scholarly journals The Application of Machine Learning and Neural Networks to Automated Text and Visual Assignment Verification Used as Assistance to Educators

Author(s):  
Н. О. Бесшапошников ◽  
М. С. Дьяченко ◽  
А. Г. Леонов ◽  
М. А. Матюшин ◽  
А. E. Орловский

Процесс цифровизации образования, активно проводимый в нашей стране и по всему миру, позволил более широко применить в учебном процессе современные приемы преподавания, перенося часть педагогической нагрузки с очного формата на дистанционный. Проектируемые и используемые цифровые образовательные платформы уже сейчас включают в себя не только оцифрованный лекционный видеоматериал и электронные формы учебников, но и элементы автоматизации проверки выполненных учащимися заданий. Расширение области применения автоматической проверки решенных учащимися задач и выполненных упражнений является объективной необходимостью, в противном случае при дистанционных формах образовательного процесса резко возрастает нагрузка на педагога, который должен выделять значительное время на проверку увеличившегося самостоятельной работы школьников и студентов. Кроме того, при дистанционном преподавании снижается эффект личного присутствия педагога, когда учитель и ученики разделены экранами компьютеров. Существенной помощью может стать использование интеллектуальных помощников преподавателя и автоматизированных систем проверки, построенных методами машинного обучения и технологии нейронных сетей. В настоящей статье рассмотрены подходы к решению поставленных задач по автоматической проверке графических заданий и выявлению заимствований в текстовом виде. Показаны возможные варианты реализации этих функций с использованием технологий искусственного интеллекта. The digitalization of education in Russia and worldwide enables a more extensive introduction of advanced teaching methods through a partial switch from offline to online teaching. The existing and coming e-learning platforms feature not only digital lecture videos and e-textbooks, but some automated assessment/grading tools. There is a need to expand the coverage of such tools to avoid the extreme burden of online teaching as the educator has to allocate significant time for assessing the increased amount of high school/university student assignments. Also, distant learning diminishes the effect of the educator personal presence since the teacher and the student are separated by their computer screens. Smart educator assistants and automated assessment tools based on machine learning and neural networks can significantly alleviate the problem. This study offers some strategies for automated assessment of graphic assignments and checks for plagiarism. Possible AI-based implementations of such features are presented.

2020 ◽  
Vol 12 (24) ◽  
pp. 10367
Author(s):  
Claudiu Coman ◽  
Laurențiu Gabriel Țîru ◽  
Luiza Meseșan-Schmitz ◽  
Carmen Stanciu ◽  
Maria Cristina Bularca

The research focuses on identifying the way in which Romanian universities managed to provide knowledge during the Coronavirus pandemic, when, in a very short time, universities had to adapt the educational process for exclusively online teaching and learning. In this regard, we analyzed students’ perception regarding online learning, their capacity to assimilate information, and the use of E-learning platforms. An online survey based on a semi-structured questionnaire was conducted. Data was collected from 762 students from two of the largest Romanian universities. The results of the research revealed that higher education institutions in Romania were not prepared for exclusively online learning. Thus, the advantages of online learning identified in other studies seem to diminish in value, while disadvantages become more prominent. The hierarchy of problems that arise in online learning changes in the context of the crisis caused by the pandemic. Technical issues are the most important, followed by teachers’ lack of technical skills and their teaching style improperly adapted to the online environment. However, the last place was assigned by students to the lack of interaction with teachers or poor communication with them. Based on these findings, research implications for universities and researchers are discussed.


2019 ◽  
Vol 5 (12) ◽  
pp. eaay6946 ◽  
Author(s):  
Tyler W. Hughes ◽  
Ian A. D. Williamson ◽  
Momchil Minkov ◽  
Shanhui Fan

Analog machine learning hardware platforms promise to be faster and more energy efficient than their digital counterparts. Wave physics, as found in acoustics and optics, is a natural candidate for building analog processors for time-varying signals. Here, we identify a mapping between the dynamics of wave physics and the computation in recurrent neural networks. This mapping indicates that physical wave systems can be trained to learn complex features in temporal data, using standard training techniques for neural networks. As a demonstration, we show that an inverse-designed inhomogeneous medium can perform vowel classification on raw audio signals as their waveforms scatter and propagate through it, achieving performance comparable to a standard digital implementation of a recurrent neural network. These findings pave the way for a new class of analog machine learning platforms, capable of fast and efficient processing of information in its native domain.


2021 ◽  
Vol 16 (1) ◽  
pp. 12-23
Author(s):  
Sriyani Mentari ◽  
Endang Sri Andayani ◽  
Sulikah Sulikah ◽  
Primasa Minerva Nagari

This paper aims to provide an alternative design for Simple Cooperative Learning on online learning by accommodating a variety constraints and difficulties faced by teachers and students and answer weaknesses of existing methods. This study used research and development method using ADDIE (Analysis, Design, Development, Implementation, and Evaluation) design to produce an online-based cooperative learning model, namely SCL-D (Simple Cooperative Learning Design). The survey was conducted on a sample of 153 students at state and private vocational schools in Malang city. The results of this research are a learning model. Therefore, this method is suitable for completing research objectives, namely producing an SCL-D learning model that is suitable for learning accounting for vocational high schools with 3M requirements ‘easy, cheap, and attractive’. Online-based learning has many advantages as well as weaknesses. Various e-learning platforms make it easy for teachers and students to interact in online learning. The teacher's ability to design attractive distant learning is a determining factor for the success of the learning process. The test results of the SCL-D model show that through this simple cooperative learning design improves student learning achievement.


Author(s):  
Syarifah Rohana

The sophisticated information and technology (IT) development can be the answer for various problems post the covid-19 pandemic, particularly the teaching and learning challenges. The role of IT that is booming nowadays is online learning. Online learning is obviously different from regular learning. In this mode of learning, the students are required to have the ability to receive and process information. It serves as media that connect teachers and students who are being remote from one another at any time and anyplace. There are various media utilized to perform online learning such as WhatsApp, Google Meet, Zoom, Google Classroom, and other e-learning platforms. Among all these media, though, WhatsApp apparently appointed as the simplest and easiest media to access in all levels of education. Online learning at current is the effective medium to carry on the teaching and learning process in all levels of education. For the effectiveness of online teaching and learning process during the covid-19 pandemic, there have been a number of learning models suggested by the expert such as remote learning, face to face learning, e-learning, project-based learning, and Blended Learning.


Author(s):  
Onorina Botezat ◽  
Ramona Mihaila

As reported by the UN, the COVID-19 pandemic has touched almost 1.5 billion students forcing school cessations in 191 countries, changing the daily-routine of over 63 million teachers. While UNESCO and partners launched the Global Educational Coalition to produce solutions to “make digital learning more inclusive,” aiming at helping countries to gather resources to implement “remote education through hi-tech, low-tech and no-tech approaches,” a lot of actors have been holding webinars on the educational challenges and dimension of the pandemic, with participants enrolled from all over the world, from East to West.The European Association for International Education, through its EAIE Community Moment and EAIE Webinar Academy organized virtual meetings on a range of subjects, COVID19 response, mobilities and international students’ recruitment, the regional Francophone center for Central and Eastern Europe organized webinars on how to teach online the Francophonie today, the Electronic Platform for Adult Learning in Europe has constantly published updates on distant learning tools or MOOCs courses.While the webinars discuss strategies to maintain education continuity, considering children and young people in need, presenting to professors and educators a wide variety of tools, there are quite a few discussing the pedagogy of online education. Although educators have been sharing debates and exchanging opinions in reference to the e-learning platforms for more than ten years now, this very situation made them found themselves obliged to embrace, at last, the distant online learning. So, from hypothetical, theoretical, or, in some happy cases, complementary mode of e-learning platform teaching and learning, we quickly moved to the reality that imposed immediate response, within modern technology tools’ use in order to make our students carry on with their studies. And here comes the real challenge! Moving to the e-learning platforms does not mean relocating your lesson from the textbook to an educational e-learning platform, but rather translating pedagogy strategy into tool-adapted, computer-assisted online education that shall surely ease our task to reach the proposed objectives, if we are opened to change! In this paper, we will address these issues based on our teaching experience through the pandemic.


2021 ◽  
Vol 11 (13) ◽  
pp. 5800
Author(s):  
Giacomo Nalli ◽  
Daniela Amendola ◽  
Andrea Perali ◽  
Leonardo Mostarda

Online learning environments such as e-learning platforms are often used to encourage collaborative activities amongst students. In this context, group work is often used to improve the learning outcomes. Group formation is often performed randomly since university courses can be composed of a large number of students. While random formation saves time and resources, the student heterogeneity in terms of learning capabilities is not guaranteed. Although advanced e-learning platforms such as Moodle are widely used, they lack plugins that allow the automatic formation of heterogeneous groups of students. This work proposes a novel intelligent plugin for Moodle that allows the creation of heterogeneous groups by using Machine Learning. This intelligent application can be used in order to improve the students’ performance in collaborative activities. Our machine learning approach first uses clustering algorithms on Moodle data to identify homogeneous groups that are composed of students having similar behavior. Heterogeneous groups are then created by combining students selected from different homogeneous groups. To this end, a novel algorithm and the corresponding software, which allow the creation of heterogeneous groups, have been developed. We have implemented our approach by realizing a Moodle plugin where teachers can create heterogeneous groups.


2021 ◽  
Vol 11 (10) ◽  
pp. 579
Author(s):  
Ruchira Gangahagedara ◽  
Muditha Karunarathna ◽  
Wasantha Athukorala ◽  
Shyamantha Subasinghe ◽  
Prabath Ekanayake

Sri Lanka’s education system was suddenly shifted from classroom-based free education to online-based distance learning as an emergency teaching and learning method (ETLM) in response to the COVID-19 pandemic lockdown. This study examines how various stakeholders used online-based distant learning as an ETLM, and highlights the lessons learned from such a transition in Sri Lanka through a case study of the Kandy education zone (KEZ), in response to the country’s COVID-19 pandemic lockdown. We obtained the data through a questionnaire survey from 19 schools in KEZ, selecting the teachers, students, and parents as a survey sample. The findings revealed that nearly 64.7% of teachers used social media for the teaching–learning process (TLP), 27.9% used standard online teaching platforms, and only 7.4% used traditional teaching methods during the pandemic lockdown. Additionally, 36.5% of teachers and 41.2% of students favored the WhatsApp mobile application for the TLP, while others preferred other applications. However, during the COVID-19 lockdown, most of the less privileged schools in the peripheral areas of the KEZ adopted traditional teaching methods (TTM). The extent of the gap in ETLM adaptation and the driving factors that led to observable discrepancies between privileged and non-privileged schools, even in the urban settings of the KEZ, are also discussed in this study. These findings are significant in terms of educational policy making and management. Overall, this research contributes to understanding the ETLM adaptation of the KEZ by proposing policy directions that policymakers and other higher education authorities in the country should consider in an emergency.


2022 ◽  
Author(s):  
Daniela Alice Luta (Manolescu) ◽  
◽  
Adrian Ioana ◽  
Bianca Cezarina Ene ◽  
Ionela Daniela Jugănaru ◽  
...  

The aim of this paper is to identify and analyze the role that the use of the computer has in stimulating the logical thinking of young schoolchildren. Through this, the purpose of the activity of solving operations with natural numbers, is to develop logical thinking, properly combining intuitive elements with abstract ones. Solving arithmetic problems, we can activate young students in the formation of skills and abilities to analyze the given situation, to intuit and discover the way to get what is required in the mathematical problem. This paper aims to prove that, if both traditional methods and computer-based teaching methods are used in the instructive-educational process, then school performance will register a significant increase in terms of quantity and quality. This experimental study started from the premise that solving arithmetic problems with the help of computer, using e-learning platforms is an important activity in the mathematics lesson in primary school through which we stimulate young students’ logical thinking.


2012 ◽  
Vol 10 (1) ◽  
pp. 1-30 ◽  
Author(s):  
Chia-Wen Tsai ◽  
Tsang-Hsiung Lee

Vocational education in Taiwan is highly competitive in that it must attract sufficient student enrollment in the environment with a rapidly increasing number of schools. Many students in this context tend to have lower levels of academic achievement, and do not adequately get involved in their schoolwork. Under such constraints but moving toward more practical orientation, the authors conducted five experiments, applying web-mediated problem-based learning (PBL), self-regulated learning (SRL), blended learning (BL), or their combinations to help low-achieving students improve their computing skills. This study further develops appropriate course design and online teaching methods for both teachers and schools. Each of the five studies addressed a different project whose goal was to develop students’ computing skills in online classes. The five studies: (a) provide demonstrations of the effects of web-based PBL and SRL, (b) illustrate how to design and implement web-based PBL and SRL for low-achieving students, (c) provide refined interventions of web-based PBL and SRL based on multiple-phase experiences of real practices and reflections, and (d) demonstrate the effects of BL and the relevant technologies to provide more channels and opportunities for students to review and practice their computing skills.


PLoS ONE ◽  
2021 ◽  
Vol 16 (9) ◽  
pp. e0257729
Author(s):  
Claudiu Coman ◽  
Luiza Mesesan-Schmitz ◽  
Laurentiu Gabriel Tiru ◽  
Gabriela Grosseck ◽  
Maria Cristina Bularca

Prior to the COVID 19 pandemic, discussions about online learning referred to the use of e-learning platforms and social networks as auxiliary tools in the educational process. Due to the pandemic, universities were forced to adopt an exclusive online teaching process and most universities today use platforms dedicated to online learning such as Moodle platforms. In this context, we were interested in analyzing the attitude of students regarding the way social networks could be integrated into the educational process, and if the positive attitude of students towards social networks and their use for academic purposes, proven in previous studies, remains positive under the conditions generated by the pandemic. In this regard, the present study aimed at identifying the attitude of Romanian students towards the use of Facebook and Instagram as educational tools and the circumstances in which students believe these platforms could be used by them and their teachers. An online survey was conducted on 872 students from public higher education institutions in Romania. Based on the exploratory factor analysis and the parametric test, the empirical results show that students have a slightly positive attitude towards using Facebook in the educational process, but they have a more reticent, less positive attitude towards using Instagram. Thus, the most appropriate contexts in which these platforms could be used are represented by extracurricular activities. A higher preference for the use of Facebook rather than Instagram, was identified among master and PhD students. No major differences were revealed in student subgroups sorted by gender or study domain.


Sign in / Sign up

Export Citation Format

Share Document