Online-Journals.org (International Association of Online Engineering)
Not a member yet
9805 research outputs found
Sort by
Detect Lane Line for Self-Driving Car Using Hue Saturation Lightness and Hue Saturation Value Color Transformation
Get PDFSelf-driving vehicles require the ability to perceive and understand their surroundings, just like human drivers. It entails navigating efficiently on roads, obeying traffic signs and signals, and avoiding collisions with other vehicles and pedestrians. To address the challenges associated with object detection in self-driving cars, an effort was made to demonstrate lane detection using the OpenCV library. To achieve this goal, the well-established probabilistic Hough transform technique is used for line detection. Before applying Hough transforms, several pre-processing techniques are used, including converting the image to grayscale, camera calibration, and implementing a masking filter. In addition, edge detection is performed using the edge detection method. The study also indicates a preference for the use of HSL (Hue, Saturation, and Lightness) and HSV (Hue, Saturation, Value) color spaces. When HSL is applied, white lines appear purer and brighter, resulting in superior performance compared to using HSV specifically to detect white. This algorithm proved particularly effective in detecting straight lanes, which achieved an accuracy ratio of 96.06%. By incorporating these methodologies, the lane detection algorithm implemented with the OpenCV library addresses the challenges of self-driving vehicles, providing them with improved perception capabilities similar to human drivers
Pre-Evaluation with a Personalized Feedback Conversational Agent Integrated in Moodle
Get PDFPre-evaluation of the learner's level is a common learning strategy designed to determine the prior knowledge and skills of learners. A pre-evaluation is carried out at the beginning of the course and based on the results obtained, personalized resources will be provided that respond to individual learner needs. This paper presents a pre-evaluation for a C programming language course by providing, at the end of the quiz, a personalized formative feedback and recommendation to the learners. We have developed our conversational chatbot named QuizCbot, which allows learners to go directly to the parts where they need the most help through the personalized feedback provided to them, including their final scores, the questions they answered correctly and the questions they answered incorrectly with the correct answer and explanation. Hence, the chatbot makes a recommendation on the concepts in which the learner did not obtain the average, identifying the concepts not mastered where the learner needs more (or less) support. Determining what learners know and don't know can help to improve the learning experience. We have integrated our QuizCbot chatbot, which is based on Natural Language Understanding (NLU), into the Moodle learning environment
Influences of Use of Flipped Classroom Models on the Learning Outcomes of Students Majoring in Road and Bridge Engineering Technology
Get PDFAbstract—The new “Internet+” teaching mode during the COVID-19 pandemic has guaranteed the smooth learning progress of university students in China. High-efficiency reconstruction of time and space for knowledge teaching and internalization based on informationalized teaching mean is an important approach to online learning. A flipped classroom is a teaching mode that is formed through bottom-up exploration. Combined with teaching practical situations, the flipped classroom realizes the transformation from the teacher-centered mode to the student-oriented mode successfully and has important value to the teaching of professional core courses, which are difficult to be learned. In this study, 80 freshmen majoring in Road and Bridge Engineering Technology at Yellow River Conservancy Technical Institute in Henan Province of China were selected as research objects, and Road Survey Design and Lofting was chosen as the teaching course. Under these circumstances, a teaching experiment comparison was designed. The experimental group used flipped classroom technology based on Attention, Relevance, Confidence, and Satisfaction (ARCS) motivation model theory, while the control group used the traditional teaching mode. Research results demonstrate that before the experiment, the learning outcomes of two groups in Road Survey Design and Lofting were basically consistent (P=0.908>0.05) without obvious differences. After finishing the experiment, the post-test results of the control group have not improved significantly compared with the pre-test results (P=0.0938>0.05). However, the post-test results of the experimental group have improved significantly compared with the pre-test results (P < 0.001). The average scores of the experimental group are far higher than that of the control group, thus indicating the evident progress of the experimental group. Noticeable differences in the post-test results between the experimental group and the control group are observed (P < 0.001). The research results are of great significance to enriching the teaching mode of core application courses for engineering majors in university, as they provide evidence that the flipped classroom increases the learning interests and motivation of students and demonstrate the teaching effect of flipped classroom technology in universities
Effects of Touch-type Online Educational Games on Learners’ Learning Motivations
Get PDFWith the advancement of science and technology, electronic devices are more extensively popularized, and students are being exposed to touch-type online at an early age, thus promoting the digitalization of children’s education and contributing to the proliferation of learning resources. Touch-type educational games emphasize learning autonomy, integrate teaching knowledge contents with games, and highlight that when using educational games, learners can obtain immediate and real feedback and identify learning and game objectives, thereby intensifying their learning. In this study, a questionnaire regarding the effect of touch-type online game education on learners’ learning motivations was designed on the basis of educational game theory. The mediating role played by learning immersion between the two was also measured. Results show that the overall Cronbach α coefficient is 0.825, the KMO value is 0.688, and the corresponding P value of Bartlett sphericity test is 0.0. In touch-type online game education, multi-organ sensing, touch gesture, and multi-hotspot response significantly affects learners’ learning motivations. Learning immersion exerts a masking effect on teachers’ initiatives in promoting learning motivations. The proportion of touch games play during class hours has different effects on learning motivation (p=0.020<0.05). The findings are critical for investigating the effects of touch interaction models on learners’ learning motivations, developing a set of evaluation indexes for educational game learning accessibility, and perfecting their evaluation methods
Comprehensive Test and Evaluation Path of College Teachers' Professional Development Based on a Cloud Education Big Data Platform
Get PDFTeachers serve as carriers who shoulder the important task of improving the quality of education, and their professional level affects the quality of vocational and technical personnel training. At present, the professional growth of teachers in vocational colleges has attracted more and more attention from the society. This article studies the comprehensive test and evaluation path of college teachers' professional development based on cloud education big data platform. This article constructs a "supply-demand relationship" model between cloud education big data platform and college teachers' professional development, and expounds the comprehensive test and evaluation strategy of college teachers' professional development based on cloud education big data platform. This article constructs a comprehensive measure index system of influencing factors of college teachers' professional development, and weights the evaluation indexes based on AHM attribute hierarchy model. By optimizing the super-efficiency SBM model, it proposes a comprehensive evaluation method considering the temporal and spatial features of college teachers' professional development level, which is suitable for different professional teachers' professional development features. The experimental results verify the effectiveness of the evaluation index system and evaluation model
Impact of Deep Learning Strategy in Mathematics Achievement and Practical Intelligence among High School Students
Get PDF— To identify the effect of deep learning strategy on mathematics achievement and practical intelligence among secondary school students during the 2022/2023 academic year. In the research, the experimental research method with two groups (experimental and control) with a post-test were adopted. The research community is represented by the female students of the fifth scientific grade from the first Karkh Education Directorate. (61) female students were intentionally chosen, and they were divided into two groups: an experimental group (30) students who were taught according to the proposed strategy, and a control group (31) students who were taught according to the usual method. For the purpose of collecting data for the experiment, an achievement test was built, which is in its final form (25) test items and a practical intelligence test out of (20) test items of the objective type for both of them. Based on the findings, the students of the experimental group who studied according to deep learning strategies outperformed on those who by the traditional.
 
Top 10 Most-Cited Articles Concerning Blended Learning for Introductory Algorithms and Programming: A Bibliometric Analysis and Overview
Get PDFBlended learning, also known as mixed-mode instruction, combines in-person and online instruction. Blended learning is widely used in school and university subjects. This research aims to determine how blended learning has been applied to algorithms and programming courses over the last 20 years. This study analyzes the quality and quantity of scientific publications using bibliometric techniques and then provides an overview of how blended learning is used and its impact. For this analysis and review, this study conducted a bibliometric analysis of articles published in the last 20 years (2000–2021) and then presented the 10 most cited articles. We established the following criteria for articles: 1) sourced from the Scopus database, 2) concerned about blended learning in algorithms and programming, and 3) publication is limited to articles published in indexed international journals and proceedings. The VOSviewer and MS-Excel applications help with data presentation in this method. We collected 240 articles that met these criteria from the Scopus database, which contained 297 articles published between 2000 and 2021. The most-cited article received 52 citations, while the least received only 3. The top 10 most cited articles are from the following countries: 1) Norway, 2) Serbia, and 3) Saudi Arabia. We divided the articles into categories based on the Sustainable Development Goals (SDGs). The findings of this study can be used as a reference for state-of-the-art and novelty, as well as for the dissemination of scientific references related to the use of blended learning for introductory algorithms and programming
An Analysis of Educational Portals’ Implementation for Effective Online Learning
Get PDFInformation Communication Technology (ICT) is advancing with rapid development aimed at offering quality education among learners to ensure satisfaction as well as convenience. With the devastating effects of Coronavirus, many institutions are relying on e-learning technologies to carry out both administrative and academic activities to promote social distancing as well as curb the spread of the novel coronavirus. E-learning allows students from different geographical locations to learn as if in the classroom through the internet; providing tools that enhance effective teaching and learning. The question we ask is: are e-learning platforms performing as expected? To find out the answer to this question, an analysis of the factors identified to have affected implementation utilizing the IS implementation framework within two HEIs in Ghana is outlined in other to enable the identification of similarities and differences to be done
Expanding Multilingual Learning as a Pathway to Equity during the COVID-19 Pandemic: A Geographical Analysis of a WHO Online Course in 45 Languages
Get PDFReal-time learning in health emergencies is a critical mechanism to provide frontline health workers, responders, decision-makers and the public with access to the latest knowledge to save lives, reduce disease transmission and protect the vulnerable. The World Health Organization (WHO) established the OpenWHO.org learning platform to meet this need. Courses are free, self-paced, accessible in low-bandwidth and offline formats, and available in national and local languages. Multilingual production was prioritized and expanded to meet the learning needs of the COVID-19 pandemic. Enrolment data from the introductory COVID-19 course, which has more than 1 million enrolments across 45 language versions, were examined according to language and geographical reach to assess how multilingual availability contributes to equity in learning. The analysis found that most language versions had uptake clustered in key countries where native speakers are concentrated, while use of some translations was more broadly dispersed. In nearly ¾ of the available language versions of the course, more than ⅓ of enrolments were found in the top country of use. The findings suggest that multilingual courses served as entryways for learners who may not have otherwise been able to participate, even as enrolment numbers likely underestimate the impact. A production policy that prioritizes translation of open online courses into diverse languages contributes to equity in access to public health knowledge at the global and country levels during health emergencies
Analysis and Prediction of Student Performance Based on Moodle Log Data using Machine Learning Techniques
Get PDFDuring the COVID-19 Pandemic, many universities in Thailand were mostly locked down and classrooms were also transformed into a fully online format. It was challenging for teachers to manage online learning and especially to track student behavior since the teacher could not observe and notify students. To alleviate this problem, one solution that has become increasingly important is the prediction of student performance based on their log data. This study, therefore, aims to analyze student behavior data by applying Predictive Analytics through Moodle Log for approximately 54,803 events. Six Machine Learning Classifiers (Neural Network, Random Forest, Decision Tree, Logistic Regression, Linear Regression, and Support Vector Machine) were applied to predict student performance. Further, we attained a comparison of the effectiveness of early prediction for four stages at 25%, 50%, 75%, and 100% of the course. The prediction models could guide future studies, motivate self-preparation and reduce dropout rates. In the experiment, the model with 5-fold cross-validation was evaluated. Results indicated that the Decision Tree performed best at 81.10% upon course completion. Meanwhile, the SVM had the best result at 86.90% at the first stage, at 25% of the course, and Linear Regression performed with the best efficiency at the middle stages at 70.80%, and 80.20% respectively. The results could be applied to other courses and on a larger e-learning systems log that has similar student activity conditions and this could contribute to more accurate student performance prediction