Online-Journals.org (International Association of Online Engineering)
Not a member yet
9805 research outputs found
Sort by
A Mobile-Enabled Adaptive Gamification Framework for Programming Education
Get PDFWhile traditional teaching and learning methods in education have turned to be more active and engaging with the help of technology, this study proposes a Holistic Gamification Learning Adventure (HGLA) framework, which integrates gamification principles, multidimensional progression, and narrative-driven experiences for programming education. Different from most other gamification models, adaptive pathways and collaboration in the HGLA framework ensure novelty in accommodating diverse learning styles and proficiency levels of both novice and advanced programmers. It’s a framework that uses responsive design to ensure access across devices, creating ubiquitous learning environments. The embedment of gamified missions and narrative-driven challenges shall make students active participants instead of passive observers, while the motivation, engagement, and retention concerning programming concepts shall be developed. The multi-dimensional progression within the framework caters to individual learning paces, ensuring an individualized educational experience for deeper conceptual understanding and long-term retention. The present study shows how the HGLA framework has transformed programming education into an adaptive, inclusive, and impactful learning journey—a beacon of change in innovative teaching methodologies
Mobile Application for Continuous Recognition and Classification of Sign Language Images through Deep Learning
Get PDFThroughout the world, sign languages (SL) present significant challenges for effective communication in everyday environments and technological applications. In the field of SL recognition (SLR) using artificial intelligence (AI), two approaches have been developed: isolated SLR (ISLR) and continuous SLR (CSLR). To overcome the limitations of CSLR in SL, we developed a mobile application that integrates an AI-based algorithm in Python, designed to capture and analyze sign sequences through the device’s camera. The application facilitates the creation of a continuous database containing 14 dynamic signs, with 240 videos per sign, resulting in a total of 3360 videos and 50,400 frames. We used a neural network model based on the long short-term memory (LSTM) architecture to improve accuracy in sign identification and promote inclusive communication in digital environments. The model achieved 99.80% accuracy during training and 99.40% in testing, with overall accuracy, recall, and F1-score metrics above 99%. These results evidence the effectiveness of the mobile application and the LSTM model in recognizing, classifying, and translating basic SLP utterances in real time, demonstrating its ability to generalize and avoid overfitting and contributing to more inclusive and accessible communication
Implementation of Professionally Oriented Tasks with Interactive Cloud Environment Google Colab
Get PDFThe purpose of the paper is to analyze the necessity of implementing professionally oriented tasks in higher mathematics courses for technical students during practical classes using the interactive cloud environment Google Colab. The results are as follows. The main mathematical concepts are analyzed; the indicators of professionally oriented mathematical tasks are characterized; the aspects of solving professionally oriented tasks are considered. The students’ survey as a pilot study has shown that students do not have very high self-esteem, have little problem-solving skills, it affects students’ motivation, academic performance. The examples of solving professionally oriented tasks with the interactive cloud environment Google Colab are shown. The conclusion is that a balance between the fundamental mathematical knowledge and the practical value is needed; Google Colab helps a lot. The prospect for further research is to monitor the success of students’ learning in other courses using Google Colab
Development of a Mobile Application with Artificial Intelligence for Mexican Sign Language Recognition
Get PDFIn Mexico, the community of people with hearing disabilities faces significant communication barriers due to the limited availability of interpreters and the lack of supportive technological tools. This paper presents the development of a sign language system using artificial intelligence (SLSAI), a mobile application that uses artificial intelligence (AI) for the recognition of Mexican sign language (MSL). Using machine learning techniques and image processing, SLSAI translates signs from the alphabet in real-time, facilitating interaction between deaf and hearing individuals. Additionally, the tool features a module where students can learn sign language through interactive games, creating a fun and engaging learning environment. The development methods, obtained results, and social implications of the tool are discussed
Risk Research on Blockchain Technology in Interactive Mobile Hospitals Based on the Entropy Method
Get PDFThis paper aims to study the risk situation of blockchain technology in interactive mobile hospitals. With the development of blockchain technology, interactive mobile hospitals have begun to use blockchain technology to empower technological capabilities in aspects such as diagnosis and treatment management, data security, and sharing. Firstly, by referring to relevant literature, this paper identifies that the existing risks include technical risks, privacy risks, compliance risks, management and operation risks, as well as cognitive and acceptance risks. Then, the entropy method is used to analyze the weights of these risks, and the fuzzy comprehensive evaluation (FCE) method is applied to calculate the risk levels. The calculation results show that the overall risk score of blockchain technology in interactive mobile hospitals is 63.3705, among which the technical risk score is 59.3491, the management and operation risk score is 59.8643, the privacy risk score is 65.8097, the compliance risk score is 64.1854, and the cognitive and acceptance risk score is 69.2427. This study conclusion is that the degree of risk of blockchain technology in interactive mobile hospitals is between general and high. Among them, technical risks and management and operation risks are between low and general, while privacy risks, compliance risks, and cognitive and acceptance risks are between general and high. Finally, this paper puts forward corresponding countermeasures and suggestions based on the risk conclusions. This paper hopes that the interactive mobile hospital industry can strengthen risk management in aspects such as enhancing technological research and development, protecting privacy, improving laws and regulations, optimizing management processes, and increasing the awareness of all parties so as to promote the healthy and stable development of the entire mobile medical industry
Exploring Medical Caption Generation through OpenAI’s ChatGPT-4 Model: A PRISMA Review
Get PDFThis study explores the importance of the ChatGPT-4 model in medical caption generation, its advantages, applications, and limitations, using a PRISMA strategy on Medline and PubMed medical datasets to extract relevant studies from over a year ago concerning “ChatGPT” and “Medical Report Generation.” The search employed keywords such as (“ChatGPT” OR “GPT model”) AND (“medical caption generation” OR “medical image captioning” OR “radiology captioning”). The PRISMA search strategy led to the selection of seven promising papers. We conducted a brief comparison among the selected papers, taking into account their key focus, the datasets used, the models evaluated, the research results, and the challenges highlighted. Additionally, ChatGPT4’s performance was evaluated by uploading sample medical images from different dataset modalities such as PathVQA, VQA-Med 2020, RadioGraphy Captions (RGC), and Radiology Objects in Context (ROCO) to establish whether it could generate coherent and contextually correct medical captions as true outputs and correctly answer medical questions with output performance BLEU = 0.5012 and ROUGE-L = 0.8000 scores. This study provides state-of-the-art evidence that ChatGPT demonstrates remarkable performance in report generation and answering medical questions under supervision
Integrating Predictive Analytics and Deep Neural Networks for Early Lung Cancer Diagnosis
Get PDFOne of the leading causes of cancer-related mortality globally is lung cancer; hence, early and effective screening methods are crucial. This work combines advanced deep learning models with predictive analytics to improve the early detection of lung cancer. The lung cancer histopathological images dataset is used to analyze histopathological slides and clinical data using a range of models, including convolutional neural networks (CNN), recurrent neural networks (RNN), long short-term memory (LSTM) networks, feedforward neural networks (FNN), and deep reinforcement learning (DRL). Because CNN can extract spatial characteristics, it performs better than the other models in accurately categorizing tissues that are malignant and those that are not. While FNN is a supplementary tool for incorporating non-image clinical metadata, LSTM and RNN models are investigated for their capacity to manage sequential patterns within patient data. By mimicking clinical operations, improving diagnostic accuracy, and lowering false positives, DRL streamlines decision-making processes. This study demonstrates the revolutionary potential of deep learning-powered predictive analytics in the early detection of lung cancer. These techniques open the door for AI-driven advancements in customized medicine and precision oncology by increasing diagnosis accuracy and facilitating prompt therapies. Prospective avenues for future research are provided by the further integration of hybrid systems and multimodal data
Design and Implementation of a Force Sensor Glove for Post-Accident Patient Rehabilitation
Get PDFIntegrating force sensors into wearable devices offers an advanced solution to optimize physical therapy processes in patients’ post-accident recovery. This system uses an ergonomic rehabilitation glove equipped with force-sensitive sensors (FSR), capable of measuring real-time forces ranging from 0.10 kg to 0.60 kg during therapeutic exercises. These data, transmitted to a database in real-time and stored in a structured manner, allow for precise adjustments to treatment regimens and monitoring of therapeutic progress. The 3.7V rechargeable lithium-ion battery ensures prolonged sessions without interruptions, while the ergonomic design of the glove promotes comfort and treatment adherence. By combining IoT technology with biomedical sensors and a robust storage system, this solution addresses the accessibility gap to advanced rehabilitation tools, especially in regions with limited resources. Its implementation has the potential to transform therapeutic practices, providing personalized treatments and improving the quality of life of patients with reduced mobility
DATDL-DCNN-BiLSTM: Dual Attention Temporal Difference Learning Based Distributed Deep Learning Model for Brain Tumor Detection
Get PDFThe brain tumor (BT) is a critical disorder related to neurons characterized through the proliferation growth. The survival rates associated with this disease are steadily declining, primarily due to insufficient early detection and precise diagnosis of BT. The manual inspection often suffers from subjectivity, low accuracy, and inefficiency due to complex tumor shapes. To identify and handle the large sized datasets along with capturing the more subtle tumor features, this study proposes a model named socio-swarm intelligence optimizer (SSIO) enabled dual attention temporal difference learning with distributed convolutional neural network and bidirectional long short-term memory (SSIO-DATDL-DCNN-BiLSTM) framework for identification of BT, focusing on the integration of advanced optimization techniques. The dual attention-AlexNet layer efficient statistical triangular ResNet (DA-ALESTR) provides detailed localization of relevant features. The LayerCAM (layer-wise class activation map) and AlexNet features in the model add more deliberation by capturing high-level semantic patterns and enhancing interpretability. The SSIO optimizer increase the interpretation through adjusting the factors. The results of the proposed SSIO-DATDL-DCNN-BiLSTM demonstrates higher scores on accuracy, recall, F1-score, and precision with 99.56%, 98.27%, 96.80%, and 99.79% with training data, and with k-fold 96.95%, 96.96%, 96.77% and 97.15% using BraTS 2018 dataset
Role of AI in Education: A Review
Get PDFIn general, recent developments in AI or artificial intelligence have resulted in positive expectations about the future effects of AIED or AI in education and learning. However, it is important to note that most of these expectations are usually based on misunderstanding the current possibilities and lack of awareness about the current applications of AI in education. That is why in this review paper, a detailed review of the role of AI in education is offered together with a typology of AIED. Different AI systems in education are reviewed, and the obstacles of AI in education are also identified and discussed that must be addressed to make sure that AI systems can be better used in the field of education