Search

Process, supply voltage, and temperature (PVT) are three important factors which contribute to performance variation of the complementary metal– oxide–semiconductor (CMOS) based analog circuits. In this paper, CMOS based analog circuit design with the PVT variation effects are explored. The effects of the PVT variation on the performance of CMOS based analog circuits are introduced. The optimization of CMOS based analog circuits such as differential amplifier (DA) and two-stage operational amplifier (op amp) circuits with PVT variations with different algorithms such as cockoo search (CS), particle swam optimization (PSO), hybrid CSPSO, and differential evaluation (DE) algorithms is presented. Each algorithm is implemented using the C programming language, interfaced with Ngspice circuit simulator, and tested on the Intel®core™ i5, 2.40 GHz processor with 8 GB internal RAM using the Ubuntu operating system (OS). The result shows PVT variation affects the performance of CMOS circuit.

These days, there are an increasing number of electronic devices that use batteries as their energy source, often known as portable electronic devices. However, the battery may run out of energy and a recharging process is required to keep the electronic device functional. A charger that is in accordance with the battery specifications is required to complete the charging process. Incompatible chargers can overcharge batteries and shorten their lifetime. Since there are many different types of electronic devices, many different chargers are required, especially since most chargers on the market are static and can only be used with one kind of electronic device. This will increase the costs that customers must pay, especially those who have many types of electronic devices. As a result, this research will create a smart charger using the PSO algorithm that can be used to complete the charging process on all types of portable electronic devices. To test smart chargers, five different battery types from electronic devices with different specifications are used. From the test result, the smart charger can charge five different types of battery loads with various specifications with 100% accuracy at a speed that takes 50.4 seconds to reach a steady state.

Wireless Sensor Networks (WSNs) have been widely deployed in hostile locations for environmental monitoring. Sensor placement and energy management are the two main factors that should be focused due to certain limitations in WSNs. The nodes in a sensor network might not stay charged when energy draining takes place; therefore, increasing the operational lifespan of the network is the primary purpose of energy management. Recently, major research interest in WSN has been focused with the essential aspect of localization. Several types of research have also taken place on the challenges of node localization of wireless sensor networks with the inclusion of range-free and range-based localization algorithms. In this work, the optimal positions of Sensor Nodes (SNs) are determined by proposing a novel Hybrid M-ACO – PSO (HMAP) algorithm. In the HMAP method, the improved PSO utilizes learning strategies for estimating the relay nodes' optimal positions. The M-ACO assures the data conveyance. A route discovers when it relates to the ideal route irrespective of the possibility of a system that includes the nodes with various transmission ranges, and the network lifetime improves. The proposed strategy is executed based on the energy, throughput, delivery ratio, overhead, and delay of the information packets.

Online media has an increasing presence on the restaurants' activities through social media websites, coinciding with an increase in customers' reviews of these restaurants. These reviews become the main source of information for both customers and decision-makers in this field. Any customer who is seeking such places will check their reviews first, which usually affect their final choice. In addition, customers' experiences can be enhanced by utilizing other customers' suggestions. Consequently, customers' reviews can influence the success of restaurant business since it is considered the final judgment of the overall quality of any restaurant. Thus, decision-makers need to analyze their customers' underlying sentiments in order to meet their expectations and improve the restaurants' services, in terms of food quality, ambiance, price range, and customer service. The number of reviews available for various products and services has dramatically increased these days and so has the need for automated methods to collect and analyze these reviews. Sentiment Analysis (SA) is a field of machine learning that helps analyze and predict the sentiments underlying these reviews. Usually, SA for customers' reviews face imbalanced datasets challenge, as the majority of these sentiments fall into supporters or resistors of the product or service. This work proposes a hybrid approach by combining the SupportVector Machine (SVM) algorithm with Particle Swarm Optimization (PSO) and different oversampling techniques to handle the imbalanced data problem. SVM is applied as a machine learning classi cation technique to predict the sentiments of reviews by optimizing the dataset, which contains different reviews of several restaurants in Jordan. Data were collected from Jeeran, a well-known social network for Arabic reviews. A PSO technique is used to optimize the weights of the features, as well as four different oversampling techniques, namely, the Synthetic Minority Oversampling Technique (SMOTE), SVM-SMOTE, Adaptive Synthetic Sampling (ADASYN) and borderline-SMOTE were examined to produce an optimized dataset and solve the imbalanced problem of the dataset. This study shows that the proposed PSO-SVM approach produces the best results compared to different classiffication techniques in terms of accuracy, F-measure, G-mean and Area Under the Curve (AUC), for different versions of the datasets.

Cloud computing provides hosted services (i.e., servers, storage, bandwidth, and software) over the internet. The key benefits of cloud computing are scalability, efficiency, and cost reduction. The key challenge in cloud computing is the even distribution of workload across numerous heterogeneous servers. Several Cloud scheduling and load-balancing techniques have been proposed in the literature. These techniques include heuristic-based, meta-heuristics-based, and hybrid algorithms. However, most of the current cloud scheduling and load balancing schemes are not content-aware (i.e., they are not considering the content-type of user tasks). The literature studies show that the content type of tasks can significantly improve the balanced distribution of workload. In this paper, a novel hybrid approach named Particle Swarm Optimization based Content-Aware Load Balancing Algorithm (PSO-CALBA) is proposed. PSO-CALBA scheduling scheme combines machine learning and meta-heuristic algorithm that performs classification utilizing file content type. The SVM classifier is used to classify users' tasks into different content types like video, audio, image, and text. Particle Swarm Optimization (PSO) based meta-heuristic algorithm is used to map user's tasks on Cloud. The proposed approach has been implemented and evaluated using a renowned Cloudsim simulation kit and compared with ACOFTF and DFTF. The proposed study shows significant improvement in terms of makespan, degree of imbalance (DI).

The dynamic experimental and numerical analysis of cracked beams has been studied with the aim of quantifying the influence of depth crack on the dynamic response of steel beams. Artificial Neural Method ANN has been used where a numerical simulation was improved in Matlab. A finite element model has also been developed by using the Ansys software, and the obtained results were compared with exact crack length. The study takes into account different hidden layer values in order to determine the sensitivity of the predicted crack depth. The results show that the response of the beam (frequencies) is strongly related to the crack depth which significantly affects the beam behavior, especially when the crack is very deep where the ANN allows us to identify the crack in lower computational time. Based on the provided results, we can detect that the effect of hidden layer size can affect the results.

A fuzzy control system has been widely used in various problem solving. Its performance can be optimized using particle swarm optimization (PSO). This performance can be proven by applying it to the maximum power point tracking (MPPT) control strategy on solar photovoltaic systems. Solar photovoltaic power generation systems are increasingly popular because they are clean and renewable energy sources. The power generated by solar photovoltaic is strongly influenced by solar irradiation and the load carried. In order to obtain maximum power output, an MPPT control strategy is needed. An MPPT control strategy based on fuzzy and PSO hybrid control systems is proposed in this research. The fuzzy-PSO method selects and produces the optimal duty cycle for the boost dc-dc converter in a solar photovoltaic system. Variable duty cycle due to solar irradiation and load changes can be conditioned by the fuzzy-PSO-based MPPT method to extract maximum power. The research results show that the fuzzy-PSO method can control the solar photovoltaic output voltage through a dc-dc converter to produce maximum power at various solar irradiations. Test result by applying a resistive load produces output power at the maximum point. The best result is obtained in the 100 Ohm load test: the response time of 0.0818 seconds and excellent robustness.

The main purpose of using the hybrid evolutionary algorithm is to reach optimal values and achieve goals that traditional methods cannot reach and because there are different evolutionary computations, each of them has different advantages and capabilities. Therefore, researchers integrate more than one algorithm into a hybrid form to increase the ability of these algorithms to perform evolutionary computation when working alone. In this paper, we propose a new algorithm for hybrid genetic algorithm (GA) and particle swarm optimization (PSO) with fuzzy logic control (FLC) approach for function optimization. Fuzzy logic is applied to switch dynamically between evolutionary algorithms, in an attempt to improve the algorithm performance. The HEF hybrid evolutionary algorithms are compared to GA, PSO, GAPSO, and PSOGA. The comparison uses a variety of measurement functions. In addition to strongly convex functions, these functions can be uniformly distributed or not, and are valuable for evaluating our approach. Iterations of 500, 1000, and 1500 were used for each function. The HEF algorithm’s efficiency was tested on four functions. The new algorithm is often the best solution, HEF accounted for 75 % of all the tests. This method is superior to conventional methods in terms of efficiency, Основной целью использования гибридного эволюционного алгоритма является достижение оптимальных значений и целей, которых не могут достичь традиционные методы, и поскольку существуют различные эволюционные вычисления, каждый из них имеет различные преимущества и возможности. Поэтому исследователи объединяют более одного алгоритма в гибридную форму для увеличения способности этих алгоритмов выполнять эволюционные вычисления. В данной работе предлагается новый алгоритм для гибридного генетического алгоритма (GA) и оптимизации роя частиц (PSO) с управлением на основе нечеткой логики (FLC) для оптимизации функций. Нечеткая логика применяется для динамического переключения между эволюционными алгоритмами для повышения производительности алгоритма. Проведено сравнение гибридных эволюционных алгоритмов HEF с GA, PSO, GAPSO и PSOGA. При сравнении используются различные функции измерения. Помимо сильно выпуклых функций, эти функции могут быть равномерно распределены или нет, и являются важными для оценки нашего подхода. Для каждой функции использовались 500, 1000 и 1500 итераций. Эффективность алгоритма HEF была проверена на четырех функциях. Новый алгоритм часто оказывается лучшим решением, на него приходится 75 % всех испытаний. Этот метод превосходит традиционные методы с точки зрения эффективности, Основною метою використання гібридного еволюційного алгоритму є досягнення оптимальних значень і цілей, яких не можуть досягти традиційні методи, і оскільки існують різні еволюційні обчислення, кожен з них має різні переваги і можливості. Тому дослідники об'єднують більше одного алгоритму в гібридну форму для збільшення здатності цих алгоритмів виконувати еволюційні обчислення. У даній роботі пропонується новий алгоритм для гібридного генетичного алгоритму (GA) і оптимізації рою частинок (PSO) з управлінням на основі нечіткої логіки (FLC) для оптимізації функцій. Нечітка логіка застосовується для динамічного перемикання між еволюційними алгоритмами для підвищення продуктивності алгоритму. Проведено порівняння гібридних еволюційних алгоритмів HEF з GA, PSO, GAPSO і PSOGA. При порівнянні використовуються різні функції вимірювання. Окрім сильно опуклих функцій, ці функції можуть бути рівномірно розподілені чи ні, і є важливими для оцінки нашого підходу. Для кожної функції використовувалися 500, 1000 і 1500 ітерацій. Ефективність алгоритму HEF була перевірена на чотирьох функціях. Новий алгоритм часто виявляється кращим рішенням, на нього припадає 75 % всіх випробувань. Цей метод перевершує традиційні методи з точки зору ефективності

The Pandemic Covid-19 in Indonesia in 2020 had an impact on Termination of Employment (PHK), this has received various public opinions on social media. At a time when the poverty rate is high and unemployment increases every year, it becomes a factor of public disapproval of Termination of Employment (PHK). It is necessary to classify public opinion into a negative opinion or a positive opinion on this issue. The purpose of this study is to analyze the sentiment towards layoffs to determine negative or positive opinions using the Naïve Bayes algorithm by adding feature selection. The research stages consist of data collection, text preprocessing, feature selection, and application of algorithms. The testing process in this study uses the Rapid Miner application. The test results in this study using the Naive Bayes Algorithm, the accuracy value is 93.57% and for addition to the Naïve Bayes + PSO feature selection, the accuracy value is 93.71%. The best accuracy value in sentiment analysis of layoffs in the covid-19 pandemic is the addition of the PSO feature selection in the Naïve Bayes Algorithm, which is 0.14% better.

Particle Swarm Optimization of 3D Printing Parameters on Open-Source Commercial 3D Printer

Present paper covers performance modelling and performability evaluation of a veneer-cutting system of plywood manufacturing industry. The performability is evaluated as a function of availability. In this system the different subsystems are connected in hybrid mode. Markovian Approach was used for developing the process modeling of the subsystems and to evaluate the performability of said system. MATLAB software was used to perform the numerical computations as well as simulation of results. The current work examines the impact of varied failure rates and repair rates on the long-term availability of the system. A Particle Swarm Optimization (PSO) based technique was used to optimize the results. A Decision Support System (DSS), which can be helpful for making strategic decisions on financial investments in managing the maintenance priorities, spare part management, and human resource requirements, among other things, has been recommended based on the numerical investigation..

The paper aims are to determine the bi-objective reliability-cost problem of a series-parallel system by employing an interactive approach. Multi-objective optimization is a design methodology that optimizes a combination of objective functions orderly and concurrently. The fuzzy membership functions have been designated to settle the contrary nature of the objectives. Based on these functions and the moment of the objectives in the form of the weight vector, a crisp optimization design is formed. Lastly, the inherited problem is determined with the aid of the PSO (Particle Swarm Optimization) algorithm and confronted with the genetic algorithm. The solution resembling the various choices of the decision-makers towards the evaluation of their decision are listed. A decision-maker can pick an immeasurable one according to his requirement to reach at the aspired goal.

This study examines the understanding of Outcome-Based Education among Indian university’s higher education institutions’ faculty members. The outcome-based curriculum is one of the most significant advances in recent years of Indian Education worldwide. For some time, the result-based curricula are changing or are in the proposal stage of preparation. The outcomes, process of change, and implementation of the result-based approach are outlined. The traditional education system is losing its importance in the age of globalization. It becomes essential to work with rapidly developing technologies that expect supplementary skills and efforts. The institute aims to produce students with the ability to cope with recent trends and technologies. It becomes mandatory to adapt and become familiar with conventional Education to Outcome-Based Education (OBE) to fulfil its needs. &nbsp

In this work, the indicators of electrical power network stability and voltage stability (VS) are discussed and developed with the aim of using a power transfer stability index (PTSI) indicator as a predictor for voltage stability (VS) in electrical power networks. The power transfer stability index (PTSI) was thus used to detect abnormally weak voltages in buses within such power system networks (weak). The target data are obtained using the Newton Raphson method (NR) and include magnitude, phase angle, and active and reactive power. A new adaptive particle swarm optimization-neural network algorithm based on a guiding strategy (GSAPSO-NN) was also used to achieve the goal of the paper by improving the mixed particle updates and the weightings of the neural network to decrease the search time. All results were then compared with actual values as calculated using the PTSI NR method. The final results show only simple differences or approximately the same values using both the proposed and the classical methods. The MATLAB-PSAT package was employed to obtain most of these results and the testing of the new method was done on the IEEE14 bus system as well as the Iraqi 24-bus power system. The effectiveness validation of the new hybrid method for assessing voltage stability was thus achieved.

IntroductionViral infections have been implicated in the initiation of the autoimmune diseases. Recent reports suggest that a proportion of patients with COVID-19 develop severe disease with multiple organ injuries. We evaluated the relationship between COVID-19 severity, prevalence and persistence of antinuclear and other systemic and organ specific autoantibodies as well as SARS-CoV-2 infection specific anti-nucleocapsid (N) IgG antibodies and protective neutralizing antibody (Nab) levels.MethodsSamples from 119 COVID-19 patients categorized based on their level of care and 284 healthy subjects were tested for the presence and persistence of antinuclear and other systemic and organ specific autoantibodies as well as SARS-CoV-2 and neutralizing antibody levels.ResultsThe data shows significantly increased levels of anti RNP-A, anti-nucleocapsid and neutralizing antibody among patients receiving ICU care compared to non-ICU care. Furthermore, subjects receiving ICU care demonstrated significantly higher nucleocapsid IgG levels among the RNP-A positive cohort compared to RNP-A negative cohort. Notably, the expression of anti RNP-A antibodies is transient that reverts to non-reactive status between 20 and 60 days post symptom onset.ConclusionsCOVID-19 patients in ICU care exhibit significantly higher levels of transient RNP-A autoantibodies, anti-nucleocapsid, and SARS-CoV-2 neutralizing antibodies compared to patients in non-ICU care.

In this research, a modification of the particle swarm optimization method was proposed, which is based on an intervention technique for the design of antennas. The proposed method was tested through its application on typical benchmark functions. Moreover, it was applied to the optimal design of a narrow band antenna and two ultra-wideband antennas through shape and hybrid optimization. The objective function was based on minimizing the S 11 magnitude in the desired frequency range to improve impedance matching. The modified method had a better performance than the original particle swarm optimization in the typical benchmark functions, and the best results were obtained for the antenna optimization process. Therefore, this method is a good alternative to be applied in these processes because it allows obtaining a better quality of solution and reducing the number of evaluations of the objective function. Resumen En esta investigación se propone un método modificado de optimización de enjambre de partículas, basado en una técnica de intervención para el diseño de antenas. El método propuesto se probó mediante su aplicación a funciones de prueba típicas. Asimismo, se aplicó en el diseño óptimo de una antena de banda angosta y dos antenas de banda ultra ancha mediante optimización de forma e híbrida. La función objetivo se basó en minimizar la magnitud de S 11 en el rango de frecuencias deseado para mejorar el acoplamiento de impedancia. El método modificado presentó un buen desempeño en las funciones de prueba típicas y se obtuvieron los mejores resultados en el proceso de optimización de las antenas. De esta manera, el método propuesto es una buena alternativa para ser aplicado en estos procesos, ya que permitió obtener una mejor calidad de solución y reducir el número de evaluaciones de la función objetivo.

River water quality assessment, affected by pollution load, and river regime changes in various climate conditions, is an implementation that simplifies water resources management, and justifies terms for increases or decreases in human activities. The current paper aims to offer a water quality model of a river considering parametric, hydrologic, and pollution load uncertainty by using uncertainty indexes like Plevel, ARIL, and NUE. These indexes were used to analyze the influences of the model's parameters and the river's regime alternations on the results. A Qual2K model, calibrated with PSO algorithm, is presented and connected to GLUE algorithm to assess the model's uncertainties like effective input parameters on the modeled variations, headwater flow, and input pollutions. Zarjoob River, in the north of Iran, was chosen as the case study. The results illustrate that the interaction among parameters, hydrologic and pollutant discharge data should be considered in river water quality simulation. The presented methodology can analyze the influences of parametric uncertainty, parametric and hydrologic uncertainty, and pollution input load uncertainty according to any quantity of observations and the modeled results of any river. HIGHLIGHTS Using PSO algorithm in order to calibrate a Qual-2K model.; Assessment of parametric and hydrologic uncertainty in the meantime.; Using scenarios for input load uncertainty assessment.; Assessment of parametric uncertainty-hydrological uncertainty-point sources load uncertainty.; Presenting a framework applicable in uncertainty evaluation of any river water quality model.

An immense body of research has focused on path-planning and following of wheeled robots in unstructured surfaces. Nonholonomic robots traveling over deformable terrains together with complex operating conditions, however, pose further challenges in terms of a higher demand for robustness and optimality. In this paper, a Chaos-enhanced Accelerated Particle Swarm Optimization (CAPSO) algorithm is employed for planning an optimal path of a wheeled robot, so as to ensure shortest path from the starting point to the target location together with safety through guaranteed avoidance of collisions with static and dynamic obstacles. The fundamental terramechanics concepts are employed to derive essential forces and moments acting on the wheeled robot. Subsequently, a kineto-dynamic model of the robot is developed for designing a novel robust control algorithm based on an exponential-integral-sliding mode (EISMC) scheme and a RBF-NN approximator. The results revealed that the proposed algorithm is responsive and robust to withstand adverse effects of structured and unstructured uncertainties by using the designed adaptation law according to the Lyapunov stability theorem. The effectiveness of the proposed algorithm is also validated against several reported frameworks.

Rice is the most important staple food in Indonesia. There are various types of varieties available, one of them is Inpari Mekongga variety. In Karawang, Mekongga rice type is the most popular and superior compared to others. However, this type of rice is often mixed with the other types because there are too many varieties and various other problems. Classifying varieties of rice types can be done to identify the types of rice. The classification of rice varieties in this research is divided into 2 classes, Mekongga and not Mekongga. The method that used in this reserach is Support Vector Machine (SVM) and Particle Swarm Optimatizon (PSO). SVM method was chosen because it basically handles the classification of two classes. Meanwhile, PSO method used to optimize the accuracy level of the SVM method. Combination from the two methods is very well used in classification data because it can increase the level of accuracy better. The purpose of this reserach is compare the accuracy of the 2 methods that used. The results from research is mekongga rice classification with Support Vector Machine has accuracy value 46.67% and AUC value 0.475. Meanwhile, using Support Vector Machine based on Particle Swarm Optimization (PSO) can help improve the classification of this mekongga rice with accuracy value 70.83% and AUC value 0.671., Beras merupakan bahan makanan pokok paling penting di Indonesia. Terdapat berbagai macam jenis varietas yang ada, salah satunya ialah varietas Mekongga. Di karawang jenis beras Mekongga paling banyak diminati dan unggul dibandingkan dengan yang lainnya. Namun, jenis beras tersebut sering sekali tercampur dengan jenis beras lainnya dikarenakan terlalu banyak varietas yang ada dan berbagai macam permasalahan lain. Mengklasifikasikan varietas jenis beras dapat dilakukan guna mengidentifikasi jenis dari beras tersebut. Klasifikasi varietas jenis beras pada penelitian ini terbagi menjadi 2 kelas yaitu Mekongga dan Bukan Mekongga. Metode yang digunakan pada penelitian ini ialah Support Vector Machine dan Particle Swarm Optimatizon. Metode Support Vector Machine dipilih karna metode ini pada dasarnya menangani klasifikasi dua kelas. Sedangkan metode Particle Swarm Optimatizon digunakan untuk mengoptimasikan tingkat akurasi dari metode Support Vector Machine. Kombinasi dua metode tersebut sangat baik digunakan dalam data klasifikasi karna dapat meningkatkan tingkat akurasi menjadi lebih baik. Tujuan penelitian ini ialah membandingkan tingkat akurasi dari 2 metode yang digunakan. Hasil dari penelitian klasifikasi beras mekongga dengan Support Vector Machine menghasilkan nilai akurasi sebesar 46.67% dengan AUC 0.475. Sedangkan menggunakan Support Vector Machine berbasis Particle Swarm Optimatizon dapat membantu dalam meningkatkan klasifikasi beras mekongga ini dengan hasil akurasi 70.83% dan AUC 0.671.

This paper provides an application of the hybrid Grey Wolf Optimization and Particle Swarm Optimization (GWO-PSO) method to reach a solution to the optimal reactive power dispatch (ORPD) problem in the scope of electric power networks. PSO is a swarm based meta-heuristic optimization algorithm whose target is to seek the best solution to a problem by moving particles in a specific exploration field. On the other hand, GWO is a meta-heuristic optimization technique which is inspired by grey wolves. In this article, GWO is hybridized with a PSO method to improve the progress of the GWO. There are two objectives minimized in this research study to improve the electric power network performance. They are: 1) power losses in the transmission systems, and 2) the deviation of voltages at the load buses. The problem of ORPD has many restrictions on the networks which must be considered during the solution. The hybrid GWO-PSO is proven as an effective optimization technique when seeking the global best solution to an optimization problem. The success of the introduced hybrid technique is verified utilizing more than one standard IEEE test system. A valuation to the introduced technique is performed by comparing it with other optimization techniques stated through the literature. The simulation results confirm that the usage of the hybrid GWO-PSO techniques causes an observable improvement in a wide scale of the electric power networks behavior.

Renewable energy is becoming more popular due to environmental concerns about the previous energy source. Accurate solar photovoltaic system model parameters substantially impact the efficiency of solar energy conversion to electricity. In this matter, swarm and evolutionary optimization algorithms have been widely utilized in dealing with practical problems due to their more straightforward concepts, efficacy, flexibility, and easy-to-implement procedural frameworks. However, the nonlinearity and complexity of the photovoltaic parameter identification caused swarm and evolutionary optimizers to exhibit Immaturity in the obtained solutions. To deal with such concerns on immature convergence and imbalanced searching trends, in this paper, we proposed the PSOCS algorithm based on the core components of particle swarm optimization (PSO) and the strategy of random reselection of parasitic nests that appeared in the cuckoo search. The parameters of the single-diode model and the double-diode model are identified based on several experiments. Based on the comprehensive comparisons, results indicate that the developed PSOCS algorithm has higher convergence accuracy and better stability than the original PSO, the original cuckoo search, and other studied algorithms. The findings indicate that we suggest the PSOCS algorithm as an enhanced and efficient approach for dealing with parameter extraction of solar photovoltaic modules. We think this simple variant of PSO can be employed as a tool for the optimal designing of photovoltaic systems.

Data gathering is an active research topic for wireless sensor networks WSNs with internet of things IoTs. Optimal data gathering enables collecting sensor data efficiently with minimum cost and energy consumption for the limited resources nodes. Enabling mobile sinks for data gathering helps at reducing the cost further and enhancing the energy preservation. This article presents a novel optimization for data gathering in WSNs using multiple mobile sinks by extending multi-objective variable length particle swarm optimization to include tabu search. The developed algorithm is designated as variable length particle swarm optimization with tabu search (SCPSO-TS). It provides the best number of mobile sinks along with their corresponding trajectories that are defined using rendezvous points (RPs). The evaluation has shown a superiority of SCPSO-TS over the benchmarks in terms of domination percentage that is measured by set coverage.

Actually, path planning is one of the most crucial aspects of mobile robots study. The primary goal of this research is to develop a solution to the path planning issues that occur when a “mobile robot” operates in a static environment. The problem is handled by finding a collision-free path that meets the given criteria for the shortest distance with quite the smoothness of the path. Two nature-inspired metaheuristic algorithms are used in the computation. By leading a hybrid “gray wolf optimization” with the “particle swarm optimization” (HGWO-PSO) computation that restricts the distance and follows path perfection guidelines, the primary shape is improved. In addition, simulation findings reveal that the proposed HGWOPSO method is deeply serious in terms of path optimality when compared to path planning approaches such as group search optimizer GSO, PSO, artificial bee colony ABC, and GWO.

Fossil fuels are being replaced by renewables. Most of the renewables are intermittent, to have reliable power the renewables have to be conditioned before injecting into the utility grid. The DC-DC converters are perfect power electronic devices for conditioning the renewables. The single ended primary inductor converter (SEPIC) performs the conditioning with a very high voltage transfer gain and minimum ripples. The maximum power extraction from the PV panels is required for providing good quality DC power. Intelligent controllers can make use of optimization techniques. The particle swarm optimization (PSO) technique can optimize the controller to extract the maximum power. The SEPIC converter duty variation is optimized and a comparative analysis with the Buck-Boost converter is done in a MATLAB/Simulink environment. The proposed SEPIC converter system performed well by improving the power tracking by 40% and the system has been analysed in a battery charging environment.

A modified firefly algorithm (FA) was presented in this paper for finding a solution to the economic dispatch (ED) problem. ED is considered a difficult topic in the field of power systems due to the complexity of calculating the optimal generation schedule that will satisfy the demand for electric power at the lowest fuel costs while satisfying all the other constraints. Furthermore, the ED problems are associated with objective functions that have both quality and inequality constraints; these include the practical operation constraints of the generators (such as the forbidden working areas, nonlinear limits, and generation limits) that makes the calculation of the global optimal solutions of ED a difficult task. The proposed approach in this study was evaluated in the IEEE 30-Bus test-bed; the evaluation showed that the proposed FA-based approach performed optimally in comparison with the performance of the other existing optimizers, such as the traditional FA and particle swarm optimization. The results show the high performance of the modified firefly algorithm compared to the other methods.

Peng-Chao Zhang, Qiang Deng, Wei-Bin Sheng, Hai-Long Guo, Mardan Mamat, Yun-Xiao Luo, Shu-Tao Gao Department of Spine Surgery, The First Affiliated Hospital of Xinjiang Medical University, Urumqi, 830054, People’s Republic of ChinaCorrespondence: Qiang DengDepartment of Spine Surgery, The First Affiliated Hospital of Xinjiang Medical University, No. 137 of Liyushan South Road, Xinshi District, Urumqi, 830054, People’s Republic of ChinaTel +86 13325636562Email dengqiang_abc@163.comObjective: This study aimed to compare the changes in sagittal parameters and the efficacy of pedicle subtraction osteotomy (PSO) in patients with ankylosing spondylitis (AS) and kyphosis under different lumbar sagittal morphologies and to explore the effect of sagittal morphology on the selection of PSO levels.Methods: A total of 24 patients with AS and thoracolumbar kyphosis (TK) who were admitted to the First Affiliated Hospital of Xinjiang Medical University between 2008 and 2019 were enrolled in this study. They were divided into two groups: a lumbar lordosis group (n = 14) and a lumbar kyphosis group (n = 10). Changes in sagittal parameters, lumbar Japanese Orthopaedic Association (JOA) scores, and visual analog scale (VAS) scores for lumbar pain before and after operation were compared between the two groups to evaluate postoperative efficacy.Results: The preoperative lumbar lordosis (LL) was − 29.29 ± 5.40 (lordosis) and 13.50 ± 3.65 (kyphosis) (P < 0.01), and the preoperative sagittal vertical axis (SVA) was 171.35 ± 25.46 (lordosis) and 223.58 ± 21.87 (kyphosis) (P < 0.01). Preoperative global kyphosis (GK) was 75.71 ± 5.26 (lordosis) and 86.30 ± 10.32 (kyphosis) (P < 0.05). All patients in the lordosis group underwent PSO surgery at the twelfth thoracic vertebra (T12) or the first lumbar spinal vertebra (L1), while all patients in the kyphosis group underwent the surgery at the second or third lumbar spinal vertebra (L2 or L3). The differences in postoperative GK, LL, and SVA between the two groups were not significant (P > 0.05). The JOA scores of the two groups increased from 13.00 ± 0.83 (lordosis) and 11.30 ± 0.93 (kyphosis) before surgery to 21.00 ± 0.67 and 19.70 ± 0.60 after surgery (P < 0.05).Conclusion: Preoperative lumbar sagittal morphology needs to be considered when selecting the optimal osteotomy plane. An osteotomy can achieve the greatest success in patients with lumbar kyphosis at L2/L3; for patients with lumbar lordosis, it can achieve satisfactory outcomes at T12/L1.Keywords: ankylosing spondylitis, kyphosis, sagittal parameters, PSO, osteotomy

The operating condition of bus transit system has not been efficient in most cities of Iran, and many management methods such as regular bus scheduling, assigning exclusive bus lanes, etc., which are necessary for increasing the efficiency of this system, were not regarded enough. Thus, achieving a method for locating the bus stops and optimizing the number of such stops based on a non-homogeneous spatial and temporal distribution of passengers as well as the local traffic patterns are important to be investigated. As such, the present study aims to investigate the modeling of a bus transit system corridor according to the non-homogeneous spatial and temporal distribution of passengers throughout the route aiming at optimization of the number of attracted passengers to the bus. For this purpose, the 8-km route from Vali-e-asr roundabout to Gas roundabout in the city of Rasht in the north of Iran is selected for modeling. Hammersley sampling method, as well as two heuristic optimization techniques, including a Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) algorithm, are used for generating a non-uniform population and solving the optimization model. Therefore, the results of this analysis are compared to the optimization results by using the probabilistic analysis without considering the reference uncertainty. Finally, the PSO is selected as the superior algorithm for modeling and locating the bus stops due to its results in less travel time, and the validity of robust optimization model is shown due to its higher accuracy and adaptation to the real-world environment. Overall, although the optimization results based on indeterminate analysis in comparison to determinate analysis brought about more average travel time, more population sets were covered by the new introduced stops during 18 active hours of the bus transit system.

In the implementation of learning, several factors affect the student learning process, including internal factors, external factors, and learning approach factors. For example, the physical and spiritual condition of students. Physiological aspects (body, eyes and ears and talents of students, student interests). External factors, for example, environmental conditions around students, family, teachers, community, friends) Thus, learning achievement is significant because educational institutions' success can be seen from how many students learning achievement. This research's first focus is to do student clustering based on their learning process using 11 parameters. Second, using the PSO algorithm to get maximum clustering results. The research data were obtained from vocational secondary education institutions in the city of Pasuruan. The data is obtained from the results of school reports and questionnaires as much as 100 student data. Data attributes include environmental features, social features, and related school features to group student data for learning data processing. From the classification results using the PSO method, the silhouette value is 0.97140754, very close. These results indicate that the PSO method can improve the K-Means clustering method's performance in the classification process of student learning interest., In the implementation of learning, there are several factors that affect the student learning process, including internal factors, external factors, and learning approach factors. Internal factors (factors within students), for example: the physical and spiritual condition of the student. Namely: physiological aspects (body, eyes and ears) and psychological aspects (student intelligence, student attitudes, student talents, student interests and student motivation). External factors (factors from outside students), for example: environmental conditions around students. Namely: social environment (family, teachers, community, friends) and non-social environment (home, school, equipment, nature). While the student learning approach factors, for example: The learning approach factor, namely the type of student effort which includes the strategies and methods used by students to carry out learning activities of subject matter, which consists of a high approach, medium approach and low approach. So the first focus of this research is to do student clustering based on their learning process using 11 parameters. Second, using the PSO algorithm to get maximum clustering results. The research data were obtained from vocational secondary education institutions in the city of Pasuruan. Where the data is data obtained from the results of school reports and questionnaires as much as 350 student data. Data attributes include environmental features, social features, and related school features to group student data for learning data processing. From the classification results using the PSO method, there are 0.97140754 silhouette values that are obtained because the distance between the data is very close. From these results indicate that the PSO method is able to improve the performance of the k-means clustering method in the classification process of student learning interest.

An improved particle swarm optimization (PSO) with adaptive weighted delay velocity (PSO-AWDV) is proposed in this paper. A new scheme blending weighted delay velocity is firstly presented for a new PSO with weighted delay velocity (PSO-WDV) algorithm. Then, to adaptively update the velocity inertia weight, an adaptive PSO-AWDV algorithm is developed based on the evolutionary state of the particle swarm evaluated via a new estimation method. The newly proposed adaptive PSO-AWDV algorithm is tested based on some famous benchmark functions, which can confirm that the performance of PSO-AWDV is superior to several well-known PSO variants and intelligent optimization algorithms in literature.

A novel enhanced quantum particle swarm optimization algorithm for IIoT deployments is proposed. It provides enhanced connectivity, reduced energy consumption, and optimized delay. We consider heterogeneous scenarios of network topologies for optimal path configuration by exploring and exploiting the hunts. It uses multiple inputs from heterogeneous IIoT into quantum and bio-inspired optimization techniques. The differential evolution operator and crossover operations are used for information interchange among the nodes to avoid trapping into local minima. The different topology scenarios are simulated to study the impact of $p$ -degrees of connectivity concerning objective functions’ evaluation and compared with existing techniques. The results demonstrate that our algorithm consumes a minimum of 30.3% lesser energy. Furthermore, it offers improved searching precision and convergence swiftness in the possible search space for $p$ -disjoint paths and reduces the delay by a minimum of 26.7%. Our algorithm also improves the throughput by a minimum of 29.87% since the quantum swarm inclines to generate additional diverse paths from multiple source nodes to the gateway.

This work presents a methodology for the joint calibration and synchronization of two arrays of microphones and loudspeakers. The problem is modeled as estimation of the rigid motion of one array with respect to the other, as well as estimation of the synchronization mismatch between the two. The proposed method uses dedicated signals emitted by the loudspeakers of the two arrays to compute a set of time of arrival (TOA) estimates. Through a simple transformation, estimated TOAs are converted into a set of linearly independent time difference of arrival (TDOA) measurements, which are modeled by a system of nonlinear equations in the unknown parameters of interest. A maximum likelihood estimate is then given as the solution to a nonlinear weighted least squares (NWLS) problem, which is optimized applying a parallelizable variant of Particle Swarm Optimization (PSO). In this paper, we also derive the Cramér-Rao lower bound (CRLB), and benchmark it against the proposed method in a series of Monte Carlo (MC) simulations. Results show that the proposed method attains high-performance comparable to the CRLB.

A global epidemic disease known as the novel coronavirus (2019-nCov) had seriously hit the most area around the whole world causing unpredictable loss of manpower and finance during the past year. Modeling the spread and development of infectious diseases represented by new Coronavirus has become an important part of public health work in the world. Estimation of possible infection population and prospective suggestion of handling spread based on existing data is crucial. In this article, we build a more applicable model called SEIJR with a log-normal distributed time delay to forecast the trend of spreading considering the biology parameters obtained based on Chinese clinical data in Wuhan and the real spread feature of 2019-nCov in Italy. Adopting Particle Swarm Optimization (PSO), we estimate the early period average spreading velocity ( $\boldsymbol {\alpha _{0}}$ ) and implement inversion analysis of time point ( $\boldsymbol {T_{0}}$ ) when the virus first hit Italy. Based on fixed $\boldsymbol {\alpha _{0}}$ and $\boldsymbol {T_{0}}$ , we then obtained the average spreading velocity $\boldsymbol {\alpha _{1}}$ after the area lockdown using PSO. The result shows that it will help address the infection by generating the prediction trends of different $\boldsymbol {\alpha }$ which we considered. Finally, our research applies Logistic regression, Neural Network embedding LSTM layer, which is two representative machine learning algorithms, to directly predict future infection trends and compare the forecast with results yielded by mathematical model adopting differential equations. Not only solved the complex, nondifferentiable equation of the epidemic model, this research also performs well in inversion analysis based on PSO which conveys informative outcomes for further discussion on precautious action. The comparison with the machine learning algorithms shows that the 2019-nCov based epidemic dynamics assumption is reasonable and helpful to the mathematical model, which is better than the data-driven machine learning algorithms. Code can be freely downloaded from https://github.com/Summerwork/2019-nCov-Prediction.

Microgrid as the main building block for future smart grids is prone to instability originated from converter-based distributed generations (DG). Herein, we first analyze the small-signal stability of an inverter-interfaced microgrid. Afterwards, a novel adaptive network fuzzy inference system (ANFIS)-based optimization method is introduced which aims at online tuning of virtual inductances (VI) in the islanded microgrids. The data for ANFIS training is drawn by particle swarm optimization (PSO) algorithm and the proposed objective function. A total of 140 load scenarios are considered to provide optimal VI in each load condition and generate optimal data for ANFIS training. This process minimizes reactive power mismatches and improves microgrid stability in different load levels. The simultaneous application of PSO algorithm and ANFIS training facilitates the objectives pursued by current study. Finally, the trained ANFIS networks are installed in the converter control. The adaptive performance of ANFIS controllers makes the converters responses independent from load change location and value. The effectiveness of the proposed control methodology is verified using simulations studies.

En este trabajo se presenta un desarrollo para mejorar el desempeño del algoritmo de optimización metaheurístico nombrado Particle Swarm Optimization (PSO). El algoritmo PSO está inspirado en el comportamiento que demuestran los grupos de individuos en la naturaleza, como ejemplo podemos mencionar las parvadas y los cardúmenes. Cada individuo o partícula, de forma análoga en un proceso matemático; es considerado como una posible solución y en ellos se contempla, como información relevante, su posición y la velocidad. La velocidad de cada partícula es modificada al multiplicarse por un parámetro nombrado factor de inercia y es este parámetro que proponemos modificar para mejorar el desempeño del algoritmo. La modificación del factor de inercia se desarrolla de dos maneras, decremento lineal y decremento caótico. Se han considerado las funciones de referencia Eggholder y Six-Hump Camelback, para determinar la mejora en el desempeño del algoritmo PSO. Los resultados presentados en este trabajo indican un mejor desempeño al aplicar el decremento de tipo caótico al factor de inercia.

Conventionally, the parameters of a fuzzy logic controller (FLC) are obtained by a trial and error method or by human experience. In this paper, the problem of designing a FLC for maximum power point tracking (MPPT) of a photovoltaic system (PV) that consists of a PV generator, a DC-DC boost converter and a lead-acid battery is studied. The normalization gains, the membership functions and the fuzzy rules are automatically adjusted using a particles swarm optimization algorithm (PSO) in order to maximize the criterion based on the integration of the PV module power under standard temperature condition (STC) (T=25?C and S=1000 W/m2). The robustness test of the optimized fuzzy logic MPPT controller (FLC-MPPT) is carried out under different scenarios. Simulation results of the system clearly show that the proposed optimized FLCMPPT controller outperforms in terms of maximum efficiency the FLC-MPPT controller not optimized, the FLC-MPPT controller with optimized normalization gains and the FLC-MPPT controller with optimized normalization gains and membership functions.

Background and objective: Clustering is a widely used popular method for data analysis within many clustering algorithms for years. Today it is used in many predictions, collaborative filtering and automatic segmentation systems on different domains. Also, to be broadly used in practice, such clustering algorithms need to give both better performance and robustness when compared to the ones currently used. In recent years, evolutionary algorithms are used in many domains since they are robust and easy to implement. And many clustering problems can be easily solved with such algorithms if the problem is modeled as an optimization problem. In this paper, we present an optimization approach for clustering by using four well-known evolutionary algorithms which are Biogeography-Based Optimization (BBO), Grey Wolf Optimization (GWO), Genetic Algorithm (GA) and Particle Swarm Optimization (PSO). Method: the objective function has been specified to minimize the total distance from cluster centers to the data points. Euclidean distance is used for distance calculation. We have applied this objective function to the given algorithms both to find the most efficient clustering algorithm and to compare the clustering performances of algorithms against different data sizes. In order to benchmark the clustering performances of algorithms in the experiments, we have used a number of datasets with different data sizes such as some small scale, medium and big data. The clustering performances have been compared to K-means as it is a widely used clustering algorithm for years in literature. Rand Index, Adjusted Rand Index, Mirkin's Index and Hubert's Index have been considered as parameters for evaluating the clustering performances. Result: As a result of the clustering experiments of algorithms over different datasets with varying data sizes according to the specified performance criteria, GA and GWO algorithms show better clustering performances among the others. Conclusions: The results of the study showed that although the algorithms have shown satisfactory clustering results on small and medium scale datasets, the clustering performances on Big data need to be improved. (C) 2020 AGBM. Published by Elsevier Masson SAS. All rights reserved. WOS:000576259700004 2-s2.0-85087211302

Test case generation is a multi objective problem as the goal is to achieve multiple targets. In existing work, emphasis is given to generate test cases to achieve maximum path coverage. For quality testing, coverage of critical path is more important than percentage of code coverage. The objective of this paper is to generate test cases to achieve maximum path coverage with a challenge of covering a critical path, within the available test resources. At the time of automatic test case generation, a path is critical if the probability of covering the path is low. Search based techniques use metaheuristic algorithms for automated test case generator. Fitness function plays an important role in searching techniques. We propose a fitness function, Improved Combined Fitness (ICF) function, using Adaptive Particle Swarm Optimization (APSO), to generate test cases automatically based on path coverage criteria. We have conducted experiments on three well-known case studies and observed that though both Particle Swarm Optimization (PSO) and APSO with the existing fitness functions, branch distance function and branch distance combined with approximation level, give maximum path coverage, sometimes fail to achieve critical path. Our proposed ICF function applied on APSO gives better result in terms of number of path coverage.

In this work, the design procedure of a hybrid robust controller for crane system is presented. The proposed hybrid controller combines the linear quadratic regulator (LQR) properties with the sliding mode control (SMC) to obtain an optimal and robust LQR/SMC controller. The crane system which is represented by pendulum and cart is used to verify the effectiveness of the proposed controller. The crane system is considered one of the highly nonlinear and uncertain systems in addition to the under-actuating properties. The parameters of the proposed LQR/SMC are selected using Particle Swarm Optimization (PSO) method. The results show that the proposed LQR/SMC controller can achieve a better performance if only SMC controller is used. The robustness of the proposed controller is examined by considering a variation in system parameters with applying an external disturbance input. Finally, the superiority of the proposed LQR/SMC controller over the SMC controller is shown in this work.

In this paper certain type of biometric measurements has been used to identify the cone beam computed tomography (CBCT) radiograph of the subject in a fast and reliable way. Where the CBCT radiograph of a person is used as a data and stored in database for later use in a person’s recognition process. The aim of this research is to use various stages of the preprocessing operations of the CBCT radiograph to obtain the clearest possible image that will help us in the identification process more easily and precisely. The contourlet transformation was used for feature extraction of each particular CBCT image and the results were processed by a new hybrid particle swarm optimization (PSO) named "contourlet PSO" algorithm (CPSO), which is faster and produce more precise (due to apply contourlet algorithm) than traditional PSO. The proposed algorithm (CPSO) gave a detection ratio of 98% after its application on 100 CBCT radiographs.

Maximum Power Point Tracking (MPPT) is a technique used in photovoltaic (PV) systems to maximize the power output from the solar panel by constantly tracking and adjusting the optimal operating point. To achieve this, various algorithms have been developed, with Particle Swarm Optimization (PSO) being a widely used method. By adjusting the control system’s parameters, PSO can determine the optimal operating point of the solar panel and improve its overall performance. PSO employs swarm intelligence by simulating the behavior of particles to find the best solution for a given problem. Long Short-Term Memory (LSTM) belongs to the family of Recurrent Neural Networks (RNN) in machine learning and is designed to address the limitations of traditional RNNs in capturing long-term dependencies that exist in sequential data. The combination of PSO and LSTM techniques can result in an efficient MPPT algorithm that leverages the benefits of both. PSO is utilized to optimize the control parameters of the MPPT algorithm, while LSTM is used to predict the solar panel’s power output based on historical data. Consequently, this integration can lead to an accurate and efficient MPPT algorithm that can effectively track the solar panel’s maximum power point. In this research article, an effort has been made to control the duty cycle of the converter by suitably controlling the system gain. A Matlab-based Simulink model in conjunction with Python programming has been used to make the system more robust.

The buckling enhancement of the negative Poisson’s ratio (NPR) effect on a laminated plate under uniaxial compression with an in-plane translational restraint is investigated in this paper. According to the buckling equation of an orthotropic plate under biaxial compression, the critical buckling load of an NPR-laminated composite under uniaxial compression can be increased due to the induced tension force on the unloaded direction. Instead of layer angles and stacking sequence, the NPR envelope and buckling load enhancement are studied using lamination parameters in this paper. The Poisson’s ratio contours are given in the feasible region of membrane lamination parameters. The results show that the negative Poisson’s ratios are more sensitive to V3A, which represents the unbalance degree of the laminate. Furthermore, the buckling loads for various Poisson’s ratio layups are investigated, and it is concluded that the buckling load increases with a decrease in Poisson’s ratio for the laminated rectangular plate considering in-plane translational restraint. Finally, the inverse problem of deciding the laminate configuration to target the lamination parameters is solved using the particle swarm optimization (PSO) algorithm.

Despite the rapid advances in autonomous guidance and navigation techniques for unmanned aerial vehicle (UAV) systems, there are still many challenges in finding an optimal path planning algorithm that allows outlining a collision-free navigation route from the vehicle’s current position to a goal point. The challenges grow as the number of UAVs involved in the mission increases. Therefore, this work provides a comprehensive systematic review of the literature on the path planning algorithms for multi-UAV systems. In particular, the review focuses on biologically inspired (bio-inspired) algorithms due to their potential in overcoming the challenges associated with multi-UAV path planning problems. It presents a taxonomy for classifying existing algorithms and describes their evolution in the literature. The work offers a structured and accessible presentation of bio-inspired path planning algorithms for researchers in this subject, especially as no previous review exists with a similar scope. This classification is significant as it facilitates studying bio-inspired multi-UAV path planning algorithms under one framework, shows the main design features of the algorithms clearly to assist in a detailed comparison between them, understanding current research trends, and anticipating future directions. Our review showed that bio-inspired algorithms have a high potential to approach the multi-UAV path planning problem and identified challenges and future research directions that could help improve this dynamic research area.

In order to solve the problems of nonlinearity, uncertainty and coupling of multi-hydraulic cylinder group platform of a digging-anchor-support robot, as well as the lack of synchronization control accuracy of hydraulic synchronous motors, an improved Automatic Disturbance Rejection Controller-Improved Particle Swarm Optimization (ADRC-IPSO) position synchronization control method is proposed. The mathematical model of a multi-hydraulic cylinder group platform of a digging-anchor-support robot is established, the compression factor is used to replace the inertia weight, and the traditional Particle Swarm Optimization (PSO) algorithm is improved by using the genetic algorithm theory to improve the optimization range and convergence rate of the algorithm, and the parameters of the Active Disturbance Rejection Controller (ADRC) were adjusted online. The simulation results verify the effectiveness of the improved ADRC-IPSO control method. The experimental results show that, compared with the traditional ADRC, ADRC-PSO and PID controller, the improved ADRC-IPSO has better position tracking performance and shorter adjusting time, and its step signal synchronization error is controlled within 5.0 mm, and the adjusting time is less than 2.55 s, indicating that the designed controller has better synchronization control effect.

In large-scale meat sheep farming, high CO2 concentrations in sheep sheds can lead to stress and harm the healthy growth of meat sheep, so a timely and accurate understanding of the trend of CO2 concentration and early regulation are essential to ensure the environmental safety of sheep sheds and the welfare of meat sheep. In order to accurately understand and regulate CO2 concentrations in sheep barns, we propose a prediction method based on the RF-PSO-LSTM model. The approach we propose has four main parts. First, to address the problems of data packet loss, distortion, singular values, and differences in the magnitude of the ambient air quality data collected from sheep sheds, we performed data preprocessing using mean smoothing, linear interpolation, and data normalization. Second, to address the problems of many types of ambient air quality parameters in sheep barns and possible redundancy or overlapping information, we used a random forests algorithm (RF) to screen and rank the features affecting CO2 mass concentration and selected the top four features (light intensity, air relative humidity, air temperature, and PM2.5 mass concentration) as the input of the model to eliminate redundant information among the variables. Then, to address the problem of manually debugging the hyperparameters of the long short-term memory model (LSTM), which is time consuming and labor intensive, as well as potentially subjective, we used a particle swarm optimization (PSO) algorithm to obtain the optimal combination of parameters, avoiding the disadvantages of selecting hyperparameters based on subjective experience. Finally, we trained the LSTM model using the optimized parameters obtained by the PSO algorithm to obtain the proposed model in this paper. The experimental results show that our proposed model has a root mean square error (RMSE) of 75.422 μg·m−3, a mean absolute error (MAE) of 51.839 μg·m−3, and a coefficient of determination (R2) of 0.992. The model prediction curve is close to the real curve and has a good prediction effect, which can be useful for the accurate prediction and regulation of CO2 concentration in sheep barns in large-scale meat sheep farming.

Hospitals must continually monitor their patients’ actions to lower the chance of accidents, such as patient falls and slides. Human behavior is difficult to track due to the complexity of human activities and the unpredictable nature of their conduct. As a result, creating a static link that is used to influence human behavior is challenging, since it is hard to forecast how individuals will think or act in response to a certain event. Mobility tracking depends on intelligent monitoring systems that apply artificial intelligence (AI) applications referred to as “categories”. Because motion sensors, such as gyroscopes and accelerometers, output unconnected data that lack labels, event detection is a vital task. The fall feature parameters of tridimensional accelerometers and gyroscope sensors are presented and used, and the classification technique is based on distinguishing characteristics. This study focuses on the age-old problem of tracking turbulence in motion to improve detection precision. We trained the model, considering that detection accuracy is limited by factors such as the subject’s mass, velocity, and gait style. This is performed by employing an experimental dataset. When we used the sophisticated technique of particle swarm optimization (PSO) in combination with a four-stage forward neural network (4SFNN) to forecast four different types of turbulent motion, we observed that the total prediction accuracy was 98.615% accurate.

In this article, we have shown the possibility of improving the quality of the energy injected into the electrical network and the flexibility of its exchange between the different components of the proposed hybrid network (photovoltaic generator connected to the network-storage battery-load of the DC motor) to develop a control element based on the combination of fuzzy logic and an algorithm derived from PSO Animal Behavior. The proposed control works on DC/AC and bi-directional DC/DC converters, which form the basis of power management between the parts of the proposed hybrid network. MATLAB/Simulink software is used to demonstrate the effectiveness of the proposed control. The results show that the proposed control contributed to the stability of the photovoltaic energy produced, the improvement of the quality of energy injected into the network, as well as the response speed during the process of charging and discharging the battery, which gave more efficiency to the DC motor connected to the DC bus.

RESUMEN: Este trabajo de fin de grado expone una introducción a la rama ingenieril de ingeniería de control. En concreto, a los reguladores más usados en el ámbito industriales como son los controladores PID. Se estudiará cada una de las acciones de control así como las técnicas más habituales, y otras más modernas, de sintonización considerando diversos criterios de desempeño. Además de los métodos clásicos de sintonización de Ziegler-Nichols, se presentará algunos métodos más modernos como algoritmos genéticos y enjambres de partículas. Por tanto, el trabajo consistirá en: Estudiar el origen y el uso de los controladores PID en el ámbito industrial. Estudiar los diferentes métodos de sintonización de controladores PID. Mediante Matlab/Simulink contrastar las prestaciones del PID. Sintonizar un regulador PID para controlar el nivel de tres depósitos mediante el segundo método de Ziegler–Nichols, algoritmo genético (AGs) y el algoritmo de optimización por enjambre de partículas (PSO). Se realizará de forma practica una sintonización de un PID en una placa de desarrollo Arduino UNO. ABSTRACT: This final degree project presents an introduction to the field of control engineering. Specifically, to the most used controllers in the industrial field such as PID controllers. Each of the control actions will be studied as well as the most common tuning techniques considering different performance criteria. In addition to the classical Ziegler-Nichols tuning methods, some more modern methods such as genetic algorithms and particle swarm optimization will be presented. Therefore, the Project will consist of: To study the origin and use of PID controllers in the industrial field. To study the different methods of tuning PID controllers. Using Matlab/Simulink to contrast the PID performance. Tuning a PID to control the level of three tanks using the second Ziegler-Nichols method, genetic algorithm (GAs) and particle swarm optimization (PSO) algorithm. A PID tuning on an Arduino UNO development board will be carried out in a practical way. Grado en Ingeniería en Electrónica Industrial y Automática

Inconel 718, a hard-to-cut superalloy is reputed for having poor machining performance due to its low thermal conductivity. Consequently, the surface quality of the machined parts suffers. The surface roughness value must fall within the stringent limits to ensure the functional performance of the components used in aerospace and bioimplant applications. One doable way to enhance its machinability is the adequate dissipation of heat from the machining zone through efficient and ecofriendly cooling environment. With this perspective, an experimental and integrated green-response surface machiningbased- evolutionary optimization (G-RSM-EO) approach is presented during this investigation. The results are compared with two base-line techniques: the traditional flooded approach with Hocut WS 8065 mineral oil, and the dry green approach. A Box-Behnken response surface methodology (RSM) is employed to design the milling tests considering three control parameters, i.e., cutting speed (vs), feed/flute (fz), and axial depth of cut (ap). These control parameters are used in the various experiments conducted during this research work. The parametric analysis is then accomplished through surface plots, and the analysis of variance (ANOVA) is presented to assess the effects of these control parameters. Afterwards, a multiple regression model is developed to identify the parametric relevance of vs, fz, and ap, with surface roughness (SR) as the response attribute. A residual analysis is performed to validate the statistical adequacy of the predicted model. Lastly, the surface roughness regression model is considered as the objective function of the particle swarm optimization (PSO) model to minimize the surface roughness of the machined parts. The optimized SR results are compared to the widely employed genetic algorithm (GA) and RSM-based desirability function approach (DF). The confirmatory machining tests proved that the integrated optimization approach with PSO being an evolutionary technique is more effective compared to GA and DF with respect to accuracy (0.05% error), adequacy, and processing time (3.19 min). Furthermore, the study reveals that the Mecagreen 450 biodegradable oil-enriched flooded strategy has significantly improved the milling of Inconel 718 in terms of eco-sustainability and productivity, i.e., 42.9% cost reduction in cutting fluid consumption and 73.5% improvement in surface quality compared to the traditional flooded approach and the dry green approach. Moreover, the G-RSM-EO approach presents a sustainable alternative by achieving a Ra of 0.3942 μm that is finer than a post-finishing operation used to produce close tolerance reliable components for aerospace industry.

To meet the increasing demand for its services, a cloud system should make optimum use of its available resources. Additionally, the high and low oscillations in cloud workload are another significant symmetrical issue that necessitates consideration. A suggested particle swarm optimization (PSO)-based ensemble meta-learning workload forecasting approach uses base models and the PSO-optimized weights of their network inputs. The proposed model employs a blended ensemble learning strategy to merge three recurrent neural networks (RNNs), followed by a dense neural network layer. The CPU utilization of GWA-T-12 and PlanetLab traces is used to assess the method’s efficacy. In terms of RMSE, the approach is compared to the LSTM, GRU, and BiLSTM sub-models.

Particle swarm optimisation (PSO) is one of the widely adopted meta-heuristic methods for solving real-life problems. Its practical utility can be further enhanced by improving its performance. In order to acheive this, academics have presented several variants of the original PSO over the past few years, including the quantum PSO (QPSO), bare-bones PSO (BB-PSO), hybrid PSO, fuzzy PSO, etc. In this paper, the performance of PSO is improved by proposing a fragmented swarm optimisation approach known as the PSOα. The PSOα is tested and compared with PSOs over 14 different benchmarking cost functions to validate its efficacy. The analysis is also carried out to see the impact of α on its performance. It is observed that the average value of the cost function over 50 simulations obtained using the fragmented swarm approach is lower than that obtained using the standard PSO in 12 out of 14 benchmark functions. Similarly, the fragmented approach outperforms the standard PSO in 13 out of 14 benchmark functions when compared with the best fitness value achieved out of 50 simulations. Finally, the proposed approach is applied to solve the well-known real-life optimisation problem of load frequency control (LFC) in power systems. A test system comprising both renewable and traditional power sources is considered to evaluate the efficacy of the proposed technique. A fractional order proportional-integral-differential (FOPID) controller is used, whose parameters are optimised using the proposed PSO for achieving the LFC. The proposed fragmentation approach can be applied with other optimisation techniques to improve their performance.