Improvement of AHMES Using AI Algorithms

This research aims to improve the rationality and intelligence of AUTOMATICALLY HIGHER MATHEMATICALLY EXAM SYSTEM (AHMES) through some AI algorithms. AHMES is an intelligent and high-quality higher math examination solution for the Department of Computer Engineering at Pai Chai University. This research redesigned the difficulty system of AHMES and used some AI algorithms for initialization and continuous adjustment. This paper describes the multiple linear regression algorithm involved in this research and the AHMES learning (AL) algorithm improved by the Q-learning algorithm. The simulation test results of the upgraded AHMES show the effectiveness of these algorithms.

Challenges of Online Exam Systems in the COVID-19 Pandemic Era

The swift conversion of courses to online format and online exam systems has identified the COVID-19 pandemic era. All educators on the globe have faced the obstacles of abrupt adoption of distance education learning methods. This unexpected shift has presented numerous challenges as preparing an online course content requires developing detailed course plan design, audio and video content, and technical support equipment. This chapter focuses on determining the problems and developing solutions based on the student perceptions about the online exams, which were compulsorily transitioned during the pandemic process. A survey about student perceptions of online exams has been developed and applied to the students after they have taken the exam. Descriptive statistics is used to analyze the data. E-assessment of perception about the online exam system and its impacts on motivation and performance are discussed, and suggestions to improve the system are provided in the chapter.

Securing Logins in Electronic Examination Systems for Tertiary Institutions Using Quick Response Code (QR) Technology and Multiple Hashing Algorithms

This work is aimed at adding an extra layer of security to the login process of an electronic examination system as security has been identified as one of the critical success factors in the management of such exams. It proposes to secure the login process of an e-exam system through authentication and encryption to control access and avoid impersonation. A model of the e-exam system with Quick Response (QR) code generation capability was designed where a student’s matriculation number is accepted as input which is then converted into a two-dimensional bar code using a QR generator. Outputs from the QR code generator are then secured by encryption using MD5 and SHA-224 encryption algorithms. MD5 algorithm produces a 32-bit hash value which is further encrypted using SHA-224 that produces a resulting 56-bit hash value that is then saved in the password column of the user table in the database. This research resulted in a secure and web-based electronic examination authentication system implemented and tested on a client-server architecture. Performance evaluation of the developed system revealed that it is fast and effective, capable of authenticating students in an average of 0.624 seconds when the smartphone flashlight is off, and 0.318 seconds with flashlight turned on and consequently, resistant to brute force attacks. This paper fulfils an identified need to develop an electronic exam system that not only secures the question bank but equally ensures the security of the login process as well as the login details using a combination of two security techniques.

Beyond education by ranking: Let's not return to 'normal'

The cancellation of public examinations in England during the coronavirus pandemic drew attention to a long-standing educational concern. Grading and ranking students, in various ways, has taken place for many years, but in summer 2020 this process was shared between teachers and, initially, an 'algorithm'. Maintaining standards and consistent grade distributions is a feature of the exam system in 'normal' times. This article considers why exam grades are (roughly) normally distributed, tracing origins of bell-curve thinking, to suggest that we should not be returning to this kind of 'normal'.

Design and Implementation of Online Examination System based on MSVS and SQL for University Students in Iraq

The transfer of knowledge and skills is a process that is closely linked to the measurement of its usefulness. It's hard to imagine teaching without considering the results and evaluation of students. At the same time, the current education system is based on a longstanding traditional paradigm. The aim of this article is to propose a new digital review system based on Microsoft visual studio (MSVS); it is the only one of its kind in terms of application versatility and also features professional interfaces for the interactive display of questions and answers. In our school, we have systematically assessed this program to determine the system performance of teaching staff and students, the findings of this study demonstrate the assumption that students were prepared for this type of knowledge; the evaluation result of the propose exam system outperforms conventional system about approximately 80%.

"Online Exit Exam Preparation" Strategically facing a Nursing Competency Test during the COVID-19 Pandemic

Introduction: The enactment of Law Number 2 of 2020 from the Ministry of Education and Culture of the Republic of Indonesia concerning The Graduation Exam System for Health Graduates has a significant impact on universities, affecting the number of students who can graduate. Looking at the description of these problems, it is necessary to develop a strategy in dealing with the "Exit Exam" competency test for students majoring in the health science faculty of nursing, namely "Preparation for Exit Exam Online," so that they can answer these problems. Methods: This research method uses one group pretest-posttest design with a sample size of 54 people. Results: The results showed increased the tryout value that after participating in online tutoring activities in facing competency tests. Conclusion: This online guidance is one of the strategies in dealing with competency tests during the Covid-19 pandemic in nursing students.

Analisis Metode Cosine Similarity Pada Aplikasi Ujian Online Otomatis (Studi Kasus JTI POLINEMA)

<p>Dalam konsep <em>e-learning</em> pelaksanaan ujian dilakukan secara online salah satunya ujian esai. Ujian esai online merupakan ujian yang menggunakan metode online dan mewajibkan siswa menjawab dengan kalimat mereka sendiri. Namun, dalam ujian esai online ini memerlukan waktu yang lama untuk mengoreksi jawaban jika dikerjakan secara manual. Agar tidak memakan banyak waktu untuk mengoreksi jawaban siswa maka dalam sistem terdapat penilaian kemiripan jawaban untuk penilaian. Pada penelitian ini dilakukan pembuatan sistem ujian esai online dengan penilaian kemiripan jawaban menggunakan metode <em>Cosine Similarity</em> dan persamaan <em>Term Frequency</em> (TF) untuk menyamakan frekuensi setiap kata yang terdapat dalam kalimat. Suatu faktor yang menentukan bobot kata berdasarkan pada jumlah frekuensi kata dalam sebuah dokumen disebut dengan<em> Term Frequency</em>. Untuk pengujian akurasi metode dilakukan pengujian <em>precision, recall</em>, dan <em>f-measure</em> dan berdasarkan hasil analisis dengan menggunakan metode yang telah dicoba diperoleh rata-rata 81%.</p><p> </p><p><em>Abstract</em></p><p> </p><p><em>In the e-learning concept, the implementation of exams is carried out online, one of which is an essay exam. The online essay exam is an exam that uses an online method and requires students to answer in their own sentences. However, in this online essay exam, it takes a long time to correct answers if done manually. In order not to take a lot of time to correct student answers, the system has an assessment of the similarity of answers for the assessment. In this study, an online essay exam system was made with the similarity of answers using the Cosine Similarity method and the Term Frequency (TF) equation to equalize the frequency of each word contained in a sentence. Term Frequency is a factor that determines word weight based on the number of word frequencies in a document. To test the accuracy of the method, precision, recall, and f-measure tests were carried out and based on the results of the analysis using the method that had been tried, an average of 81% was obtained.</em></p>