Swarm Model Research Articles

Python tools for ESA’s Swarm mission: VirES for Swarm and surrounding ecosystem

ESA’s Swarm mission is a constellation probing both Earth’s interior and geospace, delivering magnetic and plasma measurements which are used to generate many derived data products. From empirical magnetic field models of the core, crust, ionosphere, and magnetosphere, to multi-point estimates of ionospheric currents and in-situ plasma properties, these are challenging to navigate, process, and visualize. The VirES for Swarm platform (https://vires.services) has been built to tackle this problem, providing tools to increase usability of Swarm data products. The VirES (Virtual environments for Earth Scientists) platform provides both a graphical web interface and an API to access and visualise Swarm data and models. This is extended with a cloud-hosted development environment powered by JupyterHub (the “Virtual Research Environment/VRE”). VirES provides two API’s: the full VirES API for which a dedicated Python client is provided, viresclient, and the more interoperable Heliophysics API (HAPI). The VRE is furnished with a bespoke Python environment containing thematic libraries supporting science with Swarm. This service aims to ease the pathway for scientists writing computer code to analyze Swarm data products, increase opportunities for collaboration, and leverage cloud technologies. Beyond simply providing data and model access to Python users, it is extremely helpful to provide higher-level analysis and visualization tools, and ready-to-use code recipes that people can explore and extend. Critically for space physics, this involves crossover with many other datasets and so it is highly valuable to embed such tools within the wider data and software ecosystems. Through Swarm DISC (Data, Innovation, and Science Cluster), we are tackling this through cookbooks and Python libraries. Cookbooks are built and presented using Jupyter technologies, and tested to work within the VRE. A new library we are building is SwarmPAL, which includes tools for time-frequency analysis and inversion of magnetic field measurements for electric current systems, among others, while relying on the VirES server to provide data portability and other utilities. This paper reviews the current state of these tools and services for Swarm, particularly in the context of the Python in Heliophysics Community, and the wider heliophysics and geospace data environment.

Self-Adapting Particle Swarm Optimization for continuous black box optimization

This paper introduces a new version of a hyper-heuristic framework: Generalized Self-Adapting Particle Swarm Optimization with samples archive (M-GAPSO). This framework is based on the authors previous works on hybridization of optimization algorithms and enhancing population based optimization with model based optimization. The paper presents the structure of the proposed framework and analyzes the impact of its modules on the final system performance. M-GAPSO hybridizes Particle Swarm Optimization, Differential Evolution and model based optimizers. A ratio of particular algorithms within a population is regulated by an adaptation scheme. The applicability of the proposed hybrid method to black-box optimization is verified on 24 continuous benchmark functions from the COCO test set and 29 functions from the CEC-2017 test set. On the BBOB test set a hybrid of PSO and DE with adaptation obtained 11 significantly better and 2 significantly worse results on 5 and 20 dimensional functions than the basic DE. Further inclusion of the model based optimizers led to 15 significantly better and 2 significantly worse results compared to the PSO-DE hybrid. On the CEC-2017 test set, M-GAPSO was significantly better than both Red Fox Optimization and Dual Opposition-Based Learning for Differential Evolution (DOBL) on 7 functions in 30 dimensions and 12 functions in 50 dimensions.

Intelligent Building Space Layout and Optimization Design Method Based on Biological Population Simulation

Smart buildings can store various types of data, analyze data at a faster speed, and quickly provide users with the most accurate and high-quality intelligent services through technical means. The main purpose is to meet the needs of users, to provide communication and a series of knowledge services for all professional participants, and to provide comfortable working resources and working environment for all professional participants to ensure the smooth implementation of the project and meet the construction engineering requirements. In this study, the spatial layout and optimization of intelligent buildings are carried out based on biological population simulation, and the following conclusions are drawn: (1) The emergence of multicore or multicore graphics converters reduces the cost and popularity of high-performance software platforms, and provides faster computing speeds for applications. A new platform and implementation method have been developed. Comparing marine biopopulation models relies on the i4Ocean platform. The i4Ocean platform is a computer platform for seascape information and virtual reality applications, including view management, production engine, and MVC core framework. (2) The swarm model simulates the movement of fish in a virtual ocean. Determine their behavioral changes based on determined behavioral conditions (e.g., in position, position, and velocity). As everyone in the group moves, the entire group is monitored for behavior. (3) Intelligent buildings involve many aspects of the social machine, such as building construction, which not only affects architecture, but also design. Smart construction helps improve quality, shorten production time, save resources, and control costs. It is an important part of the structural transformation of the supply side of the construction industry, and an important tool for the structural adjustment and modernization of the construction industry and greenhouses. (4) X2View is like the most popular configuration king, with integrated functions. Project software is placed on the X2View and sent to the door or touch screen for processing and monitoring. In the driver configuration interface, you can set the application frame time of the monitoring node and the real-time measurement time of the record value recording time frame.

Modeling Trust Decision-Making of Indonesian Food and Beverage SME Groups in the Adoption of Industry 4.0

This study aimed to model a trust decision-making of Indonesian small and medium-sized enterprise (SME) groups in the adoption of Industry 4.0 namely, ergonomic, machinery, and e-commerce technology. The data on trust and its constraints were collected through a questionnaire, and formulated in a Kansei fitness function. The trust was modeled by Swarm Modeling (SM) to extract critical constraints. Traveling salesman problem-based Ant Colony Optimization (ACO) was used to determine the optimum decision-making path. The simulation indicated that the perception of technology benefit limited the adoption of Industry 4.0. The three optimal trust decision-making paths were generated on Java, Sumatera and Nusa Tenggara groups.

An Efficient Algorithm for the Berth and Quay Crane Assignments Considering Operator Performance in Container Terminal Using Particle Swarm Model

In the existing literature, the berthing operations, the quay crane assignments, and the scheduling problems were usually conducted without considering the worker performances (WPs) and the yard truck tasks (YTTs). However, professionals in situ corroborate the crucial effect of WPs and the yard YTTs on quay crane performance and efficiency. This study introduced a new feasible model for investigating the berth and the quay crane assignments based on the scheduling problem, including worker performances and yard truck deployment constraints. First, a mixed-integer programming (MIP) model is implemented to reduce the vessel’s departure time. Then, a particle swarm optimization (PSO) algorithm is introduced to solve the problems. The Dar es Salaam port is selected as a case study to test the proposed model with a real-time dataset that was collected from a multinational company managing container terminals. The results show the efficiency and the accuracy of the proposed model. The PSO algorithm is 86% and 62% more time-saving than MILP and T2S solutions for a small number of containers, respectively. Additionally, the PSO solution is 73% and 53% time-saving for a medium number of containers than MILP and T2S models, respectively. Finally, the present study proposes consideration of the worker assignment and the yard truck deployment during the planning phase.

Multistage Clustering-Based Localization for Remote UAV Swarm: A Coalitional Game Framework

In the GNSS-denied localization scenario, only received signals and corresponding distance measurements are available. Based on that, in this letter, we construct a multistage clustering-based model for UAV swarm. We characterize the proposed model as a coalition formation game (CFG) and provide corresponding preference criteria for algorithm design. A tree-like multistage clustering mechanism is adopted based on a coalitional graph game (CGG). Each cluster (local map) performs localization calculation and then merges through neighboring drones (NDs) stage by stage. The simulation results show that the proposed scheme can achieve better localization accuracy than the comparison algorithms and is more robust for irregular network topologies.

A Generalized Gazi–Passino Model With Coordinate-Coupling Matrices for Swarm Formation With Rotation Behavior

In this article, a kinematic continuous time swarm model is considered by extending the results in the paper “A class of attractions/repulsion functions for stable swarm aggregations” (as shown in the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">International Journal of Control</i> , vol. 77, pages 1567–1579). The extension regards a more general class of attraction/repulsion functions that can be used to explain the formation of rotational patterns in a swarm of agents. The main characteristic of this model is the introduction of two coordinate-coupling matrices weighting both the attractive and the repulsive interactions among the agents. A stability analysis is presented to characterize the swarm in terms of size and cohesiveness. Moreover, a class of attraction/repulsion functions is presented to guarantee the cohesiveness of the swarm in a polytopic region and a steady-state motion of the agents in a rotational frame around the swarm centroid. Numerical simulations are provided to illustrate the obtained results.

A Swarm-Based Distributed Model Predictive Control Scheme for Autonomous Vehicle Formations in Uncertain Environments.

In this article, a novel distributed model predictive control architecture is proposed for the coordination and control of multivehicle formations moving within uncertain environments. As one of its main merits, multiagent swarm modeling and leader-follower configurations are jointly exploited within an ad hoc model predictive control framework to reduce as much as possible the use of onboard sensors that is essential in long-range missions. Moreover, the feasibility and asymptotic closed-loop stability of the resulting scheme are formally proved. Finally, a laboratory experiment is used to show the effectiveness of the proposed algorithm with particular attention to the follower capability of operating in a so-called blind fashion.

Research on Web GUI Image Recognition System Based on Improved Convolutional Neural Network

In this paper, a MobileNet V2 convolutional neural network depending on L2 regularization method, a amended particle swarm model and Dropout method are constructed in a bid for enhancing the accuracy and speed of Web GUI image recognition for establishing Web Web GUI image recognition system of Web GUI test. Firstly, an improved MobileNet V2 convolutional neural network is constructed. Secondly, the basic models of L2 regularization method, improved particle swarm method and Dropout method are studied, the improved MobileNet V2 convolution neural network optimization algorithm is proposed, and the basic model of image processing is designed. Finally, simulation analysis is carried out on Web GUI image recognition through using the amended convolutional neural network on basis of MINIST data set as the research object. The simulation results illustrate that the amended convolutional neural network proposed in this study is more accurate and efficient in Web GUI image recognition.

Modeling method of unmanned aerial vehicle swarm behavior based on spatiotemporal hybrid Petri net

The more and more widely used UAV swarm operations have received great attention in the new global military revolution of informatization, and the integrated modeling of UAV swarms has great significance and value for the testing and verification of combat modes. Aiming at the modeling and simulation requirements of combat scenarios, taking the collaborative combat process of heterogeneous UAV swarms as the research object, starting from the modeling of a single UAV, on the basis of the formalization and mathematical description of the single combat process, this paper employs Petri nets based on the hybridization of time and space to describe the discrete states and continuous processes of heterogeneous UAV swarm systems, and effectively solves the problems of the fusion between physics and computing processes, and modeling of interactive events in swarm systems. UPPAAL is selected to formally verify the modeling of UAV swarm strike mission, which shows that the proposed modeling method is feasible and effective.

Bayesian optimization of distributed neurodynamical controller models for spatial navigation.

Dynamical systems models for controlling multi-agent swarms have demonstrated advances toward resilient, decentralized navigation algorithms. We previously introduced the NeuroSwarms controller, in which agent-based interactions were modeled by analogy to neuronal network interactions, including attractor dynamics and phase synchrony, that have been theorized to operate within hippocampal place-cell circuits in navigating rodents. This complexity precludes linear analyses of stability, controllability, and performance typically used to study conventional swarm models. Further, tuning dynamical controllers by manual or grid-based search is often inadequate due to the complexity of objectives, dimensionality of model parameters, and computational costs of simulation-based sampling. Here, we present a framework for tuning dynamical controller models of autonomous multi-agent systems with Bayesian optimization. Our approach utilizes a task-dependent objective function to train Gaussian process surrogate models to achieve adaptive and efficient exploration of a dynamical controller model’s parameter space. We demonstrate this approach by studying an objective function selecting for NeuroSwarms behaviors that cooperatively localize and capture spatially distributed rewards under time pressure. We generalized task performance across environments by combining scores for simulations in multiple mazes with distinct geometries. To validate search performance, we compared high-dimensional clustering for high- vs. low-likelihood parameter points by visualizing sample trajectories in 2-dimensional embeddings. Our findings show that adaptive, sample-efficient evaluation of the self-organizing behavioral capacities of complex systems, including dynamical swarm controllers, can accelerate the translation of neuroscientific theory to applied domains.

DEVELOPMENT AND RESEARCH OF DISTRIBUTED CONTROL ALGORITHMS FOR SWARM INTELLIGENCE SYSTEMS

The subject of this paper is the development and research of distributed algorithms for organizing collective behavior in swarm robotic systems in order to solve various applied problems with these systems. Using the example of solving the problem of collective cleaning of a given area, several swarm algorithms based on classical swarm models are constructed and studied: random walk model, Reynolds model, bacterial search algorithm, stochastic gradient method. The results of numerical experiments comparing the efficiency of the proposed methods are presented

The Drought Events over the Amazon River Basin from 2003 to 2020 Detected by GRACE/GRACE-FO and Swarm Satellites

The climate anomaly in the Amazon River basin (ARB) has a very important influence on global climate change and has always been the focus of scientists from all over the world. To fill the 11-month data gap between Gravity Recovery and Climate Experiment (GRACE) and GRACE Follow-On (GRACE-FO) missions, we fused the TWSC results from six GRACE solutions by using the generalized three-cornered hat and the least square method to improve the reliability of TWSC results, and then combined Swarm data to construct an uninterrupted long time series of a TWSC-based drought index (GRACE/Swarm-DSI). The drought index was used to detect and characterize the drought events in the ARB between 2003 and 2020. The results show that GRACE/Swarm-DSI has a strong correlation with Self-Calibrating Palmer Drought Severity Index (SCPDSI) (0.6345), Standardized Precipitation Evapotranspiration Index-3 (SPEI-3) (0.5411), SPEI-6 (0.6377) and SPEI-12 (0.6820), and the Nash–Sutcliffe efficiency between GRACE/Swarm-DSI and the above four drought indices are 0.3348, 0.2786, 0.4044 and 0.4627, respectively. Eleven drought events were identified in the ARB during the study period, and the 2005, 2010 and 2016 droughts are the most severe and the longest. The correlation between GRACE/Swarm-DSI and precipitation (PPT) (the correlation coefficient is 0.55 with a 2-month delay) is higher than that of evapotranspiration (ET) (the correlation coefficient is −0.18 with a 12-month delay). It explains that less PPT is the main cause of drought events in the ARB. The influence of PPT is greater in the plains than the one in the mountains and the response time of GRACE/Swarm-DSI to PPT is 1~2 months in most regions. Our results provide a certain reference for the hydrological application of the Swarm model in filling the gap between GRACE and GRACE-FO missions.

Optimization Model of Financial Market Portfolio Using Artificial Fish Swarm Model and Uniform Distribution.

The central issue in finance is how to select a portfolio in the financial market. The traditional artificial fish swarm algorithm (AFSA) is optimized in this paper, and the improved AFSA is used to solve the portfolio model. This model generates a uniform distribution operator using uniform distribution and combines it with the basic fish swarm algorithm. Uniform variation occurs when the variance of the optimal value of continuous convergence is within the allowable error. In this manner, the fish can escape the trap of the local extremum, obtaining the global optimal state. To validate the feasibility of improving AFSA, this paper conducts simulation experiments on portfolio problems using MATLAB tools. Experiments show that this model has an accuracy of 93.56 percent, which is 8.43 percent higher than that of the NSGA-II model and 3.76 percent higher than that of the multiobjective optimization model. The experiment shows that the algorithm in this paper can solve these types of problems well and that, using this model, the optimal portfolio investment decision scheme satisfying investors can be obtained. The optimized AFSA presented in this paper can serve as an important reference for investment portfolios and has a wide range of application possibilities in the investment market.

A Survey on Swarm Microrobotics

The small size and wireless actuation of microrobots make them potential candidates for minimally invasive medicine. To advance microrobots to future clinical application, microrobotics researchers have investigated a number of key issues, in which swarm control is a primary challenge and is attracting increasing attention. As a single microrobot has limited volume and surface area, clinically relevant tasks, including <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">in-vivo</i> tracking, usually require simultaneous control of a large swarm of microrobots. Unlike macroscale robots, implementing on-board actuators and sensors for microrobots is challenging, which differentiates swarm microrobotics from other swarm robotics approaches. This article systematically summarizes the state of the art for this emerging field, including actuation systems with different power sources, swarm behaviors modeling and simulation, swarm control strategies, and targeted biomedical applications. Actuation principles of microrobot swarms are categorized in detail, and critical comparisons are made to provide guidance and insight for future swarm microrobotics researchers. Considering the unique features of swarm microrobotics compared to traditional swarm robotics, this article also emphasizes the modeling, simulation, and control of microrobot swarms. Furthermore, recent biomedical applications of microrobot swarms are summarized to illustrate specific application scenarios. Finally, we provide an assessment of the future directions of swarm microrobotics.

Mission-Oriented Real-Time Health Assessments of Microsatellite Swarm Orbits

Real-time health assessments are of great importance for the safe and stable operation of in-orbit swarms. To solve the problems of existing real-time health assessments of microsatellite swarms, such as the difficulty of selecting a multisource and assessment calculation normalization, this paper proposes a real-time health assessment method applicable to mission-oriented swarms. The method divides the microsatellite swarm into three levels: single satellite, intersatellite communication link and swarm effectiveness, which establish a multilevel index system by adopting the reliability evaluation based on random failure and failure by loss, a health evaluation based on natural connectivity, and a real-time dynamic analysis based on swarm topology. For the swarm effectiveness during the mission, the multilevel index and the entropy weight method are used to construct the effectiveness evaluation model of the whole swarm, and the health state evaluation of the swarm is realized based on the variable weight principle. The simulation results show that this method can quantify the health state of the microsatellite swarm in real-time, and it can predict the health state after the fault without maintenance.

Parallel multi-swarm cooperative particle swarm optimization for protein–ligand docking and virtual screening

BackgroundA high-quality docking method tends to yield multifold gains with half pains for the new drug development. Over the past few decades, great efforts have been made for the development of novel docking programs with great efficiency and intriguing accuracy. AutoDock Vina (Vina) is one of these achievements with improved speed and accuracy compared to AutoDock4. Since it was proposed, some of its variants, such as PSOVina and GWOVina, have also been developed. However, for all these docking programs, there is still large room for performance improvement.ResultsIn this work, we propose a parallel multi-swarm cooperative particle swarm model, in which one master swarm and several slave swarms mutually cooperate and co-evolve. Our experiments show that multi-swarm programs possess better docking robustness than PSOVina. Moreover, the multi-swarm program based on random drift PSO can achieve the best highest accuracy of protein–ligand docking, an outstanding enrichment effect for drug-like activate compounds, and the second best AUC screening accuracy among all the compared docking programs, but with less computation consumption than most of the other docking programs.ConclusionThe proposed multi-swarm cooperative model is a novel algorithmic modeling suitable for protein–ligand docking and virtual screening. Owing to the existing coevolution between the master and the slave swarms, this model in parallel generates remarkable docking performance. The source code can be freely downloaded from https://github.com/li-jin-xing/MPSOVina.

A Dual Level Analysis with Evolutionary Computing and Swarm Models for Classification of Leukemia.

One of the major reasons of mortality in human beings is cancer, and there is an absolute necessity for doctors to identify and treat a person suffering from it. Leukemia is a group of blood cancers that usually originates in the bone marrow and results in very high number of abnormal cells. For the diagnosis of cancer, microarray data serves as an important clinical application and serves as a great aid to the entire medical community. The dimensionality of the microarray data is too high, and so selection of suitable genes is quite an important step for the improvement of data classification. Therefore, for the prediction and diagnosis of cancer, there is an utmost necessity to select the most informative genes. In this work, Minimum Redundancy Maximum Relevance (MRMR), Signal to Noise Ratio (SNR), Multivariate Error Weight Uncorrelated Shrunken Centroid (EWUSC), and multivariate correlation-based feature selection (CFS) are chosen as initial feature selection techniques. Then, to select the most informative genes, five different kinds of evolutionary optimization techniques too are incorporated here such as African Buffalo Optimization (ABO), Artificial Bee Colony Optimization (ABCO), Cockroach Swarm Optimization (CSO), Imperialist Competitive Optimization (ICO), and Social Spider Optimization (SSO). Finally, the optimized values are fed through classification process and the best results are obtained when multivariate CFS with SSO is utilized and classified with Probabilistic Neural Network (PNN), and a high classification accuracy of 95.70% is obtained.

A Good Relative Percentage Increase (RPI) of Variant Job Scheduling Using Artificial Bee Colony (ABC)

Artificial Bee Colony (ABC) which is a development of the intelligent swarm model and is a branch of artificial intelligence based on self-organization systems. Artificial Bee Colony (ABC) is an intelligent algorithm that is inspired by the food search process carried out by bees. This is like what is done when there are many jobs that need to find the optimal value, where each job to be processed has a specific route of operations to be performed on a set of machines, and a different flow shop and variant: all jobs follow the same machine sequences. We will focus on the latter. In this study, ABC is implemented to optimize work scheduling, in this case 7 different variations are used with mxn values between 10x3 to 40x15 on 10 to 40 jobs. To evaluate the results, the Relative Percentage Increase (RPI) has been used in the test with an achievement range between 1.9 to 18.9.

About Modeling Digital Twins of a Social Group

The object of the study is mathematical modeling methods. The subject of the study is the application of mathematical methods in modeling digital twins of a social group. The aim of the work is to model the digital counterparts of a social group. A digital double is a digital copy of a physical object or process, with the right approach, it helps to improve the main and auxiliary business processes. This concept is part of the fourth industrial revolution and is designed to help detect problems faster, find out what will happen to the original in different conditions and, as a result, produce better products. In this article, some applied aspects are considered, the main provisions of the mathematical theory of digital twins of social groups are presented. To solve the problem of creating a digital double of a social group (students) as one of the tools, the authors proposed to use the technologies of population algorithms. The novelty of the research consists in the application of the swarm part algorithm for modeling digital twins of a social group. The particle swarm method was chosen as a research tool. As the social group under study finds the optimal position in space, so the element of the digital twin of the particle swarm model based on them can search in space, in particular, the extremes of functions. Which, for example, is applicable to finding the minimum of the loss function in machine learning. A graphical simulation in the Java Script language was performed using the three library.js. Data processing was performed using the C# Job System, which provides parallelization of computing processes and is integrated into the Entity Component System. A program was implemented that simulates the activity of a student group as one of the constituent elements of a digital twin of a social group. Swarm algorithms are promising in the field of practical application. On their basis, it is possible not only to solve the problems of digital twins, but also to manage groups of robots, robotic systems and complexes.