Supervised Machine Learning Methods Research Articles

Estimating Code Vulnerability to Timing Errors Via Microarchitecture-Aware Machine Learning

This article addresses the microarchitecture-aware modeling of timing errors and the estimation of the vulnerability of SW programs to such errors. A significance-aware code vulnerability factor (SCVF) quantifies the susceptibility of applications to such timing errors, utilizing a machine learning (ML)-based error prediction model. This is complemented by a workloadaware error prediction model, which is based on supervised ML methods.

Clustering and prediction of disease progression trajectories in Huntington's disease: An analysis of Enroll-HD data using a machine learning approach.

Huntington's disease (HD) is a rare neurodegenerative disease characterized by cognitive, behavioral and motor symptoms that progressively worsen with time. Cognitive and behavioral signs of HD are generally present in the years prior to a diagnosis; however, manifest HD is typically assessed by genetic confirmation and/or the presence of unequivocal motor symptoms. Nevertheless, there is a large variation in symptom severity and rate of progression among individuals with HD. In this retrospective study, longitudinal natural history of disease progression was modeled in individuals with manifest HD from the global, observational Enroll-HD study (NCT01574053). Unsupervised machine learning (k-means; km3d) was used to jointly model clinical and functional disease measures simultaneously over time, based on one-dimensional clustering concordance such that individuals with manifest HD (N = 4,961) were grouped into three clusters: rapid (Cluster A; 25.3%), moderate (Cluster B; 45.5%) and slow (Cluster C; 29.2%) progressors. Features that were considered predictive of disease trajectory were then identified using a supervised machine learning method (XGBoost). The cytosine adenine guanine-age product score (a product of age and polyglutamine repeat length) at enrollment was the top predicting feature for cluster assignment, followed by years since symptom onset, medical history of apathy, body mass index at enrollment and age at enrollment. These results are useful for understanding factors that affect the global rate of decline in HD. Further work is needed to develop prognostic models of HD progression as these could help clinicians with individualized clinical care planning and disease management.

Entanglement detection with artificial neural networks

Quantum entanglement is one of the essential resources involved in quantum information processing tasks. However, its detection for usage remains a challenge. The Bell-type inequality for relative entropy of coherence serves as an entanglement witness for pure entangled states. However, it does not perform reliably for mixed entangled states. This paper constructs a classifier by employing the relationship between coherence and entanglement for supervised machine learning methods. This method encodes multiple Bell-type inequalities for the relative entropy of coherence into an artificial neural network to detect the entangled and separable states in a quantum dataset.

TIVAN-indel: a computational framework for annotating and predicting non-coding regulatory small insertions and deletions.

Small insertion and deletion (sindel) of human genome has an important implication for human disease. One important mechanism for non-coding sindel (nc-sindel) to have an impact on human diseases and phenotypes is through the regulation of gene expression. Nevertheless, current sequencing experiments may lack statistical power and resolution to pinpoint the functional sindel due to lower minor allele frequency or small effect size. As an alternative strategy, a supervised machine learning method can identify the otherwise masked functional sindels by predicting their regulatory potential directly. However, computational methods for annotating and predicting the regulatory sindels, especially in the non-coding regions, are underdeveloped. By leveraging labeled nc-sindels identified by cis-expression quantitative trait loci analyses across 44 tissues in Genotype-Tissue Expression (GTEx), and a compilation of both generic functional annotations and large-scale epigenomic profiles, we develop TIssue-specific Variant Annotation for Non-coding indel (TIVAN-indel), which is a supervised computational framework for predicting non-coding regulatory sindels. As a result, we demonstrate that TIVAN-indel achieves the best prediction performance in both with-tissue prediction and cross-tissue prediction. As an independent evaluation, we train TIVAN-indel from the 'Whole Blood' tissue in GTEx and test the model using 15 immune cell types from an independent study named Database of Immune Cell Expression. Lastly, we perform an enrichment analysis for both true and predicted sindels in key regulatory regions such as chromatin interactions, open chromatin regions and histone modification sites, and find biologically meaningful enrichment patterns. https://github.com/lichen-lab/TIVAN-indel. Supplementary data are available at Bioinformatics online.

Machine Learning-Based Ransomware Classification of Bitcoin Transactions

Ransomware attacks are one of the most dangerous related crimes in the coin market. To increase the challenge of fighting the attack, early detection of ransomware seems necessary. In this article, we propose a high-performance Bitcoin transaction predictive system that investigates Bitcoin payment transactions to learn data patterns that can recognize and classify ransomware payments for heterogeneous bitcoin networks into malicious or benign transactions. The proposed approach makes use of three supervised machine learning methods to learn the distinctive patterns in Bitcoin payment transactions, namely, logistic regression (LR), random forest (RF), and Extreme Gradient Boosting (XGBoost). We evaluate these ML-based predictive models on the BitcoinHeist ransomware dataset in terms of classification accuracy and other evaluation measures such as confusion matrix, recall, and F1-score. It turned out that the experimental results recorded by the XGBoost model achieved an accuracy of 99.08%. As a result, the resulting model accuracy is higher than many recent state-of-the-art models developed to detect ransomware payments in Bitcoin transactions.

A stochastic approximation approach to fixed instance selection

Instance selection plays a critical role in enhancing the efficacy and efficiency of machine learning tools when utilised for a data mining task. This study proposes a fixed instance selection algorithm based on simultaneous perturbation stochastic approximation that works in conjunction with any supervised machine learning method and any corresponding performance metric, which we call SpFixedIS. This algorithm provides an approximate solution to the NP-hard instance selection problem and additionally serves as a way of intelligently selecting a specified number of instances within a training set with regards to a machine learning model. The shape of the objective function obtained from the test accuracy against the number of instances selected is examined extensively for our instance selection algorithm. The SpFixedIS algorithm was tested on 43 diverse datasets across 6 different machine learning classifiers. The results show that in over 90% of cases SpFixedIS provides a statistically significant improvement at a 5% level with intelligent selection over random selection for the same number of instances. Furthermore, with respect to probabilistic models, specifically Gaussian Naive Bayes, SpFixedIS provides a statistically significant improvement compared to models that utilise the entirety of the training set in 84% of the experimented values ranging from 50 to 1000 instances.

Machine learning in general practice: scoping review of administrative task support and automation

BackgroundArtificial intelligence (AI) is increasingly used to support general practice in the early detection of disease and treatment recommendations. However, AI systems aimed at alleviating time-consuming administrative tasks currently appear limited. This scoping review thus aims to summarize the research that has been carried out in methods of machine learning applied to the support and automation of administrative tasks in general practice.MethodsDatabases covering the fields of health care and engineering sciences (PubMed, Embase, CINAHL with full text, Cochrane Library, Scopus, and IEEE Xplore) were searched. Screening for eligible studies was completed using Covidence, and data was extracted along nine research-based attributes concerning general practice, administrative tasks, and machine learning. The search and screening processes were completed during the period of April to June 2022.Results1439 records were identified and 1158 were screened for eligibility criteria. A total of 12 studies were included. The extracted attributes indicate that most studies concern various scheduling tasks using supervised machine learning methods with relatively low general practitioner (GP) involvement. Importantly, four studies employed the latest available machine learning methods and the data used frequently varied in terms of setting, type, and availability.ConclusionThe limited field of research developing in the application of machine learning to administrative tasks in general practice indicates that there is a great need and high potential for such methods. However, there is currently a lack of research likely due to the unavailability of open-source data and a prioritization of diagnostic-based tasks. Future research would benefit from open-source data, cutting-edge methods of machine learning, and clearly stated GP involvement, so that improved and replicable scientific research can be done.

A COMPARATIVE STUDY OF MACHINE LEARNING CLASSIFIERS FOR CROP TYPE MAPPING USING VEGETATION INDICES

Abstract. Timely and accurate mapping of crops is crucial for agriculture management, policy-making, and food security. Due to the differences in the product calendars of various crops, it is possible to classify them by investigating the remote sensing Vegetation Indices (VIs) during crop growth season. This study developed a VI-based mapping approach to specifying crop types based on phenological and spectral metrics derived from the sentinel-2 images. We used six spectral VIs (ARVI, CVI, EVI, LAI, GLI, and NDVI) in three supervised machine learning methods, including Random Forest (RF), GBoost (GB), and K-Nearest Neighborhood (KNN) for crop mapping. Field data consisting of wheat, barley, canola, vegetables, and a bare land class, were collected as the testing and training data set. The classification results were evaluated through test samples showing high overall accuracy (OA) and satisfactory class accuracies for the most dominant crop types across different fields despite the variability of planting and harvesting dates. Among the VIs utilized to crop mapping, the Atmospherically Resistant Vegetation Index (ARVI) in all three classification methods achieved better results. The overall accuracy of RF, GB, and KNN models with the ARVI index was 95%, 88%, and 90%, respectively.

Automatic Classification of Galaxy Morphology: A Rotationally-invariant Supervised Machine-learning Method Based on the Unsupervised Machine-learning Data Set

Classification of galaxy morphology is a challenging but meaningful task for the enormous amount of data produced by the next-generation telescope. By introducing the adaptive polar-coordinate transformation, we develop a rotationally-invariant supervised machine-learning (SML) method that ensures consistent classifications when rotating galaxy images, which is always required to be satisfied physically, but difficult to achieve algorithmically. The adaptive polar-coordinate transformation, compared with the conventional method of data augmentation by including additional rotated images in the training set, is proved to be an effective and efficient method in improving the robustness of the SML methods. In the previous work, we generated a catalog of galaxies with well-classified morphologies via our developed unsupervised machine-learning (UML) method. By using this UML data set as the training set, we apply the new method to classify galaxies into five categories (unclassifiable, irregulars, late-type disks, early-type disks, and spheroids). In general, the result of our morphological classifications following the sequence from irregulars to spheroids agrees well with the expected trends of other galaxy properties, including Sérsic indices, effective radii, nonparametric statistics, and colors. Thus, we demonstrate that the rotationally-invariant SML method, together with the previously developed UML method, completes the entire task of automatic classification of galaxy morphology.

Application of Machine Learning Methods for an Analysis of E-Nose Multidimensional Signals in Wastewater Treatment

The work represents a successful attempt to combine a gas sensors array with instrumentation (hardware), and machine learning methods as the basis for creating numerical codes (software), together constituting an electronic nose, to correct the classification of the various stages of the wastewater treatment process. To evaluate the multidimensional measurement derived from the gas sensors array, dimensionality reduction was performed using the t-SNE method, which (unlike the commonly used PCA method) preserves the local structure of the data by minimizing the Kullback-Leibler divergence between the two distributions with respect to the location of points on the map. The k-median method was used to evaluate the discretization potential of the collected multidimensional data. It showed that observations from different stages of the wastewater treatment process have varying chemical fingerprints. In the final stage of data analysis, a supervised machine learning method, in the form of a random forest, was used to classify observations based on the measurements from the sensors array. The quality of the resulting model was assessed based on several measures commonly used in classification tasks. All the measures used confirmed that the classification model perfectly assigned classes to the observations from the test set, which also confirmed the absence of model overfitting.

Design of N-11-Azaartemisinins Potentially Active against <i>Plasmodium falciparum</i> by Combined Molecular Electrostatic Potential, Ligand-Receptor Interaction and Models Built with Supervised Machine Learning Methods

N-11-azaartemisinins potentially active against Plasmodium falciparum are designed by combining molecular electrostatic potential (MEP), ligand-receptor interaction, and models built with supervised machine learning methods (PCA, HCA, KNN, SIMCA, and SDA). The optimization of molecular structures was performed using the B3LYP/6-31G* approach. MEP maps and ligand-receptor interactions were used to investigate key structural features required for biological activities and likely interactions between N-11-azaartemisinins and heme, respectively. The supervised machine learning methods allowed the separation of the investigated compounds into two classes: cha and cla, with the properties εLUMO+1 (one level above lowest unoccupied molecular orbital energy), d(C6-C5) (distance between C6 and C5 atoms in ligands), and TSA (total surface area) responsible for the classification. The insights extracted from the investigation developed and the chemical intuition enabled the design of sixteen new N-11-azaartemisinins (prediction set), moreover, models built with supervised machine learning methods were applied to this prediction set. The result of this application showed twelve new promising N-11-azaartemisinins for synthesis and biological evaluation.

Borderline shades: Morphometric features predict borderline personality traits but not histrionic traits

Borderline personality disorder (BPD) is one of the most diagnosed disorders in clinical settings. Besides the fully diagnosed disorder, borderline personality traits (BPT) are quite common in the general population. Prior studies have investigated the neural correlates of BPD but not of BPT. This paper investigates the neural correlates of BPT in a subclinical population using a supervised machine learning method known as Kernel Ridge Regression (KRR) to build predictive models. Additionally, we want to determine whether the same brain areas involved in BPD are also involved in subclinical BPT. Recent attempts to characterize the specific role of resting state-derived macro networks in BPD have highlighted the role of the default mode network. However, it is not known if this extends to the subclinical population. Finally, we wanted to test the hypothesis that the same circuitry that predicts BPT can also predict histrionic personality traits. Histrionic personality is sometimes considered a milder form of BPD, and making a differential diagnosis between the two may be difficult. For the first time KRR was applied to structural images of 135 individuals to predict BPT, based on the whole brain, on a circuit previously found to correctly classify BPD, and on the five macro-networks. At a whole brain level, results show that frontal and parietal regions, as well as the Heschl’s area, the thalamus, the cingulum, and the insula, are able to predict borderline traits. BPT predictions increase when considering only the regions limited to the brain circuit derived from a study on BPD, confirming a certain overlap in brain structure between subclinical and clinical samples. Of all the five macro networks, only the DMN successfully predicts BPD, confirming previous observations on its role in the BPD. Histrionic traits could not be predicted by the BPT circuit. The results have implications for the diagnosis of BPD and a dimensional model of personality.

An olfactory perceptual fingerprint in people with olfactory dysfunction due to COVID-19.

The sense of smell is based on sensory detection of the molecule(s), which is then further perceptually interpreted. A possible measure of olfactory perception is an odor-independent olfactory perceptual fingerprint (OPF) defined by Snitz et al. We aimed to investigate whether OPF can distinguish patients with olfactory dysfunction (OD) due to coronavirus disease (COVID-19) from controls and which perceptual descriptors are important for that separation. Our study included 99 healthy controls and 41 patients. They rated 10 odors using 8 descriptors such as "pleasant," "intense," "familiar," "warm," "cold," "irritating," "edible," and "disgusting." An unsupervised machine learning method, hierarchical cluster analysis, showed that OPF can distinguish patients from controls with an accuracy of 83%, a sensitivity of 51%, and a specificity of 96%. Furthermore, a supervised machine learning method, random forest classifier, showed that OPF can distinguish patients and controls in the testing dataset with an accuracy of 86%, a sensitivity of 64%, and a specificity of 96%. Principal component analysis and random forest classifier showed that familiarity and intensity were the key qualities to explain the variance of the data. In conclusion, people with COVID-19-related OD have a fundamentally different olfactory perception.

Implementation Graph Database Framework for Credit Card Fraud Detection

Credit card use is becoming more and more commonplace every day. Financial organizations and credit card customers lose a lot of money because of complicated illegal transactions. Fraudsters constantly stay on top of new technology to quickly perpetrate fraud against customer transaction patterns. We analyze credit card transaction networks and identify suspicious patterns, such as transactions connected to multiple accounts or unusual transaction patterns, transactions made at unusual times, and to monitor credit card transactions in real-time and quickly identify suspicious transactions. TigerGraph is used to analyze data, display results on a dashboard, and send notifications via email. One meth’\\Vc 1``13-od commonly used in anomaly detection is to compare data values against the standard deviation. In this research, we explain the use of TigerGraph as a platform for anomaly detection above the standard deviation, as well as the use of the Louvain algorithm in finding merchant communities used by fraudsters. The data used in this study comes from Sparkov simulation data obtained from Kaggle. Our results show that by using TigerGraph, we managed to achieve a very high accuracy rate of 99.77%, precision 82.84%, recall 72.38%, and f1-score 77,26% in predicting transaction fraud on Sparkov simulation data. This is much better than the results reported in a paper that uses the supervised machine learning method with the AdaBoost algorithm which achieves the highest accuracy of 77%.

New Spam Filtering Method with Hadoop Tuning-Based MapReduce Na飗e Bayes

As the importance of email increases, the amount of malicious email is also increasing, so the need for malicious email filtering is growing. Since it is more economical to combine commodity hardware consisting of a medium server or PC with a virtual environment to use as a single server resource and filter malicious email using machine learning techniques, we used a Hadoop MapReduce framework and Naïve Bayes among machine learning methods for malicious email filtering. Naïve Bayes was selected because it is one of the top machine learning methods(Support Vector Machine (SVM), Naïve Bayes, K-Nearest Neighbor(KNN), and Decision Tree) in terms of execution time and accuracy. Malicious email was filtered with MapReduce programming using the Naïve Bayes technique, which is a supervised machine learning method, in a Hadoop framework with optimized performance and also with the Python program technique with the Naïve Bayes technique applied in a bare metal server environment with the Hadoop environment not applied. According to the results of a comparison of the accuracy and predictive error rates of the two methods, the Hadoop MapReduce Naïve Bayes method improved the accuracy of spam and ham email identification 1.11 times and the prediction error rate 14.13 times compared to the non-Hadoop Python Naïve Bayes method.

Data-driven model for process evaluation in wire EDM

To digitalize the wire EDM process, data-driven models are necessary for evaluating its performance. This presents a challenge due to the high volume of data and the stochastic nature of the process. In this paper, electrical parameters are measured and processed by an FPGA (field programmable gate array) system to recognize and characterize temporally and spatially resolved single discharges as either normal or abnormal. Supervised machine learning methods such as artificial neural networks (ANN) are used and models are trained with different data sets to predict the machined geometrical accuracy and cutting speed based on recorded process data.

Fine-tuning optimization of poly lactic acid impact strength with variation of plasticizer using simple supervised machine learning methods

Fine-tuning optimization of poly lactic acid impact strength with variation of plasticizer using simple supervised machine learning methods

A mathematical modelling approach for analysing the risk of low back pain in college students using student desks

Low back pain (LBP) is frequently experienced by the occupational population who are necessitated to use chairs daily. At least one study has shown that disc degeneration can start as early as the teenage years. Moreover, college students spend excessive amounts of time sitting on non-ergonomic desks. The aim of our study was to determine if college students are entering the work force predisposed to LBP. An anonymous survey was conducted on 280 students and modelling was conducted using three approaches: machine learning, dynamical systems, and regression analysis. Supervised machine learning methods showed back pain can be predicted with high accuracy from the questionnaire. Mathematical predictive modelling was employed to determine the risk of chronic back pain as a result of using the student desks. Results from the models indicated college students are experiencing significantly more back pain than has been reported in studies on the general population.

Growth Indexes and Yield Prediction of Summer Maize in China Based on Supervised Machine Learning Method

Leaf area index and dry matter mass are important indicators for crop growth and yields. In order to solve the problem of predicting the summer maize growth index and yield under different soil quality and field management conditions, this study proposes a prediction model based on the supervised machine learning regression algorithm. Firstly, the data pool was constructed by collecting the measured data for maize in the main planting area. The total water input (rainfall plus irrigation water), fertilization, soil quality, and planting density were selected as the training set. Then, the maximum leaf area index (LAImax), maximum dry material mass (Dmax), and summer maize yields (Y) in the data pool were trained by using Gaussian regression (rational quadratic kernel function and Matern kernel function), support vector machine (SVM) and linear regression models. The training models were verified with the data-set not included in the data pool, and the water and fertilizer coupling functions were developed. The prediction results showed that compared to the support vector machine models and the linear regression models, the Gaussian regression prediction models comprising the rational quadratic and Matern kernel functions had good prediction accuracy. The coefficients of determination (R2) of the prediction results were 0.91, 0.89 and 0.88; the root-mean-square errors (RMSEs) were 0.3, 1138.6 and 666.16 kg/hm2; and the relative root-mean-square errors (rRMSEs) were 6.3%, 5.94% and 6.53% for LAImax, Dmax and Y, respectively. The optimal total water inputs and nitrogen applications indicated by the prediction results and the water and fertilizer coupling functions were consistent with the measured range from the field tests. The supervised machine learning regression algorithm provides a simple method to predict the yield of maize and optimize the total water inputs and nitrogen applications using only the soil quality and planting density.

Hetnet connectivity search provides rapid insights into how biomedical entities are related.

Hetnets, short for "heterogeneous networks," contain multiple node and relationship types and offer a way to encode biomedical knowledge. One such example, Hetionet, connects 11 types of nodes-including genes, diseases, drugs, pathways, and anatomical structures-with over 2 million edges of 24 types. Previous work has demonstrated that supervised machine learning methods applied to such networks can identify drug repurposing opportunities. However, a training set of known relationships does not exist for many types of node pairs, even when it would be useful to examine how nodes of those types are meaningfully connected. For example, users may be curious about not only how metformin is related to breast cancer but also how a given gene might be involved in insomnia. We developed a new procedure, termed hetnet connectivity search, that proposes important paths between any 2 nodes without requiring a supervised gold standard. The algorithm behind connectivity search identifies types of paths that occur more frequently than would be expected by chance (based on node degree alone). Several optimizations were required to precompute significant instances of node connectivity at the scale of large knowledge graphs. We implemented the method on Hetionet and provide an online interface at https://het.io/search. We provide an open-source implementation of these methods in our new Python package named hetmatpy.