Learning Methods Research Articles

Forecasting Chinese Stock Market Volatility With Volatilities in Bond Markets

ABSTRACTIn this paper, we investigate whether the bond markets contain important information that can improve the accuracy of stock market volatility forecasts in China. We use realized volatility (RV) implemented by different maturity treasury bond futures contracts to predict the Chinese stock market volatility. Our work is based on the heterogeneous autoregressive (HAR) framework. Empirical results show that the volatility of treasury bond contracts with longer maturities (especially 10 years) has the best effect on predicting the Chinese stock market volatility, both in sample and out of sample. Two machine learning methods, the scaled principal component analysis (SPCA) and the least absolute shrinkage and selection operator (lasso), are also more effective than the HAR benchmark model's prediction. Finally, mean–variance investors can achieve substantial economic gains by allocating their investment portfolios based on volatility forecasts after introducing treasury bond futures volatility.

New Normal Learning Method Satisfaction Among University Students in the Post-Pandemic Period

E-learning has become the new normal learning method in the post-pandemic period around the globe, including Myanmar. The present study aimed to examine the satisfaction of Myanmar university students with the new normal learning method. The study utilized an inductive quantitative approach, and structural equation modeling (SEM) was employed to analyze the data. Data was collected from 262 Myanmar students who were studying locally and abroad. The results of the study indicated that e-learning trust was more critical than e-learning effectiveness (p < .001), while e-learning system quality was insignificant for e-learning satisfaction. In addition, e-learning trust and effectiveness were mediating variables between e-learning system quality and e-learning satisfaction. This study delivers valuable insights for educators and university facilitators to enhance students' satisfaction with new normal learning methods.

LINGUISTIC AND DIDACTIC BASIS FOR THE DEVELOPMENT OF FUTURE DOCTORSʼ SPEAKING COMPETENCY

The article defines the content of the concept of “future doctorʼs speech competence” as an integral quality of a medical student, which is manifested in the general ability and readiness to use language means, the laws of their functioning for the construction and understanding of speech utterances in the context of professional activity of doctors; the linguodidactic principles of development of future doctorsʼ speech competence are substantiated. These include the laws of mother tongue acquisition that contribute to the intensive development of communicative and linguistic skills; general didactic and specific principles that determine the direction in the development of means of developing linguistic skills; forms, methods and techniques that correspond to the main forms of work in higher education; teaching aids, the use of which affects the effectiveness of the content of education. It is noted that the development of future doctorsʼ speech competence can be carried out using the following methods of language teaching: oral presentation by the teacher (narration, explanation, lecture), conversation, work with a textbook, observation and analysis of language phenomena, exercise method, programmed learning and interactive methods. The following interactive learning methods have become valuable for the development of medical students’ language competence: work in small groups, imitation, simulation, discussion, microphone, talk shows, rotating groups. All these methods combine into one whole the activities of the teacher and students, which are aimed at improving language knowledge, developing communicative and speech skills, allow to manage studentsʼ cognitive activity productively and realize educational, educational, developmental, motivational, control and correctional functions of learning in a higher education institution

Molecular mechanism underlying effect of D93 and D289 protonation states on inhibitor-BACE1 binding: exploration from multiple independent Gaussian accelerated molecular dynamics and deep learning

ABSTRACT BACE1 has been regarded as an essential drug design target for treating Alzheimer’s disease (AD). Multiple independent Gaussian accelerated molecular dynamics simulations (GaMD), deep learning (DL), and molecular mechanics general Born surface area (MM-GBSA) method are integrated to elucidate the molecular mechanism underlying the effect of D93 and D289 protonation on binding of inhibitors OV6 and 4B2 to BACE1. The GaMD trajectory-based DL successfully identifies significant function domains. Dynamic analysis shows that the protonation of D93 and D289 strongly affects the structural flexibility and dynamic behaviour of BACE1. Free energy landscapes indicate that inhibitor-bound BACE1s have more conformational states in the protonated states than the wild-type (WT) BACE1, and show more binding poses of inhibitors. Binding affinities calculated using the MM-GBSA method indicate that the protonation of D93 and D289 highly disturbs the binding ability of inhibitors to BACE1. In addition, the protonation of two residues significantly affects the hydrogen bonding interactions (HBIs) of OV6 and 4B2 with BACE1, altering their binding activity to BACE1. The binding hot spots of BACE1 recognized by residue-based free energy estimations provide rational targeting sites for drug design towards BACE1. This study is anticipated to provide theoretical aids for drug development towards treatment of AD.

Exploring Teaching Reform in Fashion Design Major based on Virtual Reality Technology

With the development of technology and social progress, digital teaching has become the mainstream trend, and digital teaching technology is constantly integrated into the teaching of fashion design majors. Fashion design will further evolve and improve virtual simulation technology, continuously enhancing the intelligence and interactivity of teaching, and providing students with comprehensive and practical fashion design learning experiences. This article provides an overview of virtual reality technology, its application in fashion design teaching, application types, problems and solutions in the application of virtual reality technology in fashion design, and research on the reform of virtual reality technology in fashion design teaching. It proposes that virtual reality technology effectively improves the classroom teaching efficiency of fashion design, stimulates students' design and innovation inspiration, promotes the practicality of fashion design, and provides students with a good learning environment and methods. Applying VR technology to the field of modern education continuously promotes the development of teaching and education work, providing new teaching models and innovative teaching methods for national education work.

On most informative regions for binary classification of schizophrenia based on resting state fMRI data done by selection of functionally homogeneous regions method

In this work we solve the problem of automatic binary classification of subjects with a diagnosis of schizophrenia and control groups on a data set obtained on a Siemens 3T tomograph. The data set included 36 subjects undergoing treatment at Psychiatric Hospital no. 1 Named after N.A. Alexeev of the Department of Health of Moscow (GBUZ PKB No. 1 DZM) and 36 subjects from the control group. Machine learning methods were used to solve this problem. As a result, an accuracy of 76% was achieved, which corresponds to the results obtained in other scientific studies. The highest accuracy was obtained for the local homogeneity parameter (regional homogeneity – ReHo), already known in the literature. At the same time, the set of features developed by the authors based on the method for identifying functionally homogeneous regions (FHR) gave a classification accuracy of 74%. But at the same time, the set of FHR features provides higher classification accuracy when using a small number of brain regions. For example, already in 8 regions, the FHR set provided an almost maximum classification accuracy of 72.5% (versus 65% for the ReHo set), which suggests that it is the selected 8 regions that give the highest level of separation.

Expression of Salivary miRNAs, Clinical, and Demographic Features in the Early Detection of Gastric Cancer: A Statistical and Machine Learning Analysis.

Gastric cancer ranks as one of the top five deadliest cancers worldwide and is often diagnosed at late stages. Analysis of saliva may provide a non-invasive approach for detection of malignancies in organs associated with the oral cavity. This research aims to analyze salivary microRNA expression together with clinical and demographic features with the aim of diagnosing gastric cancer. The study included 19 patients with early-stage gastric cancer and 19 healthy controls. Saliva samples were collected and processed for RNA isolation. Salivary expression of miR-223-3p and miR-21-5p were measured using quantitative reverse-transcription polymerase chain reaction (RT-qPCR). Receiver operating characteristic (ROC) curves were generated to evaluate the accuracy of diagnostic models. Machine learning algorithms, multiple logistic regression, and principal component analysis (PCA) were used to assess the predictive power of miRNAs in conjunction with clinical-demographic features. Significant upregulation of miR-223-3p and downregulation of miR-21-5p in saliva were observed in patients with gastric cancer. The area under ROC curve (AUC) values for salivary miR-21-5p, salivary miR-223-3p, and their multiple logistic regression were determined to be 0.723, 0.791, and 0.850, respectively. The AUC for multiple logistic regression model was 0.919. The PCA model led to the highest diagnostic odds ratio (DOR) of 134.33 (sensitivity = 0.785, specificity = 1.00, AUC = 903). Application of machine learning methods, and in particular a random forest algorithm, showed high accuracy in diagnosing patients with gastric cancer (sensitivity = 1.00, specificity = 0.857, AUC = 0.93). The application of validated salivary diagnostics in clinical practice could help facilitate earlier diagnosis of gastric cancer and improve medical outcome. Expression of miR-21 and miR-223-3p in saliva together with clinical and demographic features, appears promising in screening for GC.

Research on Reactivity-Equivalent Physical Transformation Method for Double Heterogeneity in Pressurized Water Reactors Based on Machine Learning

Traditional computational methods for pressurized water reactors are unable to handle dispersed fuel particles as the double heterogeneity and the direct volumetric homogenization can result in significant errors. In contrast, reactivity-equivalent physical transformation techniques offer high precision for addressing the double heterogeneity introduced by dispersed fuel particles. This approach converts the double heterogeneity problem into a single heterogeneity problem, which is then subsequently investigated by using the conventional pressurized water reactor computational procedure. However, it is currently empirical and takes a lot of time to obtain the right k∞. In this paper, we train the RPT model by using the existing dataset of plate-dispersed fuel and rod-dispersed fuel by a machine learning method based on a linear regression model, and we then use the new data to make predictions and derive the corresponding similarity ratios. The burnup verification, density verification, fission rate verification, and neutron energy spectrum analysis are calculated through the OpenMC program. For plate-type fuel elements, the method maintains an accuracy within 200 pcm during depletion, with deviations in the 235U density and 235U fission rate within 0.1% and neutron energy spectrum errors within 6%. For rod-type fuel elements, the method maintains an accuracy within 100 pcm during depletion, with deviations in 235U and 239Pu density within 1.5% and neutron energy spectrum errors within 1%. The numerical validation indicates that the reactivity-equivalent physical transformation method based on the linear regression model not only greatly improves the computational efficiency, but also ensures a very high accuracy to deal with double heterogeneity in nuclear reactors.

Defect classification of composite materials using transfer learning methods

ABSTRACT Nowadays, composite materials have become prevalent across various sectors, particularly finding usage in large-scale applications such as spaceships, automobiles, and aircrafts. The accurate detection of the defects in these materials is crucial, yet traditional methods often rely on human inspection, which is susceptible to errors. Recent advancements in machine learning have enabled defect detection using ultrasonic non-destructive testing methods. This paper introduces a new dataset named UNDT, which is obtained from the scans of 60 different composite materials, generating a total of 1150 images depicting both defective and non-defective areas. Several transfer learning methods are applied on the newly introduced UNDT dataset as well as the publicly available USimgAIST ultrasonic dataset. Comparative performance assessments illustrate the significance of utilising the transfer learning approach for defect classification on ultrasonic inspection images. Furthermore, the research emphasises the substantial benefits of employing these transfer learning methods. Notably, the DenseNet121 and VGG19 models achieve the highest accuracy rates, with 98.8% and 98.6% on the UNDT and USimgAIST datasets, respectively.

LGS-PPIS: A Local-Global Structural Information Aggregation Framework for Predicting Protein-Protein Interaction Sites.

Exploring protein-protein interaction sites (PPIS) is of significance to elucidating the intrinsic mechanisms of diverse biological processes. On this basis, recent studies have applied deep learning-based technologies to overcome the high cost of wet experiments for PPIS determination. However, the existing methods still suffer from two limitations that remain to be solved. Firstly, the process of feature aggregation in most methods only took into account node features, but ignored the complex edge features of the target residue to its neighbor residues, resulting in insufficient local feature extraction. Secondly, such feature aggregation was limited to aggregating spatially adjacent residues, and could not capture the "remote" residues that played a critical role in determining PPIS, which can be summed up as the lack of global feature at the residue level. To break the above limitations, a local-global structural information aggregation framework, LGS-PPIS, was proposed in this study, including two modules of edge-aware graph convolutional network (EA-GCN) and self-attention integrated with initial residual and identity mapping (SA-RIM), which achieved the aggregation of local and global information for PPIS prediction. Evaluation results of LGS-PPIS showed that the proposed method outperformed state-of-the-art deep learning methods on three widely used PPIS prediction benchmarks. Besides, the results of ablation experiments demonstrated that the local features from spatially adjacent residues and global features from "remote" residues separately captured by EA-GCN and SA-RIM could benefit the model performance. Among them, the former was shown to have a more significant role in the PPIS prediction.

SSML: Semi-supervised metric learning with hard samples for hyperspectral image classification

Deep learning is widely used in hyperspectral image (HSI) classification due to its powerful learning capabilities. However, its excellent performance typically requires a large number of samples, which can be time-consuming and labor-intensive to produce. The limitation of available samples greatly constrains the model's generalization performance. To alleviate the sample pressure, we propose a semi-supervised metric learning method for HSI classification that focuses on hard samples and can obtain reliable pseudo-labels through multiscale prediction. Additionally, we employ a hard sample learning strategy for network training, which concentrates on enhancing network discrimination by adaptively optimizing intra-class and inter-class distances. Performance tests on three public datasets indicate that the proposed method surpasses other state-of-the-art methods across multiple validation metrics.

Genetic variations as predictors of dispositional and dyadic empathy—a couple study

Biological drivers of empathy have been explored in an interdisciplinary manner for decades. Research that merges the psychological and genetic perspectives of empathy has recently gained interest, and more complex designs and analyses are needed. Empathy is a multidimensional construct that might be regarded both dispositionally (as a personality trait) and contextually (experienced and/or expressed in a particular relationship/situation). This study analyzed genetic variations associated with genes encoding oxytocin, arginine vasopressin, and receptors that regulate their secretion as predictors of the empathic dimensions of emotional (empathic concern and personal distress) and cognitive (perspective taking) dyadic factors of partners in heterosexual intimate relationships. Machine learning methods to capture both linear and nonlinear relationships between SNPs, RS1 and RS2 repeat polymorphisms and dimensions of empathy in couples were employed. A total of 442 individuals (221 couples) participated in this study. Empathy was measured by the Polish version of the Interpersonal Reactivity Index and the Interpersonal Reactivity Index for Couples. The MassARRAY® 4 instrument, which combines mass spectrometry with endpoint PCR, was used for genotyping all 14 genetic variations. Microsatellite fragment analysis was performed by denaturing polyacrylamide gel electrophoresis. The results confirmed the significance of certain genetic alterations linked to oxytocin, vasopressin, serotonin and estrogen for dispositional and dyadic empathy (mainly rs1884051, rs6311, RS1, rs4686302, and rs1042778) in couples. The effects were stronger for the prediction of emotional and dyadic empathy than for perspective taking. Separate analyses for women and men indicated different predictive effects of genes for empathy (for example, effects of rs53576 were indicated only in women), which are also experienced and expressed in couples. Different dimensions of empathy should be included when the genetic predictors of empathy are examined.

Prediction of Hydrogen Production from Solid Oxide Electrolytic Cells Based on ANN and SVM Machine Learning Methods

In recent years, the application of machine learning methods has become increasingly common in atmospheric science, particularly in modeling and predicting processes that impact air quality. This study focuses on predicting hydrogen production from solid oxide electrolytic cells (SOECs), a technology with significant potential for reducing greenhouse gas emissions and improving air quality. We developed two models using artificial neural networks (ANNs) and support vector machine (SVM) to predict hydrogen production. The input variables are current, voltage, communication delay time, and real-time measured hydrogen production, while the output variable is hydrogen production at the next sampling time. Both models address the critical issue of production hysteresis. Using 50 h of SOEC system data, we evaluated the effectiveness of the ANN and SVM methods, incorporating hydrogen production time as an input variable. The results show that the ANN model is superior to the SVM model in terms of hydrogen production prediction performance. Specifically, the ANN model shows strong predictive performance at a communication delay time ε = 0.01–0.02 h, with RMSE = 2.59 × 10−2, MAPE = 33.34 × 10−2%, MAE = 1.70 × 10−2 Nm3/h, and R2 = 99.76 × 10−2. At delay time ε = 0.03 h, the ANN model yields RMSE = 2.74 × 10−2 Nm3/h, MAPE = 34.43 × 10−2%, MAE = 1.73 × 10−2 Nm3/h, and R2 = 99.73 × 10−2. Using the SVM model, the prediction error values at delay time ε = 0.01–0.02 h are RMSE = 2.70 × 10−2 Nm3/h, MAPE = 44.01 × 10−2%, MAE = 2.24 × 10−2 Nm3/h, and R2 = 99.74 × 10−2, while at delay time ε = 0.03 h they become RMSE = 2.67 × 10−2 Nm3/h, MAPE = 43.44 × 10−2%, MAE = 2.11 × 10−2 Nm3/h, and R2 = 99.75 × 10−2. With this precision, the ANN model for SOEC hydrogen production prediction has positive implications for air pollution control strategies and the development of cleaner energy technologies, contributing to overall improvements in air quality and the reduction of atmospheric pollutants.

Pseudo Replay-based Class Continual Learning for Online New Category Anomaly Detection in Advanced Manufacturing

The incorporation of advanced sensors and machine learning techniques has enabled modern manufacturing enterprises to perform data-driven classification-based anomaly detection based on the sensor data collected in manufacturing processes. However, one critical challenge is that newly presented defect category may manifest as the manufacturing process continues, resulting in monitoring performance deterioration of previously trained machine learning models. Hence, there is an increasing need for empowering machine learning models to learn continually. Among all continual learning methods, memory-based continual learning has the best performance but faces the constraints of data storage capacity. To address this issue, this paper develops a novel pseudo replay-based continual learning framework by integrating class incremental learning and oversampling-based data generation. Without storing all the data, the developed framework could generate high-quality data representing previous classes to train machine learning model incrementally when new category anomaly occurs. In addition, it could even enhance the monitoring performance since it also effectively improves the data quality. The effectiveness of the proposed framework is validated in three cases studies, which leverages supervised classification problem for anomaly detection. The experimental results show that the developed method is very promising in detecting novel anomaly while maintaining a good performance on the previous task and brings up more flexibility in model architecture.

A new cause-mechanism independence estimation based cross-domain learning method for machining deformation prediction

Monitoring data-based machining deformation prediction is fundamental for accurate deformation control and product quality guarantee. For problems where involved unobservable variables like residual stress that can lead to data distribution bias, causal cross-domain learning methods have prominent advantages over other pure data-driven methods by shifting cause distributions and mechanisms. However, existing causal methods are based on the hypothesis that cause and mechanism are independent, which ignores the corresponding changes of mechanism across domains and can limit accuracies. This paper proposes a new causal cross-domain learning method based on cause-mechanism independence estimation, where the hypothesis is broken by taking the dependence of cause and mechanism into consideration. A cause-mechanism independence estimator is established by introducing the structural integral of mechanism derivative multiplies cause distribution, and the estimation value can measure the cross-domain changes of mechanism. As a result, the proposed method based predicting model can make efficient distribution shifts according to the estimation. The machining of aero-engine casings is taken as a case study, and experimental results show that the proposed method could predict the deformation well with limited target domain data. Besides, the proposed method can be readily extended to other cross-domain regression problems involved with unobservable variables.

Decision-Making Policy for Autonomous Vehicles on Highways Using Deep Reinforcement Learning (DRL) Method

Automated driving (AD) is a new technology that aims to mitigate traffic accidents and enhance driving efficiency. This study presents a deep reinforcement learning (DRL) method for autonomous vehicles that can safely and efficiently handle highway overtaking scenarios. The first step is to create a highway traffic environment where the agent can be guided safely through surrounding vehicles. A hierarchical control framework is then provided to manage high-level driving decisions and low-level control commands, such as speed and acceleration. Next, a special DRL-based method called deep deterministic policy gradient (DDPG) is used to derive decision strategies for use on the highway. The performance of the DDPG algorithm is compared with that of the DQN and PPO algorithms, and the results are evaluated. The simulation results show that the DDPG algorithm can effectively and safely handle highway traffic tasks.

Face Modeling Based on Deep Learning and Traditional Methods: A Survey

Abstract. 3D face modeling, as an important research field in computer graphics and vision, has undergone remarkable development in recent years. The technology is widely used in various scenarios, like film and television production, virtual reality, augmented reality, facial recognition, security monitoring, and medical diagnosis. This paper aims to systematically explore the main technologies of 3D face modeling, especially the application and development of deep learning methods in it, review traditional face modeling methods, introduce in detail the latest technical advances based on deep learning, and analyze the advantages and disadvantages of these methods in practical applications.

Shaping the Quranic Generation from an Early Age (Study of Imtaq Programme Management in PAUD Akbar, Kaur Regency, Bengkulu)

This study discusses the management of the imtaq program at PAUD Akbar. The problems discussed in this study are planning, implementation, and assessment of the imtaq program at PAUD Akbar. This study uses descriptive qualitative research. Data collection techniques include interviews, observation, and documentation studies. Data analysis techniques using data reduction, data presentation, and conclusion drawing. The results of the research are: First, Akbar PAUD has formulated imtaq program planning. The imtaq program is a flagship program because it is in accordance with the need to obtain religious education in line with the vision and mission of PAUD Akbar. Program planning consists of daily, weekly, and annual programs. Secondly, the implementers of the imtaq program include the principal, teachers, parents, and the community who work together in implementing the program. Teachers apply four learning methods, namely, the play method, the storytelling method, the singing method, and the demonstration method. Third, teacher assessment is carried out in the form of assessments on aspects of child development and cognitive, affective, and psychomotor aspects. The assessment is carried out by teachers by conducting observations, children’s self-assessment, and portfolio assessment. The results of the follow-up of the program are still continued, but there are some improvements in improving facilities and infrastructure, teacher competence, and variations in learning models.

Data-Based Prediction of Redox Potentials via Introducing Chemical Features into the Transformer Architecture.

Rapid and accurate prediction of basic physicochemical parameters of molecules will greatly accelerate the target-orientated design of novel reactions and materials but has been long challenging. Herein, a chemical language model-based deep learning method, TransChem, has been developed for the prediction of redox potentials of organic molecules. Embedding an effective molecular characterization (combining spatial and electronic features), a nonlinear molecular messaging approach (Mol-Attention), and a perturbation learning method, TransChem, shows high accuracy in predicting the redox potential of organic radicals comprising over 100,000 data (R2 > 0.97, MAE <0.09 V) and is generalized to the smaller 2,1,3-benzothiadiazole data set (<3000 data points) and electron affinity data set (660 data) with low MAE of 0.07 V and 0.18 eV, respectively. In this context, a self-developed data set, i.e., the oxidation potential (OP) of a full-space disubstituted phenol data set (OPP-data set, total set: 74,529), has been predicted by TransChem with a high-throughput, and active learning strategy. The rapid and reliable prediction of OP could hopefully accelerate the screening of plausible reagents in highly selective cross-coupling of phenol derivatives. This study presents an important attempt to guide language modeling with chemical knowledge, while TransChem demonstrates state-of-the-art (SOTA) predictive performance on redox potential prediction benchmark data sets for its better understanding of molecular design and conformational relationships.

Neck pain and distance learning: A pain in the neck for university students during COVID-19

Objective The shift to online learning during COVID-19 led to increased musculoskeletal discomforts and impacted students’ quality of life. Neck pain (NP), once a minor issue, has become more prevalent due to prolonged electronic device use in new learning methods. This study aims to measure the prevalence of NP among University of Sharjah (UOS) students during the COVID-19 online learning period and to investigate the factors that provoked it. Methods This study focused on young adult students aged 17-26 and did not consider gender or athletic status due to the university’s demographics and pandemic restrictions. Demographic data, Neck Disability Index (NDI) assessments, and pain management information were gathered and analyzed using SPSS 24 through univariate and bivariate methods. Results The prevalence of NP during COVID-19, among 325 UOS students was found to be 62.7%, 64.41% of which had NP at the time of doing the survey. NDI scores were found to be skewed. The median was 16% which indicates mild NP while the interquartile range was 19.11. Most participants reported experiencing posterior neck pain (38.77%), primarily attributed to prolonged sitting (81.23%). Factors such as lifting, personal care, and emotional well-being were found to have a significant impact on NDI. Participants who did not seek medical attention exhibited significantly higher levels of neck pain disability, as measured by the NDI. The median NDI score for this group was 20, with an interquartile range of 16.89 while, those who sought medical attention had a higher median NDI score of 34 with interquartile range of 22. Conclusion This study highlights the prevalence of neck pain among UOS students, emphasizing the need for postural improvements and further research on prevention strategies in the UAE.