The new approach is proposed to color image processing and segmentation on basis of evolutionary models. The set of objective functions was developed for the estimation of segmentation quality depending on the type of...
详细信息
ISBN:
(数字)9783319325545
ISBN:
(纸本)9783319325545;9783319325538
The new approach is proposed to color image processing and segmentation on basis of evolutionary models. The set of objective functions was developed for the estimation of segmentation quality depending on the type of histological research. Experimental research was conducted on the example of histological images. Obtained results showed the efficiency of the developed evolutionary processing and segmentation algorithms.
In this paper an evolutionary algorithm for the sizing and siting of distributed energy storage systems is presented. The algorithm's objective is to maximize the penetration levels of renewable energy sources pre...
详细信息
ISBN:
(数字)9781728142180
ISBN:
(纸本)9781728142180
In this paper an evolutionary algorithm for the sizing and siting of distributed energy storage systems is presented. The algorithm's objective is to maximize the penetration levels of renewable energy sources present in the network, while maintaining network's security standards. The algorithm is applied for multiple network congestion scenarios and in the presence of high renewable energy production levels. Due to the non-convex nature of the problem the evolutionary Particle Swarm Optimization (EPSO) was used. Additionally, the intrinsic parameters of the EPSO algorithm were studied and selected in order to optimize its behaviour in the search for robust solutions for this problem. Furthermore, the contributions from the algorithm for the provision of extra flexibility to the power system with resort to dispersed energy storage systems are analysed and tested using IEEE 14 bus network.
In this paper a alternative approach to the diversity guided particle swarm optimization (PSO) is investigated. The PSO shows acceptable performance on well-known test problems, however tends to suffer from premature ...
详细信息
ISBN:
(纸本)9783319295046;9783319295039
In this paper a alternative approach to the diversity guided particle swarm optimization (PSO) is investigated. The PSO shows acceptable performance on well-known test problems, however tends to suffer from premature convergence on multi-modal test problems. This premature convergence can be avoided by increasing diversity in search space. In this paper we introduce diversity measure based on graph representation of swam evolution and we discuss possibilities of graph representation of swarm population in adaptive control of PSO algorithm. Based on our findings we concluded, that network representation of evolution population and its subsequent analysis can be used in adaptive control, in various degrees of success.
Artificial bee colony (ABC) algorithm is relatively a new bio-inspired swarm intelligence optimization technique comparative to other population based algorithms. In this study BGA (breeder GA) mutation is embedded in...
详细信息
ISBN:
(纸本)9783642353796;9783642353802
Artificial bee colony (ABC) algorithm is relatively a new bio-inspired swarm intelligence optimization technique comparative to other population based algorithms. In this study BGA (breeder GA) mutation is embedded into onlooker bee phase to improve the capability of local search. The proposed variant is named B-ABC. The experimental results on 10 constrained benchmark functions demonstrate the performance of the proposed variant against those of state-of-the-art algorithms for a set of constrained test problems. Further the efficiency of the proposed variant is tested on the car side impact problem.
This study proposes a music gene expression programming method to achieve music melody feature learning of a specific singer's compositional style. The user specifies the song format, and the program automatically...
详细信息
ISBN:
(纸本)9798350354638;9798350354621
This study proposes a music gene expression programming method to achieve music melody feature learning of a specific singer's compositional style. The user specifies the song format, and the program automatically generates and evaluates songs. A mapping mechanism between 16-bit octal numbers and musical scores is proposed to realize the evolution of musical scores in units of measures. In the melody generation stage, the modification operations that are generally performed by the composer in the process of composing music are integrated with the evolutionary operations of gene expression programming to create a music gene expression programming operation. In the music melody evaluation stage, a long short-term memory neural network evaluation model is established and trained using the main verse and chorus of the music as well as the spectrum of the entire song. The neural network evaluates the resulting song fitness value, providing feedback for music evolution. In contrast to melody generated via other methods, comparative experiments show that the melody generated by this research method has an obvious compositional style of a specific composer.
The knowledge about the responses to hazardous events is of importance throughout the whole life cycle of a complex system, regardless whether during design or operation phases. These responses also allow to draw conc...
详细信息
ISBN:
(纸本)9781665429054
The knowledge about the responses to hazardous events is of importance throughout the whole life cycle of a complex system, regardless whether during design or operation phases. These responses also allow to draw conclusions about the resilience of the system. Consequently, there is a need for an extensive consideration of all possible hazardous events a system can be exposed to. This work presents a method for determining the hazards with the most critical system response in terms of resilience. Therefore, we introduce a method for modeling failure propagation under consideration of dynamic behavior in function models. This method is then extended for assessing resilience for random hazard scenarios. Finally, we propose two solutions for determining the most critical hazard scenarios, and thus, provide a base for improvements of the system.
One of the important design problems -the problem of ECE schemes elements placement is considered in this article. It belongs to the class of NPhard problems. Statement of a placement problem is made;the complex crite...
详细信息
ISBN:
(纸本)9783319184760;9783319184753
One of the important design problems -the problem of ECE schemes elements placement is considered in this article. It belongs to the class of NPhard problems. Statement of a placement problem is made;the complex criterion considering boundary conditions and restrictions is entered. The modified hybrid architecture of the bioinspired search using multilevel evolution and migration mechanism is offered. The genetic and evolutionary algorithms allowing receiving sets of quasi-optimum decisions, for polynomial time are developed. The program environment is created and computing experiment is made. The series of tests and experiments have allowed specifying theoretical estimations of placement algorithms running time and their behavior for schemes of various structures. The best running time of algorithms is O (n log n), the worst one is O(n(3)).
In recent years, several studies discussed the use of evolutionary algorithms, as more promising approaches, for automatic design of feedforward neural networks. Such methods are particularly useful for dealing with c...
详细信息
ISBN:
(纸本)9781728118208
In recent years, several studies discussed the use of evolutionary algorithms, as more promising approaches, for automatic design of feedforward neural networks. Such methods are particularly useful for dealing with complex problems having large search spaces with many local optima. However, experimental evidence had indicated the inefficiency of these algorithms at fine tuning solutions. In this paper, we show how a pure mutation-based evolutionary algorithm could be used to find global basins of attraction by selecting the appropriate structure of a feedforward neural network and also to improve finer tuning capabilities of the designed network by using a specific self-adaptive procedure. Pertinences of this algorithm reside first in its structure selection method based on a competition between user chosen structures and second its adaptive weight perturbation with a constant mutation probability. It is a real pure evolutionary algorithm of design of multilayer neural networks with competitive and stable performances compared to popular algorithms as will be proven by simulations.
The Cartesian genetic programming (CGP) considers grid of nodes to represent a genotype. In the corresponding phenotype each node represents a processing element. The processing element has similar structure as of sma...
详细信息
ISBN:
(纸本)9781509034932
The Cartesian genetic programming (CGP) considers grid of nodes to represent a genotype. In the corresponding phenotype each node represents a processing element. The processing element has similar structure as of smallest embryonic fabric element. It can be an embryonic molecule where allmolecules combine and create an embryonic cell equivalent to a circuit. The evolutionary algorithm applied to genotypes select the fittest. The evaluated genotype determines the configurationdata for embryonic cell. The configuration data generation is automated with this approach. As well this can lead to optimizedembryonic fabric structure if optimization by evolutionary algorithmis utilized. In this paper the CGP approach is applied togenerate configuration data for embryonic fabric. The approachis simulated for 1-bit adder circuit.
Cardiac patients can be regularly monitored using low cast sensor networks which can save many lives and valuable time of experts. This monitoring can be more effective if in addition to standard clinical parameters g...
详细信息
ISBN:
(纸本)9780769528410
Cardiac patients can be regularly monitored using low cast sensor networks which can save many lives and valuable time of experts. This monitoring can be more effective if in addition to standard clinical parameters genetic information is used because of its ability to predict hereditary diseases like cardiac problems. Current clinical practices, however, only stress on physiological observation to predict heart failure rate which could miss the important information which could lead to fatal consequences. This paper presents Ambient Cardiac Expert (ACE) which combines physiological parameters observed using sensor networks with gene expression data to predict the heart failure rate. The system uses well established Support Vector Machines (SVM) for class prediction and uses Wrapper evolutionary algorithm based on Gaussian Estimation of Distribution algorithm (EDA) to determine cardiac patient's criticality. Results suggest that ACE can be successfully applied for cardiac patient monitoring and has ability to integrate the information from both clinical and genetic sources.
暂无评论