Online-Journals.org (International Association of Online Engineering)
Not a member yet
9805 research outputs found
Sort by
The Use of ChatGPT in Task-Based ESP Learning at University: Does It Make a Difference?
Get PDFThis study investigates the integration of ChatGPT into task-based learning (TBL) environments for English for specific purposes (ESP) at a technical university in Ukraine. Conducted with 27 bachelor students, the research employs a mixed-methods approach to evaluate the effectiveness of ChatGPT in enhancing students’ writing task performance (creating a sustainable campus initiative proposal). The use of a quantitative research method permitted comparing the quality of students’ writing between two TBL groups: the one that used ChatGPT to complete the tasks and the one that did not use this tool. The qualitative method was used to survey students and explore their attitudes towards using ChatGPT to complete the tasks. Results indicate that students using ChatGPT showed the same level of achievement as those who did not use it in generating ideas and structuring initial drafts but struggled with the deeper aspects of writing, such as communicative achievement and creativity. Also, the ChatGPT’s ability to enhance language accuracy was evident, yet not superior to traditional methods. Students generally perceive ChatGPT positively, appreciating its role in facilitating the writing process and providing immediate assistance. However, they also acknowledge the necessity for critical evaluation and human refinement of artificial intelligence (AI)-generated texts to ensure the quality and originality of their work. This study concludes that while AI tools, such as ChatGPT, can complement traditional teaching methods, they cannot replace human evaluation and expertise
Optimizing Learning Path Design in Mobile Learning Platforms for Online Courses
Get PDFWith the rapid advancement of information technology, online education, particularly vocational education, has become a vital avenue for enhancing skills and knowledge. Vocational education necessitates flexible and personalized learning path design to accommodate the diverse needs and behaviors of learners. Mobile learning platforms, as a pivotal form of modern online education, provide learners with the convenience of accessing educational resources anytime and anywhere. However, existing methods for optimizing learning paths exhibit notable limitations, primarily in accurately capturing learners’ dynamic behaviors and in providing personalized and intelligent path design. Therefore, how to optimize learning paths based on learners’ dynamic behavior data has become a research hotspot in academia and educational practice. At present, many studies focus on matching analysis based on students’ static characteristics with course content but overlook learners’ behavioral changes and dynamic needs during the learning process. Traditional recommendation algorithms and rule-based path design methods are difficult to cope with complex learning behaviors and diverse learner needs. This study addresses these limitations by proposing an optimization model for mobile learning path design based on multi-view prediction of dynamic student behaviors. The model extracts mobile interaction features from student groups, constructs a multiple mobile behavior collaborative encoder, and employs multiple task label prediction techniques to achieve personalized and intelligent optimization of learning paths. The results demonstrate that this approach significantly enhances the learning efficiency and experience of learners, offering novel insights and technological support for the path design of mobile learning platforms
Personalized Guidance for Moroccan Students: An Approach Based on Machine Learning and Big Data
Get PDFHelping Moroccan students choose their high school presents significant challenges influenced by a variety of factors, including academic achievement, potential, and environmental influences. This study addresses these complexities using advanced data analytics and intelligent algorithms. We collected and examined authentic data from various secondary schools across Morocco, using the MASSAR system, a centralized education platform. To ensure robust model evaluation and optimized performance, we implemented 5-fold cross-validation and extensive hyper-parameter tuning for both support vector machine (SVM) and neural network models. Advanced classification algorithms, including hybrid learning techniques with neural networks and SVM algorithms, were applied, resulting in outstanding precision measures: 99.17% accuracy, 99.20% precision, 99.37% recall, 99.28% F1 score, and 0.99 area under the curve (AUC). By integrating this hybrid learning approach, powered by big data technologies such as Hadoop and Hadoop Distributed File System (HDFS), we accurately predict student choices and offer valuable academic advice. The use of a Hadoop cluster accelerated execution time by 40%. This pioneering merger underlines the adaptability and effectiveness of our approach to meeting the real-world educational challenges specific to the Moroccan context
Attention-Driven Image Captioning for Mobile Accessibility of the Visually Impaired
Get PDFIn a world increasingly reliant on visual information, individuals with visual impairments face significant challenges in understanding their environment. This paper introduces an attention-based image captioning model to improve accessibility for visually impaired users. The model integrates ResNet-152 for visual feature extraction, long short-term memory (LSTM) for text processing, and an attention mechanism to generate contextual image descriptions. Captured images are processed via a mobile device, then the description text is translated into Bahasa and converted to speech in real-time using text-to-speech technology. The system shows an average inference time of 2.99 seconds per image, enabling real-time use. The model is tested on the Flickr dataset and new datasets covering a variety of environments and object interactions. Experimental results show superior performance on the Flickr dataset (bilingual evaluation understudy (BLEU)-1: 0.59, metric for evaluation of translation with explicit ordering (METEOR): 0.25). Performance on real-world datasets is slightly lower, indicating challenges in generalizing to scenarios with occluded objects and inconsistent text. Future research will focus on scaling up real-world datasets, adversarial training, and integrating the system into devices such as smart glasses or canes for wider accessibility
A Biometric Technique to Secure Credit Card Information on Android Devices
Get PDFAdvances in digital payment systems have increased the need for robust security measures, particularly on Android devices, which are more vulnerable due to their open-source nature. Current applications require authentication, but once users are authenticated, they can proceed with payments if credit card information is stored on the device. This creates a security risk in cases where a mobile device is stolen while an active payment session is active, allowing attackers to make unauthorized payments. This paper addresses the problem of securing sensitive information stored locally on devices. It proposes a technique based on fingerprint and advanced encryption standard (AES) cryptography. Fingerprint is used for authentication, while AES is used for encryption. The technique is implemented as an Android library. The goal is to help developers secure their Android mobile applications through simple APIs without dealing with the complexity of cryptography. Experimental results show that the overhead of integrating the library into applications in terms of time and memory is insignificant
AI Conversational Agents for Corporate Language Learning: Enhancing Engagement and Retention
Get PDFe-REAL Labs are at the forefront of language education innovation, integrating AI-driven conversational agents (avatars) to transform the learning experience. These avatars serve as interactive partners in a cooperative learning framework, engaging students in dynamic, real-life dialogues tailored to their proficiency levels. By fostering an inclusive and adaptive environment, they encourage active participation and facilitate group-based language activities, enhancing collaboration and communication. The AI avatars are pivotal in guiding learners through interactive problem-solving tasks, compelling them to negotiate meaning, resolve misunderstandings, and build linguistic competence through adaptive feedback. This immersive approach accelerates language acquisition and cultivates essential social skills such as cultural awareness, critical thinking, and teamwork. Through scenario-based interactions that demand cooperation, e-REAL Labs’ AI-powered methodology ensures that every learner contributes to group success, creating a rich and engaging language-learning experience
Toward Improved Glioma Mortality Prediction: A Multimodal Framework Combining Radiomic and Clinical Features
Get PDFGliomas, especially diffuse gliomas, remain a major challenge in neuro-oncology due to their highly heterogeneous nature and poor prognosis. Accurately predicting patient mortality is essential for improving treatment strategies and outcomes, yet current models often fail to fully utilize the wealth of available multimodal data. To address this, we developed a novel multimodal predictive model that integrates diverse magnetic resonance imaging (MRI) sequences—T1, T2, FLAIR, DWI, SWI, and advanced diffusion metrics such as high angular resolution diffusion imaging (HARDI)—with detailed clinical data, including age, sex, tumor genetic markers, and WHO CNS tumor grade. Using the UCSF Preoperative Diffuse Glioma MRI (UCSF-PDGM) dataset, our study introduces an innovative framework that integrates deep learning (e.g., VGG16 for extracting embeddings from a diverse array of MRI modalities, including standard sequences and advanced diffusion metrics) with machine learning algorithms (e.g., XGBoost) to combine imaging and clinical data. This approach captures complementary insights that surpass the capabilities of both single-modal models and previous multimodal methods, which often rely on predefined radiomic features or limited integration of data types. Our results demonstrate significant improvements in predictive accuracy for glioma mortality, showcasing the value of integrating raw imaging embeddings with detailed clinical variables. By providing a more comprehensive understanding of tumor behavior and patient outcomes, our study advances glioma prognosis and supports the development of more personalized and effective treatment strategies
Brain Tumour Segmentation and Edge Detection Using Self-Supervised Learning
Get PDFBrain tumour segmentation is critical in medical image analysis, facilitating diagnosis and treatment planning in neurosurgery. Brain tumour segmentation with supervised learning shows robust results in medical imaging; however, it requires a sufficient amount of annotated data for effective learning. It is important to detect boundaries of tumour subregions accurately in fine-grained segmentation. We propose a novel approach that uses a unique dual-decoder architecture, focusing on edge identification and segmentation accuracy enhancement. Utilising a dual-decoder 3D-UNet model, we prioritise accuracy and fine-grained details in tumour segmentation and introduce an additional tumour edge detection task, aiming to move beyond traditional single-decoder approaches. Incorporating a 3D SimSiam network as the self-supervised pretraining technique, we aim to address the limitation of annotated data and enhance the segmentation accuracy. Our model surpasses many supervised variants of U-net architectures and self-supervised approaches, highlighting the importance of edge detection in tumour segmentation. The proposed approach enhances segmentation accuracy by showing an accuracy of 98.1% and provides critical boundary details for clinical decision-making. Visualisations of segmentation and edge masks further validate the effectiveness of the proposed method
An Ontological Model for Artificial Reasoning: Application to Medical Diagnosis
Get PDFRepresenting knowledge in a language that is both understandable by humans and easily exploitable by machines remains the subject of several research studies. Domain ontologies are recognized as an efficient way to describe knowledge through concepts and relations in several domains of expertise while remaining shareable and reusable. This paper aims to propose an approach for “artificial reasoning” that we consider as a foundational pillar for “Artificial Intelligence.” Our particular interest in this work is on how to design systems that can use human knowledge to process and solve the complex problem of diagnosis, given the required expertise in a specific domain of knowledge. The approach we present in this paper is based on using properties of ontologies, by representing expert knowledge through a graph reasoning model, to formalize the diagnosis process using an ontology-based model. We first describe our proposal on how to represent expert knowledge in a general way before focusing on the diagnosis problem. Finally, we apply the whole process to the specific domain of cardiology
Developing Teacher Digital Competence through Mobile and Interactive Technologies: A Systematic Review Using the TPACK Framework
Get PDFThe systematic review uses the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines to explore the development of teacher digital competence (TDC) through various digital technologies. With an emphasis on the technological pedagogical content knowledge (TPACK) framework, the study synthesizes findings from recent peer-reviewed articles to evaluate the integration of technologies such as massive open online courses (MOOCs), serious games, Internet of Things (IoT), and immersive virtual reality (VR) into educational practices. The review highlights the transformative potential of these technologies for enhancing teachers’ pedagogical strategies, fostering digital competence, and addressing gaps in educator training programs. Findings indicate that digital technologies improve immediate teacher competencies and pave the way for more interactive and inclusive learning environments. However, the small number of included studies (n = 10) and other limitations such as short-term study designs and English language only publications highlight the need for future research. The findings offer actionable insights for curriculum design, policy development, and professional training programs to equip educators with the digital competence necessary to thrive in modern educational landscapes