Use Of Machine Learning Algorithms Research Articles

PyRETIS3: Conquering rare and slow events without boundaries.

We present and discuss the advancements made in PyRETIS3, the third instalment of our Python library for an efficient and user-friendly rare event simulation, focused to execute molecular simulations with replica exchange transition interface sampling (RETIS) and its variations. Apart from a general rewiring of the internal code towards a more modular structure, several recently developed sampling strategies have been implemented. These include recently developed Monte Carlo moves to increase path decorrelation and convergence rate, and new ensemble definitions to handle the challenges of long-lived metastable states and transitions with unbounded reactant and product states. Additionally, the post-analysis software PyVisa is now embedded in the main code, allowing fast use of machine-learning algorithms for clustering and visualising collective variables in the simulation data.

Automated Machine Learning for Predicting Diabetic Retinopathy Progression From Ultra-Widefield Retinal Images

Machine learning (ML) algorithms have the potential to identify eyes with early diabetic retinopathy (DR) at increased risk for disease progression. To create and validate automated ML models (autoML) for DR progression from ultra-widefield (UWF) retinal images. Deidentified UWF images with mild or moderate nonproliferative DR (NPDR) with 3 years of longitudinal follow-up retinal imaging or evidence of progression within 3 years were used to develop automated ML models for predicting DR progression in UWF images. All images were collected from a tertiary diabetes-specific medical center retinal image dataset. Data were collected from July to September 2022. Automated ML models were generated from baseline on-axis 200° UWF retinal images. Baseline retinal images were labeled for progression based on centralized reading center evaluation of baseline and follow-up images according to the clinical Early Treatment Diabetic Retinopathy Study severity scale. Images for model development were split 8-1-1 for training, optimization, and testing to detect 1 or more steps of DR progression. Validation was performed using a 328-image set from the same patient population not used in model development. Area under the precision-recall curve (AUPRC), sensitivity, specificity, and accuracy. A total of 1179 deidentified UWF images with mild (380 [32.2%]) or moderate (799 [67.8%]) NPDR were included. DR progression was present in half of the training set (590 of 1179 [50.0%]). The model's AUPRC was 0.717 for baseline mild NPDR and 0.863 for moderate NPDR. On the validation set for eyes with mild NPDR, sensitivity was 0.72 (95% CI, 0.57-0.83), specificity was 0.63 (95% CI, 0.57-0.69), prevalence was 0.15 (95% CI, 0.12-0.20), and accuracy was 64.3%; for eyes with moderate NPDR, sensitivity was 0.80 (95% CI, 0.70-0.87), specificity was 0.72 (95% CI, 0.66-0.76), prevalence was 0.22 (95% CI, 0.19-0.27), and accuracy was 73.8%. In the validation set, 6 of 9 eyes (75%) with mild NPDR and 35 of 41 eyes (85%) with moderate NPDR progressed 2 steps or more were identified. All 4 eyes with mild NPDR that progressed within 6 months and 1 year were identified, and 8 of 9 (89%) and 17 of 20 (85%) with moderate NPDR that progressed within 6 months and 1 year, respectively, were identified. This study demonstrates the accuracy and feasibility of automated ML models for identifying DR progression developed using UWF images, especially for prediction of 2-step or greater DR progression within 1 year. Potentially, the use of ML algorithms may refine the risk of disease progression and identify those at highest short-term risk, thus reducing costs and improving vision-related outcomes.

Voice disorder recognition using machine learning: a scoping review protocol

IntroductionOver the past decade, several machine learning (ML) algorithms have been investigated to assess their efficacy in detecting voice disorders. Literature indicates that ML algorithms can detect voice disorders with...

Rock typing and Prediction Permeability Using Machine Learning Techniques in Mishrif formation, southern Iraq

Mishrif Formation is one of the major carbonate reserves. Classifying rock types and Predicted Permeability in the Mishrif Formation in four wells (A, B, C, and D) is the primary goal of this research. Using Machine Learning Techniques, this research applies rock-typing techniques like the Flow Zone Indicator (FZI) method. In a core plug dataset, we can use unsupervised learning methods to automatically cluster hydraulic flow units (HFU) based on flow zone indicators (FZI), and we can use a supervised learning method by combining core and well log data to predict HFU (rock type) for the interval depths of the wells without core data. In this method, we were able to classify rocks into five distinct groups, or “rock types,” or “RT” for short. RT1 rocks are the highest quality reservoir rocks, RT2 rocks are of good quality, RT3 rocks are of intermediate quality, RT4 rocks are of poor quality, and RT5 rocks are of very poor quality. Accurately estimating permeability in each rock type, not only does this help reduce uncertainty that occurs in reservoirs, but it also drives improvements in project economics by optimizing resource allocation and lowering costs. This is all thanks to the use of machine learning algorithms, which have proven to be highly effective in significantly enhancing the accuracy and precision of permeability predictions.

Differences in the gut microbiome of young adults with schizophrenia spectrum disorder: using machine learning to distinguish cases from controls

While an association between the gut microbiome and schizophrenia spectrum disorders (SSD) has been suggested, the existing evidence is still inconclusive. To this end, we analyzed bacteria and bacterial genes in feces from 52 young adult SSD patients and 52 controls using fecal shotgun metagenomic sequencing. Compared to controls, young SSD patients were found to have significantly lower α-diversity and different β-diversity both regarding bacterial species (i.e., taxonomic diversity) and bacterial genes (i.e., functional diversity). Furthermore, the α-diversity measures ‘Pielou’s evenness’ and ‘Shannon’ were significantly higher for both bacterial species, bacterial genes encoding enzymes and gut brain modules in young SSD patients on antipsychotic treatment (young SSD not on antipsychotics=9 patients, young SSD on antipsychotics=43 patients). We also applied machine learning classifiers to distinguish between young SSD patients and healthy controls based on their gut microbiome. Results showed that taxonomic and functional data classified young SSD individuals with an accuracy of ≥ 70% and with an area under the receiver operating characteristic curve (AUROC) of ≥ 0.75. Differential abundance analysis on the most important features in the classifier models revealed that most of the species with higher abundance in young SSD patients had their natural habitat in the oral cavity. In addition, many of the modules with higher abundance in young SSD patients were amino acid biosynthesis modules. Moreover, the abundances of gut-brain modules of butyrate synthesis and acetate degradation were lower in the SSD patients compared to controls. Collectively, our findings continue to support the presence of gut microbiome alterations in SSD and provide support for the use of machine learning algorithms to distinguish patients from controls based on gut microbiome profiles.

Classifying Protein-Protein Binding Affinity with Free-Energy Calculations and Machine Learning Approaches.

Understanding the intricate phenomenon of neuronal wiring in the brain is of great interest in neuroscience. In the fruit fly, Drosophila melanogaster, the Dpr-DIP interactome has been identified to play an important role in this process. However, experimental data suggest that a merely limited subset of complexes, essentially 57 out of a total of 231, exhibit strong binding affinity. In this work, we sought to identify the residue-level molecular basis underlying the difference in binding affinity using a state-of-the-art methodology consisting of standard binding free-energy calculations with a geometrical route and machine learning (ML) techniques. We determined the binding affinity for two complexes using statistical mechanics simulations, achieving an excellent reproduction of the experimental data. Moreover, we predicted the binding free energy for two additional low-affinity complexes, devoid of experimental estimation, while simultaneously identifying key residues for the binding. Furthermore, through the use of ML algorithms, linear discriminant analysis, and random forest, we achieved remarkable accuracy, as high as 0.99, in discerning between strong (cognate) and weak (noncognate) binders. The presented ML approach encompasses easily transferable input features, enabling its broad application to any interactome while facilitating the identification of pivotal residues critical for binding interactions. The predictive power of the generated model was probed on similar protein families from 13 diverse species. Our ML model exhibited commendable performance on these additional data sets, showcasing its reliability and robustness across the species barrier.

New well water cut prediction using machine learning

Background: The drilling of new wells is one of the most effective geological and technical activities. In mature fields characterized by high production of reserves and high water availability, the selection of design points for drilling is a difficult task. Forecasting the parameters of new wells is possible by using geological and hydrodynamic models or analytical methods. In this paper, the authors propose the use of machine learning algorithms to predict the initial parameters of new wells based on an extensive set of geological and field data.
 Aim: The article describes the process of developing machine learning algorithms and demonstrates the performance indicators of a complex model. As part of this work, testing of machine learning algorithms was performed to predict the start-up water cut of potential candidates.
 Materials and methods: Within the framework of this work, various machine learning methods were applied on geological and technical field data.
 Results: The developed complex model showed acceptable convergence results based on classification and regression metrics, which indicates its applicability for predicting the start-up water cut of project wells.
 Conclusion: This method of predicting indicators is an alternative tool for predicting the start-up water cut of new wells, which makes it possible to clarify and supplement the forecast parameters calculated using a geological and hydrodynamic model or empirical dependencies of the initial water cut of new wells on geological parameters.

Use of machine learning tools to predict health risks from climate-sensitive extreme weather events: A scoping review

Machine learning (ML) algorithms may play a role in predicting the adverse health impacts of climate-sensitive extreme weather events because accurate prediction of such effects can guide proactive clinical and policy decisions. To systematically review the literature that describe ML algorithms that predict health outcomes from climate-sensitive extreme weather events. A comprehensive literature search was performed in the following databases from inception–October 2022: Ovid MEDLINE, Ovid EMBASE, The Cochrane Library, Web of Science, bioRxiv, medRxiv, Institute of Electrical and Electronic Engineers, Google Scholar, and Engineering Village. The retrieved studies were then screened for eligibility against predefined inclusion/exclusion criteria. The studies were then qualitatively synthesized based on the type of extreme weather event. Gaps in the literature were identified based on this synthesis. Of the 6096 records screened, seven studies met the inclusion criteria. Six of the studies predicted health outcomes from heat waves, and one for flooding. Health outcomes described included 1) all-cause non-age standardized mortality rates, 2) heat-related conditions and 3) post-traumatic stress disorder. Prediction models were developed using six validated ML techniques including non-linear exponential regression, logistic regression, spatiotemporal Integrated Laplace Approximation (INLA), random forest and decision tree methods (DT), and support vector machines (SVM). Use of ML algorithms to assess adverse health impacts from climate-sensitive extreme weather events is possible. However, to fully utilize these ML techniques, better quality data suitable for use is desirable. Development of data standards for climate change and health may help ensure model robustness and comparison across space and time. Future research should also consider health equity implications.

Forecasting Commodity Prices

A thorough project report on the study and forecasting of commodities prices via the application of machine learning and linear regression methods is summarized in this abstract. The paper explores the importance of commodity price forecasting for agricultural decision-making, discussing how changes in pricing affect everyday life and agricultural productivity. The significance of comprehending the world's commodities markets is examined, with a focus on the use of machine learning algorithms specifically, linear regression for time series forecasting. To forecast correlations between variables, the process includes procedures like feature extraction, selection, and classification. The predicted results, such as R-squared values, trend detection, and risk assessment, are presented along with a suggested system that uses machine learning to classify and comprehend data from the commodities market. The usefulness of a thorough model selection framework is discussed in the report's conclusion, with an emphasis on the principle components technique and linear regression for commodity price prediction.(Food and Agriculture Organization of the United Nations 2013) Keywords— Commodity prices, Agricultural authorities, Commodity market data, forecasting, linear regression, Python, Jupyter Notebook.

Divorce prediction using machine learning algorithms in Ha’il region, KSA

The application of artificial intelligence (AI) in predictive analytics is growing in popularity. It has the power to offer ground-breaking solutions for a range of social problems and real world societal difficulties. It is helpful in addressing some of the social issues that today’s world seems incapable of solving. One of the most significant phenomena affecting people’s lives is divorce. The goal of this paper is to study the use of machine learning algorithms to determine the effectiveness of divorce predictor scale (DPS) and identify the reasons that usually lead to divorce in the scenario of Hail region, KSA. For this purpose, in this study, the DPS, based on Gottman couples therapy, was used to predict divorce by applying different machine learning algorithms. There were 54 items of the DPS used as features or attributes for data collection. In addition to the DPS, a personal information form was utilized to gather participants’ personal data in order to conduct this study in a more structured and traditional manner. Out of 148 participants 116 participants were married whereas 32 were divorced. With the use of algorithms artificial neural network (ANN), naïve bayes (NB), and random forest (RF), the effectiveness of DPS was examined in this study. The correlation based feature selection method was used to identify the top six features from the same dataset and the highest accuracy rate was 91.66% with RF. The results show that DPS can predict divorce. This scale can help family counselors and therapists in case formulation and intervention plan development process. Additionally, it may be argued that the Hail region, KSA sampling confirmed the Gottman couples treatment predictors.

Characterization of Fatigue Damage in Hadfield Steel Using Acoustic Emission and Machine Learning-Based Methods.

Structural health monitoring (SHM) of fatigue cracks is essential for ensuring the safe operation of engineering equipment. The acoustic emission (AE) technique is one of the SHM techniques that is capable of monitoring fatigue-crack growth (FCG) in real time. In this study, fatigue-damage evolution of Hadfield steel was characterized using acoustic emission (AE) and machine learning-based methods. The AE signals generated from the entire fatigue-load process were acquired and correlated with fatigue-damage evolution. The AE-source mechanisms were discussed based on waveform characteristics and bispectrum analysis. Moreover, multiple machine learning algorithms were used to classify fatigue sub-stages, and the results show the effectiveness of classification of fatigue sub-stages using machine learning algorithms. The novelty of this research lies in the use of machine learning algorithms for the classification of fatigue sub-stages, unlike the existing methodology, which requires prior knowledge of AE-loading history and calculation of ∆K.

Application of machine learning algorithms for predicting agricultural crop yields

This article examines the use of machine learning algorithms for predicting the yield of agricultural crops. The primary classification method chosen is the C4.5 algorithm, which allows for the construction of interpretable models that identify key factors affecting yield. The analysis utilized data from a dataset available on the Kaggle platform, including information on various crops, their yields, and associated factors such as rainfall, fertilizer usage, air temperature, and the content of nitrogen, phosphorus, and potassium in the soil. The conducted correlation analysis showed that air temperature and the content of nitrogen, phosphorus, and potassium in the soil have the greatest impact on yield. Despite high correlation, the amount of fertilizer and rainfall were less significant in the model, indicating the need for further investigation of their influence. The model evaluation on the Deductor Studio platform demonstrated high classification accuracy, but there are opportunities for improvement. The importance of the results underscores the necessity for precise monitoring and management of key factors in agricultural practice to enhance productivity. Future research could focus on integrating larger datasets and more complex algorithms, as well as utilizing Internet of Things (IoT) systems for more accurate monitoring and yield prediction.

Ensuring food safety by artificial intelligence-enhanced nanosensor arrays.

Current analytical methods utilized for food safety inspection requires improvement in terms of their cost-efficiency, speed of detection, and ease of use. Sensor array technology has emerged as a food safety assessment method that applies multiple cross-reactive sensors to identify specific targets via pattern recognition. When the sensor arrays are fabricated with nanomaterials, the binding affinity of analytes to the sensors and the response of sensor arrays can be remarkably enhanced, thereby making the detection process more rapid, sensitive, and accurate. Data analysis is vital in converting the signals from sensor arrays into meaningful information regarding the analytes. As the sensor arrays can generate complex, high-dimensional data in response to analytes, they require the use of machine learning algorithms to reduce the dimensionality of the data to gain more reliable outcomes. Moreover, the advances in handheld smart devices have made it easier to read and analyze the sensor array signals, with the advantages of convenience, portability, and efficiency. While facing some challenges, the integration of artificial intelligence with nanosensor arrays holds promise for enhancing food safety monitoring.

Geographic Information Systems Applications in Business Decision-Making

The recent advancements in Geographic Information Systems (GIS) techniques and their applications across various business domains provide an overview of cutting-edge GIS methodologies, including spatial analytics, machine learning integration, and advanced visualization tools. The study sheds light on how these techniques enhance decision-making processes in industries such as retail, service, and manufacturing. Challenges encompass the complexity of integrating diverse datasets, issues of data usage, and ensuring the interpretability and efficient use of machine learning algorithms within GIS frameworks. In response to these challenges, the primary objective of this study is to address the limitations of current GIS methodologies by understanding their capabilities while ensuring the effective use of advanced technologies, and optimizing business decision making processes.

Investigating the use of machine learning algorithms to support risk-based animal welfare inspections of cattle and pig farms.

In livestock production, animal-related data are often registered in specialised databases and are usually not interconnected, except for a common identifier. Analysis of combined datasets and the possible inclusion of third-party information can provide a more complete picture or reveal complex relationships. The aim of this study was to develop a risk index to predict farms with an increased likelihood for animal welfare violations, defined as non-compliance during on-farm welfare inspections. A data-driven approach was chosen for this purpose, focusing on the combination of existing Swiss government databases and registers. Individual animal-level data were aggregated at the herd level. Since data collection and availability were best for cattle and pigs, the focus was on these two livestock species. We present machine learning models that can be used as a tool to plan and optimise risk-based on-farm welfare inspections by proposing a consolidated list of priority holdings to be visited. The results of previous on-farm welfare inspections were used to calibrate a binary welfare index, which is the prediction goal. The risk index is based on proxy information, such as the participation in animal welfare programmes with structured housing and outdoor access, herd type and size, or animal movement data. Since transparency of the model is critical both for public acceptance of such a data-driven index and farm control planning, the Random Forest model, for which the decision process can be illustrated, was investigated in depth. Using historical inspection data with an overall low prevalence of violations of approximately 4% for both species, the developed index was able to predict violations with a sensitivity of 81.2 and 79.5% for cattle and pig farms, respectively. The study has shown that combining multiple and heterogeneous data sources improves the quality of the models. Furthermore, privacy-preserving methods are applied to a research environment to explore the available data before restricting the feature space to the most relevant. This study demonstrates that data-driven monitoring of livestock populations is already possible with the existing datasets and the models developed can be a useful tool to plan and conduct risk-based animal welfare inspection.

Computational Modeling and AI in Radiation Neuro-Oncology and Radiosurgery.

The chapter explores the extensive integration of artificial intelligence (AI) in healthcare systems, with a specific focus on its application in stereotactic radiosurgery. The rapid evolution of AI technology has led to promising developments in this field, particularly through the utilization of machine learning and deep learning models. The diverse implementation of AI algorithms was developed from various aspects of radiosurgery, including the successful detection of spontaneous tumors and the automated delineation or segmentation of lesions. These applications show potential for extension to longitudinal treatment follow-up. Additionally, the chapter highlights the established use of machine learning algorithms, particularly those incorporating radiomic-based analysis, in predicting treatment outcomes. The discussion encompasses current achievements, existing limitations, and the need for further investigation in the dynamic intersection of AI and radiosurgery.

Implementing new Approaches of Digitization in Conventional Metal Forming Processes: A German perspective

The Institute for Metal Forming Technology (IFU) at the University of Stuttgart / Germany since more than six years strongly strives to future oriented research work focusing on far-reaching concepts for digitization of metal forming processes. Main activities of engaged research groups are integrating sensors and actuators into metal forming machines or dies to analyse process data gained that way. Also, development of advanced methods for production data mining are related to those fields of activities. The paper therefore highlights strategies and practical applications of such digitization concepts. Also, important issues in terms of metal forming production processes will be addressed such as avoidance of scrap during ramp up phases and batch processing. Finally, the practical use of machine learning algorithms will be demonstrated in real trimming and metal forming processes.

PREDICTION AND ANALYSIS OF HUMAN PERCEPTION AND EMOTIONAL UNDERSTANDING THROUGH TECHNOLOGY – BLUE EYES TECHNOLOGY

The human computer interaction (HCI) field has seen significant transformations throughout the course of its history, shifting from its early focus on effectiveness and utility to the innovative concept of emotional computing. This article explores these changes. This research investigates the transformational process that led to the development of goods such as Blue Eye technology. It does so by drawing on influential work such as "Affective computing," which focuses on universal representations of emotion. The destination of this journey is Blue Eye Technology, a fictitious concept that is based on true scientific advancements. In order to develop a framework that is both empathetic and responsive, the strategy that has been presented takes use of machine learning algorithms and cutting-edge sensing materials. By encompassing the historical context, significant works, and technological advancements that lay the framework for Blue Eye Technology, this abstract marks a significant step toward a more intuitive and emotionally aware period in human computer interaction. This abstraction is a significant stride. People are able to interact with computers in a manner that is more natural and efficient by utilizing these techniques, which are referred to as "Blue Eye" technology. These techniques include eye tracking and gaze recognition capabilities. Through its various uses, this technology has the potential to be beneficial to a wide range of industries, including computer gaming, virtual and augmented reality, and assistive technology for individuals with disabilities. The current status of Blue Eye technology, its potential benefits and drawbacks, and the several techniques and algorithms that are available for gaze tracking and analysis will be investigated in this paper. This will be accomplished through a review of the relevant literature.

Algorithms for predicting COVID outcome using ready-to-use laboratorial and clinical data.

The pandemic caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is an emerging crisis affecting the public health system. The clinical features of COVID-19 can range from an asymptomatic state to acute respiratory syndrome and multiple organ dysfunction. Although some hematological and biochemical parameters are altered during moderate and severe COVID-19, there is still a lack of tools to combine these parameters to predict the clinical outcome of a patient with COVID-19. Thus, this study aimed at employing hematological and biochemical parameters of patients diagnosed with COVID-19 in order to build machine learning algorithms for predicting COVID mortality or survival. Patients included in the study had a diagnosis of SARS-CoV-2 infection confirmed by RT-PCR and biochemical and hematological measurements were performed in three different time points upon hospital admission. Among the parameters evaluated, the ones that stand out the most are the important features of the T1 time point (urea, lymphocytes, glucose, basophils and age), which could be possible biomarkers for the severity of COVID-19 patients. This study shows that urea is the parameter that best classifies patient severity and rises over time, making it a crucial analyte to be used in machine learning algorithms to predict patient outcome. In this study optimal and medically interpretable machine learning algorithms for outcome prediction are presented for each time point. It was found that urea is the most paramount variable for outcome prediction over all three time points. However, the order of importance of other variables changes for each time point, demonstrating the importance of a dynamic approach for an effective patient's outcome prediction. All in all, the use of machine learning algorithms can be a defining tool for laboratory monitoring and clinical outcome prediction, which may bring benefits to public health in future pandemics with newly emerging and reemerging SARS-CoV-2 variants of concern.

Critical Review of Stack Ensemble Classifier for the Prediction of Young Adults’ Voting Patterns Based on Parents’ Political Affiliations

Aim/Purpose: This review paper aims to unveil some underlying machine-learning classification algorithms used for political election predictions and how stack ensembles have been explored. Additionally, it examines the types of datasets available to researchers and presents the results they have achieved. Background: Predicting the outcomes of presidential elections has always been a significant aspect of political systems in numerous countries. Analysts and researchers examining political elections rely on existing datasets from various sources, including tweets, Facebook posts, and so forth to forecast future elections. However, these data sources often struggle to establish a direct correlation between voters and their voting patterns, primarily due to the manual nature of the voting process. Numerous factors influence election outcomes, including ethnicity, voter incentives, and campaign messages. The voting patterns of successors in regions of countries remain uncertain, and the reasons behind such patterns remain ambiguous. Methodology: The study examined a collection of articles obtained from Google Scholar, through search, focusing on the use of ensemble classifiers and machine learning classifiers and their application in predicting political elections through machine learning algorithms. Some specific keywords for the search include “ensemble classifier,” “political election prediction,” and “machine learning”, “stack ensemble”. Contribution: The study provides a broad and deep review of political election predictions through the use of machine learning algorithms and summarizes the major source of the dataset in the said analysis. Findings: Single classifiers have featured greatly in political election predictions, though ensemble classifiers have been used and have proven potent use in the said field is rather low. Recommendation for Researchers: The efficacy of stack classification algorithms can play a significant role in machine learning classification when modelled tactfully and is efficient in handling labelled datasets. however, runtime becomes a hindrance when the dataset grows larger with the increased number of base classifiers forming the stack. Future Research: There is the need to ensure a more comprehensive analysis, alternative data sources rather than depending largely on tweets, and explore ensemble machine learning classifiers in predicting political elections. Also, ensemble classification algorithms have indeed demonstrated superior performance when carefully chosen and combined.