Traditional Techniques Research Articles

Group Validation in Recommender Systems: Framework for Multi-layer Performance Evaluation

Evaluation of recommendation systems continues evolving, especially in recent years. There have been several attempts to standardize the assessment processes and propose replacement metrics better oriented toward measuring effective personalization. However, standard evaluation tools merely possess the capacity to provide a general overview of a system’s performance; they lack consistency and effectiveness in their use, as evidenced by most recent studies on the topic. Furthermore, traditional evaluation techniques fail to detect potentially harmful data on small subsets. Moreover, they generally lack explainable features to interpret how such minor variations could affect the system’s performance. This proposal focuses on data clustering for recommender evaluation and applies a cluster assessment technique to locate such performance issues. Our new approach, named group validation , aids in spotting critical performance variability in compact subsets of the system’s data and unravels hidden weaknesses in predictions where such unfavorable variations generally go unnoticed with typical assessment methods. Group validation for recommenders is a modular evaluation layer that complements regular evaluation and includes a new unique perspective to the evaluation process. Additionally, it allows several applications to the recommender ecosystem, such as model evolution tests, fraud/attack detection, and the capacity for hosting a hybrid model setup.

Combining bag of visual words-based features with CNN in image classification

Abstract Although traditional image classification techniques are often used in authentic ways, they have several drawbacks, such as unsatisfactory results, poor classification accuracy, and a lack of flexibility. In this study, we introduce a combination of convolutional neural network (CNN) and support vector machine (SVM), along with a modified bag of visual words (BoVW)-based image classification model. BoVW uses scale-invariant feature transform (SIFT) and Oriented Fast and Rotated BRIEF (ORB) descriptors; as a consequence, the SIFT–ORB–BoVW model developed contains highly discriminating features, which enhance the performance of the classifier. To identify appropriate images and overcome challenges, we have also explored the possibility of utilizing a fuzzy Bag of Visual Words (BoVW) approach. This study also discusses using CNNs/SVM to improve the proposed feature extractor’s ability to learn more relevant visual vocabulary from the image. The proposed technique was compared with classic BoVW. The experimental results proved the significant enhancement of the proposed technique in terms of performance and accuracy over state-of-the-art models of BoVW.

Hybrid Laser Additive Manufacturing of Metals: A Review

Due to the unparalleled benefits of traditional processing techniques, additive manufacturing technology has experienced rapid development and continues to expand its applications. However, as industrial standards advance, the pressing needs for high precision, high performance, and high efficiency in the manufacturing sector have emerged as critical bottlenecks hindering the technology’s progress. Single-laser additive manufacturing methods are insufficient to meet these demands. This review presents a comprehensive exploration of metal hybrid laser additive manufacturing technology, encompassing various aspects, such as multi-process hybrid laser additive manufacturing, additive–subtractive hybrid manufacturing, multi-energy hybrid additive manufacturing, and multi-material hybrid additive manufacturing. Through a thorough examination of the principles of laser additive manufacturing technology and the concept of hybrid manufacturing, this paper investigates in depth the notable advantages of hybrid laser additive manufacturing technology. It provides valuable insights and recommendations to guide the development and research of innovative machining technologies.

Pavement Inspection in Transport Infrastructures Using Unmanned Aerial Vehicles (UAVs)

The growing demand for the transportation of goods and people has led to an increasing reliance on transportation infrastructure, which, in turn, subjects the pavements to high traffic volumes. In order to maintain adequate service and safety standards for users, it is essential to establish effective maintenance strategies that ensure the preservation of pavement conditions. As a result, emerging innovations in pavement surface inspection methods, surpassing traditional techniques in terms of inspection and data processing speed and accuracy, have garnered significant attention. One such groundbreaking innovation in inspection systems that has been tested and used in recent years to assess infrastructure condition is the use of unmanned aerial vehicles (UAVs). This study aims to present a critical open-access literature review on the use of UAVs in the inspection of transportation infrastructure pavement in order to assess the type of equipment used, the technology involved, applicability conditions, data processing, and future evolution. The analysis of relevant literature suggests that the integration of intelligent technologies substantially enhances the accuracy of data collection and the detection of pavement distress. Furthermore, it is evident that most applications and research efforts are oriented towards exploring image processing techniques for the creation of 3D pavement models and distress detection and classification.

Enhanced MADM framework for fuzzy comprehensive evaluation of attack ability of basketball defenders with the triangular fuzzy neutrosophic numbers

With the continuous improvement of modern basketball technology, higher requirements have been put forward for the personal abilities of basketball players. As the core of an organization, the offensive ability of a defender largely determines the team’s performance. Therefore, it is necessary to objectively evaluate the attacking ability of defenders. Traditional techniques cannot objectively reflect the true level of players due to their strong subjectivity. Therefore, establishing a scientific evaluation technique is particularly important. The fuzzy comprehensive evaluation of attack ability of basketball defenders is viewed as the multi-attribute decision-making (MADM). In this paper, the triangular fuzzy neutrosophic number cross-entropy (TFNN-CE) technique is designed with help of cross-entropy and triangular fuzzy neutrosophic sets (TFNSs). Furthermore, Then, TFNN-CE technique is addressed to solve the MADM. Finally, a numerical example for fuzzy comprehensive evaluation of attack ability of basketball defenders is given and some comparisons are conducted to r illustrate advantages of the designed technique. The main contribution of this paper is addressed: (1) The TFNN-CE technique is addressed under TFNSs; (2) the TFNN-CE technique is addressed for MADM under TFNSs; (2) the TFNN-CE technique for fuzzy comprehensive evaluation of attack ability of basketball defenders is addressed; (3) Through the several efficient comparisons, it is addressed that TFNN-CE technique is effective for fuzzy comprehensive evaluation of attack ability of basketball defenders.

Feeding habits of the Guiana dolphin, Sotalia guianensis, (Van Bénéden, 1864) (Cetacea: Delphinidae) in Sepetiba and Ilha Grande bays, southeastern Brazil

The analysis of gastrointestinal contents of dead animals is the primary and most traditional technique used to investigate cetacean feeding habits. The Guiana dolphin (Sotalia guianensis) is among the most common cetacean species on the Brazilian coast. Sepetiba and Ilha Grande bays currently house this species’ highest population estimates. The present study aims to characterize the feeding habits of the Guiana dolphin between 2007 and 2021 by analyzing the stomach contents of individuals found dead in Sepetiba and Ilha Grande bays. Based on this analysis, we compared feeding habits according to gender, sexual maturity, seasonality, and location. We also investigated the feeding habits of this species during the morbillivirus event. The diet of the Guiana dolphins of Sepetiba and Ilha Grande bays was predominantly composed of teleost fish, with cephalopods being the second most consumed prey. The prey family most present in the diet of the Guiana dolphin in Sepetiba and Ilha Grande bays was the teleost fish Sciaenidae. Although these populations live in very close environments, they show distinct feeding habits. The conservation of these ecosystems is crucial for preserving Guiana dolphins and other species that use Sepetiba and Ilha Grande bays to live, reproduce, and feed.

Oxidized mRNA Lipid Nanoparticles for In Situ Chimeric Antigen Receptor Monocyte Engineering

AbstractChimeric antigen receptor (CAR) monocyte and macrophage therapies are promising solid tumor immunotherapies that can overcome the challenges facing conventional CAR T cell therapy. mRNA lipid nanoparticles (mRNA‐LNPs) offer a viable platform for in situ engineering of CAR monocytes with transient and tunable CAR expression to reduce off‐tumor toxicity and streamline cell manufacturing. However, identifying LNPs with monocyte tropism and intracellular delivery potency is difficult using traditional screening techniques. Here, ionizable lipid design and high‐throughput in vivo screening are utilized to identify a new class of oxidized LNPs with innate tropism and mRNA delivery to monocytes. A library of oxidized (oLNPs) and unoxidized LNPs (uLNPs) is synthesized to evaluate mRNA delivery to immune cells. oLNPs demonstrate notable differences in morphology, ionization energy, and pKa, thereby enhancing delivery to human macrophages, but not T cells. Subsequently, in vivo library screening with DNA barcodes identifies an oLNP formulation, C14‐O2, with innate tropism to monocytes. In a proof‐of‐concept study, the C14‐O2 LNP is used to engineer functional CD19‐CAR monocytes in situ for robust B cell aplasia (45%) in healthy mice. This work highlights the utility of oxidized LNPs as a promising platform for engineering CAR macrophages/monocytes for solid tumor CAR monocyte therapy.

Structure of the ligule in American species of Selaginella P. Beauv. (Selaginellaceae)

The ligule is an important character in the taxonomic delimitation of Selaginella species. Here, the morphology of this organ is described in 11 American species. Four of these species are xerophytic: Selaginella convoluta, S. microphylla, S. peruviana, and S. sellowii, and seven are mesophytic: S. anceps, S. diffusa, S. flagellata, S. flexuosa, S. mollis, S. silvestris, and S. sulcata. Morphological data were obtained by traditional histological techniques. Observations were made by light and scanning electron microscopy. Variations in ligule size in vegetative leaves and sporophylls were determined using a correlation analysis with Spearman's coefficient. The ligule was found to have five body shapes: campanulate, linguiform, elliptic, fan-shaped, and rectangular. Each shape can have a lobed (bi-, tri-, or multi-lobed), rounded, or truncate apex. Size, shape, and apex are characteristic of each species and remain constant in young and mature leaves. No significant differences were observed between xerophytic and mesophytic species. The ligule of all species studied is described for the first time. Micrographs of all the species studied are presented, and the morphological results of this study have been mapped into the recent phylogeny of the genus.

Liposuction-Only Breast Reduction: A Systematic Review of Outcomes.

Over the past few decades, there have been multiple reports of liposuction assisted breast reduction. This technique appeals to patients due to the limited scars and complication profile, compared to traditional reduction mammaplasty techniques. We aimed to systematically review the literature, to elucidate the outcomes and safety of liposuction-only breast reduction. A systematic review was performed using the Ovid (Medline/PubMed) database, in accordance with the PRISMA checklist. In total 7 articles were included within this systematic review. A total of 652 patients were included. Liposuction-only breast reduction appears to lead to improvements in subjective outcome measures, patient satisfaction, and objective outcomes such as moderate breast volume reduction and reduction in breast ptosis. Overall, the procedure had a low complication profile. Liposuction did not preclude further surgery. No evidence of malignancy or difficulty in future breast cancer screening was noted. Macromastia leads to a considerable health burden, especially in health-related costs. From the current evidence base, liposuction-only breast reduction appears to be a safe and effective procedure, especially in patients requiring a mild-moderate breast volume reduction and mild ptosis correction. More research is required, with standardised subjective and objective outcome measures, and longer follow-up periods to confirm the effectiveness and safety of this technique. Level of Evidence III This journal requires that authors assign a level of evidence to each article. For a full description of these Evidence-Based Medicine Ratings, please refer to Table of Contents or online Instructions to Authors www.springer.com/00266 .

Neutrosophic Estimators for Estimating the Population Mean in Survey Sampling

ABSTRACT In sample survey analysis, accurate population mean estimation is an important task, but traditional approaches frequently ignore the intricacies of real-world data, leading to biassed results. In order to handle uncertainties, indeterminacies, and ambiguity, this work presents an innovative approach based on neutrosophic statistics. We proposed novel neutrosophic factor type exponential estimators that use auxiliary information to improve population mean precision. The suggested estimators are highly useful for computing results while working with unclear, hazy, and neutrosophic-type data. These estimators produce answers that are interval-form rather than single-valued, which may give our population parameter a better chance of being off. Since we now have an estimated interval with the population mean’s unknown value supplied a minimal MSE or highest Percentage Relative Efficiency (PRE), the estimators are more effective. The investigation of alpha constants in the neutrosophic framework, extending from −1 to +1, is at the heart of this research. These constants have a significant impact on how estimates are made and enable flexible accuracy modification. We choose the best neutrosophic values for characterizing constants, emphasizing their importance in obtaining precise estimations. This study further expands its originality by including preexisting estimators into the neutrosophic framework, showcasing its versatility and adaptability. We demonstrate the estimators’ superiority to traditional techniques through empirical assessments employing neutrosophic temperature information and simulation assessments. The ensuing interval-based results, influenced by alpha constants, offer concrete insights into the world of uncertainty, enabling more well-informed decision-making.

The Promise and Potential of Brain Organoids.

Brain organoids are 3D in vitro culture systems derived from human pluripotent stem cells that self-organize to model features of the (developing) human brain. This review examines the techniques behind organoid generation, their current and potential applications, and future directions for the field. Brain organoids possess complex architecture containing various neural cell types, synapses, and myelination. They have been utilized for toxicology testing, disease modeling, infection studies, personalized medicine, and gene-environment interaction studies. An emerging concept termed Organoid Intelligence (OI) combines organoids with artificial intelligence systems to generate learning and memory, with the goals of modeling cognition and enabling biological computing applications. Brain organoids allow neuroscience studies not previously achievable with traditional techniques, and have the potential to transform disease modeling, drug development, and the understanding of human brain development and disorders. The aspirational vision of OI parallels the origins of artificial intelligence, and efforts are underway to map a roadmap toward its realization. In summary, brain organoids constitute a disruptive technology that is rapidly advancing and gaining traction across multiple disciplines.

Brain Tumor Detection: Transfer Learning Approach with VGG-16

Brain tumors have a profound impact on individuals worldwide, necessitating early detection to improve patient outcomes. This study explores the potential of deep learning in facilitating early tumor detection to aid medical professionals in timely intervention and personalized treatment strategies. While current tumor detection methodologies rely on traditional imaging techniques and manual analysis, they may suffer from limitations in accuracy and efficiency. To address these challenges, we propose a novel method using the VGG-16 architecture, a powerful Convolutional Neural Network (CNN) model, with pre-trained weights for feature extraction. By harnessing the capability of VGG-16, our model effectively discerns tumor patterns from brain MRI scans. The dataset utilized for training and evaluation consists of Brain MRI Images for Brain Tumor Detection from Kaggle, featuring a diverse range of annotated scans. During the evaluation, we focus on the primary performance metric of accuracy, which measures the model's ability to precisely classify tumor and non-tumor cases. Through extensive experimentation and analysis, we critically assess the model's performance and its potential clinical applicability

Imaging of moho topography with conditional generative adversarial network from observed gravity anomalies

Accurate estimation of Moho topography plays a crucial role in understanding Earth’s structure, geodynamic processes, and resource exploration. This study presents a novel approach that utilizes conditional Generative Adversarial Networks (cGAN) to reveal Moho topography based on observed gravity anomalies. Synthetic training datasets of Moho topography were generated using the FFT filtering method due to the scarcity of true datasets. Spherical prism-based forward gravity modeling was employed to evaluate the resulting gravity anomalies. We compared the performance of our developed deep learning algorithm cGAN (conditional Generative Adversarial Networks) with a traditional inversion technique using various synthetic datasets, and a real case study in southern peninsular India, a geologically diverse region comprising ancient continental tectonic blocks. Bott’s inversion scheme was employed as a verification method for the Moho surface estimation using the presented deep learning model. Using spherical prism-based forward gravity modeling, observed gravity anomalies were corrected for multiple factors such as topography, bathymetry, sediments, crustal heterogeneities, and mantle heterogeneities. By removing these effects, we isolated the gravity contribution solely related to pure Moho undulation. The mean Moho depth and density contrast between the crust and mantle were derived from seismic constraints for improving estimation accuracy. The findings demonstrate the potential of the cGAN and spherical prism-based gravity modeling approach in accurately estimating the Moho topography, offering insights into Earth’s subsurface structures and enhancing our understanding of geodynamic processes and resource exploration efforts.

Recent molecular techniques to strengthen ecological studies in echinoderms

Introduction: Echinoderms, an integral component of marine ecosystems worldwide, have captivated scientific interest for centuries. Despite this longstanding attention, comprehending key facets such as trophic relationships, diet composition, and host-microbiota relationships still represents a challenge using traditional techniques. Recent years, however, have witnessed a transformative shift, thanks to the emergence of advanced molecular techniques, offering new approaches to strengthen ecological studies in echinoderms.
 Objective: Explore how recent advancements in molecular tools have impacted ecological research on echinoderms. Specifically, we aim to investigate the potential of these tools to shed light on trophic interactions, diet composition, and the characterization of gut microbial communities in these organisms.
 Methods: Available literature was used to clarify how novel molecular techniques can improve ecological studies. The focus is diet, trophic relationships, and gut microbiota.
 Results: Traditionally, studies of stomach contents using compound microscopy have provided an idea of ingested material; nevertheless, sometimes a simple magnified visualization of dietary content does not allow exhaustive identification of the entire food spectrum, as it is limited due to the rapid digestion and maceration of food items within the echinoderm’s digestive tract. The use of DNA-metabarcoding, targeting specific DNA regions, such as the mitochondrial COI gene, has allowed us to enhance the accuracy and precision of diet characterization by enabling the identification of prey items down to the species or even genetic variant level, providing valuable insights into specific dietary preferences. Another approach is the use of stable isotopes, particularly carbon and nitrogen, which provide a powerful tool to trace the origin and flow of nutrients through food webs. By analyzing the isotopic signatures in muscular tissues and food items, we can discern the sources of their primary food items and gain insights into their trophic position within the ecosystem. Lastly, a third new technique used to elucidate the characterization of the prokaryotic community is 16S rRNA sequencing. This method allows us to explore the composition and dynamics of the digestive tract microbial communities.
 Conclusions: This is a promising era for ecological research on echinoderms, where advances of molecular tools have enabled an unprecedented level of detail, resolving longstanding challenges in comprehending their trophic interactions, diet composition, and host-microbiota relationships, and opening new avenues of investigation in ecological studies.

Screening of Machine Learning Techniques on Predictive Maintenance: a Scoping Review

Predictive maintenance (PdM) is a set of actions and techniques to early detect failures and defects on machines before they occur, and the usage of machine learning and deep learning techniques in predictive maintenance has increased during the last years. Even with this increase of the literature, there is still a gap concerning the application of such techniques for PdM in the industry, as there are no clear guidelines about which information to use for a PdM system, how to process the information, and what machine learning techniques should be used in order to obtain acceptable results. This scoping review is performed in order to observe the current status on the use of Machine Learning and Deep Learning in predictive maintenance in academia and provide answer to the questions related to these guidelines. For this purpose, a literature review of the last five years is carried out, using those articles that cover information about sources of information used for PdM, the treatment given to such data and the machine learning (ML) methods or techniques used. The Web of Science: Core Collection database is used as a source of information, specifically the Science Citation Index Expanded (SCIE). The review shows that there are different information sources used for machine learning and deep learning in PdM, depending on the origin of the data and the availability of it, and as well whether the data sets are private or public. Also, we can observe that data used for both training and making predictions does not only use traditional pre-processing techniques, but that about one fifth of the articles even propose new techniques in this field. Additionally, we compare a wide range of techniques and algorithms which are used in Deep Learning -being ANN the most used- and in Machine Learning, being SVM the most used algorithm, closely followed by Random Forest. Based on the results, we provide indications about how to apply ML for PdM in industry. Keywords: machine learning, predictive maintenance, artificial intelligence, deep learning, data processing, data collection

Coniochaeta hoffmannii and mutabilis Invasive Fungal Keratitis: A Case Series and Literature Review

Purpose: To describe 2 Coniochaeta species (Coniochaeta hoffmannii and Coniochaeta mutabilis) as rare causes of invasive fungal keratitis resulting in enucleations and to provide a review of ocular infections caused by the genus Coniochaeta and underscore changes to its classification over the past 3 decades, which may clarify previous reports with outdated nomenclature. Methods: This is a small case series from a single academic institution (Casey Eye Institute) with a summary of the literature. Results: The first case describes a 53-year-old man who had an indolent but persistent anterior chamber reaction after repair of a penetrating nail injury. Cultures from a second penetrating keratoplasty identified C. hoffmannii, which was determined through phenotypic characterization and DNA sequencing. Despite surgical management, cultures were persistently positive for C. hoffmannii. Two years post-injury, he developed a funnel retinal detachment with proliferative vitreoretinopathy and elected for enucleation. The second case describes a 54-year-old woman with poor contact lens hygiene with a presumed filamentous fungal keratitis that remained refractory to topical natamycin. Broad-range polymerase chain reaction of an anterior chamber aspirate identified C. mutabilis. Therapeutic keratoplasty was performed for worsening infection; however, because of intractable pain, she elected for enucleation. Pathology from the enucleation specimen demonstrated persistent, but sparse, fungal elements. Conclusions: This is the first case series characterizing ocular infections caused by Coniochaeta, a rare cause of invasive fungal keratitis resulting in devastating outcomes for our patients. Identification of Coniochaeta was initially difficult by traditional culturing techniques, and subsequent molecular diagnostic testing proved useful in detection. Our review of ocular Coniochaeta clarifies previous reports with outdated nomenclature.

A miniaturized culture platform for control of the metabolic environment.

The heart is a metabolic "omnivore" and adjusts its energy source depending on the circulating metabolites. Human cardiac organoids, a three-dimensional in vitro model of the heart wall, are a useful tool to study cardiac physiology and pathology. However, cardiac tissue naturally experiences shear stress and nutrient fluctuations via blood flow in vivo, whilst in vitro models are conventionally cultivated in a static medium. This necessitates the regular refreshing of culture media, which creates acute cellular disturbances and large metabolic fluxes. To culture human cardiac organoids in a more physiological manner, we have developed a perfused bioreactor for cultures in a 96-well plate format. The designed bioreactor is easy to fabricate using a common culture plate and a 3D printer. Its open system allows for the use of traditional molecular biology techniques, prevents flow blockage issues, and provides easy access for sampling and cell assays. We hypothesized that a perfused culture would create more stable environment improving cardiac function and maturation. We found that lactate is rapidly produced by human cardiac organoids, resulting in large fluctuations in this metabolite under static culture. Despite this, neither medium perfusion in bioreactor culture nor lactate supplementation improved cardiac function or maturation. In fact, RNA sequencing revealed little change across the transcriptome. This demonstrates that cardiac organoids are robust in response to fluctuating environmental conditions under normal physiological conditions. Together, we provide a framework for establishing an easily accessible perfusion system that can be adapted to a range of miniaturized cell culture systems.

Numerical Simulation and Mathematical Analysis of Meta Heuristic MPPT System for Solar Photovoltaic Applications Under Non-Linear Operational Conditions

As a sustainable energy source, the use of solar photovoltaic (PV) systems has significantly increased. Environmental elements, especially partial shadowing circumstances, have a considerable impact on how well solar PV systems function. In such cases, the various local maxima in the power-voltage curve make it difficult for conventional Maximum Power Point Tracking (MPPT) methods to maintain peak efficiency. Heuristic Maximum Power Point Tracking (MPPT) system for solar photovoltaic (PV) applications, employing the cuckoo search algorithm. The primary objective of the research is to enhance the efficiency and reliability of solar PV systems by optimizing the MPPT process, which is crucial for maximizing energy extraction under varying environmental conditions. The model is used to simulate the performance of the system under various environmental conditions, such as changes in temperature and irradiance levels. The simulation results are then statistically analyzed to evaluate the effectiveness of the cuckoo search algorithm in tracking the maximum power point accurately and rapidly. The algorithm demonstrates a robust ability to converge to the maximum power point efficiently, thereby enhancing the overall energy yield of the solar PV system.. The performance of the hybrid PSO-CSA MPPT algorithm in contrast to traditional MPPT techniques is assessed through simulations and tests under various shading circumstances. The findings show that the hybrid strategy regularly outperforms conventional methods by enhancing the total energy production of partially shadowed solar PV installations through faster convergence, less oscillations, and greater tracking accuracy. The proposed hybrid algorithm also demonstrates stability and flexibility in real-world settings, making it a potential option for boosting the dependability and efficiency of solar PV systems when shade is present. This study advances the field of renewable energy and prepares the path for the use of sophisticated optimization methods to the problems of solar PV power generation under changing environmental circumstances.

Application of data-driven model reduction techniques in reactor neutron field calculations

High-order harmonic techniques can be used to recreate neutron flux distributions in reactor cores using the neutron diffusion equation. However, traditional source iteration and source correction iteration techniques have sluggish convergence rates and protracted calculation periods. The correctness of the implicitly restarted Arnoldi method (IRAM) in resolving the eigenvalue problems of the one-dimensional and two-dimensional neutron diffusion equations was confirmed by computing the benchmark problems SLAB_1D_1G and two-dimensional steady-state TWIGL using IRAM. By integrating Galerkin projection with Proper Orthogonal Decomposition (POD) techniques, a POD-Galerkin reduced-order model was developed and the IRAM model was used as the full-order model. For 14 macroscopic cross-section values, the TWIGL benchmark problem was perturbed within a 20% range. We extracted 100 sample points using the Latin hypercube sampling method, and 70% of the samples were used as the testing set to assess the performance of the reduced-order model The remaining 30% were utilized as the training set to develop the reduced-order model, which was employed to rebuild the TWIGL benchmark problem. The reduced-order model demonstrates good flexibility and can efficiently and accurately forecast the effective multiplication factor and neutron flux distribution in the core. The reduced-order model predicts keff and neutron flux distribution with a high degree of agreement compared to the full-order model. Additionally, the reduced-order model's computation time is only 10.18% of that required by the full-order model.The neutron flux distribution of the steady-state TWIGL benchmark was recreated using the reduced-order model. The obtained results indicate that the reduced-order model can accurately predict the keff and neutron flux distribution of the steady-state TWIGL benchmark.Overall, the proposed technique not only has the potential to accurately project neutron flux distributions in transient settings, but is also relevant for reconstructing neutron flux distributions in steady-state conditions; thus, its applicability is bound to increase in the future.

Estimation of slope stability using ensemble-based hybrid machine learning approaches

Mining is one of the most daunting occupations gain the sector since it entails risk at any point in the operation. In its operation, the main focus is on slope stability. To avoid slope failures, work should be performed in line with both the regulations and the safety criteria. Slope stability is essential in mining activities owing to slope failure putting productivity and safety at risk. Prediction of slope failure is difficult because of the complexity of traditional engineering techniques. Through study, recent technologies have helped mining companies predict slope problems quickly and effectively. In this current research, an ensemble of machine learning intelligence algorithms was used to estimate and assess the Factor of Safety (FOS). In Ostapal Chromicte Mine, India, 79 experimental and failure slope occurrences were tracked to gather in-the-moment field data. The available data were split into training and testing sets at random to build algorithms. The five influenced factors such as the unit weight, the friction angle, the cohesiveness, the mining depth, as well as the slope angle used as input variables to estimate the FOS. Selected machine learning techniques such as Multiple Linear Regression (MLR), Decision Tree, Random Forest (RF), eXtreme Gradient Boosting (XGBoost) and ensemble hybrid model combining eXtreme Gradient Boosting and Random Forest (XGBoost-RF) were developed to evaluate the FOS. The validity and efficiency of created models can be evaluated using standard evaluation parameters such as coefficient of determination (R2), root mean square error (RMSE), mean square error (MSE), normalized root mean square error (NRMSE), mean absolute percentage error (MAPE) and mean absolute deviation (MAD). The most precise model to assess the FOS across all models was discovered to be the XGBOOST-RF ensemble model, which had a high R2 of 0.931, MSE of 0.009, NRMSE of 0.069, MAD of 0.037, MAPE of 3.581 and an RMSE of 0.098.