Inertia Weight Particle Swarm Optimization Research Articles

An Optimized Public Opinion Communication System in Social Media Networks Based on K-means Cluster analysis

This study proposes a public opinion monitoring model that combines the K-means clustering algorithm with Particle Swarm Optimization (PSO) to enhance the accuracy and effectiveness of public opinion monitoring on social media. The model’s performance across various dissemination indicators is studied in detail. Through experiments conducted on social media datasets, the study comprehensively evaluates the model from four dimensions: dissemination speed, scope, depth, and sentiment dissemination effectiveness. The experimental results indicate that the proposed optimization model excels in multiple areas, particularly in dissemination depth and sentiment dissemination effectiveness. Specifically, in the three dimensions of dissemination speed, the proposed model achieves scores of 4.3, 4.2, and 4.4 in initial dissemination speed, decay speed, and peak dissemination speed, respectively. In the dimensions of user coverage, geographic coverage, and platform coverage under dissemination scope, the model scores 4.4, 4.5, and 4.3, demonstrating a broad dissemination capability. Additionally, in the dimensions of hierarchical dissemination depth and key node influence within dissemination depth, the model scores 4.3 and 4.5, indicating excellent performance in multi-level dissemination and key node activation. In sentiment dissemination effectiveness, the model receives scores of 4.4, 4.5, and 4.4 in emotional tendency change, polarity distribution, and diffusion intensity, showcasing its advantages in sentiment classification and dissemination. Sensitivity analysis further validates the model’s sensitivity to parameter settings, with experiments showing that reasonable adjustments to parameters such as the K value, PSO inertia weight, and learning factors can reduce the Sum of Squared Errors to 3209.72. Meanwhile, it can improve clustering purity to 0.822 and raise the Rand index to 0.623. Therefore, this study offers an efficient and reliable solution for public opinion monitoring on social media, providing valuable reference significance.

Research on hybrid strategy Particle Swarm Optimization algorithm and its applications

The increasing complexity and high-dimensional nature of real-world optimization problems necessitate the development of advanced optimization algorithms. Traditional Particle Swarm Optimization (PSO) often faces challenges such as local optima entrapment and slow convergence, limiting its effectiveness in complex tasks. This paper introduces a novel Hybrid Strategy Particle Swarm Optimization (HSPSO) algorithm, which integrates adaptive weight adjustment, reverse learning, Cauchy mutation, and the Hook-Jeeves strategy to enhance both global and local search capabilities. HSPSO is evaluated using CEC-2005 and CEC-2014 benchmark functions, demonstrating superior performance over standard PSO, Dynamic Adaptive Inertia Weight PSO (DAIW-PSO), Hummingbird Flight patterns PSO (HBF-PSO), Butterfly Optimization Algorithm (BOA), Ant Colony Optimization (ACO), and Firefly Algorithm (FA). Experimental results show that HSPSO achieves optimal results in terms of best fitness, average fitness, and stability. Additionally, HSPSO is applied to feature selection for the UCI Arrhythmia dataset, resulting in a high-accuracy classification model that outperforms traditional methods. These findings establish HSPSO as an effective solution for complex optimization and feature selection tasks.

Efficient resource allocation for IoT applications in mobile edge computing via dynamic request scheduling optimization

This study investigates the challenges of task scheduling and resource allocation in an ultra-dense edge cloud (UDEC) network incorporating micro (macro) base stations and different equipment users (UE) under 5G technology. By utilizing multiple access interference (MAI), we enable multiple access capabilities to the UEs under the Non-Orthogonal Multiple Access (NOMA) protocol. To accommodate the dynamic nature of user tasks, we propose a two-level scheduling framework. At the upper level, the non-convex, non-linear power allocation problem for mobile users is formulated and solved using the Inertia Weight Particle Swarm Optimization (IW-PSO) algorithm to minimize the transmission energy consumption. Simultaneously, at the lower level, the joint task offloading and resource allocation problem is formulated as MINP and solved with the binary Particle Swarm Optimization (PSO) algorithm to find an optimal schedule that maximizes the response rate and the overall welfare of the system while minimizing the energy consumption. In this study, various sensitivity analyses are conducted for different parameters, including the number of mobile users, channel power, and request profile parameters, including workload and request size. Comparative analyses with other methods from recent literature consistently reveal the comparable performance of the proposed framework and confirm its effectiveness in addressing the challenges of dynamic task scheduling.

Application of improved particle swarm optimization algorithm in the proportional integral differential-controlled semi-active suspension system

To enhance the control performance of semi-active suspension systems, this research proposes a particle swarm optimization algorithm (PSO) with adaptive nonlinear correction of inertia weights, which is then integrated with a proportional integral differential (PID) algorithm. To this end, this research establishes quarter semi-active and passive suspension models of automobiles by utilizing the Matlab/Simulink simulation platform. In this foundation, this research further compares the advantages and disadvantages regarding performance indexes of semi-active suspension controlled by the adaptive inertia weighted particle swarm optimization (APSO) algorithm and the PID algorithm, as well as the PID-controlled semi-active suspension and passive suspension through simulation. Simulation results indicate that performance indicator values for different suspension types increase with higher pavement grades. Compared with passive suspension, the semi-active suspension controlled by APSO and PID algorithms presents significantly improved performance indexes, with reductions of at least 31.61% in root mean square (RMS) concerning body vertical acceleration, 1.78% in suspension dynamic deflection, and 22.13% in tire dynamic loads. Moreover, analysis of suspension system frequency response characteristics demonstrates a significant decrease in droop acceleration transmission rate for the semi-active suspension with APSO and PID algorithms across the whole frequency range compared with that of the PID-controlled suspension and passive suspension. On the same note, despite the higher values of suspension dynamic deflection and tire dynamic load transfer rate in certain frequency bands, they are generally within acceptable suspension limits. Simply put, the findings confirm the feasibility of applying the APSO algorithm in PID-controlled semi-active suspension systems, which effectively improves both vehicle ride comfort and handling stability.

An Improved Particle Swarm Optimization Algorithm for Automated Test Resource Allocation

With the rapid increase of software complexity, automated testing has become the mainstream of software testing. However, the current automated test tools adopt a large number of common test equipment resource. At the beginning of the test, for specific test scenarios, the testers need to plan the test equipment resources according to the requirements of the software under test. An automatic test equipment resource planning and optimization algorithm based on group optimization is proposed IPSO (Improved Particle Swarm Optimization) to solve this problem. This method maps the requirement description to the equipment description to obtain the matching matrix, and then establishes a multi-objective constrained optimization model for test equipment resource planning. The solution is obtained through improved particle swarm optimization algorithm to achieve the optimal planning of test equipment resources. Compared with traditional manual planning methods, this algorithm reduces the workload of testers, and improves the automation and efficiency of testing. Experimental results demonstrate that the optimal solutions found by the algorithm proposed in this paper is superior to those of the PSO (Particle Swarm Optimization)) and Linearly Decreasing Inertia Weight Particle Swarm Optimization (LWPSO) algorithms.

Applying Particle Swarm Optimization for Investigating the Stability of DC-DC Buck-Boost Converter: A Software Based Approach

ABSTRACT Stability of power converters has always been a major concern when dealing with nonlinear behavior of the system and swarm-based optimization techniques are proven to be handy as they are widely employed. Hence, this study presents an investigative approach to explore the compatibility of applying different variants of Particle Swarm Optimization (PSO) to design an optimized PID controller for DC-DC Buck-Boost converter. This work assesses converter stability through optimization of the PID controller using classical PSO (cPSO), Time-Varying Inertia Weight PSO (TVIW-PSO), Chaotic Descending Inertia Weight PSO (CDIW-PSO), Self-organizing Hierarchical PSO (HPSO) and Random inertia weight PSO (RIW-PSO). The State Space Average (SSA) method is utilized to model and attain the transfer function; eigenvalue analysis and time domain simulation analysis are considered to investigate the stability. Moreover, four objective functions and various performance parameters such as percentage of overshoot, rise time, settling time, and peak amplitude are tabulated to assess the system’s efficiency and the outcomes of different approaches are compared extensively. Amongst all, CDIW-PSO showcased better performances e.g. overshoot of 1.08%, settling time 0.000228s and rise time 0.000143s. The findings illustrate algorithm’s capacity to reduce transient and steady-state faults and makes it compatible with more nonlinear applications.

Multi-model fusion stacking ensemble learning method for the prediction of berberine by FT-NIR spectroscopy

Rhizoma Coptidis is a Chinese herbal medicine with antibacterial and anti-inflammatory properties. It has extensive applications in modern medicine. The content of berberine in Rhizoma Coptidis directly determines its quality. Fourier transforms near-infrared (FT-NIR) spectroscopy is a commonly used non-destructive method for rapidly detecting berberine content. In contrast to single-supervised learning algorithms in machine learning, ensemble learning combines individual learning algorithms to create a stable and better-performing strong-supervised model. This study collected spectral data of Rhizoma Coptidis using FT-NIR spectroscopy technology and established a chemometric model using a stacking ensemble approach with multiple models. Partial Least Squares (PLS), Adaptive Boosting (AdaBoost), Gradient boosting decision trees (GBDT), random forest (RF), and extreme gradient boosting (XGBoost) regression models were chosen as alternative base models, different Stacking models were established by random combinations. To fully leverage the strengths of each model and enhance predictive capability, an adaptive inertia weight particle swarm optimization algorithm (AWPSO) was used to search for the optimal parameters. The correlation coefficient of the test (RT) and the root mean square error of the test (RMSET) systematically evaluated the model performance. Finally, AWPSO-RF, AWPSO-XGBoost, and AWPSO-AdaBoost were selected as the base models. The RMSET and RT for RF, XGBoost, and AdaBoost were 0.226, 0.250, 0.195, and 0.871, 0.830, 0.927. After optimizing with the AWPSO algorithm, the RMSET and RT for AWPSO-RF, AWPSO-XGBoost, and AWPSO-AdaBoost were 0.226, 0.245, 0.194, and 0.871, 0.843, 0.922, respectively. The RMSET and RT values for the stacking ensemble were 0.174 and 0.932. The prediction accuracy and generalization ability of multi-model fusion stacking ensemble learning are superior to the single-model regression methods. Therefore, the stacking ensemble learning method that combines AdaBoost, RF, and XGBoost regression models is effective and feasible for assisting in the detection of berberine content in Rhizoma Coptidis.

Comparison PSO And IWPSO Performance In Optimizing Decision Tree Algorithm On Heart Disease Dataset

Heart disease, one of the most common and potentially fatal chronic diseases, has become a major focus in global health efforts. In this study, researchers used the decision tree algorithm on the heart disease dataset with the stages of the decision algorithm including the EDA, Split Data, and Decision tree modeling stages. Furthermore, hyperparameters use PSO and IWPSO to optimize the algorithm. The purpose of this research is to analyze the performance of Particle Swarm Optimization (PSO) and Inertia Weight Particle Swarm Optimization (IWPSO) in heart disease prediction based on relevant datasets. PSO and IWPSO were applied to the heart disease dataset, with the results showing an accuracy rate of 78% for PSO and 84% for IWPSO. These results indicate that IWPSO provides significant performance improvement compared to PSO in the context of heart disease prediction. The implications of these findings can support the development of more efficient prediction systems for early detection of heart disease, making a positive contribution to prevention efforts and further treatment of this critical health condition. In addition, the purpose of this research is to continue research in the form of C4.5 on heart disease with a result of 80.43%. In this study, IWPSO got the best accuracy of 84.23% greater than previous research. The results of this study are to provide insight that PSO and IWPSO hyperparameters can optimize decision trees in handling heart disease datasets and continue research.

Analysis of Hybrid Feature Optimization Techniques Based on the Classification Accuracy of Brain Tumor Regions Using Machine Learning and Further Evaluation Based on the Institute Test Data.

The goal of this study was to get optimal brain tumor features from magnetic resonance imaging (MRI) images and classify them based on the three groups of the tumor region: Peritumoral edema, enhancing-core, and necrotic tumor core, using machine learning classification models. This study's dataset was obtained from the multimodal brain tumor segmentation challenge. A total of 599 brain MRI studies were employed, all in neuroimaging informatics technology initiative format. The dataset was divided into training, validation, and testing subsets online test dataset (OTD). The dataset includes four types of MRI series, which were combined together and processed for intensity normalization using contrast limited adaptive histogram equalization methodology. To extract radiomics features, a python-based library called pyRadiomics was employed. Particle-swarm optimization (PSO) with varying inertia weights was used for feature optimization. Inertia weight with a linearly decreasing strategy (W1), inertia weight with a nonlinear coefficient decreasing strategy (W2), and inertia weight with a logarithmic strategy (W3) were different strategies used to vary the inertia weight for feature optimization in PSO. These selected features were further optimized using the principal component analysis (PCA) method to further reducing the dimensionality and removing the noise and improve the performance and efficiency of subsequent algorithms. Support vector machine (SVM), light gradient boosting (LGB), and extreme gradient boosting (XGB) machine learning classification algorithms were utilized for the classification of images into different tumor regions using optimized features. The proposed method was also tested on institute test data (ITD) for a total of 30 patient images. For OTD test dataset, the classification accuracy of SVM was 0.989, for the LGB model (LGBM) was 0.992, and for the XGB model (XGBM) was 0.994, using the varying inertia weight-PSO optimization method and the classification accuracy of SVM was 0.996 for the LGBM was 0.998, and for the XGBM was 0.994, using PSO and PCA-a hybrid optimization technique. For ITD test dataset, the classification accuracy of SVM was 0.994 for the LGBM was 0.993, and for the XGBM was 0.997, using the hybrid optimization technique. The results suggest that the proposed method can be used to classify a brain tumor as used in this study to classify the tumor region into three groups: Peritumoral edema, enhancing-core, and necrotic tumor core. This was done by extracting the different features of the tumor, such as its shape, grey level, gray-level co-occurrence matrix, etc., and then choosing the best features using hybrid optimal feature selection techniques. This was done without much human expertise and in much less time than it would take a person.

Frequency Stability Enhancement of Microgrid Using Optimization Techniques-Based Adaptive Virtual Inertia Control

In recent years, a sharp increase in integration of renewable energy sources (RESs) in power system network has been observed. High penetration of RES interfaced with power electronics converters-inverters with reduced or no inherent inertia compromises modern power system’s overall stability. Due to low inertia, voltage and frequency deviations far off the allowable threshold occur. To overcome this challenge, an adaptive inertia control strategy based on optimization technique is proposed. The improved particle swarm optimization (PSO) and genetic algorithm (GA) optimization techniques-based PID controller has been used to generate the appropriate virtual inertia coefficient for effective emulation of inertia in the presence of energy storage system. The conventional PSO suffers local optima stagnation, resulting in premature convergence during searching process in order to achieve global and local position. To address this issue, the velocity update equation was modified on inertia weight (w) using an additional exponential term with linear decreasing inertia weight PSO (LDIW-PSO). In this paper, exponential power is taken strategically instead of squaring it in order to reduce the number of iterations for faster convergence. Finally, a microgrid based on wind and solar energy is simulated using MATLAB/Simulink where three cases, 2% disturbance, 3% disturbance, and 4% disturbance, have been considered. Here, the evaluation of proposed system is carried out based on four main performance indices (ITAE, IAE, ISE, and ITSE). Furthermore, validation was done through hardware prototype to get experimental results in real time. The results from MATLAB simulation and experimental setup are in sync.

Disassembly Sequence Optimization of Lithium Battery Pack Based on Priority Constraint Graph

With the rapid development of the new energy vehicle power industry, the power system of automobiles is about to usher in a wave of retirement. At present, most of power lithium battery packs are disassembled violently, which lack a reasonable disassembly order. This causes a waste of time and cost during the disassembly process. Some harmful parts will also pollute the environment. In order to improve the disassembly efficiency of retired lithium-ion battery packs, the disassembly sequence planning problem (DSP) based on priority constraint graph is studied in this paper. After analyzing disassembly characteristics, the priority constraint graph is constructed as the constraint matrix. Considering the disassembly efficiency, a mathematical model is established to optimize the direction and the number of tool changes. An improved Simulated Annealing Particle Swarm Optimization (SA-PSO) algorithm is designed, which is to update the disassembly sequence by the population update method. The particles are assisted to jump out of the local optimum by the Metropolis criterion of SA algorithm. An adaptive method is proposed for the PSO inertia weight ω. In order to verify the validity of the model and algorithm, an example is introduced to compare SA-PSO with PSO and SA algorithm. The results show that the improved algorithm performs well in the evaluation index of fitness. The convergence rate is fast and more stable.

A mathematical model and metaheuristic approach to solve the real-time feeder vehicle routing problem

Unlike classic vehicle routing problems, real-time vehicle routing problems (RTVRPs) are real-world dynamic vehicle routing problems (DVRPs) in which customer requests are identified over the time horizon of operations without previous knowledge. In this problem, received requests are answered as quickly as possible and then dispatched to a service vehicle. Considering the RTVRP’s timing constraints, a solution must provide the best trade-off between the computation time required to find the solution and the proposed solution’s costs. A feeder vehicle routing problem (FVRP) consists of a heterogeneous fleet of vehicles, including trucks and motorcycles. In this problem, motorcycles pass easily in crowded areas, and the traffic of urban logistics is distributed easily. The feeder approach also lowers the number of times the vehicle returns to the central depot for loading, resulting in cost and time savings. The present article proposes a real-time feeder vehicle routing problem (RTFVRP) in a situation where every truck and every motorcycle can join during the freight delivery process. After modeling the RTFVRP through mixed-integer linear programming, a dynamic inertia weight particle swarm optimization (DIWPSO) algorithm is offered to solve the problem. The results of the static version of the FVRP in the small and the last time slices show that the GAMS outputs outperform those of the DIWPSO and differential evolution (DE), both indicating a similar performance. The results of running these algorithms for 21 DVRP test instances revealed that the PSO outperforms the DE in quality and solution runtime in both static and dynamic versions. Overall, the PSO and DE algorithms generated 34.33% and 30.37% cost savings in implementing RTFVRP, respectively, compared to the case that all requests were available at the beginning of the working day.

Design of Health Healing Lighting in a Medical Center Based on Intelligent Lighting Control System

The intelligent lighting control system will unify the management of lighting equipment in outpatient buildings, inpatient buildings, and other buildings of the hospital, thereby improving the service quality of the hospital, providing a comfortable and relaxed working environment for medical staff, and providing a warm and comfortable treatment environment for patients. This project aims to develop a health rehabilitation environment lighting automation control system based on combining Zigbee Wide Ad Hoc Network and RFID (Radio Frequency Identification) technology. It can be customized according to the comfort needs of patients and can achieve lighting adjustments before the patient arrives. A PSO-based intelligent lighting control method has been proposed. To overcome the shortcomings of PSO such as being prone to local minima and premature convergence, a new PSO optimization method is proposed based on the inertia weight PSO and combined with genetic optimization theory. This method can not only learn experience from individuals in the group but also avoid the possibility of parent particles falling into local extremum. Compared with the original particle swarm optimization algorithm, the new particle swarm optimization algorithm can quickly find the optimal combination of lighting devices, improve computational efficiency by 6.208%, and also reduce the energy consumption of the calculated lighting devices, indicating the advantages of the new particle swarm optimization algorithm.

Effective Workflow Scheduling in Cloud using Constriction Factor based Inertia Weight Particle Swarm Optimization

Cloud computing allows rapid provision of resources based on the need. This enables users to execute the independent tasks and dependent tasks called workflows on the cloud system. Workflow scheduling is a crucial problem that is NP Hard and is still a challenging problem. Particle Swarm Optimization (PSO) is one of the commonly used metaheuristic algorithms for solving task scheduling problems, but it has issues with premature convergence and lack of diversity. In recent years, chaotic maps have been employed in PSO to enhance its performance. This study proposes a Constriction factor-based inertia weight in PSO for workflow scheduling (CFPSO). The proposed algorithm utilizes a constriction factor for updating the inertia weight, which enhances the exploration ability of the algorithm thereby avoid local optima. The algorithm considers a fitness function with an aim to minimize makespan, service cost, and maximize load balance. The proposed algorithm is evaluated using a set of benchmark workflows, and the obtained results are compared with the standard PSO algorithm, Grey Wolf Optimizer (GWO) algorithm and Chaotic PSO algorithm. The extensive experimentation performed show that the proposed algorithm outperforms the other algorithms in terms of makespan, service cost, and load balance. The proposed CFPSO shows reduction of 20% of makespan, 2% of the service cost and 18% load balance rate compared to the conventional algorithms on Montage workflow with 1000 tasks. The use of constriction factor enhances the performance of the algorithm and makes it suitable for solving complex problems with multiple objectives. The proposed algorithm can be used in real-world applications to optimize workflow scheduling in cloud computing environments.

Overlapping peak separation algorithm for ion mobility spectra based on multistrategy JAYA.

In the field of separation science, ion mobility spectrometry (IMS) plays an important role as an analytical tool. However, the lack of sufficient structural resolution is a common problem in qualitative and quantitative analysis using IMS. A method is needed to solve the problem of overlapping peaks caused by insufficient resolution. The method uses multiple strategies to more effectively use population information to balance exploration and exploitation capabilities, prevent local optimization, accurately resolve overlapping peaks, quickly obtain optimal spectral peak model coefficients, and accurately identify compounds. Multistrategy JAYA algorithm's (MSJAYA) performance is compared with improved particle swarm optimization (IPSO), dynamic inertia weight particle swarm optimization (DIWPSO), and multiobjective dynamic teaching-learning-based optimization (MDTLBO). The analysis shows that MSJAYA's maximum separation error is within 0.6%, a level of accuracy not guaranteed by the other algorithms. In addition, the separation error fluctuates within a much smaller range, demonstrating MSJAYA's superior robustness. Compared with other overlapping peak separation algorithms, MSJAYA is more applicable because no special parameters are used. The method allows fast deconvolution analysis of strong overlapping peaks with multiple components, which greatly improves the resolution of IMS.

Intelligent Optimization Control Method for Photovoltaic Power Generation Systems Under Shadow Occlusion Conditions

<p>In the process of photovoltaic power generation, maximum power point tracking is an important method to improve the efficiency of photovoltaic power generation. Under the actual local shadow condition, the maximum power point of Photovoltaic system fluctuates. For this reason, this paper establishes the mathematical model and output characteristic equation of photovoltaic cells according to the actual application, and then uses the adaptive inertia weight Particle Swarm Optimization algorithm to solve the problem of slow search speed and low accuracy in the process of maximum power point tracking. After optimization, the method proposed in this paper can significantly improve the tracking effect efficiency, and the optimization results in real operation scenarios can improve the photovoltaic cell power generation efficiency by 21.3%, which proves the effectiveness of the algorithm.</p> <p> </p>

Hyperbolic Tangent - Based Adaptive Inertia Weight Particle Swarm Optimization

This paper presents a study on using adaptive inertia weight (AIW) in particle swarm optimization (PSO) for solving optimization problems. An AIW function based on the hyperbolic tangent function was proposed, with the function parameters adaptively tuned based on the particle best and global best values. The performance of the proposed AIW-PSO was compared with standard PSO and other PSO variations using seven benchmark functions. The results showed that the proposed AIW-PSO outperformed the other variations in terms of minimum cost and mean cost while reducing the standard deviation of cost. The performance of the different PSO variations was also analysed by plotting the best cost against iteration, with the proposed AIW-PSO showing a faster convergence rate. Overall, the study demonstrates the effectiveness of using an adaptive inertia weight function in PSO for optimizing problems.

Fuel Consumption Efficiency Enhancement of Synchronous Diesel Generator Operating at Adjustable Speed using Adaptive Inertia Weight Particle Swarm Optimization Algorithm

Diesel generator is a reliable source of electricity, but requires quite high operational costs, especially for fuel. This paper describes a technique for reducing fuel consumption in Diesel Engine Synchronous Generator systems. The system is originally a Constant Speed Diesel Synchronous Generator (CSD-SG), but during certain conditions, the speed is reduced to minimize fuel consumption by adjusting the Specific Fuel Consumption (SFC) map. SFC is defined as the amount of fuel consumed by a diesel engine generator for each unit of power output. It shows various numbers depending on the speed and operating power. In this paper, we use the Adaptive Inertia Weight Particle Swarm Optimization (AIWPSO) algorithm to select of the proper SFC curve at a certain speed and operating power. AIWPSO employs an adaptive inertial weight adjustment method, which enables this algorithm to achieve faster convergence than conventional Particle Swarm Optimisation (PSO) algorithms. The system is embedded with AC/DC/AC power electronics converter to regulate the frequency. Data set of 1000 kVA Cummins diesel engine generator from the oil and gas company in Central Java, Indonesia was taken for simulations. The results show that the AIWPSO algorithm calculates the fuel consumption as 1,678 liters per day on a typical condition, whereas the previous method, the linear line needs 1,693 liters per day. Therefore, using AIWPSO method can save up to 450 liters of fuel per month. The simulation results show that the proposed method can improve fuel efficiency compared to the previous model.

Prediction Model of Greenhouse Tomato Yield Using Data Based on Different Soil Fertility Conditions

Tomato yield prediction plays an important role in agricultural production planning and management, market supply and demand balance, and agricultural risk management. To solve the problems of low accuracy and high uncertainty of tomato yield prediction methods in solar greenhouses, based on experimental data for water and fertilizer consumption by greenhouse tomatoes in different regions over many years, this paper investigated the prediction models of greenhouse tomato yields under three different soil fertility conditions (low, medium, and high). Under these three different soil fertility conditions, greenhouse tomato yields were predicted using the neural network prediction model (NN), the neural network prediction model based on particle swarm optimization (PSO–NN), the neural network prediction model based on an adaptive inertia weight particle swarm optimization algorithm (AIWPSO–NN), and the neural network prediction model based on the improved particle swarm optimization algorithm (IPSO–NN). The experimental results demonstrate that the evaluation indexes (mean square error, mean absolute error, and R2) of the IPSO–NN prediction model proposed in this paper were superior to the other three prediction models (i.e., NN prediction model, AIWPSO–NN prediction model, and IPSO–NN prediction model) under three different soil fertility conditions. Among them, compared with the NN prediction model, the MSE of the other three prediction models under high soil fertility decreased to 0.0082, 0.0041, and 0.0036; MAE decreased to 0.0759, 0.0511, and 0.0489; R2 decreased to 0.8641, 0.9323, and 0.9408. These results indicated that the IPSO–NN prediction model had a higher predictive ability for greenhouse tomato yields under three different soil fertility conditions. In view of the important role of tomato yield prediction in greenhouses, this technology may be beneficial to agricultural management and decision support.

Dynamic Inertia Weight Particle Swarm Optimization for Anomaly Detection: A Case of Precision Irrigation

Anomaly-based Intrusion Detection System (IDS) is a type of IDS that detects abnormal behaviors by analyzing system activity and network traffic. Anomaly-based IDS works by establishing a baseline of normal behavior for a system or a network. However, these types of systems are less used compared to signature-based IDS for one primary challenge: How to define this normal behavior baseline? The answer to this question is complicated, since it involves not only analyzing or learning from historical data, but requires and understanding of the business domain the system is implemented in. The present study proposes a novel approach to constructing an unsupervised data classifier that combines both Particle Swarm Optimization (PSO) and clustering techniques for anomaly detection. The primary objective of this methodology is to surmount the limitations that conventional clustering algorithms suffer from, such as their inability to identify non-linear patterns within the data, susceptibility to initial conditions, and difficulty in overcoming the problem of local optima. The concept of particle systems is discussed by examining their origins, search strategies, and convergence mechanisms. We use a variant of the Particle Swarm Optimization called Dynamic Inertia Weight-Particle Swarm optimization (DIW-PSO) for our clustering process, and we elaborate on the reasoning behind this decision. Subsequently, we describe the labeling algorithm used for the resulting clusters and we explain the process for identifying anomalous clusters. We have demonstrated the effectiveness of our method by applying it to an intelligent irrigation control system for cotton plants. The results show that our classifier was able to accurately detect abnormal patterns that deviated from the optimal water requirements and growth conditions of the plants.