ONLINE LEARNING AND EXAMINATION SYSTEM

As we know that before the novel coronavirus, we all majorly dependent on the old and traditional ways of conducting examinations which is very slow and, thus, decreases the efficiency of our current system. Many businesses have overturned due to COVID-induced lockdowns. There are school closures and social distancing everywhere. Normality is questioned. Governments across countries have initiated universities and higher education systems to adapt to remote instruction to cover lectures, exams, evaluations, and result publications. This technology-driven measure to promote education with equity during lockdown might work for online learning and teaching, but “how could it support online examinations?” is one of the top questions now. An online examination system during COVID could be a way out. The online examination system is a digital platform that evaluates students in a hassle-free way. The entire examination process is simplified, and exams are taken from anywhere, anytime. Eventually, with online examinations becoming the new normal, protecting the integrity of exam and exam data are becoming key areas of concern too. Experts and veterans are looking for software that comes with security features so they could evaluate student performance confidently and provide timely remediation measures for improvement, now and beyond COVID.KeywordsRemote online examinationAuto proctoringAuto evaluationVisualization

The online Examination portal is a web-based application for technical evaluation. The online examination portal not only replaces paperwork but also releases the workload of faculty. Most of the e-examination (Online Examinations) has fixed number of questions without randomizations, they have pool scalability. Online examination system is increasing rapidly with the change in scenario due to the pandemic, also it seems to be an easy, flexible, and secure methodology to carry the examinations effectively.

Online Education became far too popular in last few decades serving as a powerful platform for sharing knowledge among international groups and individuals. The motive of Online Education is to utilize the potential of World Wide Web to extend education far beyond its present limits. But the full potential of www is not utilized as there is no relevant technique implemented by which we can examine the knowledge of candidates on a mass level. As a result we are unable to appreciate actual hidden talents from different parts of world. Here we are proposing a new approach for online examinations which counters almost all the drawbacks noticed in the traditional online examination techniques. The examination model provides a relevant scheme for question presentation and tackles all major challenges faced by online examination systems.

University curriculum all over the world contain a set of learning outcomes to be achieved through different learning and teaching modes. The achievement of the Learning Outcomes is measured using some form of assessment, usually in the form of University examinations. The traditional teaching has been face-to- face, and therefore many examinations have also been conducted in a face to face manner. One of the challenges of any examination setting is cheating amongst University students, which implies that the examinations must be properly invigilated or proctored. Since the introduction of ICT in Education, there have been attempts to introduce Online examinations, although these are yet to gain full traction. In Kenya, the ODEL standards lean more towards blended learning, where each course has to have a face to face element. Many Universities have therefore been conducting their examinations in a traditional setting. The onset of COVID-19 created a different situation as the social distancing and the restricted movement meant that learners could not attend a physical class. The movement to Remote Emergency Teaching created a challenge on how examinations could be conducted and proctored. Several Universities decided to do the teaching but wait for resumption of face to face studies to conduct their exams, and this had a negative impact on the University Almanac. This paper looks at the case of one Private University that decided to complete a whole semester online but also went on to conduct examinations via the Learning Management System. Using a triangulation of Interviews, Observation and Document Reviews, staff and students who had participated in conducting and taking online examinations were interviewed. The online examinations processed was observed and documents and software used in online examinations and proctoring were reviewed. Reorganization of the examination processes, organizational and cultural change management, ICT technical issues, extensive training, software selection and communication were identified as the key requirements for successful online examinations and proctoring to take place. The use of Proctoring Systems that are integrated with the LMS give a shorter learning curve and are easier to learn and use.

In recent years, digital learning and examination system has received great importance in the educational sectors due to the present COVID-19 pandemic situation. This online digital learning and examination system had many advantages over the traditional paper-based offline system. Since the amount of paper consumption is very less in the digital online education and examination, this approach could be ideal for saving the tree and reducing the environmental risks. Moreover, digital learning and examination system could be more convenient, time-consuming and safe in the current COVID-19 pandemic. This paper describes the environmental impact of traditional education and examination systems, different types of tools available for conducting online education and assessments and strategies to minimize paper usage in the teaching-learning and examination systems.

These days e-learning has gained a great deal of importance in education and training field. Many universities and colleges are providing online courses through internet. Online examinations with multiple-choice questions are being increasingly used in education system mostly in entrance examinations and competitive examinations. Advantage of online examination is automation in evaluation process and thereby removing the personal bias towards the students. For this purpose, academic institutions are using Learning Management Systems extensively. Moodle, the open-source learning management system is mostly preferred. It is another option to proprietary online learning solutions. In fact, student's performance cannot be evaluated and assessed only by right and wrong answers in online examination. In proposed experiment an attempt is made to make the examination assessment intelligent. Data mining which is very popularly used in various domains including business but less explored in academic domain. It can be effectively used to mine data generated from e-learning systems. This paper explores the use of data mining algorithm with soft computing technique in question categorization. Proposed work decides the level of difficulty of questions. To categories the questions into different categories like as easy, moderate and tough, fuzzy c-means clustering is used. Along with this, performance of students attempting easy, moderate and tough questions is assessed.

Nowadays, deep and transfer learning technologies and its algorithms have become more popular in research area of computer vision field for image recognition and classification tasks. There are various kinds of neural networks broadly used in research area of image recognition and classification problems such as CNN, DNN, etc. In this research work, the researcher proposed and developed two customized modules. The first module is used for authentication of students in the online examination system. The second module is about to find the behavior analysis and facial expression recognition of students during online examination. The proposed authentication and facial expression analysis module is constructed by combining features of CNN and transfer learning approach with pre-trained architectures. To develop proposed system the models used are trained and validated by using various datasets. It also calculates the performance of students during the online examination period. The accuracy of these deep learning models highly based on data quantity used for training and testing model. Training and testing datasets depend on types of problems considered for which models are to be built.

With the rapid growth of online education, ensuring academic integrity in online examinations has become a significant concern. Online proctoring has emerged as a solution to monitor students remotely during exams, aiming to deter cheating and maintain assessment credibility. This scientific article thoroughly reviews the literature to investigate the effectiveness, challenges, and implications of using online proctoring in online examination settings. A systematic review was conducted by searching electronic databases, including popular scientific databases such as Web of Science, Ebsco, Scopus, and Google Scholar, for relevant articles published between 2018 and 2023. Keywords such as "online proctoring ", "remote invigilation ", "academic integrity "and "online examination "were used to identify pertinent studies. Various research designs, including experimental studies, case analyses, and qualitative assessments, were considered to capture diverse perspectives. The review synthesized findings from existing literature to elucidate the multifaceted aspects of online proctoring in online examinations. Studies highlighted the potential of online proctoring to mitigate cheating behaviors through real-time monitoring, identity verification, and surveillance mechanisms. Proponents of online proctoring argue that it offers a scalable solution to uphold academic standards in online learning environments. Furthermore, some research indicated that students perceive online proctoring as a fair method to ensure equal treatment and transparency during assessments. However, challenges such as privacy concerns, technological issues, and the potential for bias in proctoring algorithms were identified as significant drawbacks. Additionally, the implementation of online proctoring may exacerbate disparities in access to resources and exacerbate test anxiety among students. In conclusion, integrating online proctoring in online examinations presents opportunities and challenges for academic institutions. While online proctoring offers a means to enhance exam security and maintain academic integrity in remote learning environments, its implementation requires careful consideration of ethical, technical, and pedagogical implications. Adopting online proctoring should be balanced with the need to uphold academic standards while ensuring equitable access and promoting student well-being in online education.

Examinations or assessments play a vital role in every student’s life; they determine their future and career paths. The COVID pandemic has left adverse impacts in all areas, including the academic field. The regularized classroom learning and face-to-face real-time examinations were not feasible to avoid widespread infection and ensure safety. During these desperate times, technological advancements stepped in to aid students in continuing their education without any academic breaks. Machine learning is a key to this digital transformation of schools or colleges from real-time to online mode. Online learning and examination during lockdown were made possible by Machine learning methods. In this article, a systematic review of the role of Machine learning in Lockdown Exam Management Systems was conducted by evaluating 135 studies over the last five years. The significance of Machine learning in the entire exam cycle from pre-exam preparation, conduction of examination, and evaluation were studied and discussed. The unsupervised or supervised Machine learning algorithms were identified and categorized in each process. The primary aspects of examinations, such as authentication, scheduling, proctoring, and cheat or fraud detection, are investigated in detail with Machine learning perspectives. The main attributes, such as prediction of at-risk students, adaptive learning, and monitoring of students, are integrated for more understanding of the role of machine learning in exam preparation, followed by its management of the post-examination process. Finally, this review concludes with issues and challenges that machine learning imposes on the examination system, and these issues are discussed with solutions.

In order to achieve a paperless office, to improve test efficiency and save costs, we develop an online examination system. The system is designed by JSP technology and SQL Server database. Through two years of use proves that the online examination system facilitates and simplifies the test process, and makes the teacher complicated free from the examination process and has more time to study the teaching and the scientific research. The system has saved printing papers costs and office expenses. Online examination reflects the characteristics of the course Network Information Retrieval and solves the problems that paper test can not comprehensively inspects the student's ability of application.

Increasingly, many institutions and students benefit from online learning systems each year. For example, in 2016 Massive Open Online Courses (MOOCS) reported as many as 16 million enrolled students and online tutoring systems reported over half a million enrolled students. In the literature, many design patterns capture online learning system designs for class management, discussion facilitation, lecture delivery, and feedback. In this paper, we describe design patterns that describe finer-grained activities within online learning systems such as the design of problem-solving activities and their associated learning support. The three patterns presented in this paper describe designs for constructing math-problem content and corresponding learning support for students who answer these problems -- Mastery Learning Templates, Explain Worked Solutions, and Scaffold Problems with Guide Questions. We uncovered these patterns using the data-driven design pattern production (3D2P) methodology on data collected from the ASSISTments online learning system. The design patterns we describe were mined from data on student interactions with an online learning system and were linked to existing learning-science literature.

In the present decade, education is entering to the world of online learning and focusing to a learner as the center of education. To manage learning system successfully, the education courses: Learning management system (LMS) based on the online learning has been developed. In this study, LMS was developed for Programming Language course for the students of Rajamangala University of Technology Phra Nakhon by using the principle of software development life cycle (SDLC) process. Additionally, the development of the program was done via important major phases of planning analysis, design, implement and evaluated by experts in this field. From 60 randomly selected students of the Faculty of Science and Technology, online Programming Language course providing modules based on LMS model via the Internet showed higher efficiency of 85% than the control in the standard usual instruction procedure. All these aspects of system performance evaluated by the students were also at high level and satisfied with the developed lesson described on the web. Therefore, this online learning system is helpful for all learners in the present information technology world. This system would be further applied for other courses with other additional interactive systems.

Over the last decades, the computer has spread its tentacles around the globe and online examinations have blossomed on the education world/arena. This sudden shift from traditional assessment methods stems from the fact that more and more students are having recourse to distance learning and online courses from institutions worldwide. By proposing online examinations many of these organizations are cutting on their costs by avoiding the conduct of physical examinations, while at the same time benefitting from a wider pool of eligible candidates, a real panacea for those organizations. Moreover this system puts a thinner time constraints as for specific examinations users can view their results nearly instantly. Online examinations, however, have many issues involved that require organizations to resort to it after careful study. The authentication of the examinees is one of the fundamental aspects to be considered. Correctly identifying an individual is of utmost importance so that the certification/degree awarded afterwards will not be disputed or challenged. This paper will demonstrate an enhanced mechanism to rightfully identify a student for an online examination. To give the right leverage, a right dose of different authentication methods will be revised first and their strengths and weaknesses will be assessed.

In many online examinations, physical invigilation is often replaced with traditional authentication approaches for student identification. Secure and usable authentication approaches are important for high stake online examinations. A Profile Based Authentication Framework (PBAF) was developed and implemented in a real online learning course embedded with summative online examination. Based on users' experience of using the PBAF in an online course, online questionnaires were used to collect participants' feedback on effectiveness, layout and appearance, user satisfaction, distraction and privacy concerns. Based on overall findings of the quantitative analysis, there was a positive feedback on the use of a hybrid approach utilizing image and text based challenge questions for better usability. However, the number of questions presented during learning and examination processes were reported to be too many and caused distraction. Participants expressed a degree of concern on sharing personal and academic information with little or no privacy concern on using favorite questions (p < 0.01).

The goal of online examination is to ensure convenience, scalability, expanded reach, and customization. Despite the popularity of online exams, there have been some demonstrations against using them. The existing system is vulnerable and faces failures like question paper leakage, answer deception, trying to forge scorecards, difficulty in ensuring the integrity and consistency of scorecards by the exam board, and so on. Blockchain technology is the greatest and unsurpassed option for continuous authentication, confidentiality, and reliability. A blockchain-based framework for an online examination system is proposed to collect, register, and maintain a growing list of records using cryptography. It is also a peer-to-peer system that manages or stores time-stamped transactions such that no one can alter them. The proposed model combines time lock and multi-signature techniques and ensures the encrypted questions are locked till the exam starts, candidates’ answers are not altered, and scorecards are not manipulated. The system is open to the public, and the system’s processes are transparent. The costs associated are analyzed with the suggested solution’s on-chain and off-chain evaluation.