Applying Machine Learning Approaches Research Articles

Predictive Analytics for Sucker Rod Pump Failures in Kazakhstani Oil Wells Using Machine Learning

In the process of developing mature deposits, a number of geological and technological complications arise. In order to increase the smooth operation of downhole pumping equipment in oil and gas wells, companies use various methods and techniques. This article presents a novel methodology for predicting downhole pumping equipment failures. A detailed analysis was conducted on historical data regarding downhole pumping equipment failures, which were then incorporated into algorithms to calculate the operation of downhole equipment. As a result, it was discovered that in order to predict failures of downhole equipment, it is crucial to consider the historical data of the field and perform an assessment of the well’s potential. In the process of building a failure prediction model, the authors encountered the quality and completeness of historical data from the pilot field. They concluded that the data classes needed to be more balanced. The authors applied machine learning approaches to an imbalanced dataset. The significance of our approach lies in its ability to forecast equipment failures, thereby ensuring the smooth operation of wells operated by sucker rod pumps.

Predictors of HIV seroconversion in Botswana: machine learning analysis in a representative, population-based HIV incidence cohort.

To identify predictors of HIV acquisition in Botswana. We applied machine learning approaches to identify HIV risk predictors using existing data from a large, well-characterized HIV incidence cohort. We applied machine learning (randomForestSRC) to analyze data from a large population-based HIV incidence cohort enrolled in a cluster-randomized HIV prevention trial in 30 communities across Botswana. We sought to identify the most important risk factors for HIV acquisition, starting with 110 potential predictors. During a median 29-month follow-up of 8,551 HIV-negative adults, 147 (1.7%) acquired HIV. Our machine learning analysis found that for females, the most important variables for predicting HIV acquisition were the use of injectable hormonal contraception, frequency of sex in the prior 3 months with the most recent partner and residing in a community with HIV prevalence of 29% or higher. For the small proportion (0.3%) of females who had all three risk factors, their estimated probability of acquiring HIV during 29 months of follow-up was 34% (approximate annual incidence of 14%). For males, non-long-term relationships with the most recent partner and community HIV prevalence of 34% or higher were the most important HIV risk predictors. The 6% of males who had both risk factors had a 5.1% probability of acquiring HIV during the follow-up period (approximate annual incidence of 2.1%). Machine learning approaches allowed us to analyze a large number of variables to efficiently identify key factors strongly predictive of HIV risk. These factors could help target HIV prevention interventions in Botswana. NCT01965470.

Machine learning based on event-related oscillations of working memory differentiates between preclinical Alzheimer’s disease and normal aging

ObjectiveTo apply machine learning approaches on EEG event-related oscillations (ERO) to discriminate preclinical Alzheimer’s disease (AD) from age- and sex-matched controls. MethodsTwenty-two cognitively normal preclinical AD participants with elevated amyloid and 21 cognitively normal controls without elevated amyloid completed n-back working memory tasks (n = 0, 1, 2). The absolute and relative power of ERO was extracted using the discrete wavelet transform in the delta, theta, alpha, and beta bands. Four machine learning methods were employed, and classification performance was assessed using three metrics. ResultsThe low-frequency bands produced higher discriminative performances compared to high-frequency bands. The 2-back task yielded the best classification capability among the three tasks. The highest area under the curve value (0.86) was achieved in the 2-back delta band nontarget condition data. The highest accuracy (80.47%) was obtained in the 2-back delta and theta bands nontarget data. The highest F1 score (0.82) was in the 2-back theta band nontarget data. The support vector machine achieved the highest performance among tested classifiers. ConclusionThis study demonstrates the promise of using machine learning on EEG ERO from working memory tasks to detect preclinical AD. SignificanceEEG ERO may reveal pathophysiological differences in the earliest stage of AD when no cognitive impairments are apparent.

Applying machine learning approaches for predicting obesity risk using US health administrative claims database

IntroductionBody mass index (BMI) is inadequately recorded in US administrative claims databases. We aimed to validate the sensitivity and positive predictive value (PPV) of BMI-related diagnosis codes using an electronic...

Advanced prediction of rice yield gaps under climate uncertainty using machine learning techniques in Eastern India

The current study focuses on applying machine learning approaches to forecast future Kharif rice yield gaps in eastern India while accounting for climate change implications. To achieve the United Nations Sustainable Development Goals (SDGs), food security must be prioritized. Rice yield has been predicted using Cubist, GBM, MARS, RF, SVM, and XGB machine learning methods, considering six factors: elevation, soil moisture, precipitation, temperature, soil temperature, and actual evapotranspiration. Climatic change scenarios were generated using the latest climatic Coupled Model Intercomparison Project Phase 6 (CMIP6 MIROC6) Shared Socioeconomic Pathways (SSP) 2–4.5 and SSP5-8.5 datasets between 1990 and 2030. Finally, machine learning algorithms were used to identify rice yield gaps to achieve sustainable agricultural intensification. The rice yield validation was completed with 1889 field-based farmer observation records. The results suggest that Murshidabad and Purba Bardhaman districts had very high rice yields (5.60–3.45 t/ha) when using the Cubist model compared to another model. The findings also reveal a poor rice-yielding zone (1.44–0.39 t/ha) in the western region (Purulia) and a northwestern region (half of the west of Birbhum). The Cubist and RF models' maximum and minimum R2 values were 0.73 and 0.72, respectively. The R2 values were also negligible for the XGB, GBM, SVM, and MARS, machine learning models. Projections for rice production in 2030 indicate that the northern and north-eastern regions (Murshidabad and Purba Bardhaman) as well as the southeastern areas (Jhargram and Paschim Medinipur) have the highest yields, categorized as extremely very high (5.56–3.49 t/ha) and high (3.49–2.49 t/ha). A significant rice yield gap (50-40 %) was found in the center and south-east areas (Bankura, Jhargram, and Paschim Medinipur), the northern region (Murshidabad and Birbhum), and the western region (Purulia). In 2030, the north-western region (Birbhum), as well as the middle and south-eastern regions (Bankura, Jhargram, and Paschim Medinipur districts), had the highest proportion of high (50%–40 %) and very high (60%–50 %) rice yield gap. Our findings can contribute to a new viewpoint on agricultural planning and management for sustainable growth in the face of changing climate circumstances.

A supervised machine learning procedure for EPMA classification and plotting of mineral groups

An analytical method to automatically characterize rock samples for geological or petrological purposes is here proposed, by applying machine learning approach (ML) as a protocol for saving experimental times and costs.Proper machine learning algorithms, applied to automatically acquired microanalytical data (i.e., Electron Probe Micro Analysis, EPMA), carried out with a SEM-EDS microprobe on randomly selected areas from a petrographic polished thin section, are trained, used, tested, and reported.Learning and Validation phases are developed with literature mineral databases of electron microprobe analyses on 15 main rock-forming mineral groups. The Prediction phase is tested using an eclogite rock from the Western Alps, considered as an unknown sample: randomly selected areas are acquired as backscattered images whose intervals of gray levels, appropriately set in the gray level histogram, allow the automated particle mineral separation: automated separating Oxford Instruments Aztec Feature ® packages and a mineral plotting software are applied for mineral particle separation, crystal chemical formula calculation and plotting.Finally, a microanalytical analysis is performed on each separated mineral particle. The crystal chemical formula is calculated, and the final classification plots are automatically produced for any determined mineral. The final results show good accuracy and analytical ease and assess the proper nature of the unknown eclogite rock sample. Therefore, the proposed analytical protocol is especially recommended in those scenarios where a large flow of microanalytical data is automatically acquired and needs to be processed.

Applying machine learning approach in predicting short-term rockburst risks using microseismic information: a comparison of parametric and non-parametric models

Applying machine learning approach in predicting short-term rockburst risks using microseismic information: a comparison of parametric and non-parametric models

Predicting grain yield of maize using a new multispectral-based canopy volumetric vegetation index

Accurately predicting agricultural yields is crucial for developing adaptative strategies to ensure food security. Unmanned aerial vehicle (UAV) remote sensing equipped with portable multispectral sensors are commonly applied to acquire high temporal and spatial resolutions of remote sensing data. The vegetation indices (VIs) extracted from multispectral images are conducted for agricultural yield prediction. However, existing VIs often suffered from saturation problems when the canopy coverage is high. Integrating UAV-derived canopy height data with spectral indices holds the potential to solve saturation problem. However, this method is still at the infant stage and requires further validation. Here, we have newly proposed a multispectral-based canopy volumetric vegetation index (MSCVI) that integrates RGB-based volumetric index (VCI) and multispectral images derived VIs from UAV platform for predicting irrigated maize yields for three years (2019, 2020, and 2021). To test the stability of the proposed method, the maize was well managed and different levels of fertilizers were applied in each plot. The results using regression analysis showed the MSCVI outperformed the single adoption of VIs and VCI, and the MSCVI at reproductive growth stages was more strongly correlated with maize yields. Two commonly applied machine learning approaches: backpropagation neural network (BP) and random forest (RF) were applied for predicting maize yield. The R2 between actual maize yield and predicted maize yield using BP increased from 0.81 to 0.86 (RMSE decreased from 0.93 to 0.67 t/ha). The R2 between actual maize yield and predicted maize yield using RF increased from 0.91 to 0.94 (RMSE decreased from 0.65 to 0.42 t/ha). The robustness of the proposed model was further evaluated using data updating strategies, and results implied that the models was stable across sensors and different years. Overall, this study revealed the proposed MSCVI obtain high potential for predicting agricultural yields, and the proposed model was robust and stable when tested using data updating strategy.

Application of a Machine Learning-Based Classification Approach for Developing Host Protein Diagnostic Models for Infectious Disease

In recent years, infectious disease diagnosis has increasingly turned to host-centered approaches as a complement to pathogen-directed ones. The former, however, typically requires the interpretation of complex multiple biomarker datasets to arrive at an informative diagnostic outcome. This report describes a machine learning (ML)-based classification workflow that is intended as a template for researchers seeking to apply ML approaches for developing host-based infectious disease biomarker classifiers. As an example, we built a classification model that could accurately distinguish between three disease etiology classes: bacterial, viral, and normal in human sera using host protein biomarkers of known diagnostic utility. After collecting protein data from known disease samples, we trained a series of increasingly complex Auto-ML models until arriving at an optimized classifier that could differentiate viral, bacterial, and non-disease samples. Even when limited to a relatively small training set size, the model had robust diagnostic characteristics and performed well when faced with a blinded sample set. We present here a flexible approach for applying an Auto-ML-based workflow for the identification of host biomarker classifiers with diagnostic utility for infectious disease, and which can readily be adapted for multiple biomarker classes and disease states.

Campus Recruitment Prediction

For businesses and students alike, campus recruitment is an important occasion. While businesses aim to draw in the best employees, students eagerly anticipate beginning their professional careers. Salary prediction is a crucial component of college recruitment, when employers ascertain the wage ranges, they would offer prospective employees. Many criteria, including the candidate's qualifications, experience, and education, as well as the company's budget and industry norms, play a role in predicting the salary for campus recruitment. In this project, we'll apply machine learning approaches to forecast college recruitment salaries based on candidate historical data and salaries that match to those positions. In this project, we develop a predictive model for college recruitment by analysing the dataset that has been provided. Data processing and exploratory data analysis (EDA) are our initial steps. After that, we build a Flask web application that uses the trained predictive model to be deployed and lets users anticipate things based on input.

Drone-based monitoring of intertidal blue mussel beds in the Wadden Sea – comparison of a threshold and two machine learning approaches

In the Wadden Sea, intertidal mussel beds of the blue mussel (Mytilus edulis) and the Pacific oyster (Magallana gigas) form distinct epibenthic communities and local hotspots of high biomass and biodiversity. To detect and evaluate natural and anthropogenic processes, a ground-based monitoring program started over 25 years ago in the German Wadden Sea. In this study, we describe the potential of drones and machine learning approaches for a remote sensing-based integration into an existing monitoring program of intertidal mussel beds. A fixed wing drone was used to cover an area of up to 39ha in a single flight, with an overall time saving potential of 50%. Applying machine learning approaches, a detailed extraction of the intertidal blue mussel bed coverage with an overall accuracy (OA) up to 95.6% was reached, applying a Support Vector Machine (SVM). The application of a multispectral sensor improved the classification performance. Compared to ground-based monitoring, the drone-based method provided significantly more information on the area extension, coverage, and associated algae of the mussel beds. The results show that drones can provide a non-invasive way to survey large and difficult to access areas providing detailed maps of mussel beds and their internal structures.

Enhancing Network Security: Leveraging Machine Learning for Intrusion Detection

In order to precisely identify and categorise different kinds of network attacks, this study focuses on applying machine learning approaches for network intrusion detection. Data collection, preprocessing, feature scaling, model definition, feature selection, and assessment metrics are all part of the methodology. Different machine learning models, including Decision Tree Classifier and Random Forest Classifier, are considered, along with the use of all features or some part of features for each attack category. Evaluation is performed using K-fold cross-validation, with metrics such as accuracy, precision, recall, and F1-score analysed. Results indicate the efficiency of Random Forest Classifier in handling high-dimensional datasets and improving detection accuracy, making it a superior choice for network intrusion detection tasks.

A machine learning approach to study plant functional trait divergence.

Plant functional traits are often used to describe the spectra of ecological strategies used by different species. Here, we demonstrate a machine learning approach for identifying the traits that contribute most to interspecific phenotypic divergence in a multivariate trait space. Descriptive and predictive machine learning approaches were applied to trait data for the genus Helianthus, including random forest and gradient boosting machine classifiers and recursive feature elimination. These approaches were applied at the genus level as well as within each of the three major clades within the genus to examine the variability in the major axes of trait divergence in three independent species radiations. Machine learning models were able to predict species identity from functional traits with high accuracy, and differences in functional trait importance were observed between the genus and clade levels indicating different axes of phenotypic divergence. Applying machine learning approaches to identify divergent traits can provide insights into the predictability or repeatability of evolution through the comparison of parallel diversifications of clades within a genus. These approaches can be implemented in a range of contexts across basic and applied plant science from interspecific divergence to intraspecific variation across time, space, and environmental conditions.

Reinforcement Learning and Data-Generation for Syntax-Guided Synthesis

Program synthesis is the task of automatically generating code based on a specification. In Syntax-Guided Synthesis (SyGuS) this specification is a combination of a syntactic template and a logical formula, and the result is guaranteed to satisfy both. We present a reinforcement-learning guided algorithm for SyGuS which uses Monte-Carlo Tree Search (MCTS) to search the space of candidate solutions. Our algorithm learns policy and value functions which, combined with the upper confidence bound for trees, allow it to balance exploration and exploitation. A common challenge in applying machine learning approaches to syntax-guided synthesis is the scarcity of training data. To address this, we present a method for automatically generating training data for SyGuS based on anti-unification of existing first-order satisfiability problems, which we use to train our MCTS policy. We implement and evaluate this setup and demonstrate that learned policy and value improve the synthesis performance over a baseline by over 26 percentage points in the training and testing sets. Our tool outperforms state-of-the-art tool cvc5 on the training set and performs comparably in terms of the total number of problems solved on the testing set (solving 23% of the benchmarks on which cvc5 fails). We make our data set publicly available, to enable further application of machine learning methods to the SyGuS problem.

Machine learning approaches delimit cryptic taxa in a previously intractable species complex

Cryptic species are not diagnosable via morphological criteria, but can be detected through analysis of DNA sequences. A number of methods have been developed for identifying species based on genetic data; however, these methods are prone to over-splitting taxa with extreme population structure, such as dispersal-limited organisms. Machine learning methodologies have the potential to overcome this challenge. Here, we apply such approaches, using a large dataset generated through hybrid target enrichment of ultraconserved elements (UCEs). Our study taxon is the Aoraki denticulata species complex, a lineage of extremely low-dispersal arachnids endemic to the South Island of Aotearoa New Zealand. This group of mite harvesters has been the subject of previous species delimitation studies using smaller datasets generated through Sanger sequencing and analytical approaches that rely on multispecies coalescent models and barcoding gap discovery. Those analyses yielded a number of putative cryptic species that seems unrealistic and extreme, based on what we know about species’ geographic ranges and genetic diversity in non-cryptic mite harvesters. We find that machine learning approaches, on the other hand, identify cryptic species with geographic ranges that are similar to those seen in other morphologically diagnosable mite harvesters in Aotearoa New Zealand’s South Island. We performed both unsupervised and supervised machine learning analyses, the latter with training data drawn either from animals broadly (vagile and non-vagile) or from a custom training dataset from dispersal-limited harvesters. We conclude that applying machine learning approaches to the analysis of UCE-derived genetic data is an effective method for delimiting species in complexes of low-vagility cryptic species, and that the incorporation of training data from biologically relevant analogues can be critically informative.

Deep Learning Approach for Classification of Tweets in Detecting Cyber Truculent

Identification and Classification of truculent tweets is a serious problem. Studies have shown how truculent tweets on Twitter have caused anxiety and in extreme cases death of victims. Various researches have applied Machine Learning approaches while others Deep Learning in classifying toxic sentences. Impressive results have been obtained using Deep Learning approaches, the focus of the research is to develop an extended model for deep learning classification using cyber tweets. The Model developed in this research work used labelled dataset (twitter_parsed_dataset.csv), Maximum Entropy was used to extract keywords and entities. One-Dimensional Convolutional Neural Network (1d-CNN) was used to detect truculent in tweets. The experimental result from the developed model consider four preprocess datasets for classification, the Unigram, Bigram, Trigram and N-gram. The result that was obtained for Accuracy 96.1%, Precision 93.6%, Recall 73.7% and F1-Score 83.8% for different test during classification. The result obtained from the developed model for accuracy, 96.1% was compared with related work Banerjee’s accuracy of 93.97%. The developed model can be used for auto detection of truculent messages in cyberspace.

Resident space objects classification by machine learning techniques

In recent years the number of resident space objects in near-Earth space has been increasing drastically, which can lead to a “cascade collisions” effect and other catastrophic consequences. Therefore, it is crucial to monitor resident space objects, maintain and update catalogues on time, including the identification of unknown space objects to estimate their location and potential orbit. It is necessary to perform resident space object identification quickly and accurately to avoid possible satellite collisions resulting in large clouds of uncontrollable space debris fragments. That is why the task of resident space object preliminary classification by TLEs is stated and solved by applying machine learning approaches to achieve a higher classification quality and speed. This issue is a highly imbalanced classification problem, which narrows and specifies the used models. Applying the proposed resident space object classification model to space surveillance systems can decrease the time required for the object identification significantly.

Factors Associated with Unplanned Hospital Readmission after Discharge: A Descriptive and Predictive Study Using Electronic Health Record Data

Hospital readmission involves the unplanned emergency admission of patients within 30 days from discharge after the previous admission. According to the Canadian Health Institute (CIHI), 1 in 11 patients were readmitted within 30 days of leaving the hospital in 2021. In the USA, nearly 20% of Medicare patients were readmitted after discharge, where the average cost of readmission was approximately USD 15,000, as reported by the Agency for Healthcare Research and Quality (AHQR) in 2018. To tackle this issue, we first conducted a descriptive analysis study to understand the risk factors associated with hospital readmission, and then we applied machine learning approaches to predict hospital readmission by using patients’ demographic and clinical data extracted from the Electronic Health Record of the MIMIC-III clinical database. The results showed that the number of previous admissions during the last 12 months, hyperosmolar imbalance and comorbidity index were the top three significant factors for hospital readmission. The predictive model achieved a performance of 95.6% AP and an AUC = 97.3% using the Gradient Boosting algorithm trained on all features.

Applying Machine Learning Approach to Explore Childhood Circumstances and Self-Rated Health in Old Age - China and the US, 2020-2021.

Childhood circumstances impact senior health, prompting the introduction of machine learning methods to assess their individual and collective contributions to senior health. Using health and retirement study (HRS) and China Health and Retirement Longitudinal Study (CHARLS), we analyzed 2,434 American and 5,612 Chinese participants aged 60 and above. Conditional inference trees and forests were employed to estimate the influence of childhood circumstances on self-rated health (SRH). The conventional method estimated higher inequality of opportunity (IOP) values in both China (0.039, accounting for 22.67% of the total Gini coefficient 0.172) and the US (0.067, accounting for 35.08% of the total Gini coefficient 0.191). In contrast, the conditional inference tree yielded lower estimates (China: 0.022, accounting for 12.79% of 0.172; US: 0.044, accounting for 23.04% of 0.191), as did the forest (China: 0.035, accounting for 20.35% of 0.172; US: 0.054, accounting for 28.27% of 0.191). Childhood health, financial status, and regional differences were key determinants of senior health. The conditional inference forest consistently outperformed others in predictive accuracy, as demonstrated by lower out-of-sample mean squared error (MSE). The findings emphasize the need for early-life interventions to promote health equity in aging populations. Machine learning showcases the potential in identifying contributing factors.

Systematic Analysis of the Literature Addressing the Use of Machine Learning Techniques in Transportation—A Methodology and Its Application

Advances in the field of machine learning (ML) have been reflected in the intensity of research studies exploiting these techniques for a better understanding of existing phenomena, and for predicting future ones, as a mean for promoting a more efficient and sustainable transportation system. The present study aims to understand the trends of utilizing diverse ML approaches to tackle issues within sub-domains of transportation and to identify underutilized potentials among them. This paper presents a methodology for the bi-dimensional classification of a large corpus of scientific articles. The articles are classified into six transport-related sub-domains, based on the definition of the Israeli Smart Transport Research Center, whose aim is a transportation system with zero externalities, and the ML techniques used in each of them is identified. A fuzzy KNN model is implemented for the multi-classification of articles into the transportation sub-domains and an ontology-based reasoning for identifying the share of each applied ML approach is employed. The application of these methodologies to a corpus of 1718 articles revealed, among other findings, an increasing share of artificial neural networks and deep learning techniques from 2018 until 2022, particularly in the traffic management sub-domain. A significant contribution of the development of these automatic methodologies is the ability to reuse them for ongoing exploration of trends regarding the use of ML techniques for transportation sub-domains.