Robust radial basis function networks based on least trimmed squares-support vector regression

Identification of MIMO systems using radial basis function networks with hybrid learning algorithm

This article addresses the robust estimation of the output layer linear parameters in a radial basis function network (RBFN). A prominent method used to estimate the output layer parameters in an RBFN with the predetermined hidden layer parameters is the least-squares estimation, which is the maximum-likelihood (ML) solution in the specific case of the Gaussian noise. We highlight the connection between the ML estimation and minimizing the Kullback-Leibler (KL) divergence between the actual noise distribution and the assumed Gaussian noise. Based on this connection, a method is proposed using a variant of a generalized KL divergence, which is known to be more robust to outliers in the pattern recognition and machine-learning problems. The proposed approach produces a surrogate-likelihood function, which is robust in the sense that it is adaptive to a broader class of noise distributions. Several signal processing experiments are conducted using artificially generated and real-world data. It is shown that in all cases, the proposed adaptive learning algorithm outperforms the standard approaches in terms of mean-squared error (MSE). Using the relative increase in the MSE for different noise conditions, we compare the robustness of our proposed algorithm with the existing methods for robust RBFN training and show that our method results in overall improvement in terms of absolute MSE values and consistency.

This paper presents a robust radial basis function (RBF) network based classifier for polarimetric synthetic aperture radar (SAR) images. The proposed feature extraction process utilizes the covariance matrix, the gray level co-occurrence matrix (GLCM) based texture features, and the backscattering power (Span) combined with the H/α/A decomposition, which are projected onto a lower dimensional feature space using principal component analysis. For the classifier training two popular techniques are explored: conventional backpropagation (BP) and particle swarm optimization (PSO). By using both polarimetric covariance matrix and decomposition based pixel values and textural information (contrast, correlation, energy, and homogeneity) in the feature set, classification accuracy is improved. An experimental study is performed using the fully polarimetric San Francisco Bay and Flevoland data sets acquired by the NASA/Jet Propulsion Laboratory Airborne SAR (AIRSAR) at L-band to evaluate the performance of the proposed classifier. Classification results (in terms of confusion matrix, overall accuracy and classification map) compared with competing state of the art algorithms demonstrate the effectiveness of the proposed RBF network classifier.

Point-pair registration in a real scene remains a challenging task, due to the complexity of solving three transformations (scale, rotation, and displacement) simultaneously, and the influence of noise and outliers. Aimed at this problem, a registration algorithm based on histogram and vector operations is proposed in this paper. This approach converts point-based operations into vector-based operations, thereby decomposing the registration process into three independent steps solving for scale transformation factors, rotation matrices, and displacement vectors, which reduces the complexity of the solution and avoids the effects of scaling in the other two processes. The influence of outliers on the global transformation matrix is simultaneously eliminated using a histogram-based approach. Algorithm performance was evaluated through a comparison with the most commonly used SVD method in a series of validation experiments, with results showing that our methodology was superior to SVD in the cases with scaling transformation or outliers.

A major objective of this project was to apply GE’s commercial machine learning and data analytics toolsets to large-scale, real-world, anonymized Phasor Measurement Unit (PMU) datasets in order to extract signatures, correlated and/or causal factors, and precursor patterns associated with significant power system phenomena. The project had a particular emphasis on extraction of insights relevant to asset health monitoring, real-time load modeling and cybersecurity monitoring. Additionally, the team was directed to undertake a comprehensive data quality analysis for the provided datasets and encouraged to estimate the ‘machine-learning readiness’ of the datasets by documenting any major obstacles to the application of commercial machine learning algorithms. To accomplish the aforementioned objectives, the project team’s work centered around the identification of key event signatures and application of the identified event signatures for event detection and event classification. The industry-validated, semi-supervised machine learning strategy employed for event signature identification involved several major tasks, including data-preprocessing, generation of an overabundance of features, normal data identification, normality modeling, and event signature identification through a methodical, quantitative ranking of features in order of relevance to each studied event type. Throughout the project, data quality issues and mitigation techniques were investigated. In this report, insights are provided regarding the readiness of the provided synchrophasor datasets for application of machine learning and data analytics. The methodologies employed for this technical strategy are summarized in this report. With regards to data preprocessing and feature generation, the provided Training and Test Datasets were ingested into GE’s big data environment. Subsequently, the team applied bad data cleansing and data imputation scripts, event detection scripts, and application programming interfaces (APIs) to the datasets for convenient data access. The project team completed development and validation of dozens of physics-based, statistics-based and transformation-based feature functions used for the extraction of over 60 synchrophasor features. Using a new parallel feature generation technology developed on this project, over 60 features have been rapidly generated for the full two years’ worth of Training and Test Dataset data associated with both the Eastern and Western interconnects. Even accommodating for temporal down-sampling inherent to the feature extraction procedure, this parallel feature generation activity resulted in a massive feature set with a storage requirement approximately equal to that of the raw training dataset itself. With regards to normal data identification and normality modeling, a normality model was built using the feature data extracted from the Training Dataset and iteratively refined subsequent to incremental adjustments and expansions of the Training Dataset feature data. With respect to event characterization and signature identification, an event signature identification pipeline was developed and used in conjunction with the normality model to identify over 15 event signatures for key event categories within the Training Dataset. The identified event signatures were used to characterize hundreds of key events in terms of relative severity, duration, and location of the event. An investigation was undertaken to identify correlated and causal factors involved in transformer events. A separate investigation into temporal trends in ring-down analysis results was undertaken to determine possible associations between system dynamics and various other factors such as loading, season or year. To validate the identified event signatures, additional work was undertaken to develop signature-based anomaly detection and classification tools suitable for convenient application to the synchrophasor datasets. The anomaly detection and classification tools, suitable for online application, were then applied to the entirety of the Eastern Interconnect Training and Test Datasets. Performance of the event detection and classification tools was evaluated upon receipt of the Test Dataset event logs (i.e., the labels for events contained in the Test Dataset), and promising results were obtained despite several challenges (documented herein) associated with application of supervised or semi-supervised machine learning methods to large-scale, anonymized datasets. Finally, the detection and classification tools were used to detect, classify, and characterize thousands of new events not included in the original event logs provided by the DOE within both the Training and Test Datasets.

Because of the moderate heritability and the expense associated with collecting feed intake data, effective selection for residual feed intake would be enhanced if marker-assisted evaluation were used for accurate estimation of genetic merit. In this study, a suite of genetic markers predictive of residual feed intake, DMI, and ADG were preselected using single-marker regression analysis, and the top 100 SNP were analyzed further to provide prediction equations for the traits. The data used consisted of 728 spring-born beef steers, offspring of a cross between a composite dam line and Angus, Charolais, or University of Alberta hybrid bulls. Feed intake data were collected over a 5-yr period, with 2 groups (fall-winter and winter-spring) tested every year. Training and validation data sets were obtained by splitting the data into 2 distinct sets, by randomly splitting the data into training and testing sets based on sire family (split 1) in 5 replicates or by retaining all animals with no known pedigree relationships as the validation set (split 2). A total of 37,959 SNP were analyzed by single-marker regression, of which only the top 100 that corresponded to a P-value <0.002 were retained. The 100 SNP were then analyzed using random regression BLUP, and only SNP that were jointly significant (P < 0.05) were included in the final marker panels. The marker effects from the selected panels were used to derive the molecular breeding values, which were calculated as a weighted sum of the number of copies of the more frequent allele at each SNP locus, with the weights being the allele substitution effects. The correlation between molecular breeding value and phenotype represented the accuracy of prediction. For all traits evaluated, accuracy across breeds was low, ranging between 0.007 and 0.414. Accuracy was least in data split 2, where the validation individuals had no pedigree relationship with animals in the training data. Given the low predictive ability observed, a large number of individuals may be needed for prediction when using such an admixed population. Further, these results suggest that breed composition of the target population in which the marker panels are likely to be used should be an important consideration when developing prediction equations across breeds, especially where an admixed population is used as the training data set.

Financial institutions have a large amount of data on their borrowers, which can be used to predict the probability of borrowers defaulting their loan or not. Some of the models that have been used to predict individual loan defaults include linear discriminant analysis models and extreme value theory models. These models are parametric in nature since they assume that the response being investigated takes a particular functional form. However, there is a possibility that the functional form used to estimate the response is very different from the actual functional form of the response. The purpose of this research was to analyze individual loan defaults in Kenya using the logistic regression model. The data used in this study was obtained from equity bank of Kenya for the period between 2006 to 2016. A random sample of 1000 loan applicants whose loans had been approved by equity bank of Kenya during this period was obtained. Data obtained was on the credit history, purpose of the loan, loan amount, nature of the saving account, employment status, sex of the applicant, age of the applicant, security used when acquiring the loan and the area of residence of the applicant (rural or urban). This study employed a quantitative research design, it deals with individual loans defaults as group characteristics of a borrower. The data was pre-processed by seeding using R- Software and then split into training dataset and test data set. The train data was used to train the logistic regression model by employing Supervised machine learning approach. The R-statistical software was used for the analysis of the data. The test data set was used to do cross-validation of the developed logistic model which later was used for analysis prediction of individual loan defaults. This study focused on the analysis of individual loan defaults in Kenya using the logistic regression model in Machine learning. The logistic regression model predicted 303 defaults from train data set, 122 non-defaults and misclassified loans were 56 and 69. The model had an accuracy of 0.7727 with the train data and 0.7333 with the test data. The logistic regression model showed a precision of 0.8440 and 0.8244 with the train and test data respectively. The performance of the model with both the train and test data was illustrated using a plot of train errors and test errors against sample size on the same axes. The plot showed that the performance of the model increases with an increase in sample size. The study recommended the use of logistic regression in conjunction with supervised machine learning approach in loan default prediction in financial institutions and also more research should be carried out on ensemble methods of loan defaults prediction in order to increase the prediction accuracy.

Radial Basis Function (RBF) metamodels have recently attracted increased interest due to their significant advantages over other types of non-parametric metamodels. However, because of the interpolation nature of the RBF mathematics, the accuracy of the model may dramatically deteriorate if the training data set used contains duplicate information, noise or outliers. Also constructing the metamodel may be time consuming whenever the training data sets are large or a high dimensional model is required. In this paper, we propose a robust and efficient RBF metamodeling approach based on data pre-processing techniques that alleviate the accuracy and efficiency issues commonly encountered when RBF models are used in typical real engineering situations. These techniques include 1) the removal of duplicate training data information, 2) the generation of smaller uniformly distributed subsets of training data from large data sets and 3) the quantification and identification of outliers by principal component analysis (PCA) and Hotelling statistics. Simulation results are used to validate the generalization accuracy and efficiency of the proposed approach.

IFN-signaling gene (ISG) expression scores are potential markers of inflammation with significance from cancer to genetic syndromes. In Aicardi Goutières Syndrome (AGS), a disorder of abnormal DNA and RNA metabolism, this score has potential as a diagnostic biomarker, although the approach to ISG calculation has not been standardized or validated. To optimize ISG calculation and validate ISG as a diagnostic biomarker, mRNA levels of 36 type I IFN response genes were quantified from 997 samples (including 334 AGS), and samples were randomized into training and test data sets. An independent validation cohort (n = 122) was also collected. ISGs were calculated using all potential combinations up to 6 genes. A 4-gene approach (IFI44L, IFI27, USP18, IFI6) was the best-performing model (AUC of 0.8872 [training data set], 0.9245 [test data set]). The majority of top-performing gene combinations included IFI44L. Performance of IFI44L alone was 0.8762 (training data set) and 0.9580 (test data set) by AUC. The top approaches were able to discriminate individuals with genetic interferonopathy from control samples. This study validates the context of use for the ISG score as a diagnostic biomarker and underscores the importance of IFI44L in diagnosis of genetic interferonopathies.

Three Biomarker Panel at Day 7 and 14 Can Predict Development of Grade II-IV Acute Graft-Versus-Host Disease

The coronavirus disease 2019 (COVID-19) pandemic continues to destroy human life around the world. Almost every country throughout the globe suffered from this pandemic, forcing various governments to apply different restrictions to reduce its impact. In this study, we compare different time-series models with the neural network autoregressive model (NNAR). The study used COVID-19 data in Pakistan from February 26, 2020, to February 18, 2022, as a training and testing data set for modeling. Different models were applied and estimated on the training data set, and these models were assessed on the testing data set. Based on the mean absolute scaled error (MAE) and root mean square error (RMSE) for the training and testing data sets, the NNAR model outperformed the autoregressive integrated moving average (ARIMA) model and other competing models indicating that the NNAR model is the most appropriate for forecasting. Forecasts from the NNAR model showed that the cumulative confirmed COVID-19 cases will be 1,597,180 and cumulative confirmed COVID-19 deaths will be 32,628 on April 18, 2022. We encourage the Pakistan Government to boost its immunization policy.

Bias in neural network model training datasets has been observed to decrease prediction accuracy for groups underrepresented in training data. Thus, investigating the composition of training datasets used in machine learning models with healthcare applications is vital to ensure equity. Two such machine learning models are NetMHCpan-4.1 and NetMHCIIpan-4.0, used to predict antigen binding scores to major histocompatibility complex class I and II molecules, respectively. As antigen presentation is a critical step in mounting the adaptive immune response, previous work has used these or similar predictions models in a broad array of applications, from explaining asymptomatic viral infection to cancer neoantigen prediction. However, these models have also been shown to be biased toward hydrophobic peptides, suggesting the network could also contain other sources of bias. Here, we report the composition of the networks' training datasets are heavily biased toward European Caucasian individuals and against Asian and Pacific Islander individuals. We test the ability of NetMHCpan-4.1 and NetMHCpan-4.0 to distinguish true binders from randomly generated peptides on alleles not included in the training datasets. Unexpectedly, we fail to find evidence that the disparities in training data lead to a meaningful difference in prediction quality for alleles not present in the training data. We attempt to explain this result by mapping the HLA sequence space to determine the sequence diversity of the training dataset. Furthermore, we link the residues which have the greatest impact on NetMHCpan predictions to structural features for three alleles (HLA-A*34:01, HLA-C*04:03, HLA-DRB1*12:02).

Validation of artificial intelligence prediction models for skin cancer diagnosis using dermoscopy images: the 2019 International Skin Imaging Collaboration Grand Challenge

The accuracy of computed tomography angiography (CTA) image interpretation depends on the radiologist. This study aims to develop a new method for automatically detecting intracranial aneurysms from CTA images using deep learning, based on a convolutional neural network (CNN) implemented on the DeepMedic platform. Ninety CTA scans of patients with intracranial aneurysms are collected and divided into two datasets: training (80 subjects) and test (10 subjects) datasets. Subsequently, a deep learning architecture with a three-dimensional (3D) CNN model is implemented on the DeepMedic platform for the automatic segmentation and detection of intracranial aneurysms from the CTA images. The samples in the training dataset are used to train the CNN model, and those in the test dataset are used to assess the performance of the established system. Sensitivity, positive predictive value (PPV), and false positives are evaluated. The overall sensitivity and PPV of this system for detecting intracranial aneurysms from CTA images are 92.3% and 100%, respectively, and the segmentation sensitivity is 92.3%. The performance of the system in the detection of intracranial aneurysms is closely related to their size. The detection sensitivity for small intracranial aneurysms (≤ 3mm) is 66.7%, whereas the sensitivity of detection for large (> 10mm) and medium-sized (3-10mm) intracranial aneurysms is 100%. The deep learning architecture with a 3D CNN model on the DeepMedic platform can reliably segment and detect intracranial aneurysms from CTA images with high sensitivity.

A comparison of turbine mass flow models based on pragmatic identification data sets for turbogenerator model development