Learning Paradigm Research Articles

Towards Human-Interactive Controllable Video Captioning with Efficient Modeling

Video captioning is a task of describing the visual scene of a given video in natural language. There have been several lines of research focused on developing large-scale models in a transfer learning paradigm, with major challenge being the tradeoff between scalability and performance in limited environments. To address this problem, we propose a simple yet effective encoder–decoder-based video captioning model integrating transformers and CLIP, both of which are widely adopted in the vision and language domains, together with appropriate temporal feature embedding modules. Taking this proposal a step further, we also address the challenge of human-interactive video captioning, where the captions are tailored to specific information desired by humans. To design a human-interactive environment, we assume that a human offers an object or action in the video as a short prompt; in turn, the system then provides a detailed explanation regarding the prompt. We embed human prompts within an LSTM-based prompt encoder and leverage soft prompting to tune the model effectively. We extensively evaluated our model on benchmark datasets, demonstrating comparable results, particularly on the MSR-VTT dataset, where we achieve state-of-the-art performance with 4% improvement. In addition, we also show potential for human-interactive video captioning through quantitative and qualitative analysis.

Predictive Processing During Cue-Outcome Associative Learning in Autistic Children.

Predictive coding theories posit that autism is characterized by an over-adjustment to prediction errors, resulting in frequent updates of prior beliefs. Atypical weighting of prediction errors is generally considered to negatively impact the construction of stable models of the world, but may also yield beneficial effects. In a novel associative learning paradigm, we investigated whether unexpected events trigger faster learning updates in favour of subtle but fully predictive cues in autistic children compared to their non-autistic counterparts. We also explored the relationship between children's language proficiency and their predictive performances. Anticipatory fixations and explicit predictions were recorded during three associative learning tasks with deterministic or probabilistic contingencies. One of the probabilistic tasks was designed so that a fully predictive but subtle cue was overshadowed by a less predictive salient one. Both autistic and non-autistic children based their learning on the salient cue, and, contrary to our predictions, showed no signs of updating in favour of the subtle cue. While both groups demonstrated associative learning, autistic children made less accurate explicit predictions than their non-autistic peers in all tasks. Explicit prediction performances were positively correlated with language proficiency in non-autistic children, but no such correlation was observed in autistic children. These results suggest no over-adjustment to prediction errors in autistic children and highlight the need to control for general performance in cue-outcome associative learning in predictive processing studies. Further research is needed to explore the nature of the relationship between predictive processing and language development in autism.

Distributed resource optimisation using the Q-learning algorithm, in device-to-device communication: A reinforcement learning paradigm

In the context of wireless systems going forward, particularly in the Beyond 5G (B5G) era, where high data rates and low latency are critical, D2D communication is a pivotal technology that has many advantages. In D2D communication, the allocation of resources plays a critical role in achieving higher throughput while ensuring interference management, improved spectrum and energy efficiency, and system fairness. Conventional resource allocation methodologies encounter challenges in dynamically changing and diverse communication environments. To deal with the dynamic and unpredictable character of channel characteristics, we utilize a distributed iterative resource allocation technique based on the reinforcement learning (RL) approach that empowers the system to learn and adapt to the wireless environment autonomously. In this paper, we formulate a distributed Q learning-based RL method as its real-time learning capabilities, reduced communication overhead, and exploration efficiency make it well-suited for adapting to dynamic D2D environments compared to other RL methods. By applying the Q-learning method, the D2D devices act as learning agents striving to maximize the cumulative rewards. Through interactions with the environment and continuous learning from feedback, these agents adapt to real-time resource allocation decisions over time. Comparing our proposed Q-learning method to the state-of-the-art RL techniques, simulation results show improvements in energy and spectrum efficiency, latency, an increase in Jain's fairness index, and improvements in overall system throughput of about 6 %–8 %. The scalability is found to be 1.69 interpreting that Q-learning exhibits a good scalability as the throughput does not abruptly decrease for an increasing number of devices.

Increasing the immersivity of 360° videos facilitates learning and memory: implications for theory and practice

AbstractRecent years have seen an increase in the use of immersive virtual reality (IVR) technology in education and training. Studies examining the efficacy of IVR-based interventions have shown improved performance compared to traditional training programmes; however, little is known about whether such improvements can be detected at the level of individual cognitive abilities. The present study sought to examine the effect of IVR on memory using an incidental learning paradigm. Undergraduate volunteers viewed a three-minute 360° video clip under immersive and non-immersive conditions—respectively, using a Head Mounted Display (HMD) or a 2D flat screen monitor—followed by a surprise recall task. Although both devices supported active exploration of the scene in 360°, recall was significantly improved for learners in the immersive condition. These findings suggest that IVR has a facilitative effect on cognition, and that learners may naturally engage with IVR-delivered content without any special instruction or preparation.

The Effectiveness of the Mind Mapping in PjBL on the Learning Outcomes and the Creativity of Elementary School Students

The methods and models applied by teachers affect learning outcomes and student creativity. This research intends to analyze differences and effectiveness of mind mapping methods in the project-based learning model in terms of creativity and learning outcomes. The research method used is experimental research with a quasi-experimental design. The reseaech subjects were 41 students, 22 students in grade 4 A as a control group, and 19 students in grade 4 B as an experimental group. Data collection procedures in this research used test procedures and observation sheet assessment rubrics. The statistical tests used in this research include normality tests, homogeneity tests, t-tests, observation sheet tests, and N-Gain were assisted by SPPS for Windows version 25 and Microsoft Excel. The independent sample t-test yielded a significance value (sig.2-tailed) of 0.000, that is less than 0,05. This implies that H0 is disused while Ha is allowable. This suggests that there exists a major gap admist mind mapping approach used in the project-based learning paradigm and student learning outcomes. The N-Gain score for the experimental class was 0,64, while for the control class was 0,36. Both scores fell within the medium category. The N-Gain Percent for the experimental class was found to be effective, while for the control class, it was not. The data revealed that the average student creativity score for each indicator during the four meetings in the experimental class was higher than in the control class. Furthermore, the value of each N-gain score indicator at each meeting in the experimental class increased.

Predicting changes in brain metabolism and progression from mild cognitive impairment to dementia using multitask Deep Learning models and explainable AI

Background:The prediction of Alzheimer’s disease (AD) progression from its early stages is a research priority. In this context, the use of Artificial Intelligence (AI) in AD has experienced a notable surge in recent years. However, existing investigations predominantly concentrate on distinguishing clinical phenotypes through cross-sectional approaches. This study aims to investigate the potential of modeling additional dimensions of the disease, such as variations in brain metabolism assessed via [18F]-fluorodeoxyglucose positron emission tomography (FDG-PET), and utilize this information to identify patients with mild cognitive impairment (MCI) who will progress to dementia (pMCI). Methods:We analyzed data from 1,617 participants from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) who had undergone at least one FDG-PET scan. We identified the brain regions with the most significant hypometabolism in AD and used Deep Learning (DL) models to predict future changes in brain metabolism. The best-performing model was then adapted under a multi-task learning framework to identify pMCI individuals. Finally, this model underwent further analysis using eXplainable AI (XAI) techniques. Results:Our results confirm a strong association between hypometabolism, disease progression, and cognitive decline. Furthermore, we demonstrated that integrating data on changes in brain metabolism during training enhanced the models’ ability to detect pMCI individuals (sensitivity=88.4%, specificity=86.9%). Lastly, the application of XAI techniques enabled us to delve into the brain regions with the most significant impact on model predictions, highlighting the importance of the hippocampus, cingulate cortex, and some subcortical structures. Conclusion:This study introduces a novel dimension to predictive modeling in AD, emphasizing the importance of projecting variations in brain metabolism under a multi-task learning paradigm.

Client selection and resource scheduling in reliable federated learning for UAV-assisted vehicular networks

Federated Learning (FL), a promising deep learning paradigm extensively deployed in Vehicular Edge Computing Networks (VECN), allows a distributed approach to train datasets of nodes locally, e.g., for mobile vehicles, and exchanges model parameters to obtain an accurate model without raw data transmission. However, the existence of malicious vehicular nodes as well as the inherent heterogeneity of the vehicles hinders the attainment of accurate models. Moreover, the local model training and model parameter transmission during FL exert a notable energy burden on vehicles constrained in resources. In view of this, we investigate FL client selection and resource management problems in FL-enabled UAV-assisted Vehicular Networks (FLVN). We first devise a novel reputation-based client selection mechanism by integrating both data quality and computation capability metrics to enlist reliable high-performance vehicles. Further, to fortify the FL reliability, we adopt the consortium blockchain to oversee the reputation information, which boasts tamper-proof and interference-resistant qualities. Finally, we formulate the resource scheduling problem by jointly optimizing the computation capability, the transmission power, and the number of local training rounds, aiming to minimize the cost of clients while guaranteeing accuracy. To this end, we propose a reinforcement learning algorithm employing an asynchronous parallel network structure to achieve an optimized scheduling strategy. Simulation results show that our proposed client selection mechanism and scheduling algorithm can realize reliable FL with an accuracy of 0.96 and consistently outperform the baselines in terms of delay and energy consumption.

Student-Centered Learning as a New Approach in Higher Education Due to the Establishment of University Autonomy

The article emphasizes that with the gradual integration of domestic higher education into the European educational space, there is a transformation of educational programs based on student-centered learning. It was noted that the current state of development of the educational sector and the labor market requires higher education institutions to promptly take into account new trends and quickly respond to changes in society. The expediency of introducing university autonomy is substantiated. Particular attention is focused on the independent determination by institutions of higher education of the content of education in terms of learning outcomes and the independent formation of educational programs based on the competency approach. The need for the introduction of student-centered training, the basic basis of which is the training of a highly qualified and mobile specialist, ensuring the maximum chances of a graduate of a higher education institution to get the first job on the labor market, meeting the current needs of employers, is substantiated. The results of an online survey of scientific, scientific and pedagogical workers and students of higher education regarding the interaction and cooperation of the employer community with the educational community in the development of educational programs were analyzed. The research results confirmed the expediency of strengthening the dialogue between educators and all interested parties in order to create the latest successful and attractive educational programs for applicants. Such cooperation will ensure the determination of the same requirements and criteria for specialists of different qualification levels on the part of employers and institutions of higher education. The paradigm of student-centered learning is defined, which is based on increasing the transparency and publicity of educational programs, clear and understandable rules and procedures regulating the rights and responsibilities of all participants in the educational process are defined.

Personality prediction via multi-task transformer architecture combined with image aesthetics

Abstract Social media has found its path into the daily lives of people. There are several ways that users communicate in which liking and sharing images stands out. Each image shared by a user can be analyzed from aesthetic and personality traits views. In recent studies, it has been proved that personality traits impact personalized image aesthetics assessment. In this article, the same pattern was studied from a different perspective. So, we evaluated the impact of image aesthetics on personality traits to check if there is any relation between them in this form. Hence, in a two-stage architecture, we have leveraged image aesthetics to predict the personality traits of users. The first stage includes a multi-task deep learning paradigm that consists of an encoder/decoder in which the core of the network is a Swin Transformer. The second stage combines image aesthetics and personality traits with an attention mechanism for personality trait prediction. The results showed that the proposed method had achieved an average Spearman Rank Order Correlation Coefficient (SROCC) of 0.776 in image aesthetic on the Flickr-AES database and an average SROCC of 0.6730 on the PsychoFlickr database, which outperformed related SOTA (State of the Art) studies. The average accuracy performance of the first stage was boosted by 7.02 per cent in the second stage, considering the influence of image aesthetics on personality trait prediction.

Revolutionizing Wireless Networks: Cutting-edge Machine Learning Paradigms for Next Generation Connectivity

Revolutionizing Wireless Networks: Cutting-edge Machine Learning Paradigms for Next Generation Connectivity

Penerapan Model Pembelajaran Kooperatif Tipe Two Stay Two Stray untuk Meningkatkan Hasil Belajar Matematika XI IPA 3 SMAN 10 Medan

Class XI IPA 3 students at SMA Negeri 10 Medan will be using the TSTS cooperative learning paradigm to enhance their mathematical learning results. A total of thirty-two students participated in the research, which used Classroom Action Research (CAR). Conducted in two cycles, each cycle includes two sessions using the TSTS model and one session for evaluation. Data were collected through observations of teacher and student activities, as well as learning outcome tests. From the first to the second cycle, the findings demonstrate that both the teacher's and the students' actions significantly improve. During iteration two, teacher activity reached the "very good" category with an average score of 40 and a percentage of 90.90%. Student activity also improved to the "very good" category, with increased interest, attention, participation, and presentation. Student achievement significantly increased, with the average score rising from 77.34 in the first cycle to 86.56 in the second cycle. Another positive change was the increase in the percentage of students who reached mastery, which went from 65.625% to 93.75% between the two cycles. The implementation of the TSTS cooperative learning model has proven effective in enhancing student participation, interaction, and collaboration, as well as helping them better understand the subject matter.

Intrinsic structure exploitation with dual alignment for universal visual recognition

This research explores the complex yet applicable domain of universal visual recognition, where unlabeled datasets may encompass additional, as-of-yet unidentified classes and present a skewed feature distribution within labeled datasets. The primary challenge lies in concurrently distinguishing instances of known classes and uncovering new classes within the unlabeled data. This difficulty is compounded by two factors: category shift and distribution shift. Current methodologies typically overlook the potential of harnessing the inherent structural relationship between labeled and unlabeled datasets, and they fail to effectively isolate the semantic variability of the newly identified classes from the established ones. To overcome these hurdles, we introduce an innovative framework, which we have termed MESA (short for Manifold structure Exploitation with double Spaces dual Alignment), to advance the field of universal visual recognition. Our approach begins by identifying geometrically and semantically related pairs of nearest neighbors between labeled and unlabeled data, which serve as anchor points to foster an intrinsic match between the two datasets. By integrating an affinity score for similarity, we establish a novel cross-view, anchor-guided, self-supervised learning paradigm. This model is designed to spread the learned labels’ information and to conjoin novel semantic insights within the predictive space. To intensify the matching accuracy for the known classes and enhance the differentiation of novel classes, we further implement a confident-prototype-driven, self-supervised learning paradigm in a cross-view manner. This strategy is aimed at revealing the macroscopic category configuration within the embedding space. MESA employs a pioneering bidirectional dual-alignment mechanism that operates simultaneously in the embedding and prediction spaces, hence providing a more robust approach to confronting challenges brought about by distribution and category shifts. Our exhaustive evaluation across several extensive image recognition benchmarks substantiates MESA’s superior performance over the latest cutting-edge methods, marking a significant leap forward in the sphere of universal visual recognition. Finally, MESA is implemented in Python using the Pytorch machine-learning library, and it is freely available at https://github.com/aimeeyaoyao/MESA.

Analisis Kurikulum Merdeka dalam Perspektif Gender : Tinjauan Epistimologi

This research was born from the author's concerns about various cases of sexual violence and bullying in the world of education, for example there were reports of 202 students being victims of sexual violence in the school environment. With the emergence of cases like this, it is necessary to make efforts to disentangle these matters, one of which is through implementing a gender-based curriculum, so that the idea of ​​studying the independence of the curriculum from a gender perspective in epistemological observations emerged. This research aims to 1) analyze how essential it is to implement gender-based values ​​in the independent curriculum in schools, 2) how the epistemological philosophical vision responds to the independent curriculum with a gender perspective. This journal study uses library study by collecting various data sourced from books, journals, articles and certain writings, one of which is data sources related to the curriculum in Indonesia or similar references to obtain valid and actual data. After carrying out the analysis, it was found that the independent curriculum really includes the values ​​of gender equality in it, including: the independent curriculum with a differentiated approach, the P5 Project for Strengthening the Pancasila Student Profile and also in the national assessment of education reports on the Gender Equality Climate assessment. From an epistemological perspective, an independent climate from a gender perspective represents a spirit that is in line with the constructivist learning paradigm. From the results of this research, it is hoped that a curriculum with a gender perspective can be implemented on a massive scale to create a more gender-equitable educational environment.

Toward Few-Label Vertical Federated Learning

Federated Learning (FL) provides a novel paradigm for privacy-preserving machine learning, enabling multiple clients to collaborate on model training without sharing private data. To handle multi-source heterogeneous data, Vertical Federated Learning (VFL) has been extensively investigated. However, in the context of VFL, the label information tends to be kept in one authoritative client and is very limited. This poses two challenges for model training in the VFL scenario. On the one hand, a small number of labels cannot guarantee to train a well VFL model with informative network parameters, resulting in unclear boundaries for classification decisions. On the other hand, the large amount of unlabeled data is dominant and should not be discounted, and it is worthwhile to focus on how to leverage them to improve representation modeling capabilities. To address the preceding two challenges, we first introduce supervised contrastive loss to enhance the intra-class aggregation and inter-class estrangement, which is to deeply explore label information and improve the effectiveness of downstream classification tasks. Then, for unlabeled data, we introduce a pseudo-label-guided consistency mechanism to induce the classification results coherent across clients, which allows the representations learned by local networks to absorb the knowledge from other clients, and alleviates the disagreement between different clients for classification tasks. We conduct sufficient experiments on four commonly used datasets, and the experimental results demonstrate that our method is superior to the state-of-the-art methods, especially in the low-label rate scenario, and the improvement becomes more significant.

Penerapan Model Pembelajaran Kooperatif Tipe Make A Match untuk Meningkatkan Hasil Belajar Matematika Siswa

This research is motivated by low student learning outcomes caused by minimal interaction between students and lack of active participation in the learning process. As part of our endeavour to enhance classroom learning, we seek to assess how the Make a Match cooperative learning paradigm affects students' arithmetic ability. Classroom Action Research (PTK) is the methodology used. The academic year 2024–2025 saw the research team from SMA Negeri 10 Medan doing their studies, with the research subjects being class XI IPA 4 students, namely 33 students, consisting of 13 men and 20 women. The research results show an increase in learning outcomes, especially in the material Deriving Algebraic Functions. In cycle I, 20 students achieved the KKM score (≥75) and 13 students did not achieve it. In cycle II, 26 students reached the KKM and 7 students did not. There was an increase of 18.18% from 6 students who previously did not reach the KKM. This shows the effectiveness of the Make a match cooperative learning model in improving student learning outcomes.

Adaptive optimization federated learning enabled digital twins in industrial IoT

The Industrial Internet of Things (IIoT) plays a pivotal role in steering enterprises towards comprehensive digital transformation and fostering intelligent production, which serves as a critical pillar of Industry 4.0. Digital twin (DT) emerges as a highly promising technology, enabling the digital transformation of the IIoT by seamlessly bridging physical systems with digital spaces. However, the overall service quality of the IIoT is severely impacted by the resource-limited devices and the massive, heterogeneous and sensitive data in the IIoT. As an innovative distributed machine learning paradigm, federated learning (FL) inherently possesses advantages in handling private and heterogeneous data. In this paper, we propose a novel framework integrating FL with DT-enabled IIoT, termed FDEI, which combines the merits of both to improve service quality while maintaining trustworthiness. To enhance the modeling efficiency, we develop FedOA, an adaptive optimization FL method that dynamically adjusts the local update coefficient and model compression rate in resource-limited IIoT scenarios, to construct the FDEI model. Specifically, leveraging the interdependence between the two variables, we conduct a theoretical analysis of the model convergence rate and derive the associated convergence bounds. Building upon the theoretical analysis, we further propose a joint adaptive adjustment strategy by optimizing the two variables across various clients to minimize runtime differences and accelerate the convergence rate. Numerical results demonstrate that our proposed approach achieves an approximate 68% improvement in convergence speed and a reduction of approximately 66% in traffic consumption compared to the benchmarks (e.g., FedAvg, AFL, and CSFL).

Peningkatan Hasil Belajar Matematika Menggunakan Model Pembelajaran Problem Based Learning di Kelas XI IPA 1 SMAN 10 Medan

Students' poor performance in mathematics is influenced by the teacher's incompetence in designing an engaging learning environment. This study's overarching goal is to enhance the mathematical knowledge of SMA Negeri 10 Medan's IPA 1 students in the eleventh grade by using the Problem Based Learning paradigm. This study uses Classroom Action Research (PTK), a research technique that has been used in two research cycles. The four phases of research in each cycle are preparation, execution, evaluation, and reflection. In this study, 36 students (16 males and 20 females) from class XI IPA 1 of SMA Negeri 10 Medan participated. In order to gather data, we used observation and a 5-question fill-out exam. Percentage computations were used in the data analysis method. The research results showed that student learning outcomes in cycle I averaged 71.94 with classical completion at 55.55%. Meanwhile, learning outcomes in cycle II averaged 82.22 with classical completeness of 83.33%. Results show that classical learning outcomes have improved, leading us to believe that PBL (Problem Based Learning) Learning Model may help students in Science 1 of class XI at SMA Negeri 10 Medan learn more mathematics.

Development of Digital-Based Comics on National Insight Material in Class V of SD Negeri 105410 Rampah Pekan

Education is one aspect that is influenced by developments in technology, information and communication. For example, a shift in learning paradigms to accommodate advances in science and technology to increase efficiency and optimize learning. The development of the educational era indirectly requires teachers to be able to utilize technology, information and communication as media and teaching materials for learning activities. The aim of developing digital-based comic learning media is that it is considered to be able to help students understand learning material because the advantage of digital-based comic media is that it is able to present images that can arouse students' interest in learning. This type of development research uses the 4D model which was initiated by Thiagarajan (1974). This 4D development model has four stages, namely define, design, develop and desseminate, but in development research it only reaches the develop stage. The product that has been developed by this researcher has been validated by material experts getting 81.66% percentage with the criteria "very feasible", media expert validation gets 93.33% percentage with the criteria "very feasible", and language validation gets 100% percentage with the criteria " very worthy.” Based on the results of expert validation, the product that has been developed in the form of digital-based comics is suitable for students to use during the learning process.

Learning to think: Deterritorialization in Mona Lisa Smile and Dead Poets Society

Mona Lisa Smile (2003) and Dead Poets Society (1989) are two American films that made audiences across the globe reflect their learning paradigms. A rhizomatic educational ambiance helps to transform students from a state of stasis into dynamic individuals as it deterritorializes them from indoctrination by arborescent principles put forth by the ideological apparatuses of family, educational, and cultural institutions to an individual space where they can define themselves. This research paper attempts to look at Mona Lisa Smile and Dead Poets Society as visual texts that attempted to comment upon the rigidities that existed in America during the ‘Fifties’. The conclusion provides a comparison of the learning outcomes in the two sets of learners in the films selected and describes the reasons why students in Mona Lisa Smile metamorphosize into dynamic individuals committed to a definite career path.

Federated Momentum Contrastive Clustering

Self-supervised representation learning and deep clustering are mutually beneficial to learn high-quality representations and cluster data simultaneously in centralized settings. However, it is not always feasible to gather large amounts of data at a central entity, considering data privacy requirements and computational resources. Federated Learning (FL) has been developed successfully to aggregate a global model while training on distributed local data, respecting the data privacy of edge devices. However, most FL research effort focuses on supervised learning algorithms. A fully unsupervised federated clustering scheme has not been considered in the existing literature. We present federated momentum contrastive clustering (FedMCC), a generic federated clustering framework that can not only cluster data automatically but also extract discriminative representations training from distributed local data over multiple users. In FedMCC, we demonstrate a two-stage federated learning paradigm where the first stage aims to learn differentiable instance embeddings and the second stage accounts for clustering data automatically. The experimental results show that FedMCC not only achieves superior clustering performance but also outperforms several existing federated self-supervised methods for linear evaluation and semi-supervised learning tasks. Additionally, FedMCC can easily be adapted to ordinary centralized clustering through what we call momentum contrastive clustering (MCC). We show that MCC achieves state-of-the-art clustering accuracy results in certain datasets such as STL-10 and ImageNet-10. We also present a method to reduce the memory footprint of our clustering schemes.