Swarm Intelligence Research Articles

Single search investigation of various searches in recent swarm-based metaheuristics

Swarm intelligence has become a popular framework for developing new metaheuristics or stochastic optimization methods in recent years. Many swarm-based metaheuristics are developed by employing multiple searches whether it is conducted through swarm split, serial searches, stochastic choose. Unfortunately, many existing studies that introduced new metaheuristic focused on assessing the performance of the proposed method as a single package. On the other hand, the contribution of each search constructing the metaheuristic is still unknown as the consequence of the missing of single or individual search assessment. Based on this problem, this work is aimed to investigate the performance of five directed searches that are commonly found in recent swarm-based metaheuristics individually. These five searches include: motion toward the highest quality member, motion relative to a randomly chosen member, motion relative to a random solution along the space, motion toward a randomly chosen higher quality member, and motion toward the middle among higher quality members. In this assessment, these five searches are challenged to find the optimal solution of 23 classic functions. The result shows that the first, fourth, and five searches perform better than the second and third searches.

Honey bee as an alternative model invertebrate organism

Insects perfectly fit the flagship principle of animal research – 3R: to reduce (the number of animals), to replace (animals with alternative models) and to refine (methods). Bees have the most important advantages of a model organism: they cause minimal ethical controversy, they have a small and fully known genome, and they permit the use of many experimental techniques. Bees have a fully functional DNMT toolkit. Therefore, they are used as models in biomedical/genetic research, e.g. in research on the development of cancer or in the diagnostics of mental and neuroleptic diseases in humans. The reversion of aging processes in bees offers hope for progress in gerontology research. The cellular mechanisms of learning and memory coding, as well as the indicators of biochemical immunity parameters, are similar or analogous to those in humans, so bees may become useful in monitoring changes in behavior and metabolism. Bees are very well suited for studies on the dose of the substance applied to determine the lethal dose or the effect of a formula on life expectancy. Honeybees have proven to be an effective tool for studying the effects of a long-term consumption of stimulants, as well as for observing behavioral changes and developing addictions at the individual and social levels, as well as for investigating the effects of continuously delivering the same dose of a substance. The genomic and physiological flexibility of bees in dividing tasks among workers in a colony makes it possible to create a Single- Cohort Colony (SCC) in which peers compared perform different tasks. Moreover behavioral methods (e.g. Proboscis Extension Reflex – PER, Sting Extension Reflex – SER, free flying target discrimination tasks or the cap pushing response) make it possible to analyse changes occurring in honeybee brains during learning and remembering. Algorithms of actions are created based on the behavior of a colony or individual, e.g. Artificial Bee Colony Algorithm (ABCA). Honeybees are also model organisms for profiling the so-called intelligence of a swarm or collective intelligence. Additionally, they serve as models for guidance systems and aviation technologies. Bees have inspired important projects in robotics, such as B-droid, Robobee and The Green Brain Project. It has also been confirmed that the apian sense of smell can be used to detect explosive devices, such as TNT, or drugs (including heroin, cocaine, amphetamines and cannabis). This inconspicuous little insect can revolutionize the world of science and contribute to the solution of many scientific problems as a versatile model.

A dual-adaptive stochastic reinforcement chimp optimization algorithm for fire detection and multidimensional problem solving

Chimp optimization algorithm (CHOA) is a recently developed nature-inspired technique that mimics the swarm intelligence of chimpanzee colonies. However, the original CHOA suffers from slow convergence and a tendency to reach local optima when dealing with multidimensional problems. To address these limitations, we propose TASR-CHOA, a twofold adaptive stochastic reinforced variant. The TASR-CHOA algorithm integrates two novel methodologies: a stochastic approach to improve the speed at which convergence is achieved and a dual adaptive weighting approach to optimize the exploration of early patterns, which refer to initial trends or behaviors in the algorithm’s convergence process during the early stages of iterations and the exploitation of subsequent tendencies, indicating how these initial trends develop over time as the algorithm iterates and refines its search. To evaluate TASR-CHOA, we apply it to 29 conventional optimization benchmark functions, 10 IEEE CEC-06 benchmarks, 30 complicated IEEE CEC-BC benchmark functions, and ten well-known benchmark real-world challenges. We evaluate TASR-CHOA against 4 categorical optimization techniques as well as 18 top IEEE CEC-BC algorithms. Based on our broad investigation done using three statistical tests, we claim that TASR-CHOA outperforms the majority of the algorithms since within a position takes the best place, 54 out of 73 evaluation functions and engineering problems. In other cases, the results are almost the same as those of SHADE and CMA-ES over several comparisons. As an illustrative application of this joint approach, a computer-aided fire detection task is performed using a deep convolutional neural network combined with TASR-CHOA. We also outline the algorithm executed in steps, indicating computational complexity, which is O(NI×NV) + O(NI×NV×6) + O(NI×NV + 2×NI×NV) as a function of number of individuals (NI) and dimensions (NV).

Swarm intelligence and bio-inspired algorithms based active power loss reduction in microgrids using optimal placement and sizing of renewable distributed generators

Renewable energy sources now play a crucial role in meeting the world's growing energy needs sustainably. These sources, such as solar and wind energy, help reduce carbon emissions and protect the environment, making them an essential component of future energy strategies. In this paper, one of swarms’ intelligences algorithms called particle swarm optimization (PSO) and one of the most general bio-inspired metaheuristic methods called BAT algorithm are applied to determine the optimal placement and sizing of renewable distributed generators (OPSRDG) in distributed network. The focus is on enhancing energy efficiency and reduced dependency on the main grid by reducing power losses, improved voltage profile, enhanced reliability, stability enhancing the overall system stability and performance of the grid. Compared with recently published results, the obtained results are promising and demonstrate the effectiveness and robustness of the proposed approach to solve OPSRDG problems. When the DG units are optimally integrated into the system, the power loss reductions ranged from 48.23% to 71.57%. This represents a significant improvement over conventional methods, making it a promising contribution to society and academia.

Exploring phase transitions in CdSe: a machine learning and swarm intelligence approach

The phase transition of cadmium selenide (CdSe) from wurtzite to rocksalt structure has been the subject of extensive research. In this study, we present a novel approach combining machine learning potentials with swarm intelligence-based pathway sampling to elucidate the complex phase transition mechanisms in CdSe. We developed an accurate machine-learning (ML) potential for CdSe, validated against density functional theory calculations, achieving mean absolute errors (MAEs) of 1.8 meV/atom for energies and 33 meV/Å for forces. This potential was integrated with the pathway sampling via swarm intelligence and graph theory (PALLAS) method to explore the potential energy landscape and identify low-energy transition pathways. Our simulations revealed a complex network of transition pathways, and we discovered a multi-step transition mechanism involving an unexpected zinc blende intermediate phase, which appears to play a crucial role in facilitating the transition between wurtzite and rocksalt structures. This finding provides new insights into the structural flexibility of CdSe and offers an explanation for experimentally observed phenomena such as wurtzite/zinc blende coexistence in nanostructures. Our approach not only advances the fundamental understanding of phase transitions in CdSe but also establishes a powerful computational framework for exploring complex materials phenomena, opening new avenues for materials design and discovery in semiconductor systems.

Solving Multi-Objective Satellite Data Transmission Scheduling Problems via a Minimum Angle Particle Swarm Optimization

With the increasing number of satellites and rising user demands, the volume of satellite data transmissions is growing significantly. Existing scheduling systems suffer from unequal resource allocation and low transmission efficiency. Therefore, effectively addressing the large-scale multi-objective satellite data transmission scheduling problem (SDTSP) within a limited timeframe is crucial. Typically, swarm intelligence algorithms are used to address the SDTSP. While these methods perform well in simple task scenarios, they tend to become stuck in local optima when dealing with complex situations, failing to meet mission requirements. In this context, we propose an improved method based on the minimum angle particle swarm optimization (MAPSO) algorithm. The MAPSO algorithm is encoded as a discrete optimizer to solve discrete scheduling problems. The calculation equation of the sine function is improved according to the problem’s characteristics to deal with complex multi-objective problems. This algorithm employs a minimum angle strategy to select local and global optimal particles, enhancing solution efficiency and avoiding local optima. Additionally, the objective space and solution space exhibit symmetry, where the search within the solution space continuously improves the distribution of fitness values in the objective space. The evaluation of the objective space can guide the search within the solution space. This method can solve multi-objective SDTSPs, meeting the demands of complex scenarios, which our method significantly improves compared to the seven algorithms. Experimental results demonstrate that this algorithm effectively improves the allocation efficiency of satellite and ground station resources and shortens the transmission time of satellite data transmission tasks.

Использование алгоритмов роевого интеллекта для определения состава мультипроекта

One of the promising ways to reduce the dependence of domestic industry on the supply of critical goods, components and raw materials necessary for the construction and effective functioning of multi-stage production and technological chains is to intensify processes for their import substitution, including through various measures of state support. However, the critical need for a wide range of products requires the selection of the most “promising” projects for inclusion in program-target documents using a set of criteria (sometimes even non-financial). As a result, there arises an urgent scientific and practical task of developing approaches to the formation of multi-projects (a set of projects) that can qualify for state support under various programs to reduce import dependence and overcome the technological backwardness of Russian industry, based on the use of modern economic and mathematical methods. In the application to this task, a multi-project can be represented as a “set” (unrelated projects), a “chain” (rigid sequence of projects) or a “network” (projects with complex logical-temporal interrelations). The specifics of each type determine the conditions and impose restrictions on the processes of selecting components for inclusion in their composition, which consists of finding the best combination of projects and/or programs, i. e., it is reduced to a task of conditional multidimensional optimization. In the absence of a requirement to find a “strictly optimal” composition, one can use metaheuristic methods that are capable of finding solutions close to these in an “acceptable” time. Among them, the largest and most well-known class are swarm intelligence algorithms based on the principles of collective behavior of a population of living organisms. To form the composition of multi-projects, the article proposes to use algorithms inspired by the collective behavior of a pack of wolves (Grey Wolf Optimizer) and a school of fish (Fish School Search) to satisfy their food needs. To increase the efficiency of their use for solving the task of finding the best composition of a “set” and “network” of projects, their hybridization with fuzzy logic methods (in particular, fuzzy clustering and fuzzy-logical inference) was proposed.

Application of Immunological and Swarm Intelligence Learning-Based Algorithm for Industrial Grade Computer Sales Prediction

ABSTRACT This paper strives to raise the imitating effectiveness of radial basis function-based neural network (RNNet) through biological learning (BL) and swarm intelligence (SI) optimization algorithms. Latter, the artificial immune system (AIS) and particle swarm optimization (PSO) algorithms are utilized for RNNet to regulate. The proposed synthesis of AIS-inspired and PSO-inspired (SAIPS) algorithm incorporates the complementary development and prospecting abilities to realize optimized resolution. The attribute of population variation has shown high frequency to meet the global optimum to replace local optimum being restricted and outperforms in five standard nonlinear trial functions. The experimental results have represented that the consolidation of AIS-inspired and PSO-inspired algorithms is an outstanding approach and therefore a hybrid algorithm is proposed, which aims to obtain an expression that can cultivate optimum precision among related algorithms in this research. The algorithm then evaluates results from five standard inspections and an empirical industrial grade computer (IgC) sales prediction instance in Taiwan, which reveals that the proposed SAIPS algorithm exceeds the performance among related algorithms as well as the relevant auto-regressive integrated moving average (ARIMA) models in terms of accuracy and time spent.

Energy-Efficient Collision-Free Machine/AGV Scheduling Using Vehicle Edge Intelligence

With the widespread use of autonomous guided vehicles (AGVs), avoiding collisions has become a challenging problem. Addressing the issue is not straightforward since production efficiency, collision avoidance, and energy consumption are conflicting factors. This paper proposes a novel edge computing method based on vehicle edge intelligence to solve the energy-efficient collision-free machine/AGV scheduling problem. First, a vehicle edge intelligence architecture was built, and the corresponding state transition diagrams for collision-free scheduling were developed. Second, the energy-efficient collision-free machine/AGV scheduling problem was modeled as a multi-objective function with electric capacity constraints, where production efficiency, collision prevention, and energy conservation were comprehensively considered. Third, an artificial plant community algorithm was explored based on the edge intelligence of AGVs. The proposed method utilizes a heuristic search and the swarm intelligence of multiple AGVs to realize energy-efficient collision-free scheduling and is suitable for deploying on embedded platforms for edge computing. Finally, a benchmark dataset was developed, and some benchmark experiments were conducted, where the results revealed that the proposed heuristic method could effectively instruct multiple automatic guided vehicles to avoid collisions with high energy efficiency.

CSTR parameter identification and PID control optimization based on improved swarm intelligence algorithm

Abstract Aiming at the problems of strong coupling and large hysteresis that exist in the production process of a typical thermal object continuous stirred reactor (CSTR), which make it difficult to recognize the system model parameters and control the temperature, an improved firefly algorithm is proposed to recognize the system parameters, and its recognition accuracy is higher than that of the original firefly algorithm; and an improved sparrow search algorithm (BCGSSA) is used to control the temperature of the CSTR system by combining the BCGSSA algorithm with PID control, which significantly improves the dynamic performance of the CSTR system. Then an improved sparrow search algorithm (BCGSSA) is combined with PID control to control the temperature of the CSTR system, which significantly improves the dynamic performance of the CSTR, and the improved algorithm (BCGSSA) has good control accuracy and robustness.

Adaptive Navigation Based on Multi-Agent Received Signal Quality Monitoring Algorithm

In the era of industrial evolution, satellites are being viewed as swarm intelligence that does not rely on a single system but multiple constellations that collaborate autonomously. This has enhanced the potential of the Global Navigation Satellite System (GNSS) to contribute to improving position, navigation, and timing (PNT) services. However, multipath (MP) and non-line-of-sight (NLOS) receptions remain the prominent vulnerability for the GNSS in harsh environments. The aim of this research is to investigate the impact of MP and NLOS receptions on GNSS performance and then propose a Received Signal Quality Monitoring (RSQM) algorithm. The RSQM algorithm works in two ways. Initially, it performs a signal quality test based on a fuzzy inference system. The input parameters are carrier-to-noise ratio (CNR), Normalized Range Residuals (NRR), and Code–Carrier Divergence (CCD), and it computes the membership functions based on the Mamdani method and classifies the signal quality as LOS, NLOS, weak NLOS, and strong NLOS. Secondly, it performs an adaptive navigation strategy to exclude/mask the affected range measurements while considering the satellite geometry constraints (i.e., DOP≤2). For this purpose, comprehensive research to quantify the multi-constellation GNSS receiver with four constellation configurations (GPS, BeiDou, GLONASS, and Galileo) has been carried out in various operating environments. This RSQM-based GNSS receiver has the capability to identify signal quality and perform adaptive navigation accordingly to improve navigation performance. The results suggest that GNSS performance in terms of position error is improved from 5.4 m to 2.3 m on average in the complex urban environment. Combining the RSQM algorithm with the GNSS has great potential for the future industrial revolution (Industry 5.0), making things automatic and sustainable like autonomous vehicle operation.

Particle swarm optimization with local search for height-map surface reconstruction from point clouds in reverse engineering

AbstractSurface reconstruction is a classical process in industrial engineering and manufacturing, particularly in reverse engineering, where the goal is to obtain a digital model from a physical object. For that purpose, the real object is typically scanned or digitized and the resulting point cloud is then fitted to mathematical surfaces through numerical optimization. The choice of the approximating functions is crucial for the accuracy of the process. Real-world objects such as manufactured workpieces often require complex nonlinear approximating functions, which are not well suited for standard numerical methods. In a previous paper presented at the ISMSI 2023 conference, we addressed this issue by using manually selected approximation functions via optimization through the cuckoo search algorithm with Lévy flights. Building upon that work, this paper presents an enhanced and extended method for surface reconstruction by using height-map surfaces obtained through a combination of exponential, polynomial and logarithmic functions. A feasible approach for this goal is to consider continuous bivariate distribution functions, which ensures consistent models along with good mathematical properties for the output shapes, such as smoothness and integrability. However, this approach leads to a difficult multivariate, constrained, multimodal continuous nonlinear optimization problem. To tackle this issue, we apply particle swarm optimization, a popular swarm intelligence technique for continuous optimization. The method is hybridized with a local search procedure for further improvement of the solutions and applied to a benchmark of 15 illustrative examples of point clouds fitted to different surface models. The performance of the method is analyzed through several computational experiments. The numerical and graphical results show that the method is able to recover the shape of the point clouds accurately and automatically. Furthermore, our approach outperforms other alternative methods significantly in terms of the numerical errors. We conclude that our method can be successfully applied to the reconstruction of manufactured workpieces in real industrial settings.

A Review of Smart Camera Sensor Placement in Construction

Cameras, with their low cost and efficiency, are widely used in construction management and structural health monitoring. However, existing reviews on camera sensor placement (CSP) are outdated due to rapid technological advancements. Furthermore, the construction industry poses unique challenges for CSP implementation due to its scale, complexity, and dynamic nature. Previous reviews have not specifically addressed these industry-specific demands. This study aims to fill this gap by analyzing articles from the Web of Science and ASCE databases that focus exclusively on CSP in construction. A rigorous selection process ensures the relevance and quality of the included studies. This comprehensive review navigates through the complexities of camera and environment models, advocating for advanced optimization techniques like genetic algorithms, greedy algorithms, Swarm Intelligence, and Markov Chain Monte Carlo to refine CSP strategies. Simultaneously, Building Information Modeling is employed to consider the progress of construction and visualize optimized layouts, improving the effect of CSP. This paper delves into perspective distortion, the field of view considerations, and the occlusion impacts, proposing a unified framework that bridges practical execution with the theory of optimal CSP. Furthermore, the roadmap for future exploration in the CSP of construction is proposed. This work enriches the study of construction CSP, charting a course for future inquiry, and emphasizes the need for adaptable and technologically congruent CSP approaches amid evolving application landscapes.

Comparative analysis of accuracy and computational complexity across 21 swarm intelligence algorithms

Nonlinear, complex optimization problems are prevalent in many scientific and engineering fields. Traditional algorithms often struggle with these problems due to their high dimensionality and intricate nature, making them time-consuming. Many researchers have proposed new metaheuristic algorithms inspired by biological behaviors in nature, which comparatively show higher performance and accuracy than traditional optimization algorithms. Nature-inspired algorithms, particularly those based on swarm intelligence, offer adaptable and efficient solutions to these challenges. In recent years, swarm intelligence algorithms have made significant advancements. Classical and CEC benchmark suits are immersively useful for studying the performance of optimization algorithms. According to our literature survey, we identified that many algorithms were evaluated based on accuracy. Currently, swarm intelligence algorithms are used in many applications, and efficiency and computational complexity need to be evaluated. A broad-level study of the computational complexity and accuracy of popular swarm intelligence algorithms has not been done recently. Therefore this study we comprehensively evaluate and compare 21 bio-inspired swarm intelligence algorithms on eight non-separable unimodal, eight separable unimodal, five non-separable multimodal, seven separable multimodal functions, and two CEC 2018 many objective functions. We study the structure and mathematical model of the selected algorithms. Then we categorized selected algorithms into six different behavioral groups. We calculated the root mean square error between expected and actual values. Then we performed an RMSE cross-validation statistical test to understand how accurately an algorithm resolves an average problem. We found that Artificial Lizard Search Optimization (ALSO) is the most prominent algorithm in accuracy and efficiency. Besides that, Cat Swarm Optimization (CSO), Squirrel Search Algorithm (SSA), and Chimp Optimization Algorithm (CHOA-B) are also considered more universal algorithms. The Squirrel Search Algorithm (SSA) is ALSO’s second-best algorithm in time complexity. Wasp Swarm Algorithm (WSO), and Bat-Inspired Algorithm (BA) presented the lowest time complexity. Finally, several important issues and research directions are discussed.

Optimum arrangement of high-voltage transmission line conductors by utopian Pareto swarm intelligence

Optimum arrangement of high-voltage transmission line conductors by utopian Pareto swarm intelligence

Magnetic swarm intelligence of mass-produced, programmable microrobot assemblies for versatile task execution

Magnetic swarm intelligence of mass-produced, programmable microrobot assemblies for versatile task execution

Virtualization Resource Scheduling and Optimization Method Based on Swarm Intelligent Systems

Virtualization Resource Scheduling and Optimization Method Based on Swarm Intelligent Systems

AI and Multi-Agent Systems: Collaboration and Competition in Autonomous Environments

Cutting edge technology in intelligence involves multi agent systems (MAS) which allow autonomous agents to interact in shared environments by either working together or competing to achieve common or individual goals. This study delves into the aspects of cooperation and rivalry in MAS and illustrates their application in practical situations, like autonomous vehicles, robot’s interactions, and financial settings. In addition to that we explore the obstacles like coordination, learning and communication that come up while creating MAS frameworks and how sophisticated algorithms like deep reinforcement learning help in running these agents. By tackling both competitive interactions within MAS our goal is to offer a thorough grasp of the possible uses and upcoming paths, in this area. Emerging technologies like OpenAIs agent models play a significant role in showcasing the changing landscape of MAS and its transformative effects on various industries, like healthcare and defense. Keywords: Multi-Agent Systems (MAS), Autonomous Agents, Collaboration, Competition, Deep Reinforcement Learning, Game Theory, Distributed AI, Swarm Intelligence, Agent-Based Modeling, AI Coordination, Adversarial AI

Advancements in Machine Learning for Pipeline Integrity Management: A Comprehensive Review of Predictive and Optimization Techniques

Oil and gas pipeline networks are crucial component of energy infrastructure. However, as the integral elements of the energy transportation system are evolving towards Industry 4.0 and Smart Manufacturing, pipelines network are progressively shifting towards intelligence and digitization. The fields of asset integrity management, operation inspection, corrosion prevention, leak and intrusion detection, and flow assurance are just a few of the areas where machine learning and artificial intelligence (AI) algorithms are becoming more and more important. The predictive and optimization capabilities of these Models/ Algorithms have been leveraged by various Pipeline Network Integrity Management systems to avert pipeline failure, reduce environmental damage, and effectively allocate resources. This study reviews and gives a summary of current advancements in intelligent techniques, encompassing heuristic computations, mathematical programming, and machine learning techniques used in a pipeline network integrity management to enhance various operational and maintenance aspects. This work makes two intellectual accomplishments. Firstly, it offers a technical review of literatures, systematically synthesizing different computational intelligence and machine learning approaches previously applied, along with their methodologies, contributions, drawbacks, and comparisons. Secondly, the study recommends some nature-inspired meta-heuristic algorithms, which encompasses Evolutionary and the Swarm Intelligence Algorithms to be applied for future directions and challenges. Finally, the study underscores the potential of computational intelligence and algorithms for learning methods in predicting and optimizing the efficiency of pipeline network operation and management, emphasizing the necessity for further development of models/algorithms and application to enhance more intricate interactions between pipeline infrastructure monitoring, maintenance, and management.

Employee Turnover Prediction based on Particle Swarm Optimization - Support Vector Machine

Employee turnover is getting more and more attention in the human resources field. Unexpected turnover of employees is blamed for the loss of work handover. As a result, predicting whether employees would leave has become a crucial problem. This research aims to exploit a method combining particle swarm optimization with a support vector machine to address the employee departure prediction problem. In this study, the particle swarm optimization algorithm is used to optimize the parameter selection of the support vector machine to improve the performance of the latter. Moreover, employee information of a dataset is subject to correlation analysis before being transformed into standardization form to accelerate convergence and improve the accuracy of the support vector machine. Eventually, the support vector machine combined with particle swarm optimization is of best performance in accuracy score, precision score and F1 score, respectively reaching 0.873, 0.947 and 0.784. In conclusion, this method addresses the employee turnover prediction problem effectively which also provides a new direction for applying swarm intelligence algorithms.