Bacanin, Sasa Adamovic
Summary: This paper examines the impact of new approaches to distance learning during the Covid-19 pandemic, with a focus on comparing the quality of online teaching to face-to-face teaching. The presented results are based on empirical research conducted over a period of 2 years with a large group of students. The study finds that both professors and students encountered self-imposed obstacles, as well as pedagogical, technical, and financial or organizational barriers. The obtained results are further supported by conducting relevant hypothesis tests.
JOURNAL OF INTERNET TECHNOLOGY
(2023)
Article
Multidisciplinary Sciences
Nebojsa Bacanin, Nebojsa Budimirovic, K. Venkatachalam, Hothefa Shaker Jassim, Miodrag Zivkovic, S. S. Askar, Mohamed Abouhawwash
Summary: With the rapid growth of stored data in datasets, extracting crucial information becomes difficult. This research presents a novel quasi-reflection learning algorithm - firefly search, an enhanced version of the original arithmetic optimization algorithm. The proposed algorithm is tested on benchmark functions, standard datasets, and a Corona disease dataset, and the experimental results verify its improvements and statistical significance.
Article
Computer Science, Information Systems
Nebojsa Bacanin, Luka Jovanovic, Miodrag Zivkovic, Venkatachalam Kandasamy, Milos Antonijevic, Muhammet Deveci, Ivana Strumberger
Summary: Energy forecasting is crucial for effective power grid management, especially with the increasing adoption of emerging technologies and renewable energy sources. This paper presents a novel AI-driven energy forecasting system using recurrent neural networks (RNNs) and an improved swarm intelligence algorithm. The proposed approach demonstrates superior performance in predicting solar generation, wind power generation, and power grid load forecasting.
INFORMATION SCIENCES
(2023)
Article
Archaeology
Ruxandra Stoean, Nebojsa Bacanin, Catalin Stoean, Leonard Ionescu, Miguel Atencia, Gonzalo Joya
Summary: The accurate assessment of material composition and degradation in newly discovered archaeological artefacts is crucial for decision-making in the restoration and conservation stages. This study proposes a computational framework based on deep learning techniques that can automatically determine the chemical concentration of the predominant metal from microscope images and identify corrosion spots specific to that metal. The results suggest that the artificial intelligence framework can provide on-site support for early examination of metal heritage assets, even with limited training data.
JOURNAL OF CULTURAL HERITAGE
(2023)
Article
Computer Science, Software Engineering
Luka Jovanovic, Dijana Jovanovic, Milos Antonijevic, Bosko Nikolic, Nebojsa Bacanin, Miodrag Zivkovic, Ivana Strumberger
Summary: This research proposes a hybrid approach based on an improved metaheuristics algorithm to optimize the XGBoost machine learning model for enhancing Web security. Evaluations on three publicly available phishing website datasets show that the proposed solution outperforms other methods and represents a perspective solution in the domain of web security.
JOURNAL OF WEB ENGINEERING
(2023)
Article
Computer Science, Artificial Intelligence
Bratislav Predic, Luka Jovanovic, Vladimir Simic, Nebojsa Bacanin, Miodrag Zivkovic, Petar Spalevic, Nebojsa Budimirovic, Milos Dobrojevic
Summary: This paper proposes a method for forecasting cloud resource load based on recurrent neural networks and introduces an optimization algorithm to improve deep learning models. The results suggest that the method has great potential for accurately predicting cloud load and outperforms competing approaches when optimized.
COMPLEX & INTELLIGENT SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Mihailo Bjekic, Ana Lazovic, K. Venkatachalam, Nebojsa Bacanin, Miodrag Zivkovic, Goran Kvascev, Bosko Nikolic
Summary: This article proposes a module structure for semantic segmentation of walls in 2D images, which effectively addresses the problem of wall segmentation. The proposed method achieves higher accuracy and faster execution than other solutions, and can be applied to recognize other objects in the image to solve specific tasks.
PEERJ COMPUTER SCIENCE
(2023)
Article
Computer Science, Artificial Intelligence
Milos Dobrojevic, Miodrag Zivkovic, Amit Chhabra, Nor Samsiah Sani, Nebojsa Bacanin, Maifuza Mohd Amin
Summary: With the increasing integration of electronic devices into the Internet of Things (IoT), there is a growing amount of data that needs to be analyzed. However, this technology also brings risks of unauthorized access and data compromise. Machine learning and artificial intelligence can help detect potential threats and automate the diagnostic process. This article proposes an AI framework based on CNN and ELM tuned by SCA to address IoT security. The proposed model achieved superior classification performance and the results can be used to enhance IoT system security.
PEERJ COMPUTER SCIENCE
(2023)
Article
Environmental Sciences
Charli Sitinjak, Vladimir Simic, Rozmi Ismail, Nebojsa Bacanin, Charles Musselwhite
Summary: Effective end-of-life vehicle (ELV) management is crucial for minimizing the environmental and health impacts of Indonesia's growing automotive industry. However, proper ELV management has received limited attention. Our qualitative study identified barriers to effective ELV management in Indonesia's automotive sector, including inadequate regulation and enforcement, insufficient infrastructure and technology, low education and awareness, and a lack of financial incentives. We recommend a comprehensive and integrated approach involving coordination among government, industry, and stakeholders to address these barriers and develop sustainable ELV management policies and decisions.
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
(2023)
Article
Computer Science, Information Systems
B. Saravana Balaji, Wieslaw Paja, Milos Antonijevic, Catalin Stoean, Nebojsa Bacanin, Miodrag Zivkovic
Summary: Smart cities consist of intelligent industrial devices that improve people's lives and save lives. Intelligent remote patient monitoring predicts the patient's condition. Internet of Things (IoT), artificial intelligence (AI), and cloud computing have enhanced the healthcare industry. Edge computing accelerates patient data transmission and ensures latency, reliability, and response time. However, the transmission of large amounts of patient data may lead to IoT data security vulnerabilities, posing concerns and challenges. This research proposes a secure, scalable, and responsive patient monitoring system. The model uses lightweight attribute-based encryption (LABE) to encrypt and decrypt IoT patient data for cloud-based protection. Edge servers are situated between the IoT and cloud for improved quality of service (QoS) and patient diagnosis. The deep belief network (DBN) predicts and monitors patient health, while the bat optimization algorithm (BOA) optimizes hyperparameters. Deep belief is used to identify hyperparameters, and BOA is applied for optimization. Swarm intelligence enhances prediction results and edge-cloud reaction time. A simulated environment evaluates the secure patient health monitoring system for efficiency, security, and efficacy. The proposed model offers effective patient remote health monitoring through a secure edge-cloud-IoT environment, with improved accuracy (97.9%), precision (95.6%), recall (94.6%), F1-score (94.9%), and false discovery rate (0.06%).
HUMAN-CENTRIC COMPUTING AND INFORMATION SCIENCES
(2023)
Article
Computer Science, Information Systems
Sara Boskovic, Libor Svadlenka, Stefan Jovcic, Momcilo Dobrodolac, Vladimir Simic, Nebojsa Bacanin
Summary: This paper introduces a new subjective technique called FullEX for evaluating the importance of criteria in LMD courier selection. Through evaluation, on-time delivery is considered the most important criterion for sustainable LMD courier selection.
Article
Chemistry, Multidisciplinary
Mohamed Salb, Luka Jovanovic, Nebojsa Bacanin, Milos Antonijevic, Miodrag Zivkovic, Nebojsa Budimirovic, Laith Abualigah
Summary: This paper addresses the critical security challenges in the internet of things (IoT) landscape by proposing an innovative solution that combines convolutional neural networks (CNNs) and the XGBoost model for intrusion detection. By customizing the reptile search algorithm for hyperparameter optimization, the methodology provides a resilient defense against emerging threats in IoT security. The introduced algorithm constructed models with the best performance in both experiments, and its outcomes have been statistically evaluated and analyzed for feature importance using Shapley additive explanations.
APPLIED SCIENCES-BASEL
(2023)
