In this paper, it is revealed that random exploration and attraction of the best (REAB) are two underlying procedures in many swarm intelligence algorithms. This is particularly shown in two of the most known swarm al...
详细信息
In this paper, it is revealed that random exploration and attraction of the best (REAB) are two underlying procedures in many swarm intelligence algorithms. This is particularly shown in two of the most known swarm algorithms: the particle swarm optimization (PSO) and gray wolf optimizer (GWO) algorithms. From this observation, it is here proposed that instead of building algorithms based on a narrative derived from observing some animal behavior, it is more convenient to focus on algorithms that perform REAB procedures;that is, to build algorithms to make a wide and efficient explorations of the search space and then gradually make that the best-evaluated search agent to attract the rest of the swarm. Following this general idea, two REAB-based algorithms are proposed;one derived from the PSO and one derived from the GWO, called REAB-PSO and REAB-GWO, respectively. To easily and succinctly express both algorithms, variable-sized open balls are employed. A comparison of proposed procedures in this paper and the original PSO and GWO using a controller tuning problem as a test bench show a significant improvement of the REAB-based algorithms over their original counterparts. Ideas here exposed can be used to derive new swarm intelligence algorithms.
Robot-aided cleaning auditing is pioneering research that uses autonomous robots to assess a region's cleanliness level by analyzing the dirt samples collected from various locations. Since the dirt sample gatheri...
详细信息
Robot-aided cleaning auditing is pioneering research that uses autonomous robots to assess a region's cleanliness level by analyzing the dirt samples collected from various locations. Since the dirt sample gathering process is more challenging, adapting a coverage planning strategy from a similar domain for cleaning is non-viable. Alternatively, a path planning approach to gathering dirt samples selectively at locations with a high likelihood of dirt accumulation is more feasible. This work presents a first-of-its-kind dirt sample gathering strategy for the cleaning auditing robots by combining the geometrical feature extraction and swarm algorithms. This combined approach generates an efficient optimal path covering all the identified dirt locations for efficient cleaning auditing. Besides being the foundational effort for cleaning audit, a path planning approach considering the geometric signatures that contribute to the dirt accumulation of a region has not been device so far. The proposed approach is validated systematically through experiment trials. The geometrical feature extraction-based dirt location identification method successfully identified dirt accumulated locations in our post-cleaning analysis as part of the experiment trials. The path generation strategies are validated in a real-world environment using an in-house developed cleaning auditing robot BELUGA. From the experiments conducted, the ant colony optimization algorithm generated the best cleaning auditing path with less travel distance, exploration time, and energy usage.
This paper presents a study of various population partitioning techniques and their effect on the efficiency of swarm algorithms. Population partitioning techniques based on different concepts have been studied. Promi...
详细信息
This paper presents a study of various population partitioning techniques and their effect on the efficiency of swarm algorithms. Population partitioning techniques based on different concepts have been studied. Prominent amongst them is self-adaptive multi-population (SAMP) technique where populations are added and deleted dynamically based on their diversity. This techniques start with a single randomly initialised population, called free population. After evolution, if the distance between solutions drops below a limit, it is considered to have converged. If all existing populations have converged, a new randomly generated population is added. SAMP keeps at least one free population at all times, hence ensuring the algorithm doesn't get trapped in local optima. Another promising population partitioning technique studied is random partitioning, where a single population is divided into many smaller sub-populations randomly. Few extensions to the studied techniques are proposed, like an adaptive hierarchical partitioning technique, seed based partitioning with fixed seeds, random partitioning with master population, SAMP with random partitioning etc. All the studied and proposed techniques are compared over a set of benchmark functions. The strongest amongst all techniques was found to be SAMPR. SAMPR is a hybrid of self-adaptive multi-population (SAMP) technique and random partitioning where after every few generations all populations are combined together and re-partitioned randomly. Efficiency of SAMPR is validated over seven well-known swarm algorithms. Extensive comparisons are conducted over multiple benchmark functions, CEC'14 function set and 800 GKLS generated functions. Results establish the efficiency of the proposed technique for improving performance of swarm algorithms.
swarm algorithms are an efficient means to optimize various real-life problems. Their efficiency is influenced by diversity, which helps it to escape any local optima. There are multiple ways to increase diversity lik...
详细信息
ISBN:
(纸本)9781538659069
swarm algorithms are an efficient means to optimize various real-life problems. Their efficiency is influenced by diversity, which helps it to escape any local optima. There are multiple ways to increase diversity like mutation, repulsion, multi-population, replacement, etc. Of these, multi-population and replacement based techniques work without changing the internal functioning of any algorithm. In this paper we study three different replacement based techniques for multi-population swarm algorithms. The paper also proposes techniques (variant/new) to improve diversity in a multi-population scenario. All the techniques:-studied and proposed are subsequently tested with bat algorithm over 30 benchmark functions. The most efficient amongst them is further tested over six other swarm algorithms. The comparative results indicate that the identified technique is significantly better in terms of efficiency and diversity for most algorithms. Hence it can be concluded that it is an efficient means to improve the diversity and efficiency of a multi-population swarm algorithm.
This article presents an approach for the efficient and transparent parallelization of a large class of swarm algorithms, specifically those where the multiagent paradigm is used to implement the functionalities of bi...
详细信息
This article presents an approach for the efficient and transparent parallelization of a large class of swarm algorithms, specifically those where the multiagent paradigm is used to implement the functionalities of bioinspired entities, such as ants and birds. Parallelization is achieved by partitioning the space on which agents operate onto multiple regions and assigning each region to a different computing node. Data consistency and conflict issues, which can arise when several agents concurrently access shared data, are handled using a purposely developed notion of logical time. This approach enables a transparent porting onto parallel/distributed architectures, as the developer is only in charge of defining the behavior of the agents, without having to cope with issues related to parallel programming and performance optimization. The approach has been evaluated for a very popular swarm algorithm, the ant-based spatial clustering and sorting of items, and results show good performance and scalability.
As technology advances, the places we have been able to explore have drastically increased. However, the advancements in the underwater realm have staggered behind both the exploration of surface and air domains. This...
详细信息
As technology advances, the places we have been able to explore have drastically increased. However, the advancements in the underwater realm have staggered behind both the exploration of surface and air domains. This is due in part to the challenges that arise when placing a robot in water. One current shift has seen the use of a swarm of robots that are cheaper and are of a lower quality, that work together to accomplish a common goal, as opposed to using a single expensive robot. swarm robotics benefits from being more tolerant of catastrophic failure and can cover large areas in smaller time frames. However, unlike other advancements in technology, underwater swarm robotics have struggled to compete with its counterparts on the surface and in the air. This is mainly due to the problems with communication underwater, the hazardous environment, the cost and difficulties with construction of underwater robots. This article conducts a literature review into the current state of underwater swarm robotics;it covers the design of the underwater robots, the methods used by the individual robot to perceive their environment, how they can localize to said environment, the methods of communication available underwater, centralized and decentralized control, the basis of swarm algorithms, the behaviors that are exhibited when a swarm works collectively and how swarms have been applied underwater.
Modelling pedestrians and groups of people is a highly multidisciplinary technique, given the significant interest it attracts from various branches of science and engineering. This results in many different methodolo...
详细信息
Modelling pedestrians and groups of people is a highly multidisciplinary technique, given the significant interest it attracts from various branches of science and engineering. This results in many different methodologies that may arise from diverse objectives. The model developed in this work is an agent-based model, in which pedestrian behaviour is defined by a set of forces. Each force models an aspect of pedestrian gait, with the objective of creating a virtual environment to train and test control systems for collaborative robots or autonomous vehicles. To meet the modelling requirements, the system employs various algorithms, such as "flocking", which simulates the coordination and formation of groups, "pathfinding", which enables agents to discover optimal routes within a given space, and algorithms specialized in avoiding walls and dynamic obstacles. These components collaborate to accurately depict how crowds move and react in different environments and situations. Thanks to the modularity of this approach, which facilitates the adjustment and expansion of the components, the developed system can be integrated into various applications, such as simulating non-playable characters (NPCs) in video games or modelling the evacuation of a building.
In this paper, a survey about the algorithms based on swarm intelligence with parameter adaptation using some techniques to achieve the best results is presented. In this case, we analyzed the most popular algorithms ...
详细信息
In this paper, a survey about the algorithms based on swarm intelligence with parameter adaptation using some techniques to achieve the best results is presented. In this case, we analyzed the most popular algorithms such as ant colony optimization, particle swarm optimization, bee colony optimization, bat algorithm, firefly algorithm and cuckoo search. These algorithms are referenced in the paper because they have demonstrated to be superior with respect to the other optimization methods based on swarms with parameter adaptation using type-2 fuzzy logic in some applications, and also the algorithms are inspired on swarm intelligence.
The Internet of Things (IoT) and Wireless Sensor Networks (WSNs) heavily rely on the lifetime of sensor nodes, which is inversely proportional to transmission power. Nodes with greater separation demand higher transmi...
详细信息
The Internet of Things (IoT) and Wireless Sensor Networks (WSNs) heavily rely on the lifetime of sensor nodes, which is inversely proportional to transmission power. Nodes with greater separation demand higher transmission power, while those closer together require less power. In practice, node placement varies significantly due to diverse terrain and contours, making power transmission configuration a critical and challenging issue in WSNs. This paper introduces an Enhanced Grey Wolf Optimization (EGWO) algorithm designed to optimize power transmission in WSN environments. Traditional Grey Wolf Optimization (GWO) employs a parameter that decreases linearly with iterations to regulate exploitation. In contrast, the proposed EGWO adopts a concave decline in the exploitation rate, allowing for more precise optimization in areas under exploration. The enhancement utilizes a cosine function that gradually decreases from 1 to 0, providing a smoother and more controlled transition. The experimental results demonstrate that EGWO outperforms other optimization algorithms. The proposed method achieves the lowest fitness value of -4.21, compared to 1.22 for standard GWO, -2.81 for PSO, and 2.86 for BESO, indicating its superiority in optimizing power transmission in WSNs.
In machine learning models, feature selection plays a crucial role. It reduces overall data, minimizes storage requirements, and enhances algorithm performance. Despite this, greedy and exhaustive search methods may n...
详细信息
In machine learning models, feature selection plays a crucial role. It reduces overall data, minimizes storage requirements, and enhances algorithm performance. Despite this, greedy and exhaustive search methods may not be optimal as the number of features increases. Metaheuristic algorithms are a more sensible way to deal with this issue. In this study, the Grasshopper Optimization Algorithm (GOA) is applied to feature selection. Although GOA may be relatively easy to implement, it may not fully leverage each iteration and may become stuck in local optima. The comfort zone in GOA influences the grasshopper movement within the search space, influencing exploration and exploitation. As a constant, the algorithm changes the comfort zone linearly. The proposed algorithm, Signature Chaos GOA (SCGOA), overcomes these limitations in several ways. Firstly, it constructs the initial population using correlations. Second, unlike existing methods, it specifies specific procedures for initial and final iterations. After the initial iteration, the algorithm adjusts the comfort zone parameters dynamically using chaos theory and fuzzy signatures. Lastly, SCGOA aims to optimize both Support Vector Machine (SVM) parameters and feature subsets simultaneously. Objective functions include classification error, the proportion of selected features, and redundancy. In addition, different algorithms such as the Firefly Algorithm (FA), the Bat Algorithm (BA), and the Particle swarm Optimization (PSO) are compared. In comparison with FA, BA, PSO, and GOA, the proposed algorithm can improve the objective function by 30.6%, 34.9%, 7.6%, and 33.3%, respectively.
暂无评论