Knowledge Learning Research Articles

Applications of cluster-based transfer learning in image and localization tasks

Transfer learning can address the issue of insufficient labels in machine learning. Using knowledge in a labeled domain (source domain) can assist in acquiring and learning knowledge in a domain (target domain) that lacks some or all labels. In this paper, we propose a new cluster-based semi-supervised transfer learning (CBSSTL) under a new assumption that samples in the target domain are unlabeled but contain cluster information. Furthermore, we propose a new transfer learning framework and a method for fine-tuning parameters. We tested and compared the proposed method with other unsupervised and semi-supervised transfer learning methods on well-known image datasets. The experimental results demonstrate the effectiveness of the proposed method. Additionally, we created a localization dataset for transfer learning. Finally, we tested and analyzed the proposed method on this dataset. Its particularly challenging nature makes it difficult for our method to work effectively.

Mitigating gradient conflicts via expert squads in multi-task learning

The foundation of multi-task learning lies in the collaboration and interaction among tasks. However, in numerous real-world scenarios, certain tasks usually necessitate distinct, specialized knowledge. The mixing of these different task-specific knowledge often results in gradient conflicts during the optimization process, posing a significant challenge in the design of effective multi-task learning systems. This study proposes a straightforward yet effective multi-task learning framework that employs groups of expert networks to decouple the learning of task-specific knowledge and mitigate such gradient conflicts. Specifically, this approach partitions the feature channels into task-specific and shared components. The task-specific subsets are processed by dedicated experts to distill specialized knowledge. The shared features are captured by a point-wise aggregation layer from the whole outputs of all experts, demonstrating superior performance in capturing inter-task interactions. By considering both task-specific knowledge and shared features, the proposed approach exhibits superior performance in multi-task learning. Extensive experiments conducted on the PASCAL-Context and NYUD-v2 datasets have demonstrated the superiority of the proposed approach compared to other state-of-the-art methods. Furthermore, a benchmark dataset for multi-task learning in underwater scenarios has been developed, encompassing object detection and underwater image enhancement tasks. Comprehensive experiments on this dataset consistently validate the effectiveness of the proposed multi-task learning strategy. The source code is available at https://github.com/chenjie04/Multi-Task-Learning-PyTorch.

Using the ibsr technique as a psychological intervention to alleviate student stress in biology learning: Impacts on motivation, knowledge construction, and cognitive anxiety

Learning difficulties are a common issue faced by students, with stress being a significant contributing factor. One psychological treatment that has been shown to effectively reduce stress is Inquiry-Based Stress Reduction (IBSR). The objective of this study is to integrate IBSR into a discovery learning strategy in Biology in the classroom, with the aim of increasing students' learning motivation and knowledge construction while reducing their learning difficulties and cognitive anxiety. This is quasi-experimental research that used a post-test non-equivalent control group design. The study involved 72 11th-grade science students from two different classes at one of the public high schools in Bandung City. One class, consisting of 36 students, received IBSR treatment, while the other class, also consisting of 36 students, did not. Both classes used a discovery learning framework for teaching. Data on motivation, learning difficulties, and cognitive anxiety were collected using a rating scale questionnaire with eight scales. Students' ability to construct knowledge was measured using the German Cognitive Load (GCL) instrument in the form of a written test with indicators taken from Mayer's cognitive taxonomy (2002) in the realm of understanding. The study found that incorporating IBSR techniques into learning strategies for the immune system material can reduce student stress and improve learning performance, motivation, and knowledge construction (GCL), while also decreasing learning difficulties and cognitive anxiety.

Crafting innovative paths in non-linear professional learning for bilingual education: the role of connectivism in the age of AI

ABSTRACT This study introduces a novel Connectivist model for professional development (PD) aimed at enhancing AI literacy among bilingual/ESL teachers in K-12 education. As AI technologies rapidly reshape educational landscapes, effective PD programs are essential to equip educators with the skills to integrate AI responsibly and equitably. Grounded in Connectivism, which emphasizes non-linear learning and dynamic knowledge networks, this research explores how PD can transform educators’ perceptions of AI from apprehension to empowerment. The study involved a two-phase PD program with 30 elementary teachers and administrators, incorporating in-person AI training sessions, asynchronous tutorials, and collaborative activities. Data were collected through a phenomenological approach to capture educators’ lived experiences, with triangulation methods using surveys, interviews, observations, and Q&A sessions. The analysis revealed significant improvements in participants’ attitudes toward AI and their openness to integrating it into their teaching practices. The Connectivist model developed in this study fosters ongoing collaborative learning networks and equips educators to leverage AI in addressing resource gaps in bilingual education. This model offers a transformative, sustainable, and adaptive framework for integrating AI into K-12 education, providing a forward-looking approach to professional development in the digital age.

DKVMN&MRI: A new deep knowledge tracing model based on DKVMN incorporating multi-relational information.

Knowledge tracing is a technology that models students' changing knowledge state over learning time based on their historical answer records, thus predicting their learning ability. It is the core module that supports the intelligent education system. To address the problems of sparse input data, lack of interpretability and weak capacity to capture the relationship between exercises in the existing models, this paper build a deep knowledge tracing model DKVMN&MRI based on the Dynamic Key-Value Memory Network (DKVMN) that incorporates multiple relationship information including exercise-knowledge point relations, exercise-exercise relations, and learning-forgetting relations. In the model, firstly, the Q-matrix is utilized to map the link between knowledge points and exercises to the input layer; secondly, improved DKVMN and LSTM are used to model the learning process of learners, then the Ebbinghaus forgetting curve function is introduced to simulate the process of memory forgetting in learners, and finally, the prediction strategies of Item Response Theory (IRT) and attention mechanism are used to combine the similarity relationship between learners' knowledge state and exercises to calculate the probability that learners would correctly respond during the subsequent time step. Through extensive experiments on three real-world datasets, we demonstrate that DKVMN&MRI has significant improvements in both AUC and ACC metrics contrast with the latest models. Furthermore, the study provides explanations at both the exercise level and learner knowledge state level, demonstrating the interpretability and efficacy of the proposed model.

"Understanding dementia together": The design, delivery and evaluation of a collaborative, inter-professional dementia workshop for healthcare students.

A collaborative, multi-disciplinary team input is crucial for the optimal management of the older adult with complex care needs such as dementia. Interprofessional learning (IPL) at undergraduate level can lead to improved collaborative knowledge and skills. The aim of this study was to develop, deliver and evaluate an IPL dementia workshop for healthcare students across 11 disciplines. A secondary aim was to determine whether there is a clinical application of learned knowledge in students who completed the workshop and subsequently underwent clinical placement. The design of the IPL workshop aligned with Kern's map for the development of a curriculum in medical education. The Alzheimer's Disease Knowledge Scale (ADKS) was used to assess students' knowledge of dementia pre-and-post workshop, as well as opened-ended questions on role recognition and communication. A total of 102 students completed the workshop questionnaire, with a follow up of 47 students on clinical placement. There was a statistically significant increase in students' knowledge and confidence levels in communication with a person with dementia. Students reported positively on the workshop format, the collaborative nature of the workshop, as well as the role of the patient advocate. The follow up of students on clinical placement showed a perceived behavioural change in communication modification. Our study demonstrates the benefits of an IPL initiative across multiple disciplines, with perceived behavioural change on clinical placement.

Application and Innovation of Artificial Intelligence in Forensic Medicine

As the fourth industrial revolution, artificial intelligence is reshaping many industries. It has become a new cornerstone of digital conversion, and it is no exception in the field of forensic medicine.This paper mainly discusses how artificial intelligence can solve the problems related to forensic medicine.How to use artificial intelligence technology to develop into an auxiliary tool in the field of forensic medicine.This paper summarizes the exploratory data analysis, statistical modeling and machine learning in artificial intelligence, extracts insights and knowledge from the data, and applies them to various fields of forensic medicine.Artificial intelligence will improve the accuracy and efficiency of forensic work: it can automate some tasks and improve the quality of evidence. The comprehensive analysis results show that the artificial intelligence proposed in this paper will be an important auxiliary in the three directions of forensic medicine.

SCALE FOR PRE-SERVICE SCIENCE TEACHERS’ KNOWLEDGE IN DESIGNING INCLUSIVE LEARNING: CONSTRUCTION, VALIDATION, AND RELIABILITY

Scale development is essential in testing constructs and variables in social research, including education. Scales that meet the rules of validity and reliability are developed using standardized procedures. This research focuses on scale production to create reliable and valid construct measures to assess teacher knowledge in designing inclusive learning, using three frameworks, namely Technological Pedagogical and Content Knowledge, Backward Design, and Universal Design for Learning. Research on this issue involves measuring organizational and psychological constructs, which present unique challenges because they are generally unobservable, very abstract, often complex, and may consist of several different components. As a result of this complexity, developing this scale was challenging. The production of this scale followed Boateng et al., and the field test involved 259 pre-service teachers. The Rasch Rating Scale Model analysis was used to test the scale and produced 18 items that have high reliability (0.96). This scale can be used nationally to assess teachers' ability to implement inclusive education. The scale also applies as a teacher self-assessment tool for developing their competence.

An ACNAP survey assessing the cardiology multidisciplinary learning needs to support lipid management

Abstract Background/ Introduction: Reducing LDL cholesterol is a high priority in cardiovascular care but requires knowledge and skills to deliver effectively. Nurses and allied professionals (NAPs) can play a major role in supporting lipid optimisation. Most NAPs will work together with patients prescribed lipid lowering therapies, and some may be more closely involved in initiation and monitoring. The Association of Cardiovascular Nursing and Allied Professionals (ACNAP) wanted to gauge the level of understanding, confidence and learning needs of cardiology professionals to better implement European Society of Cardiology (ESC) lipid lowering guidelines. Purpose The aim of the project was to highlight gaps in knowledge to better inform needs for training and educational programmes developed by ACNAP. Methods A 29 question electronic survey was developed by expert consensus, exploring previous experience, clinical knowledge, and perceptions of learning needs. It was launched at the EuroHeartCare conference in June 2023, on social media, and members of the ESC were emailed inviting participation. Results 123 people responded. 29.5% of the respondents were physicians and 70.5% NAPs. Most respondents were involved in lipid optimisation of some description with only 7.0% of respondents having no direct involvement in their patient cohort. A higher percentage of respondents responded "totally agree" when asked it they knew what cholesterol targets to aim for in secondary prevention, compared to primary prevention (61% v 41.5%). 94% of respondents felt comfortable when to initiate statins and and 82% ezetimibe. This reduced to 45% for inclisiran and 40% for bempedoic acid. Similarly, the majority felt comfortable counselling a patient newly initiated on statins or ezetimibe, but significantly fewer the newer lipid lowering therapies. Experience and understanding of familial hypercholesterolaemia (FH) was also explored. Only half the respondents would be comfortable in identifying and diagnosing FH and a further 25% unsure. A large percentage (37%) were unaware of the Simon Broome criteria or the Dutch Lipid Criteria Network (49%). When considering learning needs, 71% of NAP respondents needed extra support to help make lipid lowering decisions. This rises to 84% and 74% when looking at nurses and pharmacists separately, respectively. Nearly 76% would prefer any learning to be delivered online, with interactive online training packages being the most popular method. Conclusions The three main gaps identified by NAPs were: management in primary prevention (initiation and targets), the newer innovative medicines (bempedoic acid, inclisiran and PCSK9 monoclonal antibodies) and FH. Interestingly, these are the same gaps highlighted by physician responders. These findings can help guide ACNAP and ESC in the development of educational programmes with the aim to improve better lipid management overall.

How to run a qualitative methods short course in epidemiology: faculty and student perspectives

Abstract Background Qualitative research and mixed methods are core competencies for epidemiologists. In response to the shortage of guidance on graduate course development, we wrote a course development to guide faculty and students designing similar courses in epidemiology curricula. We combine established educational theory with faculty and student experiences from a recent introductory course for epidemiology and biostatistics doctoral students at the University of Zurich and Swiss Federal Institute of Technology, Zurich. Objectives We propose a 1-ECTS, six session long, student-centred course with inverse in-person classroom teaching and practice exercises with faculty input. The overarching course objective is to introduce students to qualitative research and mixed methods. The proposed course covers learning outcomes in comprehension, knowledge, application, analysis, synthesis and evaluation. Results Following an introductory session, the students engage in face-to-face interviews, focus group interviews, observational methods, analysis and how qualitative and quantitative methods are integrated in mixed methods. Furthermore, the course covers interviewer safety, research ethics, quality in qualitative research and a practice session focused on the use of interview hardware, including video and audio recorders. The student-led teaching characteristic of the course allows for an immersive and reflective teaching-learning environment. Conclusions After implementation of the course and learning from faculty and student perspectives, we propose these additional foci: a student project to apply learned knowledge to a case study; integration in mixed-methods; and providing faculty a larger space to cover theory and field anecdotes. Based on: Gille, et al. A guide for a student-led doctoral-level qualitative methods short course in epidemiology: faculty and student perspectives, International Journal of Epidemiology, Volume 53, Issue 2, April 2024. Key messages • Qualitative research methods and mixed methods are core competencies for epidemiologists. • Students appreciate a student-centred course design with inverse classroom teaching and practice exercises.

Associations Between Nursing Students' Knowledge, Skills, and Attitudes and Participation in Experiential Learning on Care for People With Disabilities.

Experiential learning activities on care for people with disabilities (PWD) would help nursing students develop the knowledge, skills, and attitudes (KSAs) needed to provide quality care for PWD. The purpose of this study was to evaluate the perceived changes in nursing students' KSAs related to the care for PWD following participation in health assessment and prevention (HAP) experiential learning activities. This was a quasi-experimental, pre- and posttest educational intervention study. Nursing students (n=160) attended multiple experiential learning activities as a required part of their HAP coursework and completed a pre and posttest survey to assess changes in their KSAs. Participation in experiential learning activities on care for PWD was associated with significant increases in perceived knowledge, skills and positive attitudes toward PWD. Experiential learning activities aligned with core competencies for health care providers caring for PWDs have the potential to change nursing care and address health inequities for this population.

Research on the Practice of Ideological and Political Education in Mathematics Courses in Vocational Universities Based on Classroom-Training-Competition Mode

The purpose of this study is to explore how to effectively integrate ideological and political education into the mathematics curriculum by proposing a "combination of classroom teaching, practical training projects, and competition activities". By organically combining classroom teaching, practical training projects, and competition activities, it promotes students' learning of mathematical knowledge while enhancing their sense of social responsibility and professional ethics. Research results show that this model has significantly improved students' mathematics performance, especially in terms of basic knowledge and modelling ability. At the same time, by participating in mathematical modelling competitions and practical training, students have demonstrated strong teamwork spirit and innovation ability, and their professional ethics have been significantly improved. Through questionnaires and interviews, the feedback results show that students attach great importance to the practical value of the curriculum and ideological and political education. Finally, the research suggests that the integration of ideological and political elements into more mathematics courses should be explored in the future, in order to improve the quality of education and cultivate high-quality talents with a sense of social responsibility and professional ethics.

A breath of fresh air: a pilot flipped classroom approach to airway management skills training

ObjectivesWhile flipped classroom instruction has repeatedly shown efficacy in undergraduate medical education, evidence for its utility in procedural domains remains sparse. This holds particular significance for surgical subspecialties such as otolaryngology, which have limited time in undergraduate medical curricula. We designed a novel airway management skills simulation course with a flipped classroom approach and evaluated its efficacy in a pilot study.MethodsA simulation course was designed to provide instruction in seven airway management skills: bag valve mask ventilation, laryngoscopy, intubation, cricothyroidotomy, tracheotomy, and tracheostomy care. Publicly available YouTube videos were selected as pre-learning materials. Participating students completed surveys before the pre-learning assignment and after completion of the simulation center workshop.ResultsSixteen students participated in the workshop, and data was collected from 14 participants. Learners reported significant improvements in knowledge regarding all covered skills except tracheotomy; mean self-rated knowledge improved from 2.9 to 5.8 (p < 0.001) on a scale from 0 to 10. Significant increases in self-reported confidence in performing all seven skills were also observed, with an overall increase from 1.1 to 5.7 (p < 0.001). Students also rated all elements of the workshop highly, including a prevailing belief that the pre-learning materials markedly enhanced their learning.ConclusionOur novel framework for skills-based education using a flipped classroom approach demonstrated remarkable efficacy in improving learner knowledge and self-reported confidence regarding airway management skills. This educational design, including the use of high-quality, publicly available pre-learning videos, has significant implications for undergraduate medical education in surgical subspecialties.

Overcoming Catastrophic Forgetting in Continual Fine-Grained Urban Flow Inference

Citywide fine-grained urban flow inference (FUFI) problem aims to infer the high-resolution flow maps from the coarse-grained ones, which plays an important role in sustainable and economic urban computing and intelligent traffic management. Previous models tackle this problem from spatial constraint, external factors, and memory cost. However, utilizing the new urban flow maps to calibrate the learned model is very challenging due to the “catastrophic forgetting” problem and is still under-explored. In this article, we make the first step in FUFI and present CUFAR—Continual Urban Flow inference with augmented Adaptive knowledge Replay—a novel framework for inferring the fine-grained citywide traffic flows. Specifically, (1) we design a spatial-temporal inference network that can extract better flow map features from both local and global levels; (2) then, we present an augmented adaptive knowledge replay (AKR) training algorithm to selectively replay the learned knowledge to facilitate the learning process of the model on new knowledge without forgetting. We apply several data augmentation techniques to improve the generalization capability of the learning model, gaining additional performance improvements. We also propose a knowledge discriminator to avoid the “negative replaying” issue introduced by noisy urban flow maps. Extensive experiments on two large-scale real-world FUFI datasets demonstrate that our proposed model consistently outperforms strong baselines and effectively mitigates the forgetting problem.

Improving Patient Understanding and Outcomes in Lung Cancer Using an Animated Patient's Guide with Visual Formats of Learning.

Lung cancer patient education resources that address barriers to health literacy, improve understanding, and demonstrate improved patient outcomes are limited. Our study aim was to evaluate and report on learner knowledge improvement and intent to implement behavior change, and validate the benefits of the You and Lung Cancer website and YouTube resources. Our study occurred from November 2017 to December 2023. We evaluated audience reach (visit sessions, unique visitors, country origins, page views) and calculated top views by media type (animations, expert videos, patient videos). We assessed the impact and commitment to change through learner surveys (areas of interest, intention to modify behaviors, and intention to discuss disease management with providers) and tested the knowledge of learners pre- and post-reviewing of website content. Our program reached 794,203 views globally; 467,546 were unique visitors; and 243,124 (51%) were unique visitors from the USA. Of US visitors, 46% identified as lung cancer patients. These were patients in treatment (38%), survivors (8%), family members or caregivers (21%), and healthcare providers (14%) with other audiences unspecified (19%). Three areas of highest learner importance were the animations "Understanding Non-Small Cell Lung Cancer" (180,591), "Staging of Lung Cancer" (144,238), and "Treatment and Management of Small Cell Lung Cancer" (49,244). Our study confirmed areas of importance to lung cancer patients and suggests that visual formats of learning, such as animations, can mitigate health literacy barriers and help improve patient understanding and outcomes. Exporting this format of learning to other cancers has the potential to benefit patients and improve health outcomes.

Redefining the impact of professional development in education with ProDES (Professional Development Evaluation Scale)

This study introduces the Professional Development Evaluation Scale (ProDES), a tool that has been developed to evaluate the impact of professional development as it relates to participants' Learning and Use of New Knowledge and Skills, Organisational Support, Student Learning Outcomes, and reactions. Grounded in Guskey’s (2000) framework for evaluating Professional Development, ProDES was developed with data from five study groups in Turkey and underwent refinement across four factors. Exploratory and Confirmatory Factor Analyses confirmed the scale's structure, accounting for 62.72% of the total variance, with robust fit indices. Within this, ProDES demonstrated high internal consistency and test-retest reliability, with significant correlations validating its effectiveness. The scale's high internal consistency and test-retest reliability ensure that it can be used to make evidence-informed decisions that can foster more effective and supportive professional development activities. As a result, by identifying which professional development initiatives lead to improvements, those associated with professional development can use resources more efficiently, leading to enhanced school and system-wide improvements. Moreover, the use of ProDES can also help schools and education systems track progress over time, making ProDES an invaluable tool for continuous improvement and strategic planning.

Analysis of Tactical Knowledge for Learning an Alternative Invasion Sport

The study of declarative and procedural knowledge in sport allows us to assess students’ tactical learning processes. The aim of this study was to analyze and compare the level of declarative and procedural knowledge acquired by students according to the pedagogical model and gender, after the application of two intervention programs for an alternative invasion sport, “Rosquilla”. This study involved 136 students distributed into six groups of Primary Education (fifth and sixth year) and Secondary Education (first year). Each group in the same year participated in a different intervention program, one based on the Game-Centered Model and the other on a hybrid model of the Game-Centered Model and the Sports Education Model. A descriptive analysis was carried out to determine the characteristics of the participants. Subsequently, an independent samples Mann–Whitney U-test was applied to compare the level of knowledge between the models and genders in the pre- and post-test periods. A Linear Mixed Model was used to analyze the level of knowledge of students within each group and compare them according to methodology and gender. The results indicate that both programs generated improvements in declarative and procedural knowledge. Therefore, students learn equally regardless of the methodological perspective and gender.

DIGITAL TEACHING MATERIAL OF SUSTAINABLE LIFESTYLE THEME WITH ETHNO-PJBL TO PROMOTE STUDENTS’ KNOWLEDGE AND CREATIVE THINKING ABILITIES

Purpose: This study aims to analyze the effects of digital teaching materials on the theme of sustainable lifestyle integrated with Ethno-PjBL on knowledge and creative thinking skills in learning in the Merdeka Curriculum. Theoretical Framework: The idea behind the development of digital learning materials on the theme of sustainable lifestyle is to promote awareness and practice of sustainability among students through the integration of technology in learning. By combining a project-based learning model enriched by local cultural values (Ethno-PjBL), students are not only invited to understand the concept of sustainable lifestyle, but also how to apply it in their cultural context. Method: This study used a quasi-experimental method with a posttest only control group design. The sample of this study was grade X students at SMAN Kota Jambi, with the experimental class using integrated digital teaching materials ethno-PjBL and the control class using conventional learning methods. Data were analyzed using descriptive statistical tests, Kolmogorov-Smirnov normality tests, and Mann-Whitney tests. Results and Discussion: Digital teaching materials on sustainable lifestyle themes integrated with ethno-PjBL have a positive impact on students' knowledge and creative thinking skills. The experimental class using the digital teaching materials showed better results compared to the control class using conventional learning methods. Research Implications: The results of this study support the integration of sustainable lifestyle-themed digital teaching materials with the Ethno-PjBL approach, which not only strengthens students' academic knowledge, but also fosters creative thinking skills and awareness of local cultural values. The findings of this study can encourage educators and policy makers to further adopt and develop contextual and relevant digital teaching materials, especially those that focus on global issues such as sustainability, but are still integrated with local wisdom. The implications of this study also open up opportunities for further research to explore the potential of digital teaching materials in other subjects or at different levels of education.

Truth, Knowledge, and Information Literacy: An &lt;i&gt;Aporetic&lt;/i&gt; Approach

This paper aims to conduct a critical examination of the foundational assumptions and challenges of information literacy (IL), serving as a timely ‘reality check’ and a constructive instance of ‘problem-posing’. To this end, it advocates for an ‘aporetic’ approach, which constitutes a pivotal tool in philosophical inquiry. This approach posits that aporia—puzzlement rooted in the conflict of reasons—compels us to confront and grapple with (seemingly) insurmountable problems. It thereby creates opportunities to rethink fundamental concepts, theories, and perspectives. Through a critical literature review, this paper scrutinizes IL aporias across six scopes: conceptualization, theorization, philosophical underpinning, challenge, critique, and prospect. As a part of a broader project, the study focuses primarily on two key topics: truth and knowledge. The literature review identifies two aporias in IL: the disjunction between knowing and learning of knowledge, and the tension between information as objective truth and subjective interpretation of information, i.e., informativeness.

Exploring the role of rejection in scholarly knowledge production: Insights from granular interaction thinking and information theory

Exploring the role of rejection in scholarly knowledge production: Insights from granular interaction thinking and information theory