Search

Machine learning (ML) algorithms are getting unsurpassed exposure as a potential technique for solving and modelling the wear behaviour of polymer matrix composites (PMCs). This paper presents the application of ML algorithms in predicting volume loss of reinforced polytetrafluoroethylene (PTFE) matrix composites. Firstly, the Taguchi L27 was harnessed to generate data set in a regulated way. Then multi linear regression (MLR), support vector regression (SVR), particle swarm optimization (PSO) and Harris Hawk's optimization (HHO) coupled with SVR ML algorithms were developed to accurately predict the volume loss of reinforced PTFE matrix composites. Based on the results achieved, it was found that SVR-HHO ML algorithm predicted the volume loss of reinforced PTFE matrix composites better than the other algorithms with determination coefficient (96 %) and root mean square error of 11 %. The ML algorithms could be used for prediction of volume loss of reinforced PTFE matrix composites and development of new PMCs with specific volume loss resistance. [ABSTRACT FROM AUTHOR]

Blood sugar levels rise as a result of impaired glucose homeostasis, which is a feature of Diabetes Mellitus (DM). Coronary artery disease, nerve damage, diabetic retinal disease, kidney failure, and sex disorders are just a few of the consequences that can result from DM. DM has to be diagnosed early to minimize its effects and those of its consequences. One technique for automatically detecting DM based on the prior data is the clustering algorithm. However, the K-mean Clustering method is easy to be implemented, has fast computational time and adapted easily. However, the centroids of K-means are initialized randomly that causes to be stuck in local optima. For this reason, the robust centroids initialization on the K-means clustering method are necessary to handle this problem. This paper uses swarm intelligence algorithm for this goal since it is able to obtain solution near the global optima, is robust and easy to be implemented. As a result, this study proposes an improved K-means clustering-based technique for diagnosing DM. The K-means is improved by using robust centroid initialization-based swarm intelligence algorithm. The swarm intelligence algorithm which is used is Particle Swarm Optimization. By using experiments, the proposed method is confirmed better than the original K-means clustering in diagnosing DM. [ABSTRACT FROM AUTHOR]

A new swarm optimization algorithm known as the sparrow search algorithm (SSA) consider in this work. It fascinated a lot of consideration due to its extremely good attributes. However, it has some pitfalls like minimum global search ability, falling into local optima etc which were found by many researchers. In this paper,first time sparrow search algorithm (SSA) is tested on welded beam design (WBD) optimization problem. Welded beam design (WBD) optimization problem is an engineering optimization problem that has been solved by various metaheuristic algorithms such as SiC-PSO, neuromorphic optimization (NSO) technique etc. Obtained results of SSA were compared with othertechniques such as GWO, PSO, TLBO and it is found that although it works very well on WBD problem with regards to convergence speed, in relation to optimality, convergence accuracy and stability SSA gave the results which were obtained from other algorithms. So, SSA needs to be modified for future work. [ABSTRACT FROM AUTHOR]

The research into Photovoltaic (PV) systems under varying conditions led to developing a new maximum power point tracking technique. Commonly used techniques result in lower efficiency when faced with changeable conditions. Therefore, based on the Particle Swarm Optimization (PSO) algorithm, the proposed algorithm improves the output power of photovoltaic (PV) systems under such varying circumstances. The proposed method is tested in MATLAB/Simulink under different states involving non-uniform irradiance and variable temperatures. To examine its performance enough, the outputs of the suggested method which compared with those of conventional techniques. The goal of this paper is to explain the scheme and modeling of a particle swarm optimization algorithm linked with a boost converter for finding the maximum permitted power of solar photovoltaic panels in response to changing of atmospheric conditions. For DC to AC conversion, the CHMLI five levels can be applied to obtain high-quality output power and a low harmonic content for the output sinusoidal wave. The simulations explained that PSO method with Multilevel Inverter (MLI) has a lot more effective tracker capability, is significantly faster, and has a lower settling time and overshoot than conventional techniques. [ABSTRACT FROM AUTHOR]

This paper discusses on the applications of non-traditional method. There is different non-conventional optimization are reviewed to solve the optimization problems. In this survey, the methods we are going to review are Krill Herd Algorithm (KHA), Pattern Search Algorithm (PSA), Sal Swarm Algorithm (SSA) and Gradient Based Algorithm (GBA). These methods are approach to find the optimization methods can solve the linear and non-linear optimization problems and results the global values. These methods are broadly reviewed. [ABSTRACT FROM AUTHOR]

Cloud computing is one of the renowned technologies that providing services like data storage, data processing and providing virtualized servers over the Internet. In cloud computing introduce a Container virtualization is a new tool that improve the overall application performance by allocate Operating System level virtualization. The operating system improves its performance for providing more containers based on number of resources availability in that operating system. Optimization of the load balancing is very important concept of equally share all incoming tasks to all available servers in cloud computing environment. The objective of this paper is to fulfill the task of distribution among all servers equally in centralized cloud computing to reduce Makespan using Grey Wolf Optimization (GWO) algorithm. While comparing simulation results, GWO showing better results than that of Ant Colony Optimization (ACO), Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) algorithms for minimize load balancing, minimize time and maximize efficiency to perform various tasks in cloud. [ABSTRACT FROM AUTHOR]

A new fast vector quantization along with a novel fast heuristic optimization algorithm has been proposed in this paper that efficiently boosts the process of finding the global optimum region in the search region. Stochastic variables are used in this algorithm to excel the speed of exploration and exploitation and at the same time making the whole process of vector quantization (VQ) computationally efficient. The search domain gradually shrinks to make algorithm effective and efficient. On comparing the simulation results of VQ based on particle swarm optimization (PSO), quantum particle swarm optimization (QPSO) and firefly algorithm (FFA) using some well- known benchmark functions has validated the efficiency of the algorithm. In finding the global optimum point, the proposed algorithm decreases the computing time 44 % relative to others. Vector quantization based image compression is a NP-hard problem has been successfully and efficiently solved in this proposed work. [ABSTRACT FROM AUTHOR]

This paper speaks to the changed Tropos objective model for handling the danger related with the product advancement cycle. Here the modification is done by the hybrid optimization algorithm. The tropos model will be improved by selecting the optimal candidate solution by using Hybrid Gravitational Search Algorithm – Particle Swarm Optimization algorithm. The proposed approach characterizes a strategy to dissect the relationship between the hubs of each layer to assess their odds of raising the dangers. Here the risks are prioritized and which are identified by the improved Tropos method. The obtained results show that, the proposed optimization-based goal model has delivered better performance in terms of time and memory requirement when compared with the normal model and also the risk and cost of the proposed model is proved to be more efficient than existing model. [ABSTRACT FROM AUTHOR]

This paper presents a new hybrid optimization algorithm to be used in feature selection problem. The proposed algorithm utilizes the power of sine cosine algorithm and Cuckoo search to both exploration and exploitation the search space to reach at best promising solution. The empirical results are evaluated on four datasets, named Breast, Leukemia, Heart and Iris that obtained from UCI repository and compared with the native sine cosine and other feature selection algorithms include Particle swarm optimization and Antlion algorithm. The results of the experiments clearly showed the efficiency of the hybrid algorithm to exploration and exploitation the features space for finest features and improved high classification rate with low run time on all used datasets. [ABSTRACT FROM AUTHOR]

The demand for electricity has increased With the increase in the number of electrical gadgets and appliances, it is now very important to emphasize in the concept of demand side management to meet the required demand of electricity. DSM assures efficient use of available energy resources. DSM along with smart grid allows the consumer to have details of power consumption information and allows the sup pliers to lower the overall load demand during the peak period and modify the load curve. Necessary data of the energy consumption and price have been taken from different papers. In this research work, the primary aim is to mainly lower the overall load demand and thus the operational cost and utility bills. The work is done in different areas – residential, commercial and industrial. To get the optimized result, Meta- heuristic algorithm was developed to minimize the problem. Because of the flexibility, gradient free mechanisms and local optima avoidance of the algorithms, meta-heuristic techniques are gaining popular. The evolutionary algorithms used to solve the demand side management problem are Particle Swarm Optimization, Firefly Algorithm and Salp Swarm Algorithm. The three algorithms are used to obtain the objective of the project work in three different areas- residential, commercial and industrial area. Firefly algorithm is found out to provide the best cost as compared to other two algorithms PSO and SSA. Firefly Algorithm is able to provide better accuracy. [ABSTRACT FROM AUTHOR]

This paper discusses a quadcopter swarm collision avoidance algorithm “CA algorithm”. The algorithm builds a repulsive force field around each quadcopter and around the obstacles in the environment. The forces values which affect one quadcopter is proportional to the invers of the distances between it and the other quadcopters in the swarm, it is affected by the speeds too to improve the response of the quadcopters. The algorithm parameters were calculated so the quadcopters avoid the collisions and achieve the wanted reaction characteristics. The algorithm was tested using Matlab, Simulink and the results were discussed. [ABSTRACT FROM AUTHOR]

Economic emission dispatch (EED) problems are one of the most crucial problems in power systems. Growing energy demand, limitation of natural resources and global warming make this topic into the center of discussion and research. This paper reviews the use of Quantum Computational Intelligence (QCI) in solving Economic Emission Dispatch problems. QCI techniques like Quantum Genetic Algorithm (QGA) and Quantum Particle Swarm Optimization (QPSO) algorithm are discussed here. This paper will encourage the researcher to use more QCI based algorithm to get better optimal result for solving EED problems. [ABSTRACT FROM AUTHOR]

Uniform illumination is one of the most important problem that must be solved in the application of high-power LED array. A numerical optimization algorithm, is applied to obtain the best LED array typesetting so that the light intensity of the target surface is evenly distributed. An evaluation function is set up through the standard deviation of the illuminance function, then the particle swarm optimization algorithm is utilized to optimize different arrays. Furthermore, the light intensity distribution is obtained by optical ray tracing method. Finally, a hybrid array is designed and the optical ray tracing method is applied to simulate the array. The simulation results, which is consistent with the traditional theoretical calculation, show that the algorithm introduced in this paper is reasonable and effective. [ABSTRACT FROM AUTHOR]

Particle Swarm Optimization is a member of swarm intelligence algorithms, which is inspired by the behavior of bird flocks. The inertia weight, one of the most important parameters of PSO, is crucial for PSO, for it balances the performance of exploration and exploitation of the algorithm. This paper proposes a new inertia weight control strategy and PSO with this new strategy is tested by four benchmark functions. The results shows that the new strategy provides the PSO with better performance. [ABSTRACT FROM AUTHOR]

This paper raised a novel particle swarm optimization algorithm based on population category. Traditional particle swarm optimization algorithm is easily to trap in local optimum. In order to avoid standard algorithm appearing premature convergence, this novel algorithm use population category strategy to find new directions for particles. At last, computational results show that the new method is effective and has a high-performance. [ABSTRACT FROM AUTHOR]

In view of the needs of the vehicle unit, this paper has carried on the research to the sensor distribution question. In the case of fully taking into account the information such as target identity and target priority, the mathematical model of optimal sensor allocation is established based on the maximum information gain criterion, and then the population-based incremental learning algorithm is used to solve. Finally, the validity of the method is verified by solving the problem of sensor assignment problem of the vehicle unit. [ABSTRACT FROM AUTHOR]

In this work, a nonlinear model based approach is presented for the altitude stabilization of a hexarotor unmanned aerial vehicle (UAV). The mathematical model and control of the hexacopter airframe is presented. To stabilize the system along the vertical direction, a Proportional Derivative (PD) control is taken into account. A particle swarm optimization (PSO) approach is used in this paper to select the optimal parameters of the control algorithm taking into account different objective functions. Simulation sets are performed to carry out the results for the non-linear system to show how the PSO tuned PD controller leads to zero the error of the position along Z earth direction. [ABSTRACT FROM AUTHOR]

The Document clustering plays significant role in Information Retrieval (IR) where it organizes documents prior to the retrieval process. To date, various clustering algorithms have been proposed and this includes the K-means and Particle Swarm Optimization. Even though these algorithms have been widely applied in many disciplines due to its simplicity, such an approach tends to be trapped in a local minimum during its search for an optimal solution. To address the shortcoming, this paper proposes a Basic Firefly (Basic FA) algorithm to cluster text documents. The algorithm employs the Average Distance to Document Centroid (ADDC) as the objective function of the search. Experiments utilizing the proposed algorithm were conducted on the 20Newsgroups benchmark dataset. Results demonstrate that the Basic FA generates a more robust and compact clusters than the ones produced by K-means and Particle Swarm Optimization (PSO). [ABSTRACT FROM AUTHOR]

Nowadays, the optimization of parameters according to a set of activities performed in order to reduce time, effort and resources is gaining more attention. That is why the use of optimization algorithms has been made necessary in everyday life. This paper presents a comparison study between micro-algorithms: Genetic Algorithm (GA), Artificial Immune System (AIS), Estimation Distribution Algorithm (EDA), Particle Swarm Optimization(PSO), Bee Algorithm (BA) and Bee SwarmOptimization (BSO). To perform an activity in a confined space, this is affected by the light from the outside, which can be blocked by shutters and doors (of crystal), and lighting of lamps obtained within this space. It is then necessary to obtain the best combination using any optimization algorithm on the condition that it should be each of these objects to have a lighting comfort. [ABSTRACT FROM AUTHOR]