Selection Of Algorithm Parameters Research Articles

Validation Experiment of a Single-View Image-Sequence Algorithm to Identify Scale and Sea-State Characteristics

In applied science and engineering contexts, ocean free-surface wave-field characterization is an ongoing research area relevant to many diverse applications. The use of optical means for this characterization, in particular, is an appealing solution due to the promise of relatively high spatial resolution and modest cost (i.e., applying off-the-shelf still cameras or video cameras). This work investigates the validity of a previously published algorithm related to visible-wavelength ocean free-surface wave-field videos. The first part of the algorithm uses the video content to determine scale from a single-perspective, uncalibrated video. The second part of the algorithm applies the video content to determine sea-state characteristics, such as dominant wave period and wavelength. Due to the complications of obtaining well-characterized real-world data sets, algorithms proposed within the literature are not always validated experimentally, but the scientific community relies on the process of verification and validation to build confidence in emerging scientific contributions. This work addresses the need to assess the performance of the existing algorithm through validation experiments. Video recordings of approximate deep-water waves are collected in a controlled indoor environment to experimentally validate the algorithm, and a suite of postprocessing parameters is explored to identify the algorithm's sensitivities for a chosen unit problem. Recommendations for the algorithm parameter selection and an assessment of the algorithm efficacy are offered for researchers interested in the implementation of this algorithm.

Generalized Petrov-Galerkin time finite element weighted residual methodology for designing high-order unconditionally stable algorithms with controllable numerical dissipation

In this paper, a novel stabilized time-weighted residual methodology under the umbrella of Petrov-Galerkin time finite element formulation is developed to design a generalized computational framework, which permits unconditionally stable, high-order time accuracy, and features with controllable numerical dissipation for solving transient first-order systems. Various unconditionally stable (A/L-stable) algorithms can be readily obtained in the proposed framework having not only high-order accuracy but also controllable numerical dissipation in the high frequency. Quadratic and cubic basis functions are utilized to illustrate the specific design process of the proposed method, which consequently ends up with numerous third-/fifth-order time accurate algorithms, QUAD3(γ,ρ∞) and CUBE5(γ,ρ∞), with controllable numerical dissipation. Comparing with the well-known implicit Runge-Kutta (RK) family of algorithms, these newly developed QUAD3(γ,ρ∞) and CUBE5(γ,ρ∞) can (a) recover the Radau IIA3/RK3 and Radau IIA5/RK5 schemes by certain selection of algorithmic parameters (γ,ρ∞); (b) obtain numerous new algorithms with improved solution accuracy that is superior to the RK family of algorithms, and (c) has similar computational efficiency as that of the implicit RK family of algorithms. Several single/multi-degree of freedom (SDOF and MDOF) problems are investigated to validate the proposed developments. In addition, it is worth noting that the proposed methodology can also use high-order (not limited to the quadratic and cubic) basis functions to design more advanced schemes and can be integrated with high-order spatial discretization methods in the solution of space-time PDEs, such as isogeometric methods, SEM, Discontinuous Galerkin (DGM), p-versions FEM, etc.

Survey Analysis of Solar Power Generation Forecasting

Solar power is the conversion of sunlight into electricity using solar photovoltaic cells as a source of energy. There are various applications for solar power; here is information on PV cell generation. We seek to understand the behavior of solar power plants through the data generated by the photovoltaic modules and the power generation in different weather conditions in India. The goal of this survey is to give a thorough assessment and study of machine learning, deep learning and artificial intelligence. Artificial intelligence (AI) models as well as information preprocessing techniques, parameter selection algorithms and predictive performance evaluations are used in machine learning and deep learning models for predicting renewable energies. But in case of time series data we can predict only the errors using a linear regression model, we can also calculate things like root mean square error (RMSE), mean absolute error (MSE), mean bias error (MBE) and mean absolute percentage error (MAPE). By the analysis of weather condition also we can predict the consumption of current by solar for every 15 minutes, 1day, and 1week or even for 1 month and find the accuracy.

A gray wolf algorithm for feature and parameter selection of support vector classification

A gray wolf algorithm for feature and parameter selection of support vector classification

A gray wolf algorithm for feature and parameter selection of support vector classification

In classification problems, there are many data that contain a large number of features, some of which are irrelevant and cause confusion for the classifiers. The support vector classification (SVC) method is one of the most common methods used in classification. Feature selection, together with the parameters setting of SVC, such as the kernel parameter and the penalty parameter, significantly affects the classification performance of the SVC. In this study, the gray wolf optimisation (GWO) algorithm is proposed to improve feature selection and determine the optimal parameter values of SVC simultaneously. Based on several benchmark datasets for diseases, the experimental results show that the proposed method, FOGWO-SVC, is capable in selecting the best features with best parameters determination. Further, the comparative results demonstrate that the FOGWO-SVC is better or comparable than other competitor algorithms in terms of classification accuracy and feature reduction.

Development of tool selection process for milling of pocket features

In modern production, three-dimensional modeling of workpieces has become a logical stage in the development of the technological process. Engineering analysis, process design, CNC mill tool path design, final inspection of products and other aspects are done basing on 3D models and have become the norm in the manufacturing industry. This research aimed at deriving mathematical tools which could be used in the process of CAM software development and modernization. Structural and process related elements can be automatically recognized on the basis of a 3D model. English literature refers to such elements as features. A set of parameters necessary for the description of a pocket design feature characteristics was reviewed. Available process solutions for CNC machining of said feature were analyzed. Special attention was given to selection of the roughing and finishing mills, as well as roughing and finishing cut strategy development. A tool parameter selection algorithm was developed for CNC milling of a pocket feature.

An improved simulated annealing algorithm based on residual network for permutation flow shop scheduling

The permutation flow shop scheduling problem (PFSP), which is one of the most important scheduling types, is widespread in the modern industries. With the increase of scheduling scale, the difficulty and computation time of solving the problem will increase exponentially. Adding the knowledge to intelligent algorithms is a good way to solve the complex and difficult scheduling problems in reasonable time. To deal with the complex PFSPs, this paper proposes an improved simulated annealing (SA) algorithm based on residual network (SARes). First, this paper defines the neighborhood of the PFSP and divides its key blocks. Second, the Residual Network (ResNet) is used to extract and train the features of key blocks. And, the trained parameters are stored in the SA algorithm to improve its performance. Afterwards, some key operators, including the initial temperature setting and temperature attenuation function of SA algorithm, are also modified. After every new solution is generated, the parameters trained by the ResNet are used for fast ergodic search until the local optimal solution found in the current neighborhood. Finally, the most famous benchmarks including part of TA benchmark are selected to verify the performance of the proposed SARes algorithm, and the comparisons with the-state-of-art methods are also conducted. The experimental results show that the proposed method has achieved good results by comparing with other algorithms. This paper also conducts experiments on network structure design, algorithm parameter selection, CPU time and other problems, and verifies the advantages of SARes algorithm from the aspects of stability and efficiency.

A Survey of Machine Learning Models in Renewable Energy Predictions

The use of renewable energy to reduce the effects of climate change and global warming has become an increasing trend. In order to improve the prediction ability of renewable energy, various prediction techniques have been developed. The aims of this review are illustrated as follows. First, this survey attempts to provide a review and analysis of machine-learning models in renewable-energy predictions. Secondly, this study depicts procedures, including data pre-processing techniques, parameter selection algorithms, and prediction performance measurements, used in machine-learning models for renewable-energy predictions. Thirdly, the analysis of sources of renewable energy, values of the mean absolute percentage error, and values of the coefficient of determination were conducted. Finally, some possible potential opportunities for future work were provided at end of this survey.

Machine learning for a combined electroencephalographic anesthesia index to detect awareness under anesthesia.

Spontaneous electroencephalogram (EEG) and auditory evoked potentials (AEP) have been suggested to monitor the level of consciousness during anesthesia. As both signals reflect different neuronal pathways, a combination of parameters from both signals may provide broader information about the brain status during anesthesia. Appropriate parameter selection and combination to a single index is crucial to take advantage of this potential. The field of machine learning offers algorithms for both parameter selection and combination. In this study, several established machine learning approaches including a method for the selection of suitable signal parameters and classification algorithms are applied to construct an index which predicts responsiveness in anesthetized patients. The present analysis considers several classification algorithms, among those support vector machines, artificial neural networks and Bayesian learning algorithms. On the basis of data from the transition between consciousness and unconsciousness, a combination of EEG and AEP signal parameters developed with automated methods provides a maximum prediction probability of 0.935, which is higher than 0.916 (for EEG parameters) and 0.880 (for AEP parameters) using a cross-validation approach. This suggests that machine learning techniques can successfully be applied to develop an improved combined EEG and AEP parameter to separate consciousness from unconsciousness.

Genetic Algorithm with New Stochastic Greedy Crossover Operator for Protein Structure Folding Problem

Introduction. The spatial protein structure folding is an important and actual problem in biology. Considering the mathematical model of the task, we can conclude that it comes down to the combinatorial optimization problem. Therefore, genetic and mimetic algorithms can be used to find a solution. The article proposes a genetic algorithm with a new greedy stochastic crossover operator, which differs from classical approaches with paying attention to qualities of possible ancestors. The purpose of the article is to describe a genetic algorithm with a new greedy stochastic crossover operator, reveal its advantages and disadvantages, compare the proposed algorithm with the best-known implementations of genetic and memetic algorithms for the spatial protein structure prediction, and make conclusions with future steps suggestion afterward. Result. The work of the proposed algorithm is compared with others on the basis of 10 known chains with a length of 48 first proposed in [13]. For each of the chain, a global minimum of free energy was already precalculated. The algorithm found 9 out of 10 spatial structures on which a global minimum of free energy is achieved and also demonstrated a better average value of solutions than the comparing algorithms. Conclusion. The quality of the genetic algorithm with the greedy stochastic crossover operator has been experimentally confirmed. Consequently, its further research is promising. For example, research on the selection of optimal algorithm parameters, improving the speed and quality of solutions found through alternative coding or parallelization. Also, it is worth testing the proposed algorithm on datasets with proteins of other lengths for further checks of the algorithm’s validity. Keywords: spatial protein structure, combinatorial optimization, genetic algorithms, crossover operator, stochasticity.

Direct Least Absolute Deviation Fitting of Ellipses

Scattered data from edge detection usually involve undesired noise which seriously affects the accuracy of ellipse fitting. In order to alleviate this kind of degradation, a method of direct least absolute deviation ellipse fitting by minimizing the ℓ1 algebraic distance is presented. Unlike the conventional ℓ2 estimators which tend to produce a satisfied performance on ideal and Gaussian noise data, while do a poor job for non-Gaussian outliers, the proposed method shows very competitive results for non-Gaussian noise. In addition, an efficient numerical algorithm based on the split Bregman iteration is developed to solve the resulting ℓ1 optimization problem, according to which the computational burden is significantly reduced. Furthermore, two classes of ℓ2 solutions are introduced as the initial guess, and the selection of algorithm parameters is studied in detail; thus, it does not suffer from the convergence issues due to poor initialization which is a common drawback existing in iterative-based approaches. Numerical experiments reveal that the proposed method is superior to its ℓ2 counterpart and outperforms some of the state-of-the-art algorithms for both Gaussian and non-Gaussian artifacts.

Predicting Prostephanus truncatus (Horn) (Coleoptera: Bostrichidae) populations and associated grain damage in smallholder farmers’ maize stores: A machine learning approach

Prostephanus truncatus is a notorious pest of stored-maize grain and its spread throughout sub-Saharan Africa has led to increased levels of grain storage losses. The current study developed models to predict the level of P. truncatus infestation and associated damage of maize grain in smallholder farmer stores. Data were gathered from grain storage trials conducted in Hwedza and Mbire districts of Zimbabwe and correlated with weather data for each site. Insect counts of P. truncatus and other common stored grain insect pests had a strong correlation with time of year with highest recorded numbers from January to May. Correlation analysis showed insect-generated grain dust from boring and feeding activity to be the best indicator of P. truncatus presence in stores (r = 0.70), while a moderate correlation (r = 0.48) was found between P. truncatus numbers and storage insect parasitic wasps, and grain damage levels significantly correlated with the presence of Tribolium castaneum (r = 0.60). Models were developed for predicting P. truncatus infestation and grain damage using parameter selection algorithms and decision-tree machine learning algorithms with 10-fold cross-validation. The P. truncatus population size prediction model performance was weak (r = 0.43) due to the complicated sampling and detection of the pest and eight-week long period between sampling events. The grain damage prediction model had a stronger correlation coefficient (r = 0.93) and is a good estimator for in situ stored grain insect damage. The models were developed for use under southern African climatic conditions and can be improved with more input data to create more precise models for building decision-support tools for smallholder maize-based production systems.

On the ‘optimal’ density power divergence tuning parameter

The density power divergence, indexed by a single tuning parameter α, has proved to be a very useful tool in minimum distance inference. The family of density power divergences provides a generalized estimation scheme which includes likelihood-based procedures (represented by choice for the tuning parameter) as a special case. However, under data contamination, this scheme provides several more stable choices for model fitting and analysis (provided by positive values for the tuning parameter α). As larger values of α necessarily lead to a drop in model efficiency, determining the optimal value of α to provide the best compromise between model-efficiency and stability against data contamination in any real situation is a major challenge. In this paper, we provide a refinement of an existing technique with the aim of eliminating the dependence of the procedure on an initial pilot estimator. Numerical evidence is provided to demonstrate the very good performance of the method. Our technique has a general flavour, and we expect that similar tuning parameter selection algorithms will work well for other M-estimators, or any robust procedure that depends on the choice of a tuning parameter.

HEVC quantization parameter selection algorithm based on inter-frame dependency

Massive inter predictive modes are adopted in latest High Efficiency Video Coding (HEVC) standard to eliminate temporal redundancies, which results in stronger inter-frame dependency among neighboring frames than previous standards like H.264. The inter-frame dependency makes currently independent rate-distortion optimization (RDO) non-optimal any more. Quantization parameter (QP) selection algorithm taking inter-frame dependency into consideration is supposed to optimize RDO based rate control greatly. According to our research, the inter-frame dependency is reflected by the linear relationship between QP change (ΔQP) and the resulting change of distortion (ΔD). An adaptive QP selection algorithm for global RDO is proposed based on the modeling function between ΔD and ΔQP in this paper. Firstly, based on intensive statistic analysis, three parameters (initial QP ($\overline {QP}$), the length of pictures of group (GOP), and the average of SATD of one frame) are used to formulate the relationship between ΔD and ΔQP. Secondly, the resulting rate change ΔR relative to ΔQP is also formulated similarly. Thirdly, optimized Lagrangian multiplier (λ) is calculated with these two mathematic models. Finally, we refine QP values based on the optimized λ in terms of dependent RDO. The experimental results show that the proposed frame-level QP selection algorithm can decrease Bj⊘tegaard Delta BitRate (BD-BR) by about 1.62% at the random-access (RA) configuration and 1.13% at the low-delay (LD) configuration, respectively. At the same time, it doesn’t increase complexity significantly.

Implementation of MOIDS Algorithm for Optimal Parameter Selection of SFPT for Modern Radars

Modern radars require signals of the large frequency range to attain relatively greater range resolution. Frequency stepping is the technique to convert the narrowband signal, i.e., a train of pulses into a wideband signal to achieve high accuracy in range resolution measurements. Due to the cause of constant step in frequency of successive pulses, grating lobes appeared when the period of pulse multiplied by step in frequency exceeds unity as is needed in modern radars. Hence to achieve the best resolution, grating lobes height, sidelobes level, and mainlobe width have to be minimum. In this paper an attempt has been made to diminish grating lobes, minimize sidelobes and reduce mainlobe width using MOIDSA to find the parameters of Stepped Frequency Pulse Train (SFPT) mechanism. The compromise between various lobes is obtained by using three dimensional Pareto fronts for different ranges of SFPT parameters.

Research and Application of the Transient Electromagnetic Method Inversion Technique Based on Particle Swarm Optimization Algorithm

The transient electromagnetic (TEM) method is widely used in shallow surface engineering geological surveys due to its advantages such as light weight, high efficiency, and strong resolution. However, interpretation and inversion of TEM data is a complicated process. The traditional algorithm of TEM inversion employs the “smoke ring” fast imaging method, which can only reflect the approximate morphology of the stratigraphic model, and the inversion accuracy is low. Therefore, this method cannot meet the requirements of high-precision inversion. In this article, we present the particle swarm optimization (PSO) algorithm for TEM inversion. First of all, the response of the rectangular loop source TEM based on electric dipole integration was calculated and compared with the analytical solution results of the rectangular loop source and the accuracy of the algorithm was verified. Then, we introduced the solution process of the particle swarm optimization algorithm and analyzed the influence of particle swarm optimization algorithm parameter selection on the accuracy of the inversion result and the convergence speed. Next, a layered medium model was established. The particle swarm optimization algorithm and “smoke ring” fast imaging method were used to perform inversion calculation. The results show that the PSO algorithm has the advantages of high efficiency and accuracy. Finally, we examined the effectiveness of the particle swarm optimization algorithm for TEM data processing by inverting survey data from an Air-raid shelter on the campus of Chongqing University in China and comparing the results with those from the “smoke ring” fast imaging. The research works in this article provide new methods and techniques for TEM data processing.

Research on the order parameter selection algorithm based on correlation analysis and principal component analysis——Taking the Logistics sector in Gansu Province as an example

An order parameter selection algorithm based on correlation analysis and principal component analysis was designed according to the statistical analysis method, the selection principle of order parameters of social system, and the correlation test in correlation analysis and the variable contribution test in principal component analysis in this paper. The redundant variables were eliminated from the system by correlation analysis first, and then the variables with high contribution to the system were selected by principal component analysis, so the order parameters obtained accordingly not only have low information redundancy, but also reflect the actual information of the social system to the greatest extent. At the end of this paper, the logistics sector in Gansu Province was taken as an example to select the panel data from 2006 to 2015. Eight indices were extracted as the order parameters of the logistics sector in Gansu Province from the sixteen indices which are redundant selected by this algorithm. The order parameters selected by rational judgment reflect 99% of the original information. The results show that the order parameters in the social system can be correctly and reasonably selected by this order parameter selection algorithm based on correlation analysis and principal component analysis.

LAK: Lasso and K-Means Based Single-Cell RNA-Seq Data Clustering Analysis

The single-cell RNA sequencing provides a way to obtain marker genes of different cells, which lays the foundation for discovering new cell types. The general strategy of achieving this goal is to build a clustering pipeline and derive differentially expressed genes, followed by the cell type enrichment analysis and driving force analysis. Throughout the entire analysis process, clustering models and appropriate methods of dimension reduction are two vital and challenging tasks. In this study, we present a novel method LAK (a computational pipeline for single-cell RNA-seq data clustering analysis using Lasso and K-means based feature selection method) that can be applied to single-cell RNA-seq data by selecting the candidate genes. To deal with the sparse high-dimensional data, we integrated Lasso penalty into clustering method for single-cell RNA-seq data as the feature selection method, which extracts out the genes that have an actual effect on clustering. We also improved the parameter selection algorithm to search the appropriate parameters automatically by binary search according to the size of the data. Compared with other computational approaches, LAK obtains a better performance in reliability, stability, convenience and accuracy applied to the real datasets, the simulation data, and the datasets with a large number of dropout events.

Improved smoothness priors using bilinear transform

Smoothness priors is a well-known and most commonly used method in the analysis of stochastic processes making it very useful in the field of stochastic signal processing. It is particularly suited for smoothing the noisy data and detrending the time-series signals. The method is based on an optimization problem where the n-th order derivative of the signal enters as a constraint. When the method is designed in discrete time domain, the backward difference rule is used to perform differential-to-difference conversion. Moreover, the solution depends on a smoothness trade-off parameter. An efficient algorithm for the trade-off parameter selection remains an important and challenging issue. In this paper, first, we propose a closed-form expression for the trade-off parameter. The closed-form expression resulted from a frequency domain interpretation of the smoothness priors procedure. The trade-off parameter determines the amount of frequency components that the procedure allows to pass. We show that the trade-off parameter is related to the arbitrary choice of cutoff frequency. Second, we introduce a new way to the design and implementation of smoothness priors using bilinear transformation method. Frequency analysis and experiments on both synthetic and real world signals with different levels of noise demonstrate that bilinear transform is indeed more effective for smoothness priors implementation when compared with the traditional ones, i.e., the backward difference rule.

Parameter selection algorithm of DBSCAN based on K‐means two classification algorithm

Clustering algorithm is one of the most important algorithms in unsupervised learning. For density-based spatial clustering of applications with noise (DBSCAN) density clustering algorithm, the selection of neighborhood radius and minimum number is the key to get the best clustering results. Aiming at the problems of traditional DBSCAN algorithm, such as the neighborhood radius and the minimum number of points, this article puts forward two classifications based on K-means algorithm, and gets two clustering centers. Where calculated between two data points and the cluster center-to -center distance, clustering, distance, statistics in a distance of data points within the scope of the search, the number of data points corresponding to the maximum distance value, and thus the parameters for the DBSCAN algorithm to estimate and selection of initial radius of neighborhood with the minimum number of clustering start critical value. When the parameters are iterated and optimized continuously, the data are divided into clusters, and the most suitable neighborhood radius and the minimum point number are obtained. The experimental data analysis show that the improved algorithm reduces the human factors in the traditional algorithm and improves the efficiency, so as to get the accurate clustering results.