Use Of Particle Swarm Optimization Research Articles

Investigate the Application of Particle Swarm Optimization to Fine-Tune the Architecture and Parameters of Deep Convolutional Neural Networks for Enhanced Accuracy in Brain Tumor Detection from Medical Images

This study researches the use of Particle Swarm Optimization (PSO) to adjust the design and boundaries of Deep Convolutional Neural Networks (DCNNs) for improved precision in cerebrum growth recognition from clinical pictures. Different PSO calculation variants are investigated for division and grouping of MR pictures. A clever PSO-based strategy for picture gathering is presented, alongside a half and half K-Means/SBM-PSO approach for MR picture division. The proposed methods are assessed utilizing MR pictures from assorted sources, uncovering the adequacy of PSO in both picture division and advancing the K-Means grouping strategy. A half breed PSO approach is exhibited for characterizing MR pictures as typical or strange in light of the presence of mind growths, and for evaluating MR pictures as per the WHO characterization framework for cerebrum cancers. The exploratory outcomes demonstrate that the proposed techniques lead to more modest intra-bunch distances and bigger between-bunch distances, bringing about superior division results. Eminently, the reconciliation of PSO with K-Means shows improved strength and execution contrasted with individual methodologies. The reviewing discoveries recommend impediments in the ongoing X-ray approach for growth evaluating. Overall, this study highlights the potential of PSO in optimizing DCNN architectures for accurate brain tumor detection from medical images, emphasizing the effectiveness of hybrid PSO-K-Means models for improved segmentation and classification outcomes.

Information gain ratio-based subfeature grouping empowers particle swarm optimization for feature selection

Feature selection is a critical preprocessing step in machine learning with significant real-world applications. Despite the widespread use of particle swarm optimization (PSO) for feature selection, owing to its robust global search capabilities, developing an effective PSO method for this task is still a substantial challenge. This study introduces a novel PSO variant, ISPSO, which integrates the information gain ratio for assessing feature importance. ISPSO’s feature selection process involves partitioning features into distinct groups to establish the initial population. Recognizing that feature selection tasks are inherently binary, ISPSO replaces the traditional PSO velocity concept with a probabilistic approach. In addition, introducing a penalty term enhances the algorithm’s ability to achieve superior results. Experimental evaluations on 16 datasets consistently show that ISPSO surpasses compared algorithms, highlighting its efficiency in eliminating redundant and irrelevant features.

Global Resource Scheduling for Distributed Edge Computing

Recently, there has been a surge in interest surrounding the field of distributed edge computing resource scheduling. Notably, applications like intelligent traffic systems and Internet of Things (IoT) intelligent monitoring necessitate the effective scheduling and migration of distributed resources. In addressing this challenge, distributed resource scheduling must weigh the costs associated with resource scheduling, aiming to identify an optimal strategy amid various feasible solutions. Different application scenarios introduce diverse optimization objectives, including considerations such as cost, transmission delay, and energy consumption. While current research predominantly focuses on the optimization problem of local resource scheduling, there is a recognized need for increased attention to global resource scheduling. This paper contributes to the field by defining a global resource scheduling problem for distributed edge computing, demonstrating its NP-Hard nature through proof. To tackle this complex problem, the paper proposes a heuristic solution strategy based on the ant colony algorithm (ACO), with optimization of ACO parameters achieved through the use of particle swarm optimization (PSO). To assess the effectiveness of the proposed algorithm, an experimental comparative analysis is conducted. The results showcase the algorithm’s notable accuracy and efficient iteration cost performance, highlighting its potential applicability and benefits in the realm of distributed edge computing resource scheduling.

Trajectory Optimization and Control Applied to Landing Maneuvers on Phobos from Mars-Phobos Distant Retrograde Orbits

This paper presents research on the application of trajectory design, optimization, and control to an orbital transfer from Mars–Phobos Distant Retrograde Orbits to the surface of Phobos. Given a Distant Retrograde Orbit and a landing location on the surface of Phobos, landing trajectories for which total Δv for a direct 2-burn maneuver is minimized are computed. This is accomplished through the use of Particle Swarm Optimization in which the required Δv and time of flight are optimization parameters. The non-uniform gravitational environment of Phobos is considered in the computation. Results show how direct transfers can be achieved with Δv on the order of ∼30 m/s.

Measuring chemical exchange saturation transfer exchange rates in the human brain using a particle swarm optimisation algorithm.

The z-spectrum contains many pools with different exchange rates and T2 values, which can make it difficult to interpret in vivo data and complicates the design of experiments aimed at providing sensitivity to one pool. This work aims to characterise the main pools observable with MRI at 7T in the human brain. To achieve this, we acquired z-spectra at multiple saturation powers in the human brain at 7T. We used simulations to optimise the use of particle swarm optimisation (PSO) to fit these data, validating this approach using further simulations and creatine phantoms. We then used the PSO to fit data from grey and white matter for the pool size, exchange rate, and T2 of five proton pools (magnetisation transfer, amides, amines, nuclear Overhauser enhancement NOE-3.5ppm and NOE-1.7ppm in addition to water). We then devised an approach for using PSO to fit z-spectra while limiting the computational burden, and we investigated the sensitivity of the fit to T2 and k for three overlapping pools. We used this to measure the exchange rate of creatine and to show that it varied with temperature, as expected. In the brain we measured a significantly larger pool size in white matter than in grey matter for the magnetisation transfer pool and the NOE-3.5ppm pool. For all other parameters we found no significant difference between grey and white matter. We showed that PSO can be used to fit z-spectra acquired at a range of B1 to provide information about peak position, amplitude, exchange rate, and T2 in vivo in the human brain. These data could provide more sensitivity to change in some clinical conditions and will also provide key information for further experimental design.

Classification of Blighted Ovum Factors in Pregnant Women Using PSO-Based Naïve Bayes

Classification of Blighted Ovum Factors or undeveloped fetuses is carried out considering that many cases occur in pregnant women. Blighted Ovum is 60% of the causes of miscarriage. In Indonesia, it is found in 37% of every 100 pregnancies. Classification uses Naïve Bayes based on Particle Swarm Optimization (PSO), which only requires small training data to determine the parameter estimates needed in the classification process, and the use of Particle Swarm Optimization can increase accuracy and solve optimization problems with the process of selecting variable data and attribute data to create a questionnaire as a data collection method. The results of the classification of blighted Ovum in pregnant women using the Naïve Bayes algorithm with the Rapid Miner framework obtained an accuracy value of 71.56% with an Area Under Curve (AUC) of 0.674 included in the excellent classification category. After using the PSO optimization, the accuracy value rose to 79.82% with an Area Under the Curve of 0.764, including a good classification category. Naïve Bayes is a suitable method for classification, and PSO can improve the accuracy and AUC values .

Global Optimization of Dinitrogen Clusters Bound to Monolayer and Bilayer Graphene: A Swarm Intelligence Approach

Locating the global minimum of a potential energy surface is an arduous task. The complexity of the potential energy surface increases as the number of degrees of freedom of the system increases. The highly rugged nature of the potential energy surface makes the minimization of the total energy of the molecular clusters a difficult optimization problem. A solution to this conundrum is the use of metaheuristic techniques that efficiently track down the global minima through a trade-off between exploration and exploitation. Herein, we use the swarm intelligence technique, particle swarm optimization to locate the global minima geometries of N2 clusters of size 2-10, in free and adsorbed states. We have investigated the structures and energetics of bare N2 clusters, followed by N2 clusters adsorbed on graphene and intercalated between the layers in bilayer graphene. The noncovalent interactions between dinitrogen molecules are modeled using the Buckingham potential as well as the electrostatic point charge model, while those of the N2 molecules with the carbon atoms of graphene are modeled using the improved Lennard-Jones potential. The interactions of the carbon atoms belonging to different layers in a bilayer are modeled using the Lennard-Jones potential. The bare cluster geometries and intermolecular interaction energies obtained using particle swarm optimization are found to be the same as reported in the literature, validating the use of particle swarm optimization for studying molecular clusters. The N2 molecules are found to adsorb as a monolayer on top of the graphene sheet and intercalate themselves right in the middle of the two sheets of bilayer graphene. Our study establishes that particle swarm optimization is a feasible global optimization technique for performing the optimization of high-dimensional molecular clusters, both in pristine and in confined forms.

Application of particle swarm optimization to understand the mechanism of action of allosteric inhibitors of the enzyme HSD17β13

Understanding a drug candidate's mechanism of action is crucial for its further development. However, kinetic schemes are often complex and multi-parametric, especially for proteins in oligomerization equilibria. Here, we demonstrate the use of particle swarm optimization (PSO) as a method to select between different sets of parameters that are too far apart in the parameter space to be found by conventional approaches. PSO is based upon the swarming of birds: each bird in the flock assesses multiple landing spots while atthe same time sharing that information with its neighbors. We applied this approach to the kinetics ofHSD17β13 enzyme inhibitors, which displayed unusually large thermal shifts. Thermal shift data for HSD17β13 indicated that the inhibitor shifted the oligomerization equilibrium toward the dimeric state. Validation of the PSO approach was provided by experimental mass photometry data. These results encourage further exploration of multi-parameter optimization algorithms as tools in drug discovery.

Design and Analysis of RSA and Paillier Homomorphic Cryptosystems Using PSO-Based Evolutionary Computation

Non-lattice based homomorphic encryption schemes usually involve huge modular exponentiation operations. Thus, improving the efficiency of modular exponentiation for large exponents is a real-world issue. Modular exponentiation can be computed by a series of modular multiplications. However, performing a series of modular multiplications is computationally expensive. This paper proposes hardware /software co-design for efficient modular exponentiation. This article first explores the use of particle swarm optimization (PSO) for the modular exponentiation in software, and present an efficient hardware co-design utilizing FPGA. Our findings reveal that the suggested PSO approach surpasses all other deterministic and non-deterministic approaches already in use. Further, we also demonstrate a comprehensive analysis for the optimal performance and parameter selection of our proposed PSO approach. Finally, we implement homomorphic encryption schemes, such as RSA and Paillier, using our PSO-based hardware /software co-design. Our approach gains resource savings for 1024-bit as follows: RSA encryption/decryption - 60.7% (area) and 65.3% (DSP); Paillier encryption - 46.3% (area) and 40% (DSP) and Paillier decryption - 73.7% (area) and 66.6% (DSP). We have obtained area-time improvements of 1024-bit as follows: RSA encryption/decryption - 2.7x; Paillier encryption - 2x and Paillier decryption - 4.6x using Xilinx Virtex-7 FPGAs.

Intelligent RGV Dynamic Scheduling Virtual Simulation Technology Based on Machine Learning

With the development of workshop automation, the complexity of RGV (Rail Guided Vehicle) dynamic scheduling schemes using virtual simulation technology is increasing. For the widely valued intelligent machining systems, machine learning based optimization algorithms can effectively respond to the increasingly complex RGV dynamic intelligent scheduling. In the whole model construction, how to complete the modular design of the intelligent processing system and optimize the solution is the key problem that needs to be solved urgently at present. This paper studied the use of particle swarm optimization to design the RGV dynamic scheduling model, aiming to improve the material processing production efficiency of RGV dynamic scheduling and reduce the system failure rate. Through problem modeling, solution and simulation experiment analysis, this paper applied particle swarm optimization based on machine learning, combined with RGV structure modular design and task parameter test set samples. According to the data results, the following conclusions can be drawn from the discussion. Under the background of intelligent logistics system, the RGV dynamic scheduling model using particle swarm optimization had higher material processing production efficiency than the traditional scheduling method in all job test samples, and the average increase was 13.25%. Meanwhile, in terms of system failures, optimization algorithms were better than traditional scheduling methods, with an average reduction of 4.6%. This shows that the RGV dynamic scheduling model based on particle swarm optimization has a better practical application effect.

Using particle swarm optimization and genetic algorithms for optimal control of non-linear fractional-order chaotic system of cancer cells

The purpose of this paper is to investigate optimal control the non-linear fractional-order chaotic system of cancer cells by use of particle swarm optimization and genetic algorithms. The chaotic behavior of cancer cell growth and the tumor growth model were expressed as a system of differential equations. Then, optimal control of cancer cells using drugs was presented. Particle swarm optimization method and genetic algorithms were used to solve the problem of optimal control of cancer cell growth. The results of the control applied to the model can control the cancer cell growth. The application of control results in decreasing the number of cancer cells to zero. When the controller is applied from the beginning, the Results of genetic algorithm method are excellent. All the results obtained for the particle swarm optimization method show that this method has also been very successful and have results very close to the genetic algorithm method.

EGD-SNet: A computational search engine for predicting an end-to-end machine learning pipeline for Energy Generation & Demand Forecasting

Load forecasting avoids energy wastage by accurately estimating the future quantity of energy generation and demand. Existing load forecasting approaches do not utilize the potential of feature selection and dimensionality reduction approaches that remove irrelevant/redundant features and improve the performance of machine learning (ML) regressors. This research presents an end-to-end framework named Energy Generation and Demand forecasting Search Net (EGD-SNet) capable of predicting energy generation, demand and temperature in multiple regions. EGD-SNet framework contains 13 different feature selection and 11 dimensionality reduction algorithms along with 10 most widely used ML regressors. It makes use of Particle Swarm Optimizer (PSO) to smartly train regressors by finding optimal hyperparameters. Further, it has potential to design an end to end pipeline by finding appropriate combination of regressor and feature selection or dimensionality reduction approaches for precisely predicting energy generation or demand for a particular regional data based on the characteristics of data. EGD-SNet as web service is accessible here. http://111.68.102.19:8000/

Particle Swarm Optimization and Modular Multilevel Converter Communication in Electrical Applications with Machine Learning Algorithm.

As a result of their natural capacity to recover harmonic current and reactive power from alternating current sources, power electronic devices utilized in conjunction with nonlinear loads have the potential to generate significant harmonic problems within the power system when employed in this way. When this occurs, voltage instability occurs, which must be avoided in order to maintain the consistency and dependability of the power system's power flow. With this approach, the series controller has been replaced by a multilevel modular controller in order to improve power handling capability and achieve higher modular levels with minimal distortions. The shunt compensator is the most effective way to achieve an extremely protected energy system as well as righteous steadiness in electric potential difference under a variety of load constraints. The DQ thesis is employed in this proposed converter to separate the harmonic components by establishing reference frame current, which is accomplished by machine learning techniques. As part of the constant mode operation, the PI controller contributes to maintaining the direct current-potential difference, which is given to the PWM generator. Optimization of the values of K p and K i is accomplished by the use of particle swarm optimization (PSO). The construction of this power system simulation model has been made feasible by the use of time-fluctuating characteristics modeling and the MATLAB programming environment. The new (unified power flow controller) UPFC research that has been made available is persuasive in its capacity to reduce distortions and watt-less power components while simultaneously enhancing efficiency and reducing costs.

Particle swarm optimization algorithm for dynamic synchronization of smart grid

ABSTRACT In recent decades, traditional energy generation and consumption have undergone a transformation to cleaner energy sources. The transition to a sustainable energy system based on efficiency and renewable energies will thus require the replacement of a complex and heavily implemented energy system with one based on concepts such as microgrids. A microgrid is a controlled small-scale power system and the elements that make up it are: distributed generation systems; energy storage systems; load management techniques; monitoring systems, etc. Consequently, since ac devices are used, synchronization criteria must be satisfied to switch operation between them. The synchronization criteria consist of making the values of the phase-angle difference, slip frequency, and voltage difference as small as possible. This is very important to ensure the correct operation of the grid. In the other hand, the use of Particle Swarm Optimization (PSO) algorithm has been increasing, because of their simplicity and efficiency in engineering optimization problems. Therefore, this paper proposes an active synchronizing control scheme that allows to synchronize a generator set to the grid and a particle swarm optimization algorithm, which makes the synchronizing control as efficient as possible. With the implemented control and with the help of the synchronization algorithm, improvements in the reduction of settling time (from 9 seconds to 3 seconds) are obtained in comparison to other controls in the literature.

RETRACTED ARTICLE: Optimal scheduling of integrated energy system based on improved grey wolf optimization algorithm

The optimal scheduling problem of integrated energy system (IES) has the characteristics of high-dimensional nonlinearity. Using the traditional Grey Wolf Optimizer (GWO) to solve the problem, it is easy to fall into a local optimum in the process of optimization, resulting in a low-quality scheduling scheme. Aiming at the dispatchability of electric and heat loads, this paper proposes an electric and heat comprehensive demand response model considering the participation of dispatchers. On the basis of incentive demand response, the group aggregation model of electrical load is constructed, and the electric load response model is constructed with the goal of minimizing the deviation between the dispatch signal and the load group aggregation characteristic model. Then, a heat load scheduling model is constructed according to the ambiguity of the human body's perception of temperature. On the basis of traditional GWO, the Fuzzy C-means (FCM) clustering algorithm is used to group wolves, which increases the diversity of the population, uses the Harris Hawk Optimizer (HHO) to design the prey to search for the best escape position, and reduces the local The optimal probability, and the use of Particle Swarm Optimizer (PSO) and Bat Optimizer (BO) to design the moving modes of different positions, increase the ability to find the global optimum, so as to obtain an Improved Gray Wolf Optimizer (IGWO), and then efficiently solve the model. IGWO can improve the defect of insufficient population diversity in the later stage of evolution, so that the population diversity can be better maintained during the entire evolution process. While taking into account the speed of optimization, it improves the algorithm's ability to jump out of the local optimum and realizes continuous deep search. Compared with the traditional intelligent Optimizer, IGWO has obvious improvement and achieved better results. At the same time, the comprehensive demand response that considers the dispatcher's desired signal improves the accommodation of new energy and reduces the operating cost of the system, and promotes the benign interaction between the source and the load.

Algoritma Backpropagation Menggunakan PSO Prediksi Penerimaan Retribusi Peminjaman Rumah Adat Dulohupa

Regional retribution as payment for services or granting certain permits specifically granted and/or issued by local governments for personal or business interests. Gorontalo City Government has several public facilities that are used as a source of regional income in the form of taxes or levies. The Dulohupa traditional house levy carried out by the Gorontalo City Youth and Sports Tourism Office often experiences ups and downs because it is caused by uncertainty about rentals or competition. The purpose of this research is to overcome the existing problems by predicting retribution receipts using the backpropagation method, the use of particle swarm optimization (PSO) to increase the accurate value in predicting. The data collected is daily quantitative univariate time series data. This type of data is the Dulohupa Traditional House Retribution Receipt Data. The dataset taken from the levy receipt variable has 211 records. The best model is generated on the backpropagation algorithm using the particle swarm optimization (PSO) selection feature, which can be seen from the smallest error rate of 0.122. Thus the addition of a selection feature can improve the performance of an algorithm. The results of the predictions for the next four months from January to April which have been denormalized with an average number of predictions of Rp. 1,806,789 with an error value of 0.112.

Keratoconus Classification with Convolutional Neural Networks Using Segmentation and Index Quantification of Eye Topography Images by Particle Swarm Optimisation.

In keratoconus, the cornea assumes a conical shape due to its thinning and protrusion. Early detection of keratoconus is vital in preventing vision loss or costly repairs. In corneal topography maps, curvature and steepness can be distinguished by the colour scales, with warm colours representing curved steep areas and cold colours representing flat areas. With the advent of machine learning algorithms like convolutional neural networks (CNN), the identification and classification of keratoconus from these topography maps have been made faster and more accurate. The classification and grading of keratoconus depend on the colour scales used. Artefacts and minimal variations in the corneal shape, in mild or developing keratoconus, are not represented clearly in the image gradients. Segmentation of the maps needs to be carried out for identifying the severity of the keratoconus as well as for identifying the changes in the severity. In this paper, we are considering the use of particle swarm optimisation and its modifications for segmenting the topography image. Pretrained CNN models are then trained with the dataset and tested. Results show that the performance of the system in terms of accuracy is 95.9% compared to 93%, 95.3%, and 84% available in the literature for a 3-class classification that involved mild keratoconus or forme fruste keratoconus.

Modeling of the operating characteristics of photovoltaic modules based on particle swarm optimization

AbstractThis work evaluates the use of particle swarm optimization to extract the parameters that represent a photovoltaic cell in the model of one diode and five parameters (1D5P) to obtain current versus voltage characteristic curves (I × V) of a photovoltaic module operating under a wide range of temperature and irradiation scenarios. In all the modeling and simulation processes, only information of the module's data sheet provided by the manufacturers was used, without depending on results from other simulations or external data collections. To validate the study, the simulation of the current versus voltage (I × V) curves of a commercial photovoltaic module was made, and this was compared with data provided by the manufacturer and also compared with Chenni's method, which is consolidated by the literature. Errors of less than 0.3% were obtained for the simulations performed under the standard test conditions and in temperature and irradiation situations commonly found in practice, as is the case, of G = 700 W/m2 and Tc = 40°C, the 1D5P method showed an average error of approximately 1%, slightly surpassing the Chenni's method where the error was approximately 1.4%.Statement of Industrial RelevanceIn developing countries, such as Brazil, a significant increase in the portion referring to solar energy in the Brazilian energy grid is noted. As in 2016, this portion was only 0.02%, though in 2020, according to the Brazilian Solar Energy Association (ABSOLAR),1 this portion had an increase of 75 times and reached the value of 1.5%. In addition, ABSOLAR's forecast for 2030 is that solar energy will reach 10% of the Brazilian energy grid. One of the reasons for this is that industrial consumer units are increasingly looking for alternative energy sources due to high energy inflation. Photovoltaic generators are an excellent option for industries because they are clean and sustainable energy.2 It is silent and brings a financial return for the investor. Although, even with all the benefits, the photovoltaic generator has a high acquisition cost, especially for consumer units that demand much energy, as is the case of industries. Thus, correct and precise dimensioning for the photovoltaic generator is necessary. One way to increase the accuracy of dimensioning is to use simulation of the photovoltaic modules, which is the objective of this article.Novelty or SignificanceThe developed method uses the particle swarm optimization with constriction factor to simulate I × V curves of a photovoltaic module for any temperature and irradiation values, using only the module's datasheet information. This study demonstrates that the proposed method presents more accurate results than consolidated methods in the literature, as is the case with the Chenni's method.3

Particle Swarm Optimization for Dynamic Risk-Aware Path Following for Autonomous Ships

This work presents the use of particle swarm optimization (PSO) for dynamic risk-aware path following, or waypoint re-planning during autonomous surface navigation in a maritime environment with polygonal grounding obstacles. Although recent research on control and local or global path planning for maritime autonomous surface ships (MASS) is considerable, few deal with the concept of risk during dynamic path following along a preplanned path. The proposed method introduces risk-based terms in the PSO fitness function for dynamic (online) adjustment or re-planning of intermediate waypoints during path following of a pre-planned route, where the control of the vessel in this work is left to a standard line-of-sight PID controller. Moreover, the results are compared to the performance of an analogous implementation of risk-aware model predictive control (MPC) using a gradient-based solver. The suggested method yields adequate performance similar to that of the MPC algorithm. Ultimately, the PSO approach may in future works allow for more complex and dynamic risk-aware behavior related to e.g. weather conditions implemented through lookup tables, or discrete machinery modes that are non-smooth.

Analysis of the Use of Particle Swarm Optimization on Naïve Bayes for Classification of Credit Bank Applications

The selection of prospective customers who apply for credit in the banking world is a very important thing to be considered by the marketing department in order to avoid non-performing loans. The website www.kaggle.com currently provides South German Credit data in the form of supervised learning data. The use of data mining techniques makes it possible to find hidden patterns contained in large data sets, one of which is using classification modeling. This study aims to compare the classification of South German Credit data using the Naïve Bayes algorithm and compare the classification of South German Credit data using the Naïve Bayes algorithm with particle swarm optimization (PSO). The test was carried out using a confusion matrix to determine the accuracy, precision and recall values of the research model. Based on the test, it is known that PSO is able to increase the accuracy and recall of Nave Bayes, but PSO has not been able to increase the precision value of Nave Bayes. The test results show that PSO optimization gives Naïve Bayes an increase in the value of accuracy by 0.46%, and gives Naïve Bayes an increase in recall value by 3.02%.