JOIV : International Journal on Informatics Visualization
Not a member yet
786 research outputs found
Sort by
Artificial Neural Network Accuracy Optimization Using Transfer Function Methods on Various Human Gait Walking Environments
Get PDFA bionic leg with ergonomic functionality can increase the user’s independence. However, an ergonomic bionic leg can be challenged to be developed. One of its challenges is related to functionality, where the bionic leg motor can be rugged to adapt to the user. One of the solutions for the bionic leg challenge is the application of a motor driver controlled by the user’s muscle signal. EMG signal can be utilized as the user’s signal source. The EMG signal is then fed back into the motor device. EMG signals obtained during a natural walking environment can result in smooth and natural movement. This study classifies EMG signals into 8 classes: a controlled walking environment (treadmill walking with various speeds) and a natural walking environment (ground walking, upstairs and downstairs walking). This research aims to optimize the ANN method using transfer function variations. The best method will be used to train EMG-driven motors for future studies related to bionic legs. The best ANN parameter in this research using Levenberg-Marquardt backpropagation as a training algorithm with transfer function pairing of the exponential function: Hyperbolic tangent sigmoid transfer function and SoftMax transfer function with 98.8% accuracy and 0.036 MSE value. The best method from the experiment and ANN classification can be used as a training method for a bionic leg in future research
Technology and Language: Improving Speaking Skills through Cybergogy-Based Learning
Get PDFLanguage learning in the Industrial Revolution 4.0 and Society 5.0 era is required to produce students with 21st-century skills by increasing the capacity and capability of using technology in learning. Technology-based learning, known as cybergogy, is a continuity of learning paradigms that previously applied the principles of pedagogy and andragogy in the learning process. As a new concept in learning, cybergogy is essential in improving 21st-century skills in the form of the 6Cs (Citizenship, Character, Critical Thinking and Problem Solving, Communication, Creativity, and Collaboration). Enhancing communication skills through cybergogy-based learning is a novelty that has not been done much and has become the focal point of research. This research, part of development research using the ADDIE model, employed a quasi-experimental design conducted in 3 senior high schools in Yogyakarta, representing one school per category, namely the lower, medium, and high categories, based on UTBK scores. A non-equivalent control group design involving an experimental and control class was applied. The results of this study, which showed a significant improvement in students' communication skills, especially speaking aspects, through blended learning, are of great significance. Therefore, it can be concluded that cybergogy-based language learning has proven effective in improving students' communication skills through blended learning
Web and Android-based Test Application Development and its Implementation on Final Semester Examination
Get PDFThis research aims to revolutionize the examination process in vocational schools by developing the FlyExam application, an Android-based test platform derived from improvements to the TCExam interface. The core goal was to create a powerful, easy-to-use, and effective tool for semester assessment. Following a Research and Development (R&D) approach, this research uses a 4D model: Define, Design, Develop, and Disseminate. Validation procedures require expert evaluation of the technical aspects and usability of the application. At the same time, practicality is assessed through engagement with students and teachers, and effectiveness is measured by student performance. Expert reviews and user feedback confirm the validity and practicality of the application. During implementation, the LAN network topology proved to be a conducive environment for conducting semester exams, increasing the efficiency and reliability of the testing process. The integration of TCExam and FlyExam on mobile devices shows the potential of transitioning from traditional paper-based exams to digital platforms, offering greater flexibility and accessibility. Future research efforts could explore FlyExam's scalability and adaptability in various educational contexts and its long-term impact on assessment practices and academic outcomes. Additionally, ongoing improvements based on user feedback can lead to further improvements and the incorporation of new features, ensuring FlyExam remains relevant and effective in meeting evolving vocational education needs. In summary, the development of FlyExam represents significant progress in the modernization of assessment methodology, with the potential to simplify the process and improve the learning experience in vocational schools
Determinants Generating General Purpose Technologies in Economic Systems: A New Method of Analysis and Economic Implications
Get PDFThis research proposes using the fishbone diagram, a visualization tool for constructing a comprehensive theoretical framework to analyze the sources of innovation. Traditionally employed to identify causes of specific events, the fishbone diagram is applied innovatively to explore the root causes driving the emergence and evolution of General Purpose Technologies (GPTs). The study identifies critical driving forces such as increased democratization, population growth, demographic shifts, significant investments in research and development (R&D), global leadership aspirations among major powers, competitive socioeconomic environments, and potential threats from adversarial actors. By visually representing these drivers, the fishbone diagram offers insights crucial for technological analysis and foresight, illuminating groundbreaking innovations that drive technological and economic progress. Illustrated through examples from historical GPTs like the steam engine and contemporary technologies such as Information and Communication Technologies (ICTs), this study establishes a foundational framework for developing precise hypotheses about the specific causes and socio-economic impacts of GPTs. The fishbone diagram emerges as a versatile tool adept at systematically analyzing the complex root causes associated with GPTs, facilitating foresight and strategic management of these transformative innovations within society
Improved Face Image Authentication Scheme based on Embedding in Adjacent Coefficients
Get PDFFace image authentication (FIA) schemes have recently been developed using face detection and image watermarking technology. The research in this direction proved the presented schemes' efficiency in accurately detecting the manipulated face regions and recovering the original face region. Recovering the original face region is very important in practical applications. Still, it was at the cost of increasing the secret data that must be embedded in the face image. The increment in the secret data required a large embedding capacity, which was not available in some images. To overcome this limitation, an improved FIA scheme based on a new data embedding algorithm is presented in this paper. The suggested FIA scheme consists of two main algorithms applied at the sender and receiver sides, where both start by detecting the face region and dividing and classifying the image into blocks that belong to the face region or outside the face region. At the sender side, the secret data are generated from the face region and embedded in the blocks outside the face region using the suggested algorithm called Embedding in Adjacent Coefficients (EAC) for three subbands obtained after applying the Slantlet transform of the blocks. On the receiver side, the secret data are extracted from the blocks outside the face region using the suggested algorithm called Extraction from Adjacent Coefficients (ExAC). The extracted data is used to authenticate the face region and recover the original one when manipulations occur. The proposed FIA scheme obtained higher embedding capacity than previous ones, making it applicable to protect more face images that could not be protected using previous FIA schemes
ChatGPT in Science Education: A Visualization Analysis of Trends and Future Directions
Get PDFChatGPT, as one of the products of artificial intelligence (AI)-based technology, has shown significant potential in science education. This study aims to analyze the development trends and focal points of ChatGPT research, especially in science education from the Scopus database in 2022-2024. This study used Bibliometric analysis which is a quantitative and qualitative evaluation technique of documents in a database. The search method was carried out with the Dimensions and Publish or Perish (PoP) databases using Scopus and data visualization using VOSviewer. Searches were conducted on article titles, abstracts, and keywords at once (TITLE-ABS-KEY) with the keywords "ChatGPT" and "science education". The results of the bibliometric analysis showed a significant increase in the number of ChatGPT-related publications in the field of science education, with several key topics taking center stage, such as pedagogical adaptation, AI-based learning, and evaluation of technology effectiveness in the teaching and learning process. Visual analysis using VOSviewer identified a clustering of research covering the integration of ChatGPT in the science education curriculum, the role of AI in facilitating collaborative learning, and the impact of using ChatGPT on student motivation and learning outcomes. This suggests that the use of AI, particularly ChatGPT, in science education is a growing area of research with significant potential impact. This research provides a comprehensive overview of recent developments in the use of ChatGPT in the field of science education and provides insights for future research
A Novel Information Hiding Approach using Selective Quantization Technique in Video Coding
Get PDFThis research examines the different areas of information hiding in current and emerging video compression standards. In the subsequent sections, we provide a detailed comparison of these techniques based on partition modes, prediction units, transform coding, and syntax elements. It shows the engineer and the reader that none of the methods are perfect but are the best for selected applications. We also consider the new video coding standards that have recently appeared, H.266/Versatile Video Coding (VVC) and H.265/High-Efficiency Video Coding (HEVC) and stress the fact that information hiding is critical in attaining such high compression efficacy. To facilitate the reader's understanding of all the relative information, the table that provides the analysis of each technique is presented in the form of a simple listing containing information about each technique's advantages, disadvantages, impacts, and practical applications. The current resource is intended to assist researchers and practitioners in optimizing information hiding for improved video compression. The study's outcome can contribute to enhancing knowledge of information hiding and the new developments of information hiding in video compression beyond what current research offers now, as well as provide a foundation for fresh advances in the field. Further, it is introduced to selective quantization techniques as the approach to information hiding. This method also minimizes this distortion while putting the information into the compressed stream. Finally, we evaluate the performance of this introduced approach towards information hiding capacity and maintaining video quality, with the potential to inspire further research and development in the field
Predicting Different Classes of Alzheimer's Disease using Transfer Learning and Ensemble Classifier
Get PDFAlzheimer's disease (AD), the most prevalent cause of dementia, affects over 55 million individuals globally. With aging populations, AD cases are expected to increase substantially, presenting a pressing public health challenge. Early diagnosis is crucial but remains challenging, particularly in the mild cognitive impairment stage before extensive neurodegeneration. Existing diagnostic methods often fall short due to the subtle nature of early AD symptoms, highlighting the need for more accurate and efficient approaches. In response to this challenge, we introduce a hybrid framework to enhance the diagnosis of Alzheimer's Disease (AD) across four classes by integrating various deep learning (DL) and machine learning (ML) techniques on an MRI image dataset. We applied multiple preprocessing techniques to the MRI images. Then, the methodology employs three pre-trained convolutional neural networks (CNNs): VGG-16, VGG-19, and MobileNet - each undergoing training under diverse parameter settings through transfer learning to facilitate the extraction of meaningful features from images, utilizing convolution and pooling layers. Subsequently, for feature selection, a decision tree-based RFE method was employed to iteratively select the most significant features and enable more accurate AD classification. Finally, an XGBoost classifier was used to classify the multiclass types of AD under 5-fold cross-validation to assess the performance of our proposed model. The proposed model achieved the highest accuracy of 93% for multiclass classification, indicating that our approach significantly outperforms state-of-the-art methods. This model could apply to clinical applications, marking a significant advancement in AD diagnostics
Applying Deep Learning Models to Breast Ultrasound Images for Automating Breast Cancer Diagnosis
Get PDFBreast cancer is a result of uncontrolled human cell division. The vast growth of breast cancer patients has been an issue worldwide. Most of the patients are women, but breast cancer also affects men with a much lesser percentage. Breast cancer might lead to death for those who are suffering from it. Numerous types of research have been done to make an early diagnosis of breast cancer. It has been proven that the tumor can be detected by using an ultrasound image. Artificial Intelligence techniques have been used to detect breast cancer fundamentally. This paper studies the effectiveness of deep learning (DL) techniques in automating breast cancer diagnosis. Subsequently, the paper evaluates the diagnosis performance of three DL models utilizing the criteria of accuracy, recall, precision, and f1-score. The Densenet-169, U-Net, and ConvNet DL models are selected based on the examination of the related work. The DL diagnosis process involves identifying two types of breast cancer tumors: benign and malignant. The evaluation outcomes of the DL models show that the most effective model for diagnosing breast cancer among the three is the ConvNet, which achieves an accuracy of 91%, a recall of 83%, a precision of 85%, and an F1-score of 83%
Classifying Gender Based on Face Images Using Vision Transformer
Get PDFDue to various factors that cause visual alterations in the collected facial images, gender classification based on image processing continues to be a performance challenge for classifier models. The Vision Transformer model is used in this study to suggest a technique for identifying a person’s gender from their face images. This study investigates how well a facial image-based model can distinguish between male and female genders. It also investigates the rarely discussed performance on the variation and complexity of data caused by differences in racial and age groups. We trained on the AFAD dataset and then carried out same-dataset and cross-dataset evaluations, the latter of which considers the UTKFace dataset. From the experiments and analysis in the same-dataset evaluation, the highest validation accuracy of happens for the image of size pixels with eight patches. In comparison, the highest testing accuracy of occurs for the image of size pixels with patches. Moreover, the experiments and analysis in the cross-dataset evaluation show that the model works optimally for the image size pixels with patches, with the value of the model’s accuracy, precision, recall, and F1-score being , , , and , respectively. Furthermore, the misclassification analysis shows that the model works optimally in classifying the gender of people between 21-70 years old. The findings of this study can serve as a baseline for conducting further analysis on the effectiveness of gender classifier models considering various physical factors