Search

The extreme ultraviolet (EUV) photolithography process is a cornerstone of semiconductor manufacturing and operates under demanding precision standards realized via nanometer-level overlay (OVL) error modeling. This procedure allows the machine to anticipate and correct OVL errors before impacting the wafer, thereby facilitating near-optimal image exposure while simultaneously minimizing the overall OVL error. Such models are usually high dimensional and exhibit rigorous statistical phenomena such as collinearities that play a crucial role in the process of tuning their parameters. Ordinary least squares (OLS) is the most widely used method for parameters tuning of overlay models, but in most cases it fails to compensate for such phenomena. In this paper, we propose the usage of ridge regression, a widely known machine learning (ML) algorithm especially suitable for datasets that exhibit high multicollinearity. The proposed method was applied in perturbed data from a 300 mm wafer fab, and the results show reduced residuals when ridge regression is applied instead of OLS. [ABSTRACT FROM AUTHOR]

Aiming at the problem of poor uniformity of maize sowing caused by ground wheel slip, an electronic control seed-metering system (ECSMS) for maize single seed precision sowing was designed and a mathematical model for motor control of the ECSMS was determined. The PID parameters were set by Z-N method and fuzzy control. The fuzzy PID control design and Simulink simulation were completed by MATLAB, which reduced response time of the system by 0.23 s and improved the control accuracy. Experiments on the JPS-12 test bench show that the qualification index (QI) of maize seed-metering device with the ECSMS increases by 4.47%, the multiples index (MI) decreases by 1.96%, the miss index (MIX) decreases by 2.81%, and the coefficient of variation (CV) of qualified seed spacing decreases by 5.06%, and the sowing uniformity has been greatly improved. Test results of the soil-tank test bench show that the system has good sowing uniformity and stability. And the QI is 96.74%, the MI is 2.15%, the MIX is 1.10%, and the CV of qualified seed spacing is 16.24%. Under different setting seed spacing and different sowing operation speed, the change range of seeding quality index was within 10%. The results of field sowing test show that the QI was 84.21%, the MI was 2.63%, the MIX was 7.89%, and the CV of qualified seed spacing was 22.15%, which meet the requirements of JB/T 10293-2013 ‘Specification for single seed planters (precision planters)’ and the agronomic requirements for maize precision sowing. The system runs stably and reliably in practical operation and has good operation performance. [ABSTRACT FROM AUTHOR]

Multiple-point geostatistics (MPS) is an established tool for the uncertainty quantification of Earth systems modeling, particularly when dealing with the complexity and heterogeneity of geological data. This study presents a novel pixel-based MPS method for modeling spatial data using advanced machine-learning algorithms. Pixel-based multiple-point simulation implies the sequential modeling of individual points on the simulation grid, one at a time, by borrowing spatial information from the training image and honoring the conditioning data points. The developed methodology is based on the mapping of the training image patterns database using the t-Distributed Stochastic Neighbor Embedding (t-SNE) algorithm for dimensionality reduction, and the clustering of patterns by applying the Density-based Spatial Clustering of Applications with Noise (DBSCAN) algorithm, as an efficient unsupervised classification technique. For the automation, optimization, and input parameter tuning, multiple stages are implemented, including entropy-based determination of the template size and a k-nearest neighbors search for clustering parameter selection, to ensure the proposed method does not require the user's interference. The proposed model is validated using synthetic two- and three-dimensional datasets, both for conditional and unconditional simulations, and runtime information is provided. Finally, the method is applied to a case study gold mine for stochastic orebody modeling. To demonstrate the computational efficiency and accuracy of the proposed method, a two-dimensional training image with 101 by 101 pixels is simulated for 100 conditional realizations in 453 s (~4.5 s per realization) using only 361 hard data points (~3.5% of the simulation grid), and the resulting average simulation has a good visual match and only an 11.8% pixel-wise mismatch with the training image. [ABSTRACT FROM AUTHOR]

The extreme ultraviolet (EUV) photolithography process is a cornerstone of semiconductor manufacturing and operates under demanding precision standards realized via nanometer-level overlay (OVL) error modeling. This procedure allows the machine to anticipate and correct OVL errors before impacting the wafer, thereby facilitating near-optimal image exposure while simultaneously minimizing the overall OVL error. Such models are usually high dimensional and exhibit rigorous statistical phenomena such as collinearities that play a crucial role in the process of tuning their parameters. Ordinary least squares (OLS) is the most widely used method for parameters tuning of overlay models, but in most cases it fails to compensate for such phenomena. In this paper, we propose the usage of ridge regression, a widely known machine learning (ML) algorithm especially suitable for datasets that exhibit high multicollinearity. The proposed method was applied in perturbed data from a 300 mm wafer fab, and the results show reduced residuals when ridge regression is applied instead of OLS.

Multiple-point geostatistics (MPS) is an established tool for the uncertainty quantification of Earth systems modeling, particularly when dealing with the complexity and heterogeneity of geological data. This study presents a novel pixel-based MPS method for modeling spatial data using advanced machine-learning algorithms. Pixel-based multiple-point simulation implies the sequential modeling of individual points on the simulation grid, one at a time, by borrowing spatial information from the training image and honoring the conditioning data points. The developed methodology is based on the mapping of the training image patterns database using the t-Distributed Stochastic Neighbor Embedding (t-SNE) algorithm for dimensionality reduction, and the clustering of patterns by applying the Density-based Spatial Clustering of Applications with Noise (DBSCAN) algorithm, as an efficient unsupervised classification technique. For the automation, optimization, and input parameter tuning, multiple stages are implemented, including entropy-based determination of the template size and a k-nearest neighbors search for clustering parameter selection, to ensure the proposed method does not require the user’s interference. The proposed model is validated using synthetic two- and three-dimensional datasets, both for conditional and unconditional simulations, and runtime information is provided. Finally, the method is applied to a case study gold mine for stochastic orebody modeling. To demonstrate the computational efficiency and accuracy of the proposed method, a two-dimensional training image with 101 by 101 pixels is simulated for 100 conditional realizations in 453 s (~4.5 s per realization) using only 361 hard data points (~3.5% of the simulation grid), and the resulting average simulation has a good visual match and only an 11.8% pixel-wise mismatch with the training image.

Research on using energy storage devices in ships is actively underway globally to reduce marine environmental pollution. This is due to the fact that existing internal combustion engines emit CO2 continuously. In this study, we investigated a control parameter optimization technique to reduce overshoot during the CC charging of lithium-ion batteries, which are applicable as energy storage devices for ships. We modeled a synchronous buck converter, a lithium-ion battery, and a PID controller using MATLAB/Simulink. Then, we performed a search for the optimal parameters of the PID controller and conducted simulations by varying the state of charge (SOC) values of the lithium-ion battery to 50, 70, and 80.We compared the simulation results of the proposed control method with those of the existing Ziegler-Nichols PID controller, and confirmed that the proposed method effectively suppressed 0.5 A overshoot during the charging of the lithium-ion battery. [ABSTRACT FROM AUTHOR]

Copyright of Machine Tool & Hydraulics is the property of Guangzhou Mechanical Engineering Research Institute (GMERI) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

A methodology for enabling the implementation of the Digital Twins (DTs) of industrial robots and complex machines is presented. The enabled DT can provide a series of benefits, for instance when combined with the degradation curves of critical health indicators can allow predicting the robots' RUL. This paper suggests a systematic and generic methodology to address challenges such as (1) the definition of the physics-based model parameters for accurate DTs, (2) selection of the parameters to tune and the frequency of their tuning to capture the physical changes in the digital world, (3) calculation of new modeling parameters values based on the collected filed data and their automated propagation to the digital model. A software module to implement these functionalities was developed, whereas the testing and validation of the module were held for an industrial robotic manipulator for a manufacturing application. The results prove that the methodology is generic to accommodate the desired granularity per case, and that the tuning of the digital model ensures realistic DTs, which sets the foundation for physics-based predictive maintenance tools. [ABSTRACT FROM AUTHOR]

The (1 + (λ , λ)) genetic algorithm is a younger evolutionary algorithm trying to profit also from inferior solutions. Rigorous runtime analyses on unimodal fitness functions showed that it can indeed be faster than classical evolutionary algorithms, though on these simple problems the gains were only moderate. In this work, we conduct the first runtime analysis of this algorithm on a multimodal problem class, the jump functions benchmark. We show that with the right parameters, the (1 + (λ , λ)) GA optimizes any jump function with jump size 2 ≤ k ≤ n / 4 in expected time O (n (k + 1) / 2 e O (k) k - k / 2) , which significantly and already for constant k outperforms standard mutation-based algorithms with their Θ (n k) runtime and standard crossover-based algorithms with their O ~ (n k - 1) runtime guarantee. For the isolated problem of leaving the local optimum of jump functions, we determine provably optimal parameters that lead to a runtime of (n / k) k / 2 e Θ (k) . This suggests some general advice on how to set the parameters of the (1 + (λ , λ)) GA, which might ease the further use of this algorithm. [ABSTRACT FROM AUTHOR]

This paper proposes a method that combines active disturbance rejection control (ADRC) and adaptive fuzzy sliding mode control (AFSMC), which is beneficial for the optoelectronic platform to enhance the target tracking capability. A servo system model based on the LuGre friction is first established. The AFSMC controller estimates the unknown part of the platform, and the fuzzy approximator can reduce chattering. Then, an ADRC controller based on Back-Propagation neural network tuning is designed and compared with the empirical method, which makes the system's tracking accuracy higher. Lyapunov's theorem and Barbara's lemma are forceful methods to prove engineering stability. Simulations illustrate that the influence of external disturbances on the optoelectronic platform can be suppressed, thereby enhancing the disturbance isolation of the controller. • The control scheme with double speed loop can improve tracking performance. • The adaptive fuzzy sliding mode controller can estimate model nonlinearities and torque disturbances. • The ADRC controller using neural network tuning can suppress external disturbances faster than traditional tuning. • The simulations show that the control method is effective. [ABSTRACT FROM AUTHOR]

Background Spatial transcriptomics (ST) combines stained tissue images with spatially resolved high-throughput RNA sequencing. The spatial transcriptomic analysis includes challenging tasks like clustering, where a partition among data points (spots) is defined by means of a similarity measure. Improving clustering results is a key factor as clustering affects subsequent downstream analysis. State-of-the-art approaches group data by taking into account transcriptional similarity and some by exploiting spatial information as well. However, it is not yet clear how much the spatial information combined with transcriptomics improves the clustering result. Results We propose a new clustering method, Stardust , that easily exploits the combination of space and transcriptomic information in the clustering procedure through a manual or fully automatic tuning of algorithm parameters. Moreover, a parameter-free version of the method is also provided where the spatial contribution depends dynamically on the expression distances distribution in the space. We evaluated the proposed methods results by analyzing ST data sets available on the 10x Genomics website and comparing clustering performances with state-of-the-art approaches by measuring the spots' stability in the clusters and their biological coherence. Stability is defined by the tendency of each point to remain clustered with the same neighbors when perturbations are applied. Conclusions Stardust is an easy-to-use methodology allowing to define how much spatial information should influence clustering on different tissues and achieving more stable results than state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

The flower pollination algorithm (FPA) is a highly efficient metaheuristic optimization algorithm that is inspired by the pollination process of flowering species. FPA is characterised by simplicity in its formulation and high computational performance. Previous studies on FPA assume fixed parameter values based on empirical observations or experimental comparisons of limited scale and scope. In this study, a comprehensive effort is made to identify appropriate values of the FPA parameters that maximize its computational performance. To serve this goal, a simple non-iterative, single-stage sampling tuning method is employed, oriented towards practical applications of FPA. The tuning method is applied to the set of 28 functions specified in IEEE-CEC'13 for real-parameter single-objective optimization problems. It is found that the optimal FPA parameters depend significantly on the objective functions, the problem dimensions and affordable computational cost. Furthermore, it is found that the FPA parameters that minimize mean prediction errors do not always offer the most robust predictions. At the end of this study, recommendations are made for setting the optimal FPA parameters as a function of problem dimensions and affordable computational cost. [ABSTRACT FROM AUTHOR]

The quad tilt rotor (QTR) has complex dynamics characteristics, and the environmental factors have a great influence on it. This increases the difficulty of its control especially in transition mode. To solve this problem, the design of the controller based on active disturbance rejection control (ADRC) with a novel tuning algorithm is proposed in this paper. The aerodynamic models of propeller, wing, vertical tail and fuselage are build respectively by using the idea of component modeling. The pitch channel of the linearized flight dynamic model is provided for the control system. A simple tuning method of active disturbance rejection control for the quad tilt rotor in transition process that achieves high performance and good robustness is presented. The proposed method makes ADRC become easy to tune and more practical. The problem of parameter tuning is turned into a multi-objective optimization problem, and using radial basis function (RBF) neural network with particle swarm optimization algorithm (PSO) and bacterial foraging optimization algorithm (BFO) hybrid algorithm tuning method (NBPO) to fit the tuning rules. We introduce the control input, the overshoot and rise time of the system into the fitness function. The local and global optimal solutions are introduced into the chemotaxis and migration to improve the information exchange ability of BFO. The correctness and effectiveness of the NBPO tuning method were verified by numerical simulation results, compared with the one parameter tuning method (OPM) and PID, the results showed that the NBPO tuning method can greatly improve the control performance of the system.

This paper demonstrates a recapitulated historic evolution further to a future overview of all vehicular ad-hoc network (VANET) routing problems that concern either directly related routing tasks or targeting a set of diverse routing-related techniques with the aid of the bio-inspired approaches. In this lecture, we serialize, in a synchronous observation, the evolution and tendencies of the VANET routing problem's solving simultaneously with the emergence of different classes of nature-based meta-heuristics, by bringing a proposed taxonomy of different major VANET routing problems seen their nature, studied range and metaheuristic types used for their optimization. Then, we follow with a visionary deduction of the other appearing routing issues of VANETs that can be approached or already began to be solved by nature-inspired optimization algorithms. Noting that each spread routing problem is illustrated with notable related works, describing initially realized conventional protocols to vulgarize different routing modules, then detailing bio-inspired protocols for VANET routing to explain the utility of nature-inspired optimization techniques. The motivation of this work came from the lack of a reference classifying the VANET-related routing problems within the notion of nature-inspired optimization. That's further to giving and up-to-date literature on the context for opening out a visionary opinion on the tendencies of either emerging recent bio-inspired optimization approaches or the different metaheuristic-based combinations on specific VANET routing problems. [ABSTRACT FROM AUTHOR]

The continuous penetration of renewable energy resources (RES) into the energy mix and the transition of the traditional electric grid towards a more intelligent, flexible and interactive system, has brought electrical load forecasting to the foreground of smart grid planning and operation. Predicting the electric load is a challenging task due to its high volatility and uncertainty, either when it refers to the distribution system or to a single household. In this paper, a novel methodology is introduced which leverages the advantages of the state-of-the-art deep learning algorithms and specifically the Convolution Neural Nets (CNN). The main feature of the proposed methodology is the exploitation of the statistical properties of each time series dataset, so as to optimize the hyper-parameters of the neural network and in addition transform the given dataset into a form that allows maximum exploitation of the CNN algorithm's advantages. The proposed algorithm is compared with the LSTM (Long Short Term Memory) technique which is the state of the art solution for electric load forecasting. The evaluation of the algorithms was conducted by employing three open-source, publicly available datasets. The experimental results show strong evidence of the effectiveness of the proposed methodology. [ABSTRACT FROM AUTHOR]

The frequency stability in the sending-end network with renewable energy generating units should be paid attention especially for an asynchronous interconnection system. When the DC blocking fault occurs in the system, the problem of high frequency in the sending-end network can be suppressed by using the frequency limit controller (FLC). This study introduces the structure and the parameters tuning method of the FLC, and the parameters optimisation method is proposed to avoid FLC acting repeatedly. In the study, a case is studied, and the results show that the FLC is important in the sending-end network. Finally, aiming at the coordination problem between multiple FLCs, a control strategy based on FLC influence coefficient is proposed in the study, and the strategy can suppress the over regulation effectively.

This paper presents a predator-prey pigeon-inspired optimization (PPPIO) algorithm for an automatic landing system of a fixed-wing unmanned aerial vehicle (UAV) in the longitudinal plane. A pitch command autopilot and two types of approach power compensators are presented and evaluated in automatic landing. The design of a glide slope command system and an approach power compensator are converted to a finite-dimensional optimization problem. The longitudinal flight controller parameters are optimized by the proposed PPPIO algorithm. The differences between the two proposed approach power compensators are also analyzed. The proposed optimization process can guarantee the control gains vector converge to an approximate optimal solution, and it is computationally much more efficient. Simulation results are presented to demonstrate that this approach helps solve control system optimization problems for different criteria and attains a rather accurate result. As verified by these simulation results, the proposed automatic landing system can help improve UAV's performance during the landing phase. [ABSTRACT FROM AUTHOR]

Aiming at parameter tuning of fractional order PIλ controller of PMSM. this paper proposed a method , which combined the frequency-domain method and moths fire optimization algorithm. This paper used the fractional order model of PMSM as the controlled object. Firstly, it used the frequency-domain method, the it obtained the equation of the controller according to the relative stability of the system and the robustness of the gain variation. After that, it solved the parameters of fractional order P1Acontroller by combining the image of the equation and optimized these parameters by using moths fire optimization algorithm. The simulation and experiment results show that the fractional order controller can reduce the overshoot of the system, improve the rapidity and anti-interference ability of the system, and has a certain degree of robustness. [ABSTRACT FROM AUTHOR]

Copyright of Control Theory & Applications / Kongzhi Lilun Yu Yinyong is the property of Editorial Department of Control Theory & Applications and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The frequency stability in the sending-end network with renewable energy generating units should be paid attention especially for an asynchronous interconnection system. When the DC blocking fault occurs in the system, the problem of high frequency in the sending-end network can be suppressed by using the frequency limit controller (FLC). This study introduces the structure and the parameters tuning method of the FLC, and the parameters optimisation method is proposed to avoid FLC acting repeatedly. In the study, a case is studied, and the results show that the FLC is important in the sending-end network. Finally, aiming at the coordination problem between multiple FLCs, a control strategy based on FLC influence coefficient is proposed in the study, and the strategy can suppress the over regulation effectively. [ABSTRACT FROM AUTHOR]

This study focused on the use of the non‐dominated sorting genetic algorithm (NSGA‐II) to achieve an optimal power system stabiliser (PSS) parameters for a given operating point with a renewable source of energy so as to increase the system damping and guarantee enough stability margin. The parameters tuning was formulated using an eigenvalue‐based multi‐objective function. In recent years, the changeability and fluctuation of the wind power injected into the network have led to new challenges in small signal stability (SSS). These wind speed change and load demand change perturbations take place routinely and cause the variation of the operating conditions. However, as the conventional PSS is conceived for a fixed operating point in order to obtain the linearised transfer function model, it cannot yield good results when the operating range is too wide. To this end, the adaptive neuro‐fuzzy inference system was proposed to estimate the stabiliser parameters in real time after a learning phase. The nine‐bus Western System Coordinating Council and the obtained simulations results were assessed using Matlab/Simulink package. The validity of the proposed methodology was checked through the PSS parameters evolution simulation for daily load forecast curves and monthly wind speed prediction curves. [ABSTRACT FROM AUTHOR]

The continuous penetration of renewable energy resources (RES) into the energy mix and the transition of the traditional electric grid towards a more intelligent, flexible and interactive system, has brought electrical load forecasting to the foreground of smart grid planning and operation. Predicting the electric load is a challenging task due to its high volatility and uncertainty, either when it refers to the distribution system or to a single household. In this paper, a novel methodology is introduced which leverages the advantages of the state-of-the-art deep learning algorithms and specifically the Convolution Neural Nets (CNN). The main feature of the proposed methodology is the exploitation of the statistical properties of each time series dataset, so as to optimize the hyper-parameters of the neural network and in addition transform the given dataset into a form that allows maximum exploitation of the CNN algorithm’s advantages. The proposed algorithm is compared with the LSTM (Long Short Term Memory) technique which is the state of the art solution for electric load forecasting. The evaluation of the algorithms was conducted by employing three open-source, publicly available datasets. The experimental results show strong evidence of the effectiveness of the proposed methodology.

Owing to its significant roles in computer vision applications, human face tracking has drawn extensive attention in recent years. Most researchers solve face tracking using particle filter, meanshift and their derivatives. Unlike the traditional methods, in this study, face tracking is treated as an optimisation problem and a new meta‐heuristic optimisation algorithm, differential harmony search (DHS), is introduced to solve face tracking problems. We compare the speed and accuracy of the proposed method with particle filter, meanshift and improved harmony search. Experimental results show that DHS‐based tracker is faster and more accurate and it is easy to handle the parameters tuning. Furthermore, to improve the reliability of tracking, multiple visual cues are applied to DHS‐based tracking system and experimental results demonstrate the increased robustness achieved by fusing multiple cues.

Abstract This paper presents a parameters tuning method based on the genetic algorithm (GA) for an active disturbance rejection control (ADRC) of a three-axis inertially stabilized platform (ISP) with imaging sensors. To improve the stabilization accuracy and robustness of an aerial ISP under multi-source disturbances environment, an ADRC control scheme is first proposed. Then, to accurately identify and tune the parameters in the ADRC controller, a GA-based parameters tuning method is proposed. In this way, the performance of the ADRC is superior to the empirical method. To validate the proposed method, the simulations and experiments are carried out. The results show that the proposed ADRC with GA-based parameters tuning method has significant disturbance rejection ability which can improve the stabilization accuracy obviously. Compared with the ADRC with empirically tuning method, the stabilization error (RMS) under movable base is decreased up to 50.09%. Highlights • An ADRC control scheme is proposed to improve the stabilization accuracy and disturbance rejection ability of an ISP. • A GA-based parameters tuning method is proposed to accurately identify and tune the parameters of the ADRC controller. • The empirical parameters tuning method and the proposed GA-based method are both applied in the work as a comparison. • Simulations and experiments are carried out to validate the proposed method. [ABSTRACT FROM AUTHOR]

Copyright of Computer Measurement & Control is the property of Magazine Agency of Computer Measurement & Control and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Modern scientific applications are composed of various methods, techniques and models to solve complicated problems. Such composite applications commonly are represented as workflows. Workflow scheduling is a well-known optimization problem, for which there is a great amount of solutions. Most of the algorithms contain parameters, which affect the result of a method. Thus, for the efficient scheduling it is important to tune parameters of the algorithms. Moreover, performance models, which are used for the estimation of obtained solutions, are crucial parts of workflow scheduling. In this work we present a combined approach for automatic parameters tuning and performance models construction in the background of the WMS lifecycle. Algorithms tuning is provided by hyper-heuristic genetic algorithm, whereas models construction is performed via symbolic regression methods. Developed algorithm was evaluated using CLAVIRE platform and is applicable for any distributed computing systems to optimize the execution of composite applications. [ABSTRACT FROM AUTHOR]

This paper presents an adaptive PSO algorithm whose numerical parameters can be updated following a scheduled protocol respecting some known criteria of convergence in order to enhance the chances to reach the global optimum of a hard combinatorial optimization problem, such those encountered in global optimization problems of composite laminates. Some examples concerning hard design problems are provided, showing the effectiveness of the approach.

This paper concerns with the parameters tuning of active disturbance rejection control (ADRC) for a class of nonlinear systems with sampling rate not fast enough. The theoretical results show the quantitative relationship between the sampling rate, the parameters of ADRC, the size of uncertainties in system and the properties of the closed-loop system. Furthermore, the capability of the sampled-data ADRC under given sampling rate is quantitatively discussed. [ABSTRACT FROM AUTHOR]

The process of tuning the parameters that characterize evolutionary algorithms is difficult and can be time consuming. This paper presents a self-tuning algorithm for dynamically updating the crossover and mutation probabilities during a run of genetic programming. The genetic operators that are considered in this work are the geometric semantic genetic operators introduced by Moraglio et al. Differently from other existing self-tuning algorithms, the proposed one works by assigning a (different) crossover and mutation probability to each individual of the population. The experimental results we present show the appropriateness of the proposed self-tuning algorithm: on seven different test problems, the proposed algorithm finds solutions of a quality that is better than, or comparable to, the one achieved using the best known values for the geometric semantic crossover and mutation rates for the same problems. Also, we study how the mutation and crossover probabilities change during the execution of the proposed self-tuning algorithm, pointing out an interesting insight: mutation is basically the only operator used in the exploration phase, while crossover is used for exploitation, further improving good quality solutions. [ABSTRACT FROM AUTHOR]