The Kellgren-Lawrence (KL) grading system is commonly used to evaluate knee osteoarthritis (OA), but it can be subjective and subject to variation among assessors. Our study looked at three Convolutional Neural Network (CNN) methods for OA severity classification from a dataset of 15,770 X-ray images to overcome this difficulty and create a more objective technique. Under the same preprocessing conditions, we contrasted a baseline custom CNN, DenseNet201, and a hybrid model with a CBAM attention mechanism. With an overall accuracy of 65%, a weighted precision and recall of 65%, and an F1-score of 64%, the hybrid model, which uses DenseNet201 as a fixed feature extractor, performed the best. This was better than both the baseline model (59% accuracy) and the standalone DenseNet201 (59% accuracy). Although the hybrid architecture has a lot of promise, we also had to deal with issues like overfitting. Our thorough comparison demonstrates how this hybrid strategy can successfully combine strong pre-trained features with the flexibility required for particular tasks. Although more clinical validation is necessary, this shows that automated systems like ours could improve diagnostic consistency in OA grading.
 
Keywords - Knee Osteoarthritis, Kellgren-Lawrence Grading, Deep Learning, Attention Mechanism, CBAM

Amyotrophic Lateral Sclerosis (ALS) is a progressive neurodegenerative disorder that presents significant diagnostic challenges due to its heterogeneous clinical manifestations and symptom overlap with other neurological conditions. Early and accurate diagnosis is critical for initiating timely interventions and improving patient outcomes. Traditional diagnostic approaches rely heavily on clinical expertise and manual interpretation of neuroimaging data, such as structural MRI, Diffusion Tensor Imaging (DTI), and functional MRI (fMRI), which are inherently time-consuming and prone to interobserver variability. Recent advances in Artificial Intelligence (AI) and Deep Learning (DL) have demonstrated potential for automating neuroimaging analysis, yet existing models often suffer from limited generalizability across modalities and datasets. To address these limitations, we propose a Transformer-augmented deep learning ensemble framework for automated ALS diagnosis using multi-modal neuroimaging data. The proposed architecture integrates Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Vision Transformers (ViTs) to leverage the complementary strengths of spatial, temporal, and global contextual feature representations. An adaptive weighting-based fusion mechanism dynamically integrates modality-specific outputs, enhancing the robustness and reliability of the final diagnosis. Comprehensive preprocessing steps, including intensity normalization, motion correction, and modality-specific data augmentation, are employed to ensure cross-modality consistency. Evaluation using 5-fold cross-validation on a curated multi-modal ALS neuroimaging dataset demon-strates the superior performance of the proposed model, achieving a mean classification accuracy of 94.5% ± 0.7%, precision of 93.9% ± 0.8%, recall of 92.9% ± 0.9%, F1-score of 93.4% ± 0.7%, spec-ificity of 97.4% ± 0.6%, and AUC-ROC of 0.968 ± 0.004. These results significantly outperform baseline CNN models and highlight the potential of transformer-augmented ensembles in complex neurodiagnostic applications. This framework offers a promising tool for clinicians, supporting early and precise ALS detection and enabling more personalized and effective patient management strategies.

Children are one of the most vulnerable groups during disasters due to their limited physical and psychological resilience. Therefore, providing disaster mitigation education to children is essential to enhance their awareness, preparedness, and response capabilities in the face of potential disasters. This community service activity aims to increase children's understanding of disaster mitigation through both theoretical education and participatory simulations that reflect real-life scenarios. The activities were carried out using a cooperative-participatory approach in collaboration with the local Indonesian Red Cross (PMI) in Tanah Karo and members of the surrounding community. The stages of implementation included conducting a site survey, securing necessary permits, determining the time and location, coordinating with local stakeholders, and executing the service program. The educational activities covered disaster phases, including pre-disaster, during disaster, and post-disaster, with a focus on practical and age-appropriate learning strategies. The educational team involved an interprofessional group of facilitators who delivered the material through socialization and counseling sessions. The sessions were enthusiastically received by the children, indicating a high level of engagement and interest. However, findings revealed that children's knowledge of disaster mitigation was still minimal, emergency response plans were underdeveloped, and community involvement in disaster preparedness training remained low. This highlights the need for continuous and sustainable disaster education efforts, especially for children and communities in disaster-prone areas. By fostering early awareness and preparedness through ongoing education and simulation-based activities, it is expected that children will be better equipped to respond effectively and safely during disaster situations. Long-term, this approach also aims to build a more resilient and disaster-aware community.

Sports are an important physical activity to engage in, but they can also lead to issues such as injuries, particularly for futsal players. The risk of injury is higher in sports that involve physical contact with opponents, such as futsal, and athletes who have experienced injuries may experience anxiety. This research used a cross-sectional design and a descriptive research methodology. The sample consisted of 18 respondents obtained through purposive sampling. Data analysis techniques used descriptive percentages. The results of the study showed that the anxiety levels of the respondents were categorized as “very low” 0 (0%), “low” 7 players (39%), “moderate” 3 players (16%), ‘high’ 7 players (39%), and “very high” 1 player (6%). Based on the average value of “27.11,” the anxiety level of UNESA futsal players falls into the “moderate” category. The injury levels of the respondents were as follows: “Level 1 injury” for 5 respondents (28%), “Level 2 injury” for 11 respondents (61%), and “Level 3 injury” for 2 respondents (11%). The injury levels of the respondents were categorized as “Level 2 Injury.” The conclusion of this study is categorized as “Moderate” with a percentage of 27.11%.

An This study aims to analyze the advertisement of Mie Sedaap Tasty Beef Yakiniku reviewed from the perspective of Indonesian Advertising Ethics. Instant food advertisements are often packaged creatively and persuasively, but often violate advertising norms and ethics. This study uses a descriptive qualitative approach with a content analysis method. The results of the study indicate that several elements in this advertisement violate the principles of honesty and social responsibility as stated in the Indonesian Advertising Ethics, especially in terms of taste claims, visualization of ingredients, and excessive depictions of deliciousness. This study recommends that advertisers pay more attention to ethical standards so as not to mislead consumers.

This study aims to determine the factors that influence the achievement of the Budget Implementation Performance Indicator (IKPA) value of the Work Unit in the Medan II KPPN Work Area. The Budget Implementation Performance Indicator (IKPA) is an indicator set by the Ministry of Finance as BUN which is used as a measure and reflects the performance of the work unit on the quality of budget planning, the quality of budget implementation and the quality of budget implementation results. This study aims to determine what factors influence the achievement of the IKPA value in the work unit at the Medan II KPPN. This research method uses a quantitative approach with primary data through the distribution of questionnaires to employees who play a role in the achievement of the Satker IKPA, namely PPK, PPSPM, Treasurer, Budget Operator and Commitment/Payment Operator. The study population consisted of 170 Work Units, while the sample of this study was 200 respondents conducted in 40 Work Units in the Medan II KPPN work area with the criteria of Work Units that obtained IKPA value achievements in the sufficient and less categories for the 2022 to 2024 budget years. Hypothesis testing used analysis with the help of SmartPLS 4. The results of the study showed that transparency, organizational commitment, human resource competence, government regulations and coordination had a positive and significant effect on the achievement of IKPA values. This finding confirms the importance of transparency in state financial management accompanied by organizational commitment, increasing human resource competence, compliance with government regulations and increasing coordination between Work Units and Medan II KPPN which play a role in increasing the achievement of IKPA values ??of Work Units

The development of digital technology has driven significant changes in advertising strategies in Indonesia. However, this transformation has also brought new challenges in maintaining ethical standards in marketing communications. This study aims to examine the extent to which the Indonesian Advertising Ethics (Etika Pariwara Indonesia/EPI) is applied in digital advertising practices. Using a qualitative approach and document analysis, this research analyzes several digital advertisements suspected of violating religious, ethical, and consumer protection principles, including honesty and social responsibility. The findings reveal that despite the existence of formal regulations, violations of EPI provisions still occur—particularly on digital platforms that are difficult to monitor directly. This study highlights the importance of strengthening regulations, educating industry players, and encouraging active public participation in monitoring advertising content. Thus, advertising ethics are expected to be preserved in an increasingly fast-paced and digital communication era.

This study analyzes advertising ethics violations in Hanasui’s Instagram advertisement, which claims its serum product as the “No.1 Serum in Indonesia” without adequate data substantiation. The digital era and the high penetration of social media have transformed the advertising landscape but have also opened up opportunities for practices that violate the Indonesian Advertising Ethics (EPI). This research uses a qualitative approach with content analysis and case study methods to examine Hanasui's Instagram advertisements. The analytical framework is based on EPI articles related to honesty, responsibility, and substantiation of advertising claims. The findings indicate that the superlative claim “No.1 Serum in Indonesia” violates fundamental EPI principles, particularly in the aspects of honesty and responsibility, due to the absence of clear supporting data or methodology. This violation not only misleads consumers but also creates unfair competitive advantages and risks eroding consumer trust in the local cosmetics industry. The study also reveals challenges in implementing EPI in the context of social media, where the unique characteristics of digital platforms require adaptations to the existing regulatory framework. Recommendations include strengthening EPI enforcement mechanisms for digital advertising, developing specific social media guidelines, enhancing coordination with digital platforms, and implementing a peer-review mechanism within the advertising industry. This research contributes to the literature on communication ethics and provides practical insights for regulators, advertising practitioners, and academics in addressing advertising ethics challenges in the digital era.
 

The 2024 General Election in Indonesia marked a significant shift in the landscape of political communication from conventional media to the digital sphere. Political campaigns conducted through social media and online platforms have opened new opportunities for persuasive effectiveness but also introduced serious challenges in terms of communication ethics, particularly in advertising. This study aims to analyze digital political campaign practices during the 2024 election through the lens of the Indonesian Advertising Ethics Code (Etika Pariwara Indonesia/EPI), which serves as a self-regulatory standard in the advertising industry. This research employs a qualitative approach using a case study method, supported by documentation analysis, digital observation, and literature review. The findings reveal that many digital political advertisements violate key EPI principles, including honesty, transparency, and social responsibility. The most prominent violations include negative campaigning, the use of religious symbols to construct candidate images, and undisclosed endorsements by political influencers. Weaknesses in digital monitoring systems exacerbate these issues, allowing unethical content to spread massively and uncontrollably. This study concludes that the implementation of EPI in digital political campaigns remains weak and requires a more adaptive, collaborative, and technology-based monitoring approach to safeguard democratic integrity in the digital communication era.

This study aims to analyze the effectiveness of the Indonesian Advertising Ethics (EPI) in regulating advertisements in the digital era, based on the gap between regulations and practice in the field. The research utilizes a qualitative approach, employing documentary studies and in-depth interviews to gain a comprehensive understanding of the issue. The results show that the EPI's effectiveness in maintaining fairness, honesty, and responsibility in digital advertising is still weak. This weakness is not due to the substance of the EPI itself, but mainly because of the rapid development of technology, the vast expansion of digital media, low compliance from practitioners, and the self-regulatory approach that relies on the awareness and responsibility of each actor. The study also finds a gap between regulation and practice due to the EPI’s continued use of a framework designed for traditional media, making it less adaptable to digital media's unique challenges. Therefore, the research concludes that a more adaptive, collaborative, and multi-stakeholder approach is required to safeguard advertising ethics and protect the public's interest in the digital era