Learning Module Research Articles

A novel intelligent fault diagnosis method for gearbox based on multi-dimensional attention denoising convolution.

In the field of intelligent fault diagnosis, particularly concerning rotating machinery, convolutional neural networks (CNNs) face significant challenges when applied to real industrial vibration data. These data are not only contaminated by various types of noise but also exhibit fault features that vary across different scales. Consequently, the effective suppression of extraneous noise and accurate extraction of multi-scale fault features are crucial issues. To address these challenges, this study proposes a novel deep neural network framework, termed the Multidimensional Fusion Residual Attention Network (MFRANet), for gearbox fault diagnosis. The MFRANet employs a multi-scale deep separable convolution module to thoroughly investigate the fundamental characteristics of the original vibration signals in both the time and time-frequency domains. To enhance the detailed analysis of diagnostic data and mitigate the risks of overfitting and noise interference, an efficient residual channel attention module is incorporated to weight and denoise the feature maps. Additionally, an external attention module is introduced to create implicit connections between the denoised multi-scale feature maps and to highlight potential correlations within the sample data, thereby improving the accuracy of fault diagnosis. Experimental evaluations on a gearbox fault dataset demonstrate that the proposed method surpasses several benchmark and state-of-the-art techniques in terms of diagnostic performance, exhibiting robust noise resilience across various noise levels. This indicates enhanced reliability and accuracy in gearbox fault diagnosis, providing an innovative and efficient solution for fault diagnosis in rotating machinery. The study underscores the contributions of artificial intelligence through the innovative structure of the method and the integration of advanced deep learning modules, while its engineering application is evidenced by addressing practical challenges in rotating machinery fault diagnosis. This work meets the urgent need for reliable diagnostic methods in industrial environments.

Combine multi-order representation learning and frame optimization learning for skeleton-based action recognition

Skeleton-based action recognition has broad application prospects in many fields such as virtual reality. Currently, the most popular way is to employ Graph Convolutional Networks (GCNs) or Hypergraph Convolutional Networks (HGCNs) for this task. However, GCN-based methods may heavily rely on the physical connectivity relationship between joints while lack the capture of higher-order information about interactions among distant joints, and HGCN-based methods usually introduce unnecessary noise when capturing low-order information of skeleton structures with simple topology. Besides, the current methods do not deal well with redundant frames and confusing frames. These limitations hinder the improvement of recognition accuracy. In this paper, we propose a novel network, called Hyper-Net, which combines multi-order representation learning and frame optimization learning for skeleton-based action recognition. Specifically, the proposed Hyper-Net contains Temporal-Channel Aggregation Graph Convolution (TCA-GC), Spatial-Temporal Aggregation Hypergraph Convolution (STA-HC) and Frame Optimization Learning (F-OL) modules. The TCA-GC aggregates low-order and local information from simple joint and bone topologies across different temporal and channel dimensions. The STA-HC captures high-order and global information from complex motion streams as well as solving the problem of spatial-temporal weight imbalance. The F-OL can adaptively extract key frames and distinguish confusing frames, thus improving the ability of the network to recognize confusing actions. A large number of experiments are conducted on the NTU RGB+D, NTU RGB+D 120 and NW-UCLA datasets for action recognition task. Experimental results demonstrate the superiority and effectiveness of the proposed network.

Scale-Aware Neural Architecture Search for Multivariate Time Series Forecasting

Multivariate time series (MTS) forecasting has attracted much attention in many intelligent applications. It is not a trivial task, as we need to consider both intra-variable dependencies and inter-variable dependencies. However, existing works are designed for specific scenarios, and require much domain knowledge and expert efforts, which is difficult to transfer between different scenarios. In this paper, we propose a scale-aware neural architecture search framework for MTS forecasting (SNAS4MTF). A multi-scale decomposition module transforms raw time series into multi-scale sub-series, which can preserve multi-scale temporal patterns. An adaptive graph learning module infers the different inter-variable dependencies under different time scales without any prior knowledge. For MTS forecasting, a search space is designed to capture both intra-variable dependencies and inter-variable dependencies at each time scale. The multi-scale decomposition, adaptive graph learning, and neural architecture search modules are jointly learned in an end-to-end framework. Extensive experiments on two real-world datasets demonstrate that SNAS4MTF achieves a promising performance compared with the state-of-the-art methods.

Dual Contrastive Learning for Cross-Domain Named Entity Recognition

Benefiting many information retrieval applications, named entity recognition (NER) has shown impressive progress. Recently, there has been a growing trend to decompose complex NER tasks into two subtasks (e.g., entity span detection (ESD) and entity type classification (ETC), to achieve better performance. Despite the remarkable success, from the perspective of representation, existing methods do not explicitly distinguish non-entities and entities, which may lead to ESD errors. Meanwhile, they do not explicitly distinguish entities with different entity types, which may lead to entity type misclassification. As such, the limited representation abilities may challenge some competitive NER methods, leading to unsatisfactory performance, especially in the low-resource setting (e.g., cross-domain NER). In light of these challenges, we propose to utilize contrastive learning to refine the original chaotic representations and learn the generalized representations for cross-domain NER. In particular, this article proposes a dual contrastive learning model (Dual-CL), which respectively utilizes a token-level contrastive learning module and a sentence-level contrastive learning module to enhance ESD, ETC for cross-domain NER. Empirical results on 10 domain pairs under two different settings show that Dual-CL achieves better performances than compared baselines in terms of several standard metrics. Moreover, we conduct detailed analyses to are presented to better understand each component’s effectiveness.

Softskill Base Arabic Language Teaching Model in Improving Talaqul Kalam for College Student in Universitas Sains Al-Quran Jawa Tengah Wonosobo

Arabic language learning has a major problem related to its renewal. Arabic language learning is always identical with grammatical (Qawa’id) aspects which seem to be rigid, complicated, and confusing. There are two major Arabic language learning orientations: as body of knowledge and mastery. The purpose of this research is to produce an Arabic language learning model based on soft skills to effectively improve the students’ Talaqah al kalaam at Universitas Sains Al-Qur’an (UNSIQ), Wonosobo, Central Java, Indonesia. This research was considered as a field study in the form of Research and Development (R&D) involving students from each faculty of Universitas Sains Al-Qur’an (UNSIQ), Wonosobo, Central Java, Indonesia. The research data were collected through observation, in-depth interview, questionnaire, test, and documentation. The collected data were then analyzed through several stages: (a) initial-product test analysis, (b) limited data trial result analysis, (c) extensive data trial result analysis, and (d) student learning response analysis. The research results showed that the Arabic language learning model based on soft skills had fulfilled the validity elements through Expert Judgment method and been considered very effective proven by the significant improvement in post-test results. This model was also proven practical proven by the test results showing that the supporting instruments, such as Course Learning Unit, Learning Module, Semester Learning Plan, Test Instrument, and Learning Implementation Sheet, were very good.

The Development Model of Educational Management for Special Classrooms of School Under The Secondary Educational Service Area Office Kalasin

Background and Aims: The creation of special classes aimed at helping students with exceptional abilities in academics and other areas reach their full potential, according to the guidelines set forth by the Ministry of Education regarding the decentralization of management and administration of education to the educational Service area office by giving schools the chance to set up special classrooms if they have the staff and finances to do so. According to projects started by the Basic Education Commission, special classrooms are spaces where educational institutions concentrate on teaching and learning activities meant to promote the potential of students with extraordinary abilities. Therefore, the objective of this research is to 1) study the components and indicators of educational management for special classrooms of schools. 2) to study the current situation, desirable condition and needs assessment of educational management for special classrooms of school under the secondary education service area office Kalasin. 3) to create a model for educational management for special classrooms of schools under the secondary education service area office Kalasin. Methodology: The research was divided into 4 phases: Phase 1 studied components and indicators of educational management for special classrooms of the school, the key informant group was 7 experts, and the research tool was an interview form. Phase 1 studied the current situation, desirable condition, and needs assessment of educational management for special classrooms of school, the sample group consisted of 358 people, research tool was a questionnaire with a reliability of .79. Data were analyzed by means and standard deviation. Phase 3 created a model for educational management for special classrooms school, The key informant group was 9 experts to create and evaluate the suitability Feasibility, and usefulness of the model and the evaluating group the manual for using the model was 15 people. The research tool was an interview form evaluation form, data were analyzed by means and standard deviation Results: 1. The components and indicators of educational management for special classrooms of school consisted of 1) management, 2) curriculum and academics, 3) environment that promotes learning, 4) personnel and budget, and 5) learner quality. 2. The overall current condition is at a high average level. The overall desirable condition was at the highest mean level. The necessary needs index was ranked from the highest to the lowest as follows: 1) curriculum and academics, 2) personnel and budget, 3) environment that promotes learning, 4) quality of learners, and 5) management. Respectively. 3. The model consists of components: 1) principles, 2) objectives, 3) content, 4) development process, and 5) measurement and evaluation. There are 4 learning modules: Module 1, Curriculum and Academic Module 2, Personnel and Budget Module 3, Environment that Promotes Learning Module 4, Quality of Learners Module 4, and Management. The model has a suitability assessment result. The model's possibility and overall usefulness were at the highest level. Conclusion: The management of special classrooms in schools currently faces various challenges and suggestions for improvement in several aspects including administration and research into developing management models for more effective governance. School administrators, teachers, parents, and students must all participate in the management process, collaborate in designing operational frameworks in various aspects, and identify areas that require expedited development within the project to achieve efficiency and effectiveness for the students. There are clear and coherent curricula aligned with students' development. There are various supplementary activities in different formats to enhance the curriculum. There is a learning management system that emphasizes both theory and practice, and there should be support systems in place to assist students with their needs and potential.

A Comprehensive Survey on Deep Clustering: Taxonomy, Challenges, and Future Directions

Clustering is a fundamental machine learning task which aims at assigning instances into groups so that similar samples belong to the same cluster while dissimilar samples belong to different clusters. Shallow clustering methods usually assume that data are collected and expressed as feature vectors within which clustering is performed. However, clustering high-dimensional data, such as images, texts, videos, and graphs, poses significant challenges for clustering tasks, such as indiscriminate representation and intricate relationships among instances. Over the past decades, deep learning has achieved remarkable success in effective representation learning and modeling complex relationships. Motivated by these advancements, Deep Clustering seeks to improve clustering outcomes through deep learning techniques, garnering considerable interest from both academia and industry. Despite many contributions to this vibrant area of research, the lack of systematic analysis and a comprehensive taxonomy has hindered progress in this field. In this survey, we first explore how deep learning can be integrated into deep clustering and identify two fundamental components: the representation learning module and the clustering module. Then we summarize and analyze the representative design of these two modules. Furthermore, we introduce a novel taxonomy of deep clustering based on how these two modules interact, specifically through multistage, generative, iterative, and simultaneous approaches. In addition, we present well-known benchmark datasets, evaluation metrics, and open-source tools to clearly demonstrate different experimental approaches. Finally, we examine the practical applications of deep clustering and propose challenging areas for future research.

A Novel Approach to Pedestrian Re-Identification in Low-Light and Zero-Shot Scenarios: Exploring Transposed Convolutional Reflectance Decoders

In recent years, pedestrian re-identification technology has made significant progress, with various neural network models performing well under normal conditions, such as good weather and adequate lighting. However, most research has overlooked extreme environments, such as rainy weather and nighttime. Additionally, the existing pedestrian re-identification datasets predominantly consist of well-lit images. Although some studies have started to address these issues by proposing methods for enhancing low-light images to restore their original features, the effectiveness of these approaches remains limited. We noted that a method based on Retinex theory designed a reflectance representation learning module aimed at restoring image features as much as possible. However, this method has so far only been applied in object detection networks. In response to this, we improved the method and applied it to pedestrian re-identification, proposing a transposed convolution reflectance decoder (TransConvRefDecoder) to better restore details in low-light images. Extensive experiments on the Market1501, CUHK03, and MSMT17 datasets demonstrated that our approach delivered superior performance.

Troubles and Sweets: Reflecting Critically on Historical Offerings for Contemporary Issues

Implementing critical reflective practice, an art education professor details the design of a preservice undergraduate-level learning module to address troubling anti-trans legislation in their state. While centering contemporary art featuring a historically significant local hero, a drag queen by the name of Sweet Evening Breeze, and resisting a didactic or progress narrative, the author reflects on power dynamics, centering joy, and the importance of partnerships in art teacher preparation.

Developing Graduate Curriculum for Digital Language Archive Stewardship

Our interdisciplinary team including information and language scholars and educators and practicing information professionals at University of North Texas (UNT) and Indiana University (IU) is developing an evidence-based practice-oriented online curriculum to train library, archives, and museums (LAM) professionals in the archiving, curation, and ethical dissemination of resources that provide the means to revitalize community memory and language. During this 2-year project, over 30 LAM students will complete the project-developed UNT graduate course INFO 5385 Community Language Archiving and Curation for Information Professionals, and additional estimated 100 students at UNT and IU will complete individual project-developed learning modules integrated into other courses. Development of the learning materials is informed by digital language archive practices, research, and existing training materials for archive depositors. Resulting open-access adaptable learning resources are expected to be widely used by academic programs and educators for training LAM students and by participatory archives as continuing education resources.

Batch channel normalized-CWGAN with Swin Transformer for imbalanced data fault diagnosis of rotating machinery

Abstract In real scenarios, rotating machinery is mainly operated in optimal condition, leading to fault data scarce and difficult to collect. This issue results in imbalanced data, significantly limiting the effectiveness of intelligent fault diagnosis methods. To address this issue, a novel fault diagnosis method for rotating machinery is proposed in this paper, which combines the batch channel normalized conditional wasserstein generative adversarial network (BCN-CWGAN) with Swin Transformer. Firstly, the one-dimensional vibration signal is preprocessed into two-dimensional feature images using a symmetrized dot pattern (SDP). Subsequently, self-attention mechanism and deep feature learning module constructed by DenseNet are integrated into the generator of GAN to acquire more discriminative feature information. Meanwhile, the discriminator of GAN is combined with batch channel normalization strategy, which further enhances the generalization ability. Besides, a two time-scale update rule strategy enhances training stability and convergence speed by updating model parameters at different time scales. Then, the data augmentation capability of BCN-CWGAN is used to generate high-quality fault samples to augment the imbalanced dataset. Finally, Swin Transformer is combined to achieve accurate fault diagnosis. The performance enhancement of the proposed method is verified through comparison and diagnosis results of two engineering experiments, demonstrating its substantial value for research in engineering practice. With the proposed data augmentation method, the average accuracy of A1, B1, C1, and D1 datasets in experiment 1 reached 99.24%, 98.85%, 96.78%, and 96.04%, respectively. Meanwhile, the proposed method achieved the best accuracy in experiment 2.

Promoting Machine Abilities of Discovering and Utilizing Knowledge in a Unified Zero-shot Learning Paradigm

Knowledge discovery and utilization are two essential cognitive processes that enable humans to understand the world and extract new insights from their surroundings. These processes have motivated machine learning studies, particularly zero-shot learning (ZS), which seeks to identify unseen concepts through the use of side information. Previous ZS studies primarily focused on utilizing existing knowledge to infer unseen events, yet they overlook the crucial process of knowledge discovery and the integrated modeling of these knowledge-aware processes. In this study, we present a comprehensive ZS learning approach that explores and evaluates the machine's abilities of discovering and utilizing knowledge. More specifically, to emulate human-like knowledge discovery and utilization processes, we propose a novel visual-aware ZS knowledge graph completion task for evaluation, incorporating a traditional ZS image classification task. Technically, we develop a unified ZS learning paradigm named Cognitive Learner (CoLa) to foster the two knowledge-aware abilities. Including a knowledge representation learning (KRL) module and a knowledge adaptation (KA) module, CoLa adapts well to the two specified tasks with the corresponding data. Extensive experiments on large-scale datasets demonstrate CoLa models’ outstanding performance over compared methods in the two ZS tasks, illustrating their superior ability of discovering and utilizing knowledge.

Multi-Task Diffusion Learning for Time Series Classification

Current deep learning models for time series often face challenges with generalizability in scenarios characterized by limited samples or inadequately labeled data. By tapping into the robust generative capabilities of diffusion models, which have shown success in computer vision and natural language processing, we see potential for improving the adaptability of deep learning models. However, the specific application of diffusion models in generating samples for time series classification tasks remains underexplored. To bridge this gap, we introduce the MDGPS model, which incorporates multi-task diffusion learning and gradient-free patch search (MDGPS). Our methodology aims to bolster the generalizability of time series classification models confronted with restricted labeled samples. The multi-task diffusion learning module integrates frequency-domain classification with random masked patches diffusion learning, leveraging frequency-domain feature representations and patch observation distributions to improve the discriminative properties of generated samples. Furthermore, a gradient-free patch search module, utilizing the particle swarm optimization algorithm, refines time series for specific samples through a pre-trained multi-task diffusion model. This process aims to reduce classification errors caused by random patch masking. The experimental results on four time series datasets show that the proposed MDGPS model consistently surpasses other methods, achieving the highest classification accuracy and F1-score across all datasets: 95.81%, 87.64%, 82.31%, and 100% in accuracy; and 95.21%, 82.32%, 78.57%, and 100% in F1-Score for Epilepsy, FD-B, Gesture, and EMG, respectively. In addition, evaluations in a reinforcement learning scenario confirm MDGPS’s superior performance. Ablation and visualization experiments further validate the effectiveness of its individual components.

Spike-based computational primitives to reproduce neural dynamics in the parietal cortex during motor preparation

Abstract Biologically plausible spiking neural network models of sensory cortices can be instrumental in understanding and validating their principles of computation.
 Models based on Cortical Computational Primitives (CCPs), such as Hebbian plasticity and Winner-Take-All (WTA) networks, have already been successful in this approach.
 However, the specific nature and roles of CCPs in sensorimotor cortices during cognitive tasks are yet to be fully deciphered.
 The evolution of motor intention in the Posterior Parietal Cortex (PPC) before arm-reaching movements is a well-suited cognitive process to assess the effectiveness of different CCPs.
 To this end, we propose a biologically plausible model composed of heterogeneous spiking neurons which implements and combines multiple CCPs, such as multi-timescale learning and soft WTA modules.
 By training the model to replicate the dynamics of in-vivo recordings from non-human primates, we show how it is effective in generating meaningful representations from unbalanced input data, and in faithfully reproducing the transition from motor planning to action selection.
 Our findings elucidate the importance of distributing spike-based plasticity across multi-timescales, and provide an explanation for the role of different CCPs in models of frontoparietal cortical networks for performing multisensory integration to efficiently inform action execution.

Ecopedagogy and Environmental Literacy in Research Trends in Indonesia

This study analyzes the trend and development of eco-pedagogy literacy in Indonesia from 2016 to 2024. The method used was a Systematic Literature Review (SLR) with the PRISMA protocol, analyzing 27 articles that met the inclusion criteria. The results of this study showed 1) a significant increase in the number of publications related to eco pedagogy literacy, especially publications in 2023, 2) Qualitative research with high school students as subjects and questionnaires as research tools are often used, 3) Problem-Based Learning (PBL) and Contextual Learning (CL) are the most common learning strategies applied in eco pedagogy. In addition, environmental awareness is the theme most often associated with ecopedagogy literacy in Indonesia. The study also revealed that the Research and Development (RnD) approach is rarely applied, so there are opportunities for developing innovative learning modules and educational media that are more interactive in introducing eco-pedagogy. This research contributes to understanding how environmental education can be strengthened through eco pedagogy and encourages further research that focuses on using technology in learning to improve environmental literacy. As such, the findings are highly relevant to supporting the development of more sustainable education programs in Indonesia.

Multi-objective topological design considering functionally graded materials and coated fiber reinforcement

This study presents a multi-objective topology optimization method tailored to structures fabricated from functionally graded materials (FGMs), coated FGMs, and coated fiber-reinforced composite materials (FRCMs) with fixed fiber thickness. The design objective is the simultaneous minimization of elastic and thermal compliance. The material properties of these composite materials were derived to generate datasets using the representative volume element method under periodic boundary conditions. Subsequently, machine learning modules were developed based on the datasets to combine with the design process. The multi-objective optimization problem was addressed using the weighted sum method ensuring the generation of the Pareto front. The adaptive weighting strategy is employed to avoid biased results toward a single objective function. To define the coated boundaries within the design domain, image post-processing techniques such as convolution filters, interpolation schemes, and erosion methods were employed on the material layout information of the optimized FGM structures. Through numerical examples, optimized material layouts for coated assemblies incorporating FGMs and FRCMs are presented, with the performance verified through objective function values.

Teaching student-driven modules in macroeconomics classes

The authors of this article describe three student-driven learning modules developed from their respective College Fed Challenge courses. These activities are ready-to-apply in a wide range of courses to facilitate adoption without a large time commitment. In the Pick a Policy Maker module, students gain an understanding of the diversity of policy makers by learning about the careers and views of various officials. In the Major Debates on Monetary Policy module, student groups select debates, create original charts, conduct academic research, and present their findings. In the Fun with FRED module, students learn how to work with the FRED interactive graphing tools in the FRED dashboard to analyze current and past macroeconomic data. Through these modules, students develop research, presentation, data analytics, and teamwork skills.

Development of a virtual teaching module for advanced semiconductor fabrication and its learning effectiveness analysis

AbstractSemiconductor fabrication is the process of manufacturing semiconductor devices, typically integrated circuits (ICs) such as microprocessors and memory. This involves transferring circuit diagrams onto a silicon wafer using photomasks and photoresists. After a series of fabrication processes, ICs are created on the wafer surface and then diced into individual chips, which are packaged and tested with quality control procedures to become the final products. Virtual reality (VR) simulates imaginary experiences or environments difficult to achieve in the real world through human senses and immersive equipment, allowing users to interact in a virtual 3D space in real time, making it well suited for applications in science education and industrial training. This study transforms the essential knowledge of advanced semiconductor manufacturing processes into an easily understandable virtual teaching module, thereby creating educational resources for high school and college students. The objective is to enhance their scientific and technological literacy, yielding substantial benefits for the general public. This study utilized VR technology to simplify and clarify the knowledge about the semiconductor manufacturing process, making it more engaging for learners. The virtual teaching module's learning content includes an overview of wafer preparation, semiconductor fabrication, chip packaging, and IC testing. Users can interact with the virtual teaching module and conduct virtual experiments to enhance their understanding by trial and error. Experimental results show that it can improve students' learning achievement and learning motivation. Therefore, the virtual teaching module is suitable for high‐school students and the general public to understand semiconductor technology and its applications. The effectiveness of the virtual teaching module is heavily dependent on the availability and quality of VR hardware and software. Limited access to advanced VR equipment or technical issues could have affected the learning experience, thereby influencing the learning outcomes.

Cloud detection for HY-1C/COCTS over the ocean based on spectral-and-textural-information-guided deep neural network

AbstractGiven that clouds can absorb and scatter radiation signals in the visible and infrared bands, cloud detection is a key preprocessing step for ocean color and sea surface temperature retrievals. In this research, a Spectral-and-Textural-Information-Guided deep neural Network (STIGNet) is designed for cloud detection in global ocean data from the Haiyang-1C (HY-1C)/Chinese Ocean Color and Temperature Scanner (COCTS). Considering the spectral and textural properties of clouds, the model incorporates HY-1C/COCTS spectral data, differences in brightness temperature (BT), local statistical characteristics of BT, and geographical location information–all of which are closely related to cloud features. Notably, an edge learning module is implemented to emphasize edge features during the training process. We construct a HY-1C/COCTS cloud detection dataset to train and test the cloud detection model. In the dataset, labels are generated by combining the Bayesian cloud detection method with a manual mask. Analysis of the resulting cloud detection images indicates that STIGNet exhibits accurate performance across various types of clouds while showing minimal overestimated errors in areas such as ocean fronts or sun glints, where they tend to occur frequently. The ablation experiments performed on physical-based input features and edge learning modules show enhancements in cloud detection accuracy. Evaluation results demonstrate an overall accuracy of 96.64%, with a cloud overestimated error of 1.61% and a cloud missed error of 1.76%. These findings highlight the effectiveness of STIGNet in generating precise cloud masks for HY-1C/COCTS data.

ASCL: Accelerating semi‐supervised learning via contrastive learning

SummarySSL (semi‐supervised learning) is widely used in machine learning, which leverages labeled and unlabeled data to improve model performance. SSL aims to optimize class mutual information, but noisy pseudo‐labels introduce false class information due to the scarcity of labels. Therefore, these algorithms often need significant training time to refine pseudo‐labels for performance improvement iteratively. To tackle this challenge, we propose a novel plug‐and‐play method named Accelerating semi‐supervised learning via contrastive learning (ASCL). This method combines contrastive learning with uncertainty‐based selection for performance improvement and accelerates the convergence of SSL algorithms. Contrastive learning initially emphasizes the mutual information between samples as a means to decrease dependence on pseudo‐labels. Subsequently, it gradually turns to maximizing the mutual information between classes, aligning with the objective of semi‐supervised learning. Uncertainty‐based selection provides a robust mechanism for acquiring pseudo‐labels. The combination of the contrastive learning module and the uncertainty‐based selection module forms a virtuous cycle to improve the performance of the proposed model. Extensive experiments demonstrate that ASCL outperforms state‐of‐the‐art methods in terms of both convergence efficiency and performance. In the experimental scenario where only one label is assigned per class in the CIFAR‐10 dataset, the application of ASCL to Pseudo‐label, UDA (unsupervised data augmentation for consistency training), and Fixmatch benefits substantial improvements in classification accuracy. Specifically, the results demonstrate notable improvements in respect of 16.32%, 6.9%, and 24.43% when compared to the original outcomes. Moreover, the required training time is reduced by almost 50%.