Application Of Swarm Intelligence Research Articles

Application of Swarm Intelligence in Transportation System Optimisation

Swarm intelligence is a branch of artificial and natural intelligence that studies systems with many characters that manage their activities through distributed control and self-organisation. The field focuses on the actions of social insects such as fish schools, bird flocks, ants, termites, bees, and wasp colonies. Particle swarm optimisation (PSO) and ant colony optimisation (ACO) are two of the most common systems reported by swarm intelligence. Ant Colony Optimization (ACO) is a probabilistic method used to find optimal pathways in computationally complex situations by condensing the problem. This paper analyses the use of ACO metaheuristics to find the initial basic feasible solution in an unbalanced and balanced transportation method. Then, it compares it to other traditional methods (The least cost method, Northwest Corner method, and Vogel’s approximation method). The primary goal of this study is to provide a helpful framework for understanding new trends in applying swarm intelligence in system optimisation and implementing/using the ACO algorithm in a real-life situation. Examples were generated online. At the end of the paper, for the unbalanced transportation problem, the Least Cost method, Northwest Corner method, Vogel’s Approximation method, and ACO method gave us (472, 547, 374, and 389) as the total cost, respectively. For the balanced transportation problem, the Least Cost, Northwest Corner, Vogel’s Approximation, and ACO methods gave us (2450, 3700, 2150, and 3650) as the total cost, respectively.

Enhancing radioactive environment exploration with bio-inspired swarm robotics: A comparative analysis of Lévy flight and stigmergy methods

Enhancing radioactive environment exploration with bio-inspired swarm robotics: A comparative analysis of Lévy flight and stigmergy methods

A swarm-intelligence based formulation for solving nonlinear ODEs: γβII-(2+3)P method

A swarm-intelligence based formulation for solving nonlinear ODEs: γβII-(2+3)P method

GENETIC FUZZY LOGIC ALGORITHM AS INTELLIGENT AGENTS FOR SWARM INTELLIGENCE APPLICATION

This research introduces a novel approach to harnessing the power of Genetic Fuzzy Logic Algorithms (GFLAs) in the context of Swarm Intelligence applications. Swarm Intelligence relies on decentralized, self-organized systems, where individual agents collaborate to achieve complex tasks. However, existing methods often face challenges in adapting to dynamic environments and optimizing system performance. To address this, our study proposes the integration of GFLAs as intelligent agents within Swarm Intelligence frameworks. GFLAs leverage genetic algorithms and fuzzy logic to evolve and adapt their rules autonomously, enhancing the system adaptability and efficiency. The research addresses the gap in current literature by investigating the potential of GFLAs as intelligent agents in Swarm Intelligence, emphasizing their ability to learn and optimize behaviors in real-time. Through rigorous experimentation, we demonstrate the effectiveness of the proposed method in improving swarm performance across diverse scenarios.

A scoping review of literature on the application of swarm intelligence in the object classification domain

This scoping review aims to explore the various swarm technologies and how they have been used in the object classification domain with the desire to motivate the design of a generic swarm intelligence ontology based on the components of various swarm technologies. We used the PRISMA-ScR as a guide to our scoping review protocol. We conducted a search across thirteen databases and a random search as well on the internet for articles. We performed screening of all the articles by title to remove duplicates, we further on did a screening by the year of publication to ensure that all articles to be considered were published between 2012 and 2022 and we then did abstract or text synthesis. Our search query retrieved 3224 potential articles from the thirteen databases and 10 articles from a random search on the internet making a total of 3234 articles identified. Deduplication and screening were done on the identified articles and 287 articles which satisfied our inclusion criteria remained. We grouped the articles into three categories namely year of publication, swarm technology and swarm application. The year of publication showed a linear trend line which is an indication of growth in the swarm intelligence domain. Of the six categories of aims we identified we voluntarily chose to ignore articles where the aim was not specified. We noticed that 64.9% of articles were aimed at either modifying or improving. The swarm technology category indicated that 58.54% of the included articles were based on the Particle Swarm Optimization either independently or as part of a hybrid algorithm. 83.97% of the articles used classification as their swarm application. Interesting to note was the appearance of feature selection and optimization in this category. This scoping review gave an overview of how swarm technologies have been used in the object classification domain. Further research can be done by bringing and using existing algorithms in the development of generic swarm intelligence inspired ontologies.

Intelligent evaluation model of basketball teaching reliability based on swarm intelligence and edge computing

Campus basketball culture is gradually affecting students’ sports spirit and sports accomplishment. As for the evaluation of basketball teaching achievements, the method of specified items is generally used for testing, which is highly subjective. It’s completely teacher-led, and teachers make relevant evaluations of students’ basketball behavior. Teachers can’t be absolutely fair and just in the evaluation, because teacher evaluation can be affected by many factors, such as teachers’ mood on that day, teachers’ affection for students, and so on, the traditional way of teacher basketball evaluation is easy to cause negative emotional impact on some students, so that students have negative emotions on basketball activities, and even affect their sports quality, and finally affect their health. Based on the evaluation method of basketball teaching, this paper introduced a reliability intelligent evaluation model based on swarm intelligence and edge computing and used this model to evaluate students’ performance in basketball teaching classes. Moreover, this paper designed a related experiment, the experimental results showed that boys and girls in basketball level gap was more obvious. As far as dribbling skills were concerned, the highest score of boy A was 91 points, while the lowest score of girl C was 54 points. The gap was quite large. At the same time, the introduction results of the reliability intelligent evaluation model were studied by using the questionnaire survey method. As can be seen from the results of the questionnaire, the number of people who are very interested in basketball teaching activities is obviously high, and the number of people who are still not interested in the six activities is no more than 2. Through the change data of students’ interests and attitudes, it was proved that the reliability intelligent evaluation model could improve the students’ enthusiasm for learning basketball courses, thus improving their sports quality. This study provided a reference value for the application of swarm intelligence and edge computing in the intelligent evaluation model of basketball teaching reliability, and provided a direction for the future development of basketball teaching.

Multilevel Multiobjective Particle Swarm Optimization Guided Superpixel Algorithm for Histopathology Image Detection and Segmentation.

Histopathology image analysis is considered as a gold standard for the early diagnosis of serious diseases such as cancer. The advancements in the field of computer-aided diagnosis (CAD) have led to the development of several algorithms for accurately segmenting histopathology images. However, the application of swarm intelligence for segmenting histopathology images is less explored. In this study, we introduce a Multilevel Multiobjective Particle Swarm Optimization guided Superpixel algorithm (MMPSO-S) for the effective detection and segmentation of various regions of interest (ROIs) from Hematoxylin and Eosin (H&E)-stained histopathology images. Several experiments are conducted on four different datasets such as TNBC, MoNuSeg, MoNuSAC, and LD to ascertain the performance of the proposed algorithm. For the TNBC dataset, the algorithm achieves a Jaccard coefficient of 0.49, a Dice coefficient of 0.65, and an F-measure of 0.65. For the MoNuSeg dataset, the algorithm achieves a Jaccard coefficient of 0.56, a Dice coefficient of 0.72, and an F-measure of 0.72. Finally, for the LD dataset, the algorithm achieves a precision of 0.96, a recall of 0.99, and an F-measure of 0.98. The comparative results demonstrate the superiority of the proposed method over the simple Particle Swarm Optimization (PSO) algorithm, its variants (Darwinian particle swarm optimization (DPSO), fractional order Darwinian particle swarm optimization (FODPSO)), Multiobjective Evolutionary Algorithm based on Decomposition (MOEA/D), non-dominated sorting genetic algorithm 2 (NSGA2), and other state-of-the-art traditional image processing methods.

Artificial intelligence support for 5G/6G-enabled Internet of Vehicles networks: An overview

Improving transportation efficiency and on-road safety using Intelligent Transportation Systems (ITSs) has become crucial as road congestion and vehicle complexity increase coupled with ongoing rapid development and deployment of electric vehicles across the globe. Recent advances in computer systems and wireless communications have ushered in more possibilities for smart solutions to road traffic safety, congestion reduction, convenience, and overall efficiency. The evolution and deployment of 5G have opened up new technologies and features that can provide the much needed high-mobility wireless networks for the emerging Internet of Vehicles (IoV). The application of AI consisting of Deep Learning (DL), Machine Learning (ML) and Swarm Intelligence (SI) techniques have emerged in both conventional and vehicular wireless networks with strong promises towards enhancing traditional data-centric methods. Particularly, in the application domains of IoV, big data is frequently generated from various sources within the vehicular communication environment. The collected big data is usually processed and used for both safety and infotainment services including routing, broadening drivers' awareness, traffic mobility prediction for hazardous situation avoidance to improve overall safety and passenger comfort, and general quality of road experience. Applying data-driven methods enables AI to address high mobility and dynamic vehicular communications and network issues facing traditional solutions and approaches like network optimization techniques and conventional control loop design. This study provides a concise review of DL, ML and SI techniques and applications that are currently being explored by different research efforts within the application area of vehicular networks. The paper further discusses the strengths and weaknesses of the proposed AI-based solutions for the IoV networks.

Swarm Intelligence in Internet of Medical Things: A Review.

Continuous advancements of technologies such as machine-to-machine interactions and big data analysis have led to the internet of things (IoT) making information sharing and smart decision-making possible using everyday devices. On the other hand, swarm intelligence (SI) algorithms seek to establish constructive interaction among agents regardless of their intelligence level. In SI algorithms, multiple individuals run simultaneously and possibly in a cooperative manner to address complex nonlinear problems. In this paper, the application of SI algorithms in IoT is investigated with a special focus on the internet of medical things (IoMT). The role of wearable devices in IoMT is briefly reviewed. Existing works on applications of SI in addressing IoMT problems are discussed. Possible problems include disease prediction, data encryption, missing values prediction, resource allocation, network routing, and hardware failure management. Finally, research perspectives and future trends are outlined.

Swarm Intelligence Research: From Bio-inspired Single-population Swarm Intelligence to Human-machine Hybrid Swarm Intelligence

Swarm intelligence has become a hot research field of artificial intelligence. Considering the importance of swarm intelligence for the future development of artificial intelligence, we discuss and analyze swarm intelligence from a broader and deeper perspective. In a broader sense, we are talking about not only bio-inspired swarm intelligence, but also human-machine hybrid swarm intelligence. In a deeper sense, we discuss the research using a three-layer hierarchy: in the first layer, we divide the research of swarm intelligence into bio-inspired swarm intelligence and human-machine hybrid swarm intelligence; in the second layer, the bio-inspired swarm intelligence is divided into single-population swarm intelligence and multi-population swarm intelligence; and in the third layer, we review single-population, multi-population and human-machine hybrid models from different perspectives. Single-population swarm intelligence is inspired by biological intelligence. To further solve complex optimization problems, researchers have made preliminary explorations in multi-population swarm intelligence. However, it is difficult for bio-inspired swarm intelligence to realize dynamic cognitive intelligent behavior that meets the needs of human cognition. Researchers have introduced human intelligence into computing systems and proposed human-machine hybrid swarm intelligence. In addition to single-population swarm intelligence, we thoroughly review multi-population and human-machine hybrid swarm intelligence in this paper. We also discuss the applications of swarm intelligence in optimization, big data analysis, unmanned systems and other fields. Finally, we discuss future research directions and key issues to be studied in swarm intelligence.

Human activity recognition using marine predators algorithm with deep learning

Human activity recognition using marine predators algorithm with deep learning

Application of swarm intelligence for dynamic properties of moored floating structures using two-dimensional fluid dynamic program

This paper presents a numerical investigation into interactions between oscillatory waves and moored floating structures by through applying Swarm Intelligence (SI). The effects of small and large incident waves placing a force on the obstacles were studied using two floating structures composed of a rectangle and a cage kind with taut-moored and slack-moored situations. The aforementioned problem was reduced to solve systems of sparse-nonlinear equations for surge, heave, and pitch responses, as well as mooring forces considering that there is a distorted wave motion due to the presence of the movable obstacle boundary. The particle swarm optimization (PSO) algorithm is proposed here to provide insight into computational intelligence factors affecting calculation results and efficiency. Besides that, a computational fluid dynamic (CFD) program is based on a full Navier-Stokes solver. A series of numerical examinations for selected wave heights and wavelengths including a set of optimization procedures have been taken into account in the evaluation of formulated objective function, F, where the best potential solution is computed at each computational step. Meanwhile, a collection of empirical benchmarks were also developed based on reported measurements in the literature to provide sound empirical support for the theoretical findings. The results show that the optimization method exhibits a favorable convergent behavior (F≈0), where the computed results agree well with the measurements in terms of mean amplitudes of the surge, heave, and pitch responses and peak values of mooring-line tensions. The approach would firmly converge on benchmarks with improved computational steps of 18,321 running for 20.1 wave cycles in the case of the taut-moored rectangular structure. For the slack-moored cage, a satisfactory convergence was achieved using a series of data calibrations into an algorithm that took 27,976 iterations and 24.5 s to complete. Furthermore, CFD captures of wave deformations, dynamic forces, and streamlines were able to qualitatively corroborate the results.

An Investigation into the Utilization of Swarm Intelligence for the Design of Dual Vector and Proportional–Resonant Controllers for Regulation of Doubly Fed Induction Generators Subject to Unbalanced Grid Voltages

This work presents an investigation into the use of swarm intelligence techniques for the control of the doubly fed induction generator under unbalanced grid voltages. Swarm intelligence is a concept that was introduced in the late 20th century but has since undergone constant evolution and modifications. Similarly, the doubly fed induction generator has recently come under intense investigation. Owing to the direct grid connection of the DFIG, an unbalanced grid voltage harshly impacts its output power. Established mitigation measures include the use of the dual vector and proportional–resonant control methods. This work investigates the effectiveness of utilizing swarm intelligence for the purpose of controller gain optimization. A comparison of the application of swarm intelligence to the dual vector and proportional–resonant controllers was carried out. Three swarm intelligence techniques from across the timeline were utilized including particle swarm optimization, the bat algorithm, and the gorilla troops optimization algorithm. The system was subject to single-phase voltage dips of 5% and 10%. The results indicate that modern swarm intelligence techniques are effective at optimizing controller gains. This shows that as swarm intelligence techniques evolve, they may be suitable for use in the optimization of controller gains for numerous applications.

Application of Swarm Intelligence and Evolutionary Computation Algorithms for Optimal Reservoir Operation

Application of Swarm Intelligence and Evolutionary Computation Algorithms for Optimal Reservoir Operation

Application of swarm intelligence and a bioinspired computing algorithm in remote sensing image registration

Application of swarm intelligence and a bioinspired computing algorithm in remote sensing image registration

Review of multiple unmanned surface vessels collaborative search and hunting based on swarm intelligence

In recent years, the research of multiple unmanned surface vessels collaboration has received great attention. More and more researchers have proposed different methods of multiple unmanned surface vessels collaboration, such as cooperative collision avoidance, formation, and rendezvous. Based on the significant advantages of biological swarm intelligence applications in these collaborative methods, this article summarizes the research methods of multiple unmanned surface vessels collaborative search and hunting from the perspective of swarm intelligence. First of all, this article summarizes the key technologies of multiple unmanned surface vessels collaborative search and hunting from the aspects of the multi-robot system, group communication, environment modeling, collaboration mechanism, and path planning. Then, it reviews some classic swarm intelligence algorithms, analyzes the advantages and disadvantages of these algorithms, and proposes optimization directions for existing disadvantages based on relevant literature. Finally, the article points out some existing problems in every stage and suggestions for future research.

Simple agents, smart swarms: a cooperative search algorithm for swarms of autonomous underwater vehicles

Searching within an unknown environment quickly by utilising a small number of high-capacity robots or a large number of low-cost robots poses an endless question with a non-trivial answer. If the robot's operating environment is underwater, the problem becomes even more complicated due to its three-dimensional nature and the communication restrictions. In this paper, we propose an algorithm appropriate for target searching in unknown underwater environments. The proposed method considers a homogeneous decentralised multi-robot coordination scheme applied from a single-robot configuration to a large swarm. In this model, simple agents (SA) form smart swarms (SS), despite SA do not need to have a strong ability to transmit search and location information, and the SS can efficiently perform search tasks in unknown environments. Specifically, when a swarm performs a search task, agents only search according to the simple strategy and share mapping information within their communication range, enhancing search efficiency. Simulation results demonstrate the effectiveness and that search time reduces proportionally by increasing the number of robots comprising the swarm, while the repetition search rate does not increase with the expansion of the swarm size. We believe that our SS architecture provides insights into the future application of swarm intelligence.

Numerical Investigation on Motion Responses of Floating Structures by Application of Swarm Intelligence

In presence of complex-hydrodynamic interaction between water waves and floating structures, a reliable method that can analyse nonlinear structural properties is necessarily required. This paper presents a numerical investigation of the moored floating structures by application of swarm intelligence (SI). Here, a hybrid particle swarm optimization (PSO) algorithm with various swarm parameters are proposed to solve systems of sparse-nonlinear equations for the surge, heave, and pitch motion responses by considering distorted wave motion. In addition, a computational fluid dynamic (CFD) programme is developed using Reynolds Average Navier-Stokes (RANS) solver. Various wave parameters including a set of optimization criteria have been taken into account in a complete optimization simulation, where the optimum solutions are then selected at each numerical iteration. Meanwhile, the computed results of surge, heave, and pitch motions will be qualitatively validated, in which they are then visualized using CFD approach. The results show that the integrated SI-CFD model can simulate fairly well on hydrodynamics of floating structures with reasonable computational efficiency. Harnessing computational intelligence into a novel design concept of floating structures can serve as useful engineering decision-making tool.

Swarm Evaluated Threshold Elimination Approach for Symmetrical Fault Detection During Power Swing

This paper introduces the application of swarm intelligence in relaying to detect symmetrical faults during power swing. The swarm intelligence assistance reduces the computational burden and enhances the overall reliability of the fault detection scheme irrespective of the system conditions. For this purpose, a simple fault detector using instantaneous three-phase active power is implemented and particle swarm optimization (PSO) assistance is provided to identify the optimal value of threshold elimination factor (TEF) by considering fault and swing parameters as decision variables. In the optimal TEF search, the detailed coefficients of frequency components of the input signal are extracted using wavelet transform by generating the solutions using PSO. As a result, a direct trip command is activated with the help of the swarm-assisted wavelet TEF technique. The PSO-assisted proposed method is fast and secure in detecting faults during stressed conditions. Later, the performance of the proposed method is tested on numerous fault cases simulated on a two-bus test power system model using MATLAB/Simulink(R). Results clearly show that using the proposed method faults can be detected within a quarter cycle during the power swing. The comparative assessment with the existing methods confirms the effectiveness of the proposed scheme.

Architecture and Algorithm of Formation control of Multi-unmanned vehicles Based on Swarm intelligence

The main contents of this dissertation are the application of swarm intelligence to multi-unmanned vehicle system and the realization of cooperative control of multi-unmanned vehicle system. Firstly, this thesis introduces the research background and significance of multi-unmanned vehicle system and swarm intelligence. Secondly, we introduce the research contents of cooperative control of multi-unmanned vehicle system. Then the research status of cooperative control of multi-unmanned vehicle system in the domestic and overseas are introduced. Finally, this dissertation summarizes the mainstream types of architecture and algorithm of the multi-unmanned vehicle system.