Ali B. Hashemi

A note on the learning automata based algorithms for adaptive parameter selection in PSO

PSO, like many stochastic search methods, is very sensitive to efficient parameter setting such that modifying a single parameter may cause a considerable change in the result. In this paper, we study the ability of learning automata for adaptive PSO parameter selection. We introduced two classes of learning automata based algorithms for adaptive selection of value for inertia weight and acceleration coefficients. In the first class, particles of a swarm use the same parameter values adjusted by learning automata. In the second class, each particle has its own characteristics and sets its parameter values individually. In addition, for both classed of proposed algorithms, two approaches for changing value of the parameters has been applied. In first approach, named adventurous, value of a parameter is selected from a finite set while in the second approach, named conservative, value of a parameter either changes by a fixed amount or remains unchanged. Experimental results show that proposed learning automata based algorithms compared to other schemes such as SPSO, PSOIW, PSO-TVAC, PSOLP, DAPSO, GPSO, and DCPSO have the same or even higher ability to find better solutions. In addition, proposed algorithms converge to stopping criteria for some of the highly multi modal functions significantly faster.

Cellular PSO: A PSO for Dynamic Environments

Many optimization problems in real world are dynamic in the sense that the global optimum value and the shape of fitness function may change with time. The task for the optimization algorithm in these environments is to find global optima quickly after the change in environment is detected. In this paper, we propose a new hybrid model of particle swarm optimization and cellular automata which addresses this issue. The main idea behind our approach is to utilized local interactions in cellular automata and split the population of particles into different groups across cells of cellular automata. Each group tries to find an optimum locally which results in finding the global optima. Experimental results show that cellular PSO outperforms mQSO, a well known PSO model in literature, both in accuracy and complexity in a dynamic environment where peaks change in width and height quickly or there are many peaks.

CellularDE: a cellular based differential evolution for dynamic optimization problems

In real life we are often confronted with dynamic optimization problems whose optima change over time. These problems challenge traditional optimization methods as well as conventional evolutionary optimization algorithms. In this paper, we propose an evolutionary model that combines the differential evolution algorithm with cellular automata to address dynamic optimization problems. In the proposed model, called CellularDE, a cellular automaton partitions the search space into cells. Individuals in each cell, which implicitly create a subpopulation, are evolved by the differential evolution algorithm to find the local optimum in the cell neighborhood. Experimental results on the moving peaks benchmark show that CellularDE outperforms DynDE, cellular PSO, FMSO, and mQSO in most tested dynamic environments.

A hibernating multi-swarm optimization algorithm for dynamic environments

Many problems in the real world are dynamic in which the environment changes. However, the nature itself provides solutions for adaptation to these changes in order to gain the maximum benefit, i.e. finding the global optimum, at any moment. One of these solutions is hibernation of animals when food is scarce and an animal may use more energy in searching for food than it would receive from consuming the food. In this paper, we applied the idea of hibernation in a multi-swarm optimization algorithm, in which a parent swarm explores the search space and child swarms exploit promising areas found by the parent swarm. In the proposed model, whenever the search efforts of a child swarm for exploiting an area becomes unproductive, the child swarm hibernates. Similar to the nature, which the change of the season awakens hibernating animals, in the proposed model hibernating swarms are awakened upon the detection of a change in the environment. Experimental results on various dynamic environments modeled by the moving peaks benchmark show that the proposed algorithm outperforms other PSO algorithms, including similar particle swarm algorithms for dynamic environments like mQSO, adaptive mQSO, and FMSO.

A multi-role cellular PSO for dynamic environments

In real world, optimization problems are usually dynamic in which local optima of the problem change. Hence, in these optimization problems goal is not only to find global optimum but also to track its changes. In this paper, we propose a variant of cellular PSO, a new hybrid model of particle swarm optimization and cellular automata, which addresses dynamic optimization. In the proposed model, population is split among cells of cellular automata embedded in the search space. Each cell of cellular automata can contain a specified number of particles in order to keep the diversity of swarm. Moreover, we utilize the exploration capability of quantum particles in order to find position of new local optima quickly. To do so, after a change in environment is detected, some of the particles in the cell change their role from standard particles to quantum for few iterations. Experimental results on moving peaks benchmark show that the proposed algorithm outperforms mQSO, a well-known multi swarm model for dynamic optimization, in many environments.

A New Particle Swarm Optimization Algorithm for Dynamic Environments

Many real world optimization problems are dynamic in which global optimum and local optima change over time. Particle swarm optimization has performed well to find and track optima in dynamic environments. In this paper, we propose a new particle swarm optimization algorithm for dynamic environments. The proposed algorithm utilizes a parent swarm to explore the search space and some child swarms to exploit promising areas found by the parent swarm. To improve the search performance, when the search areas of two child swarms overlap, the worse child swarms will be removed. Moreover, in order to quickly track the changes in the environment, all particles in a child swarm perform a random local search around the best position found by the child swarm after a change in the environment is detected. Experimental results on different dynamic environments modelled by moving peaks benchmark show that the proposed algorithm outperforms other PSO algorithms, including FMSO, a similar particle swarm algorithm for dynamic environments, for all tested environments.

Towards ontology evaluation across the life cycle: The Ontology Summit 2013

The goal of the Ontology Summit 2013 was to create guidance for ontology developers and users on how to evaluate ontologies. Over a period of four months a variety of approaches were discussed by participants, who represented a broad spectrum of ontology, software, and system developers and users. We explored how established best practices in systems engineering and in software engineering can be utilized in ontology development.

Modular first-order ontologies via repositories

From its inception, the focus of ontological engineering has been to support the reusability and shareability of ontologies, as well as interoperability of ontology-based software systems. Among the approaches employed to address these challenges have been ontology repositories and the modularization of ontologies. In this paper we combine these approaches and use the relationships between first-order ontologies within a repository (such as non-conservative extension and relative interpretation) to characterize the criteria for modularity. In particular, we introduce the notion of core hierarchies, which are sets of theories with the same non-logical lexicons and which are all non-conservative extensions of a unique root theory. The technique of relative interpretation leads to the notion of reducibility of a theory to a set of theories in different core hierarchies. We show how these relationships support a semi-automated procedure that decomposes an ontology into irreducible modules. We also propose a semi-automated procedure that can use the relationships between modules to characterize which modules can be shared and reused among different ontologies.

Two phased cellular PSO: A new collaborative cellular algorithm for optimization in dynamic environments

Many real world optimization problems are dynamic in which the fitness landscape is time dependent and the optima change over time such as dynamic economic modeling, dynamic resource scheduling, and dynamic vehicle routing. Such problems challenge traditional optimization methods as well as conventional evolutionary optimization algorithms. For such environments, optimization algorithms not only have to find the global optimum but also closely track its trajectory. In this paper, we propose a collaborative version of cellular PSO, named Two Phased cellular PSO to address dynamic optimization problems. The proposed algorithm introduces two search phases in order to create a more efficient balance between exploration and exploitation in cellular PSO. The conventional PSO in cellular PSO is replaced by a proposed PSO to increase the exploration capability and an exploitation phase is added to increase exploitation is the promising cells. Moreover, the cell capacity threshold which is a key parameter of cellular PSO is eliminated due to these modifications. To demonstrate the performance and robustness of the proposed algorithm, it is evaluated in various dynamic environment modeled by Moving Peaks Benchmark. The results show that for all the experimented dynamic environments, TP-CPSO outperforms all compared algorithms including cellular PSO.

Alpinist CellularDE: a cellular based optimization algorithm for dynamic environments

In this paper, we propose Alpinist CellularDE to address dynamic optimization problems. Alpinist CellularDE tries to detect different regions of the landscape and uses this information to perform more effective search and increase its performance. Moreover, in Alpinist CellularDE a directed local search is proposed to track local optima after detecting a change in the environment. The proposed algorithm is evaluated on various dynamic environments, modeled by Moving Peaks Benchmark. Experiments show superior performance of Alpinist CellularDE in all test cases in comparison with some of the best performing evolutionary algorithms for dynamic optimization problems.