Advanced Machine Learning Research Articles

Machine learning the in-medium correction factor on nucleon-nucleon elastic cross section

Abstract The nuclear equation of state cannot be directly measured in the heavy-ion collision experiments; it is usually inferred from the comparison between transport model simulations and experimental measurements. The in-medium correction factor (F , which is defined as the ratio of the cross section in the nuclear medium to that in free space) on the nucleon-nucleon elastic cross section is one of the important inputs of the transport model, and its magnitude is still debated. The advent of Machine Learning (ML) has profoundly influenced the way scientists study the natural world and has provided a new paradigm that merges traditional investigation with advanced datadriven techniques. The aim of this work is to present a ML-based method to study the in-medium correction factor F . The ultra-relativistic quantum molecular dynamics (UrQMD) transport model is used to simulate 132Sn + 124Sn collisions at beam energy of 0.27 GeV/nucleon with different impact parameters. The value of F is randomly selected from 0.4 to 0.8 for the simulation of each event. Several observables simulated by the UrQMD model with different F , which are thought to be probably sensitive to the in-medium nucleon-nucleon cross sections, are fed into the LightGBM (Light Gradient Boosting Machine, which is a modern decision tree-based ML algorithm) to establish the mapping between the observables and F . The mean absolute error (MAE), which is the absolute difference between the true and the predicted F , is about 0.080 and 0.021 by using event-by-event and 40-event summed observables, respectively. It indicates that ML can recognize information about the F factor. Furthermore, according to the results of Shapley Additive exPlanations (SHAP), an interpretability analysis method in ML, features that have the greatest effect on the F are identified. ML combined with the transport model may open a new venue to study the F factor. In addition, the interpretability analysis of the ML algorithm may also offer valuable insights for subsequent research.

Machine learning approaches for predicting and diagnosing chronic kidney disease: current trends, challenges, solutions, and future directions.

Chronic Kidney Disease (CKD) represents a significant global health challenge, contributing to increased morbidity and mortality rates. This review paper explores the current landscape of machine learning (ML) techniques employed in CKD prediction and diagnosis, highlighting recent trends, inherent challenges, innovative solutions, and future directions. Through an extensive literature survey, we identified key limitations and challenges, including the use of small datasets, the absence of stage-specific predictions, insufficient focus on model interpretability, and a lack of discussions on safeguarding patient privacy in managing sensitive CKD data. We considered these limitations and challenges as research gaps, and this review paper aims to address them. We emphasize the potential of Generative AI to augment dataset sizes, thereby enhancing model performance and reliability. To address the lack of stage-specific predictions, we highlight the need for effective multi-class models to accurately predict CKD stages, enabling tailored treatments and improved patient outcomes. Furthermore, we discuss the critical importance of model interpretability, utilizing methods such as SHAP (SHapley Additive exPlanations) and LIME (Local Interpretable Model-agnostic Explanations) to ensure transparency and trust among healthcare professionals. Privacy concerns surrounding sensitive patient data are also addressed. We present innovative privacy-preserving solutions using technologies, such as homomorphic encryption, federated learning, and blockchain. These solutions facilitate collaboration across institutions while maintaining patient confidentiality and addressing challenges related to limited generalizability and reproducibility in CKD prediction. This review informs healthcare professionals and researchers about advancements in ML for CKD prediction, to improve patient outcomes and address research gaps.

Surrogate model of turbulent transport in fusion plasmas using machine learning

Abstract The advent of machine learning (ML) has revolutionized the research of plasma confinement, offering new avenues for exploration. It enables the construction of models that effectively streamline the simulation process. While previous first-principles simulations have provided physics-based transport information, they have been inadequate fast for real-time applications or plasma control. In order to address this challenge, we introduce SExFC, a surrogate model based on the Gyro-Landau Extended Fluid Code (ExFC). An approach of physics-based database construction is detailed, as well the validity is illustrated. Through harnessing the power of ML, SExFC offers the capability to deliver rapid and precise predictions, facilitating real-time applications and enhancing plasma control. The proposed model integrates the recurrent neural network (RNN) algorithm, specifically leveraging the Gated Recurrent Unit (GRU) for iterative prediction of flux evolutions based on radial profiles. Therefore, the SExFC model has the potential to enable rapid and physics-based predictions that can be seamlessly integrated into future real-time plasma control systems.

Abstract B053: NucAE: Autoencoder-based enhancement of nucleosome occupancy signals from low-coverage cfDNA sequencing

Abstract Introduction: Cell-free DNA (cfDNA) is emerging as a valuable cancer biomarker, enabling both the detection and epigenetic characterization of malignancies through sequencing. cfDNA sequencing can reveal cancer-specific nucleosome occupancy patterns, which provide insights into tumor type and differentiation status, which define prognosis and therapy recommendations. Low-coverage whole-genome cfDNA sequencing is a cost-efficient approach to assay multiple cfDNA samples, however, the low coverage limits its sensitivity. We developed NucAE, a denoising autoencoder model, to enhance nucleosome occupancy signals from low-coverage cfDNA-sequencing. Methods: We designed NucAE to estimate nucleosome occupancy genome- wide from low-coverage sequencing data. To train the model, we undersampled high-coverage cfDNA-sequencing data and produced high- and low-coverage sample pairs at varying coverages (1x-90x). Inputs to NucAE include cfDNA fragment data and the corresponding genomic nucleotide sequence, with the model leveraging a symmetrical architecture comprising two convolutional layers in both the encoder and decoder, connected by ReLU activations. Mean squared error relative to the high-coverage signal was employed as the loss function. To evaluate the model independently, we performed peak detection from the nucleosome occupancy signals. We conducted a grid search to optimize hyperparameters. Results: We found that NucAE enhances the signal to noise ratio by detecting periodicities in nucleosome occupancy data. Denoising was improved by supplementing the cfDNA fragment signals with the genomic nucleotide sequences as input, which demonstrates that the model learned the nucleotide- sequence dependence of nucleosome positioning. Independent validation through peak detection on previously unseen samples demonstrated a significant improvement (p<0.001) in accuracy compared to raw signals across all tested coverages (1x-45x). Remarkably, at extremely low coverages (1x-2x), denoised signals allowed for more accurate peak detection than raw signals from 10-20x deeper sequencing. Conclusions: By using advanced machine-learning, we were able to enhance low-coverage cfDNA sequencing data to assay nucleosome positions at a nucleotide resolution. NucAE achieves an order of magnitude improvement over the low- coverage signals and greatly improves the utility of cfDNA-sequencing data to identify cancer- specific nucleosome occupancy, while preserving its low cost. Our model is the first to use autoencoders for genome-wide signal enhancement with potential use cases in many other areas of genomics. Citation Format: Zsolt Balázs, Jean Radig, Noah Wolford, Manuel Schürch, Michael Krauthammer. NucAE: Autoencoder-based enhancement of nucleosome occupancy signals from low-coverage cfDNA sequencing [abstract]. In: Proceedings of the AACR Special Conference: Liquid Biopsy: From Discovery to Clinical Implementation; 2024 Nov 13-16; San Diego, CA. Philadelphia (PA): AACR; Clin Cancer Res 2024;30(21_Suppl):Abstract nr B053.

Evaluating and improving the predictive accuracy of mixing enthalpies and volumes in disordered alloys from universal pretrained machine learning potentials

The advent of machine learning in materials science opens the way for exciting and ambitious simulations of large systems and long time scales with the accuracy of calculations. Recently, several pretrained universal machine learned interatomic potentials (UPMLIPs) have been published, i.e., potentials distributed with a single set of weights trained to target systems across a very wide range of chemistries and atomic arrangements. These potentials raise the hope of reducing the computational cost and methodological complexity of performing simulations compared to models that require for-purpose training. However, the application of these models needs critical evaluation to assess their usability across material types and properties. In this work, we investigate the application of the following UPMLIPs: MACE, CHGNET, and M3GNET to the context of alloy theory. We calculate the mixing enthalpies and volumes of 21 binary alloy systems and compare the results with DFT calculations to assess the performance of these potentials over different properties and types of materials. We find that the small relative energies necessary to correctly predict mixing energies are generally not reproduced by these methods with sufficient accuracy to describe correct mixing behaviors. However, the performance can be significantly improved by supplementing the training data with relevant training data. The potentials can also be used to partially accelerate these calculations by replacing the structural relaxation step. Published by the American Physical Society 2024

Creep Lifetime Prediction of Alloy 617 Using Black Box Machine Learning Approach

Abstract This study explored the application of black box machine learning (ML) to build high throughput models that predict the creep response of Ni-based Alloy 617. Black box ML refers to highly complex machine learning algorithms that generate outputs from inputs without an interpretable internal process. The rapid implementation of suitable heat of alloys into targeted service is impeded by the extended qualification process involving chemistry-processing-structure-performance assessment. The ASME B&PV Code III outlines the requirement of 10,000 h of creep testing before each heat can be qualified for service and 30,000 h for heats that exhibit metastable phases. There is a critical need to shorten the development-to-deployment timeline for heats of an alloy at specific applications. Recent advancement in ML offers the ability to identify correlations in data which is difficult to elucidate by other approaches. To that end, black box ML is employed to expedite the HEAT qualification of Alloy 617 and predict performance from HEAT chemistry out to an unprecedented timescale. In this study, creep data for Ni-based Alloy 617—a solid solution strengthened material is gathered from a wide range of data sources. The alloy chemistry, phases, precipitates, and microstructural features are analyzed to obtain the key strengthening mechanism. Service conditions, mechanical properties, chemistry, and chemical ratios are provided as potential input features. The Pearson correlation coefficient with a 95% confidence bound is employed for input feature screening where poorly correlated inputs are eliminated to speed up the ML process and prevent under- and/or over-fitting of predictions. In the ML algorithm, the selected input features are regarded as predictors, and rupture is regarded as the response. An algorithm evaluation is performed where 20 ML algorithms are trained with the training set. The three-layered neural network (NN) was observed to be the best algorithm for the given data based on statistical rationale. The NN accurately predicts rupture across a range of isotherms and data sources. The interpolative and extrapolative predictions are in compliance with ECCC V5 guidelines. A post-audit validation exhibits neither under- nor over-fitting and confirms the applicability of NN algorithms to unseen data. The black box ML provides a pathway to predict the performance directly from chemistry and opens avenues to rapid heat qualification.

Exploring Machine Learning Applications in Sports Injury Prediction Analysis

Abstract: Injuries, particularly those resulting from repetitive strain on the body, pose a significant challenge in athletics, where prevention has traditionally relied on historical data and human expertise. Existing methods for injury prevention have struggled to achieve higher precision in practice. However, technological advancements now enable artificial intelligence (AI) and machine learning (ML) to emerge as promising tools for enhancing both injury mitigation and rehabilitation strategies. This article provides a detailed overview of recent ML advances applied to sports injury prediction and prevention. A comprehensive literature review was conducted using databases such as PubMed/Medline, IEEE/IET, and Science Direct, with additional resources from Ovid Discovery and Google Scholar, including a grey literature search. Focus was placed on studies published between 2017 and 2022, examining algorithms including K-Nearest Neighbor (KNN), K-means, decision trees, random forest, gradient boosting, AdaBoost, and neural networks. A total of 42 original research papers were reviewed and their findings summarized. While the current lack of open-source, standardized datasets and the reliance on dated regression models limit strong conclusions about ML’s real-world efficacy in sports injury prediction, addressing these challenges could enable the deployment of advanced ML architectures, thereby accelerating progress in this field and supporting the development of validated clinical tools.

Enhancing Regional Wind Power Forecasting through Advanced Machine-Learning and Feature-Selection Techniques

In this study, an in-depth analysis is presented on forecasting aggregated wind power production at the regional level, using advanced Machine-Learning (ML) techniques and feature-selection methods. The main problem consists of selecting the wind speed measuring points within a large region, as the wind plant locations are assumed to be unknown. For this purpose, the main cities (province capitals) are considered as possible features and four feature-selection methods are explored: Pearson correlation, Spearman correlation, mutual information, and Chi-squared test with Fisher score. The results demonstrate that proper feature selection significantly improves prediction performance, particularly when dealing with high-dimensional data and regional forecasting challenges. Additionally, the performance of five prominent machine-learning models is analyzed: Long Short-Term Memory (LSTM) networks, Artificial Neural Networks (ANNs), Support Vector Machines (SVMs), Convolutional Neural Networks (CNNs), and Extreme-Learning Machines (ELMs). Through rigorous testing, LSTM is identified as the most effective model for the case study in northern Italy. This study offers valuable insights into optimizing wind power forecasting models and underscores the importance of feature selection in achieving reliable and accurate predictions.

Machine learning for predictive AAC: Improving speech and gesture-based communication systems

Augmentative and alternative communication (AAC) systems play a crucial role in supporting individuals with severe communication disabilities by providing accessible means of expression and engagement. However, many conventional AAC devices rely on manual input or basic predictive functions, which can limit communication efficiency and responsiveness. The application of machine learning (ML) to AAC offers new opportunities to enhance these systems, enabling them to provide faster, more accurate, and contextually relevant communication assistance. Advances in ML, particularly in predictive text, speech recognition, and gesture interpretation, allow AAC systems to adapt more intuitively to user needs, predicting intent based on usage patterns and multimodal data, such as voice and gestures. Current research highlights the potential of ML to address key gaps in AAC technology by creating more responsive, personalized systems that align with individual user behaviours. This study proposes a novel ML framework designed to integrate these capabilities, promising improvements in communication speed, user autonomy, and accuracy. By addressing the challenges and limitations of traditional AAC devices, this research aims to advance accessible communication solutions that empower users and improve quality of life.

Constitutive Modeling of Anisotropic Plasticity with ML Algorithms in Metals

Nuclear reactors hold significant promise for mitigating the environmental crisis and achieving a carbon-free world. The advancement of nuclear technology, however, is intricately tied to the materials used in reactors, with metals and alloys forming their core components. Understanding the plasticity and degradation of these materials is crucial to prevent critical reactor failures caused by factors such as radiation-induced embrittlement, creep, and fuel-cladding interactions. While traditional plasticity modeling has relied on constitutive laws and yield functions, the advent of machine learning (ML) and artificial intelligence has opened new avenues for this field. This paper explores the potential of data-driven approaches to enhance plasticity modeling for metals used in nuclear reactors. Recent studies have leveraged ML algorithms, including support vector machines and artificial neural networks, to model yield surfaces and correct theoretical yield functions with experimental data. Despite their accuracy, these models often lack interpretability and generality. To address these challenges, we investigate the applicability of various ML algorithms, i.e. neural networks, logistic regressions, decision trees, K-nearest neighbors, and Gaussian processes (GPs), in developing data-oriented flow rules for plasticity modeling. The paper demonstrates the superiority of GPs in terms of interpretability and generality. Using stress data generated from PyLabFEA, we compared the performance of these algorithms, highlighting the intrinsic uncertainties associated with GP predictions. Our findings indicate that Gaussian process classifiers (GPCs) offer a promising approach for modeling plasticity in metals, providing a balance between precision and physical insight. Additionally, this work presents a deep neural network (DNN) to model anisotropic Hill-type plasticity with perfect test data accuracy (accuracy score: 1.0), which is often hard to achieve with a classification problem. This shows the superiority of DNNs in terms of accuracy in modeling yield functions. The implications of our results for bridging the scale gaps in macrolevel simulations are discussed, and future directions for incorporating microstructural features into ML-based plasticity models are proposed. Overall, the ML framework presented in this paper can be employed for modeling constitutive relations that can be incorporated within traditional Finite Element Method (FEM)–based codes. Specifically, the GPC or DNN developed in this work can be readily swapped with the yield function within the so-called return mapping algorithm of nonlinear FEM-based plasticity subroutines to indicate yielding. Consequently, this merging of ML and FEM will allow us to leverage the geometric representational ability of FEM alongside the superior modeling capabilities of the ML algorithms.

A New Computer-Aided Diagnosis System for Breast Cancer Detection from Thermograms Using Metaheuristic Algorithms and Explainable AI

Advances in the early detection of breast cancer and treatment improvements have significantly increased survival rates. Traditional screening methods, including mammography, MRI, ultrasound, and biopsies, while effective, often come with high costs and risks. Recently, thermal imaging has gained attention due to its minimal risks compared to mammography, although it is not widely adopted as a primary detection tool since it depends on identifying skin temperature changes and lesions. The advent of machine learning (ML) and deep learning (DL) has enhanced the effectiveness of breast cancer detection and diagnosis using this technology. In this study, a novel interpretable computer aided diagnosis (CAD) system for breast cancer detection is proposed, leveraging Explainable Artificial Intelligence (XAI) throughout its various phases. To achieve these goals, we proposed a new multi-objective optimization approach named the Hybrid Particle Swarm Optimization algorithm (HPSO) and Hybrid Spider Monkey Optimization algorithm (HSMO). These algorithms simultaneously combined the continuous and binary representations of PSO and SMO to effectively manage trade-offs between accuracy, feature selection, and hyperparameter tuning. We evaluated several CAD models and investigated the impact of handcrafted methods such as Local Binary Patterns (LBP), Histogram of Oriented Gradients (HOG), Gabor Filters, and Edge Detection. We further shed light on the effect of feature selection and optimization on feature attribution and model decision-making processes using the SHapley Additive exPlanations (SHAP) framework, with a particular emphasis on cancer classification using the DMR-IR dataset. The results of our experiments demonstrate in all trials that the performance of the model is improved. With HSMO, our models achieved an accuracy of 98.27% and F1-score of 98.15% while selecting only 25.78% of the HOG features. This approach not only boosts the performance of CAD models but also ensures comprehensive interpretability. This method emerges as a promising and transparent tool for early breast cancer diagnosis.

Advent of machine learning in autonomous vehicles

The advent of Machine Learning has significantly transformed the landscape of automation, heralding a new era of efficiency, precision, and innovation. This literature review explores the pivotal role of machine learning in advancing automation across various industries. By examining the evolution of machine learning algorithms and their integration into automated systems, the paper highlights key developments and breakthroughs that have enabled machines to perform complex tasks with minimal human intervention. The review delves into case studies from manufacturing, healthcare, finance, and driver-less vehicles, illustrating how machine learning-driven automation has improved productivity, enhanced decision-making, and reduced operational costs. Furthermore, the paper discusses the challenges and ethical considerations associated with the widespread adoption of machine learning in automation, such as data privacy, job displacement, and algorithmic bias. By synthesizing findings from recent research, this review provides a thorough study of the current state and future potential of machine learning in automation. The insights gained underscore the huge impact of machine learning technologies, along with the need for continuous innovation and regulation to harness their full potential while mitigating associated risks. This paper serves as a valuable resource for academics, industry professionals, and policymakers aiming to navigate and contribute to the rapidly evolving field of machine learning in automation.

Text Analytics on YouTube Comments for Food Products

YouTube is a popular social media platform in the contemporary digital landscape. The primary focus of this study is to explore the underlying sentiment in user comments about food-related videos on YouTube, specifically within two pivotal food categories: plant-based and hedonic product. We labeled comments using sentiment lexicons such as TextBlob, VADER, and Google’s Sentiment Analysis (GSA) engine. Comment sentiment was classified using advanced Machine-Learning (ML) algorithms, namely Support Vector Machines (SVM), Multinomial Naive Bayes, Random Forest, Logistic Regression, and XGBoost. The evaluation of these models encompassed key macro average metrics, including accuracy, precision, recall, and F1 score. The results from GSA showed a high accuracy level, with SVM achieving 93% accuracy in the plant-based dataset and 96% in the hedonic dataset. In addition to sentiment analysis, we delved into user interactions within the two datasets, measuring crucial metrics, such as views, likes, comments, and engagement rate. The findings illuminate significantly higher levels of views, likes, and comments in the hedonic food dataset, but the plant-based dataset maintains a superior overall engagement rate.

A comprehensive comparison of machine learning models for ICH prognostication: Retrospective review of 1501 intra-cerebral hemorrhage patients from the Qatar stroke database.

Multiple prognostic scores have been developed to predict morbidity and mortality in patients with spontaneous intracerebral hemorrhage(sICH). Since the advent of machine learning(ML), different ML models have also been developed for sICH prognostication. There is however a need to verify the validity of these ML models in diverse patient populations. We aim to create machine learning models for prognostication purposes in the Qatari population. By incorporating inpatient variables into model development, we aim to leverage more information. 1501 consecutive patients with acute sICH admitted to Hamad General Hospital(HGH) between 2013 and 2023 were included. We trained, evaluated, and compared several ML models to predict 90-day mortality and functional outcomes. For our dataset, we randomly selected 80% patients for model training and 20% for validation and used k-fold cross validation to train our models. The ML workflow included imbalanced class correction and dimensionality reduction in order to evaluate the effect of each. Evaluation metrics such as sensitivity, specificity, F-1 score were calculated for each prognostic model. Mean age was 50.8(SD 13.1) years and 1257(83.7%) were male. Median ICH volume was 7.5ml(IQR 12.6). 222(14.8%) died while 897(59.7%) achieved good functional outcome at 90 days. For 90-day mortality, random forest(RF) achieved highest AUC(0.906) whereas for 90-day functional outcomes, logistic regression(LR) achieved highest AUC(0.888). Ensembling provided similar results to the best performing models, namely RF and LR, obtaining an AUC of 0.904 for mortality and 0.883 for functional outcomes. Random Forest achieved the highest AUC for 90-day mortality, and LR achieved the highest AUC for 90-day functional outcomes. Comparing ML models, there is minimal difference between their performance. By creating an ensemble of our best performing individual models we maintained maximum accuracy and decreased variance of functional outcome and mortality prediction when compared with individual models.

From lab to field with machine learning – Bridging the gap for movement analysis in real-world environments: A commentary

Biomechanical data collection was largely confined to controlled laboratory setups, relying on marker-based systems or force platforms. However, the emergence of wearable sensors and markerless motion capture has revolutionized this field, enabling data collection in real-world scenarios. This shift has also sparked interest in integrating machine learning (ML) into biomechanical workflows, promising to revolutionize data acquisition in field settings and refine data analysis (Halilaj et al., 2018). Figure 1 provides an overview of corresponding ML applications for key tasks in the biomechanical workflow. This commentary explores the transformative potential of ML in biomechanics, focusing on enhancing data collection and analysis in real-world environments. Pose estimation (a) is the process of automatically tracking and determining the body’s anatomical landmarks, body segments, or joint centre locations in video images using ML, enabling the quantification of human movement without marker and sensor attachments to the human body. Feature estimation (b) employs ML to predict complex biomechanical data, e.g. joint moments from more accessible data sources, including IMUs, pressure insoles, and RGB video cameras. Event detection (c) in time series data is the annotation of certain events that are used to extract useful and vital information or to remove unwanted and unnecessary data for further analysis. Clustering (d) involves grouping instances or individuals with similar biomechanical characteristics using unsupervised ML, thereby revealing underlying structures and subgroups within complex biomechanical data. Finally, automated classification (e) refers to the process of developing a predictive model that assigns input features of data samples to predefined categories or classes using supervised ML. Despite the advancements of ML in biomechanics, central challenges are faced. Estimation errors remain critically high depending on the task and application field, necessitating a careful reflection on data acquisition potentials. Furthermore, especially complex Deep Learning models, while showing promising performances, exhibit a lack of transparency in understanding their decision-making processes and the underlying patterns and rules learned from the data. This phenomenon, often termed as the black-box nature of these models, poses a considerable obstacle. In response, Explainable Artificial Intelligence (XAI), a field that encompasses different explainability approaches to shed light on the inner workings of complex, non-linear ML models, has gained increasing attention in recent years (Slijepcevic et al., 2023). A further central challenge is the availability of data and annotations, which describes the limited availability or insufficiency of relevant and comprehensive datasets, as well as task-specific annotations, for conducting thorough analyses and research in biomechanics. The lack of large-scale benchmark datasets available restricts the widespread adoption of ML-based approaches in biomechanics. Privacy concerns present significant ethical and legal issues, e.g. with identifiable video data. Additionally, model validation remains a critical problem, as many studies fail to validate their models on diverse datasets, often relying on limited data from a single laboratory. Furthermore, there is a risk that the fundamental mechanical understanding of biomechanical processes might be overshadowed by an over-reliance on ML techniques. In conclusion, the integration of ML into biomechanics presents a transformative opportunity for understanding human movement by enabling and improving data collection and analysis in real-world settings. Challenges in data accessibility and methodological transparency necessitate collaborative efforts for future advancements.

A review of deep learning within the framework of artificial intelligence for enhanced fiber and yarn quality

In the textile production chain, fibers serve as the foundational units for yarn, and yarn, in turn, acts as a fundamental component for woven or knitted fabrics. The quality control of fabrics is intricately tied to the management of fibers and yarns. Traditional laboratory methods have been utilized to assess their quality, but the advent of machine learning and deep learning introduces a transformative approach. This review explores the application of machine learning methods such as principal component analysis, support vector machine, and deep learning methods such as artificial neural networks, convolutional neural networks, you look only once, and genetic algorithms to predict various properties of fibers and yarns. In the context of fibers, the review delves into topics such as cotton fiber grading based on color, characterization of jute fiber, and the identification of medullation in alpaca fibers. For yarns, the focus shifts to predicting parameters such as yarn tenacity, evenness, abrasion index of spun yarns, inspection of false twist textured yarn packages, breaking elongation of ring-spun cotton yarns, tensile properties of cotton/spandex yarns, yarn thickness, and yarn hairiness. The review also provides insights into the advantages and limitations of the discussed studies. Despite the comprehensiveness of this review, it is acknowledged that there might be additional relevant work not covered. The review encourages the sharing of data to expedite the integration of these technologies in future applications within the field.

A machine learning framework to generate star cluster realisations

Computational astronomy has reached the stage where running a gravitational $N$-body simulation of a stellar system, such as a Milky Way star cluster, is computationally feasible, but a major limiting factor that remains is the ability to set up physically realistic initial conditions. We aim to obtain realistic initial conditions for $N$-body simulations by taking advantage of machine learning, with emphasis on reproducing small-scale interstellar distance distributions. The computational bottleneck for obtaining such distance distributions is the hydrodynamics of star formation, which ultimately determine the features of the stars, including positions, velocities, and masses. To mitigate this issue, we introduce a new method for sampling physically realistic initial conditions from a limited set of simulations using Gaussian processes. We evaluated the resulting sets of initial conditions based on whether they meet tests for physical realism. We find that direct sampling based on the learned distribution of the star features fails to reproduce binary systems. Consequently, we show that physics-informed sampling algorithms solve this issue, as they are capable of generating realisations closer to reality.

Advancements in Machine Learning and Deep Learning for Early Diagnosis of Chronic Kidney Diseases: A Comprehensive Review

Chronic kidney disease (CKD) is a prevalent and debilitating condition worldwide, characterized by progressive loss of kidney function over time. Early detection plays a crucial role in mitigating its impact on patient health and healthcare systems. In recent years, there has been a burgeoning interest in leveraging machine learning (ML) and deep learning (DL) techniques to enhance the early diagnosis of CKD. This comprehensive review explores the advancements in ML and DL models applied to CKD diagnosis, focusing on their ability to integrate diverse data sources including clinical biomarkers, imaging modalities, and patient demographics. Key ML algorithms such as Support Vector Machines (SVM), Random Forests (RF), and neural network architectures like Convolutional Neural Networks (CNNs) and Long Short-Term Memory networks (LSTMs) are examined in the context of their performance in predicting CKD progression, classifying disease stages, and identifying at-risk populations. Furthermore, the review discusses challenges such as data quality, model interpretability, and integration into clinical practice, alongside emerging trends in explainable AI, transfer learning, federated learning, and integration with electronic health records (EHRs). By synthesizing findings from recent literature, this paper aims to provide insights into current methodologies, identify gaps for future research, and underscore the transformative potential of ML and DL in revolutionizing early CKD diagnosis and management..

Recognition of Molecular Structure of Phosphonium Salts from the Visual Appearance of Material with Deep Learning Can Reveal Subtle Homologs.

Determining molecular structures is foundational in chemistry and biology. The notion of discerning molecular structures simply from the visual appearance of a material remained almost unthinkable until the advent of machine learning. This paper introduces a pioneering approach bridging the visual appearance of materials (both at the micro- and nanostructural levels) with traditional chemical structure analysis methods. Quaternary phosphonium salts are opted as the model compounds, given their significant roles in diverse chemical and medicinal fields and their ability to form homologs with only minute intermolecular variances. This research results in the successful creation of a neural network model capable of recognizing molecular structures from visual electron microscopy images of the material. The performance of the model is evaluated and related to the chemical nature of the studied chemicals. Additionally, unsupervised domain transfer is tested as a method to use the resulting model on optical microscopy images, as well as test models trained on optical images directly. The robustness of the method is further tested using a complex system of phosphonium salt mixtures. To the best of the authors' knowledge, this study offers the first evidence of the feasibility of discerning nearly indistinguishable molecular structures.

Application of Machine Learning in Education: Recent Trends Challenges and Future Perspective

In recent times, Machine learning (ML) is one of the most valuable fields of artificial intelligence (AI) that is transforming education. The application of ML in education provides a promising benefit both to the scientists and researchers and this is the focus of this study. This paper reviews recent trends and advancements of ML in education focusing on areas such as personalisation of learning, predictive analytics, plagiarism detection, intelligent tutoring systems, gamification of learning and recommendation systems. After conducting the literature review we found out the current benefits and challenges of ML in education. The paper also provides insight into the applications and provide the recommendations to address the challenges of ML in the field of education.