Idea Of Cross-validation Research Articles

Research on the diagnosis of corona virus disease 2019(COVID-19) based on machine-learning

In recent years, the Corona Virus Disease 2019(COVID-19) has brought a huge impact on people's daily life and the normal operation of society, and as machine learning research deepens, this technology could help detect viruses such as the novel coronavirus. According to this, how to accurately, quickly and effectively analyze and classify laboratory results with multiple indicators through the method of machine learning is the object of this paper. In order to explore the classification performance of various machine learning classification algorithms on laboratory results, linear and non-linear methods were used respectively to analyze and classify the laboratory results. In linear analysis, distance discriminant and fisher discriminant were used to explore the classification effect of linear classification on laboratory results. The non-linear analysis mainly used Adaptive Boosting(AdaBoost) and Random Forest algorithm which are widely used to test the classification effect under the influence of multiple indexes. In this paper, python and other tools were used to classify samples of different combinations by using the idea of cross validation. By comparing the running time and detection accuracy, it was found that Adaboost algorithm is applicable in most cases and was a relatively fast and accurate classification method. In addition, Random Forest algorithm had similar accuracy, but it might have better performance on a large data set.

Random embedded calibrated statistical blind steganalysis using cross validated support vector machine and support vector machine with particle swarm optimization

The evolvement in digital media and information technology over the past decades have purveyed the internet to be an effectual medium for the exchange of data and communication. With the advent of technology, the data has become susceptible to mismanagement and exploitation. This led to the emergence of Internet Security frameworks like Information hiding and detection. Examples of domains of Information hiding and detection are Steganography and steganalysis respectively. This work focus on addressing possible security breaches using Internet security framework like Information hiding and techniques to identify the presence of a breach. The work involves the use of Blind steganalysis technique with the concept of Machine Learning incorporated into it. The work is done using the Joint Photographic Expert Group (JPEG) format because of its wide use for transmission over the Internet. Stego (embedded) images are created for evaluation by randomly embedding a text message into the image. The concept of calibration is used to retrieve an estimate of the cover (clean) image for analysis. The embedding is done with four different steganographic schemes in both spatial and transform domain namely LSB Matching and LSB Replacement, Pixel Value Differencing and F5. After the embedding of data with random percentages, the first order, the second order, the extended Discrete Cosine Transform (DCT) and Markov features are extracted for steganalysis.The above features are a combination of interblock and intra block dependencies. They had been considered in this paper to eliminate the drawback of each one of them, if considered separately. Dimensionality reduction is applied to the features using Principal Component Analysis (PCA). Block based technique had been used in the images for better accuracy of results. The technique of machine learning is added by using classifiers to differentiate the stego image from a cover image. A comparative study had been during with the classifier names Support Vector Machine and its evolutionary counterpart using Particle Swarm Optimization. The idea of cross validation had also been used in this work for better accuracy of results. Further parameters used in the process are the four different types of sampling namely linear, shuffled, stratified and automatic and the six different kernels used in classification specifically dot, multi-quadratic, epanechnikov, radial and ANOVA to identify what combination would yield a better result.

CT2‐MDS: Cooperative trust‐aware tolerant misbehaviour detection system for connected and automated vehicles

Connected and automated vehicles (CAVs) are recognized as a promising solution to improve road safety. Before deploying CAVs, securing the communication environment is a critical challenge. To secure the exchanged sensitive messages between CAVs, a novel cooperative trust-aware tolerant misbehaviour detection system (CT2-MDS) is proposed in this paper. The vehicle-to-everything (V2X) network model in real complex scenarios is built first, and several typical types of attacks are simulated. The cooperative trust factor is then defined to evaluate the received message packet's plausibility instead of the node. And the measuring uncertainty of sensors is considered to improve the overall detection precision. At last, a multi-model fusion misbehaviour detection method is presented based on the idea of cross-validation. In this mechanism, different from the binary classification, the misbehaviour messages are categorized into particular misbehaving classes. To verify the proposed system's performance, the simulation is conducted, and the results showed that the proposed method outperformed existing single classifiers and provided good prediction accuracy in different attack density.

On data-driven choice of [formula omitted] in nonparametric Gaussian regression via Propagation–Separation approach

A new procedure is proposed for selecting the input value for the adaptation bandwidth λ in nonparametric Gaussian regression via Propagation–Separation approach. Since λ stands at the bias–variance trade-off of this estimation technique, it is its key tuning parameter. So far, however, apart from theoretical concepts, there exists no approach for a data-driven choice of its input value. This complicates the practical application of the Propagation–Separation method despite its highly desirable statistical properties — it is dimension-free and very well suited for estimation problems where the underlying regression function has sharp discontinuities and large homogeneous regions. The proposed selection method is based on the idea of cross-validation. Therefore, it allows to choose λ in a data-driven way. Its performance is evaluated via simulations. The results are very convincing: Cross-validation is a very transparent selection procedure that provides for each sample a “tailor-made” input value for λ and allows a successful identification of the underlying regression function. As the sample size increases, the accuracy of estimation improves in the sense that the estimates approach the true regression function. In addition, cross-validation accounts for the weighting functions and other parameter values used within the Propagation–Separation method by adjusting λ accordingly, which results in very robust estimates.

RETRACTED ARTICLE: Feature reduced blind steganalysis using DCT and spatial transform on JPEG images with and without cross validation using ensemble classifiers

The paper discuss the outcome evaluation of JPEG images in both spatial and DCT transform and a comparative study is being done. There are four distinct steganographic algorithms—LSB matching, LSB replacement, pixel value differencing and F5 are used. The embedding performed on the images are 25% with text. The idea of cross validation is used to validate the classifier better and a comparative analysis is performed on results with and without cross validation. Features removed for investigation are the first order, second order, extended features and Markov features. Relevant features are chosen by feature reduction. This process is done using principal component analysis (PCA). This is done to eliminate redundant feature that can hamper the efficiency of classification. The classifiers used are support vector machine (SVM) and support vector machine with particle swarm optimisation (SVM-PSO). The classification is done based on six kernels like radial, dot, multiquadratic, epanechnikov and ANOVA and four sampling techniques like shuffled, linear, stratified and automatic sampling. The existing techniques had always used radial as kernel without sampling for a classification. The proposed system make use of this imperfection and has formulated the result.

Ensemble of online sequential extreme learning machine based on cross-validation

The online sequential extreme learning machine (OS-ELM) was proposed as an evolution of the Extreme learning machine (ELM) in 2006. The learning algorithm can learn data by fixing or changing the size of the chunk (a block of data). Compared with other online algorithms, it has faster training speed, and the generalization performance is better. The proposed ensemble of neural networks further demonstrates that the use of the neural network sets with multiple consensus schemes has a greater improvement over the stability of a single network. The basic idea of cross-validation is to group the original data sets, part of which is to train as the training set and the other part of which is to verify as the test set, so the algorithm can reduce the over-fitting problem of the data to a certain extent, and extract more valid information in the limited data set. In this paper, a new ensemble of online sequential extreme learning machine based on cross-validation (ENOS-ELM) is proposed. Through application of cross-validation and integration to the training stage, the accuracy of the algorithm in classification is further improved.

Fractional-Order Model-Based Incremental Capacity Analysis for Degradation State Recognition of Lithium-Ion Batteries

State of health (SOH) estimation of lithium-ion batteries is a key but challengeable technique for the application of electric vehicles. Due to the ambiguous aging mechanisms and sensitivity to the applied conditions of lithium-ion batteries, the recognition of aging mechanisms and SOH monitoring of the battery might be difficult. A novel SOH estimation and aging mechanism identification method is presented in this paper. First, considering the dispersion effect, a fractional-order model is constructed, and the parameter identification approach is proposed, and a comparison between integer-order model and fractional-order model has been done from the prospect of predicting accuracy. Then, based on the identified open-circuit voltage, the battery aging mechanism can be analyzed by the means of an incremental capacity analysis method. Moreover, the normalized incremental capacity peak is used to estimate the remaining capacity. Finally, the robustness of the SOH estimation method is validated by batteries aged at different conditions based on the idea of cross validation, and the estimation error of the remaining capacity can be reduced within 3.1%.

A cross-selection instance algorithm

Motivated by the idea of cross-validation, a novel instance selection algorithm is proposed in this paper. The novelties of the proposed algorithm are that (1) it cross selects the important instances from the original data set with a committee, (2) it can deal with the problem of selecting instance from large data sets. We experimentally compared our algorithm with five state-of-the-art approaches which are CNN, ENN, RNN, MCS, and ICF on 3 artificial data sets and 6 UCI data sets, including 4 large data sets, ranking from 130K to 4898K in size. The experimental results show that the proposed algorithm is very efficient and effective, especially on large data sets.

Study about Recognition of Digital Meter Dial Reading Based on SVM

In practice, it is difficult for Support Vector Machine (SVM) to have a relatively high recognition rate as well as a quite fast recognition speed. In order to resolve this defect, in this paper we build a SVM classification model combining numerical characteristics. We use readings of rotary natural meters as the test temple, do positioning, preprocessing, feature points extracting, classifying and other series of operations to the numeric region of the dial. Then with the idea of cross-validation, we keep doing parameter optimation to SVM. At last, after making a comprehensive contrast of the effects which numerous performance factors make on the experimental outputs, we try to give our explanation of the outputs from different perspectives.

Nonparametric regression with doubly truncated data

Nonparametric regression with a doubly truncated response is introduced. Local constant and local linear kernel-type estimators are proposed. Asymptotic expressions for the bias and the variance of the estimators are obtained, showing the deterioration provoked by the random truncation. To solve the crucial problem of bandwidth choice, two different bandwidth selectors based on plug-in and cross-validation ideas are introduced. The performance of both the estimators and the bandwidth selectors is investigated through simulations. A real data illustration is included. The main conclusion is that the introduced regression methods perform satisfactorily in the complicated scenario of random double truncation.

Kernel Conditional Density Estimation When the Regressor is Valued in a Semi-Metric Space

This article deals with the conditional density estimation when the explanatory variable is functional. In fact, nonparametric kernel type estimator of the conditional density has been recently introduced when the regressor is valued in a semi-metric space. This estimator depends on a smoothing parameter which controls its behavior. Thus, we aim to construct and study the asymptotic properties of a data-driven criterion for choosing automatically and optimally this smoothing parameter. This criterion can be formulated in terms of a functional version of cross-validation ideas. Under mild assumptions on the unknown conditional density, it is proved that this rule is asymptotically optimal. A simulation study and an application on real data are carried out to illustrate, for finite samples, the behavior of our method. Finally, we mention that our results can also be considered as novel in the finite dimensional setting and several other open questions are raised in this article.

An alternative procedure for selecting a good value for the parameter c in RBF-interpolation

The impact of the scaling parameter c on the accuracy of interpolation schemes using radial basis functions (RBFs) has been pointed out by several authors. Rippa (Adv Comput Math 11:193---210, 1999) proposes an algorithm based on the idea of cross validation for selecting a good such parameter value. In this paper we present an alternative procedure, that can be interpreted as a refinement of Rippa's algorithm for a cost function based on the euclidean norm. We point out how this method is related to the procedure of maximum likelihood estimation, which is used for identifying covariance parameters of stochastic processes in spatial statistics. Using the same test functions as Rippa we show that our algorithm compares favorably with cross validation in many cases and discuss its limitations. Finally we present some computational aspects of our algorithm.

Optimal bandwidth selection for multivariate kernel deconvolution density estimation

Assume we have i.i.d. replications from the mismeasured random vector Y=X+e, where X and e are mutually independent. We consider a data-driven bandwidth, based on a cross-validation ideas, for multivariate kernel deconvolution estimator of the density of X. The proposed data-driven bandwidth selection method is shown to be asymptotically optimal. As a by-product of the proof of this result, we show that the average squared error, the integrated squared error, and the mean integrated squared error are asymptotically equivalent error measures.

Nonparametric regression for functional data: Automatic smoothing parameter selection

We study regression estimation when the explanatory variable is functional. Nonparametric estimates of the regression operator have been recently introduced. They depend on a smoothing factor which controls its behavior, and the aim of our work is to construct some data-driven criterion for choosing this smoothing parameter. The criterion can be formulated in terms of a functional version of cross-validation ideas. Under mild assumptions on the unknown regression operator, it is seen that this rule is asymptotically optimal. As by-products of this result, we state some asymptotic equivalences for several measures of accuracy for nonparametric estimate of the regression operator. We also present general inequalities for bounding moments of random sums involving functional variables. Finally, a short simulation study is carried out to illustrate the behavior of our method for finite samples.

Sélection automatique du paramètre de lissage pour l'estimation non paramétrique de la régression pour des données fonctionnelles

We study regression estimation when the explanatory variable is functional. Nonparametric estimates of the regression operator have been recently introduced. They depend on a smoothing factor which controls its behaviour, and the aim of our Note is to construct some data-driven criterion for choosing this smoothing parameter. The criterion can be formulated in terms of a functional version of cross-validation ideas. Under mild assumptions on the unknown regression operator, it is seen that this rule is asymptotically optimal. As by-products of this result, we state asymptotic equivalences for several measures of accuracy for nonparametric estimate of the regression operator. To cite this article: M. Rachdi, P. Vieu, C. R. Acad. Sci. Paris, Ser. I 341 (2005).

A crossvalidation method for estimating conditional densities

SUMMARY We extend the idea of crossvalidation to choose the smoothing parameters of the 'double-kernel' local linear regression for estimating a conditional density. Our selection rule optimises the estimated conditional density function by minimising the integrated squared error. We also discuss three other bandwidth selection rules, an ad hoc method used by Fan et al. (1996), a bootstrap method of Hall et al. (1999) for bandwidth selection in the estimation of conditional distribution functions, modified by Bashtannyk & Hyndman (2001) to cover conditional density functions, and finally a simple approach proposed by Hyndman & Yao (2002). The performance of the new approach is compared with these three methods by simulation studies, and our method performs outstandingly well. The method is illustrated by an application to estimating the transition density and the Value-at-Risk of treasury-bill data.

Local polynomial M-smoothers in nonparametric regression

In the case of the equally spaced fixed design nonparametric regression, the local polynomial M-smoother (LPM) is proposed for estimating the regression function. The LPM is developed directly from both the local constant M-smoother in Chu et al. (J. Amer. Statist. Assoc. 93 (1998) 526) and the local linear M-smoother in Rue et al. (J. Nonparametric Statist. 14 (2002) 155). It is shown that, in the smooth region, our LPM has the same asymptotic bias as the local polynomial estimator, but has larger asymptotic variance. On the other hand, in the jump region, it has the interesting property of edge-preserving, but is inconsistent. In practice, a fast algorithm for computing the LPM is presented, and the idea of cross-validation is applied to select the value of the smoothing parameter. More importantly, the results including the fast computation algorithm obtained for the LPM in the one-dimensional case can be extended directly to the multidimensional case. Simulation studies demonstrate that our LPM is competitive with alternatives, in the sense of yielding both smaller sample mean average squared error and better visual performance.

Least squares cross-validation for the kernel deconvolution density estimator

Assume we have i.i.d. replications from the corrupted random variable Y= X+ ε, where X and ε are independent. We propose a data-driven bandwidth based on cross-validation ideas, for the kernel deconvolution estimator of the density of X. The proposed method is shown to be asymptotically optimal. To cite this article: É. Youndjé, M.T. Wells, C. R. Acad. Sci. Paris, Ser. I 334 (2002) 509–513.

A study of local linear ridge regression estimators

Abstract In the case of the random design nonparametric regression, to correct for the unbounded finite-sample variance of the local linear estimator (LLE), Seifert and Gasser (J. Amer. Statist. Assoc. 91 (1996) 267–275) apply the idea of ridge regression to the LLE, and propose the local linear ridge regression estimator (LLRRE). However, the finite sample and the asymptotic properties of the LLRRE are not discussed there. In this paper, upper bounds of the finite-sample variance and bias of the LLRRE are obtained. It is shown that if the ridge regression parameters are not properly selected, then the resulting LLRRE has some drawbacks. For example, it may have a nonzero constant asymptotic bias, may suffer from boundary effects, or may be unable to share the nice asymptotic bias quality of the LLE. On the other hand, if the ridge regression parameters are properly selected, then the resulting LLRRE does not suffer from the above problems, and has the same asymptotic mean-square error as the LLE. For this purpose, the ridge regression parameters are allowed to depend on the sample size, and converge to 0 as the sample size increases. In practice, to select both the bandwidth and the ridge regression parameters, the idea of cross-validation is applied. Simulation studies demonstrate that the LLRRE using the cross-validated bandwidth and ridge regression parameters could have smaller sample mean integrated square error than the LLE using the cross-validated bandwidth, in reasonable sample sizes.

Forecasts from a Nonparametric Approach: ACE

selection algorithm like the state space models do. ACE does internally make use of the idea of cross validation, which is closely related to prediction error. We have carried that empirical philosophy over to the area of model selection and combined strongly held economic priors with a search for models with low values of the final prediction error criterion. Our model selection strategy was to consider only those models with homogeneity and per capita quantities. Because our interest is in prediction, we considered only those models in which the regressors would be predetermined.