• International Journal of Control, Automation, and Systems
• /
• v.3 no.2
• /
• pp.183-194
• /
• 2005

In this study, we introduce an advanced architecture of genetically optimized Hybrid Fuzzy Neural Networks (gHFNN) and develop a comprehensive design methodology supporting their construction. A series of numeric experiments is included to illustrate the performance of the networks. The construction of gHFNN exploits fundamental technologies of Computational Intelligence (CI), namely fuzzy sets, neural networks, and genetic algorithms (GAs). The architecture of the gHFNNs results from a synergistic usage of the genetic optimization-driven hybrid system generated by combining Fuzzy Neural Networks (FNN) with Polynomial Neural Networks (PNN). In this tandem, a FNN supports the formation of the premise part of the rule-based structure of the gHFNN. The consequence part of the gHFNN is designed using PNNs. We distinguish between two types of the linear fuzzy inference rule-based FNN structures showing how this taxonomy depends upon the type of a fuzzy partition of input variables. As to the consequence part of the gHFNN, the development of the PNN dwells on two general optimization mechanisms: the structural optimization is realized via GAs whereas in case of the parametric optimization we proceed with a standard least square method-based learning. To evaluate the performance of the gHFNN, the models are experimented with a representative numerical example. A comparative analysis demonstrates that the proposed gHFNN come with higher accuracy as well as superb predictive capabilities when comparing with other neurofuzzy models.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.4
• /
• pp.1603-1623
• /
• 2020

Multiple Mobile Robots System (MMRS) has shown many attractive features in lots of real-world applications that motivate their rapid and wide diffusion. In MMRS, the Cooperative Localization (CL) is the basis and premise of its high-performance task. However, the statistical characteristics of the system noise should be already known in traditional CL algorithms, which is difficult to satisfy in actual MMRS because of the numerous of disturbances form the complex external environment. So the CL accuracy will be reduced. To solve this problem, an improved Adaptive Active Cooperative Localization (A²CL) algorithm based on information optimization strategy for MMRS is proposed in this manuscript. In this manuscript, an adaptive information fusion algorithm based on the variance component estimation under Extended Kalman filter (VCEKF) method for MMRS is introduced firstly to enhance the robustness and accuracy of information fusion by estimating the covariance matrix of the system noise or observation noise in real time. Besides, to decrease the effect of observation uncertainty on CL accuracy further, an observation optimization strategy based on information theory, the Model Predictive Control (MPC) strategy, is used here to maximize the information amount from observations. And semi-physical simulation experiments were carried out to verity the A²CL algorithm's performance finally. Results proved that the presented A²CL algorithm based on information optimization strategy for MMRS cannot only enhance the CL accuracy effectively but also have good robustness.

• Geomechanics and Engineering
• /
• v.36 no.3
• /
• pp.259-276
• /
• 2024

The undrained shear strength is widely acknowledged as a fundamental mechanical property of soil and is considered a critical engineering parameter. In recent years, researchers have employed various methodologies to evaluate the shear strength of soil under undrained conditions. These methods encompass both numerical analyses and empirical techniques, such as the cone penetration test (CPT), to gain insights into the properties and behavior of soil. However, several of these methods rely on correlation assumptions, which can lead to inconsistent accuracy and precision. The study involved the development of innovative methods using extreme gradient boosting (XGB) to predict the pile set-up component "A" based on two distinct data sets. The first data set includes average modified cone point bearing capacity (q_t), average wall friction (f_s), and effective vertical stress (σ_vo), while the second data set comprises plasticity index (PI), soil undrained shear cohesion (S_u), and the over consolidation ratio (OCR). These data sets were utilized to develop XGBoost-based methods for predicting the pile set-up component "A". To optimize the internal hyperparameters of the XGBoost model, four optimization algorithms were employed: Particle Swarm Optimization (PSO), Social Spider Optimization (SSO), Arithmetic Optimization Algorithm (AOA), and Sine Cosine Optimization Algorithm (SCOA). The results from the first data set indicate that the XGBoost model optimized using the Arithmetic Optimization Algorithm (XGB - AOA) achieved the highest accuracy, with R2 values of 0.9962 for the training part and 0.9807 for the testing part. The performance of the developed models was further evaluated using the RMSE, MAE, and VAF indices. The results revealed that the XGBoost model optimized using XGBoost - AOA outperformed other models in terms of accuracy, with RMSE, MAE, and VAF values of 0.0078, 0.0015, and 99.6189 for the training part and 0.0141, 0.0112, and 98.0394 for the testing part, respectively. These findings suggest that XGBoost - AOA is the most accurate model for predicting the pile set-up component.

• International Journal of Contents
• /
• v.17 no.3
• /
• pp.74-83
• /
• 2021

A location-aware algorithm is proposed in this study to optimize the system performance of distributed systems for processing big data with low data reliability and application performance. Compared with previous algorithms, the location-aware data block placement algorithm uses data block placement and node data recovery strategies to improve data application performance and reliability. Simulation and actual cluster tests showed that the location-aware placement algorithm proposed in this study could greatly improve data reliability and shorten the application processing time of I/O interfaces in real-time.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.6
• /
• pp.367-374
• /
• 2022

The acceleration of neural networks has become an important topic in the field of computer vision. An accelerator is absolutely necessary for accelerating the lightweight model. Most accelerator-supported operators focused on direct convolution operations. If the accelerator does not provide GEMM operation, it is mostly replaced by CPU operation. In this paper, we proposed an optimization technique for 2-stage tiling-based GEMM routines on VTA. We improved performance of the matrix multiplication routine by maximizing the reusability of the input matrix and optimizing the operation pipelining. In addition, we applied the proposed technique to the DarkNet framework to check the performance improvement of the matrix multiplication routine. The proposed GEMM method showed a performance improvement of more than 2.4 times compared to the non-optimized GEMM method. The inference performance of our DarkNet framework has also improved by at least 2.3 times.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.12
• /
• pp.5972-5989
• /
• 2019

With the onset of the big data age, data is growing exponentially, and the issue of how to optimize large-scale data processing is especially significant. Large-scale global optimization (LSGO) is a research topic with great interest in academia and industry. Spark is a popular cloud computing framework that can cluster large-scale data, and it can effectively support the functions of iterative calculation through resilient distributed datasets (RDD). In this paper, we propose a hybrid mechanism of particle swarm optimization (PSO) and differential evolution (DE) algorithms based on Spark (SparkPSODE). The SparkPSODE algorithm is a parallel algorithm, in which the RDD and island models are employed. The island model is used to divide the global population into several subpopulations, which are applied to reduce the computational time by corresponding to RDD's partitions. To preserve population diversity and avoid premature convergence, the evolutionary strategy of DE is integrated into SparkPSODE. Finally, SparkPSODE is conducted on a set of benchmark problems on LSGO and show that, in comparison with several algorithms, the proposed SparkPSODE algorithm obtains better optimization performance through experimental results.

• Journal of Power Electronics
• /
• v.19 no.5
• /
• pp.1248-1258
• /
• 2019

This paper presents a moth-flame optimization (MFO)-based maximum power point tracking (MPPT) method for photovoltaic (PV) systems. The MFO algorithm is a new optimization method that exhibits satisfactory performance in terms of exploration, exploitation, local optima avoidance, and convergence. Therefore, the MFO algorithm is quite suitable for solving multiple peaks of PV systems under partial shading conditions (PSCs). The proposed MFO-MPPT is compared with four MPPT algorithms, namely the perturb and observe (P&O)-MPPT, incremental conductance (INC)-MPPT, particle swarm optimization (PSO)-MPPT and whale optimization algorithm (WOA)-MPPT. Simulation and experiment results demonstrate that the proposed algorithm can extract the global maximum power point (MPP) with greater tracking speed and accuracy under various conditions.

• Journal of Power Electronics
• /
• v.11 no.1
• /
• pp.105-111
• /
• 2011

By having accurate knowledge of the magnetic field distribution and the thrust calculation in linear synchronous motors, assessing the performance and optimization of the motor design are possible. In this paper, after carrying out a performance analysis of a single-sided wound secondary linear synchronous motor by varying the motor design parameters in a layer model and a d-q model, machine single- and multi-objective design optimizations are carried out to improve the thrust density of the motor based on the motor weight and the motor efficiency multiplied by its power factor by defining various objective functions including a flexible objective function. A genetic algorithm is employed to search for the optimal design. The results confirm that an overall improvement in the thrust mean, efficiency multiplied by the power factor, and thrust to the motor weight ratio are obtained. Several design conclusions are drawn from the motor analysis and the design optimization. Finally, a finite element analysis is employed to evaluate the effectiveness of the employed machine models and the proposed optimization method.

• Journal of Mechanical Science and Technology
• /
• v.19 no.5
• /
• pp.1080-1086
• /
• 2005

The preliminary design optimization of multi-stage spur gear reduction units has been a subject of considerable interest, since many high-performance power transmission applications (e.g., automotive and aerospace) require high-performance gear reduction units. There are multiple objectives in the optimal design of multi-stage spur gear reduction unit, such as minimizing the volume and maximizing the surface fatigue life. It is reasonable to formulate the design of spur gear reduction unit as a multi-objective optimization problem, and find an appropriate approach to solve it. In this paper an interactive physical programming approach is developed to place physical programming into an interactive framework in a natural way. Class functions, which are used to represent the designer's preferences on design objectives, are fixed during the interactive physical programming procedure. After a Pareto solution is generated, a preference offset is added into the class function of each objective based on whether the designer would like to improve this objective or sacrifice the objective so as to improve other objectives. The preference offsets are adjusted during the interactive physical programming procedure, and an optimal solution that satisfies the designer's preferences is supposed to be obtained by the end of the procedure. An optimization problem of three-stage spur gear reduction unit is given to illustrate the effectiveness of the proposed approach.

• Journal of the Korean Society for information Management
• /
• v.18 no.3
• /
• pp.29-40
• /
• 2001

In this paper, we suggest a query optimization algorithm to select the optimal processing method of an extended boolean query on inverted files. There can be a lot of methods for processing an extended boolean query according to the processing sequence oh the keywords con tamed in the query, In this sense, the problem of optimizing an extended boolean query it essentially that of optimizing the keyword sequence in the query. In this paper, we show that the problem is basically analogous to the problem of finding the optimal join order in database query optimization, and apply the ideas in the area to the problem solving. We establish the cost model for processing an extended boolean query and develop an algorithm to filled the optimal keyword-processing sequence based on the concept of keyword rank using the keyword selectivity and the access costs of inverted file. We prove that the method selected by the optimization algorithm is really optimum, and show, through experiments, that the optimal method is superior to the others in performance We believe that the suggested optimization algorithm will contribute to the significant enhancement of the information retrieval performance.