Combination of Feature Selection and Learning Methods for IoT Data Fusion

Cloud computing provides the computational machines as a support of the clients utilizing cloud organize. In cloud computing, the user inputs are executed with required machines to convey the administrations. Numerous task scheduling methods are utilized to plan the client tasks to the machines. In this paper, another successful hybrid task scheduling is proposed to minimize the total execution time using Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) algorithms. In hybrid Genetic Algorithm - Particle Swarm Optimization (GA-PSO) algorithm, PSO helped GA to obtain better results compare to a standard genetic algorithm, Min-Min, and Max-Min algorithms results.

Sustainable NO[formula omitted] emission reduction at a coal-fired power station through the use of online neural network modeling and particle swarm optimization

ABSTRACTThis article introduces a method of mistuned parameter identification which consists of static frequency testing of blades, dichotomy and finite element analysis. A lumped parameter model of an engine bladed-disc system is then set up. A bladed arrangement optimization method, namely the genetic particle swarm optimization algorithm, is presented. It consists of a discrete particle swarm optimization and a genetic algorithm. From this, the local and global search ability is introduced. CUDA-based co-evolution particle swarm optimization, using a graphics processing unit, is presented and its performance is analysed. The results show that using optimization results can reduce the amplitude and localization of the forced vibration response of a bladed-disc system, while optimization based on the CUDA framework can improve the computing speed. This method could provide support for engineering applications in terms of effectiveness and efficiency.

As it is well-known, orange peel is used for making jam and oil. For this purpose, orange samples with high peel thickness are best. In order to predict peel thickness in orange fruit, we present a system based in image features, comprising: area, eccentricity, perimeter, length/area, blue value, green value, red value, wide, contrast, texture, wide/area, wide/length, roughness, and length. A novel identification solution based on the hybrid of particle swarm optimization (PSO), genetic algorithm (GA) and artificial neural network (ANN) is proposed. In addition, principal component analysis (PCA) has been applied to reduce the number of dimensions, without much loss of information. Taguchi's robust optimization technique has been applied to determine the optimal setting for parameters of PSO, GA, and ANN. The optimal level of factors were: Number of Neuron in first layer=7, Number of Neuron in second layer=2, Maximum Iteration=400, Crossover probability=0.7, Mutation probability=0.1, and Swarm (Population) Size=200. Results for prediction of orange peel thickness based on levels that are achieved by Taguchi method were evaluated by five performance measures: the coefficient of determination (R2), mean squared error (MSE), mean absolute error (MAE), sum square error (SSE), and root mean square error (RMSE), reaching values of 0.8571, 0.0123, 0.0924, 1.392, and 0.1109, respectively.

An inverse design framework incorporating a physics-based surrogate model and global optimization is proposed to assist in the design of low warpage ultra-thin packages by adjusting the metal densities over substrate subsections and layers. The surrogate model is derived from two finite element analysis (FEA) models. The first one describes the relationship between the metal density in the substrate layer to the coefficient of thermal expansion (CTE) while the second one describes the relationship between in-plane CTE variation of the substrate to the warpage profile. Results from these two FEA models are used to train separate artificial neural networks (ANN). When these ANNs are run sequentially, the surrogate model can accurately determine the warpage profile for any set of metal densities. Three global optimization algorithms, Particle Swarm Optimization (PSO), Genetic Algorithm (GA) and Cross Entropy (CE) were then evaluated using this surrogate model. Three case studies consisting of different warpage profiles (original and 20% reduced warpage) and constraints to the optimization search space (±20% or ±50% change to metal density) were then evaluated using these algorithms. For all three cases, the three algorithms converged to similar solutions, indicating that indeed the global minimum has been attained and determined. However, GA took a significantly longer time to converge than PSO and CE. Based on these results, PSO and CE are recommended to be suitable algorithms to carry out inverse design for this type of problem.

Objective: Particle Swarm Optimization (PSO) and Artificial Neural Network (ANN) are two broadly used for rule generation process in data mining. ANN have been widely used for pattern extraction from medical databases. Methods: Heart disease is one of the leading death cause disease in all over the world in the present situation. A large number of research works have been carried out for diagnosing heart failures using data mining techniques. As the number of heart disease features increasing along with a number of instances, the traditional approaches such as PSO, ANN and BPSO are fail to predict the exact disease causing features. Findings: In this research work, an improved ANN approach model called Optimized Artificial Neural Network (OANN) was implemented on the medical data sets. In this paper, an Optimized Particle Swarm Optimization (PSO) technique is used for disease dimension reduction. Filter based Artificial Neural Network is used for classifying the disease type as positive or negative based on the disease features. Applications/Improvements: The performance of the proposed algorithm is analyzed by using the traditional approaches of Performance plot, Regression, ROC Value and Confusion Matrix. It is proved that the performance of the whole ANN network is optimized after the inclusion of proposed PSO for Feature Reduction.

In this paper, an artificial neural network (ANN)-based dynamic weighted combination model trained by novel particle swarm optimization (PSO) algorithm is proposed for software reliability prediction. Different software reliability growth models (SRGMs) are merged based on the weights derived by the learning algorithm of the proposed ANN. To avoid trapping in local minima during training of the ANN, we propose a neighborhood-based adaptive PSO (NAPSO) algorithm for learning of the proposed ANN in order to find global optimal weights. We conduct the experiments on real software failure data sets for validation of the proposed dynamic weighted combination model (PDWCM). Fitting performance and predictability of the proposed PSO-based neural network are compared with the conventional PSO-based neural network (CPSO) and existing ANN-based software reliability models. We also compare the performance of the proposed PSO algorithm with the CPSO algorithm through learning of the proposed ANN. Empirical results indicate that the proposed PSO and CPSO-based neural network present fairly accurate fitting and prediction capability than the other existing ANN-based software reliability models. Moreover, the proposed PSO-based neural network is most promising for the purpose of software fault prediction since it shows comparatively better fitting and prediction performance results than the other models.

Metaheuristic techniques are enormously being used nowadays for their applications in field like Power system and are being applied to many optimization problems of power system due to difficult approach of classical methods. Transmission expansion planning (TEP) is a challenging task to deal in power system. A new approach, hybrid genetic algorithm particle swarm optimization (HGAPSO) for solving TEP problem, is introduced to eliminate the drawback of GA and PSO. Problems of immature convergence in particle swarm optimization (PSO) and low convergence speed in genetic algorithm (GA) mitigate to the hybridization of both techniques. Proposed HGAPSO Algorithm is tested for three standard electric test systems for TEP problem in MATLAB tool. Experimental results found by HGAPSO are compared with GA and PSO Algorithm to test its performance for TEP problem.

The objective of the research work is to examine energy-efficient routing in wireless sensor networks for moving nodes by contrasting new evolutionary algorithms with the Particle Swarm Optimization (PSO) Algorithm. Comparative analysis of energy efficient routing is performed by a novel genetic algorithm where there are several samples (N = 10) and a PSO algorithm where there are several samples (N = 10) techniques with pre-test power of 80% using NS2. When routing wireless sensor networks with moving nodes, Various metrics, including delay, energy use, and packet delivery ratio, are used to compare PSO and genetic algorithms. The evolutionary algorithm outperforms the PSO algorithm in these ways in terms of packet delivery ratio, energy usage, and delay. (p < 0.05) indicates a statistically significant difference. The research's findings comprised the three metrics of delay, energy consumption and packet delivery ratio. The method shows that the novel Genetic algorithm outperforms the PSO algorithm for wireless sensor network energy-efficient routing for moving nodes by identifying a set of routes that can satisfy the delay restrictions.KeywordsNovel genetic algorithmParticle Swarm Optimization (PSO)Wireless sensor networkDelayEnergy consumptionPacket delivery ratio

The complexity of embedded system design increase as the technology keeps evolving from day to day. Hardware software partitioning has been a promising approach to solve this design problem of complexity in the embedded systems, by providing a solution that automatically decides the partitioning. A lot of research has been done to automate the partitioning which focusing on exact and heuristic algorithm. Then due to the slow performance of the exact algorithms, the study focus shift to heuristic algorithms such as Genetic Algorithm (GA) and Particle Swarm Optimization (PSO). In this research the performance of both PSO algorithm and GA are analyzed in the application of the partitioning. In order to get the best among these two algorithms, hybrid combination across the two algorithms is designed. The best cost and their average time to achieve it are compared among PSO, GA and hybrid design. As a result, the graph obtained from the hybrid GA-GA-PSO required a smaller number of iterations to reach best cost. Compared to previous work, GA-GA-PSO obtained a smooth as the successive PSO graph. In conclusion, a new idea of hybrid across PSO and GA has been introduced and it results into a better solution for Hardware Software Partitioning.

In recent years, genetic algorithm (GA), particle swarm optimization (PSO) and hybrid genetic algorithm particle swarm optimization (HGAPSO) have attracted considerable attention among various modern heuristic optimization techniques. In this study the HGAPSO, PSO and GA optimization techniques are used for to search the optimal placement and sizing of static VAR compensator (SVC) in power system. The objective function is defined for reducing power loss, voltage deviation and investment costs of SVC. The effectiveness of the proposed hybrid based approach is applied and demonstrated on IEEE 30 Bus network. The results show that the proposed hybrid HGAPSO compared with PSO and GA optimization for performs and giving better solution.

An optimal artificial neural network (ANN) has been developed to predict the Nusselt number of non-Newtonian nanofluids. The resulting ANN is a multi-layer perceptron with two hidden layers consisting of six and nine neurons, respectively. The tangent sigmoid transfer function is the best for both hidden layers and the linear transfer function is the best transfer function for the output layer. The network was trained by a particle swarm optimization (PSO) algorithm. Nanofluid concentration, Reynolds number, and Prandtl number are input for the ANN and the nanofluid Nusselt number is its output. There exists an excellent agreement between the ANN predicted values and experimental data. The average and maximum differences between experimental data and those predicted by ANN are about 0.8 and 5.6 %, respectively. It was also found that ANN predicts the Nusselt number of nanofluids more accurately than the previously proposed correlation.

این مطالعه به منظور بررسی پیش بینی شاخص های عملکرد تولیدی در مرغان تخم گذار با استفاده از شبکه های عصبی مصنوعی و رگرسیون غیرخطی چندگانه انجام شد. بررسی بر روی اطلاعات چهار دوره متوالی پرورش در یک واحد پرورش مرغ تخم گذار صورت گرفت. روش های داده-کاوی شامل رگرسیون خطی و غیر خطی، شبکه عصبی پرسپترون سه لایه، شبکه عصبی پرسپترون چهار لایه و شبکه عصبی با تابع پایه ای شعاعی بود. در این مدل ها از متغیرهای سن گله، میزان خوراک مصرفی و فصل تولید به عنوان متغیر پیشگو و شاخص های عملکرد تولیدی شامل درصد تخم-گذاری، وزن توده ای تخم مرغ تولیدی و ضریب تبدیل غذایی به عنوان متغیر پاسخ استفاده شد. نتایج نهایی رگرسیون های خطی نشان داد که برای تمامی متغیرهای وابسته مورد مطالعه متغیر مستقل سن گله معنی دار می باشد. بنابراین رگرسیون غیر خطی شاخص های عملکرد تولیدی در مقابل سن برای مقایسه با شبکه های عصبی مختلف مورد بررسی قرار گرفت و برای مقایسه کلیه مدل ها از ضریب تعیین (R2) و میانگین قدر مطلق خطا (MAE) استفاده شد. نتایج نشان داد بین شبکه های عصبی مصنوعی مختلف مورد مطالعه، شبکه با تابع پایه ای شعاعی بهتر از سایر مدل های در پیش‌بینی شاخص های عملکرد تولیدی مرغان تخم گذار عمل می کند.

The effective exploitation of smart technology in applications helps farmers make better decisions without increasing costs. Agricultural Research Centers (ARCs) are continually updating and producing new datasets from applied research, so the smart model should dynamically address all surrounding agricultural variables and improve its expertise from all available datasets. This research concentrates on sustainable agriculture using Adaptive Particle Swarm Optimization (PSO) and Artificial Neural Networks (ANNs). Therefore, if a new related dataset is created, this new incoming dataset is merged with the existing dataset. The proposed PSO then bypasses the summarization of the dataset. It deletes the least essential and speculative records and keeps the records that are the most influential in the classification process. The summarized dataset is interposed in the training process without re-establishing the system again by modifying the classical ANN. The proposed ANN comprises an adaptive input layer and an adaptive output layer to handle the process of continuously updating the datasets. A comparative study between the proposed adaptive PSO-ANN and other known and used methods on different datasets has been applied. The results prove the quality of the proposed Adaptive PSO-ANN from various standard measurements. The proposed PSO-ANN achieved an accuracy of 94.8%, precision of 91.15%, recall of 97.93%, and F1-score of 94.42%. The smart olive cultivation case study is accomplished with the proposed adaptive PSO-ANN and technological tools from the Internet of Things (IoT). The advanced tools from IoT technology are established and analyzed to control all the required procedures of olive cultivation. This case study addresses the necessary fertilizers and irrigation water to adapt to the changes in climate. Empirical results show that smart olive cultivation using the proposed adaptive PSO-ANN and IoT has high quality and efficiency. The quality and efficiency are measured by diversified metrics such as crop production and consumed water, which confirm the success of the proposed smart olive agriculture method.

This paper proposes an advanced control strategy for DFIG based Wind Turbine. The designed method is based on a combination of Particle Swarm Optimization (PSO) and Artificial Neural Network (ANN). PSO combined ANN is suggested to track the available maximum power point (MPPT) at varying wind speeds. Thus, PSO is used to improve the dynamic performance of Doubly Fed Induction Generator (DFIG) by optimizing its Proportional Integral (PI) controller gains. This work highlights the performance of the PSO optimized PI controller against classical one. The proposed control strategy is verified via 2 MW DFIG-WT using the MATLAB/Simulink environment. The obtained results validate the proposed PSO-PI as an effective tool for improving the dynamic behavior of DFIGWT, it reveals that the overshoots are reduced by 50 % compared to the classical PI. In addition, a faster transient response is achieved using the proposed control strategy.