Narrow Results

For civil engineering structures, structural damage usually occurs at limited positions in the preliminary stage of the structural failure. Compared with the numerous elements of the entire structure, the damaged elements are sparsely distributed in space. Based on this important prior information, this paper proposed to utilize a sparse Bayesian learning method to identify the damage to structures while considering the measurement noise and modeling error. The particle Swarm Optimization (PSO) algorithm was first introduced to address the associated computational efficiency issue, and the optimization performances of PSO and Sequential Quadratic Programming (SQP) algorithm in the process of model updating were compared, positive outcomes revealed that the PSO algorithm has the stronger searching ability and better robustness. To investigate the effectiveness and practicality of the sparse Bayesian learning with a PSO algorithm in structural damage detection, an asymmetrical frame in different scenarios (e.g. with single and multiple damages) was constructed in the laboratory. The encouraging results of the experimental case studies compellingly demonstrate that the presented methodology not only can detect the location and extent of structural damage with high precision and efficiency, but also can proficiently assess the posterior uncertainties associated with the damage detection results.

We present a solution of the multiprocessor scheduling problem based on applying a relatively new metaheuristic called Generalized Extremal Optimization (GEO). GEO is inspired by a simple coevolutionary model known as Bak-Sneppen model. The model assumes existing of an ecosystem consisting of N species. Evolution in this model is driven by a process in which the weakest species in the ecosystem, together with its nearest neighbors is always forced to mutate. This process shows characteristic of a phenomenon called a punctuated equilibrium which is observed in evolutionary biology. We interpret the multiprocessor scheduling problem in terms of the Bak-Sneppen model and apply the GEO algorithm to solve the problem. We show that the proposed optimization technique is simple and yet outperforms both genetic algorithm (GA)-based and particle swarm optimization (PSO) algorithm-based approaches to the multiprocessor scheduling problem.

A Low Energy Beam Transport (LEBT) has been designed and optimized to inject both a 50keV/u, 50mA $H^{+}$ beam and a 20keV/u, 1mA ${}^3{\mathrm{\text{He}}}^{2+}$ beam into the downstream Radio Frequency Quadrupole (RFQ) at the Lanzhou Light Ion Cancer Therapy Facility (LLICTF). The overall aim is to increase the operation efficiency and simplify the complexity of the LLICTF. This dual-beam operation mode creates phase space distortions as a result of the intense space charge, and causes transverse asymmetry due to a mixture of solenoids and a dipole magnet. To mitigate the phase space distortions of the high-intensity proton beam, two beam scrapers have been placed at locations determined through careful analysis of the space charge forces and external focusing force of the beam. Additionally, the Particle Swarm Optimization (PSO) algorithm has been utilized to obtain an approximate solution for the dipole parameters, which helps maintain the symmetry of different symmetrical beams passing through it. Optics designs that implement these solutions are verified with multi-particle simulations.

Obtaining the more exact parameters of slip surfaces is proved to be crucial in the analysis of landslide stability, and there are four study methods available i.e. in-site test, laboratory test, back analysis and theoretical analysis. In general, the former two are the basic one, whereas the latter two are secondary. A set of test values about shearing stress and direct stress can be obtained through in-situ and lab tests, then the parameters of slip surface should be calculated to fitting for the test value by the least square method usually, but the effect of anomalous values should increase markedly because the quadratic sum of residual errors is adopted in calculations. In order to reduce the effect of anomalous value, a new method based on the robust regression analysis and the particle swarm optimization method are adopted to calculate the mechanics parameter of landslides in this paper. In the new method, the sum of residual absolute values is used to replace the quadratic sum of residual error, and then the quadratic sum of anomalous value can be avoided. Comparing to the least square method, the new method can reduce availably the effect of abnormal values, and the results are more credible. Furthermore, an engineering example is cited to show the validity.

Today, with real-life problems, modeling is a primary step in organizing, analyzing and optimizing them. Queueing theory is a particular approach used to model this category of issues. Space constraints, feedback, service dependency, etc. are often inseparable from the issues they create. In light of this objective, this research presents a model and analysis of the steady-state behavior of an $M/G/1$ feedback retrial queue with two dependent phases of service under a Bernoulli vacation policy. The service times for the two stages are often independent in normal queueing frameworks. We presume that they are dependent random variables in this case. Indeed, this dependence is one-way (i.e., the service time of the second phase has no effect on the service time of the first phase). Yet, the first phase service time has an impact on the second phase service time. In order to determine the steady-state probabilities and probability-generating functions (PGF) for the different states, the supplementary variable technique (SVT) was utilized. Furthermore, a broad range of performance metrics had been established. The generated metrics are then envisioned and validated with the aid of graphs and tables. Additionally, a nonlinear cost function is constructed, which is subsequently minimized by distinct approaches like particle swarm optimization (PSO), artificial bee colony (ABC) and genetic algorithm (GA). Furthermore, we used certain figures to examine the convergence of these optimization methods. Finally, validation outcomes are compared with neuro-fuzzy results generated with the “adaptive neuro-fuzzy inference system” (ANFIS).

In virtue of the particle swarm optimization (PSO) algorithm, the global minimum candidate structures with the lowest energy for ${({\mathrm{\text{Fe}}}_3{\mathrm{\text{O}}}_4)}_n(n=1-3)$ clusters were obtained by first-principles structural searches. The geometric structures and spin configurations of three cationic ${({\mathrm{\text{Fe}}}_3{\mathrm{\text{O}}}_4)}_n^{+}(n=1-3)$ clusters have been identified for the first time by comparing the experimental IR spectra with the calculated results from density functional theory by using different exchange-correlation functionals. It is found that the lowest energy structures of these clusters are of a shape of hat, boat and tower, respectively, with a ferrimagnetic arrangement of spins, and M06L functional is more suitable for ${\mathrm{\text{Fe}}}_3{\mathrm{\text{O}}}_4$ clusters than other ones.

This paper presents geometric feature-based model for age group classification of facial images. The feature extraction is performed considering significance of the effects that age has on facial anthropometry. Particle Swarm Optimization (PSO) technique is used to find optimized subset of geometric features. The relevance and importance of age differentiation capability of the features are evaluated using support vector classifier. The facial images are categorized in seven major age groups. The effectiveness and accuracy of the proposed feature extraction is demonstrated with the experiments that are conducted on two publicly available databases namely Face and Gesture Recognition Research Network (FGNET) Aging Database and Iranian Face Database (IFDB). The results demonstrate that the success rate of the classification is 92.62%. The results also show significant improvement compared to the state-of-the-art models.

To remove image noise without considering the noise model, a dual-tree wavelet thresholding method (CDOA-DTDWT) is proposed through noise variance optimization. Instead of building a noise model, the proposed approach using the improved chaotic drosophila optimization algorithm (CDOA), to estimate the noise variance, and the estimated noise variance is utilized to modify wavelet coefficients in shrinkage function. To verify the optimization ability of the improved CDOA, the comparisons with basic DOA, GA, PSO and VCS are performed as well. The proposed method is tested to remove addictive noise and multiplicative noise, and denoising results are compared with other representative methods, e.g. Wiener filter, median filter, discrete wavelet transform-based thresholding (DWT), and nonoptimized dual-tree wavelet transform-based thresholding (DTDWT). Moreover, CDOA-DTDWT is applied as pre-processing utilization for tracking roller of mining machine as well. The experiment and application results prove the effectiveness and superiority of the proposed method.

Path planning is the essential aspect of autonomous flight system for unmanned aerial vehicles (UAVs). An improved particle swarm optimization (PSO) algorithm, named GBPSO, is proposed to enhance the performance of three-dimensional path planning for fixed-wing UAVs in this paper. In order to improve the convergence speed and the search ability of the particles, the competition strategy is introduced into the standard PSO to optimize the global best solution during the process of particle evolution. More specifically, according to a set of segment evaluation functions, the optimal path found by single waypoint selection way is adopted as one of the candidate global best paths. Meanwhile, based on the particle as an integrated individual, an optimal trajectory from the start point to the flight target is generated as another global best candidate path. Subsequently, the global best path is determined by considering the pre-specified elevation function values of two candidate paths. Finally, to verify the performance of the proposed method, GBPSO is compared with some existing path-planning methods in two simulation scenarios with different obstacles. The results demonstrate that GBPSO is more effective, robust and feasible for UAV path planning.

Airfoil optimization algorithm is studied and a hybrid PSO and GA method is proposed in this paper. After function test, it shows that algorithm is well in convergence performance, fast speed, and optimization capability. Then, the airfoil parametric expression theory is analyzed. A new airfoil is obtained after combining CFD and PSO-GA optimization. The aerodynamic of new airfoil is compared with the airfoil optimized by GA-PSO and basic airfoil NACA0018. The results indicate that new airfoil is better than the other two airfoils in lift coefficient, lift-drag ratio, and surface pressure. At last, wing-sail of new airfoil and NACA0018 wing-sail are designed and manufactured. Both of them are applied in land-yacht robot linear motion and steering motion experiment. For the linear motion, in the situation of wind speed being 15m/s and angle of attack being 5, running speed of robot with optimized new wing-sail is 1.853m/s. In steering motion, trajectory with new wing-sail is closer to the real situation and it gets more thrust. The experiments data verify that the simulation results are correct and PSO-GA algorithm is effective.

Particle Swarm Optimization (PSO) is a population-based meta-heuristic known for its simplicity, being successfully used in clustering task with interesting performance. Clustering of multi-view data sets has received increasing attention since it explores multiple sources or views of data sets aiming at improving clustering accuracy. Previous studies mainly focused on PSO-based clustering of single-view vector data, neither single- nor multi-view PSO-based clustering of relational received proper attention. This paper introduces a PSO-based approach to the fuzzy clustering of multi-view relational data, which can cluster data sets described by several dissimilarity matrices, each of them representing a particular view. In this work, ten fitness functions were considered, in which eight of them were adapted to deal with multi-view relational data and to consider the relevance weights of views. These fitness functions were compared to evaluate which best fit to cluster multi-view relational data. The performance and usefulness of the proposed approach, in comparison with previous single- and multi-view relational fuzzy clustering algorithms, are illustrated with several multi-view data sets. The Adjusted Rand Index (ARI) and F-measure were used to assess the quality of fuzzy partitions provided by clustering algorithms. The results have shown that the proposed methods significantly outperformed the compared algorithms in the majority of cases.

Image segmentation is a classical problem in the field of computer vision. Fuzzy $c$-means algorithm (FCM) is often used in image segmentation. However, when there is noise in the image, it easily falls into the local optimum, which results in poor image boundary segmentation effect. A novel method is proposed to solve this problem. In the proposed method, first, the image is transformed into a neutrosophic image. In order to improve the ability of global search, a combined FCM based on particle swarm optimization (PSO) is proposed. Finally, the proposed algorithm is applied to the neutrosophic image segmentation. The results of experiments show that the novel algorithm can eliminate image noise more effectively than the FCM algorithm, and make the boundary of the segmentation area clearer.

White blood cells (WBCs) play a main role in identifying the health condition and disease characteristics of a normal person. An automated classification system is capable of recognizing white blood cells that may help doctors to diagnose several diseases like malaria, anemia, leukemia, etc. Automated blood cell analysis allows fast and accurate outcomes and often involves broad data without performance negotiation. The state-of-the-art systems use a lot of different stages (feature extraction, segmentation, pre-processing, etc.) to provide the automated blood cell analysis using blood smear images which is a lengthy process. To overcome these problems, this paper presents an efficient peripheral blood cell image recognition and classification using a combination of the salp swarm algorithm and the cat swarm optimization (SSPSO) algorithm-based optimized convolutional neural networks (SSPSO-CNN) method. This paper uses the CNN approach to classify five peripheral blood cells such as eosinophil, basophil, lymphocytes, monocytes, and neutrophils without any human intervention. The other objective of this paper is to propose an improved version of salp swarm optimizer (SSO) using particle swarm optimization (PSO) to attain competitive classification performance over the database of the blood cell images. In this paper, the CNN uses VGG19 architecture for training purposes. The accuracy of the classification achieved with VGG19 models is 98%. The proposed model based on the CNN approach optimized by SSPSO achieves high classification accuracy and provides automatic peripheral blood cell classification. This method establishes the fine-tuning process to develop a classifier trained using 10 674 images obtained from medical practice. The proposed method augmented the performance in terms of high precision and $F$1-score and obtained an overall classification accuracy of 99%.

The internet of things (IoT) is a rapidly expanding network of smart digital devices that can communicate with one another and be controlled remotely over the internet. Moreover, IoT devices are cheap and can be used to control and monitor activities remotely. Due to this reason, IoT is widely used in the applications of a smart city. Moreover, the smart devices that are used in IoT-based smart city applications are used to gather information from devices, humans, and other sources for analyzing purposes. Hence, it is crucial to conduct the face recognition process to ensure the safety of the city. Several works were conducted by the researchers to recognize the face accurately. Typically, the effectiveness of achieving face recognition is still an intricate one. To tackle those issues, we have proposed a novel condition convolutional neural network (condition-CNN)-based bee foraging learning (BFL)-based particle swarm optimization (PSO) algorithm (CCNNBFLPSO). To recognize the facial images from the face image datasets, the proposed CCNNBFLPSO model is used. To ensure the prediction accuracy condition, CNN uses the conditional probability weight matrix (CPWM) to estimate the higher and lower class level of image features. Meanwhile, the learning of CPWM can be performed by utilizing the adopted BPL-PSO approach. For experimental purposes, we have taken three datasets namely the CVL face database, the MUCT database, and the CMU multi-PIE face database. The training time and the training accuracy are analyzed for all the three datasets, and comparative studies are performed with state-of-art works such as LBPH, FoL TDL, and TPS approaches. The training and validation loss functions are analyzed with baseline CNNs, B-CNN, and condition-CNN. The proposed approach accomplishes better face recognition accuracy and F1-score of about 99.9% and 99.9%, respectively.

In view of the premature convergence of particle swarm optimization (PSO) that is often caused by the loss of diversity, an improved cooperative PSO (ICPSO) is proposed. The method can dynamically combine the optimum values of the particles themselves, the global particles and the optimum values in groups, use the current optimization stage to dynamically adjust the shared proportion of information and effectively fuse various reference information, which can obtain superior global and local optimization performance. Additionally, to improve the diversity of the algorithm, a dynamic adjustment method using the grouping coefficient $r$ for the convergence rate is put forward. This method makes the algorithm have a more appropriate convergence rate while improving the convergence precision and enhancing the performance of the algorithm. Finally, the algorithm is used to optimize a neural network. The convergence condition and convergence rate of the algorithm are assessed by theoretical analysis and simulation experiments. The results show that ICPSO has more advantages in its diversity and the adjustment of the convergence rate compared to other related algorithms. Regarding neural network optimization, the training speed and optimization precision of the ICPSO-BP neural network are the highest, which has reached the best and average level of classification accuracy 98.5%, 96.3% for 20 iterations in Iris, and 98.7%, 95.1% in Wine. Its average iteration times score the best in five problems out of six.

In this paper, a model-order reduction (MOR) technique with the advantage of critical frequency preservation capability is proposed using the particle swarm optimization (PSO). The new approach is capable of simplifying single-input single-output (SISO) systems as well as multi-input multi-output (MIMO) systems. If critical frequency preservation is desired, then this objective is achieved by retaining the exact critical frequencies of the full-order model as a subset in the reduced-order model. Otherwise, the reduction process is proceeded without such restriction. The reduction process is performed using the PSO technique to determine all of the necessary parameters in the reduced model. Determining the reduced-order model is performed based on minimizing the mean square error between the outputs of the original full-order model and the outputs of the reduced model. For method evaluation and validation, the proposed technique was applied to different models and compared with some of the well-known methods and recently published work for MOR. Results' comparison shows clearly the superiority of the proposed technique in terms of quality performance and accuracy of substructure preservation.

In this paper, the hybrid direct torque control (DTC) technique is proposed for controlling the speed of the induction motor (IM). The hybrid technique is the combination of an enhanced firefly algorithm (FA) and the adaptive neuro fuzzy inference system (ANFIS) technique. The performance of the FA is improved by updating the randomized parameter. Here, the genetic algorithm (GA) is utilized for updating the parameter and improved the performance of the FA. Initially, the actual torque and the change of toque are applied to the input of the enhanced FA and form the electromagnetic torque as a dataset. The output of the enhanced FA is given to the input of the ANFIS which is determined from the output of interference system. The dynamic behavior of the IM is analyzed in terms of the parameters such as the speed, torque, flux, etc. Based on the parameters, the motor speed is controlled by utilizing the proposed technique. Then the output of the ANFIS is translated into the stator voltage which is given to the input of the support vector machine (SVM). After that, the control signal is generated for controlling the speed of the IM. The proposed hybrid technique is implemented in the Matlab/Simulink platform. The performance analysis of the proposed method is demonstrated and contrasted with the existing techniques such as without controller, particle swarm optimization (PSO)-based ANFIS and FA-ANFIS controller.

This paper proposes an efficient design technique for two commonly used VLSI circuits, namely, CMOS current mirror load-based differential amplifier circuit and CMOS two-stage operational amplifier. The hybrid evolutionary method utilized for these optimal designs is random particle swarm optimization with differential evolution (RPSODE). Random PSO utilizes the weighted particles for monitoring the search directions. DE is a robust evolutionary technique. It has demonstrated an exclusive performance for the optimization problems which are continuous and global but suffers from the uncertainty issues. PSO is a robust optimization method but suffers from sub-optimality problem. This paper effectively hybridizes the random PSO and DE to remove the limitations related to both the techniques individually. In this paper, RPSODE is employed to optimize the sizes of the MOS transistors to reduce the overall area taken by the circuit while satisfying the design constraints. The results obtained from RPSODE technique are validated in SPICE environment. SPICE-based simulation results justify that RPSODE is a much better technique than other formerly reported methods for the designs of the above mentioned circuits in terms of MOS area, gain, power dissipation, etc.

In this study, field-programmable gate array (FPGA)-based hardware implementation of the wavelet neural network (WNN) training using particle swarm optimization (PSO) and improved particle swarm optimization (iPSO) algorithms are presented. The WNN architecture and wavelet activation function approach that is proper for the hardware implementation are suggested in the study. Using the suggested architecture and training algorithms, test operations are implemented on two different dynamic system recognition problems. From the test results obtained, it is observed that WNN architecture generalizes well and the activation function suggested has approximately the same success rate with the wavelet function defined in the literature. In the FPGA-based implementation, IEEE 754 floating-point number format is used. Experimental tests are done on Xilinx Artix 7 xc7a100t-1csg324 using ISE Webpack 14.7 program.

Ultrasound (US) imaging is the initial phase in the preliminary diagnosis for the treatment of kidney diseases, particularly to estimate kidney size, shape and position, to give information about kidney function, and to help in diagnosis of abnormalities like cysts, stones, junctional parenchyma and tumors which is shown in Figs. 7–9. This study proposes Grey Level Co-occurrence Matrix (GLCM)-based Probabilistic Principal Component Analysis (PPCA) and Artificial Neural Network (ANN) method for the classification of kidney images. Grey Wolf Optimization (GWO) is used to update the current positions of abnormal kidney images in the discrete searching space, thus getting the optimal feature subset for better classification purposes based on Feed Forward Neural Network (FFNN). The scanned image is pre-processed and the required features are extracted by GLCM, among those, some features are selected by PPCA. Feed Forward Back propagation Neural Network (FFBN) is used to classify the normalities and abnormalities in the part of kidney images. The proposed methodology is implemented in MATLAB platform and the analyzed result produces 98% accuracy using GWO-FFBN technique.