Proposed Particle Swarm Optimization Algorithm Research Articles

Video Deepfake classification using particle swarm optimization-based evolving ensemble models

The recent breakthrough of deep learning based generative models has led to the escalated generation of photo-realistic synthetic videos with significant visual quality. Automated reliable detection of such forged videos requires the extraction of fine-grained discriminative spatial-temporal cues. To tackle such challenges, we propose weighted and evolving ensemble models comprising 3D Convolutional Neural Networks (CNNs) and CNN-Recurrent Neural Networks (RNNs) with Particle Swarm Optimization (PSO) based network topology and hyper-parameter optimization for video authenticity classification. A new PSO algorithm is proposed, which embeds Muller's method and fixed-point iteration based leader enhancement, reinforcement learning-based optimal search action selection, a petal spiral simulated search mechanism, and cross-breed elite signal generation based on adaptive geometric surfaces. The PSO variant optimizes the RNN topologies in CNN-RNN, as well as key learning configurations of 3D CNNs, with the attempt to extract effective discriminative spatial-temporal cues. Both weighted and evolving ensemble strategies are used for ensemble formulation with aforementioned optimized networks as base classifiers. In particular, the proposed PSO algorithm is used to identify optimal subsets of optimized base networks for dynamic ensemble generation to balance between ensemble complexity and performance. Evaluated using several well-known synthetic video datasets, our approach outperforms existing studies and various ensemble models devised by other search methods with statistical significance for video authenticity classification. The proposed PSO model also illustrates statistical superiority over a number of search methods for solving optimization problems pertaining to a variety of artificial landscapes with diverse geometrical layouts.

An Enhanced Particle Swarm Optimization Algorithm via Adaptive Dynamic Inertia Weight and Acceleration Coefficients

The particle swarm optimization (PSO) algorithm counts among the most popular metaheuristic algorithms based on swarm intelligence. Since the publication of the first article on this optimization technique, researchers have developed many PSO variants with some improvement in its performance. The PSO optimization performance hinges on its ability to achieve a good exploration-exploitation balance. The most common method that helps to improve exploration-exploitation balance is modifying the PSO three controlling parameters, namely the inertia weight and two acceleration coefficients. In this paper a PSO variant that combines adaptive dynamic inertia weight and adaptive dynamic acceleration coefficients to enhance the exploration-exploitation balance of the PSO is proposed. The enhanced PSO algorithm called Adaptive Dynamic Inertia Weight and Acceleration Coefficient Optimization (ADIWACO) algorithm is tested on seven well-known standard test functions comprising four unimodal and three multimodal ones. The performance of the PSO is then compared with that of the standard PSO (SPSO) and four existing PSO variants. The experimental results comprising optimum value, runtime, mean value, standard deviation and convergence rate, and confirmed by the results of ranking statistics and Wilcoxon signed rank test conducted on the experimental results, indicate significantly better performance by the proposed PSO algorithm.

An efficient particle swarm optimization with evolutionary multitasking for stochastic area coverage of heterogeneous sensors

This paper investigates the stochastic area coverage problem of sensors with uncertain detection probability. The risk associated with uncertain parameters is managed using the conditional value-at-risk (CVaR) risk measure. The loss function is represented by the uncovered area coverage rate. We then formulate the minimum CVaR-based uncovered area coverage (CVaR-UAC) problem and provide some theoretical guarantees for the problem. Unlike previous research that treats area coverage as a single problem, we propose an efficient particle swarm optimization (PSO) with evolutionary multitasking to solve the stochastic area coverage problem along with multiple simplified problem forms. These simplified problems act as the auxiliary tasks for the original CVaR-UAC to enhance the evolutionary search. We have improved the proposed PSO algorithm from the framework of disturbance PSO and virtual force directed co-evolutionary particle swarm optimization, using a hybrid method in population initialization and an adaptive perturbation in individual updating. As a result, the exploration ability of the algorithm is significantly enhanced. The experiment results have demonstrated the effectiveness of the proposed algorithm compared with state-of-the-art algorithms in terms of solution quality.

Parameters extraction of photovoltaic cells using swarm intelligence based optimization technique: research on single diode model and double diode model

Solar-energy is a clean source of energy and photovoltaic (PV) panels are constructed from solar cells (SC) which convert energy of light into electricity without any environmental effect. The researchers and policy makers focus on the huge scale adoption of solar panels due to its cleaner production. However, there is non-linear behavior in current-voltage characteristics of solar panels and shortage of data in manufacturer’s datasheet. In order to enhance the efficiency of solar panels it is mandatory to develop the PV panels scheme accurately by extracting the basic parameters. In this research study a mathematical model of two different solar cell models is used such as Single Diode Model (SDM) and Double Diode Model (DDM). The Particle Swarm Optimization (PSO) is used to extract the five and seven unknown parameters of SDM and DDM. The algorithm runs with one thousand iterations to minimize the Root Mean Square Error (RMSE) where the RMSE is the vector of five unknown parameters for SDM and seven for DDM. The superiority of proposed PSO algorithm is proved by the optimized results of unrevealed parameters with minimized RMSE of up to 10-3. Optimum parameter values for the solar cell models are applied on the real time data of a 55 mm diameter commercial RTC-France SC. Finally, the results reveal that P-V and I-V curves exhibit smallest deviation between estimated and real time values. The results reveal that the proposed PSO converges to optimal solution with least number of iterations compared to the existing metaheuristic algorithms.

Robust optimization for casualty scheduling considering injury deterioration and point-edge mixed failures in early stage of post-earthquake relief.

Scientifically organizing emergency rescue activities to reduce mortality in the early stage of earthquakes. A robust casualty scheduling problem to reduce the total expected death probability of the casualties is studied by considering scenarios of disrupted medical points and routes. The problem is described as a 0-1 mixed integer nonlinear programming model. An improved particle swarm optimization (PSO) algorithm is introduced to solve the model. A case study of the Lushan earthquake in China is conducted to verify the feasibility and effectiveness of the model and algorithm. The results show that the proposed PSO algorithm is superior to the compared genetic algorithm, immune optimization algorithm, and differential evolution algorithm. The optimization results are still robust and reliable even if some medical points fail and routes are disrupted in affected areas when considering point-edge mixed failure scenarios. Decision makers can balance casualty treatment and system reliability based on the degree of risk preference considering the uncertainty of casualties, to achieve the optimal casualty scheduling effect.

Low-Complexity Beamforming Design for a Cooperative Reconfigurable Intelligent Surface-Aided Cell-Free Network

Cell-free (CF) networks are proposed to suppress the interference among collocated cells by deploying several BSs without cell boundaries. Nevertheless, as installing several base stations (BSs) may require high power consumption, cooperative CF networks integrated with a reconfigurable intelligent surface (RIS)/metasurface can avoid this problem. In such cooperative RIS-aided MIMO networks, efficient beamforming schemes are essential to boost their spectral and energy efficiency. However, most of the existing available beamforming schemes to maximize spectral and energy efficiency are complex and entail high complexity due to the matrix inversions. To this end, in this work we present a computationally efficient stochastic optimization-based particle swarm optimization (PSO) algorithm to amplify the spectral efficiency of the cooperative RIS-aided CF MIMO system. In the proposed PSO algorithm, several swarms are generated, while the direction of each swarm is tuned in each iteration based on the sum-rate performance to obtain the best solution. Our simulation results show that our proposed scheme can approximate the performance of the existing solutions for both the performance metrics, i.e., spectral and energy efficiency, at a very low complexity.

Fitting of TC model according to key parameters affecting Parkinson's state based on improved particle swarm optimization algorithm

Biophysical models contain a large number of parameters, while the spiking characteristics of neurons are related to a few key parameters. For thalamic neurons, relay reliability is an important characteristic that affects Parkinson's state. This paper proposes a method to fit key parameters of the model based on the spiking characteristics of neurons, and improves the traditional particle swarm optimization algorithm. That is, a nonlinear concave function and a Logistic chaotic mapping are combined to adjust the inertia weight of particles to avoid the particle falling into a local optimum in the search process or appearing premature convergence. In this paper, three parameters that play an important role in Parkinson's state of the thalamic cell model are selected and fitted by the improved particle swarm optimization algorithm. Using the fitted parameters to reconstruct the neuron model can predict the spiking trajectories well, which verifies the effectiveness of the fitting method. By comparing the fitting results with other particle swarm optimization algorithms, it is shown that the proposed particle swarm optimization algorithm can better avoid local optima and converge to the optimal values quickly.

A Service-Aware Latency-Relaxed uRLLC Multiplexing Strategy within eMBB Traffic for Hyperloop Communications

The train-to-ground communications for Hyperloop encounter numerous challenges compared to the previous systems as a result of ultrahigh velocity, metal confined tube, severe penetration attenuation, frequent handover, etc. Ultrareliable low latency communication (uRLLC) services are extremely pivotal to the operation of Hyperloops since they are responsible for the transmission of safety-related messages like train control system (TCS) information. Furthermore, the sporadic generated uRLLC traffic is strictly latency-sensitive and requires stringent transmission reliability, which is usually realized by multiplexing with the enhanced mobile broadband (eMBB) traffic when coexisting with heterogeneous traffic. Different from current multiplexing schemes which handle all uRLLC traffic indiscriminately, we focus on the detailed demands of different uRLLC services for Hyperloops, including the end-to-end transmission latency and bit error rate (BER). Then, we classify the safety-related uRLLC traffic into 5 levels according to the metrics and relax the multiplexing latency properly. On this basis, an optimization problem incorporating minimizing uRLLC power and maximizing the eMBB throughput is formulated. Then, a particle swarm optimization (PSO) algorithm is proposed to cope with this nondeterministic polynomial- (NP-) hard problem. Simulation results imply that our proposed service-aware latency-relaxed concept enables a flexible multiplexing of the uRLLC traffic, and the proposed PSO algorithm can obtain the suboptimal solutions with the constraints of BER and time-frequency range, which can cater to the demands of uRLLC and improve the passengers’ in-journey communication quality of services to some degree.

Increase the WSN-Lifespan Used in Monitoring Forest Fires by PSO

The Wireless Sensor Networks (WSNs) have become the most cost-effective monitoring solution due to their low cost, despite their major drawback of limited power due to dependence on batteries. Clustering is one of the successful solutions for extending the life of the WSN. Where optimal CH selection results in an increase in the lifetime of WSN. The paper discusses a strategy for field deployment of nodes in the form of clusters and a method for Cluster Head (CH) selection using Particle Swarm Optimization (PSO). The method employs a fitness function to select the optimum CHs for cluster nodes. This paper simulates a case study for the early detection of forest fires and demonstrates how to extend the lifetime of a WSN by utilizing the proposed PSO algorithm.

A cooperative image object recognition framework and task offloading optimization in edge computing

The development of AIoT (Artificial Intelligence of Things) and communication technologies has recently brought with it many promising applications. Intelligent surveillance is one of the new models of applications that synthesizes both technologies of IoTs and the object recognition method of artificial intelligence. However, this system suffers from the heavy computation load problem, but the processing devices are generally lightweight with only limited memory and computation power. In this paper, we propose a cooperative image object recognition framework to integrate the process of AIoT devices into the edge computing environment to overcome this problem. The proposed scheme offloads some captured surveillance video frames to nearby GPU equipped edge servers and then integrates the returned results to enhance the overall recognition accuracy of the surveillance system. We also formulate the AIoT Task Offloading scheduling to a mathematical programming Problem (named ATOP) and prove it to be an NP-complete problem. A heuristic Particle Swarm Optimization algorithm is also proposed to determine near optimal offloading scheduling for the ATOP such that the overall object recognition precision is maximized. Although the object recognition precision is enhanced, there still remains a gap to the ground truth, and the cumulative gap might cause significant errors as times goes by. In this research, we also develop a mechanism to help the designer to automatically diagnose when the cumulative errors become significant. Simulation results demonstrate that the proposed framework is feasible and the proposed Particle Swarm Optimization algorithm for the ATOP outperforms the greedy approach and the genetic algorithm. The simulation results also show that the abnormal data diagnosis mechanism can figure out when the cumulative errors happen using a real-world human-flow counting data set.

A Novel Particle Swarm Optimizer and Its Application to the Yield Curve Estimation Problem

Particle swarm optimization (PSO) has been considered as one of the main swarm intelligence algorithms for solving single-objective optimization problem. How to update the velocities and positions of a swarm of particles is key to its optimization performance. In this paper, we propose to use the moving average of the local best positions visited so far as a key information to update the velocities and positions. Further, a central learning strategy is proposed in which the center of the local best positions is computed and used to update the global best position. Combining these two strategies with the updating formulas which are inspired by the free electron model in metal conductors placed in an external electric field, we name the proposed PSO algorithm as PSO with moving average and central learning strategies (dubbed as MAPSO). We test the performance of MAPSO on the CEC 2017 test problems with 10 and 30 dimensions. Experimental results show that MAPSO significantly outperforms some well-known PSOs in general. We then apply MAPSO on a very challenging real-world problem, i.e. the yield curve estimation problem, in macroeconomics. Our experimental study on the yield curve estimation problem with Shanghai interbank offered rates shows that MAPSO can effectively solve the problem and achieve the state-of-the-art performance.

Sound classification using evolving ensemble models and Particle Swarm Optimization

Automatic sound classification attracts increasing research attention owing to its vast applications, such as robot navigation, environmental sensing, musical instrument classification, medical diagnosis, and surveillance. In this research, we propose an ensemble convolutional bidirectional Long Short-Term Memory (CBiLSTM) network with optimal hyper-parameter selection for undertaking sound classification. We first transform each audio signal into a spectrogram representation using the Short-time Fourier transform (STFT). A Particle Swarm Optimization (PSO) variant is subsequently proposed to optimize the learning rate, weight decay, numbers of filters and hidden units in the convolutional and BiLSTM layers, respectively, in order to extract effective spatial–temporal characteristics from the spectrogram inputs. To tackle the issue of stagnation in optimization, the proposed algorithm incorporates local exploitation using secant and Newton–Raphson methods, promising leader generation using regular and irregular super-ellipse formulae, and three-dimensional spherical search coefficients. Moreover, it takes into account multiple fused elite signals in conjunction with numerical analysis based exploitation to balance between diversification and intensification. A variety of CBiLSTM networks with distinctive optimized settings are devised. An ensemble model is then constructed by incorporating a set of three yielded networks based on a majority voting scheme. Evaluated using several audio data sets, our ensemble CBiLSTM networks outperform those with default and optimal settings identified by other search methods, existing deep architectures and state-of-the-art related studies. In addition to sound classification tasks, the proposed PSO algorithm also outperforms a number of classical and advanced search methods for solving diverse unimodal and multimodal benchmark functions with statistical significance.

Optimal integration of photovoltaic distributed generation in electrical distribution network using hybrid modified PSO algorithms

The satisfaction of electricity customers and environmental constraints imposed have made the trend towards renewable energies making them more essential due to their advantages as reducing power losses and ameliorating system’s voltage profiles and reliability. This article addresses the optimal location and size of multiple distributed generations (DGs) based on solar photovoltaic panels (PV) connected to electrical distribution network (EDN) using the various proposed hybrid particle swarm optimization (PSO) algorithms based on chaotic maps and adaptive acceleration coefficients. These algorithms are implemented to optimally allocate the DGs based PV (PV-DG) into EDN by minimizing the multi-objective function (MOF), which is represented as the sum of three technical parameters of the total active power loss (TAPL), total voltage deviation (TVD), and total operation time (TOT) of overcurrent relays (OCRs). The effectiveness of the proposed PSO algorithms were validated on both standards IEEE 33-bus, and 69-bus. The optimal integrating of PV-DGs into EDNs reduced the TAPL percentage by 56.94 % for the IEEE 33-bus and by 61.17 % for the IEEE 69-bus test system, enhanced the voltage profiles while minimizing the TVD by 37.35 % and by 32.27 % for two EDNs, respectively.

An Improved Energy-Aware Routing Protocol Using Multiobjective Particular Swarm Optimization Algorithm

The energy of sensor nodes in wireless sensor networks is limited, which is one of the most important challenges due to the lack of a fixed power supply. Because data transmission consumes the most energy of nodes, a node that transmits more packets runs out of energy faster than the others. When the energy of a node comes to the end of a network, the process of network operation may be disrupted. In this case, critical information in the network with the desired quality may not reach the hole and eventually the base stations. Therefore, considering the dynamic topology and distributed nature of wireless sensor networks, designing energy-efficient routing protocols is the main challenge. In this paper, an energy-aware routing protocol based on a multiobjective particle swarm optimization algorithm is presented. In the proposed particle swarm optimization algorithm method, the proportionality function for selecting the optimal threaded node is set based on the goals related to service quality including residual energy, link quality, end-to-end delay, and delivery rate. The simulation results show that the proposed method consumes less energy and has a longer lifespan compared with the state-of-the-art methods due to balancing the goals related to service quality criteria.

Predicting Academic Performance of Deaf Students Using Feed Forward Neural Network and An Improved PSO Algorithm

Literacy rate of deaf students is very less in India. So there is a need to build an effective academic prediction model for identifying weak deaf students. Many machine learning techniques like Decision tree, Support Vector Machine, Neural Network are used to build prediction models. But the most preferred technique is neural network. It is found out that regression model build with neural networks takes more time to converge and the error rate is quite high. To solve the problems of neural network, we use Particle Swarm Optimization (PSO) for weight adjustment in the neural network. But, one of the main drawback of PSO lies in setting the initial parameters. So, a new PSO algorithm which determines the initial weight of the neural network using regression equation is proposed. The results show that neural network build with the proposed PSO algorithm performs well than neural network build with basic PSO algorithm. The Mean Square Error (MSE) achieved in this work is 0.0998, which is comparatively less than many existing models.

Optimizing parcel sorting process of vertical sorting system in e-commerce warehouse

The vertical sorting system is an emerging system in warehouse section. It achieves higher level of automated sorting by applying conveyor sorter and AGVs. This paper investigates the optimization problem of parcel sorting in an e-commerce warehouse where parcels are waiting to be sorted and delivered. The assignment among the parcels, picking stations and AGVs are determined together with the objective of minimizing the finishing time of processing the last parcel, so that a detailed operational plan for warehouse sorting can be worked out. A mixed-integer linear programming model is developed based on the problem, and particle swarm optimization (PSO) algorithm is employed for problem solving. Numerical experiment shows that the proposed PSO algorithm can solve the model with high efficiency, and sensitivity analysis give suggestion about the arrangement of trailers’ location.

Study on conical source transient electromagnetic based on AWPSO algorithm

The transient electromagnetic conical field source device can effectively reduce the inductance between the coils and improve the resolution of the small device to detect the shallow underground layer. However, the conventional inversion method requires an initial model and has the disadvantage of low inversion precision. Combined with the results of previous studies, this paper proposed an adaptive weighted particle swarm optimization (AWPSO) algorithm based on Sigmoid function through the analysis and research of PSO, which solved the problem of artificial initial model and low precision of inversion results. By calculating the test function, the algorithm can effectively improve the searching ability of particle swarm optimization algorithm. Several different typical geoelectric models are designed, and the algorithm is applied to data inversion of transient electromagnetic geoelectric model. Combined with the measured data of a hot spring practice area, the inversion calculation and interpretation of the sounding data were carried out, and the inversion calculation results were confirmed by the geological and hydrological data. The results show that the proposed particle swarm optimization algorithm has a high inversion fitting degree to the theoretical model and the measured data, achieves the separation of the apparent resistivity anomalies in the shallow subsurface, and improves the resolution and interpretation accuracy of the measured data in the conical field source transient electromagnetic method.

Optimization of Continuous Berth Scheduling by Taking into Account Double-Line Ship Mooring

“Double-Line Ship Mooring” (DLSM) mode has been applied as an initiative operation mode for solving berth allocation problems (BAP) in certain giant container terminals in China. In this study, a continuous berth scheduling problem with the DLSM model is illustrated and solved with exact and heuristic methods with an objective to minimize the total operation cost, including both the additional transportation cost for vessels not located at their minimum-cost berthing position and the penalties for vessels not being able to leave as planned. First of all, this problem is formulated as a mixed-integer programming model and solved by the CPLEX solver for small-size instances. Afterwards, a particle swarm optimization (PSO) algorithm is developed to obtain good quality solutions within reasonable execution time for large-scale problems. Experimental results show that DLSM mode can not only greatly reduce the total operation cost but also significantly improve the efficiency of berth scheduling in comparison with the widely used single-line ship mooring (SLSM) mode. The comparison made between the results obtained by the proposed PSO algorithm and that obtained by the CPLEX solver for both small-size and large-scale instances are also quite encouraging. To sum up, this study can not only validate the effectiveness of DLSM mode for heavy-loaded ports but also provide a powerful decision support tool for the port operators to make good quality berth schedules with the DLSM mode.

Mathematical Model of Port Scheduling Problem Based on Multi-Objective Particle Swarm Optimization

Wang, N.N. and Liu, W., 2020. Mathematical model of port scheduling problem based on multi-objective particle swarm optimization. In: Bai, X. and Zhou, H. (eds.), Advances in Water Resources, Environmental Protection, and Sustainable Development. Journal of Coastal Research, Special Issue No. 115, pp. 561-565. Coconut Creek (Florida), ISSN 0749-0208.With the rapid development of international trade, it is particularly important for port enterprises to accelerate the construction and improvement of port collection and distribution, so as to promote the development of other modes of transportation. In this paper, the Particle Swarm Optimization (PSO) algorithm is used to solve the two-way flow of quayside vessel and Counter truck SCS problem. To solve this problem, A linear integer programming model is established, the lower bound is constructed, and the particle swarm optimization algorithm is solved. The performance of the proposed particle swarm optimization algorithm is tested by random experiments. The experimental results show that the average deviation between the proposed PSO and the optimal solution and the lower bound is 1.26% and 2.48%, respectively, it is shown that the proposed particle swarm algorithm can effectively solve bidirectional flows of ribbed and collecting card SCS problems.

Design of irrigation canals with minimum overall cost using particle swarm optimization – case study: El-Sheikh Gaber canal, north Sinai Peninsula, Egypt

Abstract Nowadays, the scarcity of freshwater sources, climate change and the deterioration of freshwater quality have a great impact on the lives of human beings. As such, improving the design of irrigation canals will reduce water losses through evaporation and seepage. In this paper, particle swarm optimization (PSO) is used to determine the optimum design of irrigation canals' cross-sections with the objective to minimize the overall costs. The overall costs include the costs of earthwork, lining, and water loss by both seepage and evaporation. The velocity constraints for sedimentation and erosion have been taken into consideration in the proposed design method. The proposed PSO is compared with both the Probabilistic Global Search Lausanne (PGSL) and classical optimization methods to verify its usefulness in optimal design of canals' cross-sections. The proposed PSO is then used to design El-Sheikh Gaber canal, north Sinai Peninsula, Egypt and the obtained dimensions are compared with the existing canal dimensions. To facilitate the use of the developed model, optimal design graphs are presented. The results show that the reduction of overall cost ranged from 28 to 41% and consequently, the proposed PSO algorithm can be reliably used for the design of irrigation open canals without going through the conventional and cumbersome trial and error methods.