Learning Scenarios Research Articles

Robust hyperspectral image classification using generative adversarial networks

This paper introduces Sill-Rgan, a novel Generative Adversarial Network (GAN) designed to improve hyperspectral image (HSI) classification under varying lighting conditions. Sill-Rgan uniquely maps different light condition domains, enhancing sample classification robustness and generating new virtual samples. Addressing challenges like high spectral dimensionality and noise in HSI classification, our approach utilizes a deep proxy-based learning framework. It integrates and improves advanced GAN models and multitask networks for optimal training stability and loss function optimization. The model's mapping network is adept at generating domain-specific latent codes, enabling the transformation of original hyperspectral data into enhanced versions. Extensive experiments conducted on hyperspectral datasets of agricultural products under diverse indoor and outdoor lighting conditions confirm the effectiveness of Sill-Rgan. The results highlight the model's adaptability in both supervised and semi-supervised learning scenarios, yielding exceptional classification accuracy and enhanced data quality. The versatile potential of Sill-Rgan extends its applicability to a broad range of spectral data classifications, underlining its significant contribution to hyperspectral imaging. This advancement opens new avenues in machine vision systems, particularly in scenarios with dynamic lighting challenges.

Building soft skills through a role-play based approach for Requirements Engineering remote education

Teaching Requirements Engineering requires adopting pedagogical techniques to develop students' technical skills for identifying users' needs and designing software solutions. Additionally, since requirements engineering involves group work, students must cultivate social skills such as communication, empathy, and conflict resolution. In remote learning scenarios, developing these skills becomes more challenging due to limited interaction. To address these needs, this paper proposes adapting a project-based collaborative learning approach for remote education that combines Role-Play and Send-a-Problem learning techniques. In this approach, students collaborate on software projects in teams, assuming two roles: customers and software developers. We evaluated this approach during two cycles of Action Research, conducted remotely in two disciplines of a Software Engineering undergraduate course involving advanced and beginner students, respectively. In the advanced students' class, we observed that the methodology enhanced communication skills, analytical reasoning, conflict resolution, and empathy. To validate these results, we conducted a new study with beginning students, achieving positive outcomes despite the need for more support in team communication. As our primary contribution, we provide guidelines for implementing this collaborative learning approach online.

Beyond the Passive Absorption of Information: Engaging Students in the Critical Reading of Scientific Articles

AbstractThere is a consensus within the science education community that primary scientific literature is a legitimate and desirable educational resource. Moreover, critical reading of scientific articles is widely recognized as a key aspect of scientific literacy. However, university science courses rarely provide students with explicit opportunities to cultivate their critical reading skills. Much of the reason for this is that instructors tend to hold a passive learning view of reading in which students are expected to absorb information from scientific articles. The purpose of this study was to provide research evidence that an active learning scenario (ALS) combining (1) argumentation, (2) peer critique (also referred to as peer assessment), and (3) the Task-Oriented Reading Instruction framework (Ritchey & List, College Teaching, 70(3), 280–295, 2022) could be a concrete and realistic possibility for engaging students in the critical reading of scientific papers. The data analyzed in this study were the written critiques of scientific research articles and written peer feedback produced by sixty-one university students (38 females and 23 males, 19–25 years old). The results indicate that the ALS effectively offered students explicit opportunities to become more active and more critical readers of scientific articles, producing arguments, anticipating counterarguments, and constructing rebuttals. Implications related to critical reading instruction in science education and supporting students’ development of critical reading skills are discussed.

How to Evaluate Augmented Reality Embedded in Lesson Planning in Teacher Education

How to Evaluate Augmented Reality Embedded in Lesson Planning in Teacher Education

Cultural–Historical Activity Theory as an integrative model of socioscientific issue based learning in museums using extended reality technologies

ABSTRACT The transformation of natural history and science museums from receptacles (temples) to facilitators (forums) of knowledge fosters discourse around issues relating to science and society, known as social scientific issues (SSI). To assist guests with enhanced object-based learning, extended reality (XR) technologies are thought to leverage the leisure and social motivations of guests for greater object-based learning and SSI engagement. To model guests’ experiences using XR, this theoretical paper identifies and describes how a new conceptualization of Cultural–Historical Activity Theory (CHAT) to facilitate SSI outcomes through shared outcome spaces of interacting guest and museum activity systems, mediated by XR technology. We present two scenarios of forum-forward SSI-based learning utilizing this emergent CHAT model in: (i) scrutinizing the environmental and ecological consequences of human activity and (ii) unveiling the contributions of Indigenous Science Knowledge. Issues surrounding ownership and representation are discussed when ‘transforming’ singular objects into digital, decontextualized, and distributable entities.

Semi-Supervised and Unsupervised Deep Visual Learning: A Survey.

State-of-the-art deep learning models are often trained with a large amount of costly labeled training data. However, requiring exhaustive manual annotations may degrade the model's generalizability in the limited-label regime.Semi-supervised learning and unsupervised learning offer promising paradigms to learn from an abundance of unlabeled visual data. Recent progress in these paradigms has indicated the strong benefits of leveraging unlabeled data to improve model generalization and provide better model initialization. In this survey, we review the recent advanced deep learning algorithms on semi-supervised learning (SSL) and unsupervised learning (UL) for visual recognition from a unified perspective. To offer a holistic understanding of the state-of-the-art in these areas, we propose a unified taxonomy. We categorize existing representative SSL and UL with comprehensive and insightful analysis to highlight their design rationales in different learning scenarios and applications in different computer vision tasks. Lastly, we discuss the emerging trends and open challenges in SSL and UL to shed light on future critical research directions.

Blockchain and signcryption enabled asynchronous federated learning framework in fog computing

Federated learning combines with fog computing to transform data sharing into model sharing, which solves the issues of data isolation and privacy disclosure in fog computing. However, existing studies focus on centralized single-layer aggregation federated learning architecture, which lack the consideration of cross-domain and asynchronous robustness of federated learning, and rarely integrate verification mechanisms from the perspective of incentives. To address the above challenges, we propose a Blockchain and Signcryption enabled Asynchronous Federated Learning (BSAFL) framework based on dual aggregation for asynchronous cross-domain federated learning scenarios. In particular, we first design two types of signcryption schemes to secure the interaction and access control of collaborative learning between domains. Second, we construct a differential privacy approach that adaptively adjusts privacy budgets to ensure data privacy and local models' availability of intra-domain user. Furthermore, we propose an asynchronous aggregation solution that incorporates consensus verification and elastic participation using blockchain. Finally, security analysis demonstrates the security and privacy effectiveness of BSAFL, and the evaluation on real datasets further validates the high model accuracy and performance of BSAFL.

Incremental Learning, Incremental Backdoor Threats

Class incremental learning from a pre-trained DNN model is gaining lots of popularity. Unfortunately, the pre-trained model also introduces a new attack vector, which enables an adversary to inject a backdoor into it and further compromise the downstream models learned from it. Prior works proposed backdoor attacks against the pre-trained models in the transfer learning scenario. However, they become less effective when the adversary does not have the knowledge of the downstream tasks or new data, which is more practical and considered in this paper. To this end, we design the first latent backdoor attacks against incremental learning. We propose two novel techniques, which can effectively and stealthily embed a backdoor into the pre-trained model. Such backdoor can only be activated when the pre-trained model is extended to a downstream model with incremental learning. It has a very high attack success rate, and is able to bypass existing backdoor detection approaches. Extensive experiments confirm the effectiveness of our attacks over different datasets and incremental learning methods, as well as strong robustness against state-of-the-art backdoor defense mechanisms including <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Neural Cleanse</i> , <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Fine-Pruning</i> and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">STRIP</i> .

Development and Evaluation of an Infectious Disease Disaster Management Simulation Program for Nursing Students

This study was designed to develop and evaluate simulation program on infectious disease disaster management for nurse students. This study explores the efficacy of a simulation-based learning scenario in enhancing the competencies of nursing students in infectious disease disaster management. The methodology involved foundational learning tailored to the four stages of infectious disease disaster followed by a detailed simulation scenario. Reflective thinking was encouraged through debriefing sessions. The findings revealed significant improvements in the students' problem-solving abilities (t=-4.71, p&lt;.001), infectious disease knowledge (t=-3.39, p=.001), attitudes towards infectious diseases (t=-4.49, p&lt;.001), and clinical performance capabilities in infectious disease settings (t=-4.43, p&lt;.001) post-simulation training. This study confirmed that infectious disease disaster management simulation program can enhance problem-solving abilities, knowledge about infectious disease management, attitudes towards infectious disease management, and clinical performance capabilities among participants. Based on these findings, there is a need to expand infectious disease disaster management simulation training for nursing students.

Exploring language alternation and participation in an ‘in-between learning scenario’: a case study of a WhatsApp chat with secondary students of English

ABSTRACT The study of participation from a socio-interactional perspective relates to the exploration of the interactional practices displayed by interactants and the close examination of the multimodal resources they employ. Here we observe the language choices made by 2 teachers and 10 students who participate in a WhatsApp chat over the summer break. Since language choice is a social category-bound activity linked to social forms of participation, our analysis focuses on the negotiation participants engage in to determine their practiced language policy and to select their medium of interaction. Our analysis reveals that language choices reshape and construct what we would refer to as an ‘in-between learning scenario’. This scenario creates tensions between the teachers’ and the students’ agenda, observed through their alignment with other interactants and their interpretation of the task at hand. Language selection is not a strict, personal choice. Instead, it is socially situated and depends on how speakers co-construct the communicative event they participate in and who holds the control of topic selection.

Out with the old, in with the new: contrasts involving new features with acoustically salient cues are more likely to be acquired than those that redeploy L1 features

Feature-based approaches to second language (L2) phonology conceptualize the acquisition of new segments as operations that involve either the addition of new phonological features, or the rebundling of existent ones. While the deficit hypothesis assumes that only features that are fully specified in the L1 can be redeployed to the L2 in order to create new segments, it has been shown that features which are completely absent in the L1 can also be learned. This article investigates whether a learning scenario in which features are only partially available (that is, they are present in the L1, but are redundant with other features) is less challenging than learning an entirely new feature, even when the new feature has acoustically salient cues. Since Spanish has a much smaller vowel system /i e a o u/, L2 learners of German with Spanish as L1 need to learn a system with front rounded vowels as well as tense/lax contrasts. We tested L1 Spanish speakers' perception of the German contrasts /i/ ~ /I/ (e.g., Miete/mitte, where [+/– tense] is acquired) and /u/ ~ /y/ (e.g., Spulen/spülen, where L1 feature [+/–round] redeploys to a front vowel). The results showed that experienced L2 learners are more successful when discriminating between sounds in a feature acquisition scenario than in redeployment; however, neither of the non-native contrasts was easier to perceive than the other in the identification task. The differences in performance between tasks and in the acoustic saliency of the cues by contrast (F2 vs. duration and F1) suggests that L2 phonological acquisition is likely to take place at a surface level and favors learning through attunement to auditorily salient acoustic cues over internal rearrangement of abstract features, regardless of their presence in the L1.

Collaborative Development of a Farm Systems Learning Platform "4D Virtual Farm".

Over the past 20 years, a lower percentage of veterinary and animal science students entering Australian and New Zealand schools have a background or ongoing contact with livestock production systems. The increasing use of digital technologies over the same time provides a practical option to introduce students to the seasonal operations on livestock farms. This article describes the development of the 4D Virtual Farm, established to showcase 11 representative livestock farms across Australasia allowing students to virtually travel through seasons and place over each farming enterprise. Students can virtually visit different beef cattle, prime lamb, wool-sheep and dairy cattle farms, and a piggery. Any electronic device connected to the web including mobile phones, tablets, computers, and virtual reality headsets can be used to view the enterprises. For educators, the virtual farm can be used for a range of teaching and learning scenarios, such as demonstration of a particular production system via weblink for lectures or embedding within learning management systems. It also allows students to start at a particular point in time and space and guide themselves to other areas for self-learning or for a range of assessment tasks. This site provides an example that could be used in other teaching areas including abattoirs, exotic diseases, surgery, communication, and many other veterinary examples.

Evaluation of the learning state of online video courses based on functional near infrared spectroscopy.

Studying brain activity during online learning will help to improve research on brain function based on real online learning situations, and will also promote the scientific evaluation of online education. Existing research focuses on enhancing learning effects and evaluating the learning process associated with online learning from an attentional perspective. We aimed to comparatively analyze the differences in prefrontal cortex (PFC) activity during resting, studying, and question-answering states in online learning and to establish a classification model of the learning state that would be useful for the evaluation of online learning. Nineteen university students performed experiments using functional near-infrared spectroscopy (fNIRS) to monitor the prefrontal lobes. The resting time at the start of the experiment was the resting state, watching 13 videos was the learning state, and answering questions after the video was the answering state. Differences in student activity between these three states were analyzed using a general linear model, 1s fNIRS data clips, and features, including averages from the three states, were classified using machine learning classification models such as support vector machines and k-nearest neighbor. The results show that the resting state is more active than learning in the dorsolateral prefrontal cortex, while answering questions is the most active of the three states in the entire PFC, and k-nearest neighbor achieves 98.5% classification accuracy for 1s fNIRS data. The results clarify the differences in PFC activity between resting, learning, and question-answering states in online learning scenarios and support the feasibility of developing an online learning assessment system using fNIRS and machine learning techniques.

An Emotion Recognition Method Based on Eye Movement and Audiovisual Features in MOOC Learning Environment

In recent years, more and more people have begun to use massive online open course (MOOC) platforms for distance learning. However, due to the space–time isolation between teachers and students, the negative emotional state of students in MOOC learning cannot be identified timely. Therefore, students cannot receive immediate feedback about their emotional states. In order to identify and classify learners’ emotions in video learning scenarios, we propose a multimodal emotion recognition method based on eye movement signals, audio signals, and video images. In this method, two novel features are proposed: feature of coordinate difference of eyemovement (FCDE) and pixel change rate sequence (PCRS). FCDE is extracted by combining eye movement coordinate trajectory and video optical flow trajectory, which can represent the learner’s attention degree. PCRS is extracted from the video image, which can represent the speed of image switching. A feature extraction network based on convolutional neural network (CNN) (FE-CNN) is designed to extract the deep features of the three modals. The extracted deep features are inputted into the emotion classification CNN (EC-CNN) to classify the emotions, including interest, happiness, confusion, and boredom. In single modal identification, the recognition accuracies corresponding to the three modals are 64.32%, 74.67%, and 71.88%. The three modals are fused by feature-level fusion, decision-level fusion, and model-level fusion methods, and the evaluation experiment results show that the method of decision-level fusion achieved the highest score of 81.90% of emotion recognition. Finally, the effectiveness of FCDE, FE-CNN, and EC-CNN modules is verified by ablation experiments.

Enhancing Human Activity Recognition in Smart Homes with Self-Supervised Learning and Self-Attention.

Deep learning models have gained prominence in human activity recognition using ambient sensors, particularly for telemonitoring older adults' daily activities in real-world scenarios. However, collecting large volumes of annotated sensor data presents a formidable challenge, given the time-consuming and costly nature of traditional manual annotation methods, especially for extensive projects. In response to this challenge, we propose a novel AttCLHAR model rooted in the self-supervised learning framework SimCLR and augmented with a self-attention mechanism. This model is designed for human activity recognition utilizing ambient sensor data, tailored explicitly for scenarios with limited or no annotations. AttCLHAR encompasses unsupervised pre-training and fine-tuning phases, sharing a common encoder module with two convolutional layers and a long short-term memory (LSTM) layer. The output is further connected to a self-attention layer, allowing the model to selectively focus on different input sequence segments. The incorporation of sharpness-aware minimization (SAM) aims to enhance model generalization by penalizing loss sharpness. The pre-training phase focuses on learning representative features from abundant unlabeled data, capturing both spatial and temporal dependencies in the sensor data. It facilitates the extraction of informative features for subsequent fine-tuning tasks. We extensively evaluated the AttCLHAR model using three CASAS smart home datasets (Aruba-1, Aruba-2, and Milan). We compared its performance against the SimCLR framework, SimCLR with SAM, and SimCLR with the self-attention layer. The experimental results demonstrate the superior performance of our approach, especially in semi-supervised and transfer learning scenarios. It outperforms existing models, marking a significant advancement in using self-supervised learning to extract valuable insights from unlabeled ambient sensor data in real-world environments.

The Implementation of Blended Learning for English Courses at Higher Education in Vietnam: Teachers’ Perceptions

Advancements in technology and the Internet characterize the current English teaching and learning scenario. In this trend, the issue of blending face-to-face and online learning into English learning and teaching has drawn significant attention from teachers, researchers, and educators worldwide, including Vietnam, especially after the COVID-19 pandemic. Although this mode has been applied widely and shown its noticeable benefits, there have been relatively few studies regarding the perceptions of English lecturers at the tertiary level in English as a Foreign Language (EFL) context. Therefore, the objectives of this research are to (1) critically review knowledge of blended learning (BL); (2) investigate the tertiary level English lecturers’ perceptions of the BL model implementation in a college in Ho Chi Minh City, Vietnam; (3) provide some practical recommendations for future research and implementations. Online questionnaires and interviews with 14 English lecturers in the Summer 2023 semester were used to collect qualitative and quantitative data. At the end of the paper, EFL lecturers’ perceptions were revealed. Several educational implications and practical recommendations were suggested as well. The research findings are expected to contribute to a complete picture of BL in higher education in Vietnam.

Pengembangan Media Pembelajaran Fisika Berbantuan 3D Application Scratch Pada Topik Rotasi Dan Revolusi Untuk Meningkatkan Hasil Belajar Peserta Didik

Physics requires an innovative learning approach so that students can understand abstract concepts. This research aims to develop physics learning media assisted by 3D Application Scratch on the topic of rotation and revolution to improve students' learning outcomes. Using the 4D development research approach, this research involves four stages: Define, Design, Develop, and Disseminate. In the Define stage, physics learning needs and problems were identified. The Design stage includes learning scenario planning and media design using Scratch. Next, at the Develop stage, the 3D learning media prototype is implemented and then validated. The last stage, Disseminate, is conducted through journal publications. The results of the feasibility test validation score show that Scratch learning media can improve students' learning outcomes, namely for the display aspect of 3.4; the access aspect of 3.0 and the language aspect of 3.75. As obtained from the validation score, Scratch learning media on the topic of rotation and revolution is feasible to use. The results of this study are expected to contribute to the development of innovative learning media to improve the effectiveness of physics learning.

Кибератаки: иммерсионная образовательная среда и ее формирование

The article discusses the features of the formation of an immersion educational environment using a controlled simulator of computer attacks. The use of a controlled simulator of computer attacks as a method of teaching students disciplines related to information security is considered. This tool allows you to simulate various types of attacks on an information system and conduct training to improve its protection skills. Immersion educational environment in the field of information security – allows you to implement the principle of interactive learning with a nonlinear learning scenario and involvement in the process of the teacher and the student using information technology. The use of controlled simulators makes it possible to check the stability of computer networks and other systems to advanced cyber attacks and develop effective methods to combat them. To organize such an immersive educational environment, it is advisable to involve software manufacturers on the principles of strategic partnership.

Heterogeneous decentralised machine unlearning with seed model distillation

AbstractAs some recent information security legislation endowed users with unconditional rights to be forgotten by any trained machine learning model, personalised IoT service providers have to put unlearning functionality into their consideration. The most straightforward method to unlearn users' contribution is to retrain the model from the initial state, which is not realistic in high throughput applications with frequent unlearning requests. Though some machine unlearning frameworks have been proposed to speed up the retraining process, they fail to match decentralised learning scenarios. A decentralised unlearning framework called heterogeneous decentralised unlearning framework with seed (HDUS) is designed, which uses distilled seed models to construct erasable ensembles for all clients. Moreover, the framework is compatible with heterogeneous on‐device models, representing stronger scalability in real‐world applications. Extensive experiments on three real‐world datasets show that our HDUS achieves state‐of‐the‐art performance.

Catering for the Needs of Diverse Patient Populations: Using ChatGPT to Design Case-Based Learning Scenarios.

Artificial intelligence (AI) represents an opportunity for medical education to enhance efficiency, interactivity, and realism in learning scenarios. This project uses it to identify angles we have not considered before, particularly in creating culturally sensitive educational cases that represent the needs of a diverse patient population. The implementation showed encouraging results, as the ChatGPT algorithm was successful in writing cases that are more culturally sensitive; however, iteration for refinement was needed. An evolution of these prompts and resulting cases are presented. AI-generated material is only as good as the prompts we use, and how we define the task depends on digital literacy and pedagogical intent.