Article
Automation & Control Systems
Guosen Li, Ting Zhou
Summary: This paper proposes a particle swarm optimizer based on reference point, termed RPPSO, which effectively handles global and local solutions in multimodal multi-objective optimization problems, achieving competitive performance on multiple benchmark test functions.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2022)
Article
Computer Science, Artificial Intelligence
Diana Cristina Valencia-Rodriguez, Carlos A. Coello Coello
Summary: Particle Swarm Optimization (PSO) is a bio-inspired metaheuristic algorithm that utilizes information exchange between particles to explore the search space. This study focuses on the influence of the number of connections among particles in Multi-Objective Particle Swarm Optimizers (MOPSOs) using random regular graphs as the swarm topology. Experimental results indicate that a higher connection degree can lead to algorithm instability in various problems, and MOPSOs with the same connection degree exhibit similar behavior.
SWARM AND EVOLUTIONARY COMPUTATION
(2023)
Article
Computer Science, Interdisciplinary Applications
Xiaoli Shu, Yanmin Liu, Jun Liu, Meilan Yang, Qian Zhang
Summary: This paper proposes a multi-objective particle swarm optimization algorithm (D-MOPSO) to solve complex multi-objective optimization problems in the real world. It addresses the lack of convergence and diversity in traditional optimization methods and makes use of existing resources in the search process. D-MOPSO dynamically adjusts the population size based on the resources in the archive, improves particle exploration through local perturbations, and controls population size through non-dominated sorting and population density.
JOURNAL OF COMPUTATIONAL DESIGN AND ENGINEERING
(2023)
Article
Mechanics
Ricardo Fitas, Goncalo das Neves Carneiro, Carlos Conceicao Antonio
Summary: Optimization is a crucial area of research in Engineering that can result in cost savings and improved structural safety. Composite structures, which are often complex, require the use of the Finite Element Method for evaluation. Robust Design Optimization (RDO) is an approach that considers uncertainty in design variables or material properties to achieve robust and lightweight solutions. This study combines the advantages of Particle Swarm Optimization (PSO) with fitness assignment methodologies and elitist strategies to obtain a more perceptible Pareto front and faster optimization.
COMPOSITE STRUCTURES
(2022)
Article
Computer Science, Artificial Intelligence
Amirali Madani, Andries Engelbrecht, Beatrice Ombuki-Berman
Summary: Many real-life applications involve conflicting objectives and decision variables. Multi-guide particle swarm optimization (MGPSO) is a novel meta-heuristic that addresses multi-objective optimization problems through particle swarm optimization (PSO). A recent study found that MGPSO does not perform well when the number of decision variables increases. This paper proposes a scalable algorithm called cooperative coevolutionary multi-guide particle swarm optimization (CCMGPSO) that addresses this issue and achieves competitive results for high-dimensional problems.
SWARM AND EVOLUTIONARY COMPUTATION
(2023)
Article
Computer Science, Artificial Intelligence
Boyang Qu, Guosen Li, Li Yan, Jing Liang, Caitong Yue, Kunjie Yu, Oscar D. Crisalle
Summary: This paper proposes a grid-guided particle swarm optimizer for solving multimodal multi-objective optimization problems. By using a grid in the decision space, the algorithm is able to detect promising subregions and generate multiple subpopulations, maintaining diversity and improving search efficiency. Experimental results demonstrate that the proposed algorithm outperforms other evolutionary methods.
APPLIED SOFT COMPUTING
(2022)
Article
Computer Science, Artificial Intelligence
Abdolreza Rashno, Milad Shafipour, Sadegh Fadaei
Summary: This paper introduces a novel multi-objective particle swarm optimization feature selection method. It decodes feature vectors as particles and ranks them in a two-dimensional optimization space. The proposed method incorporates feature ranks to update particle velocity and position during the optimization process. Experimental results demonstrate the effectiveness of the method in finding Pareto Fronts of the best particles in multi-objective optimization space.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Yun Hou, Guosheng Hao, Yong Zhang, Feng Gu, Wenyang Xu
Summary: This paper proposes a multi-objective discrete particle swarm optimization algorithm to solve the particle routing problem in distributed particle filters. Experimental results show that the algorithm is highly competitive and can provide multiple high-quality Pareto optimal solutions.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Hailin Liu, Fangqing Gu, Zixian Lin
Summary: This study introduces a novel auto-sharing parameter technique for transfer learning based on multi-objective optimization, which uses a multi-swarm particle swarm optimizer to solve the optimization problem. By sharing the best particle information between target and source tasks, the proposed algorithm shows effective performance across various datasets.
INTEGRATED COMPUTER-AIDED ENGINEERING
(2021)
Article
Computer Science, Information Systems
Honggui Han, Yucheng Liu, Ying Hou, Junfei Qiao
Summary: To solve the problem of under-convergence solutions affecting particle motion and convergence in multi-modal multi-objective optimization, a self-adjusting multi-modal multi-objective particle swarm optimization (MMOPSOSS) algorithm is proposed. This algorithm promotes the convergence of multiple solution sets through parameter and population size adjustments. It incorporates a multi-swarm optimization framework, a self-adjusting local search mechanism, and a sub-swarm-balancing strategy, which are compared with other optimization algorithms in various experiments. The results show that MMOPSOSS improves the convergence of multiple solution sets for multi-modal multi-objective optimization.
INFORMATION SCIENCES
(2023)
Article
Thermodynamics
Hakan Aygun, Mehmet Kirmizi, Ulas Kilic, Onder Turan
Summary: The application of small turbojet engines is increasing due to their high power to weight ratio and reliability. This study analyzes the effects of different design variables on the performance metrics of small turbojet engines. By using multi-objective genetic algorithm, particle swarm optimization, and grey wolf optimization, the study considers several performance metrics of the engines. The findings show that increasing turbine inlet temperature improves net thrust but increases specific fuel consumption, while increasing compressor pressure ratio decreases net thrust but reduces specific fuel consumption. The optimization results suggest that different optimization methods can be utilized depending on the specific mission of the turbojet engine.
Article
Physics, Multidisciplinary
Hanlin Yang, Cunlai Pu, Jiexin Wu, Yanqing Wu, Yongxiang Xia
Summary: This paper proposes a multi-objective particle swarm optimization (MOPSO) framework to enhance the performance of the Optimized Link State Routing Protocol (OLSR) in vehicular ad hoc networks (VANETs). By considering both the quality and cost of service, the MOP is solved using MOPSO and the Pareto front is obtained. The optimization framework is applied to obtain the optimal parameters of OLSR, which are further validated in realistic VANET scenarios.
PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Hongtao Tang, Senli Ren, Weiguang Jiang, Qingfeng Chen
Summary: This paper proposes a method combining improved lowest horizontal line method and particle swarm optimization algorithm to solve UA-FLP, achieving multi-objective optimization of material handling cost, the adjacent value, and the utilization rate of floor shop. The algorithm simplifies the legalization of facility layout, overcomes the shortcomings of previous facility layout methods, and shows promising results in experiments.
Article
Computer Science, Artificial Intelligence
Pradip Dhal, Chandrashekhar Azad
Summary: In this study, a binary version of the hybrid two-phase multi-objective FS approach based on PSO and GWO is proposed. The approach aims to minimize classification error rate and reduce the number of selected features. By utilizing global and local search strategies, the method shows efficient and effective performance in selecting prominent features in high-dimensional data.
APPLIED SOFT COMPUTING
(2021)
Article
Computer Science, Artificial Intelligence
Jinhua Zheng, Zeyu Zhang, Juan Zou, Shengxiang Yang, Junwei Ou, Yaru Hu
Summary: This paper proposes a dynamic multi-objective particle swarm optimization algorithm based on adversarial decomposition and neighborhood evolution (ADNEPSO). The algorithm utilizes the complementary characteristics in the search area of the adversarial vector and introduces a novel particle update strategy to enhance performance and adaptability to environmental changes.
SWARM AND EVOLUTIONARY COMPUTATION
(2022)
Article
Computer Science, Hardware & Architecture
Suyel Namasudra, Pratima Sharma, Ruben Gonzalez Crespo, Vimal Shanmuganathan
Summary: This article proposes a privacy-preserving technique using blockchain technology for IoT-based healthcare systems to generate and maintain healthcare documents. The proposed scheme ensures security by specifying rules with a smart contract and is more efficient than existing schemes.
IEEE CONSUMER ELECTRONICS MAGAZINE
(2023)
Article
Operations Research & Management Science
Qin Xin, Ruben Gonzalez Crespo, Carlos Enrique Montenegro-Marin, Vicente Garcia Diaz, Mamoun Alazab
Summary: The emergence of the Internet of Things has revolutionized digital communications, bridging the gap between the real and digital worlds. To ensure security, a decentralized and scalable safety architecture has been proposed, utilizing intelligent computation and tree-based hashing systems for privacy and authorization. The performance of this architecture in terms of accuracy, loss, ratio, and latency has been evaluated and found to be excellent.
ANNALS OF OPERATIONS RESEARCH
(2023)
Article
Computer Science, Artificial Intelligence
Yu Du, Ruben Gonzalez Crespo, Oscar Sanjuan Martinez
Summary: Recognition of human emotion plays a crucial role in interpersonal relationships. In e-learning, challenges include lack of learner motivation, perceived lack of support, and busy schedules. This paper presents a heuristic multimodal real-time emotion recognition approach that uses learners' vocal intonations and facial expressions to provide timely and appropriate online feedback to foster their learning.
PROGRESS IN ARTIFICIAL INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Amartya Mukherjee, Ayan Kumar Panja, Nilanjan Dey, Ruben Gonzalez Crespo
Summary: This research proposes an ecosystem for precision agriculture based on an opportunistic MQTT protocol in an edge-enabled intelligent drone network. It leverages low latency vehicular communication and intelligent computing paradigms to achieve intelligent crop sensing and prediction. Experimental results show that the opportunistic MQTT protocol achieves a maximum message delivery ratio and minimal latency in an ultra-low latency sparse network scenario. The system also achieves high accuracy in predicting crop types.
Article
Psychology, Developmental
Saswati Debnath, Pinki Roy, Suyel Namasudra, Ruben Gonzalez Crespo
Summary: This paper presents a system based on Audio-Visual Automatic Speech Recognition (AV-ASR) to enhance the education of physically challenged individuals. By utilizing appearance-based visual features and co-occurrence statistical measures, accurate lip tracking is achieved, resulting in high accuracy rates in the experiments.
JOURNAL OF AUTISM AND DEVELOPMENTAL DISORDERS
(2023)
Article
Computer Science, Information Systems
Pratima Sharma, Suyel Namasudra, Naveen Chilamkurti, Byung-Gyu Kim, Ruben Gonzalez Crespo
Summary: Blockchain technology provides a secure platform for managing data in various application areas, and its combination with IoT has significant potential in the healthcare industry. This paper proposes a privacy-preserving distributed application using blockchain to create and maintain healthcare certificates, with the use of smart contracts for security. Experimental tests and comparative analysis show that the proposed scheme is more efficient than existing techniques.
ACM TRANSACTIONS ON SENSOR NETWORKS
(2023)
Article
Engineering, Electrical & Electronic
Amartya Mukherjee, Debashis De, Nilanjan Dey, Ruben Gonzalez Crespo, Enrique Herrera-Viedma
Summary: Internet of Things (IoT) application in disaster responses and management is a significant research domain. The introduction of consumer drones, flying ad-hoc networks, low latency 5G, and beyond 5G has greatly accelerated this research. This study proposes the implementation of the Consumer Internet of Drone Things (CIoDT) framework for emergency message transfer and stable network connectivity in disaster scenarios. The results show high message delivery probability, low latency, and suitability for mass production of light weight drone networks for disaster management.
IEEE TRANSACTIONS ON CONSUMER ELECTRONICS
(2023)
Article
Computer Science, Information Systems
Santosh Kumar Das, Nilanjan Dey, Ruben Gonzalez Crespo, Enrique Herrera-Viedma
Summary: This work proposes a strategy management technique based on hybrid peer-to-peer communication system, utilizing multi-objective optimization, game theory, non-linear geometric programming, and intuitionistic fuzzy logic. These techniques provide effective mathematical modelling to analyze conflicting situations and derive intelligent communication. Mathematical analysis and simulation results using performance metrics are conducted to validate the method.
INFORMATION SCIENCES
(2023)
Article
Computer Science, Hardware & Architecture
N. K. Rayaguru, N. Mahiban Lindsay, Ruben Gozalez Crespo, S. P. Raja
Summary: A hybrid BAT-GH and BAT-MMVO algorithm is proposed for maximizing power extraction from PV using an implanted controller. The controller finds the best switching pulse for the boost converter using the hybrid algorithm. The implementation of the algorithm is found to be less complex compared to other existing methods.
COMPUTERS & ELECTRICAL ENGINEERING
(2023)
Article
Computer Science, Information Systems
Javaria Amin, Muhammad Almas Anjum, Muhammad Sharif, Seifedine Kadry, Ruben Gonzalez Crespo
Summary: Liver cancer is a major cause of death worldwide, and manually detecting infected tissues is challenging and time-consuming. Computerized methods can assist in making accurate decisions and therapies. Semantic segmentation plays a vital role in segmenting infected liver regions.
IEEE LATIN AMERICA TRANSACTIONS
(2023)
Article
Computer Science, Information Systems
Pratima Sharma, Suyel Namasudra, Ruben Gonzalez Crespo, Javier Parra-Fuente, Munesh Chandra Trivedi
Summary: Blockchain technology is essential for ensuring data security in various fields such as artificial intelligence, supply chain, cloud computing, and healthcare. The blockchain-based IoT systems have significantly enhanced security, privacy, transparency, and efficiency in the healthcare sector, offering better business opportunities.
INFORMATION SCIENCES
(2023)
Article
Computer Science, Information Systems
Andres Ovidio Restrepo-Rodriguez, Maddyzeth Ariza-Riano, Paulo Alonso Gaona-Garcia, Carlos Enrique Montenegro-Marin
Summary: This paper presents the EDaLI dataset for emotional analysis, which collects emotional data during the interaction of 19 participants with 4 initial lessons in Portuguese as a second-language. It is concluded that visualization techniques can be applied to show the emotional behavior exhibited by the participants during their interactions.
Article
Computer Science, Interdisciplinary Applications
Lilian Astrid Bejarano, Carlos Enrique Montenegro, Helbert Eduardo Espitia
Summary: This article models the behavior of drivers on urban roads by using a Mamdani-type fuzzy system considering different environmental factors. The behavior of drivers is characterized using a leader-following traffic model and a fuzzy logic system. Real data obtained from cameras on the roads are employed to fit the fuzzy model through an optimization process. The optimization process incorporates the fuzzy logic system into a dynamic vehicle tracking model, allowing for consideration of different environmental factors in the traffic model simulation. Linguistic labels are assigned to the fuzzy sets associated with the output, enhancing the interpretability of the proposed fuzzy system. The results demonstrate that the proposed model accurately represents real data and adapts the fuzzy sets to the measured data for different cases.
Article
Mathematics, Interdisciplinary Applications
Carlos Montenegro, Victor Medina, Helbert Espitia
Summary: Automatic emotion identification is crucial for obtaining information on an individual's emotions during specific activities, with the aim of improving their performance or preparing for similar experiences. This study focuses on establishing clusters of variables related to emotion identification in students taking a Portuguese foreign language exam. By determining these data clusters, the perception of emotions in students can be established using relevant variables and decision thresholds. This research can be used to develop a model linking measured variables and students' performance to generate strategies for better test results. The findings show that clusters and range values of variables can be obtained to monitor changes in students' concentration, providing preliminary information for designing a fuzzy inference system to identify students' concentration levels.
