Class Activities Research Articles

A modified deep learning method for Alzheimer’s disease detection based on the facial submicroscopic features in mice

Alzheimer’s disease (AD) is a chronic disease among people aged 65 and older. As the aging population continues to grow at a rapid pace, AD has emerged as a pressing public health issue globally. Early detection of the disease is important, because increasing evidence has illustrated that early diagnosis holds the key to effective treatment of AD. In this work, we developed and refined a multi-layer cyclic Residual convolutional neural network model, specifically tailored to identify AD-related submicroscopic characteristics in the facial images of mice. Our experiments involved classifying the mice into two distinct groups: a normal control group and an AD group. Compared with the other deep learning models, the proposed model achieved a better detection performance in the dataset of the mouse experiment. The accuracy, sensitivity, specificity and precision for AD identification with our proposed model were as high as 99.78%, 100%, 99.65% and 99.44%, respectively. Moreover, the heat maps of AD correlation in the facial images of the mice were acquired with the class activation mapping algorithm. It was proven that the facial images contained AD-related submicroscopic features. Consequently, through our mouse experiments, we validated the feasibility and accuracy of utilizing a facial image-based deep learning model for AD identification. Therefore, the present study suggests the potential of using facial images for AD detection in humans through deep learning-based methods.

Social media in the linguistic classroom: Discussing appreciation vs. appropriation

In our paper, we focus on integrating topics directly relevant to students’ lives, a principle we consistently strive to embody in our pedagogical approach. Specifically, we explore the dynamics of appreciation and appropriation within the music industry, inspired by Garza’s (2021) work, as a leading topic for a module of a linguistic course. Through the implementation of in-class discussion activities, we utilized platforms such as TikTok, YouTube and Twitter (currently X), to center the modality and the topics that are of high importance for students and their lived experiences. Our paper highlights the benefits of effectively engaging students with topics that are related to their experiences and through the use of technology. By adapting and refining the curriculum based on student interests, we aim to promote equity, diversity, and inclusion within linguistics classrooms.

A Multi-label Artificial Intelligence Approach for Improving Breast Cancer Detection With Mammographic Image Analysis.

Breast cancer remains a major global health concern. This study aimed to develop a deep-learning-based artificial intelligence (AI) model that predicts the malignancy of mammographic lesions and reduces unnecessary biopsies in patients with breast cancer. In this retrospective study, we used deep-learning-based AI to predict whether lesions in mammographic images are malignant. The AI model learned the malignancy as well as margins and shapes of mass lesions through multi-label training, similar to the diagnostic process of a radiologist. We used the Curated Breast Imaging Subset of Digital Database for Screening Mammography. This dataset includes annotations for mass lesions, and we developed an algorithm to determine the exact location of the lesions for accurate classification. A multi-label classification approach enabled the model to recognize malignancy and lesion attributes. Our multi-label classification model, trained on both lesion shape and margin, demonstrated superior performance compared with models trained solely on malignancy. Gradient-weighted class activation mapping analysis revealed that by considering the margin and shape, the model assigned higher importance to border areas and analyzed pixels more uniformly when classifying malignant lesions. This approach improved diagnostic accuracy, particularly in challenging cases, such as American College of Radiology Breast Imaging-Reporting and Data System categories 3 and 4, where the breast density exceeded 50%. This study highlights the potential of AI in improving the diagnosis of breast cancer. By integrating advanced techniques and modern neural network designs, we developed an AI model with enhanced accuracy for mammographic image analysis.

Increasing Student Learning Activeness by Using Puzzle Media in Learning Pancasila Education at SMPN 38 Palembang

This research was motivated by the problem of low learning activeness of class VIII students in junior high schools. Students look passive, lack self-confidence, and show low learning motivation in the learning process. This research aims to increase students' learning activeness through the use of crossword puzzle and word search puzzle media in learning Pancasila Education class VIII.6 at SMP Negeri 38 Palembang. This research was carried out using the classroom action research method which was carried out over 2 cycles where each cycle consisted of 1 meeting and 1 assessment which consisted of 4 stages, namely: planning, action, reflection and evaluation. The subjects in this research were all students in class VIII.6 of SMP Negeri 38 Palembang, consisting of 15 male students and 17 female students. This research was conducted using a quantitative approach with observational data collection techniques. Observations were carried out by observing observers whose results were analyzed using percentage descriptive data analysis techniques. This research shows that the use of crossword puzzle and word search puzzle media in learning can increase the learning activity of class VIII.6 students at SMP Negeri 38 Palembang. This can be seen from the observation results obtained in the pre-cycle which show that students' learning activeness has a percentage of 49.78%, then in cycle 1 it increased by 24.66% to 74.44%, and in cycle 2 it increased by 14.40% to 88.84%. This shows that the use of crossword puzzle and word search puzzle media in learning can increase the learning activity of students in class VIII.6 SMPN 38 Palembang.

An interpretable deep learning model for detecting BRCA pathogenic variants of breast cancer from hematoxylin and eosin-stained pathological images.

Determining the status of breast cancer susceptibility genes (BRCA) is crucial for guiding breast cancer treatment. Nevertheless, the need for BRCA genetic testing among breast cancer patients remains unmet due to high costs and limited resources. This study aimed to develop a Bi-directional Self-Attention Multiple Instance Learning (BiAMIL) algorithm to detect BRCA status from hematoxylin and eosin (H&E) pathological images. A total of 319 histopathological slides from 254 breast cancer patients were included, comprising two dependent cohorts. Following image pre-processing, 633,484 tumor tiles from the training dataset were employed to train the self-developed deep-learning model. The performance of the network was evaluated in the internal and external test sets. BiAMIL achieved AUC values of 0.819 (95% CI [0.673-0.965]) in the internal test set, and 0.817 (95% CI [0.712-0.923]) in the external test set. To explore the relationship between BRCA status and interpretable morphological features in pathological images, we utilized Class Activation Mapping (CAM) technique and cluster analysis to investigate the connections between BRCA gene mutation status and tissue and cell features. Significantly, we observed that tumor-infiltrating lymphocytes and the morphological characteristics of tumor cells appeared to be potential features associated with BRCA status. An interpretable deep neural network model based on the attention mechanism was developed to predict the BRCA status in breast cancer. Keywords: Breast cancer, BRCA, deep learning, self-attention, interpretability.

Identifying heart failure dynamics using multi-point electrocardiograms and deep learning

Abstract Background Heart failure (HF) hospitalizations are related to poor survival outcomes, emphasizing the need for early detection and intervention. Recent studies have reported the potential of deep learning algorithms in identifying heart failure through electrocardiogram (ECG) with notable accuracy. However, evidence supporting their utility in the ongoing monitoring and follow-up of HF patients remains uncertain. Advanced diagnostic tools that can effectively track heart failure progression or improvement over time are needed. Purpose To address this challenge, we developed a deep learning model analyzing 12-lead ECG waveforms at two time points, aiming to detect HF deterioration or improvement, potentially revolutionizing HF management. Methods This study analyzed 32,045 ECGs from 6,892 unique adult patients (aged 18 years and older) visiting the Department of Cardiology at Kobe University Hospital. The participants were randomly assigned to training (4,284 patients), validation (1,034 patients), and test (1,034 patients) datasets. ElecTransformer was developed to classify HF status into deteriorated, improved, and no change classes based on ECG waveform signals at two different time points and to estimate brain natriuretic peptide (BNP) levels. Performance metrics, such as the area under the receiver operating characteristic curve (AUROC) and accuracy, were calculated, and attention mapping via gradient-weighted class activation mapping was utilized to interpret the model's decision-making ability. Results The patients had an average age of 65 years (±15.4 years) and BNP levels averaged 71.5 pg/mL (25.8 to 185.2 pg/mL). For HF status classification, ElecTransformer achieved an AUROC of 0.845 and an accuracy of 0.821, improving to an AUROC of 0.885 and an accuracy of 0.833 with baseline BNP integration. The ElecTransformer accurately estimated BNP levels from ECG data, evidenced by a correlation coefficient of 0.798. Averaged attention mapping showed that the QRS complex was the most important feature for determining model outputs with lesser effects seen for P waves and T waves variance Conclusions Harnessing a Transformer-based deep learning model to analyze multiple ECGs markedly improves the accuracy in detecting changes in heart failure status. This method offers a valuable non-invasive option for monitoring heart failure progression, potentially leading to better patient management and earlier intervention in heart failure treatment.Architecture and Performance of ModelsAveraged attention mapping

Efficient and Compressed Deep Learning Model for Brain Tumour Classification With Explainable AI for Smart Healthcare and Information Communication Systems

ABSTRACTThe detection of brain tumours presents a significant challenge in the medical domain, where prompt and precise diagnosis is crucial as patient outcomes depend on it. Conventional deep neural networks perform well in carrying out various imaging tasks within the healthcare sector; however, their effectiveness often falls short of expectations in practical applications due to the substantial computational resources required and issues with reliability. In this research, an optimised and effective deep learning model founded on the DenseNet‐169 architecture is introduced for the classification of magnetic resonance imaging brain tumours, which is particularly advantageous for smart healthcare systems and information and communication technology (ICT) settings with limited computational capabilities. The model compression methodologies, including pruning and quantization, have been employed to significantly diminish the dimensions and intricacy of the model while achieving a classification accuracy of 97.07%. Furthermore, this endeavour necessitates the enhancement of the model's interpretability through the utilisation of explainable artificial intelligence methodologies such as Gradient‐weighted Class Activation Mapping (Grad‐CAM) and SHapley Additive exPlanations (SHAP), which will aid clinicians in highlighting crucial areas of the images and validating feature importance concerning the decisions rendered by the model. A comparative performance evaluation is conducted against DenseNet‐169, ResNet‐50 and various other models to delineate the superior efficacy of our model, rendering it exceptionally adept for knowledge‐driven, real‐time brain tumour diagnosis within smart healthcare and ICT systems where resources are constrained.

Enhancing instructional design learning: a comparative study of scaffolding by a 5E instructional model-informed artificial intelligence chatbot and a human teacher

ABSTRACT To address the limitations of general-purpose artificial intelligence (AI) tools, we developed a task-oriented AI chatbot based on the 5E (i.e. “engage”, “explore”, “explain”, “elaborate” and “evaluate”) model to scaffold students’ instructional design process. We examined the impact of integrating the 5E instructional model-informed AI chatbot on students’ learning performance and perceptions. The results indicated that the AI chatbot, when combined with human teacher scaffolding, significantly improved the students’ instructional design performance relative to receiving human teacher scaffolding only. The chatbot provided valuable suggestions on instructional design frameworks, class activities and teaching topics during the “explore” phase. In the “evaluate” phase, the chatbot offered immediate feedback on the students’ design plans and proposed alternative instructional frameworks regarding areas for improvement. However, the students expressed concerns about the chatbot’s evaluation quality, noting that it needed to be better aligned with the course assessment rubric. We recommend using AI chatbots for instructional design conceptualisation, although we emphasise the critical role of human teachers in evaluating final design work and providing timely support.

Exploring multiple optimization algorithms in transfer learning with EfficientNet models for agricultural insect classification

Dangerous insects are a significant risk to the global agricultural industry, threatening food security, economic stability, and crop quality. This study investigates the impact of multiple optimization algorithms within transfer learning, employing EfficientNet models for the classification of agricultural insects. The explored optimization algorithms include Adam, Adamax, AdamW, RMSprop, and SGD, while utilizing the EfficientNetB0, EfficientNetB3, EfficientNetB5, and EfficientNetB7 architectures. Experimental results show notable performance differences between optimization algorithms across all EfficiencyNet models in the study. Among the measured metrics are precision, recall, f1-score, accuracy, and loss, the AdamW optimizer consistently demonstrates superior performance compared to other algorithms. The findings underscore the critical influence of optimization algorithms in enhancing classification accuracy and convergence within transfer learning scenarios. Additionally, the study employs various visualization techniques, such as Gradient-weighted Class Activation Mapping (Grad-CAM) to enhance the interpretation of the image classification model’s results. By focusing on these methodologies, this research aims to improve the model’s performance, optimize its capabilities, and ultimately contribute to effective pest management strategies in agriculture, safeguarding crop yields, farmer livelihoods, and global food security.

Fatigue life prediction of composite materials using strain distribution images and a deep convolution neural network

The damage process of composite materials, such as short fiber-reinforced plastics (SFRP), is complex. Therefore, it is necessary to accurately represent the damage process in fatigue life prediction. Herein, fatigue life prediction was conducted by combining the digital image correlation method, which is a non-destructive testing technique, with a convolutional neural network (CNN), using Xception as the network architecture. High prediction accuracy was obtained when training and testing were performed on the same SFRP specimens. In contrast, using different specimens for training and testing resulted in lower accuracy. This issue may be improved by increasing the number of specimens. The regions of interest in the model were visualized by Gradient-weighted Class Activation Mapping. Notably, the model indicated the breaking point as the region of interest from the early stages of the test. The breaking point was identified at an earlier stage by the CNN than by visual inspection, demonstrating the potential for a new method of damage observation.

Development of Interactive Learning Media Based on Learning Management System in Class X English Learning at SMAN 1 Gunungputri

This research aims to develop, test the feasibility, and measure the effectiveness of developing interactive learning media based on the Learning Management System in class X English subjects at SMAN 1 Gunungputri. This research uses the ADDIE development model. To test feasibility, researchers used validation from media experts, learning design experts and material experts and considered the results of user responses, namely teachers and students. The feasibility test results obtained from media experts were 74%, instructional design experts were 85%, material expert tests were 98%, teacher users were 92%, small group tests were 95% and large group tests were 97%. These results indicate that the use of interactive learning media is suitable to support the process of English learning activities in class X at SMAN 1 Gunungputri. Data analysis of pre-test and post-test scores showed that the average pre-test score of students was 55 and the average post-test score was 89. The results of effectiveness testing using the N-Gain test showed a result of 0.8, which is at “Effective” category. So, it is concluded that the use of interactive media based on the Learning Management System is effective in improving the learning outcomes of class X students at SMAN 1 Gunungputri.

Flipped Classroom Trial for Python Programming with Raspberry Pi Using Moodle

A flipped classroom is a pedagogical method that flips traditional lectures and homework. In the case of a flipped classroom, the traditional lecture is viewed at home before class and homework activities are completed in the classroom with the tutor present to guide students in their work. At present, the above-mentioned flipped classroom has become increasingly popular, and sometimes controversial, within higher education. In this paper, we describe the flipped classroom example for Python programming to control I/O devices with Raspberry Pi. First, the tutor uploads the lecture notes onto Moodle. Secondly, students read the lecture notes prior to the class. Students can then ask questions on the Moodle Forum if there are any questions about the class notes. Thirdly, the students attend the class. As part of the class activities, students form into 10 groups. Each group creates a Python programme based on topics related to the class note, one hour is permitted for this activity. This is an example of a group activity. Next, each group will demonstrate the Python programme they have created to the tutor and other students in a 5-minute presentation. Following this, the tutor and other students will provide comments on the demonstration. Students will then complete a self-reflection journal about the flipped classroom on Moodle after the class. The tutor evaluates each journal written by the students. In this paper, a description of the Python programmes aims to control 8 LEDs is given as an example of a flipped classroom. Finally, the tutor added a questionnaire about the flipped classroom onto Moodle at the end of the semester. Collated questionnaire responses show that students felt the flipped classroom was appealing and helped improve programming skill. Thus, the author concludes that the flipped classroom is engaging and an effective way of teaching.

Longitudinal Effects of Moderate to Vigorous Physical Activity in Physical Education Classes on Attention and Academic Achievement

Previous studies showed moderate to vigorous physical activity (MVPA) and aerobic fitness in adolescents are significant factors for cognitive and academic performance. Most previous studies have employed a cross-sectional design; consequently, the evidence on the longitudinal effect of physical education classes (PECs) on cognitive performance and academic achievement is limited. Therefore, the current study utilized a longitudinal design to examine the longstanding effect of MVPA during PECs on cognitive and academic performance across gender groups. Structural equation modeling analyses were employed to understand how MVPA influences youth academic achievement in a nationally representative sample (n = 2092). Study findings indicated that (a) MVPA exerted a direct effect on initial academic achievement as well as an indirect effect, which is mediated by middle school students’ attention in both gender groups; (b) MVPA had both long-term direct effects on academic achievement as well as indirect effects on attention, which ultimately affected the subsequent academic achievements of female middle school students.

Loss of a single Zn finger, but not that of two Zn fingers, of GATA3 drives skin inflammation.

Transcription factor GATA3 is essential for the developmental processes of T cells. Recently, the silencer of a cytokine IFNγ gene was identified, the inhibitory activity of which requires GATA3. GATA3 has 2 Zn fingers and the commonly used GATA3 deficient mice lack both fingers (D2). We have established a mouse line that lacks only one Zn finger close to the C terminus (D1). The D1 mice line developed dermatitis, which was not observed in D2 mice. The expression of S100a8/S100a9 was elevated in D1 to a level higher than in D2, suggesting their roles in dermatitis development. CD8 T cells of both D1 and D2 lines expressed inhibitory receptors associated with the exhausted state. In the absence of MHC class II, the skin inflammation was exacerbated in both lines. The gene expression pattern of CD8 T cells became similar to that of effector T cells. Blocking Ab against LAG3 upregulated the expression of the effector molecules of T cells. These results suggest that the disfunction of GATA3 can lead to the spontaneous activation of CD8 T cells that causes skin inflammation, and that suppressive activity of MHC class II - LAG3 interaction ameliorates dermatitis development.

MaskAppendix: Backbone-Enriched Mask R-CNN Based on Grad-CAM for Automatic Appendix Segmentation

Background: A leading cause of emergency abdominal surgery, appendicitis is a common condition affecting millions of people worldwide. Automatic and accurate segmentation of the appendix from medical imaging is a challenging task, due to its small size, variability in shape, and proximity to other anatomical structures. Methods: In this study, we propose a backbone-enriched Mask R-CNN architecture (MaskAppendix) on the Detectron platform, enhanced with Gradient-weighted Class Activation Mapping (Grad-CAM), for precise appendix segmentation on computed tomography (CT) scans. In the proposed MaskAppendix deep learning model, ResNet101 network is used as the backbone. By integrating Grad-CAM into the MaskAppendix network, our model improves feature localization, allowing it to better capture subtle variations in appendix morphology. Results: We conduct extensive experiments on a dataset of abdominal CT scans, demonstrating that our method achieves state-of-the-art performance in appendix segmentation, outperforming traditional segmentation techniques in terms of both accuracy and robustness. In the automatic segmentation of the appendix region in CT slices, a DSC score of 87.17% was achieved with the proposed approach, and the results obtained have the potential to improve clinical diagnostic accuracy. Conclusions: This framework provides an effective tool for aiding clinicians in the diagnosis of appendicitis and other related conditions, reducing the potential for diagnostic errors and enhancing clinical workflow efficiency.

An One-step Triple Enhanced weakly supervised semantic segmentation using image-level labels.

Weakly supervised semantic segmentation, based on image-level labels, abandons the pixel-level labels relied upon by traditional semantic segmentation algorithms. It only utilizes images as supervision information, thereby reducing the time cost and human resources required for marking pixel data. The prevailing approach in weakly supervised segmentation involves two-step method, introducing an additional network and numerous parameters, thereby complicating the model structure. Furthermore, image-level labels typically furnishes only category information for the entire image, lacking specific location details and accurate target boundaries during model training. We propose an innovative One-Step Triple Enhanced weakly supervised semantic segmentation network(OSTE). OSTE streamlines the model structure, which can accomplish both pseudo-labels generation and semantic segmentation tasks in just one step. Furthermore, we augment the weakly supervised semantic segmentation network in three key aspects based on the class activation map construction method, thereby enhancing segmentation accuracy: Firstly, by integrating local information from the activation map with the image, we can enhance the network's localization and expansion capabilities to obtain more accurate and rich location information. Then, we refine the seed areas of the class activation map by exploiting the correlation between multi-level feature. Finally, we incorporate conditional random field theory to generate pseudo-labels with higher confidence and richer boundary information. In comparison to the prevailing two-step weakly supervised semantic segmentation schemes, the segmentation network proposed in this paper achieves a more competitive mean Intersection over Union (mIoU) score of 58.47% on Pascal VOC. Additionally, it enhances the mIoU score by at least 5.03% when compared to existing end-to-end schemes.

Mango leaf disease diagnosis using Total Variation Filter Based Variational Mode Decomposition

Mango leaf diseases significantly threaten mango cultivation, impacting both yield and quality. Accurate and early diagnosis is essential for effectively managing and controlling these diseases. This study introduces a novel approach for diagnosing mango leaf diseases, leveraging Total Variation Filter-based Variational Mode Decomposition. The proposed method enhances the extraction of disease-specific features from leaf images by decomposing them into intrinsic mode functions while simultaneously reducing noise and preserving important edge information. Experimental results demonstrate that the proposed method effectively isolates relevant patterns associated with various mango leaf diseases, improving diagnostic accuracy compared to traditional methods. Deep learning models, DenseNet121 and VGG-19, are used for feature extraction from sub-band images, and extracted features are concatenated and fed to Random Forest for classification. Utilizing tenfold cross-validation, our model demonstrated enhanced classification accuracy (98.85 %), specificity (99.37 %), and sensitivity (98.0 %) in detecting diseases from Mango leaf images. Feature maps and Gradient-weighted Class Activation Mapping analysis was conducted to visualize and scrutinize the essential regions crucial for accurate predictions. Statistical analysis indicates that our proposed architecture outperforms pre-trained models and existing mango leaf disease detection methods. This diagnostic approach can be a rapid disease detection tool for imaging specialists utilizing leaf images. The robustness and efficiency of the presented work in handling complex and noisy image data make it a promising tool for automated agricultural disease diagnosis systems, facilitating timely and precise interventions in mango orchards.

Enhancing the learning experience by empowering medical students to co-create learning tools and classroom activities.

This study aimed to enhance the learning experience among medical students by empowering them to co-create learning tools and classroom activities. A cross-sectional study was conducted with 10 participants from Year 2 of the new curriculum volunteering to participate in this study. Five were selected based on their diversities and empowered to design learning tools and class activities. Student satisfaction was presented as mean scores. A comparison of self-confidence scores in subjects learned before and after the class was analyzed using the paired t-test. Comparisons of multiple-choice question (MCQ) scores before and after the class between Years 2 (n = 96) and Year 3 of the previous curriculum attending inclass teaching (n = 98) were analyzed using the independent sample t-test. A high level of satisfaction (M=87.5, SD=15.7%) and significant improvements in student self-confidence in subjects learned between before (M=46.4, SD=20.8%) and after (M=82.7, SD=16.9%) the class were noted (t (223) = -23.73, p<.001). Additionally, Year 2 students achieved significantly higher MCQ scores after the class (M=85.6, SD=19.0%) compared with the scores from Year 3 (M=77.3, SD=23.6%) (t (190) = 3.32, p<.001). Empowering medical students to co-create learning tools and class activities could positively enhance their learning experience. The result of this study addressed the importance of student empowerment with well-designed student-centered learning strategies based on their learning environment. Additional qualitative research is required to better understanding the "why" and "how" behind the findings of this study.

Training learners to use Quizlet vocabulary activities on mobile phones in Vietnam with Facebook

Mobile phone ownership among university students in Vietnam has reached almost 100%, exceeding that of Internet-capable desktop computers. This has made them increasingly popular to allow learners to carry out learning activities outside of the classroom, but some studies have suggested that learners are not always willing to engage in activities outside of the classroom (Kim et al., 2013). Recent research has suggested that providing training to learners that includes not only how but also why activities are important can improve learner engagement in mobile-based activities (Stockwell &amp; Hubbard, 2014). In this paper, Vietnamese learners of English engaged in vocabulary and grammar tasks using the Quizlet app on their mobile phones outside of class time. Learners were provided with technical training in class, while ongoing strategic and pedagogical training were provided through a combination of in-class activities and interactions through a dedicated Facebook page over a 5-week period. Usage patterns of the site were recorded through a learning journal and interactions on the Facebook page were analysed to determine the nature of the discussions that took place. Learner attitudes towards the tasks and the training were examined through pre- and post-questionnaires and a focus group discussion. The results are discussed in terms of the problems encountered, and some suggestions for providing appropriate training to learning through mobile phones outside of class through social networking.

Penerapan Media Postcard untuk Meningkatkan Keaktifan Siswa SMK Ma’arif NU Kajen Tahun 2021/2022

The learning model applied during the COVID-19 pandemic has changed the way students learn, so that student activity in the learning process in class is still low and there are many student absences after the pandemic. Almost 2 years of the pandemic have required students to study from their respective homes so that students are increasingly lazy or less active in learning. This is the basis for the idea of ​​how to make them more effective in learning by using postcard media. Postcard media is a media containing questions related to learning that must be answered by students by taking lucky coupons. The purpose of this study is 1) To describe the teacher's process in implementing postcard media in building student activity in learning in class XI of SMK Ma'arif NU Kajen. 2) To analyze the level of student activity of class XI of SMK Ma'arif NU Kajen through the application of postcard media in learning. This classroom action research was conducted at SMK Ma'arif NU Kajen with the research subjects of class XI students totaling 72 students with almost the same academic abilities, able to understand simple materials, but the level of student activity is low, the majority are less brave in expressing ideas, ideas and opinions. Data collection techniques include questionnaire sheets and documentation. Data analysis used is qualitative and quantitative data analysis. The results of the study showed that the process of implementing postcard media which was carried out through three stages, namely the process of designing a learning plan, the process of implementing learning, and the process of evaluating the use of learning media has been implemented well by teachers. In cycle I, the results of the questionnaire showed that the application of postcard media to increase student activity was successful with an average score reaching 86%. In cycle II, the application of postcard media to increase student activity was successful with an average questionnaire score reaching 88%. Postcard media has proven to be effective in increasing student activity in learning. For teachers, it is expected to be able to improve learning media so that students can be encouraged to be active in class. For schools, it is expected to be able to provide adequate facilities, especially the provision of teaching aids so that teachers can be more free in creating a creative learning process.