Supervised Machine Learning Methods Research Articles

Abstract 4138272: CMR Quantification of Myocardial Oxygenation Extraction Fraction Maps Using a Model-based Self-supervised Learning Network: Initial Experience in Patients with Cardiomyopathies

Background: Measurements of myocardial oxygenation extraction fraction (mOEF) maps with cardiovascular magnetic resonance (CMR) has been recently developed to assess myocardial oxygen metabolism in healthy. Recent studies focus on developing supervised machine learning methods to improve the quantification of mOEF. However, these supervised learning methods may be limited by the lack of ground-truth mOEF maps because MRI cannot directly measure mOEF with the same precision as PET. Hypothesis: Model-based self-supervised learning neural networks maybe feasible to generate mOEF maps accurately. Aims: To develop a physical model-based self-supervised learning neural network to accurately estimate mOEF for the patients with a variety of cardiomyopathies. Methods: An ECG triggered, two-dimensional asymmetric spin-echo (ASE) prepared sequence was employed to scan 71 patients with dilated, hypertrophic, or ischemic cardiomyopathies. At least 3 slices were scanned for each patient and each ASE scan was performed free-breathing with a spatial resolution of 1.7 × 1.7 × 8 mm 3 and scan time of 18 RR-interval. Acquisition of late gadolinium enhancement (LGE) was performed in each patient after the administration of 0.15 mmol/kg gadolinium agent for the visualization of myocardial infarction regions. A fully convolutional neural network with U-Net architecture was optimized with a physical model-based signal loss function (see Figure 1) on the ASE training dataset from 67 patients to generate mOEF maps. To evaluate if the method can accurately quantify abnormal mOEF, four patients with myocardial infarction were selected as the test set. Results: A previous publication reported normal mOEF levels at approximately 0.6-0.7 in healthy subjects. Figure 2 shows our proposed method generated mOEF maps from two representative patients and their LGE images for comparisons. In comparison with the remote region (mOEF = 0.70±0.10), the mOEF of myocardial regions with infarction was significantly lower (mOEF = 0.36±0.12, p < 0.001). The infarction areas predicted by the network overlapped well with the LGE. Conclusion: Quantification of mOEF using the proposed model-based self-supervised U-Net is feasible to detect abnormalities in regional myocardial oxygenation. Current study is ongoing to evaluate the proposed technique in a large cardiac patient dataset.

The application of template matching and novel unsupervised and supervised machine learning methodology to forensic hair analysis

ABSTRACT Hair pigmentation is a valuable feature in forensic hair analysis and hair comparisons. Microscopic pigmentation features from participants' hair were classified and documented. The discriminating power of template matching, unsupervised and supervised machine learning methods were compared to determine which method best distinguished between participants and accurately assigned hairto an individual, based on pigmentation features. Template matching analysis revealed a higher frequency of inter-person matches compared to intra-person matches, and the unsupervised model’s predicted labels did not align with true labels. These findings suggest the presence of an unknown dimensionality beyond the observable pigmentation features used in forensic hair classification, highlighting the crucial role of forensic expertise. In contrast, supervised machine learning demonstrated superior accuracy and greater interpretability due to its training on labelled data, making it more appropriate for forensic applications. This research underscores the continued importance of human expertise, particularly in the initial classification of training data for supervised machine learning. The potential applications of supervised machine learning in forensic science include training, competency testing and rapid intelligence as a novel and innovative tool while advancing the field towards more objective methodologies.

Polytope Fraud Theory

Polytope Fraud Theory (PFT) extends the existing triangle and diamond theories of accounting fraud with ten abnormal financial practice alarms that a fraudulent firm might trigger. These warning signals are identified through evaluation of the shorting behavior of sophisticated activist short sellers, which are used to train several supervised machine learning methods in detecting financial statement fraud using published accounting data. Our contributions include a systematic manual collection and labeling of companies that are shorted by professional activist short sellers. We also combine well-known asset pricing factors with accounting red flags in financial features selections. Using 80 % of the data for training and the remaining 20 % for out-of-sample test and performance assessment, we find that the best method is XGBoost, with a Recall of 72 % and F1-score of 82 %. Other methods have relatively lower performance, demonstrating the robustness of our results. This shows that the sophisticated activist short sellers, from whom the algorithms are learning, have excellent accounting insights, tremendous forensic analytical knowledge, and sharp business acumen. Our feature importance analysis indicates that potential short-selling targets share many similar financial characteristics, such as bankruptcy or financial distress risk, clustering in some industries, inconsistency of profitability, high accrual, and unreasonable business operations. Our results imply the possible automation of advanced financial statement analysis, which can both improve auditing processes and effectively enhance investment performance. Finally, we propose the Unified Investor Protection Framework, summarizing and categorizing investor-protection related theories from the macro-level to the micro-level.

The Application of Selected Supervised Machine Learning Methods in the Classification of Family Businesses in the Context of Cluster Formation

The Application of Selected Supervised Machine Learning Methods in the Classification of Family Businesses in the Context of Cluster Formation

A Systematic Review of Features Forecasting Patient Arrival Numbers.

Adequate nurse staffing is crucial for quality healthcare, necessitating accurate predictions of patient arrival rates. These forecasts can be determined using supervised machine learning methods. Optimization of machine learning methods is largely about minimizing the prediction error. Existing models primarily utilize data such as historical patient visits, seasonal trends, holidays, and calendars. However, it is unclear what other features reduce the prediction error. Our systematic literature review identifies studies that use supervised machine learning to predict patient arrival numbers using nontemporal features, which are features not based on time or dates. We scrutinized 26 284 studies, eventually focusing on 27 relevant ones. These studies highlight three main feature groups: weather data, internet search and usage data, and data on (social) interaction of groups. Internet data and social interaction data appear particularly promising, with some studies reporting reduced errors by up to 33%. Although weather data are frequently used, its utility is less clear. Other potential data sources, including smartphone and social media data, remain largely unexplored. One reason for this might be potential data privacy challenges. In summary, although patient arrival prediction has become more important in recent years, there are still many questions and opportunities for future research on the features used in this area.

Enhancing search pipelines for short gravitational-wave transients with Gaussian mixture modeling

We present an enhanced method for the application of Gaussian mixture modeling (GMM) to the coherent WaveBurst (cWB) algorithm in the search for short-duration gravitational wave (GW) transients. The supervised machine learning method of GMM allows for the multidimensional distributions of noise and signal to be modeled over a set of representative attributes, which aids in the classification of GW signals against noise transients (glitches) in the data. We demonstrate that updating the approach to model construction eliminates bias previously seen in the GMM analysis, increasing the robustness and sensitivity of the analysis over a wider range of burst source populations. The enhanced methodology is applied to the generic burst all-sky short search in the LIGO-Virgo full third observing run (O3), marking the first application of GMM to the 3 detector Livingston-Hanford-Virgo network. For both 2- and 3- detector networks, we observe comparable sensitivities to an array of generic signal morphologies, with significant sensitivity improvements to waveforms in the low quality factor parameter space at false alarm rates of 1 per 100 years. This proves that GMM can effectively mitigate blip glitches, which are one of the most problematic sources of noise for unmodeled GW searches. The cWB-GMM search recovers similar numbers of compact binary coalescence (CBC) events as other cWB postproduction methods, and concludes on no new gravitational wave detection after known CBC events are removed. Published by the American Physical Society 2024

Unravelling incipient accidents: a machine learning prediction of incident risks in highway operations

PurposeSafety research has focused on drivers, pedestrians and vehicles, with scarce attention given to highway traffic officers (HTOs). This paper develops a robust prediction model which enables highway safety authorities to predict exclusive incidents occurring on the highway such as incursions and environmental hazards, respond effectively to diverse safety risk incident scenarios and aid in timely safety precautions to minimise HTO incidents.Design/methodology/approachUsing data from a highway incident database, a supervised machine learning method that employs three algorithms [namely Support Vector Machine (SVM), Random Forests (RF) and Naïve Bayes (NB)] was applied, and their performances were comparatively analysed. Three data balancing algorithms were also applied to handle the class imbalance challenge. A five-phase sequential method, which includes (1) data collection, (2) data pre-processing, (3) model selection, (4) data balancing and (5) model evaluation, was implemented.FindingsThe findings indicate that SVM with a polynomial kernel combined with the Synthetic Minority Over-sampling Technique (SMOTE) algorithm is the best model to predict the various incidents, and the Random Under-sampling (RU) algorithm was the most inefficient in improving model accuracy. Weather/visibility, age range and location were the most significant factors in predicting highway incidents.Originality/valueThis is the first study to develop a prediction model for HTOs and utilise an incident database solely dedicated to HTOs to forecast various incident outcomes in highway operations. The prediction model will provide evidence-based information to safety officers to train HTOs on impending risks predicted by the model thereby equipping workers with resilient shocks such as awareness, anticipation and flexibility.

Renewable energy technology innovation and ESG greenwashing: Evidence from supervised machine learning methods using patent text

As global environmental pollution worsens, environmental governance has become a critical aspect of corporate development. In environmental, social, and governance (ESG) risk management, how firms address the threat of greenwashing has emerged as a central focus in achieving sustainable green development. This study explores an under-researched factor contributing to ESG greenwashing: renewable energy technology innovation (RETI). Using supervised machine learning and text analysis methods, the study constructs a proxy variable for RETI and applies it to a sample of Chinese listed companies. The findings reveal that RETI reduces corporate ESG greenwashing, and this effect remains consistent after a series of endogeneity and robustness tests. The inhibitory impact of RETI on ESG greenwashing is more significant when board experiential diversity and media attention are higher. This study contributes to the theoretical basis and demonstration for the research on RETI, greenwashing, managerial experience, and corporate governance.

The application of machine learning for identifying frailty in older patients during hospital admission

BackgroundEarly identification of frail patients and early interventional treatment can minimize the frailty-related medical burden. This study investigated the use of machine learning (ML) to detect frailty in hospitalized older adults with acute illnesses.MethodsWe enrolled inpatients of the geriatric medicine ward at Taichung veterans general hospital between 2012 and 2022. We compared four ML models including logistic regression, random forest (RF), extreme gradient boosting, and support vector machine (SVM) for the prediction of frailty. The feature window as well as the prediction window was set as half a year before admission. Furthermore, Shapley additive explanation plots and partial dependence plots were used to identify Fried’s frailty phenotype for interpreting the model across various levels including domain, feature, and individual aspects.ResultsWe enrolled 3367 patients. Of these, 2843 were frail. We used 21 features to train the prediction model. Of the 4 tested algorithms, SVM yielded the highest AUROC, precision and F1-score (78.05%, 94.53% and 82.10%). Of the 21 features, age, gender, multimorbidity frailty index, triage, hemoglobin, neutrophil ratio, estimated glomerular filtration rate, blood urea nitrogen, and potassium were identified as more impactful due to their absolute values.ConclusionsOur results demonstrated that some easily accessed parameters from the hospital clinical data system can be used to predict frailty in older hospitalized patients using supervised ML methods.

An empirical isochrone archive for nearby open clusters

Context. The ages of star clusters and co-moving stellar groups contain essential information about the Milky Way. Their special properties and placement throughout the galactic disk make them excellent tracers of galactic structure and key components to unlocking its star formation history. Yet, even though the importance of stellar population ages has been widely recognized, their determination remains a challenging task often associated with highly model-dependent and uncertain results. Aims. We propose a new approach to this long-standing problem, which relies on empirical isochrones of known clusters extracted from high-quality observational data. These purely observation-based data products open up the possibility of relative age determination, free of stellar evolution model assumptions. Methods. For the derivation of the empirical isochrones, we used a combination of the statistical analysis tool principal component analysis for preprocessing and the supervised machine learning method support vector regression for curve extraction. To improve the statistical reliability of our result, we defined the empirical isochrone of a color-magnitude diagram (CMD) of a cluster as the median calculated from a set of nboot = 1000 curves derived from bootstrapped data. The algorithm requires no physical priors, is computationally fast, and can easily be generalized over a large range of CMD combinations and evolutionary stages of clusters. Results. We provide empirical isochrones in all Gaia DR2 and DR3 color combinations for 83 nearby clusters (d < 500 pc), which cover an estimated age range of 7 Myr to 3 Gyr. In doing so, we pave the way for a relative comparison between individual stellar populations based on an age-scaling ladder of empirical isochrones of known clusters. Furthermore, due to the exceptional precision of the available observational data, we report accurate lower main sequence empirical isochrones for many clusters in our sample, which are of special interest as this region is known to be especially complex to model. We validate our method and results by comparing the extracted empirical isochrones to cluster ages in the literature. We also investigate the added information that empirical isochrones covering the lower main sequence can provide on case studies of the IC 4665 cluster and the Meingast 1 stream. Conclusions. The archive of empirical isochrones offers a novel approach to validating age estimates and can be used as an age-scaling ladder or age brackets for new populations and serve as calibration data for further constraining stellar evolution models.

A comprehensive in silico analysis and experimental validation of miRNAs capable of discriminating between lung adenocarcinoma and squamous cell carcinoma.

Accurate differentiation between lung adenocarcinoma (AC) and lung squamous cell carcinoma (SCC) is crucial owing to their distinct therapeutic approaches. MicroRNAs (miRNAs) exhibit variable expression across subtypes, making them promising biomarkers for discrimination. This study aimed to identify miRNAs with robust discriminatory potential between AC and SCC and elucidate their clinical significance. MiRNA expression profiles for AC and SCC patients were obtained from The Cancer Genome Atlas (TCGA) database. Differential expression analysis and supervised machine learning methods (Support Vector Machine, Decision trees and Naïve Bayes) were employed. Clinical significance was assessed through receiver operating characteristic (ROC) curve analysis, survival analysis, and correlation with clinicopathological features. Validation was conducted using reverse transcription quantitative polymerase chain reaction (RT-qPCR). Furthermore, signaling pathway and gene ontology enrichment analyses were conducted to unveil biological functions. Five miRNAs (miR-205-3p, miR-205-5p, miR-944, miR-375 and miR-326) emerged as potential discriminative markers. The combination of miR-944 and miR-326 yielded an impressive area under the curve of 0.985. RT-qPCR validation confirmed their biomarker potential. miR-326 and miR-375 were identified as prognostic factors in AC, while miR-326 and miR-944 correlated significantly with survival outcomes in SCC. Additionally, exploration of signaling pathways implicated their involvement in key pathways including PI3K-Akt, MAPK, FoxO, and Ras. This study enhances our understanding of miRNAs as discriminative markers between AC and SCC, shedding light on their role as prognostic indicators and their association with clinicopathological characteristics. Moreover, it highlights their potential involvement in signaling pathways crucial in non-small cell lung cancer pathogenesis.

Assessment of a probabilistic supervised machine learning method to estimate biomass expansion and conversion factors: A case study on cedar and pine trees.

Assessment of a probabilistic supervised machine learning method to estimate biomass expansion and conversion factors: A case study on cedar and pine trees.

Performance Comparison of Supervised Machine Learning Methods in Classifying Celestial Objects

In recent times, astronomy has entered a new era with rapidly growing data sources and advanced observation techniques. The construction of powerful telescopes has enabled the collection of spectral data from millions of celestial objects. However, the increasing number and variety of data have made it challenging to categorize these celestial objects. This study employs machine learning methods to address the fundamental problem of classifying stars, galaxies, and quasars in astronomy. The dataset underwent detailed preprocessing to identify effective features for classification. KNIME Analytics Platform was used for data analysis and visualization, facilitating rapid and efficient data analysis through its drag-and-drop interface. Among the machine learning methods used in our study—Decision Trees, Random Forest, and Naive Bayes—the highest accuracy rate of 97.86% was achieved with the Random Forest model. Notably, despite its lower overall performance compared to other models, the Naive Bayes classifier exhibited superior performance in distinguishing the STAR class, which is one of the study's interesting findings. Future studies aim to enhance model accuracy by using larger and more diverse datasets and exploring different machine learning algorithms. Additionally, the impact of deep learning methods on classification performance will be investigated.

Preparation for CSST: Star-galaxy Classification using a Rotationally Invariant Supervised Machine Learning Method

Most existing star-galaxy classifiers depend on the reduced information from catalogs, necessitating careful data processing and feature extraction. In this study, we employ a supervised machine learning method (GoogLeNet) to automatically classify stars and galaxies in the COSMOS field. Unlike traditional machine learning methods, we introduce several preprocessing techniques, including noise reduction and the unwrapping of denoised images in polar coordinates, applied to our carefully selected samples of stars and galaxies. By dividing the selected samples into training and validation sets in an 8:2 ratio, we evaluate the performance of the GoogLeNet model in distinguishing between stars and galaxies. The results indicate that the GoogLeNet model is highly effective, achieving accuracies of 99.6% and 99.9% for stars and galaxies, respectively. Furthermore, by comparing the results with and without preprocessing, we find that preprocessing can significantly improve classification accuracy (by approximately 2.0% to 6.0%) when the images are rotated. In preparation for the future launch of the China Space Station Telescope (CSST), we also evaluate the performance of the GoogLeNet model on the CSST simulation data. These results demonstrate a high level of accuracy (approximately 99.8%), indicating that this model can be effectively utilized for future observations with the CSST.

Remote sensing framework for geological mapping via stacked autoencoders and clustering

Supervised machine learning methods for geological mapping via remote sensing face limitations due to the scarcity of accurately labelled training data that can be addressed by unsupervised learning, such as dimensionality reduction and clustering. Dimensionality reduction methods have the potential to play a crucial role in improving the accuracy of geological maps. Although conventional dimensionality reduction methods may struggle with nonlinear data, unsupervised deep learning models such as autoencoders can model non-linear relationships. Stacked autoencoders feature multiple interconnected layers to capture hierarchical data representations useful for remote sensing data. We present an unsupervised machine learning-based framework for processing remote sensing data using stacked autoencoders for dimensionality reduction and k-means clustering for mapping geological units. We use Landsat 8, ASTER, and Sentinel-2 datasets to evaluate the framework for geological mapping of the Mutawintji region in Western New South Wales, Australia. We also compare stacked autoencoders with principal component analysis (PCA) and canonical autoencoders. Our results reveal that the framework produces accurate and interpretable geological maps, efficiently discriminating rock units. The results reveal that the combination of stacked autoencoders with Sentinel-2 data yields the best performance accuracy when compared to other combinations. We find that stacked autoencoders enable better extraction of complex and hierarchical representation of the input data when compared to canonical autoencoders and PCA. We also find that the generated maps align with prior geological knowledge of the study area while providing novel insights into geological structures.

Optimization of reliability and speed of the end-of-line quality inspection of electric motors using machine learning

Consistently maintaining high-end product quality in the production process is challenging. End-quality inspection must be highly sensitive to detect even minimal deviations, while being fast and accurate. However, quality inspection systems often face calibration intricacies, are time-consuming, and rely heavily on expert knowledge. They handle substantial data flows and inspect numerous features, some of which contribute minimally to the final grade. To address these challenges, the paper proposes employing statistically supervised machine learning methods for classification. Decision trees, Random forests, Bagging, and Gradient boosting classifiers are recommended for feature selection and accurate diagnosis, particularly for electric motor classification. By utilizing the feature importance attribute for feature selection, the proposed approach compares model accuracies, reducing rampup and commission times significantly. The study found that all suggested classifiers achieved high accuracy in classifying electric motors in end-of-line quality inspection system. Moreover, they effectively reduced the number of features and optimize database operations. Utilizing a reduced feature set streamlined diagnostic algorithms, accelerated learning, and improved model interpretability, enhancing overall efficiency and comprehension. Furthermore, analysing the feature importance attribute could simplify diagnostic hardware and expedite quality inspection by eliminating unnecessary steps. Newly generated models can also verify expert decisions on feature selection and limit adjustments, enhancing efficiency in production processes.

Stock Return Prediction under US Federal Funds Rate Hike Based on Supervised Machine Learning

As US Federal Reverse Systems has continued to raise federal funds in the past few years in order to curb inflation, this has had a huge impact on chinese capital market. Investors and financial institude are actively engaged in predicting stock returns to maximize their investment income. This study constructs a model to analyze and predict the financial factor of stock income based on supervised machine learning methods and evaluate the results. The datasample is extracted from wind, for the period half a year before and after the recent federal funds rate hike. Utilizing machine learning packages in R, this paper construct models based on linear discriminant analysis, decision tree and random forest models. After constructing estimation models, this paper visualizes the prediction result by utilizing drawing package in R. It has been found that the random forest algorithm predicting model generates very successful results for the financial factor prediction as the model accuracy reaches 99%. According to the analysis, relevant model to predict financial factors and non-financial factors based on non-linear supervised machine learning algorithm can be built by investors or hedge fund agency to estimate stock performance in the future. This study also investigates the economic result of the Federal Funds Rate hikes, which is instructive for investors to make well-informed decisions.

A machine learning analysis of the value-added intellectual coefficient’s effect on firm performance

Purpose Recently, machine learning (ML) methods gained popularity in finance and accounting research as alternatives to econometric analysis. Their success in high-dimensional settings is promising as a cure for the shortcomings of econometric analysis. The purpose of this study is to prove further the relationship between intellectual capital (IC) efficiency and firm performance using ML methods. Design/methodology/approach This study used the double selection, partialing-out and cross-fit partialing-out LASSO estimators to analyze the IC efficiency’s linear and nonlinear effects on firm performance using a sample of 2,581 North American firms from 1999 to 2021. The value-added intellectual capital (VAIC) and its components are used as indicators of IC efficiency. Firm performance is measured by return on equity, return on assets and market-to-book ratio. Findings The findings revealed significant connections between IC measures and firm performance. First, the VAIC, as an aggregate measure, significantly impacts both firm profitability and value. When the VAIC is decomposed into its breakdowns, it is revealed that structural capital efficiency substantially affects firm value, and capital employed efficiency has the same function for firm profitability. In contrast to the prevalent belief in the area, human capital efficiency’s impact is found to be less important than the others. Nonlinearities are also detected in the relationships. Originality/value As ML tools are most recently introduced to the IC literature, only a few studies have used them to expand the current knowledge. However, none of these studies investigated the role of IC as a determinant of firm performance. The present study fills this gap in the literature by investigating the effect of IC efficiency on firm performance using supervised ML methods. It also provides a novel approach by comparing the estimation results of three LASSO estimators. To the best of the author’s knowledge, this is the first study that has used LASSO in IC research.

Passive sensing data predicts stress in university students: a supervised machine learning method for digital phenotyping.

University students are particularly susceptible to developing high levels of stress, which occur when environmental demands outweigh an individual's ability to cope. The growing advent of mental health smartphone apps has led to a surge in use by university students seeking ways to help them cope with stress. Use of these apps has afforded researchers the unique ability to collect extensive amounts of passive sensing data including GPS and step detection. Despite this, little is known about the relationship between passive sensing data and stress. Further, there are no established methodologies or tools to predict stress from passive sensing data in this group. In this study, we establish a clear machine learning-based methodological pipeline for processing passive sensing data and extracting features that may be relevant in the context of mental health. We then use this methodology to determine the relationship between passive sensing data and stress in university students. In doing so, we offer the first proof-of-principle data for the utility of our methodological pipeline and highlight that passive sensing data can indeed digitally phenotype stress in university students. Australia New Zealand Clinical Trials Registry (ANZCTR), identifier ACTRN12621001223820.

Extended Fayans energy density functional: optimization and analysis

The Fayans energy density functional (EDF) has been very successful in describing global nuclear properties (binding energies, charge radii, and especially differences of radii) within nuclear density functional theory. In a recent study, supervised machine learning methods were used to calibrate the Fayans EDF. Building on this experience, in this work we explore the effect of adding isovector pairing terms, which are responsible for different proton and neutron pairing fields, by comparing a 13D model without the isovector pairing term against the extended 14D model. At the heart of the calibration is a carefully selected heterogeneous dataset of experimental observables representing ground-state properties of spherical even–even nuclei. To quantify the impact of the calibration dataset on model parameters and the importance of the new terms, we carry out advanced sensitivity and correlation analysis on both models. The extension to 14D improves the overall quality of the model by about 30%. The enhanced degrees of freedom of the 14D model reduce correlations between model parameters and enhance sensitivity.