Search Results (5,327)

Online learning is a framework for processing and learning from sequential data in real time, offering benefits such as promptness and low memory usage. However, it faces critical challenges, including concept drift, where data distributions evolve over time, and class imbalance, which significantly hinders the accurate classification of minority classes. Addressing these issues simultaneously remains a challenging research problem. This study introduces a novel algorithm that integrates adaptive weighted kernel density estimation (awKDE) and a conscious biasing mechanism to efficiently manage memory, while enhancing the classification performance. The proposed method dynamically detects the minority class and employs a biasing strategy to prioritize its representation during training. By generating synthetic minority samples using awKDE, the algorithm adaptively balances class distributions, ensuring robustness in evolving environments. Experimental evaluations across synthetic and real-world datasets demonstrated that the proposed method achieved up to a 13.3 times improvement in classification performance over established oversampling methods and up to a 1.66 times better performance over adaptive rebalancing approaches, while requiring significantly less memory. These results underscore the method’s scalability and practicality for real-time online learning applications. Full article

Stance detection seeks to identify the public’s position on a specific topic, providing critical insights for applications such as recommendation systems and rumor detection, which are essential for maintaining a secure social media environment. As one of China’s most influential social media platforms, Weibo significantly shapes public discourse within its complex social network structure. Despite recent advancements in stance detection research on Weibo, many studies fail to adequately address the nuanced emotional features present in text, limiting detection accuracy and effectiveness, and potentially compromising online security. This paper proposes a stance detection approach based on multi-task learning that considers the influence of emotional features to tackle these challenges. Our method utilizes a RoBERTa pre-trained model in the shared layer to extract textual features for both stance detection and sentiment analysis. In the stance detection module, a BiLSTM model captures deeper temporal information, followed by three independent modules dedicated to extracting semantic features for specific stances. Concurrently, the sentiment analysis module employs a BiLSTM model to predict emotional polarity. The experimental results on the NLPCC2016-task4 dataset demonstrate that our approach outperforms existing methods, highlighting the effectiveness of integrating sentiment analysis with stance detection to enhance both accuracy and reliability, ultimately contributing to the security of social networks. Full article

The gradual growth of oxides inside thermal barrier coatings is a key factor leading to the degradation of thermal barrier coating performance until its failure, and accurate monitoring of the growth stress during this process is crucial to ensure the long-term stable operation of engines. In this study, terahertz time-domain spectroscopy was introduced as a new method to characterize the growth stress in thermal barrier coatings. By combining metallographic analysis and scanning electron microscope (SEM) observation techniques, the real microstructure of the oxide layer was obtained, and an accurate simulation model of the oxide growth was constructed on this basis. The elastic solutions of the thermally grown oxide layer of thermal insulation coatings were obtained by using the controlling equations in the rate-independent theoretical model, and the influence of the thickness of the thermally grown oxide (TGO) layer on the stress distribution was explored. Based on experimental data, multidimensional 3D numerical models of thermal barrier coatings with different TGO thicknesses were constructed, and the terahertz time-domain responses of oxide coatings with different thicknesses were simulated using the time-domain finite difference method to simulate the actual inspection scenarios. During the simulation process, white noise with signal-to-noise ratios of 10 dB to 20 dB was embedded to approximate the actual detection environment. After adding the noise, wavelet transform (WT) was used to reduce the noise in the data. The results showed that the wavelet transform had excellent noise reduction performance. For the problems due to the large data volume and small sample data after noise reduction, local linear embedding (LLE) and kernel-based extreme learning machine (KELM) were used, respectively, and the kernel function was optimized using the gray wolf optimization (GWO) algorithm to improve the model’s immunity to interference. Experimental validation showed that the proposed LLE-GWO-KELM hybrid model performed well in predicting the TGO growth stress of thermal insulation coatings. In this study, a novel, efficient, nondestructive, online, and high-precision measurement method for the growth in TGO stress of thermal barrier coatings was developed, which provides reliable technical support for evaluating the service life of thermal barrier coatings. Full article

In this study, an active fault-tolerant control problem was addressed for a rigid spacecraft in the presence of unknown actuator faults, uncertainties, and disturbances. First, an adaptive sliding mode iterative learning-based observer (ASILO) is proposed for diagnosing and reconstructing unknown faults. It achieves greater accuracy and rapidity while consuming less computing resources by constructing adaptive gain based on an auxiliary error. Specifically, it significantly improved the computational efficiency by 76% compared with the Strong Tracking Kalman Filter while achieving a similar accuracy. It also enhanced the accuracies relative to the traditional ILO and adaptive ILO by 67% and 36%, respectively, and demonstrated 82% and 52% increases in rapidity. Then, fault-tolerant control with resilient prescribed performance (RPP) that can adapt to changing initial conditions and adaptively adjust performance constraints online by sensing faults and error trends is proposed. It avoided the control singularity by constructing adaptive resilient boundaries with almost no impact on the computational overhead. It significantly improved the performance and conservatism. Finally, the robustness and effectiveness of the proposed strategy were demonstrated by numerical simulations. Full article

This study aims to identify the best deep learning and machine learning models to identify the unethical behavior patterns of learners using distance education exam data of an educational institution. One hundred twenty-nine online exam data were analyzed by the researcher with three different scenarios to reveal the best model performance in regression and classification. For regression and classification, deep neural network (DNN) from deep learning algorithms and support vector machine (SVM), decision trees (DTs), k-nearest neighbor (KNN), random forest (RF), logistic regression (LR), and extreme gradient boosting (XGBoost) algorithms from machine learning algorithms were used. In the regression analysis conducted within the scope of Scenario-1, the model we proposed to detect “cheating” behavior, which is one of the unethical learner behaviors, was found to be a 5-layer DNN model with a test performance success of 80.9%. In the binary classification analysis for Scenario-2, students who “copied” from unethical behaviors were obtained with an accuracy rate of 96.9% by the model established by the 10-layer DNN algorithm we proposed. In the triple classification analysis for Scenario-3 defined in the study, the XGBoost model was found to have the highest accuracy rate of 97.7% for students who “cheated” due to unethical behaviors and the highest performance in all other metric values. In addition, SHAP and LIME methods, which are explanatory methods for the XGBoost model, which is one of the best-performing models, were applied, and the attributes and percentages affecting the model were shared. As a result of this study, it has been shown that the application of the most appropriate layer functions and parameter selection that will increase performance can be effective in estimating complex problems and target values that cannot be solved using classical mathematical models. The proposed models can provide educational institutions with a roadmap and insight in evaluating online examination practices and ensuring academic integrity. Future researchers may need more data sets and different analyses for better performance of the established models. Full article

In the past decade, the diversification of steganographic techniques has posed significant threats to information security, necessitating effective countermeasures. Current defenses, mainly reliant on steganalysis, struggle with detection accuracy. While “image vaccines” have been proposed, they often target specific methodologies. This paper introduces a universal steganographic vaccine to enhance steganalysis accuracy. Our symmetric approach integrates with existing methods to protect images before online dissemination using the Contrast Limited Adaptive Histogram Equalization (CLAHE) algorithm. Experimental results show significant accuracy improvements across traditional and deep learning-based steganalysis, especially at medium-to-high payloads. Specifically, for payloads of 0.1–0.5 bpp, the original detection error rate was reduced from 0.3429 to 0.2346, achieving an overall average reduction of 31.57% for traditional algorithms, while the detection success rate of deep learning-based algorithms can reach 100%. Overall, integrating CLAHE as a universal vaccine significantly advances steganalysis. Full article

The Internet of Things (IoT) and Industrial Internet of Things (IIoT) have drastically transformed industries by enhancing efficiency and flexibility but have also introduced substantial cybersecurity risks. The rise of zero-day attacks, which exploit unknown vulnerabilities, poses significant threats to these interconnected systems. Traditional signature-based intrusion detection systems (IDSs) are insufficient for detecting such attacks due to their reliance on pre-defined attack signatures. This study investigates the effectiveness of Adaptive SAMKNN, an adaptive k-nearest neighbor with self-adjusting memory (SAM), in detecting and responding to various attack types in Internet of Things (IoT) environments. Through extensive testing, our proposed method demonstrates superior memory efficiency, with a memory footprint as low as 0.05 MB, while maintaining high accuracy and F1 scores across all datasets. The proposed method also recorded a detection rate of 1.00 across all simulated zero-day attacks. In scalability tests, the proposed technique sustains its performance even as data volume scales up to 500,000 samples, maintaining low CPU and memory consumption. However, while it excels under gradual, recurring, and incremental drift, its sensitivity to sudden drift highlights an area for further improvement. This study confirms the feasibility of Adaptive SAMKNN as a real-time, scalable, and memory-efficient solution for IoT and IIoT security, providing reliable anomaly detection without overwhelming computational resources. Our proposed method has the potential to significantly increase the security of IoT and IIoT environments by enabling the real-time, scalable, and efficient detection of sophisticated cyber threats, thereby safeguarding critical interconnected systems against emerging vulnerabilities. Full article

This study investigates the impact and mechanisms of achievement goal orientation on online learning engagement among undergraduates, using a sample of 461 students enrolled in online courses from four universities of varying levels in Shanghai, China. Self-efficacy is introduced as a mediating variable, and structural equation modeling is employed to assess the effects. The findings reveal that different types of achievement goals have varying natures and intensities in their associations with undergraduate online learning engagement. Self-efficacy partially mediates the effect of mastery-approach goals on online learning engagement, but does not mediate the effects of mastery-avoidance, performance-approach, or performance-avoidance goals. The study recommends leveraging the guiding role of mastery-approach achievement goals to help students set scientific and reasonable goals, and stimulating students’ self-efficacy through the dual influences of external support and internal motivation. With the support of these strategies, significant improvements in undergraduate online learning engagement can be achieved. Full article

The real-time prediction of energy production is essential for effective energy management and planning. Forecasts are essential in various areas, including the efficient utilization of energy resources, the provision of energy flexibility services, decision-making amidst uncertainty, the balancing of supply and demand, and the optimization of online energy systems. This study examines the use of tree-based ensemble learning models for renewable energy production prediction, focusing on environmental factors such as temperature, pressure, and humidity. The study’s primary contribution lies in demonstrating the effectiveness of the bagged trees model in reducing overfitting and achieving higher accuracy compared to other models, while maintaining computational efficiency. The results indicate that less sophisticated models are inadequate for accurately representing complex datasets. The results evaluate the effectiveness of machine learning methods in delivering valuable insights for energy sectors managing environmental conditions and predicting renewable energy sources Full article

In this post-pandemic hybrid world of PK12 education, the onus is still on education leaders to close achievement gaps through equitable means. There are current socioeconomic, racial, gender, and geographical disparities that limit students’ full access to computer science education (CS). This case study reports how one urban PK12 school district in the United States is addressing the “leaky pipeline” with sustainable solutions for CS education with minoritized students. Using an online engagement framework, an ethnographic lens was used with document review, to conduct a content analysis of projects, programs, and services set up through the central office for nearly 20,000 students at the primary, middle grades, and secondary levels in computer sciences. Findings acknowledge leadership’s planning for student engagement in STEM+C (science, technology, engineering, math and computer science) for virtual instruction. This study will contribute to the burgeoning knowledge of leadership for CS activities in PK12, and serve as a beacon for learning organizations bolstering CS activities in the future. Full article

Introduction: Traditional medical education often emphasises theory, but clinical competence relies greatly on practical, hands-on skills. This quasi-experimental study examines how a combined approach—flipped classroom learning and simulation-based internships—affects medical students’ self-assessed clinical abilities. This model seeks to build students’ understanding, practical skills, and confidence in clinical settings through online preparation and realistic simulation exercises. Methods: This study examined changes in medical students’ self-perceived clinical skills after a flipped classroom and simulation-based internship. A total of 391 third- and fourth-year students completed a nine-hour program with morning practice sessions and afternoon high-fidelity scenarios. Surveys before and after the program assessed self-perceived thoracic and abdominal/general skills. Principal Component Analysis (PCA) confirmed the survey’s structure. ANCOVA controlled baseline scores and paired Wilcoxon tests examined subgroup improvements. Results: After the program, significant improvements were observed in self-perceived clinical skills across all domains. Thoracic skills increased from a median of 2.19 to 7.36, and abdominal skills from 5.11 to 9.46. Medical history, vital signs, and blood pressure scores also improved significantly. Third-year students and those attending the Clinical Methodology course showed the greatest gains. All post-intervention improvements were statistically significant (p < 0.001). Conclusions: The combination of flipped classroom learning and intensive simulation training markedly improved students’ perceived clinical competence. These findings suggest that such methods boost students’ practical skills and confidence. Further research is recommended to explore the long-term impact of this approach on skill retention and professional practice. Full article

Autonomous maneuvering decision-making in unmanned serial vehicles (UAVs) is crucial for executing complex missions involving both individual and swarm UAV operations. Leveraging the successful deployment of recommendation systems in commerce and online applications, this paper pioneers a framework tailored for UAV maneuvering decisions. This novel approach harnesses recommendation systems to enhance decision-making in UAV maneuvers. Our framework incorporates a comprehensive six-degree-of-freedom dynamics model that integrates gravitational effects and defines mission success criteria. We developed an integrated learning recommendation system capable of simulating varied mission scenarios, facilitating the acquisition of optimal strategies from a blend of expert human input and algorithmic outputs. The system supports extensive simulation capabilities, including various control modes (manual, autonomous, and hybrid) and both continuous and discrete maneuver actions. Through rigorous computer-based testing, we validated the effectiveness of established recommendation algorithms within our framework. Notably, the prioritized experience replay deep deterministic policy gradient (PER-DDPG) algorithm, employing dense rewards and continuous actions, demonstrated superior performance, achieving a 69% success rate in confrontational scenarios against a versatile expert algorithm after 1000 training iterations, marking an 80% reduction in training time compared to conventional reinforcement learning methods. This framework not only streamlines the comparison of different maneuvering algorithms but also promotes the integration of multi-source expert knowledge and sophisticated algorithms, paving the way for advanced UAV applications in complex operational environments. Full article

Background: As part of simulation-based learning, it is well known that debriefing plays a crucial role; ineffective debriefing can lead to a reiteration of errors in decision-making and a poor understanding of one’s limitations, compromising the learner’s psychological safety and making future simulated learning experiences less effective. In Italy, although simulation has been used in nursing education for more than 20 years, there is a general lack of data regarding the elements of debriefing. Methods: An exploratory, cross-sectional, multicenter nationwide study was conducted to identify current debriefing practices in Italian simulation-based nursing education. A non-probability sample of all directors of the Italian Bachelor school of Nursing and the directors of simulation centers on Italian national territory was surveyed with an online questionnaire. Results: Fifty-four nursing degree programs and 11 simulation centers participated in the survey. Significant differences were found between debriefing practices used by simulation centers and those used by the Bachelor School of Nursing. Specifically, differences concerned the training of debriefers, the knowledge of a debriefing framework, the use of different rooms for debriefing and the time spent on this activity. Conclusions: There is an emerging need for a harmonization process in Italian nursing education debriefing practices that would align the current reality with the best practices of the literature. Full article

In the present study, a short instrument (eight-item self-report, five-point Likert scales) was developed and validated to assess self-perceived mental health problems in online learning. The participants were 398 Romanian university students from nine different faculties. The factor structure of the scale was assessed using Exploratory Factor Analysis (Principal Axis Factoring extraction method) and Confirmatory Factor Analysis. The high goodness-of-fit indices validated a second-order factor model of mental health problems, with two distinct but correlated sub-constructs, psychological distress, and online academic difficulties, integrated under a single higher-level factor. Psychological distress comprises indicators such as anxiety and stress, while online academic difficulties contain, for instance, indicators such as decreased performance, fatigue or lack of motivation. The results of applying multiple assessment criteria showed good reliability (e.g., McDonald’s omega), as well as convergent validity (e.g., Average Variance Extracted) and discriminant validity (e.g., the heterotrait–monotrait ratio of correlations) of the scale. Also, correlations analysis between mental health problems occurred in online learning context and other measures indicated a strong negative relation with online course satisfaction and weak negative relations with subjective academic performance, perceived social competence, and perceived digital competence. In conclusion, the scale appears to be a valid instrument for measuring some negative mental health outcomes in online learning, perceived by university students. The implications of the results and limitations of this study are also discussed. In conclusion, the scale has multiple possible applications, the most important being (1) the assessment of mental health problems both in ordinary online learning situations and in emergency ones, which would allow the early detection of these issues, (2) the possibility of assessing relations between the sub-constructs of the scale and other psychological constructs of interest in scientific research, and (3) the feedback for teaching staff involved in the online learning system. Full article

The international tertiary education sector was significantly affected by the COVID-19 pandemic due to the risk of negative learning and psychosocial experiences. Most international students who remained in the host countries demonstrated admirable resilience and adaptability during those challenging times. An integrative review of factors shaping international students’ learning and mental wellbeing during the COVID-19 pandemic was conducted. Five electronic databases—CINAHL, MEDLINE, ProQuest, PsycINFO, and Web of Science—were searched from 2020 to 2023 using the key search terms ‘international students’, ‘tertiary education’, ‘mental health and wellbeing’, and ‘COVID’. A total of 38 studies were included in this review. They revealed six factors across learning and psychosocial experiences. Predisposing factors for maladjustments included the students being younger and possessing poor English proficiency. Precipitating factors were related to online teaching/learning, and lack of accessibility and or insufficient learning and living resources. Perpetuating factors pertained to living arrangements. The protective factor identified was institutional support. This review highlighted that multifaceted factors were associated with international students’ experiences and mental health and wellbeing. In-depth understanding of risk and protective factors can help policymakers to prepare for unprecedented challenges and reduce disruptions to international students’ education and mental health when studying abroad. Full article