As a primary data mining method for knowledge discovery, clustering is a technique of classifying a dataset into groups of similar objects. The most popular method for data clustering K-means suffers from the drawbacks of requiring the number of clusters and their initial centers, which should be provided by the user. In the literature, several methods have proposed in a form of k-means variants, genetic algorithms, or combinations between them for calculating the number of clusters and finding proper clusters centers. However, none of these solutions has provided satisfactory results and determining the number of clusters and the initial centers are still the main challenge in clustering processes. In this paper we present an approach to automatically generate such parameters to achieve optimal clusters using a modified genetic algorithm operating on varied individual structures and using a new crossover operator. Experimental results show that our modified genetic algorithm is a better efficient alternative to the existing approaches
Over the last years, home service robots have a wide range of potential applications, such as home security, patient caring, cleaning, etc. When developing robot software, one of the main challenges is to build the software architectural model. Software architecture is used throughout the software life-cycle for supporting analysis, guiding development, and acting as a roadmap for designers and implementers. Though many software architectures for robotic systems have been defined, none of them have reached all its objectives due to the great variability among systems behaviors, and still lack of systematic techniques to derive the robot software architecture from its requirements model. In this paper, we present a generic architectural model for home service robots, allowing for software architecture design, and preserving a continuous architectural view all along the development cycle. While avoiding the predominant decomposition problems, our approach allows for integration of the architectural components in a systematic and comprehensive way for efficient maintainability and reusability.
Genetic algorithms (GA) are a class of powerful metaheuristic search methods that solve complex and highly nonlinear problems. However, reuse opportunities have been underexploited because reuse was made at the code level. We argue that this is inefficient because it is complex and error prone. At the opposite, we propose the use of Software Product Lines engineering (SPLE) because it offers an effective way to easily manage commonalities at the model level and efficiently customize and derive a relevant product from a family of products. Another important feature of our approach is that it opens the door to the exploitation of dynamic Software product line techniques for dynamically evolving a genetic algorithm during execution.
To achieve the multi-agent systems' goals, agents interact to exchange information, to cooperate and to coordinate their tasks. Interaction is generally recognized as an important characteristic of multi-agent systems (MAS). The usual approaches to model agents' interactions consist of describing them as protocols [Hug04]. In the literature, several representation formalisms of agents' interactions have been proposed. AUML is one among the most used formalisms [Hug02]. However, AUML diagrams only offer a semi-formal specification of interactions. Indeed, the lack of formal semantics in AUML, can lead to several incoherencies in the description of a MAS' behaviour. We present, in this paper, a visual tool that essentially allows: (1) translating the description of agents' interaction protocols (AIP), specified by means of AUML formalism, in a Maude specification and, (2) validating the generated formal descriptions through simulation. Based on rewriting logic, the formal and object-oriented language Maude offers an interesting way for concurrent systems formal specification and programming. By an example of multi-agent systems interaction protocol, we illustrate the proposed translation and the developed tool.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.