Machine Learning Methods For Analysis Research Articles

Comparative Analysis of Machine Learning Methods for Predicting Robotized Incremental Metal Sheet Forming Force.

This paper proposes a method for extracting information from the parameters of a single point incremental forming (SPIF) process. The measurement of the forming force using this technology helps to avoid failures, identify optimal processes, and to implement routine control. Since forming forces are also dependent on the friction between the tool and the sheet metal, an innovative solution has been proposed to actively control the friction forces by modulating the vibrations that replace the environmentally unfriendly lubrication of contact surfaces. This study focuses on the influence of mechanical properties, process parameters and sheet thickness on the maximum forming force. Artificial Neural Network (ANN) and different machine learning (ML) algorithms have been applied to develop an efficient force prediction model. The predicted forces agreed reasonably well with the experimental results. Assuming that the variability of each input function is characterized by a normal distribution, sampling data were generated. The applicability of the models in an industrial environment is due to their relatively high performance and the ability to balance model bias and variance. The results indicate that ANN and Gaussian process regression (GPR) have been identified as the most efficient methods for developing forming force prediction models.

Comparative Analysis of Machine learning Methods to Identify signs of suspicious Transactions of Credit Institutions and Their Clients

In the field of financial monitoring, it is necessary to promptly obtain objective assessments of economic entities (in particular, credit institutions) for effective decision-making. Automation of the process of identifying unscrupulous credit institutions based on machine learning methods will allow regulatory authorities to quickly identify and suppress illegal activities. The aim of the research is to substantiate the possibilities of using machine learning methods and algorithms for the automatic identification of unscrupulous credit institutions. It is required to select a mathematical toolkit for analyzing data on credit institutions, which allows tracking the involvement of a bank in money laundering processes. The paper provides a comparative analysis of the results of processing data on the activities of credit institutions using classification methods — logistic regression, decision trees. The author applies support vector machine and neural network methods, Bayesian networks (Two-Class Bayes Point Machine), and anomaly search — an algorithm of a One-Class Support Vector Machine and a PCA-Based Anomaly Detection algorithm. The study presents the results of solving the problem of classifying credit institutions in terms of possible involvement in money laundering processes, the results of analyzing data on the activities of credit institutions by methods of detecting anomalies. A comparative analysis of the results obtained using various modern algorithms for the classification and search for anomalies is carried out. The author concluded that the PCA-Based Anomaly Detection algorithm showed more accurate results compared to the One-Class Support Vector Machine algorithm. Of the considered classification algorithms, the most accurate results were shown by the Two-Class Boosted Decision Tree (AdaBoost) algorithm. The research results can be used by the Bank of Russia and Rosfinmonitoring to automate the identification of unscrupulous credit institutions

A Hyperspectral Library of Foliar Diseases of Wheat.

This work established a hyperspectral library of important foliar diseases of wheat induced by different fungal pathogens, representing a time series from infection to symptom appearance for the purpose of detecting spectral changes. The data were generated under controlled conditions at the leaf scale. The transition from healthy to diseased leaf tissue was assessed, and spectral shifts were identified and used in combination with histological investigations to define developmental stages in pathogenesis for each disease. The spectral signatures of each plant disease that indicate a specific developmental stage during pathogenesis, defined as turning points, were combined into a spectral library. Machine learning analysis methods were applied and compared to test the potential of this library to detect and quantify foliar diseases in hyperspectral images. All evaluated classifiers had high accuracy (≤99%) for the detection and identification of both biotrophic and necrotrophic fungi. The potential of applying spectral analysis methods in combination with a spectral library for the detection and identification of plant diseases is demonstrated. Further evaluation and development of these algorithms should contribute to a robust detection and identification system for plant diseases at different developmental stages and the promotion and development of site-specific management techniques for plant diseases under field conditions.

Exploratory analysis of machine learning methods in predicting subsurface temperature and geothermal gradient of Northeastern United States

Geothermal scientists have used bottom-hole temperature data from extensive oil and gas well datasets to generate heat flow and temperature-at-depth maps to locate potential geothermally active regions. Considering that there are some uncertainties and simplifying assumptions associated with the current state of physics-based models, in this study, the applicability of several machine learning models is evaluated for predicting temperature-at-depth and geothermal gradient parameters. Through our exploratory analysis, it is found that XGBoost and Random Forest result in the highest accuracy for subsurface temperature prediction. Furthermore, we apply our model to regions around the sites to provide 2D continuous temperature maps at three different depths using XGBoost model, which can be used to locate prospective geothermally active regions. We also validate the proposed XGBoost and DNN models using an extra dataset containing measured temperature data along the depth for 58 wells in the state of West Virginia. Accuracy measures show that machine learning models are highly comparable to the physics-based model and can even outperform the thermal conductivity model. Also, a geothermal gradient map is derived for the whole region by fitting linear regression to the XGBoost-predicted temperatures along the depth. Finally, through our analysis, the most favorable geological locations are suggested for potential future geothermal developments.

Statistical and machine learning methods for analysis of multiplex protein data from a novel proximity extension assay in patients with ST-elevation myocardial infarction

Using data from patients with ST-elevation myocardial infarction (STEMI), we explored how machine learning methods can be used for analysing multiplex protein data obtained from proximity extension assays. Blood samples were obtained from 48 STEMI-patients at admission and after three months. A subset of patients also had blood samples obtained at four and 12 h after admission. Multiplex protein data were obtained using a proximity extension assay. A random forest model was used to assess the predictive power and importance of biomarkers to distinguish between the acute and the stable phase. The similarity of response profiles was investigated using K-means clustering. Out of 92 proteins, 26 proteins were found to significantly distinguish the acute and the stable phase following STEMI. The five proteins tissue factor pathway inhibitor, azurocidin, spondin-1, myeloperoxidase and myoglobin were found to be highly important for differentiating between the acute and the stable phase. Four of these proteins shared response profiles over the four time-points. Machine learning methods can be used to identify and assess novel predictive biomarkers as showcased in the present study population of patients with STEMI.

A Comparative Analysis of Machine Learning Methods for Joint Attention Classification in Autism Spectrum Disorder Using Electroencephalography Brain Computer Interface

A Comparative Analysis of Machine Learning Methods for Joint Attention Classification in Autism Spectrum Disorder Using Electroencephalography Brain Computer Interface

Comparative Analysis of Machine Learning Methods to Detect Chronic Kidney Disease

Chronic Kidney disease (CKD) is a lifelong health hazard that can cause the failure of kidneys. Symptoms of this develop slowly and are not obvious. Early detection of Chronic Kidney Disease can lead to significant progress in finding the cure for this disease. Through this study, we aim to employ ML techniques for the prediction and diagnosis of Chronic Kidney Disease. The findings obtained from our predictive analysis combined with the expertise of healthcare professionals can help in making an accurate prognosis. For this, we have used a dataset containing data from 400 individuals acquired from the University of California Irvine (UCI) repository. Various feature selection techniques have been used to optimize the number of features affecting Chronic Kidney Disease. Subsequently, these desirable features are chosen and used in different ML models and their accuracy, sensitivity is compared. Multiple Machine learning algorithms have been explored such as Logistic Regression, Naïve Bayes, KNN, SVM, Decision Trees, Random Forest Classifier, and Extra Trees Classifier. It was concluded that Decision Trees using information gain gave six optimal features and the Extra Trees Classifier model gives the best accuracy of 99.36 % with Extra Trees Classifier having one of the least execution times.

Radiomic and Genomic Machine Learning Method Performance for Prostate Cancer Diagnosis: Systematic Literature Review.

BackgroundMachine learning algorithms have been drawing attention at the joining of pathology and radiology in prostate cancer research. However, due to their algorithmic learning complexity and the variability of their architecture, there is an ongoing need to analyze their performance.ObjectiveThis study assesses the source of heterogeneity and the performance of machine learning applied to radiomic, genomic, and clinical biomarkers for the diagnosis of prostate cancer. One research focus of this study was on clearly identifying problems and issues related to the implementation of machine learning in clinical studies.MethodsFollowing the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) protocol, 816 titles were identified from the PubMed, Scopus, and OvidSP databases. Studies that used machine learning to detect prostate cancer and provided performance measures were included in our analysis. The quality of the eligible studies was assessed using the QUADAS-2 (quality assessment of diagnostic accuracy studies–version 2) tool. The hierarchical multivariate model was applied to the pooled data in a meta-analysis. To investigate the heterogeneity among studies, I2 statistics were performed along with visual evaluation of coupled forest plots. Due to the internal heterogeneity among machine learning algorithms, subgroup analysis was carried out to investigate the diagnostic capability of machine learning systems in clinical practice.ResultsIn the final analysis, 37 studies were included, of which 29 entered the meta-analysis pooling. The analysis of machine learning methods to detect prostate cancer reveals the limited usage of the methods and the lack of standards that hinder the implementation of machine learning in clinical applications.ConclusionsThe performance of machine learning for diagnosis of prostate cancer was considered satisfactory for several studies investigating the multiparametric magnetic resonance imaging and urine biomarkers; however, given the limitations indicated in our study, further studies are warranted to extend the potential use of machine learning to clinical settings. Recommendations on the use of machine learning techniques were also provided to help researchers to design robust studies to facilitate evidence generation from the use of radiomic and genomic biomarkers.

Partial least squares and machine learning for the prediction of intramuscular fat content of lamb loin

Given the paucity of lamb carcase grading tools, there is a distinct need for the development of rapid, non-destructive grading tools for Australian lamb carcases, particularly fat content given its importance to meat and eating quality. The aim of the current study was to determine the potential for Near Infrared (NIR) spectroscopy to predict IMF using Partial Least Squares (PLS) and machine learning analysis methods. As such, 299 lamb loins were measured using a NIR fibre optic device, a sample was excised for Soxhlet determination of IMF content and prediction models were created using either PLS or machine learning analyses methods. IMF prediction model outcomes were similar between analysis methods with an R2 = 0.6 and RMSE = 0.84 and R2 = 0.65 and RMSE = 0.72, respectively. This study highlighted that spectra from one slaughter varied greatly from the two succeeding slaughters and wavelengths selected between studies are not consistent.

Experimental analysis of machine learning methods for credit score classification

Credit scoring concerns with emerging empirical model to assist the financial institutions for financial decision-making process. Credit risk analysis plays a vital role for decision-making process; statistical and machine learning approaches are utilized to estimate the risk associated with a credit applicant. Enhancing the performance of credit scoring model, particularly toward non-trustworthy “or non-creditworthy” group, may result incredible effect for financial institution. However, credit scoring data may have excess and unimportant data and features which degrades the performance of model. So, selection of important features (or reduction in irrelevant and redundant features) may play the key role for improving the effectiveness and reducing the complexity of the model. This study presents a experimental results analysis of various combinations of feature selection approaches with various classification approaches and impact of feature selection approaches. For experimental results analysis, nine feature selection and sixteen classification state-of-the-art approaches have been applied on seven benched marked credit scoring datasets.

Prediction of secondary testosterone deficiency using machine learning: A comparative analysis of ensemble and base classifiers, probability calibration, and sampling strategies in a slightly imbalanced dataset

Testosterone is the most important male sex hormone, and its deficiency brings many physical and mental harms. Efficiently identifying individuals with low testosterone is crucial prior to starting proper treatment. However, routine monitoring of testosterone levels can be costly in many regions, resulting in an underreporting of cases, especially in developing countries. Moreover, there are few studies that employ machine learning (ML) in prognosticating testosterone deficiency. This research, therefore, aims to offer a coherent comparative analysis of machine learning methods that can predict testosterone deficiency without having patients undergo costly medical tests. In doing so, we seek to provide to the urological community a publicly available dataset ( https://github.com/osmarluiz/Testosterone-Deficiency-Dataset ) to increase research in this yet untapped field. For this analysis, we used ten base classifiers (optimized with grid search stratified K-fold cross-validation); three ensemble methods; and eight sampling strategies to analyze a total of 3397 patients. The analysis was based on six features (age; abdominal circumference; triglycerides; high-density lipoprotein; diabetes; and hypertension), all of which were obtained by low-cost exams. We compared the sampling strategies and the classifiers' performance on an independent test set using ranking (PR-AUC), probabilistic (Brier score), and threshold metrics. We found that: (1) within the ranking metrics, sampling strategies did not enhance results in this slightly imbalanced (4:1 ratio) dataset; (2) the ensemble classifier using weighted average presented the best performance; (3) the best base classifier was XGBoost; (4) calibration showed significant improvement for the sampling strategies and slight improvements for the no sampling strategy; (5) the McNemar's test presented statistically similar results among all classifiers; and (6) abdominal circumference (AC) had by far the highest feature importance, followed by triglycerides (TG). Age showed very little significance in predicting testosterone deficiency.

Assessment of the actual shape of the hot-rolled strip cross-section contour. Part 2. Profile Classifier

The geometric parameters describing the features of the crosssectional profile of a hot-rolled strips do not give a complete picture of the flatness acquired by the cold-rolled strips rolled from these strips. An additional analysis, the results of which are presented in Message 1, showed that there are four characteristic classes of cross-sectional profiles of hot rolled strips that have a significant effect on the shape of the strips during cold rolling, three of which negatively affect the flatness of the cold rolled strips. The cross-sectional profiles of hot-rolled strips with a concave middle part and / or marginal thickenings lead to the appearance of edge waviness, peak-like cross-sectional profiles cause central warping. Therefore, the actual task is to determine the factual shape of cross-sectional profile. 6th order polynomials were used to digitalize and parameterize hot-rolled profile. As a result, we developed analytic function of the transverse profile, which keeps important information about its near-edge areas and features in the middle part. To assign a specific crosssectional profile of a hot-rolled strip to one of four characteristic classes of cross-sections, mathematical software was developed, called a classifier, and implemented with the programming environment R. To classify the profiles of the hot-rolled cross-section according to characteristic classes, a linear discriminant method was used as a machine learning method analysis. The result is an adequate mathematical model for recognizing the shape of the cross-sectional profile. The study was carried out with the financial support of the Russian Foundation for Basic Research within the framework of scientific project No. 19-38-90257.

Comparative analysis of machine learning methods by the example of the problem of determining muon decay

The history of using machine learning algorithms to analyze statistical models is quite long. The development of computer technology has given these algorithms a new breath. Nowadays deep learning is mainstream and most popular area in machine learning. However, the authors believe that many researchers are trying to use deep learning methods beyond their applicability. This happens because of the widespread availability of software systems that implement deep learning algorithms, and the apparent simplicity of research. All this motivate the authors to compare deep learning algorithms and classical machine learning algorithms. The Large Hadron Collider experiment is chosen for this task, because the authors are familiar with this scientific field, and also because the experiment data is open source. The article compares various machine learning algorithms in relation to the problem of recognizing the decay reaction + + + at the Large Hadron Collider. The authors use open source implementations of machine learning algorithms. We compare algorithms with each other based on calculated metrics. As a result of the research, we can conclude that all the considered machine learning methods are quite comparable with each other (taking into account the selected metrics), while different methods have different areas of applicability.

Profiles’ classifier of hot-rolled rolling

The geometric parameters describing the features of the cross-sectional profile of the hot-rolled strips do not give a complete picture of the flatness acquired by the cold-rolled strips rolled from these strips. An additional analysis showed that there are four characteristic classes of cross-sectional profiles of hot rolled strips that have a significant effect on the shape of the strips during cold rolling, three of which negatively affect the flatness of the cold rolled strips. The cross-sectional profiles of hot-rolled strips with a concave middle part and (or) marginal thickenings lead to the appearance of edge waviness, peak-like cross-sectional profiles cause central warping. Therefore, the actual task is to determine the factual shape of cross-sectional profile. Sixth order polynomials were used to digitalize and parameterize hot-rolled profile. As a result, we developed analytic function of the transverse profile, which keeps important information about its near-edge areas and features in the middle part. To assign a specific cross-sectional profile of a hot-rolled strip to one of four characteristic classes of cross-sections, mathematical software was developed, called a classifier, and implemented with the programming environment R. To classify the profiles of the hot-rolled cross-section according to characteristic classes, a linear discriminant method was used as a machine learning method analysis. The result is an adequate mathematical model for recognizing the shape of the cross-sectional profile.

A Comparative Analysis of Machine Learning Methods for Image Compression

A Comparative Analysis of Machine Learning Methods for Image Compression

An Alternative Credit Scoring System in China's Consumer Lending Market: A System Based on Digital Footprint Data

Ever since the late 1990s, China has experienced explosive growth in consumer lending, especially in short-term consumer loans, among which, the growth rate of non-bank lending has surpassed bank lending due to the development in financial technology. On the other hand, China does not have a universal credit scoring and registration system that can guide lenders during the processes of credit evaluation and risk control, for example, an individual’s bank credit records are not available for online lenders to see and vice versa. Given this context, the purpose of this paper is three-fold. First, we explore if and how alternative digital footprint data can be utilized to assess borrower’s creditworthiness. Then, we perform a comparative analysis of machine learning methods for the canonical problem of credit default prediction. Finally, we analyze, from an institutional point of view, the necessity of establishing a viable and nationally universal credit registration and scoring system utilizing online digital footprints, so that more people in China can have better access to the consumption loan market. Two different types of digital footprint data are utilized to match with bank’s loan default records. Each separately captures distinct dimensions of a person’s characteristics, such as his shopping patterns and certain aspects of his personality or inferred demographics revealed by social media features like profile image and nickname. We find both datasets can generate either acceptable or excellent prediction results, and different types of data tend to complement each other to get better performances. Typically, the traditional types of data banks normally use like income, occupation, and credit history, update over longer cycles, hence they can’t reflect more immediate changes, like the financial status changes caused by business crisis; whereas digital footprints can update daily, weekly, or monthly, thus capable of providing a more comprehensive profile of the borrower’s credit capabilities and risks. From the empirical and quantitative examination, we believe digital footprints can become an alternative information source for creditworthiness assessment, because of their near-universal data coverage, and because they can by and large resolve the thin-file issue, due to the fact that digital footprints come in much larger volume and higher frequency.

A Comparative Analysis of Machine Learning Methods for Class Imbalance in a Smoking Cessation Intervention

Smoking is one of the major public health issues, which has a significant impact on premature death. In recent years, numerous decision support systems have been developed to deal with smoking cessation based on machine learning methods. However, the inevitable class imbalance is considered a major challenge in deploying such systems. In this paper, we study an empirical comparison of machine learning techniques to deal with the class imbalance problem in the prediction of smoking cessation intervention among the Korean population. For the class imbalance problem, the objective of this paper is to improve the prediction performance based on the utilization of synthetic oversampling techniques, which we called the synthetic minority over-sampling technique (SMOTE) and an adaptive synthetic (ADASYN). This has been achieved by the experimental design, which comprises three components. First, the selection of the best representative features is performed in two phases: the lasso method and multicollinearity analysis. Second, generate the newly balanced data utilizing SMOTE and ADASYN technique. Third, machine learning classifiers are applied to construct the prediction models among all subjects and each gender. In order to justify the effectiveness of the prediction models, the f-score, type I error, type II error, balanced accuracy and geometric mean indices are used. Comprehensive analysis demonstrates that Gradient Boosting Trees (GBT), Random Forest (RF) and multilayer perceptron neural network (MLP) classifiers achieved the best performances in all subjects and each gender when SMOTE and ADASYN were utilized. The SMOTE with GBT and RF models also provide feature importance scores that enhance the interpretability of the decision-support system. In addition, it is proven that the presented synthetic oversampling techniques with machine learning models outperformed baseline models in smoking cessation prediction.

A comparative analysis of machine learning methods for emotion recognition using EEG and peripheral physiological signals

Emotion recognition using brain signals has the potential to change the way we identify and treat some health conditions. Difficulties and limitations may arise in general emotion recognition software due to the restricted number of facial expression triggers, dissembling of emotions, or among people with alexithymia. Such triggers are identified by studying the continuous brainwaves generated by human brain. Electroencephalogram (EEG) signals from the brain give us a more diverse insight on emotional states that one may not be able to express. Brainwave EEG signals can reflect the changes in electrical potential resulting from communications networks between neurons. This research involves analyzing the epoch data from EEG sensor channels and performing comparative analysis of multiple machine learning techniques [namely Support Vector Machine (SVM), K-nearest neighbor, Linear Discriminant Analysis, Logistic Regression and Decision Trees each of these models] were tested with and without principal component analysis (PCA) for dimensionality reduction. Grid search was also utilized for hyper-parameter tuning for each of the tested machine learning models over Spark cluster for lowered execution time. The DEAP Dataset was used in this study, which is a multimodal dataset for the analysis of human affective states. The predictions were based on the labels given by the participants for each of the 40 1-min long excerpts of music. music. Participants rated each video in terms of the level of arousal, valence, like/dislike, dominance and familiarity. The binary class classifiers were trained on the time segmented, 15 s intervals of epoch data, individually for each of the 4 classes. PCA with SVM performed the best and produced an F1-score of 84.73% with 98.01% recall in the 30th to 45th interval of segmentation. For each of the time segments and “a binary training class” a different classification model converges to a better accuracy and recall than others. The results prove that different classification models must be used to identify different emotional states.

Empirical Asset Pricing via Machine Learning

Abstract We perform a comparative analysis of machine learning methods for the canonical problem of empirical asset pricing: measuring asset risk premiums. We demonstrate large economic gains to investors using machine learning forecasts, in some cases doubling the performance of leading regression-based strategies from the literature. We identify the best-performing methods (trees and neural networks) and trace their predictive gains to allowing nonlinear predictor interactions missed by other methods. All methods agree on the same set of dominant predictive signals, a set that includes variations on momentum, liquidity, and volatility. Authors have furnished an Internet Appendix, which is available on the Oxford University Press Web site next to the link to the final published paper online.

Towards automatically filtering fake news in Portuguese

In the last years, the popularity of smartphones and social networks has been contributing to the spread of fake news. Through these electronic media, this type of news can deceive thousands of people in a short time and cause great harm to individuals, companies, or society. Fake news has the potential to change a political scenario, to contribute to the spread of diseases, and even to cause deaths. Despite the efforts of several studies on fake news detection, most of them only cover English language news. There is a lack of labeled datasets of fake news in other languages and, moreover, important questions still remain open. For example, there is no consensus on what are the best classification strategies and sets of features to be used for automatic fake news detection. To answer this and other important open questions, we present a new public and real dataset of labeled true and fake news in Portuguese, and we perform a comprehensive analysis of machine learning methods for fake news detection. The experiments were performed using different sets of features and employing different types of classification methods. A careful analysis of the results provided sufficient evidence to respond appropriately to the open questions. The various evaluated scenarios and the drawn conclusions from the results shed light on the potentiality of the methods and on the challenges that fake news detection presents.