Learning Methodology Research Articles

Research on Assessment Method for Cognitive Influence Factors of Nuclear Power Plant Operators Based on Fuzzy Analytic Hierarchy Process and Deep Learning of Electroencephalogram Signals

This study explores the factors influencing the cognitive processes of operators in digital nuclear power plants, with a focus on the correlation between these factors and electroencephalogram (EEG) features. Initially, based on expert consultations, seven factors were considered: stress, time, fatigue, procedural complexity, user interface experience, procedural clarity, and efficiency. From these, four were identified as the most crucial for each stage of the cognitive process, highlighting their significant roles in influencing cognitive performance and potentially correlating with distinct EEG characteristics. These were assessed using the fuzzy analytic hierarchy process (FAHP) to determine the weightings of influences across the cognitive stages of monitoring, decision making, and execution. Employing a simulated scenario of a steam generator tube rupture, subjective questionnaires were utilized to gauge participant perceptions of influencer impacts at each stage, calculating human factors fuzzy synthetic values. Concurrently, EEG signals were segmented by operational steps, extracting around 114 features across the time, frequency, and time-frequency domains, which were then dimensionally reduced to 17 principal components via adaptive principal components analysis (APCA). A correlation analysis was performed between the human factors fuzzy synthetic values and the APCA-reduced EEG features of participants. Subsequently, the EEG feature columns of the eight selected participants were used as inputs to construct a transformer-based self-attention network model to evaluate the participants’ human factors fuzzy comprehensive values. The findings confirm the transformer model’s efficacy in assessing these values, evidencing a significant correlation between the EEG features and human factors fuzzy synthetic values. Integrating FAHP with machine learning methodologies, this model proficiently estimated operators’ cognitive states during various cognitive processes, significantly enhancing human-machine interface design and the operational safety and efficiency at nuclear power plants.

Pulmonary Nodule Detection, Segmentation and Classification Using Deep Learning: A Comprehensive Literature Review

Lung cancer is a leading cause of cancer-related deaths worldwide, emphasizing the significance of early detection. Computer-aided diagnostic systems have emerged as valuable tools for aiding radiologists in the analysis of medical images, particularly in the context of lung cancer screening. A typical pipeline for lung cancer diagnosis involves pulmonary nodule detection, segmentation, and classification. Although traditional machine learning methods have been deployed in the previous years with great success, this literature review focuses on state-of-the-art deep learning methods. The objective is to extract key insights and methodologies from deep learning studies that exhibit high experimental results in this domain. This paper delves into the databases utilized, preprocessing steps applied, data augmentation techniques employed, and proposed methods deployed in studies with exceptional outcomes. The reviewed studies predominantly harness cutting-edge deep learning methodologies, encompassing traditional convolutional neural networks (CNNs) and advanced variants such as 3D CNNs, alongside other innovative approaches such as Capsule networks and transformers. The methods examined in these studies reflect the continuous evolution of deep learning techniques for pulmonary nodule detection, segmentation, and classification. The methodologies, datasets, and techniques discussed here collectively contribute to the development of more efficient computer-aided diagnostic systems, empowering radiologists and dfhealthcare professionals in the fight against this deadly disease.

A systematic literature review on software applications used to support curriculum development and delivery in primary and secondary education

The evolution of educational software applications has revolutionised teaching and learning methodologies in primary and secondary education over the past decade. This paper conducts a review of primary studies based on N = 21 papers published between 2013 and 2023, focusing on the diverse landscape of software applications designed for student learning, curriculum development, delivery, and assessment. Findings from this study showcases a range of software solutions ranging from assessment tools to tutoring applications. Distinctive features supporting various aspects of teaching and learning, including lesson planning, delivery, management, assessment, and self-directed learning, were also identified. Regarding the features of software solutions used in primary and secondary schools, some differences were identified in terms of complexity, interactivity, assessment methodologies, and the collaborative functionalities of these tools. While highlighting the potential benefits, findings from this study also showed that challenges such as deployment costs, user self-efficacy, and technology anxiety are influential factors affecting the adoption of these technologies in primary and secondary educational settings. The evidence presented in this study serves as a resource for educational leaders and practitioners, facilitating a deeper understanding of available educational tools and essential considerations in the design and adoption of future tools.

Predicting and optimizing CO2 foam performance for enhanced oil recovery: A machine learning approach to foam formulation focusing on apparent viscosity and interfacial tension

Carbon dioxide foam injection stands as a promising method for enhanced oil recovery (EOR) and carbon sequestration. However, accurately predicting its efficiency amidst varying operational conditions and reservoir parameters remains a significant challenge for conventional modeling techniques. This study explores the application of machine learning (ML) methodologies to develop a robust model for matching experimental values in CO2 foam flooding scenarios. Leveraging a comprehensive dataset encompassing diverse surfactants and rock types, with varied porosity and permeability, our model demonstrates accurate predictions across a wide spectrum of conditions. By focusing on key parameters such as foam apparent viscosity, interfacial tension (IFT), injected foam volume, initial oil saturation, porosity, and permeability, we unveil the pivotal role of these factors in determining CO2 foam EOR performance. Through rigorous analysis, we identify the relative importance of each input parameter, with injected foam volume, apparent viscosity, and IFT emerging as dominant factors. The most accurate model was deep neural network (DNN) (R2 value of 0.99). Higher foam viscosity and lower IFT were found to significantly enhance oil recovery rates, though their effects plateau beyond certain thresholds (apparent viscosities above 1200 cP and IFT values below 0.2 mN/m). The findings underscore the potential of ML-driven approaches in enhancing CO2 foam EOR predictions, offering insights crucial for optimizing foam flooding performance across diverse reservoir settings.

Lessons on Datasets and Paradigms in Machine Learning for Symbolic Computation: A Case Study on CAD

Symbolic Computation algorithms and their implementation in computer algebra systems often contain choices which do not affect the correctness of the output but can significantly impact the resources required: such choices can benefit from having them made separately for each problem via a machine learning model. This study reports lessons on such use of machine learning in symbolic computation, in particular on the importance of analysing datasets prior to machine learning and on the different machine learning paradigms that may be utilised. We present results for a particular case study, the selection of variable ordering for cylindrical algebraic decomposition, but expect that the lessons learned are applicable to other decisions in symbolic computation. We utilise an existing dataset of examples derived from applications which was found to be imbalanced with respect to the variable ordering decision. We introduce an augmentation technique for polynomial systems problems that allows us to balance and further augment the dataset, improving the machine learning results by 28% and 38% on average, respectively. We then demonstrate how the existing machine learning methodology used for the problem—classification—might be recast into the regression paradigm. While this does not have a radical change on the performance, it does widen the scope in which the methodology can be applied to make choices.

Combining High-Throughput Experiments and Active Learning to Characterize Deep Eutectic Solvents.

The high tunability of deep eutectic solvents (DESs) stems from the ease of changing their precursors and relative compositions. However, measuring the physicochemical properties across large composition and temperature ranges, necessary to properly design target-specific DESs, is tedious and error-prone and represents a bottleneck in the advancement and scalability of DES-based applications. As such, active learning (AL) methodologies based on Gaussian processes (GPs) were developed in this work to minimize the experimental effort necessary to characterize DESs. Owing to its importance for large-scale applications, the reduction of DES viscosity through the addition of a low-molecular-weight solvent was explored as a case study. A high-throughput experimental screening was initially performed on nine different ternary DESs. Then, GPs were successfully trained to predict DES viscosity from its composition and temperature, showcasing the ability of these stochastic, nonparametric models to accurately describe the physicochemical properties of complex mixtures. Finally, the ability of GPs to provide estimates of their own uncertainty was leveraged through an AL framework to minimize the number of data points necessary to obtain accurate viscosity modes. This led to a significant reduction in data requirements, with many systems requiring only five independent viscosity data points to be properly described.

Implementasi Model Pembelajaran Make a Match pada Siswa Kelas XI-B1 SMAN 9 Surabaya untuk Meningkatkan Hasil Belajar Teks Cerpen

This study uses the Make a Match learning methodology in class XI-B1 SMAN 9 Surabaya to increase student learning outcomes on short story text content. 36 students participated in two cycles of the study. Following the implementation of the Make a Match learning paradigm, the results demonstrated a significant increase in student participation and learning outcomes. Despite some students still falling short of the KKM, the number of students in cycle 1 who received good and very good categories grew. Every student outperformed the KKM in cycle 2, with 41.7% placing them in the outstanding group and 58.3% in the good category. This approach worked well to increase overall student participation and learning results.

Machine learning algorithm-based biomarker exploration and validation of mitochondria-related diagnostic genes in osteoarthritis.

The role of mitochondria in the pathogenesis of osteoarthritis (OA) is significant. In this study, we aimed to identify diagnostic signature genes associated with OA from a set of mitochondria-related genes (MRGs). First, the gene expression profiles of OA cartilage GSE114007 and GSE57218 were obtained from the Gene Expression Omnibus. And the limma method was used to detect differentially expressed genes (DEGs). Second, the biological functions of the DEGs in OA were investigated using Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analysis. Wayne plots were employed to visualize the differentially expressed mitochondrial genes (MDEGs) in OA. Subsequently, the LASSO and SVM-RFE algorithms were employed to elucidate potential OA signature genes within the set of MDEGs. As a result, GRPEL and MTFP1 were identified as signature genes. Notably, GRPEL1 exhibited low expression levels in OA samples from both experimental and test group datasets, demonstrating high diagnostic efficacy. Furthermore, RT-qPCR analysis confirmed the reduced expression of Grpel1 in an in vitro OA model. Lastly, ssGSEA analysis revealed alterations in the infiltration abundance of several immune cells in OA cartilage tissue, which exhibited correlation with GRPEL1 expression. Altogether, this study has revealed that GRPEL1 functions as a novel and significant diagnostic indicator for OA by employing two machine learning methodologies. Furthermore, these findings provide fresh perspectives on potential targeted therapeutic interventions in the future.

Mapping low-lying states and [formula omitted] in even-even nuclei with machine learning

A machine-learning algorithm, Light Gradient Boosting Machine, was applied for the first time to investigate the fundamental experimental observables in even-even nuclei over the Segrè chart. Specifically, we focused on the excitation energies of the 21+ and 41+ states, and the reduced electric quadrupole transition probability B(E2;01+→21+). Present obtained results well reproduced experimental data within an accuracy of 1.07, 1.05, and 1.14 times for the 21+ and 41+ states as well as B(E2;01+→21+), respectively, being significantly precise than the results from any state-of-the-art nuclear models and from any machine-learning-based approaches. The predictive capability of our machine learning methodology was further validated using 17 newly measured data points which were not used in the training set. Taking O, Ca, Sn, and Pb isotopes as examples, it has been found that our methodology precisely captures both the isotopic trend and absolute values, surpassing all theoretical models hitherto. Our findings reveal the double-magic nature of 100Sn and the disappearance of the N=20 shell in 28O.

A Deep Learning-Enhanced Compartmental Model and Its Application in Modeling Omicron in China.

The mainstream compartmental models require stochastic parameterization to estimate the transmission parameters between compartments, whose calculation depend upon detailed statistics on epidemiological characteristics, which are expensive, economically and resource-wise, to collect. In addition, infectious diseases spread in three dimensions: temporal, spatial, and mobile, i.e., they affect a population through not only the time progression of infection, but also the geographic distribution and physical mobility of the population. However, the parameterization process for the mainstream compartmental models does not effectively capture the spatial and mobile dimensions. As an alternative, deep learning techniques are utilized in estimating these stochastic parameters with greatly reduced dependency on data particularity and with a built-in temporal-spatial-mobile process that models the geographic distribution and physical mobility of the population. In particular, we apply DNN (Deep Neural Network) and LSTM (Long-Short Term Memory) techniques to estimate the transmission parameters in a customized compartmental model, then feed the estimated transmission parameters to the compartmental model to predict the development of the Omicron epidemic in China over the 28 days for the period between 4 June and 1 July 2022. The average levels of predication accuracy of the model are 98% and 92% for the number of infections and deaths, respectively. We establish that deep learning techniques provide an alternative to the prevalent compartmental modes and demonstrate the efficacy and potential of applying deep learning methodologies in predicting the dynamics of infectious diseases.

Design, Building and Deployment of Smart Applications for Anomaly Detection and Failure Prediction in Industrial Use Cases

This paper presents a comparative analysis of deep learning techniques for anomaly detection and failure prediction. We explore various deep learning architectures on an IoT dataset, including recurrent neural networks (RNNs, LSTMs and GRUs), convolutional neural networks (CNNs) and transformers, to assess their effectiveness in anomaly detection and failure prediction. It was found that the hybrid transformer-GRU configuration delivers the highest accuracy, albeit at the cost of requiring the longest computational time for training. Furthermore, we employ explainability techniques to elucidate the decision-making processes of these black box models and evaluate their behaviour. By analysing the inner workings of the models, we aim at providing insights into the factors influencing failure predictions. Through comprehensive experimentation and analysis on sensor data collected from a water pump, this study contributes to the understanding of deep learning methodologies for anomaly detection and failure prediction and underscores the importance of model interpretability in critical applications such as prognostics and health management. Additionally, we specify the architecture for deploying these models in a real environment using the RAI4.0 metamodel, meant for designing, configuring and automatically deploying distributed stream-based industrial applications. Our findings will offer valuable guidance for practitioners seeking to deploy deep learning techniques effectively in predictive maintenance systems, facilitating informed decision-making and enhancing reliability and efficiency in industrial operations.

Blended Learning: Analysis of University Student Learning Motivation for Citizenship Learning Courses in Elementary Teacher Education

The COVID-19 pandemic highlighted the need for ongoing education, prompting the education sector to seek alternatives to solely online learning. One of the steps that this university has taken is to combine the benefits of face-to-face and online learning through the use of technology, which is called blended learning. This study aims to assess the extent of student motivation for learning in a mixed learning environment in the Citizenship Learning course within the Elementary School Teacher Education department at UIN Sunan Kalijaga, Yogyakarta. This study employs a mixed method approach, with a sample size of 30 students as participants. Data for the study was acquired via observations, interviews, and questionnaires. The study results showed that the level of university student motivation towards Citizenship Learning through blended learning was 63.72% with a high category. This study showed that students’ learning motivation remains strong when using blended learning despite challenges like internet network reliability, device availability, and implementing appropriate learning methodologies.

Removal of heavy metals using lichen-derived activated carbons: adsorption studies, machine learning, and response surface methodology approaches

Removal of heavy metals using lichen-derived activated carbons: adsorption studies, machine learning, and response surface methodology approaches

DrugSynthMC: An Atom-Based Generation of Drug-like Molecules with Monte Carlo Search.

A growing number of deep learning (DL) methodologies have recently been developed to design novel compounds and expand the chemical space within virtual libraries. Most of these neural network approaches design molecules to specifically bind a target based on its structural information and/or knowledge of previously identified binders. Fewer attempts have been made to develop approaches for de novo design of virtual libraries, as synthesizability of generated molecules remains a challenge. In this work, we developed a new Monte Carlo Search (MCS) algorithm, DrugSynthMC (Drug Synthesis using Monte Carlo), in conjunction with DL and statistical-based priors to generate thousands of interpretable chemical structures and novel drug-like molecules per second. DrugSynthMC produces drug-like compounds using an atom-based search model that builds molecules as SMILES, character by character. Designed molecules follow Lipinski's "rule of 5″, show a high proportion of highly water-soluble nontoxic predicted-to-be synthesizable compounds, and efficiently expand the chemical space within the libraries, without reliance on training data sets, synthesizability metrics, or enforcing during SMILES generation. Our approach can function with or without an underlying neural network and is thus easily explainable and versatile. This ease in drug-like molecule generation allows for future integration of score functions aimed at different target- or job-oriented goals. Thus, DrugSynthMC is expected to enable the functional assessment of large compound libraries covering an extensive novel chemical space, overcoming the limitations of existing drug collections. The software is available at https://github.com/RoucairolMilo/DrugSynthMC.

Domain generalization through meta-learning: a survey

Deep neural networks (DNNs) have revolutionized artificial intelligence but often lack performance when faced with out-of-distribution data, a common scenario due to the inevitable domain shifts in real-world applications. This limitation stems from the common assumption that training and testing data share the same distribution-an assumption frequently violated in practice. Despite their effectiveness with large amounts of data and computational power, DNNs struggle with distributional shifts and limited labeled data, leading to overfitting and poor generalization across various tasks and domains. Meta-learning presents a promising approach by employing algorithms that acquire transferable knowledge across various tasks for fast adaptation, eliminating the need to learn each task from scratch. This survey paper delves into the realm of meta-learning with a focus on its contribution to domain generalization. We first clarify the concept of meta-learning for domain generalization and introduce a novel taxonomy based on the feature extraction strategy and the classifier learning methodology, offering a granular view of methodologies. Additionally, we present a decision graph to assist readers in navigating the taxonomy based on data availability and domain shifts, enabling them to select and develop a proper model tailored to their specific problem requirements. Through an exhaustive review of existing methods and underlying theories, we map out the fundamentals of the field. Our survey provides practical insights and an informed discussion on promising research directions.

Improving Cardiopulmonary Resuscitation skills for layperson in cases of heart attack: a scoping review

The proficiency of trained individuals in effectively administering Cardiopulmonary Resuscitation (CPR) is paramount in mitigating the impact of out-of-hospital cardiac arrest incidents. Inadequate CPR skills among laypersons can result in missed opportunities to save lives. Therefore, it is imperative to prioritize unified efforts to enhance CPR competencies within the general populace. This scoping review aims to consolidate literature discussing the enhancement of laypeople's CPR skills using various methodologies.This scoping review employed the PRISMA methodology and encompassed an extensive search across four critical databases (Science Direct, Proquest, Pubmed, and Google Scholar) for literature published between 2013 and 2023. The search utilized the keywords "CPR Teaching," "Skill," and "Layperson." Out of 487 collected articles, 20 were deemed relevant. The findings of all relevant articles consistently indicated an improvement in laypeople's CPR skills following training.Incorporating concise CPR instructional videos and smartphone applications has shown potential for enhancing CPR knowledge and improving emergency responsiveness. Nonetheless, integrating these modern technological approaches with traditional simulation methods has demonstrated greater efficacy in CPR training, resulting in enhanced compression quality and depth.In conclusion, Integrating traditional and technology-based learning methodologies improves the capability of individuals without specialized medical training to administer CPR effectively.

Physics-informed neural network for volumetric sound field reconstruction of speech signals

Recent developments in acoustic signal processing have seen the integration of deep learning methodologies, alongside the continued prominence of classical wave expansion-based approaches, particularly in sound field reconstruction. Physics-informed neural networks (PINNs) have emerged as a novel framework, bridging the gap between data-driven and model-based techniques for addressing physical phenomena governed by partial differential equations. This paper introduces a PINN-based approach for the recovery of arbitrary volumetric acoustic fields. The network incorporates the wave equation to impose a regularization on signal reconstruction in the time domain. This methodology enables the network to learn the physical law of sound propagation and allows for the complete characterization of the sound field based on a limited set of observations. The proposed method’s efficacy is validated through experiments involving speech signals in a real-world environment, considering varying numbers of available measurements. Moreover, a comparative analysis is undertaken against state-of-the-art frequency domain and time domain reconstruction methods from existing literature, highlighting the increased accuracy across the various measurement configurations.

Affinity-Driven Transfer Learning for Load Forecasting.

In this study, we introduce an innovative method for load forecasting that capitalizes on the concept of task affinity score to measure the similarity between various tasks. The task affinity score emerges as a superior technique for assessing task similarity within the realm of transfer learning. Through empirical evaluation on a synthetic dataset, we establish the superiority of the task affinity score over traditional metrics in task selection scenarios. To operationalize this method, we unveil the Affinity-Driven Transfer Learning (ADTL) algorithm to enhance load forecasting precision. The ADTL algorithm enriches the transfer learning framework by incorporating insights from both pre-trained models and datasets, thereby augmenting the accuracy of load forecasting for new and unseen datasets. The robustness of the ADTL algorithm is further evidenced through its application to two empirical datasets, namely the dataset provided by the Australian Energy Market Operator (AEMO) and the Smart Australian dataset. In conclusion, our research underscores the important role of the task affinity score in refining transfer learning methodologies for load forecasting applications.

Swarm Robotics Navigation Task: A Comparative Study of Reinforcement Learning and Particle Swarm Optimization Methodologies

Automatic design methods focus on generating the collective behavior of swarm robotic systems. These methods enable multiple robots to coordinate and execute complex tasks in their environments autonomously. This research paper investigated two prominent methodologies: particle swarm optimization (PSO) and reinforcement learning (RL). A new comparative study was conducted to analyze the performance of a group of mobile robots through extensive experimentation. The objective was to produce navigational collective behavior through unknown environments. These environments differ in complexity ranging from obstacle-free environments to cluttered ones. The core metrics of the comparison include the time efficiency of individual robots and the overall swarm, flexibility in pathfinding, and the ability to generalize solutions for new environments. The obtained results from the Webots simulator with Python controller suggested that RL excels in environments closely aligned with its training conditions. RL achieved a faster completion time and demonstrated superior coordination among individual robots. However, its performance dips when facing untrained scenarios necessitating computationally expensive retraining or structural complexities to enhance adaptability. Conversely, PSO showed commendable consistency in performance. Despite its slower pace, it exhibited robustness in various challenging settings without reconfiguration.

Application of machine learning techniques in the diagnosis of endometriosis

ObjectiveThe aim of this study is to assess the use of machine learning methodologies in the diagnosis of endometriosis (EM).MethodsThis study included a total of 106 patients with EM and 203 patients with non-EM conditions (like simple cysts and simple uterine fibroids), all admitted to the Shunyi Women’s and Children’s Hospital of Beijing Children’s Hospital between January 2017 and September 2022. All participants were free of comorbidities and their diagnoses were confirmed via postoperative pathology. Comparative analysis was conducted between the EM and non-EM groups. Baseline data were assessed, including white blood cell count, neutrophil-to-lymphocyte ratio (NLR), platelet-to-lymphocyte ratio, lymphocyte-to-monocyte ratio, mean platelet volume, hemoglobin, carbohydrate antigen 125 (CA125), carbohydrate antigen 199, coagulation parameters, and other serologic indicators. An optimal predictive model was developed using an artificial intelligence algorithm to determine the presence of EM. The objective is to provide new insights for the clinical diagnosis and treatment of EM.ResultsThe random forest algorithm demonstrated superior performance when compared to decision trees, LogitBoost, artificial neural networks, naïve Bayes, support vector machines, and linear regression in machine learning methods. Combining CA125 with the NLR yielded a better prediction of EM than using CA125 alone when applying the random forest algorithm. The accuracy of predicting EM with CA125 combined with NLR was 78.16%, with a sensitivity of 86.21% and an area under the curve (AUC) of 0.85 (P < 0.05). In contrast, using CA125 alone resulted in an EM prediction accuracy of 75.8%, with a sensitivity of 79.3% and an AUC of 0.82 (P < 0.05).ConclusionThe diagnostic value of serum CA125 combined with the NLR for EM is higher than that of serum CA125 alone. This finding indicates that NLR could serve as a new supplementary biomarker along with serum CA125 in the diagnosis of EM.