Online-Journals.org (International Association of Online Engineering)
Not a member yet
9805 research outputs found
Sort by
The Impact of Implementing a Moodle Plug-in as an AI-based Adaptive Learning Solution on Learning Effectiveness: Case of Morocco
Get PDFThis article presents feedback on the implementation of an Artificial Intelligence-based adaptive learning Moodle plugin aimed at enhancing the engagement levels and academic performance of 102 Moroccan high school students. The primary objective of this study was to assess and compare the performance of students utilizing the adaptive learning system with those employing conventional learning methods. To guarantee the efficacy of this approach, a participant satisfaction survey and a comprehensive summative evaluation were conducted, revealing the positive impact of AI-based adaptive learning on the participants. The results of this study highlight the potential benefits of integrating AI-driven adaptive learning into high school computer science curricula, emphasizing how it may raise student engagement and academic performance. These results strengthen the determination to use this teaching methodology with students in future educational activities
Evaluating the Practicality of Android-Based Courseware in Enhancing Electrical Circuit Proficiency among Vocational Students
Get PDFThe evaluation and analysis of the practicality of Android-based courseware in enhancing vocational students’ understanding of electrical circuits (EC) is the primary focus of this research. A quantitative survey-based research approach was employed, utilizing the Practicality Assessment Instrument to evaluate the practicality level of the Android-based courseware among students. The collected data will undergo statistical analysis using descriptive analysis techniques. The practicality assessment results for each aspect will be calculated as a percentage and grouped into various categories. The findings reveal a high practicality level across different aspects, namely 90.19% for Availability and Accessibility, 89.88% for Performance and Responsiveness, 86.96% for Content Compatibility and Completeness, and 90.06% for Functionality and Resource Utilization. These outcomes demonstrate that the Android-based courseware serves as a highly practical learning medium for enhancing the understanding of electrical circuits. The integration of Android-based technology in the educational environment has proven to be effective and beneficial. These findings offer valuable insights for educators, instructional designers, and stakeholders to enhance modern learning environments. Future research can further investigate the impact of Android-based courseware on learning outcomes and explore additional practical dimensions to comprehensively evaluate its effectiveness
Problem-Based Learning Management System (PBLMS): A Mobile Learning Application to Facilitate Creative Thinking Skills (CTS) of Prospective Physics Teachers
Get PDFCreative thinking is a 21st-century skill that lecturers should facilitate since the current challenge and conditions are getting more complex. These skills can be facilitated using technology through mobile learning using Problem-Based Learning Management System (PBLMS). This study aimed to obtain an overview of the improvement in the creative thinking skills of prospective physics teachers after participating in mobile learning using PBLMS. This is a quasi-experimental study with a non-equivalent control group design. The population of this study consisted of 80 first-year students at a university in Tasikmalaya. The sample consisted of 50 students who were selected using purposive sampling. They were 16 men and 34 women with an age range of 19–21 years. The data were collected using tests, observations, and interviews. The instruments used in this study included Creative Thinking Skill (CTS) tests, that is, the sheets of learning process observation, and interview guidance. The enhancement of CTS was processed using normalized gain and strengthened statistically by two mean difference tests. The group that took lectures using PBLMS had a higher score with an N-Gain of 0.72 (high category), while the group without PBLMS had an N-gain of 0.61 (medium category). Statistically, the two mean difference tests showed that the significance obtained was 0.003, so it can be concluded that there was a significant difference between the groups using PBLMS and without PBLMS. The research can provide an overview of the usefulness of PBLMS in supporting the achievement of learning objectives and other related skills
Mobile Application to Improve the Follow-up and Control Process in Patients with Tuberculosis
Get PDFTuberculosis is a severe and life-threatening illness that affects numerous individuals worldwide every day. The key objective of this study was to create a system that could enhance the monitoring and management of tuberculosis patients. To achieve this goal, the Mobile D methodology was utilized because of its effectiveness in project management. This methodology emphasizes test-driven development, continuous integration, and optimization to enhance software processes. The outcome of this research was a prototype of a mobile application specifically designed for individuals with tuberculosis. Professionals and people affected by the disease assessed the quality of the prototype. They evaluated its effectiveness, user-friendliness, design, and functionality and gave ratings of 4.77 and 4.69 on a Likert scale, respectively. These figures indicate that the prototype meets high-quality criteria. In conclusion, this research successfully created an efficient prototype that enhances the monitoring and control of tuberculosis patients. The prototype includes features such as real-time consultations for immediate interaction between physicians and patients, clinical history visualization, and medication reminders, all of which improve the user’s experience
AI-Based Hate Speech Detection in Albanian Social Media: New Dataset and Mobile Web Application Integration
Get PDFThis paper aims to advance AI-based hate speech (HS) detection in the Albanian language, which is resource-limited in natural language processing (NLP). Addressing the challenge of limited data, we developed a human-annotated dataset of over 11,000 comments, carefully curated from various Albanian social media platforms, containing a substantial number of HS instances. The dataset was annotated using a detailed two-layer taxonomy to capture the complex dimensions of HS. To ensure high-quality annotations, three expert annotators applied a majority voting system, achieving a substantial Fleiss’s kappa coefficient of 0.62, underscoring the reliability and consistency of the annotations. We conducted a comparative analysis of several machine learning (ML) algorithms, including support vector machine (SVM), Naïve Bayes (NB), XGBoost, and random forest (RF), paired with various text vectorisation techniques and pre-processing methods. In binary classification, the NB model with term frequencyinverse document frequency (TF-IDF) vectorization achieved the highest performance, with an F1 score of 0.80. For multiclass classification, XGBoost outperformed other models, achieving an F1 score of 0.77. Interestingly, our experiments revealed that pre-processing steps generally reduced model performance, suggesting that raw text inputs work better for the Albanian language. Through error analysis using local interpretable model-agnostic explanations (LIME), we identified key challenges, such as polysemy and irony, which contributed to misclassifications. To demonstrate the practical applicability of our work, we developed a user-friendly mobile web application based on the best-performing model, providing realtime HS detection with the potential for integration into social media platforms
Energy-Efficient Green Information Centric Networking for Future Wireless Communications
Get PDFEnergy-efficient green information-centric networking (EEGICN) is proposed in this paper for advancing future wireless communication networks by addressing the challenge of energy consumption. This model can adapt the power consumption of network nodes to optimized values according to the associated link utilization. The model aimed to reduce energy consumption and increase network performance and stability. The EEGICN model incorporates efficient routing mechanisms, content caching strategies, and energy-intelligent communication protocols to improve resource utilization across the network infrastructure. EEGICN minimizes large data transmission, reduces power consumption, and reduces network congestion. Popular resources are cached in key network locations, and proximity data is exchanged to achieve this. The model also includes dynamic power management algorithms that adapt to changing traffic demand and network conditions to provide consistent performance across a variety of operational scenarios. In comparison to current wireless network systems that employ various forms of cache, the evaluation findings demonstrated that EEGICN can increase network efficiency by dramatically lowering the number of hops and energy consumption. Future networks may find this application to be a quick and easy way to transmit content
Implementation of the Junior Mobile Programmer Professional Competency Certification Assessment Model
Get PDFThis study is based on the gap in human resources in the proportion of Indonesian workers lower compared to other ASEAN countries, including human resources in the IT sector. Another problem is that the assessment process and results in the junior mobile programmer scheme run by the Digital Technology Professional Certification Institute (LSP) have not been maximally tested; the assessment activities carried out have not fully implemented a technology- based system in a centralized and systematic manner, causing problems in the remote assessment process. Lack of involvement of professional associations, academics, and industry in designing tested and reliable assessment models. The specific aim of this study is to implement an effective junior mobile programmer professional competency certification assessment model. This study method is an experiment by implementing a professional competency certification assessment model for junior mobile programmers. The test subjects are participants in the results of the Ministry of Communication and Information’s Digital Talent Scholarship (DTS) Vocational School Graduate Academy (VSGA) training program, totaling 40 sessions, consisting of 20 sessions for the experimental class and 20 sessions for the control class. Data collection instruments include questionnaires, documentation, interview guides, observations, and competency tests. The study results prove that after being implemented, the professional competency certification assessment model for junior mobile programmers has proven to be effective
Interoperability Blockchain, InterPlanetary File System and Health Level 7 Framework for Electronic Health Records
Get PDFPatient medical records and their accurate recording, storage, protection, and access are essential elements to high-quality healthcare. While many parts of the world have moved to traditional digital systems and electronic health records (EHRs), these systems require complex evaluation and large infrastructure investments, lack interoperability, and introduce the constantly-increasing challenges of cyber-attacks and digital security. The aim of this study is to address these challenges through a secure and accessible EHR management system, applied to allergy and family records, based on blockchain technology, the InterPlanetary File System (IPFS) protocol, and the health level 7 (HL7) fast healthcare interoperability resources standard. The proposal was carried out in four phases: (1) blockchain architecture design, (2) blockchain network design, (3) interoperability design, and (4) web application design. A performance evaluation of the system was conducted to determine the throughput and latency metrics. The results presented a maximum medical record reading and writing throughput of approximately eight transactions per second, with a write latency averaging 5,926 ms to 51,836 ms and a reading latency of 4,783 ms to 45,500 ms. With the addition of a survey of 21 patients and 10 healthcare professionals indicating that both groups strongly agree that the system meets the criteria of high-quality healthcare, all study results present a framework that could serve as a model for the adoption of standards-based, accessible, and secure EHR systems
Chatbots: The Future of Education?
Get PDFChatbots are emerging technologies with the potential to improve teaching and learning processes. This paper conducts a systematic review of research on chatbots in education, focusing on articles published in Online-Journals.org from 2011 to 2024. The aim is to examine the various aspects addressed by the authors, such as design principles, pedagogical roles, interaction styles, and evaluation methods for chatbots in educational contexts. The tools were classified according to the type of user they targeted, revealing that 42% were aimed at students, 11% at teachers, 29% at both types of users, and 18% at external users. The characteristics of the tools along the above dimensions were analyzed, highlighting trends, good practices, and observed limitations. The key findings, challenges, and implications of using chatbots to improve learning outcomes, and experiences were discussed. It was concluded that chatbots are an emerging technology that offers benefits such as teaching personalization, self-learning, and real-time feedback but also poses challenges, such as evaluation and research into their effectiveness for education
An Investigation of University Students' Attitudes Towards Artificial Intelligence Ethics
Get PDFThe increasing complexity and widespread use of artificial intelligence (AI) underscore the importance of its ethical dimensions. Understanding diverse perspectives on AI ethics is crucial, especially among university students who will shape future technological advancements. This study aims to deeply examine university students’ attitudes toward AI ethics, focusing on fairness, transparency, privacy, responsibility, and non-maleficence. A mixed-methods approach was used. In the quantitative phase, 355 students from engineering (E) and education science (ES) programs were evaluated using the AI Ethics Attitudes Scale. In the qualitative phase, semi-structured interviews with 23 students were thematically analyzed to gain detailed perspectives based on gender and discipline. The findings revealed significant gender-based differences in fairness and privacy, with female students scoring higher than male students. Interdisciplinary differences were evident in the transparency dimension, where ES students showed greater sensitivity. Interviews highlighted that female student emphasized legal compliance and data security more, whereas male students focused on financial information privacy. ES students prioritized user-friendly language and feedback and complaints in transparency discussions