Online-Journals.org (International Association of Online Engineering)
Not a member yet
9805 research outputs found
Sort by
Teachers' Perceptions and Readiness for Mobile Artificial Intelligence Integration in Elementary Education
Get PDFThe integration of artificial intelligence (AI) with mobile technologies, referred to as mobile AI, has transformed elementary education by providing personalized, interactive, and accessible learning experiences; however, its successful integration is significantly influenced by teachers’ perceptions, preparedness, and pedagogical competencies. This study employed a predominantly quantitative descriptive approach, complemented by qualitative data from open-ended questions, to investigate Indonesian elementary school teachers’ perceptions and readiness to integrate mobile AI tools. The findings revealed a gap between teachers’ positive perceptions and their moderate practical readiness. Personal experience was identified as the strongest predictor of readiness, whereas cognitive understanding and practical ability were significant predictors of perceptions. The structural equation model (SEM) supported these findings and revealed that readiness results from a series of developmental sequences rather than isolated events. This study highlights the need to address both psychological and practical barriers to adoption and offers actionable recommendations for harnessing the transformative potential of mobile AI in elementary education
Interactive Cinematic Experience Design and User Behavior Analysis Enabled by Mobile Augmented Reality
Get PDFWith the rapid advancement of mobile augmented reality (MAR) technology and its deep integration into the cultural and entertainment sectors, the traditional model of film viewing is undergoing a paradigm shift from passive reception to interactive engagement. The growing demand for immersive and participatory cinematic experiences has catalyzed the convergence of the film industry with MAR technologies. However, existing research on MAR-based interactive film scenes remains constrained by insufficient capture of real-time user interactions and a superficial understanding of underlying psychological mechanisms. This study focuses on the design of interactive experiences within film scenes enhanced by MAR and addresses two core areas. First, a method for generating interactive film scenes was proposed, integrating semantic alignment between virtual elements and real-world environments, interactive logic structuring, and immersion optimization to achieve spatially dynamic and interactive cinematic representations. Second, through the application of eye-tracking and behavioral log analysis, user behavioral patterns during interaction were investigated, with the aim of mapping these behaviors to their corresponding psychological needs. The study is intended to overcome the methodological limitations of prior research, offering a theoretical foundation for the precise design of MAR-based cinematic interaction environments. Additionally, it provides practical insights for the development of interactive film products, aiming to enhance user satisfaction and promote a paradigm innovation in cinematic interaction research through a “technology + art” integrated perspective
Enhancing Mobile Application Security through Mobile Crowd Sensing and Sourcing Solutions
Get PDFThe market for Android applications has expanded dramatically, providing users with an ever-expanding array of functionality to meet a range of needs. Because mobile applications are so widely used, users are sharing more sensitive data, so protecting personal data is essential. However, this expansion has also led to a commensurate increase in cyber security threats, particularly for malware and adware that target mobile devices. To strengthen the mobile ecosystem, it is essential to divide mobile applications into discrete categories such as benign, adware, and malware. A unique sensing technique called Mobile Crowd Sensing/ Sourcing (MCS) uses users’ collective participation and their mobile devices to gather sensing data. Artificial intelligence (AI) approaches are used to make well-informed decisions that help optimize system performance as the MCS platform stores and processes vast amounts of data. The investigation primarily focuses on how AI is being applied to various MCS components, such as task distribution and data aggregation, to boost security and performance. Additionally, a novel categorization system that may be modified to compare research in this field is proposed in this paper. Because it makes it easier to identify attack surfaces that adversaries can exploit, this framework can be used to study AML in the context of MCS. It also highlights the potential vulnerabilities of AI-based MCS systems to adversarial attacks, which encourages future research to concentrate on designing resilient systems
Intelligent Task Prediction and Partial Computation Offloading in Mobile Edge Cloud Computing
Get PDFThe risk of fraudulent software or apps undermining user privacy is rising for users of cell phones and other portable electronics. Because malicious apps need less permission to run, they are more intrusive than necessary. Due to its open-source nature, support for third-party app stores, and stringent app assessment, the Android platform is more susceptible to assaults. Thus, the Android platform has also led to an increase in the use of portable computing apps. Using edge computing and cloud services, Mobile Edge Cloud Computing (MECC), showing promise in the fractional computation offload approach, has opened up fresh opportunities for mobile apps that are delay-sensitive and computationally demanding. We thoroughly examine the unpredictability method, calculating the arrivals of requests, assistance latency, and variable processing resources to solve this problem. High traffic volumes are produced by many devices that the MEC architecture can manage. First, we give a comprehensive introduction to MCC/MEC technology in this paper, covering the history and development of remote computation techniques. This paper’s main body then examines current research regarding the ideas of computing offloading, offloading granularities, and offloading procedures techniques. Furthermore, we go over optimization techniques as well as both static and dynamic offloading mechanisms. Environments. We also go over the difficulties and possible paths for MEC research in the future
Improving the Efficiency of Predicting the Heart Diseases Using Optimized Feature Selection and Ensemble Machine Learning Techniques
Get PDFMillions of people worldwide suffer from heart failure, a chronic illness that makes an effective machine learning (ML)-based approach for early detection and treatment necessary. Although medication is still the mainstay of care, exercise is becoming recognized as a useful adjunctive therapy for the management of heart failure. In this work, we used patient health parameter data to design a ML-based method to enhance heart failure detection. Improving the early detection of heart failure is our goal in an effort to save lives. To find the most important features for enhancing performance, we conducted a comparative analysis of ten distinct ML algorithms and applied feature engineering methodologies. By developing a novel new feature set, we improved our strategy and obtained the best accuracy ratings. The proposed system works on the statistical dataset and CT scan images. Numerous experiments were carried out to assess the efficacy of different algorithms, and our suggested approach outperformed other cutting-edge models, attaining impressive accuracy. Cross-validation approaches were employed to validate all applied procedures. On the CT scan dataset, AdaBoost (AB) achieved 100% accuracy, while gradient boosting (GB) led with 96% on the statistical dataset. Accuracy improved with random or synthetic data. Notably, applying a soft voting ensemble of all models further boosted accuracies to 98% and 95% on the respective datasets. Our study advances heart failure early detection techniques, which make important scientific contributions to the medical world
Development of a Mobile Video Platform for Diagnosing Human Motor Anomalies
Get PDFThe growing demand for telemedicine services necessitates innovative solutions for monitoring patients with movement disorders. The proposed mobile video surveillance system integrates computer vision, deep learning, and intelligent analysis methods to diagnose human movement anomalies accurately in real-time. The system's key components are algorithms for detecting and tracking human movements, contextual analysis, and a decision-making system. The system makes decisions about the detection or possibility of incidents, such as falls, and sends notifications to users via a mobile application. The integration of IoT sensors enables the processing of physiological data (heart rate, activity), which increases the accuracy of diagnostics and expands the system's range of applications. The proposed modular architecture of the system provides scalability and adaptability to different operating conditions. The system meets privacy standards through the use of encryption and multi-level authentication. Our proposed system ensures effective monitoring of patients with motor disorders, detects incidents promptly, and sends alerts, improving the quality of telemedicine services. 
Transformative Approach in Engineering Curricula: Enhancing Computational Thinking Through Literacy Skills for Engineering Learners
Get PDFComputational thinking (CT) is a fundamental component of problem-solving and creativity in engineering education. The incorporation of reading comprehension tasks as a method to develop and enhance CT abilities in engineering students is examined in the present study. Students are motivated to analyse, assess, and synthesize knowledge by using textbased resources skills necessary for efficient CT. This method not only improves technical competency but also develops communication and critical thinking skills that are essential for handling challenging engineering problems. This study offers ideas for incorporating reading comprehension into engineering courses, drawing on cognitive theories and educational practices. The goal is to equip students with strong CT skills that are essential in today’s technology environment
Application of Ill-Posed Problems in Mathematical Modeling, Data Analysis, and Business Mathematics
Get PDFThis paper explores the theoretical foundations and practical applications of ill-posed problems in mathematical modeling, data analysis, and business mathematics. Ill-posed problems, which lack existence, uniqueness, or stability of solutions, frequently emerge in real-world scenarios such as inverse problems, machine learning, and optimization. The study reviews regularization techniques like Tikhonov and LASSO methods, which are essential for stabilizing solutions and ensuring reliable outcomes in fields ranging from medical imaging and geophysics to financial forecasting and risk modeling. Through detailed case studies and mathematical formulations, the authors highlight the crucial role of handling ill-posedness in extracting meaningful insights and making informed decisions under uncertainty
Enhancing Learners’ Spelling Skills with an Interactive Chatbot Facilitator
Get PDFThis study attempted to design an interactive chatbot to function as the facilitator for improving spelling skills and elicit students’ perceptions of using chatbots in the language learning process. To collect the required data, 60 Omani EFL students were divided equally into control and experimental groups, each with 30 students, to collect the necessary data. Three instruments were used to collect the necessary data, including a newly researcher-designed WhatsApp bot, a perceptions questionnaire adopted from Khan et al. [1], and the NorthStar GCC book series to elicit the vocabulary for spelling practice. The findings disclosed that using interactive chatbots in a learning context improved spelling skills among experimental group participants. Learners who interacted with the bot during the treatment period showed favorable perceptions toward its use in learning. Teachers would benefit from using a WhatsApp bot to send extra materials, allowing students to access materials without time and place limitations
Systematic Review and Framework for AI-Driven Tacit Knowledge Conversion Methods and Machine Learning Algorithms for Ontology-Based Chatbots in E-Learning Platforms
Get PDFThe conversion of tacit knowledge, which is deeply rooted in personal experience and often difficult to articulate, presents a significant challenge within knowledge management systems. Ontology-based chatbots offer a promising solution by leveraging structured knowledge representations and advanced natural language processing (NLP) techniques to facilitate this transformation. This paper explores the various methods and algorithms used in developing ontology-based chatbots, with a particular focus on their role in converting tacit knowledge into more accessible forms. Additionally, it provides a comparative analysis of the algorithms employed, highlighting their respective strengths and weaknesses. Ultimately, this study addresses the critical challenge of managing and converting tacit knowledge, with the aim of enhancing the overall effectiveness of knowledge management systems