Dynamic Learning Research Articles

Multi-group sparrow search algorithm based on K-means clustering

In order to improve the defects of the Sparrow Search Algorithm (SSA) in single-species search, which causes redundancy in its speed of collection and easily ignores high-quality solutions and falls into local optimality, a K-means Multigroup Sparrow Search Algorithm (KSSA) based on K-means clustering was proposed. Firstly, the multi-population mechanism is introduced into SSA to weaken the collection ability of a single population and reduce the probability of falling into the local optimum. Secondly, the K-means algorithm is used to divide the sub-populations to increase the differences between the sub-populations, and at the same time, the individuals in the sub-populations focus on searching in a small range, thereby improving the efficiency of the initial search. Then, the weighted centroid communication strategy is used to improve the quality of communication between populations, reduce the interference of the own population, and reduce the risk of all sub-populations falling into the local optimum due to a sub-population falling into the local optimum. Finally, dynamic reverse learning is introduced into the vigilant to enhance its anti-predator behavior and improve the defects of slower collection speed and insufficient collection accuracy caused by the increase in the number of sub-populations. The test function simulation experiment shows that KSSA has better optimization performance than SSA and other algorithms.

Dynamic Assessment-Based Curriculum Learning Method for Chinese Grammatical Error Correction

Dynamic Assessment-Based Curriculum Learning Method for Chinese Grammatical Error Correction

Generative learning for forecasting the dynamics of high-dimensional complex systems

We introduce generative models for accelerating simulations of high-dimensional systems through learning and evolving their effective dynamics. In the proposed Generative Learning of Effective Dynamics (G-LED), instances of high dimensional data are down sampled to a lower dimensional manifold that is evolved through an auto-regressive attention mechanism. In turn, Bayesian diffusion models, that map this low-dimensional manifold onto its corresponding high-dimensional space, operate on batches of physics correlated, time sequences of data and capture the statistics of the system dynamics. We demonstrate the capabilities and drawbacks of G-LED in simulations of several benchmark systems, including the Kuramoto-Sivashinsky (KS) equation, two-dimensional high Reynolds number flow over a backward-facing step, and simulations of three-dimensional turbulent channel flow. The results demonstrate that generative learning offers new frontiers for the accurate forecasting of the statistical properties of high-dimensional systems at a reduced computational cost.

A classification and recognition model for multiple fruit tree leaf diseases

Abstract Fruit tree leaf diseases affect both fruit survival rate and orchard revenue. Rapid and accurate identification of tree leaf diseases not only prevents the spread of diseases but also ensures healthy tree growth and improves fruit quality. Existing models mostly focus on individual types of tree leaf diseases, with limited applications in the identification of multiple tree leaf diseases. In response to the insensitivity of current classification models to disease region features and the issue of increased error rates due to the presence of similar diseases, this study proposes a residual network model based on the ECA channel attention mechanism and meta-Acon adaptive activation function.The model employs ResNet34 as the backbone network and incorporates the ECA module after each residual block to focus on relevant information. Additionally, a new activation function called meta-Acon is introduced to enhance the model's generalization ability through its dynamic learning capability. Finally, the model's recognition performance is improved by fusing bottom-level features with features from other layers using the Feature Pyramid Network (FPN).Experimental results on a dataset augmented with Mosaic processing show that the FPEM-ResNet34 model achieves a classification accuracy of 98.46%. Compared to other common models such as VGG-16, Inception-V1,AlexNet, and ResNet50, the proposed method mentioned in this paper demonstrates more effective improvement in the accuracy of tree leaf classification, making it highly valuable for practical applications..

AS PRÁTICAS PEDAGÓGICAS MEDIANTE AS REPERCUSSÕES DA APLICABILIDADE DAS TECNOLOGIAS

In recent years, the growing emphasis on teacher training and performance has revealed the urgency of critical and necessary actions. The rapid expansion of Information and Communication Technologies (ICTs) in the educational field not only highlights, but also intensifies, the widespread lack of preparation of many teachers in the face of the new possibilities that these technologies introduce into pedagogical practices. This study proposes an in-depth reflection on the impact of digital technologies on teachers' pedagogical practices, focusing on pedagogical innovations that emerge from classroom practices. The bibliographic research undertaken to support this study reveals that teachers recognize the pressing need for training courses that not only provide technical experiences, but also develop pedagogical dimensions in an integrated manner. Thus, teachers are required to master the curricular content and carry out a critical appropriation of ICTs, aiming to promote qualitative transformations in pedagogical practices. This integration makes it possible to combine pedagogical activities with digital technologies, promoting not only creativity and autonomy among students, but also encouraging deeper reflection on the dynamics of learning. However, by establishing this harmony between curricular knowledge and ICTs, teachers can foster an educational environment that truly takes advantage of the potential of new technologies to enrich and diversify the teaching-learning process.

Optimization of vehicle conceptual design problems using an enhanced hunger games search algorithm

Abstract Electric vehicles have become a standard means of transportation in the last 10 years. This paper aims to formalize design optimization problems for electric vehicle components. It presents a tool conceptual design technique with a hunger games search optimizer that incorporates dynamic adversary-based learning and diversity leader (referred to as HGS-DOL-DIL) to overcome the local optimum trap and low convergence rate limitations of the Hunger Games search algorithm to improve the convergence rate. The performance of the proposed algorithms is studied on six widely used engineering design problems, complex constraints, and discrete variables. For the HGS-DOL-DIL practical feasibility analysis, a case study of shape optimization of an electric car suspension arm from the industry is carried out. Overall, the inclusion of the OL strategy has proven its superiority in solving real-world problems, especially in solving real-world problems such as shape optimization of an electric vehicle automobile suspension arm, showing that the algorithm improves the search space improves the solution quality, and reflects its potential to find global optimum solutions in a well-balanced exploration and exploitation phase.

Improved identification of network anomalies through optimal CURE clustering

Abstract In this paper, we propose an advanced network anomaly behavior identification framework to overcome the constraints inherent in conventional rule- or signature-based approaches, which often struggle with emerging and previously unknown threats. Central to our framework is an Enhanced CURE (Cluster Updating and REfining) clustering algorithm, meticulously tailored and refined to incorporate a density-based methodology. This enhancement enables the algorithm to discern subtle shifts in network anomaly patterns with heightened precision. The implementation workflow commences with the application of the optimized CURE algorithm to analyze network data, followed by the deployment of a sophisticated anomaly degree ranking mechanism. This mechanism, through meticulous calculation of individual data points' anomaly degrees and subsequent ranking, effectively isolates those deviating significantly from standard behavioral norms, incorporating a strategic threshold to filter out false positives. To validate our methodology's efficacy and its superiority over existing techniques, experiments were conducted utilizing a substantial real-world network dataset. These tests affirm not only a marked increase in the accuracy of abnormal behavior recognition and a reduction in computational intricacy but also demonstrate the adaptability across diverse network ecosystems. Our approach has proven successful in pinpointing a wide array of network anomalies, encompassing malicious cyberattacks, fraudulent activities, unauthorized intrusions, and breaches of security protocols, thereby highlighting its comprehensive capability in bolstering network defense strategies. Despite the notable advancements and successful identification of various network anomalies, our framework currently lacks integration with real-time learning capabilities, limiting its immediate responsiveness to rapidly evolving attack patterns and necessitating ongoing research for dynamic updates and adaptive learning mechanisms.

The Innovation of Arabic Teaching Material Development in the Digital Era at Al-Fityan School Gowa IT High School

In facing the ever-evolving digital era, the development of Arabic teaching materials at Al-Fityan School Gowa IT High School requires innovations that are able to meet the needs of modern and effective learning. This article discusses various innovations applied in the development of Arabic teaching materials, ranging from the integration of multimedia technology to the utilization of interactive e-learning platforms. The main purpose of these innovations is to improve learning effectiveness, expand accessibility, and support students' various learning styles. Using qualitative research method through case study design, this article analyzes the implementation of digital technology in Arabic teaching materials at Al-Fityan School Gowa IT High School. Data were obtained through semi-structured in-depth interviews and analyzed with three stages of Miles and Huberman's qualitative data analysis technique: data reduction, data presentation and conclusion drawing. The results showed that the use of mobile applications, learning videos and other digital aids significantly increased students' interest and understanding of Arabic. The article also identifies challenges faced, including limited infrastructure and teacher readiness. Recommendations are given for the continued development of adaptive and inclusive digital teaching materials, in order to create a more dynamic and effective Arabic learning experience in this digital era.

Human motor learning dynamics in high-dimensional tasks.

Conventional approaches to enhance movement coordination, such as providing instructions and visual feedback, are often inadequate in complex motor tasks with multiple degrees of freedom (DoFs). To effectively address coordination deficits in such complex motor systems, it becomes imperative to develop interventions grounded in a model of human motor learning; however, modeling such learning processes is challenging due to the large DoFs. In this paper, we present a computational motor learning model that leverages the concept of motor synergies to extract low-dimensional learning representations in the high-dimensional motor space and the internal model theory of motor control to capture both fast and slow motor learning processes. We establish the model's convergence properties and validate it using data from a target capture game played by human participants. We study the influence of model parameters on several motor learning trade-offs such as speed-accuracy, exploration-exploitation, satisficing, and flexibility-performance, and show that the human motor learning system tunes these parameters to optimize learning and various output performance metrics.

The Escol@s Digitais Project. An experience of working with technologies in Primary Education in Portugal

The Escol@s Digitais Project is an action-research project that was born on the initiative of the Municipality of Amadora (Portugal) and has been under development by a research team of the Institute of Education of the University of Lisbon. As part of the Education XXI line of research, it aims to support the ongoing digital transformation in all public schools of Primary Education in the municipality to enhance the quality of processes, performances, and results of learning. Seeking to deepen and consolidate existing knowledge and practices, the Project defines four objectives to be pursued intentionally throughout its term: i) valuing the work carried out within schools in the digital transition, distinguishing and promoting successful practices; ii) reinforcing the sustained integration of teaching and learning dynamics with digital, in the classroom and in other local contexts; iii) recognizing and assessing students' digital skills, bearing in mind the Portuguese Profile of Students Leaving Compulsory Schooling; iv) monitoring project activities and understand their impact on teachers and students. In this article, we present the main starting questions and the conceptual foundations and premises that underpin the intervention plan's design. Although the plan involved other dimensions, particularly related to school management, here we will emphasize the assumption of digital technologies that we assumed and how we worked with the teachers. We conclude with the presentation of the Project's assumptions and work axes.

Exploring Learning Dynamics: A Comparative Study of IDEs and Command-Line Interfaces for Learning Java Programming language in the Department of Computer Science, Jigawa State College of Education and Legal Studies Ringim

This study explored the learning dynamics associated with Integrated Development Environments (IDEs) and Command-Line Interfaces (CLIs) for teaching and learning java programming language in the Department of Computer Science at the College of Education and Legal Studies, Ringim. The study evaluates the effectiveness of different programming tools (IDEs and CLIs) in enhancing the learning experience of Java programming students. It seeks to understand how these tools impact learners' confidence, skill development, and overall programming proficiency. The results revealed distinct advantages and challenges associated with each environment, underscoring the importance of context and learner preferences in selecting the appropriate tool for Java programming education. The study provides valuable recommendations for educators on optimizing programming instruction to better meet the needs of diverse learners.

Innovations and Challenges in Primary School English Education in the Industrial Era 4.0

The existence, dynamics, and applicability of English language instruction at the basic school level to the disruptive technology era are all covered in detail in this study. This paper aims to characterize research problems using descriptive-analytical approaches and research methodologies of the literature study type, utilizing literature data from pertinent books, journals, papers, and scientific publications. This study outlines a number of prerequisites for English language instruction in the modern day, including infrastructure and technology, curriculum and instructional strategies, certified teachers, instructional materials and resources, and parental support. The results also show that there are opportunities that can be targeted, such as more extensive access to language learning materials, dynamic and interesting learning opportunities, global connectivity and language exchange, digital applications for language practice, and the provision of a useful system for evaluation and feedback. In the meanwhile, issues include unequal access to technology, unequal user technical proficiency, linguistic difficulties, students' short attention spans and lack of focus, and threats to digital security.

CQformer: Learning Dynamics Across Slices in Medical Image Segmentation.

Prevalent studies on deep learning-based 3D medical image segmentation capture the continuous variation across 2D slices mainly via convolution, Transformer, inter-slice interaction, and time series models. In this work, via modeling this variation by an ordinary differential equation (ODE), we propose a cross instance query-guided Transformer architecture (CQformer) that leverages features from preceding slices to improve the segmentation performance of subsequent slices. Its key components include a cross-attention mechanism in an ODE formulation, which bridges the features of contiguous 2D slices of the 3D volumetric data. In addition, a regression head is employed to shorten the gap between the bottleneck and the prediction layer. Extensive experiments on 7 datasets with various modalities (CT, MRI) and tasks (organ, tissue, and lesion) demonstrate that CQformer outperforms previous state-of-the-art segmentation algorithms on 6 datasets by 0.44%-2.45%, and achieves the second highest performance of 88.30% on the BTCV dataset. The code will be publicly available after acceptance.

Integrating Molecular Dynamics and Machine Learning Algorithms to Predict the Functional Profile of Kinase Ligands.

The modulation of protein function via designed small molecules is providing new opportunities in chemical biology and medicinal chemistry. While drugs have traditionally been developed to block enzymatic activities through active site occupation, a growing number of strategies now aim to control protein functions in an allosteric fashion, allowing for the tuning of a target's activation or deactivation via the modulation of the populations of conformational ensembles that underlie its function. In the context of the discovery of new active leads, it would be very useful to generate hypotheses for the functional impact of new ligands. Since the discovery and design of allosteric modulators (inhibitors/activators) is still a challenging and often serendipitous target, the development of a rapid and robust approach to predict the functional profile of a new ligand would significantly speed up candidate selection. Herein, we present different machine learning (ML) classifiers to distinguish between potential orthosteric and allosteric binders. Our approach integrates information on the chemical fingerprints of the ligands with descriptors that recapitulate ligand effects on protein functional motions. The latter are derived from molecular dynamics (MD) simulations of the target protein in complex with orthosteric or allosteric ligands. In this framework, we train and test different ML architectures, which are initially probed on the classification of orthosteric versus allosteric ligands for cyclin-dependent kinases (CDKs). The results demonstrate that different ML methods can successfully partition allosteric versus orthosteric effectors (although to different degrees). Next, we further test the models with FDA-approved CDK drugs, not included in the original dataset, as well as ligands that target other kinases, to test the range of applicability of these models outside of the domain on which they were developed. Overall, the results show that enriching the training dataset with chemical physics-based information on the protein-ligand dynamic cross-talk can significantly expand the reach and applicability of approaches for the prediction and classification of the mode of action of small molecules.

Dynamic intercultural learning and collaboration: transforming language teacher perspectives and practices

PurposeThis study aims to examine the impact of intercultural learning and collaboration on two English as a world language teachers from South Korea and Taiwan within a virtual professional development program, emphasizing their evolving understanding of culture and interculturality and its implications for practice.Design/methodology/approachUtilizing qualitative research design, this study incorporates three sources of data: written reflections, online meetings and semistructured interviews. Data is examined through the cultural perspectives framework (Hall, Covarrubias and Kirschbaum, 2022) to analyze how teachers (re)frame culture and interculturality in English language teaching, specifically through the lens of interpretive, critical and socio-scientific perspectives.FindingsThe findings reveal that engaging in facilitated professional intercultural learning and collaboration enhances teachers’ perspectives and practices regarding cultural complexities in language classrooms. The study highlights the importance of reflective practice, collaborative professional learning and the adoption of multiple cultural perspectives.Originality/valueThis research enriches the field of intercultural education by advocating for a structured approach to teacher learning in bridging the gap between theory and practice. It uniquely applies Hall et al.’s (2022) ICS framework to analyze how teachers (re)frame culture and interculturality in English language teaching. The originality is in the in-depth analysis of the intricate dynamics of teacher learning and the transformative potential of intercultural collaboration.

Driving Digitalization: Action Research to Innovate Pronunciation Pedagogies by Building a Virtual Voice Laboratory

This paper explores the potential of digitalization in supporting English as a Second Language (ESL) students' development of pronunciation skills through a parallel action research. The author created a Virtual Voice Laboratory (VVL) platform to innovate pronunciation pedagogies in higher education; and simultaneously conducted an ongoing action research study to examine three research questions. The questions examined the efficacy of the VVL in facilitating blended learning, self-directed practice, and self-evaluation within a pronunciation course, and its impact on student engagement, participation, and pronunciation skill development. This VVL as a tailormade digital platform was implemented with undergraduate ESL students in Hong Kong's higher education context. It enabled blended learning, wherein students engaged with the mechanics and articulatory movements essential for improving English pronunciation through self-directed practice using the VVL. Adopting an action research methodology, the study investigated the process of implementing digitalization and blended learning strategies. This was achieved through the analysis of student recordings, sound chart comparisons, and qualitative-quantitative feedback collected during a pilot study. The findings reveal nuances of student experiences, their learning trajectories, and the results from the pilot study, illuminating the impacts and outcomes facilitated by the e-learning approach. The research holds valuable implications for integrating digitalization and blended learning in language education, contributing to the ongoing scholarly dialogue on the transformative potential of technology-mediated approaches in fostering dynamic and impactful learning experiences for diverse student populations.

Best Practice STEM-Based Differentiated Mathematics Learning for Improving Learning Outcomes and Self-efficacy of High School Students

Learning outcomes and self-efficacy are important learning factors. Mathematics learning outcomes can reflect the extent to which students have developed as learners, while self-efficacy reflects students' self-confidence in their own abilities in solving mathematical problems. This study was based on a qualitative approach, best practice. This best practice uses the STAR flow (“Situasi, Tantangan, Aksi, Refleksi”). The situation at SMAN 1 Mande, especially class XI, shows low learning outcomes and lack of self-efficacy. The challenge faced is planning and implementing differentiated learning to improve learning outcomes and student self-efficacy. Through a STEM-based differentiated learning approach, researchers designed and implemented contextual learning on the theme of global warming with integrating science, technology, engineering and mathematics. The results of this best practice indicate an increase in learning outcomes and student self-efficacy. STEM-based differentiated learning can also improve understanding of mathematical concepts at the high school level. Researcher recommend that educators embrace differentiated learning strategies by customizing their approaches to accommodate the diverse needs such as students' level of readiness, interests, and student’s learning profile. The significance of comprehending student characteristics, such as learning styles and thinking abilities is paramount, especially in the implementation of student-centered learning. Additionally, educators are advised to prioritize aligning learning objectives with the curriculum, ensuring relevance and engagement. This various approach aims to create a dynamic learning environment to resonates with students individualized level. Develop interventions to address students' lack of confidence in solving mathematical problems can improve self efficacy.

Dynamic reinforcement learning reveals time-dependent shifts in strategy during reward learning.

Different brain systems have been hypothesized to subserve multiple "experts" that compete to generate behavior. In reinforcement learning, two general processes, one model-free (MF) and one model-based (MB), are often modeled as a mixture of agents (MoA) and hypothesized to capture differences between automaticity vs. deliberation. However, shifts in strategy cannot be captured by a static MoA. To investigate such dynamics, we present the mixture-of-agents hidden Markov model (MoA-HMM), which simultaneously learns inferred action values from a set of agents and the temporal dynamics of underlying "hidden" states that capture shifts in agent contributions over time. Applying this model to a multi-step, reward-guided task in rats reveals a progression of within-session strategies: a shift from initial MB exploration to MB exploitation, and finally to reduced engagement. The inferred states predict changes in both response time and OFC neural encoding during the task, suggesting that these states are capturing real shifts in dynamics.

FELRec: efficient handling of item cold-start with dynamic representation learning in recommender systems

AbstractRecommender systems suffer from the cold-start problem whenever a new user joins the platform or a new item is added to the catalog. To address item cold-start, we propose to replace the embedding layer in sequential recommenders with a dynamic storage that has no learnable weights and can keep an arbitrary number of representations. In this paper, we present , a large embedding network that refines the existing representations of users and items in a recursive manner, as new information becomes available. In contrast to similar approaches, our model represents new users and items without side information and time-consuming finetuning, instead it runs a single forward pass over a sequence of existing representations. During item cold-start, our method outperforms similar method by 29.50–47.45%. Further, our proposed model generalizes well to previously unseen datasets in zero-shot settings. The source code is publicly available at https://github.com/kweimann/FELRec.

谈判: Mega-games as Catalysts for Deep Experiential Learning in Higher Education

The study deepens into the transformative potential of mega-games as an innovative educational tool, offering profound and enriching learning experiences across diverse educational landscapes. Mega-games represent a fusion of various elements, including role-play, social interaction, simulations, rule-based systems, economic dynamics, political scenarios, and decision-making processes, all woven into an immersive narrative fabric. Through experiential learning, these games provide a unique platform for students to engage deeply with complex subject matter. This research centres on the application of mega-games within the context of sixth-semester students pursuing a degree in International Business at the Mexico State Campus of Tecnológico de Monterrey. Specifically, the study focuses on the simulation exercise titled 谈判 Tánpàn, which aims to immerse students in negotiation scenarios regarding the final price of a digital device manufactured in China. Drawing upon foundational principles outlined in Jesse Schell's book on game design, the exercise is meticulously designed to emulate real-world negotiation dynamics. The integration of game design principles, coupled with positive student feedback, underscores the efficacy of mega-games as potent educational instruments. Through rigorous analysis, the study unveils the profound impact of experiential learning on students' comprehension and application of negotiation techniques. By simulating authentic real-world scenarios, students are empowered to develop critical problem-solving acumen, hone their analytical thinking prowess, and refine their decision-making aptitude. Moreover, the immersive nature of mega-games fosters a dynamic learning environment that transcends traditional pedagogical approaches, fostering a holistic understanding of intricate subject matter. The success of the 谈判 Tánpàn simulation exercise serves as a testament to the potential of mega-games to revolutionize educational paradigms. It signals a burgeoning opportunity to expand the horizons of mega-games across various academic disciplines and participant cohorts. This study advocates for the widespread integration of mega-games as educational resources within Higher Education, championing their capacity to engender profound learning experiences and cultivate essential skills, heralding a new era of dynamic, immersive, and effective educational methodologies in diverse educational settings.