Integration Of Digital Media Research Articles

DSViT: An Enhanced Transformer Model for Deepfake Detection

The rapid development of artificial intelligence and deep learning models has enabled the creation of highly realistic fake images and videos, posing significant threats to information security and safety. Accurate detection of these forged contents is crucial to prevent the spread of misinformation and to protect the integrity of digital media. Although several advanced studies in this field, such as Vision Transformer (ViT) and Convolutional Vision Transformer (CViT), have been conducted, there remain limitations that need to be addressed. In this paper, we introduce a novel model, improved from CViT, designed to optimize the process of deepfake detection, named DSViT (Deepfake Detection with SC-based Convolutional Vision Transformer). This model judiciously integrates Convolutions and a SCConvolution block with the ViT architecture. We conducted experiments on the Deepfake Detection Challenge (DFDC) dataset and compared the results with the CViT model to demonstrate the effectiveness of the proposed model

Geography Teachers' Competence in Utilizing Learning Resources at SMA Negeri 15 Central Maluku

Education has become a crucial pillar in human civilization, ensuring the transmission of knowledge, skills, and values from one generation to the next, ensuring the continuity and progress of society. With an anticipatory and preparatory approach, ideal education prepares the younger generation to face the future with critical thinking, innovation, and adaptability to change. The utilization of learning resources in SMA Negeri 15 Maluku Tengah still needs to be improved, influenced by the lack of teacher competence in effectively utilizing various learning resources. Although teaching resources such as textbooks, digital media, and practical experiences are available, the lack of teacher skills in integrating them into teaching reduces the effectiveness of education. Enhancing teacher competence in resource utilization strategies is essential to improve the quality of education in the school. This research employs a phenomenological approach to understand the meaning of interactions in specific situations, focusing on the competence of geography teachers in utilizing learning resources in SMA Negeri 15 Maluku Tengah. This qualitative descriptive study analyzes the availability and utilization of various learning resources and their impact on learning. The results will likely provide a deep understanding of effective strategies to enhance teachers' utilization of learning resources, thereby improving the quality of education in the school. Teachers at SMA Negeri 15 Maluku Tengah utilize various learning resources in geography lessons, including conventional media and additional ones like newspapers, videos, and the internet. However, the use of digital media still needs to be improved, although they demonstrate creativity in teaching methods and adaptation to student characteristics. Further integration of digital media can enrich students' learning experiences and prepare them for the digital era.

Detection of counterfeit images using SIFT and PNN

Manipulation of digital images presents a significant challenge, primarily due to the continuous advancement and sophistication of image enhancement tools. As a consequence, image feature extraction and matching have become pivotal areas of research in the field of image processing. Among the various techniques developed, the Scale-Invariant Feature Transform algorithm has gained widespread recognition for its robustness and superior performance in feature matching tasks when compared to other existing methods. In this context, our proposed method, which integrates the Scale-Invariant Feature Transform algorithm with a probabilistic neural network, offers a novel approach to digital image classification specifically aimed at counterfeit image detection. This integrated system not only enhances the accuracy of feature extraction but also leverages the probabilistic neural network to improve classification efficacy. Empirical results indicate that this hybrid approach achieves a remarkable relative error rate of just 0.666%, underscoring its potential as a reliable tool for combating digital image forgery. Such advancements are crucial for maintaining the integrity of digital media in various applications, from forensic analysis to digital content authentication.

Optimized Art Design Model With Statistical Model with Digital Media

Art design is a form of creative expression that encompasses the visual aesthetics and conceptual elements of various mediums. Art design has undergone a transformative evolution with the integration of digital media, reshaping the landscape of creative expression. In contemporary art, artists leverage digital tools and technologies to explore innovative ways of crafting visual narratives. Hence, to improve the quality of the art design this paper constructed a framework of Weighted Genetic Optimization (WGO). The proposed WGO model incorporates the statistical modeling of digital media technology. The statistical technique comprises the estimation of the features in the art design model. Through the integration of WGO with the statistical model features related to the art design with the incorporation of digital media are evaluated. The statistical features in the art design are observed as the digital information such as geometric, GLCM and HUE are the essential features in the integrated WGO with statistical techniques. The estimated features are applied over the deep learning model with the LSTM network for the automated classification of art design that uses digital media for improvement. Simulation results demonstrated that the proposed WGO integrated statistical model achieves the HUE value ranges from 0 -360 which is effective for art design modeling. Also, the proposed model achieves a significant classification rate of 0.98 accuracy with a loss value of 0.2 which is ~9% less loss than the conventional techniques.

Memodifikasi Sistem Pendidikan di Sekolah Menengah dengan Pemberdayaan Media Digital dan Keterampilan Informasi dalam Kurikulum Merdeka

This research aims to analyse the impact of modifications to the education system at Vocational School Darussalam Banyuwangi through empowering digital media and information skills in the Merdeka Curriculum. The main aim of this research is to analyse how digital media integration affects teaching methods, curriculum, and educational outcomes, as well as assess students' readiness to face future challenges. The research method used is a qualitative approach with a case study design. Data was collected through in-depth interviews with school principals, teachers, and students, classroom observations to observe the implementation of digital media in the learning process, and analysis of curriculum documents and teaching materials. Data analysis was carried out using thematic analysis techniques to identify main patterns and themes from interviews, observations, and documents. The research results show that integrating digital media into the Merdeka Curriculum has improved teaching methods by increasing interactivity and student involvement. In addition, empowering information skills helps students manage and utilize information sources effectively. Although there are challenges to implementation, such as the need for additional training for teachers and technical issues, this research identifies strategies that can overcome these obstacles and increase the effectiveness of the curriculum. This research provides valuable insight into the adaptation of the education system in the digital era and offers recommendations for improving the implementation of the Merdeka Curriculum in secondary schools.

Detecting Deep Fake Voice using Machine Learning

With the rapid advancement of deep learning techniques, the creation of synthetic media, particularly deep fake voices, has become increasingly sophisticated and accessible. This poses significant challenges in maintaining trust and authenticity in audio-based content. In response, this project proposes a machine learning-based approach to detect deep fake voices. The project begins by curating a diverse dataset consisting of genuine and deep fake voice samples, covering various demographics, accents, and emotional expressions. Pre-processing techniques are applied to clean and standardize the audio data, followed by feature extraction to capture relevant characteristics of the voice signals. For model development, a Convolutional Neural Network (CNN) architecture augmented with recurrent layers is employed, leveraging its ability to learn spatial and temporal features from the spectrogram representations of the audio. The model is trained on the prepared dataset using categorical cross-entropy loss and optimized through backpropagation.Evaluation of the trained model is conducted on a separate test set, measuring performance metrics such as accuracy, precision, recall, and F1-score. Post- processing methods, including thresholding and smoothing, are applied to refine the model’s predictions and enhance robustness. The proposed approach offers a promising framework for detecting deep fake voices in audio content, contributing to the ongoing efforts to combat the spread of misinformation and preserve the integrity of digital media. However, ongoing research and collaboration across disciplines are essential to address emerging challenges and ensure the responsible deployment of deep fake detection technologies.

The Implementation of Electronic Portfolio Assessment in Learning Chemistry through Google Classroom to Increase Students’ Critical Thinking Skills

Assessment is crucial in evaluating the success of learning and student competencies. Among the essential 21st-century skills is critical thinking. Furthermore, technological advancements necessitate the integration of digital media in education, including assessment processes. One such digital assessment method is the electronic portfolio assessment using Google Classroom. This study aimed to examine the implementation of electronic portfolio assessment via Google Classroom to enhance students' critical thinking skills. The research employed a literature review approach, drawing data from books and online journals. Data collection involved gathering information from several books and online journals pertinent to the research topic. Primary data sources included articles published in national and international journals from 2012 to 2023. Content analysis was used to analyze the data. The study's findings indicate that electronic portfolio assessment, coupled with feedback, can enhance students' critical thinking skills. Additionally, the features integrated into Google Classroom can further stimulate students' critical thinking during the learning process. Therefore, it can be concluded that electronic portfolio assessment through Google Classroom effectively enhances students' critical thinking skills.

The dark side of screens: Exploring impairment with the iRAT framework

This paper introduces the iRAT model, an extension of the existing RAT framework, to comprehensively evaluate the integration of digital media in educational settings. While the traditional RAT framework focuses on Replacement, Amplification, and Transformation, the iRAT model includes a fourth category: Impairment. This new category addresses the potential negative impacts of digital media use, such as unnecessary app usage, distractions from learning objectives, lack of pedagogical integration, and resource wastage. The study employs a mixed-methods approach, including participatory observation, lesson plan evaluation, expert think-aloud protocols, and AI-driven scenario identification, to validate the iRAT model. Findings highlight the importance of considering both positive and negative aspects of digital media integration, suggesting that future research should adopt the iRAT framework for a balanced evaluation. This study closes a significant research gap and challenges the overly optimistic view of digital media in education, advocating for a more critical perspective.

Deepfake Detection System

Abstract: Because deep fake technology allows for the creation of incredibly realistically modified material that has the potential to mislead viewers and possibly cause instability across a range of businesses, it poses a severe threat to modern society. These days, detecting such modified content is crucial to maintaining the trustworthiness and integrity of digital media. In response, this research proposes a robust deep learning-based technique for detecting deep fakes in videos. Our method uses the Deep fake Detection Challenge dataset, which contains both real and deep fake films, to train and assess our deep learning model. We want to provide a dependable solution that can differentiate between artificially generated information and actual content using stateof-the-art neural networks. Artificial intelligence-generated phony videos are more likely to spread thanks to deep learning algorithms, which raises serious concerns about official blackmail, terrorist propaganda, revenge pornography, and political manipulation. To alleviate these concerns, our approach is designed to automatically identify several forms of deep forgery, including replacement and re-enactment techniques. By means of extensive testing and analysis, we demonstrate the effectiveness of our deep fake detection system in precisely distinguishing bogus films from authentic ones. Our system, which combines cutting-edge deep learning methods with a large dataset, offers a promising way to lessen the hazards related to the spread of deep fake technologies

Pedagogical approaches to health-related physical education (PE) in the context of digitalisation – a scoping review

ABSTRACT Introduction There are varied consequences of digital transformation processes within the fitness and health-related living environments of adolescents (e.g. increased physical activity through wearables, body dissatisfaction through social media) which could potentially provide fruitful health-related learning experiences within different pedagogical approaches to health in PE (e.g. biomedical vs. alternative, Mong and Standal, 2019, “Didactics of Health in Physical Education – a Review of Literature.” Physical Education and Sport Pedagogy 24 (5): 506–518. https://doi.org/10.1080/17408989.2019.1631270). However, concerns have been raised that the integration of digital media into health-related PE could reinforce biomedical approaches to health and lead, for example, to a focus on increasing fitness through technology. This one-sided focus would not be in line with the demands for a comprehensive health education. This paper aims to map the current trend of pedagogical approaches to health-related PE in the context of digitalisation and to identify typical learning goals against this background. Methods We conducted a scoping review based on the framework of Tricco et al. (2018, “PRISMA Extension for Scoping Reviews: Checklist and Explanation.” Annals of Internal Medicine 169 (7): 467–473. https://doi.org/10.7326/M18-0850). We searched nine databases using a search term covering three topic areas: digitalisation, health, and physical education. Considering the publication years from 2013 to 2023, we selected papers in a three-step process (title-, abstract-, and full-text-screening). In total, we included 103 empirical and theoretical papers in the analysis using qualitative content analysis (Kuckartz, 2019, “Qualitative Text Analysis: A Systematic Approach.” In Compendium for Early Career Researchers in Mathematics Education, edited by G. Kaiser and N. Presmeg, 181–197. Cham: Springer). To map the pedagogical approach to health, we applied the following main deductive categories: conceptualisation of health, paradigmatic approach to health and envisaged learning goals. To analyse learning goals with regard to digitalisation, we used the distinction between learning with and about digital media as a focus of analysis. Results The scoping review shows that most of the papers discussed a broad conceptualisation of health for PE by addressing biopsychosocial aspects of health. Many of the implications for health- and digitalisation-associated learning goals related to pre-reflective and functional-reflective learning goals in the area of learning with digital media. They mainly focused, from a pathogenic viewpoint, on how digital media can increase health-enhancing physical activity, affective determinants of health behaviour and health-related knowledge. Parts of these learning goals have already been empirically investigated. Only a few papers proposed critical-reflective learning goals in the area of learning about digital media, aiming at a socio-emancipatory engagement with digital media, health and society. No empirical study within the scoping review investigated the effectiveness of such critical health- and digitalisation-related PE. Discussion and conclusion In light of the results, it is important that future genuine pedagogical research about health- and digitalisation-related PE increasingly focuses on the development and empirical evaluation of theoretically sound concepts for PE that are in line with the educational demands of comprehensive – thus also critical and salutogenic – health and digital education.

Deepfake Face Detection Using Machine Learning with LSTM

Deep fake videos, which employ artificial intelligence to manipulate and generate highly convincing fake content, have emerged as a significant threat to society, potentially undermining trust in visual media. Detecting these deceptive videos is outmost importance to combat the spread of misinformation and protect the integrity of digital media. In this study, we propose a novel approach for deep fake face video detection utilizing Long Short-Term Memory (LSTM) networks, a type of Recurrent Neural Network (RNN). Our approach capitalizes on the temporal patterns and context within video sequences, harnessing the unique strengths of LSTM in capturing sequential information. We demonstrate the effectiveness of our methodology by training the LSTM network on a diverse dataset comprising both real and deep fake videos. The network’s ability to learn temporal dependencies and identify inconsistencies in facial expressions, eye movements, and other subtle cues allows it to distinguish between genuine and manipulated content. To further enhance the accuracy and robustness of our deep fake face detection system, we integrate pre-processing techniques for frame- level analysis, such as optical flow computation and facial landmarks extraction. Additionally, we employ a comprehensive ensemble of LSTM models and other machine learning algorithms to improve the overall detection performance. In our experiments, we evaluate the LSTM-based deep fake detection system on a large-scale dataset of both known and unseen deep fake videos, achieving high detection accuracy and low false positive rates. We also compare our approach with existing methods, demonstrating its superiority in terms of robustness and generalization. The results of this study signify the potential of LSTM-based models for mitigating the adverse effects of deep fake content on society. As deep fake technology continues to evolve, our approach showcases a promising step towards combating the dissemination of deceptive multimedia, promoting media integrity, and upholding trust in visual information. Keywords: LSTM Networks, Recurrent Neural Network, Optical flow computation, Facial landmarks extraction, False positive rates.

Deuteronomy and Contextual Teaching and Learning in Christian-Jewish religious education

This research explores the contextual approach within Christian-Jewish religious education, addressing a notable gap in existing literature and offering fresh insights into the application of the Contextual Teaching and Learning (CTL) model within Christian contexts. Through a qualitative literature study employing a three-step methodology, including an in-depth analysis of Deuteronomy 11:19–20, this study reveals that this biblical text provides both educational guidance and theological significance, serving as a foundational support for the CTL model in Christian-Jewish religious education. The integration of digital media into biblical sources holds promise for future research, while the central challenge lies in harmonising life experiences and empirical phenomena with biblical reflections to seamlessly integrate inquiry processes and pedagogical phases, with potential avenues for further exploration in scripture models endorsing CTL. This research provides valuable insights for educators, parents and policymakers in Indonesia and beyond, advancing educational research in contextualised teaching models within religious education.Contribution: This article demonstrates that the CTL model in the digital era has the potential to revolutionise religious education and profoundly impact learners, making it a significant scientific contribution in the context of Christian-Jewish religious education.

E-Moticon's Effective Curriculum Revolutionizes Technical Education

This research focuses on developing an E-Moticon E-Module as a digital learning tool for classroom use in the field of basic computer network and telecommunications. Utilizing the ADDIE method, the study includes expert validation and student trials to assess the media's effectiveness. Results show an 84.31% approval rate from experts and an 82.14% acceptance rate from students, indicating high feasibility and positive reception. This E-Module addresses a knowledge gap in tailored technical learning resources and highlights the potential impact of digital media integration in enhancing classroom learning experiences. Further research is recommended to validate its broader applicability and effectiveness in larger-scale classroom settings. Highlight: Tailored Technical Resource: E-Moticon fills gaps in technical learning for classrooms. High Feasibility: Expert and student approval rates exceed 80%, validating effectiveness. Structured Development: ADDIE method ensures systematic and effective media creation. Keyword: E-Moticon, E-Module, Digital Learning, Classroom Integration, ADDIE Method

Image Forgery Detection using ResNet50

Abstract: Image forgery detection is crucial in ensuring the integrity of digital media. In this study, we propose a method for detecting image tampering using Error Level Analysis (ELA) and Convolutional Neural Networks (CNNs) with a ResNet50 architecture. Leveraging the CASIA 2.0 Image Tampering Detection Dataset, which consists of authentic (Au) and tampered (Tp) images, along with metadata and annotations provided in the CASIA 2 Ground truth dataset, we develop and evaluate our model. The dataset comprises 7492 authentic images, 5125 tampered images, and 5123 files of ground truth information. ELA transformations highlight compression discrepancies, aiding in the identification of tampered regions. Our ResNet50-based CNN model, augmented with Global Average Pooling, Dense layers, and Dropout regularization, is trained using Adam optimization and binary cross-entropy loss with early stopping. Evaluation metrics, including training and validation loss/accuracy curves and confusion matrices, are used to assess model performance. The trained model is saved for future use and tested on new images to demonstrate its classification capabilities. Our approach achieves a significant level of accuracy in distinguishing between authentic and tampered images, underscoring its potential for practical image forgery detection applications and contributing to advancements in digital media forensics

Cultural and Theological Influences on Religious Engagement with Digital Media during COVID-19: A Comparative Study of Churches in Poland and Ireland

This article investigates how cultural context and theological ideas shape the integration of digital media in religious practices. Focusing on Poland and Northern Ireland/The Republic of Ireland, we explore the diverse strategies employed by religious institutions in utilizing digital media. The study centers on the Catholic Church, analyzing its responses to the COVID-19 pandemic in different cultural contexts. Examining various denominations specific to each country, we highlight the role of theological assumptions in shaping the use of digital platforms within religious contexts. This comparative analysis provides insight into the complex interplay between culture, theology, and technology, contributing to the understanding of how religious institutions adapt to societal changes and navigate the digital landscape. Our findings reflect the theological controversies of shifting religious practices and services to digital media, and point to the non-voluntary aspect of adjusting to the pressures of deep mediatization in both cultural contexts.

Analysis of Digital Media Usage in Promoting Communication Skills in Early Childhood

Digital media has become an omnipresent element in the lives of young children. This study aims to analyze the usage of digital media in promoting communication skills in early childhood. The proliferation of smartphones, tablets, and other digital devices has revolutionized how children interact with information and communicate with others. However, concerns have been raised regarding the potential impact of excessive screen time on children's development, particularly in areas such as language acquisition and social skills. This research employs a mixed-method approach, combining quantitative surveys and qualitative interviews with parents and educators of children aged 2 to 6 years. Quantitative data will be gathered to examine the frequency and duration of digital media usage among young children, while qualitative insights will delve into the perceived benefits and drawbacks of digital media on communication skills development. Additionally, observations of children's interactions with digital media tools will provide contextual understanding. The findings of this study are expected to contribute to a nuanced understanding of the role of digital media in early childhood communication development. By identifying effective usage patterns and potential pitfalls, educators and parents can make informed decisions regarding the integration of digital media into early childhood education and upbringing. Ultimately, this research aims to inform strategies that leverage digital media to enhance rather than hinder communication skills in young children, ensuring their holistic development in today's digital age.

Research on the Development Strategy of Physical Education Teaching in Universities Based on the Integration of Digital Media

Research on the Development Strategy of Physical Education Teaching in Universities Based on the Integration of Digital Media

The Communion of Digital Media Art and the Aesthetics of Smart City Public Art in an Interdisciplinary Context

Abstract The integration of digital media art into the public art design of the smart city can enhance people’s participation and sense of identity in the art design of public space and maximize the attractiveness and cultural connotation of the city itself. Based on this, this paper builds a fusion technology framework mainly based on digital projection technology and digital interaction technology, proposes an interactive projection technology integrating digital projection and Kinect, and combines the dynamic scene image splicing and alignment fusion technology to realize the interaction between the user and the digital scene. In the case analysis of Qianjiang New City, the number of visitors reached 31.55 million in 2022. The evaluation score of landscape facilities in the public evaluation of architectural landscape is under 3.5. The overall evaluation grade is only “general,” and the evaluation mean value of the degree of intelligence of landscape facilities is only 3.089. The comprehensive evaluation satisfaction of the digital landscape includes multimedia landscape, architectural landscape, and landscape facilities, and the average value of the evaluation of the degree of intelligence of the landscape facilities is only 3.089. The satisfaction value of the multimedia landscape, landscape of buildings and structures, and water landscape in the evaluation of satisfaction is 4.36, 4.159, and 4.027, respectively, which reaches the level of “good” satisfaction, while the satisfaction value of landscape facilities is 3.479, which is less than 3.5. The satisfaction level only reaches the level of “general.” The satisfaction value of landscape facilities is 3.479, which is less than 3.5, and the satisfaction level is only “fair.”

Research on How Convergent Digital Media has Impacted the Social Space of Contemporary Cities

The integration of digital media has an important impact on the economic development, cultural development and spatial use of cities. This paper explains this idea from two main perspectives. The first is media architecture. The integration of media and architecture, supported by new technologies, is an indispensable step in modern urban planning. Media architecture can effectively increase the public's sense of participation and cultural identity. However, at the same time, too many media buildings can also bring huge information waste. Secondly, I will use the case of the Public Comment software to rethink what urban communication is. The interactive nature of digital media can both facilitate and hinder urban communication. How to grasp this scale is a question that needs to be addressed in public communication.

Improving Detection of DeepFakes through Facial Region Analysis in Images

In the evolving landscape of digital media, the discipline of media forensics, which encompasses the critical examination and authentication of digital images, videos, and audio recordings, has emerged as an area of paramount importance. This heightened significance is predominantly attributed to the burgeoning concerns surrounding the proliferation of DeepFakes, which are highly realistic and manipulated media content, often created using advanced artificial intelligence techniques. Such developments necessitate a profound understanding and advancement in media forensics to ensure the integrity of digital media in various domains. Current research endeavours are primarily directed towards addressing a common challenge observed in DeepFake datasets, which pertains to the issue of overfitting. Many suggested remedies centre around the application of data augmentation methods, with a frequently adopted strategy being the incorporation of random erasure or cutout. This method entails the random removal of sections from an image to introduce diversity and mitigate overfitting. Generating disparities between the altered and unaltered images serves to inhibit the model from excessively adapting itself to individual samples, thus leading to more favourable results. Nonetheless, the stochastic nature of this approach may inadvertently obscure facial regions that harbour vital information necessary for DeepFake detection. Due to the lack of guidelines on specific regions for cutout, most studies use a randomised approach. However, in recent research, face landmarks have been integrated to designate specific facial areas for removal, even though the selection remains somewhat random. Therefore, there is a need to acquire a more comprehensive insight into facial features and identify which regions hold more crucial data for the identification of DeepFakes. In this study, the investigation delves into the data conveyed by various facial components through the excision of distinct facial regions during the training of the model. The goal is to offer valuable insights to enhance forthcoming face removal techniques within DeepFake datasets, fostering a deeper comprehension among researchers and advancing the realm of DeepFake detection. Our study presents a novel method that uses face cutout techniques to improve understanding of key facial features crucial in DeepFake detection. Moreover, the method combats overfitting in DeepFake datasets by generating diverse images with these techniques, thereby enhancing model robustness. The developed methodology is validated against publicly available datasets like FF++ and Celeb-DFv2. Both face cutout groups surpassed the Baseline, indicating cutouts improve DeepFake detection. Face Cutout Group 2 excelled, with 91% accuracy on Celeb-DF and 86% on the compound dataset, suggesting external facial features’ significance in detection. The study found that eyes are most impactful and the nose is least in model performance. Future research could explore the augmentation policy’s effect on video-based DeepFake detection.