K-fold Cross Validation Technique Research Articles

Classification of yarn interlacement pattern in fabrics using least square support vector machines

The purpose of this paper is to suggest an effective and reliable tool that can read through fabric images in the quest of deciphering yarn interlacement patterns by means of Least-Square Support Vector Machines (LS-SVM). A LS-SVM based binary pattern recognition system is formulated for identifying two modes of yarn interlacements viz., warp over weft or warp under weft and accuracy of the classifier was assessed by k-fold cross validation techniques. A comparative study establishes that LS-SVM shows better result than the standard SVM while classifying yarn interlacement patterns in fabrics. The proposed method has the potential to classify yarn interlacement patterns with possibility of extending it to design- decoding of diverse fabrics.

Ensemble Learning Approach for Classification of Network Intrusion Detection in IoT Environment

Over the last two years,the number of cyberattacks has grown significantly, paralleling the emergence of new attack types as intruder’s skill sets have improved. It is possible to attack other devices on a botnet and launch a man-in-the-middle attack with an IOT device that is present in the home network. As time passes, an ever-increasing number of devices are added to a network. Such devices will be destroyed completely if one or both of them are disconnected from a network. Detection of intrusions in a network becomes more difficult because of this. In most cases, manual detection and intervention is ineffective or impossible. Consequently, it's vital that numerous types of network threats can be better identified with less computational complexity and time spent on processing. Numerous studies have already taken place, and specific attacks are being examined. In order to quickly detect an attack, an IDS uses a well-trained classification model. In this study, multi-layer perceptron classifier along with random forest is used to examine the accuracy, precision, recall and f-score of IDS. IoT environment-based intrusion related benchmark datasets UNSWNB-15 and N_BaIoT are utilized in the experiment. Both of these datasets are relatively newer than other datasets, which represents the latest attack. Additionally, ensembles of different tree sizes and grid search algorithms are employed to determine the best classifier learning parameters. The research experiment's outcomes demonstrate the effectiveness of the IDS model using random forest over the multi-layer perceptron neural network model since it outperforms comparable ensembles analyzed in the literature in terms of K-fold cross validation techniques.

Modeling Biophysical Variables Across an Arctic Latitudinal Gradient using High Spatial Resolution Remote Sensing Data

Biophysical variables have both direct and indirect effects on the uptake and release of carbon dioxide (CO2) within tundra ecosystems. Arctic landscape shows high levels of spatial heterogeneity. High spatial-resolution remote sensing data has the ability to capture the fine-grain spectral response of various biophysical variables at the landscape scale. To accurately model CO2 flux patterns using remote sensing data we first need to model the relationships between biophysical variables and their spectral response. In this study we model percent vegetation cover (PVC), aboveground biomass (AGB), and soil moisture using high spatial-resolution (IKONOS 4 m) normalized difference vegetation index (NDVI) values. At two non-overlapping Arctic landscape sites statistically robust landscape-scale sampling procedures were used to characterize the biophysical variables. NDVI values were extracted from IKONOS data, and linear bivariate regression models were calibrated and validated using a k-fold cross-validation technique. PVC and percent soil moisture produced the strongest and most consistent results (r2≥ .84 and .73, respectively). Analysis of covariance tested the use of common models for each site. The models were not coincidental—combining data from various sites should be done with caution—but illustrated parallelism in that NDVI responds to each biophysical variable equally, regardless of site.

Spider specie identification and verification based on pattern recognition of it cobweb

Biodiversity conservation is a global priority where the study of every type of living form is a fundamental task. Inside the huge number of the planet species, spiders play an important role in almost every habitat. This paper presents a comprehensive study on the reliability of the most used features extractors to face the problem of spider specie recognition by using their cobwebs, both in identification and verification modes. We have applied a preprocessing to the cobwebs images in order to obtain only the valid information and compute the optimal size to reach the highest performance. We have used the principal component analysis (PCA), independent component analysis (ICA), Discrete Cosine Transform (DCT), Wavelet Transform (DWT) and discriminative common vectors as features extractors, and proposed the fusion of several of them to improve the system’s performance. Finally, we have used the Least Square Vector Support Machine with radial basis function as a classifier. We have implemented K-Fold and Hold-Out cross-validation techniques in order to obtain reliable results. PCA provided the best performance, reaching a 99.65%±0.21 of success rate in identification mode and 99.98%±0.04 of the area under de Reveicer Operating Characteristic (ROC) curve in verification mode. The best combination of features extractors was PCA, DCT, DWT and ICA, which achieved a 99.96%±0.16 of success rate in identification mode and perfect verification.

An ensemble system for automatic sleep stage classification using single channel EEG signal

The present work aims at automatic identification of various sleep stages like, sleep stages 1, 2, slow wave sleep (sleep stages 3 and 4), REM sleep and wakefulness from single channel EEG signal. Automatic scoring of sleep stages was performed with the help of pattern recognition technique which involves feature extraction, selection and finally classification. Total 39 numbers of features from time domain, frequency domain and from non-linear analysis were extracted. After extraction of features, SVM based recursive feature elimination (RFE) technique was used to find the optimum number of feature subset which can provide significant classification performance with reduced number of features for the five different sleep stages. Finally for classification, binary SVMs were combined with one-against-all (OAA) strategy. Careful extraction and selection of optimum feature subset helped to reduce the classification error to 8.9% for training dataset, validated by k-fold cross-validation (CV) technique and 10.61% in the case of independent testing dataset. Agreement of the estimated sleep stages with those obtained by expert scoring for all sleep stages of training dataset was 0.877 and for independent testing dataset it was 0.8572. The proposed ensemble SVM-based method could be used as an efficient and cost-effective method for sleep staging with the advantage of reducing stress and burden imposed on subjects.

Multiclass Kernel Function Evaluation

Kernel is a key component of the support vector machines (SVMs) and other kernel methods. Based on the data distributions of classes in the feature space, this paper proposed a model selection criterion to evaluate the goodness of a kernel in multiclass classification scenario. This criterion is computationally efficient and is differentiable with respect to the kernel parameters. Compared with the k-fold cross validation technique which is often regarded as a benchmark, this criterion is found to yield about the same performance with much less computational overhead.

Predicting Future Land Use Change Using Support Vector Machine Based GIS Cellular Automata: A Case of Lagos, Nigeria

Lagos has undergone an unprecedented urban expansion. Contemporary findings favour the integration of cellular automata and geographic information systems for modelling land use change. This research introduces the support vector machine based GIS cellular automata calibration for land use change prediction of Lagos. The support vector machine based cellular automata model is loosely coupled with the geographic information systems. Support vector machine parameters are optimised with the k-fold cross-validation technique, using the linear, polynomial, and RBF kernels functions. The land use change prediction is based on three land use epochs: 1963-1978, 1978-1984, and 1984-2000. The performance of the model was evaluated using the Kappa statistic and receiver operating characteristic; which shows the order of performance of the three kernels: RBF, polynomial, and linear. The results indicate substantial agreement between the actual and predicted maps. The urban forms in 2015 and 2030 are predicted based on the three land use epochs.

Intelligent Transportation Systems and NO2 Emissions: Predictive Modeling Approach Using Artificial Neural Networks

AbstractEnvironmental or air-quality effects of Intelligent Transportation Systems (ITS) are very difficult to measure. Some researchers have attempted to quantify the effects of individual ITS application on emissions; yet, the effects of ITS as a whole on ambient air-quality have not been investigated. This paper shows how to model the relationship between ITS and ambient airquality. The multiple artificial neural networks (ANN) training with the data yielded a model for predicting the NO2 concentrations. In addition, the ANN made the measurement of the effect of ITS on NO2 concentrations in ambient air possible. Data pertaining to 59 U.S. cities (urbanized area) were used for this work. Input variables used were related to transportation, local characteristics, and ITS applications. Output variable was the annual average concentration of NO2 in ambient air. The K-fold cross-validation technique was used to train the ANN. There was an unusual finding: in contrast to the common assumptions, NO2 concentra...

Forecasting of Cotton Yarn Properties Using Intelligent Machines

An intelligence machine is a computer program that can learn from experience, i.e. modifies its processing on the basis of newly acquired information and thereafter makes decisions in a rightfully sensible manner when presented with inputs. Examples of such machine learning systems are artificial neural networks (ANNs), support vector machines (SVMs), fuzzy logic, evolutionary computation, etc. The prediction of cotton yarn properties from constituent fibre properties is quite significant from a technological point of view. Regardless of the relentless efforts made by researchers, the exact relationship between fibre and yarn properties has not yet been decisively recognized. The intelligence machine, which is a potent data-modeling tool in capturing complex input-output relationships, seems to be the right approach to decipher the fibre-to-yarn relationship. In this work, various cotton yarns properties, such as strength, elongation, evenness and hairiness, have been predicted from fibre properties by using different intelligence models, such as ANNs, SVMs and adaptive neuro fuzzy inference systems (ANFIS). A k-fold cross validation technique is applied to assess the expected generalization accuracies of these models. A comparison of the prediction efficiencies among these models shows that the performances of the SVM model has better accuracies than the other models.

Prediction of cotton yarn properties using support vector machine

This paper presents a support vector machine (SVM) regression approach to forecast the properties of cotton yarns produced on ring and rotor spinning technologies from the fibre properties measured by HVI and AFIS. Prediction performance of SVM models have been compared against those of the artificial neural network (ANN) models. A k-fold cross validation technique is applied to assess the expected generalization accuracies of both SVM and ANN models. The investigation indicates that the yarn properties can be predicted with a very high degree of accuracy using SVM models and the prediction performance of SVM models are better than that of ANN models.

Assessing the blood volume and heart rate responses during haemodialysis in fluid overloaded patients using support vector regression

This study aims to assess the blood volume and heart rate (HR) responses during haemodialysis in fluid overloaded patients by a nonparametric nonlinear regression approach based on a support vector machine (SVM). Relative blood volume (RBV) and electrocardiogram (ECG) was recorded from 23 haemodynamically stable renal failure patients during regular haemodialysis. Modelling was performed on 18 fluid overloaded patients (fluid removal of >2 L). SVM-based regression was used to obtain the models of RBV change with time as well as the percentage change in HR with respect to RBV. Mean squared error (MSE) and goodness of fit (R2) were used for comparison among different kernel functions. The design parameters were estimated using a grid search approach and the selected models were validated by a k-fold cross-validation technique. For the model of HR versus RBV change, a radial basis function (RBF) kernel (MSE = 17.37 and R2 = 0.932) gave the least MSE compared to linear (MSE = 25.97 and R2 = 0.898) and polynomial (MSE = 18.18 and R2= 0.929). The MSE was significantly lower for training data set when using RBF kernel compared to other kernels (p < 0.01). The RBF kernel also provided a slightly better fit of RBV change with time (MSE = 1.12 and R2 = 0.91) compared to a linear kernel (MSE = 1.46 and R2 = 0.88). The modelled HR response was characterized by an initial drop and a subsequent rise during progressive reduction in RBV, which may be interpreted as the reflex response to a transition from central hypervolaemia to hypovolaemia. These modelled curves can be used as references to a controller that can be designed to regulate the haemodynamic variables to ensure the stability of patients undergoing haemodialysis.

A neural network model for the numerical prediction of the diameter of electro-spun polyethylene oxide nanofibers

This paper investigates the viability of neural network as a tool for predicting the diameter of fiber formed by an electrospinning process. Published experimental data for polyethylene oxide (PEO) aqueous solution is used to train and test the neural network model. Concentration, conductivity, flow rate, and electric field strength are used as the input variables to the neural network model. Network model selection, training and testing were conducted using the k-fold cross validation technique which is demonstrated to be the most suitable scheme for the size of dataset used in this study. A statistical study was conducted to establish 95% confidence intervals on the bias and on the limits of agreement between the experimental data and the predicted data. The computer simulation results show a very good agreement between the data, demonstrating the viability of neural network as a promising tool for predicting fiber diameter. While the proposed neural network approach is not intended to model the complete complex physics of the electrospinning process, it is demonstrated to provide an accurate nonlinear mapping between the four salient input variables and the diameter of the formed fiber. This study provides some potential insights into exploring neural network model-based feedback control techniques to regulate nanofiber diameter in an electrospinning process.

Reservoir parameter estimation using a hybrid neural network

The accuracy of an artificial neural network (ANN) algorithm is a crucial issue in the estimation of an oil field’s reservoir properties from the log and seismic data. This paper demonstrates the use of the k-fold cross validation technique to obtain confidence bounds on an ANN’s accuracy statistic from a finite sample set. In addition, we also show that an ANN’s classification accuracy is dramatically improved by transforming the ANN’s input feature space to a dimensionally smaller, new input space. The new input space represents a feature space that maximizes the linear separation between classes. Thus, the ANN’s convergence time and accuracy are improved because the ANN must merely find nonlinear perturbations to the starting linear decision boundaries. These techniques for estimating ANN accuracy bounds and feature space transformations are demonstrated on the problem of estimating the sand thickness in an oil field reservoir based only on remotely sensed seismic data.

Estimation of reservoir parameter using a hybrid neural network

Estimation of an oil field's reservoir properties using seismic data is a crucial issue. The accuracy of those estimates and the associated uncertainty are also important information. This paper demonstrates the use of the k-fold cross validation technique to obtain confidence bound on an Artificial Neural Network's (ANN) accuracy statistic from a finite sample set. In addition, we also show that an ANN's classification accuracy is dramatically improved by transforming the ANN's input feature space to a dimensionally smaller, new input space. The new input space represents a feature space that maximizes the linear separation between classes. Thus, the ANN's convergence time and accuracy are imporved because the ANN must merely find nonlinear perturbations to the starting linear decision boundaries. These technique for estimating ANN accuracy bounds and feature space transformations are demonstrated on the problem of estimating the sand thickness in an oil field reservoir based only on remotely sensed seismic data.

K-fold Crossvalidation in Canonical Analysis.

A computer-assisted, K-fold crossvalidation technique is discussed within the framework of canonical correlation analysis of randomly generated data sets. Results of the analysis suggest that this technique of multi-crossvalidation can be an effective method to reduce the contamination of canonical variates and canonical correlations by sample-specific variance components.