Deep Learning Skills Research Articles

Problem-Based Learning - An Overview.

The main objective of Problem-Based Learning (PBL) is to develop problem-solving skills, collaborative learning skills, self-directed learning skills, communication skills, deeper learning skills, lifelong learning skills, and better retention in the students to equip them better in their professional careers. Unlike the traditional curriculum which is mainly based on didactic lectures, PBL is based on a group of students working on a problem and solving it. PBL is a promising teaching and learning tool that can be adopted in all fields, especially in Medical and Dental curricula.

Teachers' Strategies to Enhance Deeper Learning Skills in English Language Classes

The paper focuses on English teachers' teaching strategies in secondary-level classes to enhance students' deeper learning skills. This paper is the outcome of a qualitative study, a narrative inquiry with three secondary-level English teachers. With the help of in-depth interviews and class observation, the study figured out how the different teaching strategies allow teachers to adopt, integrate and ensure deeper learning skills in existing curricular content. The research primarily collected data through interviews and supplemented it with classroom observations. They subsequently analysed the data under three major themes. The first gives theoretical reasoning; in contrast, the second and third themes widely discuss the practical aspects and examples from actual classroom practices aligning with the researcher's observation track record that revolves around the theme. The study concludes that any strategies the teacher introduces must be reinforced by fostering an autonomous environment for learners, creating a school environment supportive of deeper learning, and ensuring the appropriate assessment of deep learning skills.

Unlocking Creative Writing Through In4D-Indigenous CIY Nature Journaling: The Indigenous Voice

This study examined the perceptions of the participants on the In4dIndigenous CIY nature journaling, their challenges in writing and how the journaling has influenced their creative writing in English Language learning. The methodology adopted for this study was an exploratory study. The instrument employed were document analysis of the In4d-Indigenous CIY Nature Journaling and focus group interview. The participants for this study were 29 Indigenous undergraduates (N=6 male,23= female) pursuing the Bachelor of Education in Iban Studies. The data from nature journaling amplified that the participants expressed their ideas in writing with elements of creative skills, critical thinking skills and emergence of character in articulating ideas for the journal. The data of focus group interview revealed that the In4D-Indigenous CIY nature journaling was a driver that connected technology-aided meaningful outdoor learning with nature, and how the environment was an inspirational teacher. On a positive note, the challenges were expressed as opportunity for improvement rather than threats. The In4d-Indigenous nature journaling indicated an encouraging and constructive influence pertaining to creative writing with six emerging themes: learner autonomy, shift attitude towards language learning, risk-taking, constructors of knowledge, technology exploration and creative-aesthetic value. This study has navigated direction for adopting an Inspired by Nature for the Indigenous CIY nature journaling, yet aspects of new pedagogies for deep learning and 21st Century Skills could be interwoven with nature for a more transformative eco-literacy research.

A systematic scoping review of the analysis of COVID-19 disease using chest X-ray images with deep learning models

<p>The significance of chest X-ray data in screening patients for COVID-19 has been recognised by medical experts. Deep learning (DL) technologies, particularly artificial intelligence (AI) algorithms, have emerged as efficient classifiers for diagnosing disease through the inspection of chest X-rays. Medical professionals may use deep learning skills to effectively allocate resources and prioritise patients, ensuring that people in critical need of medical attention receive it on time. In reviewed papers, chest X-ray images datasets are used in order to investigate if trained convolutional neural networks (CNNs) can be utilized to accurately classify COVID-19 cases. The study is made more fascinating by the availability of many kinds of new DL models designed specifically for this specific purpose. As the findings illustrate the efficacy of fine-tuned pretrained CNNs for COVID-19 identification using chest X-ray data, the usage of AI-based approaches for COVID-19 identification using chest X-ray data should see substantial growth, giving a more quick and cost-effective approach. The combination of CNN technology and the diagnostic capacity of chest X-ray imaging offers a lot of promise in the fight against COVID-19. Ultimately, the goal is to reduce the strain on healthcare resources and improve patient outcomes by providing medical practitioners with dependable technologies, such as those based on the artificial intelligence (AI), that can aid in real-time monitoring, rapid diagnosis, and patient triage. These advancements enable more effective use of healthcare resources, which benefits patients.</p>

Deep Learning Influences on Higher Education Students’ Digital Literacy: The Meditating Role of Higher-order Thinking

Digital literacy has emerged as a core competency in the 21st century society, and deep learning and higher-order thinking have been discussed as effective ways to improve digital literacy. Therefore, this study aimed to verify the influence of deep learning and higher-order thinking skills on higher education students’ digital literacy. Structural Equation Modeling was used to analyze the data gathered from 687 undergraduate and higher vocational students using a convenient sampling technique. The findings indicate that deep motivation and deep strategy were significantly positively correlated with students’ digital literacy. In such a structural relationship, digital literacy was additionally moderated by higher-order thinking. Nevertheless, students who have customarily used digital devices for more than five years could not be explained by this structural equation model. Lastly, this conclusion highlighted that educators should consider students’ digital experiences level, guide in selecting and applying deep learning, develop higher-order thinking, and improve their digital literacy.

Practical Research on Primary Mathematics Teaching Based on Deep Learning

With the rapid development of the knowledge economy, learning that stays at a shallow level is no longer able to meet the challenges of the times and deep learning has come into being. The key to deep learning is to develop students’ critical thinking, information integration, communication and collaboration, and constructive reflection skills, which can be cultivated in the process of problem solving. By exploring the theories of deep learning and problem solving, the basic elements of deep learning theory are incorporated into the design system of problem-solving teaching, and the problem-solving teaching model based on deep learning is proposed in conjunction with the content of elementary school mathematics, so that students can further develop their core literacy based on acquiring deep learning skills.

Teaching Design of Online Ideological and Political Course Based on Deep Learning Model Evaluation

In practical terms, teachers are supported to use more straightforward teaching methods, such as creating real-life contextual problems, to help students develop deep learning skills. In this paper, using Bayesian theory and Bayesian classifier research methods, a machine learning model was constructed using Python to establish the correspondence between online teaching of civics and high-level semantic features and to achieve computer learning through text and teaching design evaluation research that can identify high-frequency knowledge points. The inter-relationship model knowledge mapping, the accuracy is 90%, and the continuous knowledge update help to improve the model accuracy.

Encouraging students' engagement and promoting deep learning in immunology through an interactive clinical case problem-solving (CCPS) approach: Perception among cohort of medical students in Oman.

Modern competency-based medical education emphasizes student-centered teaching-learning strategies where students take responsibility of their own learning. Student-centered approaches facilitate multifaceted learning such as observation, critical evaluation, analysis, deeper understanding, and application of knowledge. The current study aims at assessing the students' perception on utilization of clinical case problem-solving approach (CCPS) to promote their lifelong learning. The present cross-sectional study was conducted at College of Medicine and Health Sciences (CoMHS) during the year 2021-2022. MD3 students of the academic year 2021-2022 were the study participants. The study was approved by institutional Ethic and Review Committee. Students' performances were assessed through pre-test and post-test performances. Students' feedback was collected through a predesigned questionnaire on a 3-point Likert scale. Cronbach's alpha coefficient test was used to assess the reliability of the questionnaire. The data was entered to Microsoft Excel and analyzed using SPSS software version 22. Paired t-test was used to compare pre-test and post-test scores and the data was expressed as numbers and percentages. In total, 103 participants were included in the study. Post-test scores were significantly higher compared to pre-test scores (p < 0.05). Questionnaire results showed that CCPS approach was accepted as an effective learning strategy. Majority (>90%) of the students expressed CCPS approach was interesting, motivated to learn, encouraged peer discussion, enhanced knowledge, and clarified their topic-related doubts. More than 80% students opined that CCPS enhanced their critical thinking, problem-solving ability, deep learning, and lifelong learning skills. Nearly 90% of the students suggested for including such sessions for more topics in immunology course in future. From our study results, it can be concluded that CCPS is an effective learning strategy to encourage students' engagement and promote their deep learning skills.

A comparative study on perceptions of medical students from the different curriculum on team-based learning

Objectives: Our medical school followed the traditional curriculum earlier, and due to a large amount of content embedded in each discipline, which had less scope for active and deep learning. To overcome this, we adopted an integrated curriculum and introduced a few active teaching/learning (T/L) methodologies, which promote deep learning and problem-solving skills. One such T/L methodology we introduced was team-based learning (TBL). Before implementing this active T/L methodology in the integrated curriculum, we evaluated the effectiveness of TBL in medical students from the traditional curriculum and aimed to determine students’ perceptions. Furthermore, we aimed to explore the perception of TBL in students who underwent integrated curriculum to evaluate the difference in their perception compared to the traditional curriculum. Materials and Methods: This cross-sectional study was conducted in RAK Medical and Health Sciences University on the 1st year medical students from the traditional and integrated curriculum. Institutional ethical committee clearance and informed consent were obtained before starting the study. A pre-validated 5-item survey questionnaire comprising questions related to the content, process, and teamwork was used to obtain perceptions of students’ on TBL. Results: The students positively perceived the teaching-learning experience using TBL and understood the concepts better. Even the students with integrated curriculum had the same positive impact on their learning attitudes. The majority of students in both cohorts agreed that discussion among their teams helped them to learn better. Around two-thirds (66%) of students from the traditional curriculum and one-third (39%) of students from integrated curriculum wanted TBLs as T/L methodology over didactic lectures. Conclusion: TBL helped to learn better and understand the subject and promoted self and peer engagement, which facilitated their learning by clarifying the doubts with peers. Due to this positive TBL experience, most students from both curriculums recommended its use as a T/L method over lecture. Hence, TBL sessions in medical schools can be used as an effective T/L method to facilitate meaningful learning.

Household Electricity Load Forecasting Based on Multitask Convolutional Neural Network with Profile Encoding

Household load forecasting provides great challenges as a result of high uncertainty in individual consumption of load profile. Traditional models based on machine learning tried to explore uncertainty depending on clustering, spectral analysis, and sparse coding with hand craft features. Recently, deep learning skills like recurrent neural network attempt to learn the uncertainty with one-hot encoding which is too simple and not efficient. In this paper, for the first time, we proposed a multitask deep convolutional neural network for household load forecasting. The baseline of one branch is built on multiscale dilated convolutions for load forecasting. The other branch based on deep convolutional autoencoder is responsible for household profile encoding. In addition, an efficient encoding strategy for household profile is designed that serves a novel feature fusion mechanism integrated into forecasting branch. Our proposed network serves an end-to-end manner in training and inference process. Sufficient ablation studies were conducted to demonstrate effectiveness of innovations and great generalization in point and probabilistic load forecasting at household level, which provides a promising prospect in demand response.

Interpretable detection of novel human viruses from genome sequencing data.

Viruses evolve extremely quickly, so reliable methods for viral host prediction are necessary to safeguard biosecurity and biosafety alike. Novel human-infecting viruses are difficult to detect with standard bioinformatics workflows. Here, we predict whether a virus can infect humans directly from next-generation sequencing reads. We show that deep neural architectures significantly outperform both shallow machine learning and standard, homology-based algorithms, cutting the error rates in half and generalizing to taxonomic units distant from those presented during training. Further, we develop a suite of interpretability tools and show that it can be applied also to other models beyond the host prediction task. We propose a new approach for convolutional filter visualization to disentangle the information content of each nucleotide from its contribution to the final classification decision. Nucleotide-resolution maps of the learned associations between pathogen genomes and the infectious phenotype can be used to detect regions of interest in novel agents, for example, the SARS-CoV-2 coronavirus, unknown before it caused a COVID-19 pandemic in 2020. All methods presented here are implemented as easy-to-install packages not only enabling analysis of NGS datasets without requiring any deep learning skills, but also allowing advanced users to easily train and explain new models for genomics.

Facilitating Deep Learning and Professional Skills Attainment in the Classroom: The Value of a Model United Nations Course

What is the role of Model United Nations (MUN) in facilitating deep learning and professional skills attainment in the classroom? Using a 15-week MUN course, I gather data on student progress in four levels of knowledge: factual, conceptual, procedural, and metacognitive. I use pre- and post-activity surveys as well as the instructor’s own assessments designed to capture respondents’ initial knowledge/skill levels and measure the improvement they achieve throughout the semester. Additionally, I conduct debriefing sessions with each respondent to gather additional data on their progress. The findings suggest that the in-class MUN experience as a whole has a substantial positive impact on students' factual, conceptual, and procedural knowledge as well as their self-perceived skills of negotiation, decision-making, public speaking, research, and teamwork. A comparison of respondents’ self-evaluations and the instructor’s assessment of student progress offers additional interesting findings: Despite the holistic nature of MUN as an experiential learning activity, course design is still key in targeting the skills to be improved. The course assessed here has strengthened negotiation and public speaking skills most substantially. The analyses also reveal that findings based exclusively on self-assessments must be approached with caution because they significantly overestimate students’ initial knowledge and skill levels.

Reading Skills in Self-Directed Learning

The article focuses on development of deep reading skills for high school students and university students. Deep reading is closely related to deep learning and lifelong learning skills that have to be acquired in the modern world. Developed deep reading skills create enjoyment and interest, which is a pathway to deep learning that will enable students become self-directed learners. Currently, we live in an information age when a massive amount of information comes through digital texts. At the same time, printed texts are still enjoyed by a large part of population. At this moment educators are facing a difficult task – not to give up the goal to help students develop deep reading skills when there is temptation to turn to light reading under the pressure of computer technologies that offer an easy and fast access to information. The article offers some reading strategies that can be applied to develop deep reading skills.

A deep learning based automatic surface segmentation algorithm for painting large-size aircraft with 6-DOF robot

PurposeThis paper aims to achieve automatically surface segmentation for painting different kinds of aircraft efficiently considering the demands of painting robot.Design/methodology/approachThis project creatively proposed one method that accepts point cloud, outputs several blocks, each of which can be handled by ABB IRB 5500 in one station. Parallel PointNet (PPN) is proposed in this paper for better handling six dimensional aircraft data including every point normal. Through semantic segmentation of PPN, each surface has its own identity information indicating which part this surface belongs to. Then clustering considering constraints is applied to complete surface segmentation with identity information. To guarantee segmentation paintable and improve painting efficiency, different dexterous workspaces of IRB 5500 corresponding to different postures have been analyzed carefully.FindingsThe experiments confirm the effectiveness of the proposed surface segmentation method for painting different types of aircraft by IRB 5500. For semantic segmentation on aircraft data with point normal, PPN has higher precision than PointNet. In addition, the whole algorithm can efficiently segment one complex aircraft into qualified blocks, each of which has its own identity information, can be painted by IRB 5500 in one station and has fewer edges with other blocks.Research limitations/implicationsAs the provided experiments indicate, the proposed method can segment one aircraft into qualified blocks automatically, which highly improves the efficiency in aircraft painting compared with traditional approaches. Moreover, the proposed method is able to provide identity information of each block, which is necessary for application of different paint parameters and different paint materials. In addition, final segmentation results by the proposed method behaves better than k-means cluster on variance of normal vector distance.Originality/valueInspired by semantic segmentation of 3 D point cloud, some improvements based on PointNet have been proposed for better handling segmentation of 6 D point cloud. By introducing normal vectors, semantic segmentation could be accomplished precisely for close points with opposite normal, such as wing upper and lower surfaces. Combining deep learning skills with traditional methods, the proposed method is proved to behave much better for surface segmentation task in aircraft painting.

Deep Learning for HRRP-based Satellite Recognition

An approach that employs deep learning technology is presented to recognize satellites based on radar high-resolution range profile (HRRP) data. We focus on extracting effective satellite recognition features in this paper. Thus, a deep learning model is constructed by gated recurrent unit (GRU) neural network and support vector machine (SVM) to extract more abstract and accurate features. Firstly, the radar HRRP data of four satellites is obtained by simulation. And data preprocessing has been done according to HRRP characteristic. Next, a GRU-SVM model is set up and some deep learning skills, such as dropout and cross validation, have been applied to improve recognition accuracy. The training results of GRU neural network show their effectiveness. In order to demonstrate the superiority of this approach, five other feature extraction methods have been used as a comparison based on clean satellite HRRP data and noisy data. The experiment results show that the presented GRU-SVM model could recognize satellites effectively and accurately, and has better recognition performance and noise robustness compared with five other methods.

Promoting Deeper Learning in High School: Evidence of Opportunities and Outcomes

Policymakers and practitioners are increasingly interested in students’ deeper learning skills, or the interpersonal and intrapersonal skills students need to succeed in school, careers, and civic life. This article presents evidence about whether the concept of deeper learning—applied across a variety of approaches—has potential merit as a means for education improvement. The analysis, based on 16 high schools implementing a school-wide approach to promoting deeper learning within the context of small schools, indicates that students who attended schools focused on deeper learning reported greater opportunities for deeper learning, greater competency in some deeper learning domains, had higher rates of graduating from high school, and were more likely to enroll in 4-year colleges than similar students who attended comparison schools.

فاعلیة التشارک الإلکترونی فی تنمیة مهارات حل المشکلة الإحصائیة وعمق التعلم لدى طلاب التعلیم الفنى التجارى The Effectiveness of E-Collaboration on Developing Statistical Problem Solving Skills and Deep Learning among Business Secondary School Learners

المستخلص: هدف البحث الحالى إلى تطوير تدريس مقرر الإحصاء بالتعليم الفنى التجارى من خلال إعداد تصور مقترح للتشارک الإلکترونى فى حل المشکلات الإحصائية، وقياس فاعليته فى تنمية مهارات حل المشکلة الإحصائية وعمق التعلم. ولتحقيق هذا الهدف فقد تم استخدام مزيج من إجراءات منهج البحث الوصفى، ومنهج البحث التطويرى، وشبه التجريبى. ولتحديد ولقياس المتغيرات التابعة، تم تحليل محتوى وحدات علم الإحصاء وطرق جمع البيانات والعرض الجدولي والبياني للبيانات الإحصائية ـــ مقاييس النزعة المرکزية ــــ ومقاييس التشتت) بمقرر الإحصاء للصف الثانى الثانوى التجارى نظام الثلاث سنوات، ثم صمم الباحثون التصور المقترح للمهام التعليمية المصاغة فى صورة مشکلات إحصائية، وتحديد بيئة التشارک الإلکترونى من خلال تطبيقات جوجل درايف، اختبار لقياس المعارف المرتبطة بالمهارات الإحصائية، اختبار لقياس مهارات حل مشکلة الإحصائية، ومقياس لعمق التعلم، وقد تم تطبيق هذه الأدوات على عينة من طلاب الصف الثانى الثانوى التجارى بالتعليم الفنى التجارى نظام الثلاث سنوات، بلغ حجمها (33) طالبة کمجموعة تجريبية و(33) کمجموعة ضابطة، وقد أظهرت نتائج التجريب وجود فرق ذو دلالة إحصائية بين طلاب المجموعة التجريبية والضابطة فى اختبار المعارف واختبار مهارات حل المشکلة الإحصائية، وعمق التعلم، وهذا الفرق لصالح المجموعة التجريبية؛ مما أکد فاعلية التشارک الإلکترونى فى تنمية مهارات حل المشکلة الإحصائية وعمق التعلم، وفى ضوء ما توصل إليه البحث من نتائج قدم البحث مجموعة من التوصيات والمقترحات التربوية لتعميم نتائجه. Abstract: This research amid at developing the teaching of business secondary school statistical curriculum through a suggested framework of e-collaboration in solving statistical problems and measure its effectiveness on acquiring statistical, developing statistical problem solving and deep learning skills. To achieve this objective, a mixed method approach of descriptive, developmental and quasi-experimental methodologies was applied. To measure the impact of the independent variable on the dependent variables in this research, the content of statistical course in the second year of business secondary school was analyzed, specifically, data presentation and illustration methods, measurements of central tendency, and measurement of variance units. Based on the content analysis results, researchers deigned an e-collaborative learning strategy and utilized Google drive applications. In addition, test of solving statistical problems and deep learning scale were also developed and validated. These instrumentations were applied on a sample of the second year business secondary school learners. This sample was randomly and equally distributed into two groups (33 as experimental group and 33 as control group). After application of the treatment variable (e-collaborative learning strategy), the findings showed a significant impact for the new e-collaborative strategy on acquiring statistical problem solving skills and improving the deep learning skills. The difference was in favor of the experimental group. Based on these results, a set of educational recommendation were suggested to generalize the outcomes of this research in different business education context and courses.

Model United Nations and Deep Learning: Theoretical and Professional Learning

ABSTRACTThis article demonstrates that the purposeful subject design, incorporating a Model United Nations (MUN), facilitated deep learning and professional skills attainment in the field of International Relations. Deep learning was promoted in subject design by linking learning objectives to Anderson and Krathwohl’s (2001) four levels of knowledge or cognition: factual, conceptual, procedural, and metacognitive. Students demonstrated improvement in all four areas; however, this article focuses on outcomes in the conceptual and metacognitive realms as these were where students showed the most growth. In the conceptual realm, the subject aimed to increase students’ capacity to apply international relations theories. Students tended to utilize the traditional theories of realism and liberalism; however, their explanations and applications of these theories showed deep learning. In the metacognitive realm, students were able to analyze their own negotiation styles and to explain how it influenced their approach to the Model UN, thus demonstrating strong professional skills development and metacognitive growth. Learning was enhanced by the use of open access online subject materials and online communications. The subject was designed and run in a context where simulations in teaching politics and international relations are not common.

Core Skills Training in a Teacher Training Programme

Fullan and Langworthy (2013) identified eight Deep Learning Skills in 2013. Michael Fullan later focuses on Key Future Skills or the 6 C's, which students need to know in order to live in the modern times. Public schools, worldwide, are gradually adding Deep Learning Tasks to their curriculum in order to prepare their students for a modern life. The main purpose of this paper is to investigate the effect of adding an online Learning Management System to a teacher training programme for language teachers who are not digitally as literate as their students to prepare these teachers to develop their students⿿ Key Future Skills. This study was conducted over a period of 9 months with 50 primary and secondary school English language teachers in a rural school in Malaysia during a project by the British Council for the Ministry of Education. The teachers⿿ online behaviour was monitored and documented during this period. Data were collected through questionnaires (10 questions) at the end of the project and through interviews 6 months after the end of the project. The results show that the teachers became more vigilant towards Deep Learning Skills and their significance for life in the 21st century and the application of technology in their own teaching context. On a positive note, their active online presence and collaboration with each other on the selected platform also helped them feel more confident in preparing their own students to develop their 6 C's independently.

Practical session assessments in human anatomy: Weightings and performance.

Assessment weighting within a given module can be a motivating factor for students when deciding on their commitment level and time given to study a specific topic. In this study, an analysis of assessment performances of second year anatomy students was performed over four years to determine if (1) students performed better when a higher weighting was given to a set of practical session assessments and (2) whether an improved performance in the practical session assessments had a carry-over effect on other assessment tasks within that anatomy module and/or other anatomy modules that follow. Results showed that increasing the weighting of practical session assessments improved the average mark in that assessment and also improved the percentage of students passing that assessment. Further, it significantly improved performance in the written end-semester examination within the same module and had a carry-over effect on the anatomy module taught in the next teaching period, as students performed better in subsequent practical session assessments as well as subsequent end-semester examinations. It was concluded that the weighting of assessments had significant influences on a student's performance in that, and subsequent, assessments. It is postulated that practical session assessments, designed to develop deep learning skills in anatomy, improved efficacy in student performance in assessments undertaken in that and subsequent anatomy modules when the weighting of these assessments was greater. These deep learning skills were also transferable to other methods of assessing anatomy. Anat Sci Educ 9: 330-336. © 2015 American Association of Anatomists.