Applications of Machine Learning for the Classification of Porcine Reproductive and Respiratory Syndrome Virus Sublineages Using Amino Acid Scores of ORF5 Gene

Porcine reproductive and respiratory syndrome is an infectious disease of pigs caused by PRRS virus (PRRSV). A modified live-attenuated vaccine has been widely used to control the spread of PRRSV and the classification of field strains is a key for a successful control and prevention. Restriction fragment length polymorphism targeting the Open reading frame 5 (ORF5) genes is widely used to classify PRRSV strains but showed unstable accuracy. Phylogenetic analysis is a powerful tool for PRRSV classification with consistent accuracy but it demands large computational power as the number of sequences gets increased. Our study aimed to apply four machine learning (ML) algorithms, random forest, k-nearest neighbor, support vector machine and multilayer perceptron, to classify field PRRSV strains into four clades using amino acid scores based on ORF5 gene sequence. Our study used amino acid sequences of ORF5 gene in 1931 field PRRSV strains collected in the US from 2012 to 2020. Phylogenetic analysis was used to labels field PRRSV strains into one of four clades: Lineage 5 or three clades in Linage 1. We measured accuracy and time consumption of classification using four ML approaches by different size of gene sequences. We found that all four ML algorithms classify a large number of field strains in a very short time (<2.5 s) with very high accuracy (>0.99 Area under curve of the Receiver of operating characteristics curve). Furthermore, the random forest approach detects a total of 4 key amino acid positions for the classification of field PRRSV strains into four clades. Our finding will provide an insightful idea to develop a rapid and accurate classification model using genetic information, which also enables us to handle large genome datasets in real time or semi-real time for data-driven decision-making and more timely surveillance.

Download Full-text

Phybrata Sensors and Machine Learning for Enhanced Neurophysiological Diagnosis and Treatment

Sensors ◽

10.3390/s21217417 ◽

2021 ◽

Vol 21 (21) ◽

pp. 7417

Author(s):

Alex J. Hope ◽

Utkarsh Vashisth ◽

Matthew J. Parker ◽

Andreas B. Ralston ◽

Joshua M. Roper ◽

...

Keyword(s):

Machine Learning ◽

Time Series ◽

Random Forest ◽

Binary Classification ◽

Classification Performance ◽

Support Vector ◽

Use Case ◽

Signal Features ◽

Test Population

Concussion injuries remain a significant public health challenge. A significant unmet clinical need remains for tools that allow related physiological impairments and longer-term health risks to be identified earlier, better quantified, and more easily monitored over time. We address this challenge by combining a head-mounted wearable inertial motion unit (IMU)-based physiological vibration acceleration (“phybrata”) sensor and several candidate machine learning (ML) models. The performance of this solution is assessed for both binary classification of concussion patients and multiclass predictions of specific concussion-related neurophysiological impairments. Results are compared with previously reported approaches to ML-based concussion diagnostics. Using phybrata data from a previously reported concussion study population, four different machine learning models (Support Vector Machine, Random Forest Classifier, Extreme Gradient Boost, and Convolutional Neural Network) are first investigated for binary classification of the test population as healthy vs. concussion (Use Case 1). Results are compared for two different data preprocessing pipelines, Time-Series Averaging (TSA) and Non-Time-Series Feature Extraction (NTS). Next, the three best-performing NTS models are compared in terms of their multiclass prediction performance for specific concussion-related impairments: vestibular, neurological, both (Use Case 2). For Use Case 1, the NTS model approach outperformed the TSA approach, with the two best algorithms achieving an F1 score of 0.94. For Use Case 2, the NTS Random Forest model achieved the best performance in the testing set, with an F1 score of 0.90, and identified a wider range of relevant phybrata signal features that contributed to impairment classification compared with manual feature inspection and statistical data analysis. The overall classification performance achieved in the present work exceeds previously reported approaches to ML-based concussion diagnostics using other data sources and ML models. This study also demonstrates the first combination of a wearable IMU-based sensor and ML model that enables both binary classification of concussion patients and multiclass predictions of specific concussion-related neurophysiological impairments.

Download Full-text

Damage Classification of Composites Using Machine Learning

Volume 13: Safety Engineering, Risk, and Reliability Analysis ◽

10.1115/imece2019-11851 ◽

2019 ◽

Author(s):

Shweta Dabetwar ◽

Stephen Ekwaro-Osire ◽

João Paulo Dias

Keyword(s):

Machine Learning ◽

Composite Materials ◽

Random Forest ◽

Condition Monitoring ◽

Machine Learning Algorithms ◽

Support Vector ◽

Damage Classification ◽

Combining Data ◽

Ultrasonic Measurements

Abstract Composite materials have tremendous and ever-increasing applications in complex engineering systems; thus, it is important to develop non-destructive and efficient condition monitoring methods to improve damage prediction, thereby avoiding catastrophic failures and reducing standby time. Nondestructive condition monitoring techniques when combined with machine learning applications can contribute towards the stated improvements. Thus, the research question taken into consideration for this paper is “Can machine learning techniques provide efficient damage classification of composite materials to improve condition monitoring using features extracted from acousto-ultrasonic measurements?” In order to answer this question, acoustic-ultrasonic signals in Carbon Fiber Reinforced Polymer (CFRP) composites for distinct damage levels were taken from NASA Ames prognostics data repository. Statistical condition indicators of the signals were used as features to train and test four traditional machine learning algorithms such as K-nearest neighbors, support vector machine, Decision Tree and Random Forest, and their performance was compared and discussed. Results showed higher accuracy for Random Forest with a strong dependency on the feature extraction/selection techniques employed. By combining data analysis from acoustic-ultrasonic measurements in composite materials with machine learning tools, this work contributes to the development of intelligent damage classification algorithms that can be applied to advanced online diagnostics and health management strategies of composite materials, operating under more complex working conditions.

Download Full-text

CPT Data Interpretation Employing Different Machine Learning Techniques

Geosciences ◽

10.3390/geosciences11070265 ◽

2021 ◽

Vol 11 (7) ◽

pp. 265

Author(s):

Stefan Rauter ◽

Franz Tschuchnigg

Keyword(s):

Machine Learning ◽

Grain Size ◽

Random Forest ◽

Classification Model ◽

Machine Learning Techniques ◽

Support Vector ◽

Learning Models ◽

Cone Penetration ◽

Tip Resistance ◽

Machine Learning Models

The classification of soils into categories with a similar range of properties is a fundamental geotechnical engineering procedure. At present, this classification is based on various types of cost- and time-intensive laboratory and/or in situ tests. These soil investigations are essential for each individual construction site and have to be performed prior to the design of a project. Since Machine Learning could play a key role in reducing the costs and time needed for a suitable site investigation program, the basic ability of Machine Learning models to classify soils from Cone Penetration Tests (CPT) is evaluated. To find an appropriate classification model, 24 different Machine Learning models, based on three different algorithms, are built and trained on a dataset consisting of 1339 CPT. The applied algorithms are a Support Vector Machine, an Artificial Neural Network and a Random Forest. As input features, different combinations of direct cone penetration test data (tip resistance qc, sleeve friction fs, friction ratio Rf, depth d), combined with “defined”, thus, not directly measured data (total vertical stresses σv, effective vertical stresses σ’v and hydrostatic pore pressure u0), are used. Standard soil classes based on grain size distributions and soil classes based on soil behavior types according to Robertson are applied as targets. The different models are compared with respect to their prediction performance and the required learning time. The best results for all targets were obtained with models using a Random Forest classifier. For the soil classes based on grain size distribution, an accuracy of about 75%, and for soil classes according to Robertson, an accuracy of about 97–99%, was reached.

Download Full-text

Enhanced Changeover Detection in Industry 4.0 Environments with Machine Learning

Sensors ◽

10.3390/s21175896 ◽

2021 ◽

Vol 21 (17) ◽

pp. 5896

Author(s):

Eddi Miller ◽

Vladyslav Borysenko ◽

Moritz Heusinger ◽

Niklas Niedner ◽

Bastian Engelmann ◽

...

Keyword(s):

Machine Learning ◽

Random Forest ◽

Binary Classification ◽

Model Performance ◽

Support Vector ◽

Milling Machine ◽

Vector Machines ◽

Changeover Times ◽

Flow Power

Changeover times are an important element when evaluating the Overall Equipment Effectiveness (OEE) of a production machine. The article presents a machine learning (ML) approach that is based on an external sensor setup to automatically detect changeovers in a shopfloor environment. The door statuses, coolant flow, power consumption, and operator indoor GPS data of a milling machine were used in the ML approach. As ML methods, Decision Trees, Support Vector Machines, (Balanced) Random Forest algorithms, and Neural Networks were chosen, and their performance was compared. The best results were achieved with the Random Forest ML model (97% F1 score, 99.72% AUC score). It was also carried out that model performance is optimal when only a binary classification of a changeover phase and a production phase is considered and less subphases of the changeover process are applied.

Download Full-text

Machine Learning Techniques for Land Use/Land Cover Classification of Medium Resolution Optical Satellite Imagery Focusing on Temporary Inundated Areas

Journal of Environmental Geography ◽

10.2478/jengeo-2020-0005 ◽

2020 ◽

Vol 13 (1-2) ◽

pp. 43-52

Author(s):

Boudewijn van Leeuwen ◽

Zalán Tobak ◽

Ferenc Kovács

Keyword(s):

Neural Network ◽

Machine Learning ◽

Land Use ◽

Land Cover ◽

Classification Model ◽

Machine Learning Techniques ◽

Support Vector ◽

Land Use Land Cover ◽

Learning Techniques

AbstractClassification of multispectral optical satellite data using machine learning techniques to derive land use/land cover thematic data is important for many applications. Comparing the latest algorithms, our research aims to determine the best option to classify land use/land cover with special focus on temporary inundated land in a flat area in the south of Hungary. These inundations disrupt agricultural practices and can cause large financial loss. Sentinel 2 data with a high temporal and medium spatial resolution is classified using open source implementations of a random forest, support vector machine and an artificial neural network. Each classification model is applied to the same data set and the results are compared qualitatively and quantitatively. The accuracy of the results is high for all methods and does not show large overall differences. A quantitative spatial comparison demonstrates that the neural network gives the best results, but that all models are strongly influenced by atmospheric disturbances in the image.

Download Full-text

Identification of Targeted Proteins by Jamu Formulas for Different Efficacies Using Machine Learning Approach

Life ◽

10.3390/life11080866 ◽

2021 ◽

Vol 11 (8) ◽

pp. 866

Author(s):

Sony Hartono Wijaya ◽

Farit Mochamad Afendi ◽

Irmanida Batubara ◽

Ming Huang ◽

Naoaki Ono ◽

...

Keyword(s):

Machine Learning ◽

Amino Acid ◽

Random Forest ◽

Prediction Models ◽

Amino Acid Sequences ◽

Support Vector ◽

Supporting Evidence ◽

Molecular Fingerprints ◽

Target Proteins ◽

Drug Candidates

Background: We performed in silico prediction of the interactions between compounds of Jamu herbs and human proteins by utilizing data-intensive science and machine learning methods. Verifying the proteins that are targeted by compounds of natural herbs will be helpful to select natural herb-based drug candidates. Methods: Initially, data related to compounds, target proteins, and interactions between them were collected from open access databases. Compounds are represented by molecular fingerprints, whereas amino acid sequences are represented by numerical protein descriptors. Then, prediction models that predict the interactions between compounds and target proteins were constructed using support vector machine and random forest. Results: A random forest model constructed based on MACCS fingerprint and amino acid composition obtained the highest accuracy. We used the best model to predict target proteins for 94 important Jamu compounds and assessed the results by supporting evidence from published literature and other sources. There are 27 compounds that can be validated by professional doctors, and those compounds belong to seven efficacy groups. Conclusion: By comparing the efficacy of predicted compounds and the relations of the targeted proteins with diseases, we found that some compounds might be considered as drug candidates.

Download Full-text

Machine learning in the diagnosis of Myocardial Infarction with Non-Obstructive Coronary Arteries

European Heart Journal ◽

10.1093/eurheartj/ehab724.3067 ◽

2021 ◽

Vol 42 (Supplement_1) ◽

Author(s):

M J Espinosa Pascual ◽

P Vaquero Martinez ◽

V Vaquero Martinez ◽

J Lopez Pais ◽

B Izquierdo Coronel ◽

...

Keyword(s):

Machine Learning ◽

Myocardial Infarction ◽

Support Vector Machine ◽

Logistic Regression ◽

Random Forest ◽

Obstructive Coronary Artery Disease ◽

Learning Algorithms ◽

Machine Learning Algorithms ◽

Classification Model ◽

Support Vector

Abstract Introduction Out of all patients admitted with Myocardial Infarction, 10 to 15% have Myocardial Infarction with Non-Obstructive Coronaries Arteries (MINOCA). Classification algorithms based on deep learning substantially exceed traditional diagnostic algorithms. Therefore, numerous machine learning models have been proposed as useful tools for the detection of various pathologies, but to date no study has proposed a diagnostic algorithm for MINOCA. Purpose The aim of this study was to estimate the diagnostic accuracy of several automated learning algorithms (Support-Vector Machine [SVM], Random Forest [RF] and Logistic Regression [LR]) to discriminate between people suffering from MINOCA from those with Myocardial Infarction with Obstructive Coronary Artery Disease (MICAD) at the time of admission and before performing a coronary angiography, whether invasive or not. Methods A Diagnostic Test Evaluation study was carried out applying the proposed algorithms to a database constituted by 553 consecutive patients admitted to our Hospital with Myocardial Infarction. According to the definitions of 2016 ESC Position Paper on MINOCA, patients were classified into two groups: MICAD and MINOCA. Out of the total 553 patients, 214 were discarded due to the lack of complete data. The set of machine learning algorithms was trained on 244 patients (training sample: 75%) and tested on 80 patients (test sample: 25%). A total of 64 variables were available for each patient, including demographic, clinical and laboratorial features before the angiographic procedure. Finally, the diagnostic precision of each architecture was taken. Results The most accurate classification model was the Random Forest algorithm (Specificity [Sp] 0.88, Sensitivity [Se] 0.57, Negative Predictive Value [NPV] 0.93, Area Under the Curve [AUC] 0.85 [CI 0.83–0.88]) followed by the standard Logistic Regression (Sp 0.76, Se 0.57, NPV 0.92 AUC 0.74 and Support-Vector Machine (Sp 0.84, Se 0.38, NPV 0.90, AUC 0.78) (see graph). The variables that contributed the most in order to discriminate a MINOCA from a MICAD were the traditional cardiovascular risk factors, biomarkers of myocardial injury, hemoglobin and gender. Results were similar when the 19 patients with Takotsubo syndrome were excluded from the analysis. Conclusion A prediction system for diagnosing MINOCA before performing coronary angiographies was developed using machine learning algorithms. Results show higher accuracy of diagnosing MINOCA than conventional statistical methods. This study supports the potential of machine learning algorithms in clinical cardiology. However, further studies are required in order to validate our results. FUNDunding Acknowledgement Type of funding sources: None. ROC curves of different algorithms

Download Full-text

Invisible experience to real-time assessment in elite tennis athlete training: Sport-specific movement classification based on wearable MEMS sensor data

Proceedings of the Institution of Mechanical Engineers Part P Journal of Sports Engineering and Technology ◽

10.1177/17543371211050312 ◽

2021 ◽

pp. 175433712110503

Author(s):

Mingyue Wu ◽

Ran Wang ◽

Yang Hu ◽

Mengjiao Fan ◽

Yufan Wang ◽

...

Keyword(s):

Machine Learning ◽

Real Time ◽

Learning Algorithms ◽

Machine Learning Algorithms ◽

Support Vector ◽

Test Accuracy ◽

Z Score ◽

Mems Sensor ◽

Score Normalization

This study examined the reliability of a tennis stroke classification and assessment platform consisting of a single low-cost MEMS sensor in a wrist-worn wearable device, smartphone, and computer. The data that was collected was transmitted via Bluetooth and analyzed by machine learning algorithms. Twelve right-handed male elite tennis athletes participated in the study, and each athlete performed 150 strokes. The results from three machine learning algorithms regarding their recognition and classification of the real-time data stream were compared. Stroke recognition and classification went through pre-processing, segmentation, feature extraction, and classification with Support Vector Machine (SVM), including SVM without normalization, SVM with Min–Max, SVM with Z-score normalization, K-nearest neighbor (K-NN), and Naive Bayes (NB) machine learning algorithms. During the data training process, 10-fold cross-validation was used to avoid overfitting and suitable parameters were found within the SVM classifiers. The best classifier was achieved when C = 1 using the RBF kernel function. Different machine learning algorithms’ classification of unique stroke types yielded highly reliable clusters within each stroke type with the highest test accuracy of 99% achieved by SVM with Min–Max normalization and 98.4% achieved using SVM with a Z-score normalization classifier.

Download Full-text

Automatic Identification of Rock Formation Type While Drilling Using Machine Learning Based Data-Driven Models

10.2118/201020-ms ◽

2021 ◽

Author(s):

Enrique Z. Losoya ◽

Narendra Vishnumolakala ◽

Samuel F. Noynaert ◽

Zenon Medina-Cetina ◽

Satish Bukkapatnam ◽

...

Keyword(s):

Machine Learning ◽

Random Forest ◽

Real Time ◽

Prediction Accuracy ◽

Classification Model ◽

Data Driven ◽

Classification Algorithms ◽

Rock Formation ◽

Mechanical Specific Energy ◽

Formation Type

Abstract The objective of this study is to present a novel rock formation identification model using a data-driven modeling approach. This study explores the use of real-time drilling data to train and validate a classification model to improve the efficiency of the drilling process by reducing Mechanical Specific Energy (MSE). In this study, we demonstrate the feasibility of a layer-based determination and change detection of properties of rock formation currently being drilled as accurately and fast as possible. Data for this study was collected from a custom-built lab-scale drilling rig equipped with multiple sensors. The experiment was conducted by drilling through an arrangement of different rock formations of varying rock strength properties. Data was recorded and stored at a frequency of 2 kHz, then filtered, processed, and downsampled to extract relevant features. This dataset was used to train an Artificial Neural Network and other machine learning classification algorithms. Feature selection was made first with ten most notable features found by Random Forest, and the second set with derived measurements and down-sampled dynamic features from the sensors. The classification analysis was divided into two steps: the best predictors/features extraction and classification model building. The models were trained using multiple classification algorithms, namely logistic regression, linear discriminant analysis (LDA), Support Vector Machines (SVM), Random Forest (RF), and Artificial Neural Networks (ANN). It was found that random forest and ANN performed the best with prediction accuracy of 99.48% and 99.58%, respectively, for the data set with ten most prominent features. The high prediction rate accuracy for the most prominent predictors suggests that if the high-frequency data can be processed in real-time, predicting what formation we are drilling in is possible to achieve in near real-time. This can lead to significant savings for drilling companies as optimal drilling parameters can be computed, and in turn, optimized Mechanical Specific Energy can be obtained in real-time. Since the rock formation identification is time-consuming, we also describe here an alternative approach using slightly less accurate but equally powerful dynamic predictors. In this case, we show that our dynamic predictor models with RF and ANN yielded prediction accuracy of 96.30% and 95.61%, respectively. Both the prominent feature and dynamic predictor approaches are described in detail in this paper. Our results suggest that accurately predicting rock formation type in real-time while drilling is very much feasible with lesser computational cost and complexity. This study provides the building blocks for the development of a completely autonomous downhole device and Electronic Device Recorders (EDR) that reduces the need for highly sophisticated sensors or data transmission processes downhole.

Download Full-text

Prediction of Antimalarial Drug-Decorated Nanoparticle Delivery Systems with Random Forest Models

Biology ◽

10.3390/biology9080198 ◽

2020 ◽

Vol 9 (8) ◽

pp. 198

Author(s):

Diana V. Urista ◽

Diego B. Carrué ◽

Iago Otero ◽

Sonia Arrasate ◽

Viviana F. Quevedo-Tumailli ◽

...

Keyword(s):

Machine Learning ◽

Random Forest ◽

Information Fusion ◽

High Performance ◽

Antimalarial Activity ◽

Classification Model ◽

Operating Characteristics ◽

Experimental Conditions ◽

Nanoparticle Delivery ◽

Random Forest Models

Drug-decorated nanoparticles (DDNPs) have important medical applications. The current work combined Perturbation Theory with Machine Learning and Information Fusion (PTMLIF). Thus, PTMLIF models were proposed to predict the probability of nanoparticle–compound/drug complexes having antimalarial activity (against Plasmodium). The aim is to save experimental resources and time by using a virtual screening for DDNPs. The raw data was obtained by the fusion of experimental data for nanoparticles with compound chemical assays from the ChEMBL database. The inputs for the eight Machine Learning classifiers were transformed features of drugs/compounds and nanoparticles as perturbations of molecular descriptors in specific experimental conditions (experiment-centered features). The resulting dataset contains 107 input features and 249,992 examples. The best classification model was provided by Random Forest, with 27 selected features of drugs/compounds and nanoparticles in all experimental conditions considered. The high performance of the model was demonstrated by the mean Area Under the Receiver Operating Characteristics (AUC) in a test subset with a value of 0.9921 ± 0.000244 (10-fold cross-validation). The results demonstrated the power of information fusion of the experimental-centered features of drugs/compounds and nanoparticles for the prediction of nanoparticle–compound antimalarial activity. The scripts and dataset for this project are available in the open GitHub repository.

Download Full-text