Time-varying Particle Swarm Optimization Research Articles

Optimized Preprocessing using Time Variant Particle Swarm Optimization (TVPSO) and Deep Learning on Rainfall Data

In the recent past, rainfall prediction has played a significant role in the meteorology department. Changes in rainfall might affect the world's manufacturing and service sectors. Rainfall prediction is a substantial progression in giving input data for weather information and hydrological development applications. In machine learning, accurate and efficient rainfall predictionis used to support strategy for watershed management. The prediction of rain is a problematic occurrence and endures to be a challenging task. This paper implements a novel algorithm for preprocessing and optimization using historical weather from a collection of various weather parameters. The Moving Average-Probabilistic Regression Filtering (MV-PRF) method eliminates unwanted samples with less amplitude from the database. The Time Variant Particle Swarm Optimization (TVPSO) model optimizes the preprocessing rainfall data. Then this optimized data is used for the different classification processes. The preprocessing methods emphasize the recent rainfall data of the time series to improve the rainfall forecast using classification methods. Machine Learning (ML) technique classifies the weather parameters to predict rainfall daily or monthly. These experimental results show that the proposed methods are efficient and accurate for rainfall analysis.

Optimal Coverage in Wireless Sensor Network using Augmented Nature-Inspired Algorithm

One of the difficult problems that must be carefully considered before any network configuration is getting the best possible network coverage. The amount of redundant information that is sensed is decreased due to optimal network coverage, which also reduces the restricted energy consumption of battery-powered sensors. WSN sensors can sense, receive, and send data concurrently. Along with the energy limitation, accurate sensors and non-redundant data are a crucial challenge for WSNs. To maximize the ideal coverage and reduce the waste of the constrained sensor battery lifespan, all these actions must be accomplished. Augmented Nature-inspired algorithm is showing promise as a solution to the crucial problems in “Wireless Sensor Networks” (WSNs), particularly those related to the reduced sensor lifetime. For “Wireless Sensor Networks” (WSNs) to provide the best coverage, we focus on algorithms that are inspired by Augmented Nature in this research. In wireless sensor networks, the cluster head is chosen using the Diversity-Driven Multi-Parent Evolutionary Algorithm. For Data encryption Improved Identity Based Encryption (IIBE) is used. For centralized optimization and reducing coverage gaps in WSNs Time variant Particle Swarm Optimization (PSO) is used. The suggested model's metrics are examined and compared to various traditional algorithms. This model solves the reduced sensor lifetime and redundant information in Wireless Sensor Networks (WSNs) as well as will give real and effective optimum coverage to the Wireless Sensor Networks (WSNs).

Optimal Haptic Communications Over Nanonetworks for E-Health Systems

A Tactile Internet-based nanonetwork is an emerging field that promises a new range of e-health applications, in which human operators can efficiently operate and control devices at the nanoscale for remote-patient treatment. A haptic feedback is inevitable for establishing a link between the operator and unknown in-body environment. However, haptic communications over the terahertz band may incur significant path loss due to molecular absorption. In this paper, we propose an optimization framework for haptic communications over nanonetworks, in which in-body nanodevices transmit haptic information to an operator via the terahertz band. By considering the properties of the terahertz band, we employ Brownian motion to describe the mobility of the nanodevices and develop a time-variant terahertz channel model. Furthermore, based on the developed channel model, we construct a stochastic optimization problem for improving haptic communications under the constraints of system stability, energy consumption, and latency. To solve the formulated nonconvex stochastic problem, an improved time-varying particle swarm optimization algorithm is presented, which can deal with the constraints of the problem efficiently by reducing the convergence time significantly. The simulation results validate the theoretical analysis of the proposed system.

Metaheuristic Regression Equations for Split-Ring Resonator Using Time-Varying Particle Swarm Optimization Algorithm

This article presents a new technique for determining accurate values of resonant frequency and quality factor pertaining to the split-ring resonator. Different conducting shield materials have been used around a copper split-ring. The split-ring has been designed to operate at about 2.1 GHz. Various equations were worked out earlier to determine the values of resonant frequency and quality factor. However, these equations yielded different solutions. Therefore, simulations were used to obtain the values of the resonant frequency and quality factor of the split-ring resonator with different five-shield materials, using High-Frequency Structure Simulator (HFSS) software. In this work, a novel method has been introduced for obtaining values of resonant frequency which provides results with negligible error. An optimal technique, namely time-varying particle swarm optimization (TVPSO), was then performed to obtain two sets of equations for resonant frequency and quality factor. The two sets of equations, optimized using TVPSO, were compared for their effectiveness in matching the actual frequency and quality factor for each of the five materials. It was found that the TVPSO was significant in achieving the frequency and quality factor regression equation to accurately resemble the actual values portrayed by the low mean absolute error.

Reliability-Based Fatigue Life Prediction for Complex Structure with Time-Varying Surrogate Modeling

To improve the computational efficiency and accuracy of reliability-based fatigue life prediction for complex structure, a time-varying particle swarm optimization- (PSO-) based general regression neural network (GRNN) surrogate model (called as TV/PSO-GRNN) is developed. By integrating the proposed space-filling Latin hypercube sampling technique and PSO-GRNN regression function, the mathematical model of TV/PSO-GRNN is studied. The reliability-based fatigue life prediction framework is illustrated in respect of the TV/PSO-GRNN surrogate model. Moreover, the reliability-based fatigue life prediction of an aircraft turbine blisk under multiphysics interaction is performed to validate the TV/PSO-GRNN model. We obtain the distributional characteristics, reliability degree, and sensitivity degree of fatigue failure cycle, which are useful for the turbine blisk design. By comparing the direct simulation (FE/FV model), RSM, GRNN, PSO-GRNN, and TV/PSO-GRNN, we observe that the TV/PSO-GRNN surrogate model is promising to perform the reliability-based fatigue life prediction of the turbine blisk and enhance the computational efficiency while ensuring an acceptable computational accuracy. The efforts of this study offer a useful insight for the reliability-based design optimization of complex structure.

A Clustering Based Archive Multi Objective Gravitational Search Algorithm

Gravitational search algorithm (GSA) is a recent created metaheuristic optimization algo- rithm with good results in function optimization as well as real world optimization problems. Many real world problems involve multiple (often conflicting) ob jectives, which should be optimized si- multaneously. Therefore, the aim of this paper is to propose a multi-objective version of GSA, namely clustering based archive multi-objective GSA (CA-MOGSA). Proposed method is created based on the Pareto principles. Selected non-dominated solutions are stored in an external archive. To control the size of archive, the solutions with less crowding distance are removed. These strate- gies guarantee the elitism and diversity as two important features of multi-objective algorithms. The archive is clustered and a cluster is randomly selected for e ach agent to apply the gravitational force to attract it. The selection of the proper cluster is based on the distance between clusters represen- tatives and population member (the agent). Therefore, suitable trade-off between exploration and exploitation is provided. The experimental results on eight standard benchmark functions reveal that CA-MOGSA is a well-organized multi-objective version of GSA. It is comparable with the state-of- the-art algorithms including non-dominated sorting genetic algorithm-II (NSGA-II), strength Pareto evolutionary algorithm (SPEA2) and better than multi-objective GSA (MOGSA), time-variant par- ticle swarm optimization (TV-PSO), and non-dominated sorting GSA (NSGSA).

Prediction for Gas Emission Quantity of the Working Face Based on LSSVM Optimized by Improved Particle Swarm Optimization

Gas emission quantity may forecast the quantity of gas inside the coal, which has important significance for predicting the outburst of gas, but the problem always has not been well solved. Traditional Particle swarm optimization (PSO) algorithm lacks the ability to track the optimal solution while the fitness function changes. An improved algorithm named Time Variant PSO (TVPSO) was proposed to track the optimal solution online. Then it was used to choose the parameters of Least Square Support Vector Machine (LSSVM), which could avoid the man-made blindness and enhance the efficiency of online forecasting. The TVPSO-LSSVM method is based on the minimum structure risk of SVM and the globally optimizing ability of TVPSO to forecast continuously the gas emission quantity of the working face. The method was applied to solve the problem of nonlinear chaos time series prediction. Result shows that the method satisfies the need of online forecasting.

Combining technical trading rules using particle swarm optimization

Technical trading rules have been utilized in the stock market to make profit for more than a century. However, only using a single trading rule may not be sufficient to predict the stock price trend accurately. Although some complex trading strategies combining various classes of trading rules have been proposed in the literature, they often pick only one rule for each class, which may lose valuable information from other rules in the same class. In this paper, a complex stock trading strategy, namely performance-based reward strategy (PRS), is proposed. PRS combines the two most popular classes of technical trading rules – moving average (MA) and trading range break-out (TRB). For both MA and TRB, PRS includes various combinations of the rule parameters to produce a universe of 140 component trading rules in all. Each component rule is assigned a starting weight, and a reward/penalty mechanism based on rules’ recent profit is proposed to update their weights over time. To determine the best parameter values of PRS, we employ an improved time variant particle swarm optimization (TVPSO) algorithm with the objective of maximizing the annual net profit generated by PRS. The experiments show that PRS outperforms all of the component rules in the testing period. To assess the significance of our trading results, we apply bootstrapping methodology to test three popular null models of stock return: the random walk, the AR(1) and the GARCH(1,1). The results show that PRS is not consistent with these null models and has good predictive ability.

A Random Time-Varying Particle Swarm Optimization for the Real Time Location Systems

A Random Time-Varying Particle Swarm Optimization for the Real Time Location Systems