Adis Alihodzic

Improved Bat Algorithm Applied to Multilevel Image Thresholding

Multilevel image thresholding is a very important image processing technique that is used as a basis for image segmentation and further higher level processing. However, the required computational time for exhaustive search grows exponentially with the number of desired thresholds. Swarm intelligence metaheuristics are well known as successful and efficient optimization methods for intractable problems. In this paper, we adjusted one of the latest swarm intelligence algorithms, the bat algorithm, for the multilevel image thresholding problem. The results of testing on standard benchmark images show that the bat algorithm is comparable with other state-of-the-art algorithms. We improved standard bat algorithm, where our modifications add some elements from the differential evolution and from the artificial bee colony algorithm. Our new proposed improved bat algorithm proved to be better than five other state-of-the-art algorithms, improving quality of results in all cases and significantly improving convergence speed.

Multilevel image thresholding by fireworks algorithm

This paper presents implementation of the recent fireworks algorithm adjusted for solving multilevel image thresholding problem. This is an important problem since it is often used in image processing for the purpose of image segmentation. Since the number of possible threshold combinations grows exponentially with the number of desirable thresholds, standard deterministic methods could not generate satisfying results when tackling this problem. To test the performance of our proposed approach, we employed Kapurs maximum entropy thresholding function on standard benchmark images where the optimal solutions are known (up to five thresholding points) from the exhaustive search. Results show that our approach has great potential in this field.

Improved Hybridized Bat Algorithm for Global Numerical Optimization

Swarm intelligence algorithms have been successfully applied to intractable optimization problems. Bat algorithm is one of the latest optimization metaheuristics and research about its capabilities and possible improvements is at the early stage. This algorithm has been recently hybridized with differential evolution and improved results were demonstrated on standard benchmark functions for unconstrained optimization. In this paper, in order to further enhance the performance of this hybridized algorithm, a modified bat-inspired differential evolution algorithm is proposed. The modifications include operators for mutation and crossover and modified elitism during selection of the best solution. It also involves the introduction of a new loudness and pulse rate functions in order to establish better balance between exploration and exploitation. We used the same five standard benchmark functions to verify the proposed algorithm. Experimental results show that in almost all cases, our proposed method outperforms the hybrid bat algorithm.

Multilevel image thresholding using elephant herding optimization algorithm

Digital images are widely used and numerous application in different scientific fields use digital image processing algorithms where image segmentation is a common task. Thresholding represents one technique for solving that task and Kapurs and Otsus methods are well known criteria often used for selecting thresholds. Finding optimal threshold values represents a hard optimization problem and swarm intelligence algorithms have been successfully used for solving such problems. In this paper we adjusted recent elephant herding optimization algorithm for multilevel thresholding by Kapurs and Otsus method. Performance was tested on standard benchmark images and compared with four other swarm intelligence algorithms. Elephant herding optimization algorithm outperformed other approaches from literature and it was more robust.

Cuckoo Search and Bat Algorithm Applied to Training Feed-Forward Neural Networks

Training of feed-forward neural networks is a well-known and important hard optimization problem, frequently used for classification purpose. Swarm intelligence metaheuristics have been successfully used for such optimization problems. In this chapter we present how cuckoo search and bat algorithm, as well as the modified version of the bat algorithm, were adjusted and applied to the training of feed-forward neural networks. We used these three algorithms to search for the optimal synaptic weights of the neural network in order to minimize the function errors. The testing was done on four well-known benchmark classification problems. Since the number of neurons in hidden layers may strongly influence the performance of artificial neural networks, we considered several neural networks architectures for different number of neurons in the hidden layers. Results show that the performance of the cuckoo search and bat algorithms is comparable to other state-of-the-art nondeterministic optimization algorithms, with some advantage of the cuckoo search. However, modified bat algorithm outperformed all other algorithms which shows great potential of this recent swarm intelligence algorithm.

Firefly algorithm for multi-objective RFID network planning problem

RFID network planning involves many objectives and constraints and it belongs to the class of NP-hard problems. Such problems were recently successfully tackled by nondeterministic optimization metaheuristics where swarm intelligence represents a prominent branch. We present improved firefly algorithm adjusted for multi-objective RFID network planning where our proposed algorithm improved results considering all relevant performance measures tested on the same benchmark functions and compared to the previously known results from the literature.

Multi-objective RFID network planning with probabilistic coverage model by guided fireworks algorithm

RFID technology is increasingly incorporated in many facets of life and accordingly represents an active research area. RFID network planning is a hard optimization problem that determines positions of readers and transmitter power parameters in order to satisfy requirements about coverage, interference, power consumption, total cost, etc. For such hard optimization problems, where deterministic mathematical methods are inadequate, stochastic swarm intelligence algorithms are very successful. In this paper we adjusted the recent guided fireworks algorithm for the RFID network planning problem with probabilistic model of coverage. Our proposed approach was tested on standard benchmark networks and compared with other algorithms from literature. Our approach proved to be better than other compared methods, considering the coverage, number of employed readers, used power and interference.

Drone Placement for Optimal Coverage by Brain Storm Optimization Algorithm

Unmanned aerial vehicles or drones are used in wide range of applications and one of them is area monitoring. Finding the optimal positions for drones so that the coverage is maximized, while reducing the fuel consumption represents computationally hard problem. For these kinds of problems, swarm intelligence algorithms have been successfully used. In this paper we propose recent brain storm optimization algorithm for finding the locations for static drones. Optimal drone placement maximizes the number of covered targets while minimizing drones altitude. The proposed method was tested in two different environments, with uniformly and clustered deployed targets. Based on the obtained results it can be concluded that brain storm optimization is appropriate for solving drone placement problem in both considered environments.

An upgraded bat algorithm for tuning extreme learning machines for data classification

The learning time of the synaptic weights for feedforward neural networks tend to be very long. In order to reduce the learning time, in this paper we propose a new learning algorithm for learning the synaptic weights of the single-hidden-layer feedforward neural networks by combining the upgraded bat algorithm with the extreme learning machine. The proposed approach can efficiently search for the optimal input weights as well as the hidden biases, leading to the reduced number of evaluations needed to train a neural network. The experimental results based on classification problems and comparison with other approaches from literature have shown that the proposed algorithm produces a satisfactory performance in almost all cases and that it can learn the weight factors much faster than the traditional learning algorithms.

Adjusted Artificial Bee Colony Algorithm for the Minimum Weight Triangulation

The minimum weight triangulation is a well-known NP-hard problem often used for the construction of triangulated random network models of land contours. Since it is an intractable problem, the required computational time for an exhaustive search algorithm grows exponentially with the number of points in 2D space. Nature-inspired swarm intelligence algorithms are prominent and efficient optimization techniques for solving that kind of problems. In this paper, we adjusted the artificial bee colony algorithm for the minimum weight triangulation problem. Our adjusted algorithm has been implemented and tested on several randomly generated instances of points in the plane. The performance of our proposed method was compared to the performance of other stochastic optimization algorithms, as well as with the exhaustive search for smaller instances. The simulation results show that our proposed algorithm in almost all cases outperforms other compared algorithms.