Reshu Chaudhary
University of Delhi, Department of Computer sciences, Department Member
Research Interests:
Shuffled Multi-Population Bat algorithm (SMPBat) is a recently proposed hybrid variant of bat algorithm. It incorporates the strengths of two recent variants of bat algorithm-Enhanced Shuffled Bat Algorithm and Bat algorithm with Ring... more
Shuffled Multi-Population Bat algorithm (SMPBat) is a recently proposed hybrid variant of bat algorithm. It incorporates the strengths of two recent variants of bat algorithm-Enhanced Shuffled Bat Algorithm and Bat algorithm with Ring Master-Slave strategy. SMPBat hybridizes the sub-population generation and manipulation mechanism of the two algorithms to device an enhanced variant of BA. There are multiple parameters controlling the flow of execution of SMPBat. These parameters are set at the beginning of the execution of the algorithm. This paper proposes incorporation of multi-parameter setting into SMPBat, where different sub-populations work with different sets of parameter values. Additionally, the impact of a refined search mechanism is also studied. The proposed variants are tested over 20 benchmark functions and a real-world optimization problem. Results establish the robustness of the proposed work.
Research Interests:
Modified shuffled multi-population bat algorithm (MSMPBat) is a recently proposed swarm algorithm. It divides its population into multiple sub-populations (SPs), each of which uses different parameter settings and evolves independently... more
Modified shuffled multi-population bat algorithm (MSMPBat) is a recently proposed swarm algorithm. It divides its population into multiple sub-populations (SPs), each of which uses different parameter settings and evolves independently using an enhanced search mechanism. For information exchange among these SPs, a solution from one SP is copied to the next after every generation. This process leads to duplication of solutions over time. To overcome this drawback, different techniques are introduced. Opposition-based learning is used to generate a diverse starting population. For information exchange, if a solution comes too close to the swarm best, only then it is sent (moved, not copied) to another swarm. Four techniques are proposed to select this second swarm. Initially, the selection probability of each technique is same. The algorithm adaptively updates these probabilities based on their success rate. The swarm which gave up the solution uses a modified opposition-based learnin...
Research Interests:
Bat Algorithm (BA) is a nature-inspired swarm algorithm which has been applied to solve multiple real-world optimisation problems. Due to a lack of balance between exploitation and exploration, multiple researchers have proposed different... more
Bat Algorithm (BA) is a nature-inspired swarm algorithm which has been applied to solve multiple real-world optimisation problems. Due to a lack of balance between exploitation and exploration, multiple researchers have proposed different hybrids of BA. This paper proposes Shuffled MultiPopulation Bat algorithm (SMPBat), a hybrid between two recently proposed variants of BA:-Enhanced Shuffled Bat algorithm (EShBAT) and Bat algorithm with Ring Master-Slave strategy (BatRM-S). BatRM-S is a multi-population variant of BA which partitions it's population according to a combination of the ring and master-slave strategies. EShBAT — incorporates shuffling into BA. The proposed algorithm, SMPBat combines the population partitioning strategies of these two algorithms to enhance the exploitation and exploration capabilities of BA. The evolution strategy of SMPBat also strives to retain the improved solutions. The standard BA replaces a solution with a new solution around the best. However, in this process, the information gained by that solution so far is completely lost. SMPBat changes this exploitation technique used by BA. SMPBat is compared to BatRM-S, EShBAT and BA, over 30 well-known optimisation functions. Results establish SMPBat as a significant improvement over BA, EShBAT and BatRM-S.
Research Interests:
The paper proposes a novel nature-inspired swarm algorithm: peacock algorithm (PA). It is based on the lekking and mating behavior of peacocks. The best solutions are identified as peacocks, while the remaining solutions are called... more
The paper proposes a novel nature-inspired swarm algorithm: peacock algorithm (PA). It is based on the lekking and mating behavior of peacocks. The best solutions are identified as peacocks, while the remaining solutions are called peahens. The peahens are assigned to the peacocks based on their relative positions. Peacocks perform exploitation while peahens perform both, exploration as well as exploitation. A peahen explores the search space and moves towards the lek peacock. Once it is near, it may to choose to mate (exploitation) or pursue another peacock (exploration). Every peacock moves towards the dominant peacock (best solution) to enhance its mating chances. The dominant peacock maintains his lek by pushing away other peacocks if they encroach upon its lekking area. The algorithm maintains diversity by adding random solutions whenever two solutions are found to be similar. To test the efficiency of the proposed work, it is compared over a set of 23 benchmark functions to nine other algorithms, which are a mixture of well-established and new algorithms. Its performance is also compared over the CEC’14 test suite to six algorithms. Experimental results demonstrate the superiority of PA, establishing it as a promising novel algorithm.
Research Interests:
Research Interests:
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,... more
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.
Research Interests:
Shuffled Multi-Population Bat algorithm (SMPBat) is a recently proposed hybrid variant of bat algorithm. It incorporates the strengths of two recent variants of bat algorithm-Enhanced Shuffled Bat Algorithm and Bat algorithm with Ring... more
Shuffled Multi-Population Bat algorithm (SMPBat) is a recently proposed hybrid variant of bat algorithm. It incorporates the strengths of two recent variants of bat algorithm-Enhanced Shuffled Bat Algorithm and Bat algorithm with Ring Master-Slave strategy. SMPBat hybridizes the sub-population generation and manipulation mechanism of the two algorithms to device an enhanced variant of BA. There are multiple parameters controlling the flow of execution of SMPBat. These parameters are set at the beginning of the execution of the algorithm. This paper proposes incorporation of multi-parameter setting into SMPBat, where different sub-populations work with different sets of parameter values. Additionally, the impact of a refined search mechanism is also studied. The proposed variants are tested over 20 benchmark functions and a real-world optimization problem. Results establish the robustness of the proposed work.
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Bat Algorithm (BA), is a relatively new nature inspired metaheuristic algorithm, which works on the echolocation capabilities of micro-bats. Although being highly efficient, it suffers from pre-mature convergence. To overcome this... more
Bat Algorithm (BA), is a relatively new nature inspired metaheuristic algorithm, which works on the echolocation capabilities of micro-bats. Although being highly efficient, it suffers from pre-mature convergence. To overcome this limitation, this paper proposes a multimodal variant of BA, called Multi-Modal Bat Algorithm (MMBA), which includes the foraging behaviour of bats. The standard BA exhibits a random movement for catching its prey. This work also proposes an enhancement to these exploration capabilities of bat, called Bat Algorithm with Improved Search (BAIS). Each of these variants is tested for its efficacy against BA over 30 benchmark functions. An integration of both these modifications, the Multi-Modal Bat Algorithm with Improved Search (MMBAIS), is also subsequently compared against the same 30 benchmark functions. Results established the superiority of MMBAIS over BA. Experimental comparison of MMBAIS with a recent variant of BA also revealed the efficiency of MMBAIS.
Research Interests: Information Systems, Evolutionary algorithms, Soft Computing, Computational Science, Natural Computing, and 8 moreOptimisation techniques, Numerical Optimization, Bat Algorithm, Soft Computing and optimization, Evolutionary Algorithm, Multi-Modal Optimization, Bat-inspired Optimization Algorithm, and Hybrid bat algorithm
Bat Algorithm (BA) is a simple and effective global optimization algorithm which has been applied to a wide range of real-world optimisation problems. Various extensions to Bat algorithm have been proposed in the past; prominent amongst... more
Bat Algorithm (BA) is a simple and effective global optimization algorithm which has been applied to a wide range of real-world optimisation problems. Various extensions to Bat algorithm have been proposed in the past; prominent amongst them being ShBAT. ShBAT is a hybrid between BA and Shuffled Frog Leaping Algorithm-SFLA; a memetic algorithm based on food search behavior of frogs. ShBAT integrates the shuffling and reorganization technique of SFLA to enhance the exploitation capabilities of BAT. This paper proposes Enhanced Shuffled Bat algorithm (EShBAT) an extension to ShBAT. In ShBAT, different memeplexes evolve independently, with different cultures. EShBAT improves the exploitation capabilities of ShBAT by grouping together the best of each memeplex to form a super-memeplex. This super-memeplex evolves independently to further exploit the best solutions. The performance of EShBAT is verified over 30 well-known benchmark functions. Experimental results indicate a significant improvement of EShBAT over BA and ShBAT.
Research Interests: Evolutionary algorithms, Evolutionary Computation, Swarm Intelligence, Soft Computing, Soft Computing Techniques, and 8 moreNatural Computing, Numerical Optimization, Optimisation, Bat Algorithm, Soft Computing and optimization, Hybrid Algorithm, Hybrid Evolutionary Algorithm, and Bat-inspired Optimization Algorithm
Bat Algorithm (BA) is a nature-inspired swarm algorithm which has been applied to solve multiple real-world optimization problems. Due to a lack of balance between exploitation and exploration, multiple researchers have proposed different... more
Bat Algorithm (BA) is a nature-inspired swarm algorithm which has been applied to solve multiple real-world optimization problems. Due to a lack of balance between exploitation and exploration, multiple researchers have proposed different hybrids of BA. This paper proposes Shuffled Multi-Population Bat algorithm (SMPBat), a hybrid between two recently proposed variants of BA:-EShBAT and BatRM-S. BatRM-S – Bat algorithm with Ring Master-Slave strategy, is a multi-population variant of BA which partitions it's population according to a combination of the ring and master-slave strategies. EShBAT – Enhanced Shuffled Bat algorithm, incorporates shuffling into BA. SMPBat combines the population partitioning strategies of these two algorithms to enhance the exploitation and exploitation capabilities of BA. The evolution strategy of SMPBat also strives to retain the improved solutions. The standard BA replaces a solution with a new solution around the best. However, n this process, the information gained by that solution so far is completely lost. SMPBat changes this exploitation technique used by BA. SMPBat is compared to BatRM-S, EShBAT and BA, over 30 well-known optimisation functions. Results establish SMPBat as a significant improvement over BA, EShBAT and BatRM-S.
Research Interests:
Bat Algorithm (BA) is a simple and effective global optimization algorithm which has been applied to a wide range of real-world optimisation problems. Various extensions to Bat algorithm have been proposed in the past; prominent amongst... more
Bat Algorithm (BA) is a simple and effective global optimization algorithm which has been applied to a wide range of real-world optimisation problems. Various extensions to Bat algorithm have been proposed in the past; prominent amongst them being ShBAT. ShBAT is a hybrid between BA and Shuffled Frog Leaping Algorithm-SFLA; a memetic algorithm based on food search behavior of frogs. ShBAT integrates the shuffling and reorganization technique of SFLA to enhance the exploitation capabilities of BAT. This paper proposes Enhanced Shuffled Bat algorithm (EShBAT) an extension to ShBAT. In ShBAT, different memeplexes evolve independently, with different cultures. EShBAT improves the exploitation capabilities of ShBAT by grouping together the best of each memeplex to form a super-memeplex. This super-memeplex evolves independently to further exploit the best solutions. The performance of EShBAT is verified over 30 well-known benchmark functions. Experimental results indicate a significant improvement of EShBAT over BA and ShBAT.
Research Interests:
Bat Algorithm (BA), is a relatively new nature inspired metaheuristic algorithm, which works on the echolocation capabilities of micro-bats. Although being highly efficient, it suffers from pre-mature convergence. To overcome this... more
Bat Algorithm (BA), is a relatively new nature inspired metaheuristic algorithm, which works on the echolocation capabilities of micro-bats. Although being highly efficient, it suffers from pre-mature convergence. To overcome this limitation, this paper proposes a multimodal variant of BA, called Multi-Modal Bat Algorithm (MMBA), which includes the foraging behaviour of bats. The standard BA exhibits a random movement for catching its prey. This work also proposes an enhancement to these exploration capabilities of bat, called Bat Algorithm with Improved Search (BAIS). Each of these variants is tested for its efficacy against BA over 30 benchmark functions. An integration of both these modifications, the Multi-Modal Bat Algorithm with Improved Search (MMBAIS), is also subsequently compared against the same 30 benchmark functions. Results established the superiority of MMBAIS over BA. Experimental comparison of MMBAIS with a recent variant of BA also revealed the efficiency of MMBAIS.