Traditional Learning Methods Research Articles

PANet: Pluralistic Attention Network for Few-Shot Image Classification

Traditional deep learning methods require a large amount of labeled data for model training, which is laborious and costly in real word. Few-shot learning (FSL) aims to recognize novel classes with only a small number of labeled samples to address these challenges. We focus on metric-based few-shot learning with improvements in both feature extraction and metric method. In our work, we propose the Pluralistic Attention Network (PANet), a novel attention-oriented framework, involving both a local encoded intra-attention(LEIA) module and a global encoded reciprocal attention(GERA) module. The LEIA is designed to capture comprehensive local feature dependencies within every single sample. The GERA concentrates on the correlation between two samples and learns the discriminability of representations obtained from the LEIA. The two modules are complementary to each other and ensure the feature information within and between images can be fully utilized. Furthermore, we also design a dual-centralization (DC) cosine similarity to eliminate the disparity of data distribution in different dimensions and enhance the metric accuracy between support and query samples. Our method is thoroughly evaluated with extensive experiments, and the results demonstrate that with the contribution of each component, our model can achieve high-performance on four widely used few-shot classification benchmarks of miniImageNet, tieredImageNet, CUB-200-2011 and CIFAR-FS.

Memristor-based Bayesian spiking neural network for IBD diagnosis

Traditional deep learning methods, such as deep neural networks, have achieved remarkable success in image processing, natural language processing, graph computation, and other fields. However, in the diagnosis of Inflammatory Bowel Disease (IBD), conventional deep learning methods are highly susceptible to generating overconfident results, which can lead to great loss of life and property if it results in misdiagnosis of the patient. In this work, we propose a memristor-based IBD diagnostic system inspired by the idea of variational inference based on Bayes' law. The memristors in our system are used for both synaptic weight storage and entropy sources so that an efficient Bayesian inference system can be realized. Our memristor-based true random number generator can produce probability-tunable bitstreams required for Bayesian inference with a mean-square error that is reduced by 10.9 × than that of a conventional pseudo-random generator. The proposed system consists of a coarse-grained and a fined-grained spiking neural network, and an optimized strategy that trims the neuron's threshold is proposed for maintaining the appropriate model sparsity and reducing information loss. With Bayesian inference, our work achieves lower diagnostic error rates, which are reduced by 10.79 % and 0.49 % for the coarse-grained and fine-grained networks, respectively. The proposed system is easy to hardware implement and presents a novel solution for community-wide IBD diagnosis.

A comparison of virtual reality and three-dimensional multiplanar educational methods for student learning of cone beam computed tomography interpretations.

The purpose of this study was to compare student learning of cone beam computed tomography (CBCT) interpretation using immersive virtual reality (VR) and three-dimensional multiplanar (MP) reconstructions. Sixty first-year dental students were randomly allocated to two groups, VR and MP, and underwent a one-on-one educational intervention to identify anatomic structures using CBCT data. All participants completed three multiple-choice questionnaires (MCQs) before (T1), immediately after (T2), and 2weeks following (T3) the intervention. Additionally, pre-survey, post-survey, NASA Task Load Index (NASA-TLX), and presence questionnaires were completed. Analysis of objective measures of performance on MCQs and subjective data from the questionnaires was completed (α=0.05). There was a significant increase in test performance and informational recall between T1-T2 and T1-T3 for VR and MP groups (p<0.001). However, there were no significant differences in performance on MCQs between T2 and T3. Analysis of the Presence questionnaire indicated that the VR group felt decreased distraction (p=0.013), increased realism (p=0.035), and increased involvement (p=0.047) during the educational intervention when compared with the MP group. Analysis of the NASA-TLX indicated that the VR group experienced more physical demand (p<0.01) but similar cognitive demand when compared with the MP group. Qualitative responses indicated that the VR group had a more dynamic sense of visualization and manipulation compared to the MP group. Results from this study show that VR is as effective as traditional MP methods of CBCT interpretation learning. Further benefits of VR educational intervention include increased involvement, realism and less distraction.

Machining quality prediction of multi-feature parts using integrated multi-source domain dynamic adaptive transfer learning

Machining quality prediction of multi-feature parts has been a challenging problem because of small dataset and inconsistent quality data distribution with respect to each machining feature. Transfer learning that leverages knowledge of one task and can be repurposed on another task seems a good solution for this purpose. However, traditional transfer learning typically has a single source domain and a target domain, which limits its applications in multi-source scenarios (e.g., multi-feature). To solve this issue, this paper proposes a novel integrated multi-source domain dynamic adaptive transfer learning (IMD-DATL) framework for machining quality prediction of multi-feature part machining systems. Specifically, a domain-sample similarity double matching multi-source domain integration method is designed to construct the integration knowledge transfer from multiple source domains to the target domain. A residual feature extraction network based on sample entropy-dynamic channel double-layer attention structure and a fine-grained transferable feature attention module are designed. These three attentions are used to improve the feature learning ability and the adaptation level to the predicted object in the three dimensions of sample, channel and data feature. Finally, multiple sets of comparative experiments in thin-walled part machining systems confirm the effectiveness and superiority of the proposed method for cross-domain quality prediction. Compared with other traditional transfer learning methods, the MAE, RMSE and Score on average of this method are increased by 5.47 %, 4.59 % and 4.84 %, respectively, compared with other multi-source domain adaptation methods, the MAE, RMSE and Score on average of this method are increased by 7.13 %, 7.37 % and 6.52 %, respectively.

MuBaBaO: Bridging the Gap between Human and Artificial Intelligence

This paper explores the applications of MuBaBaO Creative Thinking Blocks as an educational tool in the artificial intelligence-driven era. The multidimensional MuBaBaO method diverges from traditional learning methods and emphasizes fostering critical thinking, effective communication, creativity, spatial and emotional intelligence through non-linear pedagogy. By engaging participants in creative and problem-solving tasks using wooden blocks, this dynamic exploratory approach enhances cognitive abilities and prepares students to thrive alongside AI advancements. The paper highlights the importance of developing distinctive human qualities and skills, such as adaptability, imagination, and innovative thinking, to complement the technical knowledge required in a technology-dominated landscape.

Incorporating face-to-face and online learning features to propose blended learning framework for Post-COVID classrooms in India

PurposeThis study examines learner readiness and satisfaction with blended learning systems in India’s post-vaccine classrooms, focusing on the relationship between face-to-face (F2F), online learning (OL), and blended learning (BL) indicators and identifying which predictors within these systems most significantly affect learners’ satisfaction (LS).Design/methodology/approachAn online survey was conducted with 451 students from both public and private universities in India. The data were analyzed using factor analysis and confirmatory factor analysis, followed by multiple regression to test the hypotheses.FindingsThe findings reveal a significant positive correlation between learners’ satisfaction and online learning and blended learning, with β values of 28.3 and 27.2, bearing a p-value of 0.000. In contrast, face-to-face (F2F) learning was insignificant, with a β value of 0.070 and a p-value of 0.119. These insights underscore the effectiveness of online and blended learning formats in enhancing learner satisfaction in higher education while also suggesting a re-evaluation of the role of traditional F2F learning methods. The research supports the integration of online learning in higher education due to its balanced mix of teacher-led and student-centered instruction, alongside the practical benefits of reduced travel costs and access to independent study resources.Practical implicationsThis study provides insights into student perceptions and attitudes towards blended learning in India’s post-vaccine classrooms. It highlights the importance of tailoring blended learning strategies to meet colleges’ and universities’ diverse learning needs and goals in this evolving context. The findings serve as a valuable resource for educators and administrators, aiding in designing effective blended learning frameworks suited explicitly for higher education in India.Originality/valueWhile there is extensive literature on F2F, OL, and BL, limited research compares these learning approaches and their impact on learner satisfaction within the Indian higher education context. This study fills this gap by providing valuable insights for shaping educational strategies in India’s post-vaccine classrooms.

DNA recognition using Novel Deep Learning Model

DNA, a significant physiological biometric, is present in all human cells like hair, blood, and skin. This research introduces a new approach called the Deep DNA Learning Network (DDLN) for person identification based on their DNA. This novel Machine Learning model is designed to gather DNA chromosomes from an individual’s parents. The model’s flexibility allows it to expand or contract and has the capability to determine one or both parents of an individual using the provided chromosomes. Notably, the DDLN model offers quick training in comparison to traditional deep learning methods. The study employs two real datasets from Iraq: the Real Iraqi Dataset for Kurds (RIDK) and the Real Iraqi Dataset for Arabs (RIDA). The outcomes demonstrate that the proposed DDLN model achieves an Equal Error Rate (EER) of 0 for both datasets, indicating highly accurate performance.

Advancing arrhythmia education through the CDIO approach: a new paradigm in nursing student training

BackgroundThe accurate diagnosis and effective management of arrhythmias are crucial, with nurses playing a key role in the early detection and treatment, significantly impacting patient outcomes. Improving education on arrhythmias among nurses, especially in critical care and perioperative settings, can enhance patient safety and the quality of care.MethodsA total of 116 trainee nurses were randomly divided into two groups: one utilizing the conceive-design-implement-operate (CDIO) model and the other employing a traditional lecture-based learning (LBL) method, to undergo arrhythmia training. The studyassessed the effects of the two teaching methods and investigated the students’ attitudes toward these educational practices, with all participants completing pre- and post-course tests.ResultsThe CDIO model significantly enhances nursing students’ arrhythmia proficiency, yielding higher test scores and sustained improvement after 24-week compared to the traditional LBL method, alongside markedly better self-learning enthusiasm, understanding, satisfaction with the teaching approach and effectiveness, and interest in learning arrhythmia. The CDIO model in nursing arrhythmia courses boosts theoretical knowledge and application, showing potential in clinical skill enhancement.ConclusionsOur study introduces the CDIO model in nursing arrhythmia courses, with improvement in knowledge and skills, and promise for broader application.

Development and implementation of the course entitled "Virtual Simulation Experiment of Recombinant Human Erythropoietin Manufacturing Process"

Considering the issues present in traditional learning methods of manufacturing process for biotechnology majors, this paper presents the development and implementation process of the course entitled "Virtual Simulation Experiment of Recombinant Human Erythropoiesis Manufacturing Process". The experiment combines modern biological manufacturing technology and three-dimensional information technology, with recombinant human erythropoiesis drug serving as the focal point. This paper elaborates on the teaching concepts, objectives, contents, implementation methods, experimental procedures, interactive steps, and assessment criteria used in the experiment. Through innovative experimental scheme design, teaching methodologies, and evaluation systems, this course aims to cultivate students' analytical and problem-solving skills in the field of biopharmaceutical engineering, while also broadening students' perspective and expanding their vision.

Multi-Branch Attention Fusion Network for Cloud and Cloud Shadow Segmentation

In remote sensing image processing, the segmentation of clouds and their shadows is a fundamental and vital task. For cloud images, traditional deep learning methods often have weak generalization capabilities and are prone to interference from ground objects and noise, which not only results in poor boundary segmentation but also causes false and missed detections of small targets. To address these issues, we proposed a multi-branch attention fusion network (MAFNet). In the encoder section, the dual branches of ResNet50 and the Swin transformer extract features together. A multi-branch attention fusion module (MAFM) uses positional encoding to add position information. Additionally, multi-branch aggregation attention (MAA) in the MAFM fully fuses the same level of deep features extracted by ResNet50 and the Swin transformer, which enhances the boundary segmentation ability and small target detection capability. To address the challenge of detecting small cloud and shadow targets, an information deep aggregation module (IDAM) was introduced to perform multi-scale deep feature aggregation, which supplements high semantic information, improving small target detection. For the problem of rough segmentation boundaries, a recovery guided module (RGM) was designed in the decoder section, which enables the model to effectively allocate attention to complex boundary information, enhancing the network’s focus on boundary information. Experimental results on the Cloud and Cloud Shadow dataset, HRC-WHU dataset, and SPARCS dataset indicate that MAFNet surpasses existing advanced semantic segmentation techniques.

Multi-UAV pursuit-evasion gaming based on PSO-M3DDPG schemes

The sample data for reinforcement learning algorithms often exhibit sparsity and instability, making the training results susceptible to falling into local optima. Mini-Max-Multi-agent Deep Deterministic Policy Gradient (M3DDPG) algorithm is a multi-agent reinforcement learning algorithm, which introduces the minimax theorem into Multi-Agent Deep Deterministic Policy Gradient (MADDPG) algorithm. It also has unstable convergence caused by sparse sample data and randomization. However, the Particle Swarm Optimisation (PSO) algorithm, unlike traditional reinforcement learning methods, involves the construction of independent populations of policy networks to generate sample data, followed by training the reinforcement learning algorithm. PSO optimizes and updates the policy population based on a fitness function, aiming to enhance the efficiency and convergence speed of the algorithm in learning from the sample data. In order to address the multi-agent pursuit-evasion problem, we propose the PSO-M3DDPG algorithm, which combines the PSO algorithm with the M3DDPG algorithm. Through experimental simulations, the improved algorithm demonstrates superior training results and faster convergence speeds, thus validating its effectiveness.

An interactive self-learning system using smartphone app and cards enabling braille touch experience for blindness

This research is conducted to address the challenges faced by individuals with visual impairment (VI) in learning braille through the development and evaluation of an innovative self-learning system. Traditional methods of braille education often rely on resource-intensive one-on-one guidance, which may not be feasible for all due to resource constraints. This study introduces a novel approach that leverages smartphone technology and tangible braille cards to create an engaging and effective self-learning experience. The study’s findings highlight the self-learning system’s effectiveness, evidenced by high ratings in technology acceptance model (TAM) evaluations and interviews with students and teachers, conducted collaboratively at the VI Rehabilitation Center in Malang, Indonesia. As an inclusive educational tool, the system bridges the gap between traditional braille learning methods and modern technological advancements, promoting independence and enhanced literacy for the community with VI.

Evaluating the Effectiveness of the iPusnas in Enhancing Elementary Students’ Numeracy Skills

Background of the study: Integrating digital resources in education is increasingly important for enhancing student learning experiences and outcomes. This study examines the impact of using iPusnas e-books on the numeracy skills of fifth-grade elementary school students. Purpose: The primary aim of this study was to determine the effectiveness of iPusnas e-books in improving the numeracy skills of elementary school students compared to traditional learning methods using textbooks. Method: A quasi-experimental design with a non-equivalent control group was employed. The sample consisted of two fifth-grade classes from SD Muhammadiyah 1 Wonopeti, Yogyakarta, Indonesia. One class served as the experimental group using iPusnas e-books, while the other served as the control group using traditional textbooks. Pre-tests and post-tests were administered to assess numeracy skills. Data were analyzed using T-tests and N-Gain tests. Findings: The results indicated a significant improvement in the numeracy skills of students in the experimental group compared to the control group. iPusnas e-books were more effective than traditional textbooks, as evidenced by higher post-test scores and N-Gain values. Conclusion: The study concludes that iPusnas e-books significantly enhance numeracy skills in fifth-grade students, highlighting the potential of digital learning resources to improve educational outcomes.

Problematika Guru dalam Mengembangkan Media Pembelajaran Berbasis Teknologi Informasi di Sekolah Dasar

This research is intended to identify and examine the various obstacles faced by teachers in creating information technology-based learning media in elementary schools. The approach applied is a case study and qualitative method. This research involves in-depth interviews with teachers in several regions. The research results show that the main obstacles include a lack of training and technical support, limited technological infrastructure, and resistance to changes in traditional learning methods. Thus, this research provides important insights for educational policy makers in designing strategies for increasing teacher competency and developing technological infrastructure in elementary schools.

Prostate Cancer Diagnosis via Visual Representation of Tabular Data and Deep Transfer Learning.

Prostate cancer (PC) is a prevalent and potentially fatal form of cancer that affects men globally. However, the existing diagnostic methods, such as biopsies or digital rectal examination (DRE), have limitations in terms of invasiveness, cost, and accuracy. This study proposes a novel machine learning approach for the diagnosis of PC by leveraging clinical biomarkers and personalized questionnaires. In our research, we explore various machine learning methods, including traditional, tree-based, and advanced tabular deep learning methods, to analyze tabular data related to PC. Additionally, we introduce the novel utilization of convolutional neural networks (CNNs) and transfer learning, which have been predominantly applied in image-related tasks, for handling tabular data after being transformed to proper graphical representations via our proposed Tab2Visual modeling framework. Furthermore, we investigate leveraging the prediction accuracy further by constructing ensemble models. An experimental evaluation of our proposed approach demonstrates its effectiveness in achieving superior performance attaining an F1-score of 0.907 and an AUC of 0.911. This offers promising potential for the accurate detection of PC without the reliance on invasive and high-cost procedures.

Robust PCA with Lw,∗ and L2,1 Norms: A Novel Method for Low-Quality Retinal Image Enhancement.

Nonmydriatic retinal fundus images often suffer from quality issues and artifacts due to ocular or systemic comorbidities, leading to potential inaccuracies in clinical diagnoses. In recent times, deep learning methods have been widely employed to improve retinal image quality. However, these methods often require large datasets and lack robustness in clinical settings. Conversely, the inherent stability and adaptability of traditional unsupervised learning methods, coupled with their reduced reliance on extensive data, render them more suitable for real-world clinical applications, particularly in the limited data context of high noise levels or a significant presence of artifacts. However, existing unsupervised learning methods encounter challenges such as sensitivity to noise and outliers, reliance on assumptions like cluster shapes, and difficulties with scalability and interpretability, particularly when utilized for retinal image enhancement. To tackle these challenges, we propose a novel robust PCA (RPCA) method with low-rank sparse decomposition that also integrates affine transformations τi, weighted nuclear norm, and the L2,1 norms, aiming to overcome existing method limitations and to achieve image quality improvement unseen by these methods. We employ the weighted nuclear norm (Lw,∗) to assign weights to singular values to each retinal images and utilize the L2,1 norm to eliminate correlated samples and outliers in the retinal images. Moreover, τi is employed to enhance retinal image alignment, making the new method more robust to variations, outliers, noise, and image blurring. The Alternating Direction Method of Multipliers (ADMM) method is used to optimally determine parameters, including τi, by solving an optimization problem. Each parameter is addressed separately, harnessing the benefits of ADMM. Our method introduces a novel parameter update approach and significantly improves retinal image quality, detecting cataracts, and diabetic retinopathy. Simulation results confirm our method's superiority over existing state-of-the-art methods across various datasets.

Survei Keterlaksanaan Kurikulum Merdeka Mata Pelajaran Pendidikan Jasmani Olahraga dan Kesehatan (Pjok) pada Tingkat Satuan Pendidikan SMAN/SMKN Se-Kecamatan Driyorejo

The independent curriculum is the newest curriculum in Indonesia which changes traditional learning methods to encourage learning that is centered on students' abilities. It is implemented in all subjects, one of which is Education, Physical, Sports and Health (PJOK). The purpose of this research is to determine the implementation of PJOK learning in SMAN/SMKN in Driyorejo District using the Independent Curriculum and the supporting and inhibiting factors in implementing the independent curriculum. The method used in this research is a survey by distributing questionnaires to respondents. This research is a type of quantitative descriptive research. The population used was PJOK teachers and eleventh grade students at SMAN and SMKN Driyorejo and the research sample was the principal, deputy principal, five PJOK teachers, and two hundred and twenty-one students. The sampling technique applies cluster random sampling. Data analysis used percentage. Based on the research results, it can be explained that; 1) The implementation of the independent curriculum in PJOK subjects in SMAN and SMKN throughout Driyorejo District is in the "sufficient" category. Therefore, there are still several indicators or components that need to be improved for both teachers and students. 2) The factors that support the implementation of the independent curriculum at SMAN 1 Driyorejo and SMKN 1 Driyorejo are that the principal and head of curriculum support the continuous PJOK teacher training and development program regarding the implementation of the independent curriculum, and 3) the factor that hinders the implementation of the independent curriculum is that not all teachers understand learning flow in the independent curriculum.

Safe reinforcement learning based optimal low-carbon scheduling strategy for multi-energy system

Multi-energy system with distributed energy resources has become the inevitable trend in recent years due to their potential for creating the efficient and sustainable energy infrastructure, with a strong ability on carbon emission reduction. To accommodate the uncertainties of renewable energy generation and energy demand, model-free deep reinforcement learning methods are emerging for energy management in multi-energy system. However, traditional reinforcement learning methods still have operation safety issue of violating the physical constraints of multi-energy system. To address the challenges, a low-carbon scheduling strategy based on safe soft actor-critic algorithm is proposed in this paper. Firstly, an electricity-thermal-carbon joint scheduling framework is constructed, where carbon trading mechanism is incorporated to further motivate carbon emission reductions. Secondly, the energy cost and carbon trading cost are simultaneously integrated in the objective function, and the dynamic optimization problem of multi-energy system is modeled as a constrained Markov decision process by taking into account the diverse uncertainties. Then, a novel safe soft actor-critic method is proposed to achieve the benefits of economic and carbon emissions, where the security networks and Lagrangian relaxation are introduced to deal with operation constraints. The case study validates that the proposed scheduling strategy can reduce the energy cost and carbon trading cost by up to 26.24% and 33.73% within constraints, compared with existing methods.

Game Edukasi Interaktif Sejarah Kerajaan Hindu-Buddha menggunakan Platform Scratch

The lack of effectiveness of traditional history learning methods at SMKN 1 Pedan. So, it is necessary to develop educational game learning media using the Scratch application, with the aim of fostering interest in learning and student involvement in learning the history of Hindu-Buddhist kingdoms. This research aims to produce and develop products in the form of learning media with a scratch platform for Hindu-Buddhist History subjects. This type of research is development by building or creating Scratch-based learning media. The method used in research to develop educational game media is Research and Development (R&amp;D). The instruments used are media questionnaires, materials, observations, interviews and literature studies. The research model used is ADDIE with stages of analysis, design, development and implementation, and the data analysis technique used is descriptive statistics. Our findings show that the results of media testing are very feasible. Meanwhile, the response of users of this media in the category is very good. So, this game can be used by students to learn the History of Hindu-Buddhist Kingdoms in grade 10 SMKN 1 Pedan.

Effectiveness of spaced repetition for clinical problem solving amongst undergraduate medical students studying paediatrics in Pakistan

BackgroundStudies using spaced repetition for teaching and learning in undergraduate clinical rotations such as paediatrics are limited, even more so in the South Asian region. Therefore, this study aimed to identify the effectiveness of utilizing spaced repetition compared to traditional learning methods among undergraduate medical students during their paediatric rotation at a medical university in Pakistan.MethodsBahria University Medical and Dental College (BUMDC) conducted quasii-experimental research in Karachi. Four topics were identified from the Year 5 Pediatrics curriculum to be used in the study, using which the study content was developed along with 50 multiple choice questions (MCQs) for assessment. All BUMDC Year 5 medical students rotating in Pediatrics were included and randomly allocated to the control or intervention group. In the control group, they provided the students with traditional study methods consisting of books and lectures to learn topics. In the intervention group, we created an Anki flashcard deck of the same topics to enable learning via spaced repetition. The researchers conducted a pretest and post test assessment of the 50 MCQs in both groups at the beginning and after the four-week study interval. The data were analysed using SPSS 19.ResultsA total of 115 BUMDC medical students agreed to participate in the study; 70 (59.1%) were in the intervention group, and 45 (41.7%) were in the control group. The pretest mean score of the control group was 27.96 ± 3.70, and the posttest mean score was 27.22 ± 5.02, with no statistically significant difference at the 95% confidence level. The mean score of the pretest for the intervention group was 27.93 ± 4.53, and that of the posttest was 30.8 ± 4.56, with a statistically significant difference at the 95% confidence level. The intervention showed a significant effect size of 0.8.ConclusionThe use of spaced repetitions resulted in significantly greater scores for medical students studying paediatrics than for those using more traditional methods of learning, compromising medical books and lectures. Considering that medical students need to retain a vast amount of information, using spaced repetition through flashcards can be a more effective learning tool that is more cost-efficient and time-efficient than traditional learning methods.