Conference Paper

Biometrics in Online Assessments: A Study Case in High School Students

Authors:
To read the full-text of this research, you can request a copy directly from the authors.

Abstract

This paper describes the use of a prototype online assessment system with biometric recognition capabilities applied to evaluate basic knowledge in a High School. The prototype system represents a first approach to identify remote students in online assessment to solve the well known problem: Who's there?. For our experiment, we randomly selected a sample of students (n=102) from a public High School, located in Morelos, Mexico. We carried out two evaluations, a control evaluation (paper and pencil), and a second test with our system with biometric recognition, this system authenticates the student by means of index fingerprint, allows subject selection to be evaluated, and shows the assessment consisting of a set of time limited questions and randomly ordered answers, simultaneously the student is being monitored by web cams until test is finished. Low grades were obtained using computerized test, due students feel lot of stress when time to answer is limited and a web cam is monitoring them, fingerprint recognition was very well accepted.

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the authors.

... Another approach has been proposed that combines fingerprint and real-time video-monitoring [84]. When connection to the server is established, the examinee is asked to scan his fingerprint for authentication. ...
... When connection to the server is established, the examinee is asked to scan his fingerprint for authentication. Figure 3.11 illustrates client and server sides of this scheme [84]. If it matches the stored one on the server-side, the interface automatically fills user and password fields and allows him to continue. ...
... False Acceptance Rate (FAR) and False Rejection Rate (FRR), as shown in the pair of Equation 3.7 and Equation 3.8 [84]. ...
Thesis
Full-text available
The advancements in information and communication technology, within the previous decade, have initiated new pedagogical methods leading to e-learning. Summative e-assessment, i.e. e-examination, which measures students’ performance, has been considered a vital process in e-learning systems. The main objective is to enable students to conduct electronic (i.e. online) exams securely. The major vulnerabilities of e-examination schemes can be summarized in cheating and impersonation threats as well as possible attacks for unauthorized access. Also, applicability, ease of use and automation are still challenging features. This thesis contributes to defend the claims of the opponents who reject e-learning claiming that it never provides trustful and cheating-free e-examinations. It proposes new approaches for continuous e-examination authentication. These approaches enable institutions to conduct secure e-exams distantly, e.g. at home. Two e-examination models have been proposed to ensure an examinee is the correct student, detect cheating actions and apply penalties throughout his exam. They provide smart, interactive and secure virtual e-examination sessions. Prototypes for both models have been developed on an open source learning management system (i.e. Moodle) using PHP, MySQL, JavaScript and AJAX. A media server and a media encoder are required to broadcast e-examination sessions. A control toolbox has been developed to provide several functions to its users. The first model, named ISEEU, is proctor-based, where a proctor interacts with the models and the examinees using the provided functions. A webcam or a mobile unit with a camera attached is required for each examinee to capture his video during the e-exam. It cannot be started without approval by a proctor who can also pause, resume or terminate an e-exam any time if an examinee violates instructions. The second model, named SABBAH, came as an upgrade to the first, in order to improve performance, automate the process and reduce the cost by dispensing with proctors. It utilizes a combination of automatic video matching and continuous bimodal biometrics authentication using fingerprint and keystroke dynamics. The required application programming interfaces (APIs) of biometrics authentication have been used in its development. For higher performance, it is required to enhance and customize the existing video matching and feature extraction algorithms. An implementation environment has been proposed, and some modifications have been recommended to be typical. It is supposed to provide the expected e-learning services by integration of e-learning system and university management information system (MIS). A security module has been proposed that ensures a secure environment with high protection and availability. Both models provide a cheating indicator which appears on each examinee’s screen with relevant warning messages on any violation. Violation rate is based on manual selection from a weighted cheating list in the first model. The second uses video-feature extraction and matching to detect cheating actions automatically. A suitable penalty is applied on each violation, and if a specific limit is exceeded (e.g. 50%), an exam will be terminated automatically with zero accumulative grade. Both models were evaluated in terms of security, applicability and performance. A risk analysis and an empirical analysis were conducted to measure security and applicability compared with the previous ones. Also, several experiments were performed to measure performance such as average delay, storage requirement, memory usage and CPU usage. Both models proved higher scores than the previous schemes with a preference to the second, i.e. SABBAH model. Finally, the proposed models could be used in academic institutions that offer e-learning services, if they provide the described typical-environment.
... Two metrics of security level are defined for fingerprint, as shown in Eqs. (1) and (2) [35]: ...
... This scheme combines fingerprint and real-time video-monitoring, as illustrated in Fig. 11 [35]. When connection to the server is established, the examinee is asked to scan his fingerprint. ...
... Structure of combined fingerprint and video-monitoring in e-Examination[35] ...
Chapter
Full-text available
Online-examination modeling has been advancing at a slow, thus steady pace. Such an endeavor is embedded in many of today’s fast-paced educational institutions. So, the online examination (i.e. e-Examination) model demonstrated in this chapter proposes two major schemes that utilize the most up-to-date features of information and communication technology (ICT). We have integrated authentication methods into this model in the form of simulated and controlled, thus measurable enhancements. The new model complies with international examination standards and have been proved to be equally, if not more, immuned to its predecessor models, including classroom-based examination sessions. Therefore, it can be selected as a new model of examination to cut-down on the cost of exam administration and proctoring.
... However, they concluded that web security is a well investigated area but it is insufficient to fulfil the security needs of eassessment. In addition to the well defined web security areas, we include that data security [8] and the network security [18] of summative eassessments are also well researched. However, we suggest that the user security phase of the eassessment security is a continuing research field. ...
... It can also refer to a specific, measureable occurrence that any business or system plans or intends to achieve or avoid. One method of generating the security goals of a system is by specifying that the actions on the assets listed in threat descriptions can be prevented [8]. ...
... Regardless of the techniques employed, the identity and authentication of a student remains a major challenge to the summative e-assessment process [1,8]. Hence, we do not suggest the unsuitability of the mechanisms used; rather we propose that satisfying the identity and authentication goals alone is insufficient to ensure user security. ...
Conference Paper
Full-text available
The general security goals of computer a system are known to include confidentiality, integrity and availability (C-I-A) which prevent critical assets from potential threats.. The C-I-A security goals are well researched areas; however they may be insufficient to address all the needs of the summative e-assessment. In this paper, we do not discard the fundamental C-I-A security goals; rather we define security goals which are specific to summative e-assessment security. Copyright © 2009 by the Institute of Electrical and Electronics Engineers, Inc. All rights reserved.
... A major problem when conducting online assessments is the inability to know who is there taking the exam i.e. to know if the correct student is there taking the exam or someone else has taken over the test on their behalf (Wisher et al, 2005;Aojula et al, 2006;Levy & Ramim, 2007;Hernandez et al, 2008). This has informed this study to focus on impersonation threat. ...
... The issue of impersonation is considered as a major cause of concern and it is perceived as an even greater risk by the academic community (Ramu, 2013). There exists an implicit consideration of impersonation threats in online assessments (Wisher et al, 2005;Hernandez, 2008;Ramu, 2013). According to Maria (2010) impersonation threats can be classified into three types, namely Type A, B and C. ...
Article
Full-text available
Online learning mediated by ICT is fast growing in popularity worldwide. There is need to consider modes of assessment using ICT tools which are flexible given that candidates can take assessments anywhere and possibly anytime. However, the main challenge when conducting online assessments is the imminent impersonation threat. It is difficult to know if the correct candidate is the one taking the exam or someone else is taking examination on their behalf. Impersonation threats have been classified into three types: Type A, B, C and this study introduces type D. Majority of existing online assessments systems employ one time authentication using passwords but they are prone to impersonation challenges given that the candidate may willingly share this information with another person to take exam on their behalf. More is required to verify the identity and presence of an authenticated student for the whole examination duration. Potential approaches apply continuous scan of biometrics but they are incapable of addressing concealed impersonation or Type D threats. This proposed Temporal Information and System Interaction (TISI) model will not only address all the four type of impersonation but will also minimize the human involvement.
... The system was successfully used with a group of industrial engineering students at UNED (National University of Online Education, in Spain) to get access to their online laboratory tests. In the same way, Hernández, Ortiz, Andaverde et al. (2008) describe the use of an online assessment through biometrics recognition systems in a secondary school. For the experiment, a sample of secondary school students (n = 102) was randomly chosen. ...
Article
Full-text available
Nowadays, one of the key challenges for distance education is to be able to verify the students’ identity in order to check if they are actually who they claim to be when they are doing their online tasks and to avoid identity thief. This can be achieved through facial authentication software. In e-learning, thanks to this technology there is a way to confirm that the students are not committing fraud in their studies and besides to improve this kind of education by equaling its validity and prestige to traditional face-to-face education. The goal of this research is to avoid fake users that perform educational tasks on behalf of others in the Learning Management Systems (LMSs), and more specifically to develop a new technique to design activities with glossaries that properly allow control of the student learning process through facial authentication software. The presented technique is composed of several steps that guide instructors in the elaboration of this kind of activities. This work has used Moodle platform for the experimentation, and analyzes the experience of 67 students with the activities designed with the presented technique.
... In an online exam, the issue of impersonation is considered as the most important cause of concern and it is supposed to be as a greater risk by the academic community [4,21]. Based on the exiting literature [22][23][24] there is an implicit consideration of impersonation threats in online exam, and it can classified into four types [4,25]: 1-Type A impersonation, which may occurs in two cases, either the proctors could not notice it, or they allowed impersonation by force, empathy or bribery.2-Type B, which occurs when users pass their security information to others, who use them to answer the exam on their behalf. ...
Article
Full-text available
User authentication is a very important online environment issue. Further, investigation is needed to focus on improving user authentication methods for the sake of improving e-Learning security mechanisms; especially in the field of online exams. This study is the result of a systematic literature review which will answer the following three main questions of online exam user authentication methods, systems and threats. The results cover four main directions. First, it shows complete authentication methods that have been used in online exam systems; whether they are classified as knowledge, possession or biometric based. Second, it summarizes the online exam systems and authentication techniques used whether they are classified as user identification, authentication or continuous authentication. Third, it explores the threats that may occur during exam sessions and specifically classifies impersonation threats. Finally, it investigates existing commercial user authentication products that are used to observe online exams.
... If the evaluation process is finished successfully, the assessment is processed at the Server Side, and the final results of evaluation and security status are shown at the Client Side. For a detailed review of the performance schema refer to (Hernández-Aguilar et al., 2008). ...
... The Client-Server Application supporting fingerprint recognition to authenticate students in online assessments If someone else tries to get the control of the computer during the online assessment, the evaluation process is finished prematurely, and the results are sent to server side to be processed as they are. To the contrary, the evaluation process is finished successfully, the assessment is processed at Server Side, and the final results of evaluation and security status are shown at Client Side (Hernández et al. 2008). The stage of data mining is executed asynchronously to verify students' behaviour patterns: keystroke dynamics (Gutierréz et al. 2002), navigation patterns (Xing & Shen 2004) and performance patterns (Hernández et. ...
Chapter
Full-text available
The quickly grown of the Web has done that it is a great information source in many areas, which can be used to obtain important data in different areas like social, psychological, marketing, among others. As one saw from point psychological are possible to be studied some behaviors and found certain landlords with the help of Data Mining, also it is possible to determine future behaviors on the basis of certain antecedents as one is in the application on the basis of social networks information like Orkut. On the other hand it can predict certain preferences by some product or service; this could be observed through the Web Radio application. The Web Data Mining can help us to understand more some things and provide a base for the decision make. In the Web one can find a great amount of information sources, the unique thing that there is to think is those that are wanted to obtain. In this case our applications analyzed were Social Networks, Web radio, Security and Internet frauds. In this work to show a conceptual model to develop systematically web radio applications taking into account social acceptability factor using the social data mining and cultural algorithms. With the matching information about the users (listener profiles) with the knowledge building for a society based on cultural algorithms (content metadata), it could be possible to automatically generate more pertinent playlists for individual listeners. Then, it is feasible that a web radio purpose could interpret the human behaviour under certain situations to which it is exposed, this by means of the behaviour that will have the users when interacting with the Web Radio. This is only one part of everything what it is possible to be done with the aid of the Social Data Mining. With the creation of the web radio one hopes that one undertakes new projects that are developed with the aid of the Social Data Mining and cultural algorithms. Nevertheless there are a lot of research work that will be doing with Data Mining for Web applications and some future works that can be: In the area of social networks it is the search of criminal networks in the diverse social networks like Orkut, MySpace, Badoo, Hi5, etc. these criminal networks are possible to be dedicated to the kidnapping, traffic of bodies, drug traffic, among others activities. Another application is to make an analysis of these networks to obtain information that can be used to offer products and services in specific sectors, an example of this is the Web radio, but it is possible to be analyzed another types of services with the security that these are going well to be received by a certain Web user group. In the Internet area fraud we want to improve human-computer interface and assessment methodology by including student’s comments and users feedback. We want to test the tool with different groups at different high schools and Universities. Regarding biometric recognition, we want to improve facial recognition, due at this point of our research we can
... Such physiological characteristics that do not change often can be used for identifi cation and authentication. They have been tried out for use in some settings of high-stakes assessment to authenticate and then to monitor the identity of a respondent during an examination, for instance, in the absence of proctoring (Hernández et al. 2008 ) . Here we are perhaps more concerned with biometrics as behavioral characteristics that may be a refl ection of a user response pattern related to a construct of interest to measure. ...
Article
Full-text available
In this paper, I will review some aspects of psychometric projects that I have been involved in, emphasizing the nature of the work of the psychometricians involved, especially the balance between the statistical and scientific elements of that work. The intent is to seek to understand where psychometrics, as a discipline, has been and where it might be headed, in part at least, by considering one particular journey (my own). In contemplating this, I also look to psychometrics journals to see how psychometricians represent themselves to themselves, and in a complementary way, look to substantive journals to see how psychometrics is represented there (or perhaps, not represented, as the case may be). I present a series of questions in order to consider the issue of what are the appropriate foci of the psychometric discipline. As an example, I present one recent project at the end, where the roles of the psychometricians and the substantive researchers have had to become intertwined in order to make satisfactory progress. In the conclusion I discuss the consequences of such a view for the future of psychometrics.
... Reference [34] proposed capturing random video footages during secure internet exams (SIE-VM). 5) Biometrics and Webcam Monitoring: combines fingerprint for login and real-time video-monitoring (FP-VM) [35]. ...
Article
Full-text available
This paper presents a secure and smart model for summative e-assessment, where exams can be conducted distantly, e.g. at home. This model aims to provide e-learning systems with an authentication approach that guarantees minimum cheating in summative e-assessment. It utilizes a combination of automatic video matching and continuous bimodal biometric authentication using fingerprint and keystroke dynamics. This ensures that the examinee is the correct person on the other side throughout the e-examination without a need for a proctor. It is based on one of the open source e-learning and content management systems. Moreover, it employs a media server, a suitable media encoder, and the necessary application programming interfaces (APIs). Finally, its implementation requires advanced algorithms of video matching and feature extraction.
... The proposed solution would enhance the authentication process and would reduce the chances of cheating during the exam. Another biometric recognition system was applied to evaluate the basic knowledge in high school students in [25]. The assessment was carried out in order to answer the main problem, who is there? ...
Article
Full-text available
Many organizations and institutions around the globe are moving or planning to move their paper-and-pencil based testing to computer-based testing (CBT). However, this conversion will not be the best option for all kinds of exams and it will require significant resources. These resources may include the preparation of item banks, methods for test delivery, procedures for test administration, and last but not least test security. Security aspects may include but are not limited to the identification and authentication of examinee, the risks that are associated with cheating on the exam, and the procedures related to test delivery to the examinee. This paper will mainly investigate the security considerations associated with CBT and will provide some recommendations for the security of these kinds of tests. We will also propose a palm-based biometric authentication system incorporated with basic authentication system (username/password) in order to check the identity and authenticity of the examinee.
... Sabbah [13] has proposed a multimodal approach combining fingerprint recognition and keystroke analysis, in addition to video monitoring, although, the study did not demonstrate how the approaches overcame the issue of cheating nor the biometric performance being experienced in practice. Hernández et al. [14] suggested a prototype using fingerprint recognition to deal with or overcome the problem of student identification at the beginning of the exam together with synchronized student continuous observation using a web camera until the end of the online test. Even though it is well evaluated, this study did not explain the continuous video monitoring during the exam time (e.g., how it could be used in practice -would an examiner need to watch the individual video feeds of all participants?) ...
Conference Paper
Full-text available
Over the last ten years, e-learning has played a vital role in education. A leading Virtual Learning Environment (VLE) reports a user base of 70 million students and 1.2 million teachers across 7.5 million courses. Whilst e-learning has introduced flexibility and remote/distance-based learning, there are still aspects of course delivery that rely upon traditional approaches. The most significant of these is examinations. Students are still required to attend physical testing centers in order to ensure strict examination conditions are applied. Whilst research has begun to propose solutions in this respect, they fundamentally fail to provide the integrity required. This paper presents an analysis of invigilation and e-assessment solutions. A core framework for an e-assessment system has been developed based upon maintaining student convenience but providing effective verification of participants throughout the test, rather than merely at the beginning. Transparent or non-intrusive identity verification is utilized to conveniently capture and process biometric signals, which has the potential to facilitate continuous verification. This novel e-invigilation system is designed in a modular fashion to incorporate a range of behavioral and physiological biometrics including: face recognition, keystroke analysis, mouse dynamics, linguistic analysis and iris recognition. This range of techniques provides an opportunity to capture biometric samples under a range of differing examination scenarios (e.g. essay writing, multiple choice test). The key to user acceptance is usability and the system has been designed to specifically ensure ease of use for all users.
... Reference [15] developed and implemented a distributed and autonomous biometric system to monitor students' class attendance at Budapest University of Technology and Economics (BME) in Hungary. Also [16] developed a biometric system to authenticate students admitted into an online assessment system. Other use of biometric technology includes access to places, such as work or bank premises, and network resources, information protection [1]. ...
Article
The airline industry is losing millions of dollars each year due to lost or stolen passenger luggage. The current system used for both checking-in and checking-out passengers' luggage has not proven to be effective in curbing luggage loss. On the other hand numerous businesses, including airlines, have turned into biometrics for effective access control and user authentication. It is on the basis of this undisputed success of biometric systems that this research study proposes the extended use of a fingerprint biometric system for passenger luggage check-in and check-out at the airports. The use of biometrics at various international airports in other business areas has yielded positive results. Therefore, the usage of a biometric system for luggage check-in and check-out would be one way of nipping luggage theft in the bud.
... Све је више индиција да се ово може остварити конвергенцијом ИоТ технологије и система за управљање учењем (Wakim & Mershad, 2018). На пример, уређаји за детекцију лица и био-метријско препознавање се развијају као средства за обезбеђивање идентитета у системима за онлајн образовање, што укључује контролу приступа онлајн образовним садржајем (Montgomery & Marais, 2014), као и за детекцију идентитета студента (потврђивање да су људи који учествују у активностима на настави или који полажу испит заиста пријављени студенти) (Valera et al., 2015;Hernández et al., 2008;Apampa et al., 2010). ...
Article
Full-text available
The aim of this paper is to present and analyse the Internet of Things and Technology-Supported Learning Environments, which represent current technological trends of higher education development. The method used in the paper is content analysis of available scientific literature - theoretical and empirical. It is shown how the application and integration of these technologies trigger significant socio-technological changes in the conditions in which higher education operates. The results show that the application of these technologies enables material savings, that it can result in increasing of the efficiency and effectiveness of the higher education processes and in adapting of the teaching process to the individual needs of students. The paper further discusses the challenges and risks that these technological change can bring to higher education and society as a whole. In the conclusion, it is pointed out that despite the numerous advantages that are being realized, it is necessary to develop human resource competencies and find solutions related to the ethical use of data.
... arning to test scores, with a risk to destroy students' intrinsic motivation. Test scores are mainly meaningful within the educational context, while the actual learning outcome is what creates meaning outside of the education and after a course is completed. Biometrics is an emerging field that opens up new opportunities for online authentication Hern?ndez et al., 2008), but with side effects that also raise new ethical issues of integrity and data protection. Biometric systems based on the digitisation of various physiological criteria has been widely discussed in research during the last 30 years (Alexandre, 1997; Jain, Bolle & Pankanti, 2006). In this study the aim is to explore and discuss how a r ...
Conference Paper
Full-text available
Assessment of students in traditional higher education has always had mechanisms to prevent cheating and plagiarism, and the same need exists today for online assessment in virtual learning platforms. The number of students that are suspended from courses in tertiary education has increased in the last decade and there is a need for new techniques to handle the problem in online environments. To achieve zero cheating is hard (or impossible) without repelling not only cheaters but also those students who do not cheat, where a zero‐tolerance emphasis also would risk inhibiting students' intrinsic motivation. Several studies indicate that existing virtual learning environments do not provide the features needed to control that the intended student is the one taking the online exam. New technology opens up opportunities for online authentication through biometrics, but raises new ethical issues in the fields of integrity and data protection. The aim of this study is to explore and discuss how a reliable model for online authentication in distance education could be constructed with the use of biometrics without the risk of unnecessary integrity violation. Data has been collected in a literature study and discussed in the light of existing technology applied to the field. Findings show that promising digital techniques exist which could be combined to assure authentication in online exams without violating students' privacy or storing sensitive data. A suggestion is to develop a biometric belt and braces model with a combination of scanned facial coordinates and voice recognition, where only a minimum of biometric data is stored. Conclusions are that online examination becomes feasible when the associated cheat risks are not zero but as low as in traditional examination, and that students' integrity have to be considered in all learning modalities.
... The system was successfully used with a group of industrial engineering students at UNED (National University of Online Education, in Spain) to get access to their online laboratory tests. In the same way, Hernández, Ortiz, Andaverde et al. (2008) describe the use of an online assessment through biometrics recognition systems in a secondary school. For the experiment, a sample of secondary school students (n = 102) was randomly chosen. ...
Article
Full-text available
The research arises from the necessity of knowing the degree of students' perception about biometrical facial authentication within distance education in order to check whether students are who they claim to be while they participate in lessons within the Moodle Learning Management System (LMS) platform. With the use of this technology within e-learning, a new path of opportunity just opens to verify the lack of fraud when students carry out their activities using the platform. © 2014 Francisco D. Guillén-Gámez, Iván García-Magariño, Silvia Prieto-Preboste.
... Whilst the idea has merit, his research neither clearly dissected how the approaches overcame the issue of cheating, nor the biometric performance being experienced in practice. Hernández et al. [9] proposed a prototype using fingerprint recognition to deal with the problem of student identification at the beginning of the e-assessment, together with a synchronized and continuous surveillance employing a web camera until the end of the online examination. Despite the fact this study is well evaluated, it did not explain the continuous video monitoring during the exam time (e.g., how it could be used in practicewould an examiner need to watch the individual video feeds of all participants?). ...
Article
Full-text available
In the history of learning development, e-learning has been a key factor in the education evolution. The significant growth in users of e-learning technologies (students and teachers) and their use in courses has given rise to a major concern over protecting them from misuse; a significant concern is that of the potential for cheating or illicit assistance during online examinations. This paper presents the development of a more secure, flexible, transparent and continuous authentication mechanism for e-assessments. To monitor the exam taker and ensure that only the legitimate student is taking the exam, the system offers a continuous user identification employing multimodal biometrics; a security layer using an eye tracker to follow/record the student’s eye movement; and, speech recognition to detect inappropriate communication. The focus of this paper in particular is the development and evaluation of 3D facial authentication. An experiment has been conducted to investigate the ability of the proposed platform to detect any cheating attempts. During the experiment, participants' biometric data (2D, depth, and infrared images), left and right eye images, eye movement or focus on the screen, and head movements have been collected using custom software. In addition to capturing facial images, the 3D camera also captures the session using a built-in microphone with noise-cancelation and the system recognizes speech (employing a speech recognition algorithm). To prove the applicability and feasibility, 51 participants participated in this experiment. The FRR of those 51 legitimate participants was 0% in 2D and 0.0063% in 3D facial recognition mode. In order to evaluate the robustness of the approach against targeted misuse three participants were tasked with a series of eight scenarios that map to typical misuse. The results of the FAR and FRR of five of these threat scenarios in both 2D and 3D facial recognition modes were 0% with two cases exhibiting an FAR of 0.11% and 0.076% in the 2D facial recognition mode. Therefore, relying on these encouraging results, the paper has experimentally explored the viability of the previously proposed e-invigilation of e-assessment system architecture.
... The idea of using biometrics for authentication of remote exam takers is not new, there were proposals for this more than a decade ago (Hernández, Ortiz, Andaverde, & Burlak, 2008;. However, technology for biometric authentication has made much progress recently, offering a wider range of measures to mitigate cheating. ...
Chapter
Full-text available
E-exams have different cheating opportunities and mitigations than paper exams, and remote exams also have different cheating risks that on-site exams. It is important to understand these differences in risk and possible mitigations against them. Authenticating the candidate may be a bigger challenge for remote exams, and biometric authentication has emerged as a key solution. This chapter delivers a categorization of different types of high-stakes assessments, different ways of cheating, and what types of cheating are most relevant for what types of assessments. It further presents an analysis of which threats biometric authentication can be effective against and what types of threats biometric authentication is less effective against. Insecure aspects of various biometric authentication approaches also indicate that biometric authentication and surveillance should be combined with other types of approaches (e.g., how questions are asked, timing of the exam) to mitigate cheating.
... Though the platform proved suitable for ridding impersonation and countering intrusion, cases of server downtime often lead to authentication or monitoring error. The authors in [18] presented a prototype fingerprint recognition system for student identification during electronic-based assessment. A web-camera-based synchronized surveillance system was also proposed for monitoring students' activities during examination. ...
... This includes controlling access to online educational content (Montgomery and Marais 2014), as well as using webcam-based facial recognition to authenticate online learners (i.e., confirming that the people engaging in online learning activities are actually who they claim to be) (Valera, Valera, and Gelogo 2015). Similarly, there is a growing interest in using facial recognition technology for so-called eassessment securityi.e., verifying the identity of students taking computer-based tests and examinations, and confirming their continued presence during the whole examination period (Hernández et al. 2008;Apampa, Wills, and Argles 2010). ...
Article
Full-text available
Facial recognition technology is now being introduced across various aspects of public life. This includes the burgeoning integration of facial recognition and facial detection into compulsory schooling to address issues such as campus security, automated registration and student emotion detection. So far, these technologies have largely been seen as routine additions to school systems with already extensive cultures of monitoring and surveillance. While critical commentators are beginning to question the pedagogical limitations of facially driven learning, other this article contends that school-based facial recognition presents a number of other social challenges and concerns that merit specific attention. This includes the likelihood of facial recognition technology altering the nature of schools and schooling along divisive, authoritarian and oppressive lines. Against this background, the article considers whether or not a valid case can ever be made for allowing this form of technology in schools.
... (iii) To include information from other body limbs, such as the arms and neck. (iv) To develop an ad hoc expert system to support studies of diabetic diseases with atrophy factors in the patient's gait and/or to assist the specialist in predicting DN in persons, given the efficiency achieved by combining the metaclassifier with the deep learning algorithm FilteredClassifier + Dl4jMlpClassifier. is proposed expert system, motivated by the biometric recognition of Hernández et al. [39], could be used online with only basic and standard network protocols, without requirements for advanced network mechanisms (i.e., from the perspective of ubiquitous computing for a better experience for study subjects). (v) To improve the results by considering the implementation of the use of the method of Combined selection and optimization of hyperparameters of classification algorithms [40,41], to explore the behavior of this method, and to increase the maximum percentage of 86.46% achieved in the present research. ...
Article
Full-text available
Machine learning, one of the core disciplines of artificial intelligence, is an approach whose main emphasis is analytical model building. In other words, machine learning enables an automaton to make its own decisions based on a previous training process. Machine learning has revolutionized every research sector, including health care, by providing precise and accurate decisions involving minimal human interventions through pattern recognition. This is emphasized in this research, which addresses the issue of “support for diabetic neuropathy (DN) recognition.” DN is a disease that affects a large proportion of the global population. In this research, we have used gait biomarkers of subjects representing a particular sector of population located in southern Mexico to identify persons suffering from DN. To do this, we used a home-made body sensor network to capture raw data of the walking pattern of individuals with and without DN. The information was then processed using three sampling criteria and 23 assembled classifiers, in combination with a deep learning algorithm. The architecture of the best combination was chosen and reconfigured for better performance. The results revealed a highly acceptable classification with greater than 85% accuracy when using these combined approaches.
... Though the platform proved suitable for ridding impersonation and countering intrusion, cases of server downtime often lead to authentication or monitoring error. The authors in [18] presented a prototype fingerprint recognition system for student identification during electronic-based assessment. A web-camera-based synchronized surveillance system was also proposed for monitoring students' activities during examination. ...
... Previous research has shown that one of the most serious challenges of assessment in a VLE is the potential for cheating and plagiarism (Mellar et al., 2018;Nickels, 2013). Due to the abrupt and rapid transition to e-learning under the COVID-19 pandemic, most universities utilized only basic security measures and did not use advanced systems (Hernández et al., 2008). Several studies insist that summative assessment requires more stringent procedure than the formative assessment (Andreatta & Gruppen, 2009). ...
Article
Full-text available
Aim/Purpose This study investigates the perceptions of faculty members at Prince Sattam bin Abdulaziz University, Saudi Arabia, towards preparedness of institutions of higher education (IHE) for assessment in virtual learning environments (VLEs) during the COVID-19 lockdown. In addition, the study explores evidence of bona fide challenges that impede the implementation of assessment in VLE for both formative and summative purposes, and it attempts to propose some pragmatic solutions. Background Assessment of student performance is an essential aspect of teaching and learning. However, substantial challenges exist in assessing student learning in VLEs.
... However, the effectiveness of these systems is low, as there is no way to check who actually performed those tasks [5], and the necessity to continuously perform some actions to verify presence is perceived to severely distract the student [14]. Many systems based on the acquisition of passive biometric data (e.g., fingerprints, keystroke and mouse dynamics) have been proposed [16,17]. Such systems are usually well accepted, despite systems based on fingerprints result intrusive and distracting to the student during exams [18]. ...
Article
Full-text available
This paper introduces an e-learning platform for the management courses based on MOOCs, able to continuously monitoring student’s behavior through facial coding techniques, with a low computational effort client-side and provide useful insight for the instructor. The system exploits the most recent developments in Deep Learning and Computer Vision for Affective Computing, in compliance with the European GDPR. Taking as input the video capture by the webcam of the device used to attend the course it: (1) perform continuous students’ authentication based on face recognition, (2) monitor the students’ level of attention through head orientation tracking and gaze detection analysis, (3) estimate emotions student’s emotion during the course attendance. The paper describes the overall system design and reports the results of a preliminary survey, which involved a total of 14 subjects, aimed at investigating user acceptance, in terms of intention to continue using such a system.
... The literature shows that amongst the most compelling challenges facing e-assessment is that there is ample room for plagiarism and other dishonest behavior from some students during the testing (Mellar, Peytcheva-Forsyth, Kocdar, Karadeniz, & Yovkova, 2018). Because of the sudden and quick shift to virtual learning during the lockdown, most IHE made use of only uncomplicated security procedures instead of using intricate high-security software (Hernández, Ortiz, Andaverde, & Burlak, 2008). A number of studies indicate that for summative assessment, stricter measures are needed than for formative assessment for obvious reasons (Andreatta & Gruppen, 2009). ...
Article
Full-text available
This study aims to delineate the observations of instructors at Princess Sumaya University for Technology (PSUT) in Jordan with regards to online assessment of their students in the time of the Coronavirus lockdown. Specifically, the study attempts to find out whether universities are prepared for online assessment during the lockdown and to probe feasible solutions to the challenges that hinder proper assessment in a virtual learning environment (VLE). As the challenges are determined, the study suggests a number of practical solutions. Data on faculty’s observations were obtained by means of an online survey. Eighty-three faculty members participated in this study. The findings showed that universities swiftly shifted to e-classes during the lockdown but that they were not adequately primed for an appropriate assessment in an online environment. The findings further showed that instructors were skeptical about the efficiency of remote assessment of their students. In addition, faculty members believed there was still a long way to go with regards to (1) the unavailability of reliable software to preclude academic dishonesty; (2) some faculty being unable to assess their students in VLE as it was their first experience; and (3) formative assessment not having been given enough attention. It is concluded that universities should have an exigency strategy for any sudden future lockdowns. This strategy includes, among other things, intensive e-teaching and e-testing training for faculty, high-tech invigilation and plagiarism software, reliable e-learning platforms with sufficient Internet bandwidth, setting up an e-assessment council at the university level.
... The literature shows that amongst the most compelling challenges facing e-assessment is that there is ample room for plagiarism and other dishonest behavior from some students during the testing (Mellar, Peytcheva-Forsyth, Kocdar, Karadeniz, & Yovkova, 2018). Because of the sudden and quick shift to virtual learning during the lockdown, most IHE made use of only uncomplicated security procedures instead of using intricate high-security software (Hernández, Ortiz, Andaverde, & Burlak, 2008). A number of studies indicate that for summative assessment, stricter measures are needed than for formative assessment for obvious reasons (Andreatta & Gruppen, 2009). ...
Preprint
Full-text available
This study aims to delineate the observations of instructors at Princess Sumaya University for Technology (PSUT) in Jordan with regards to online assessment of their students in the time of the Coronavirus lockdown. Specifically, the study attempts to find out whether universities are prepared for online assessment during the lockdown and to probe feasible solutions to the challenges that hinder proper assessment in a virtual learning environment (VLE). As the challenges are determined, the study suggests a number of practical solutions. Data on faculty’s observations were obtained by means of an online survey. Eighty-three faculty members participated in this study. The findings showed that universities swiftly shifted to e-classes during the lockdown but that they were not adequately primed for an appropriate assessment in an online environment. The findings further showed that instructors were skeptical about the efficiency of remote assessment of their students. In addition, faculty members believed there was still a long way to go with regards to (1) the unavailability of reliable software to preclude academic dishonesty; (2) some faculty being unable to assess their students in VLE as it was their first experience; and (3) formative assessment not having been given enough attention. It is concluded that universities should have an exigency strategy for any sudden future lockdowns. This strategy includes, among other things, intensive e-teaching and e-testing training for faculty, high-tech invigilation and plagiarism software, reliable e-learning platforms with sufficient Internet bandwidth, setting up an e-assessment council at the university level.
... Such physiological characteristics that do not change often can be used for identifi cation and authentication. They have been tried out for use in some settings of high-stakes assessment to authenticate and then to monitor the identity of a respondent during an examination, for instance, in the absence of proctoring (Hernández et al. 2008 ) . Here we are perhaps more concerned with biometrics as behavioral characteristics that may be a refl ection of a user response pattern related to a construct of interest to measure. ...
Chapter
Full-text available
In this chapter the authors have surveyed the methodological perspectives seen as important for assessing twenty-first century skills. Some of those issues are specific to twenty-first century skills, but the majority would apply more generally to the assessment of other psychological and educational variables. The narrative of the paper initially follows the logic of assessment development, commencing by defining constructs to be assessed, designing tasks that can be used to generate informative student responses, coding/valuing of those responses, delivering the tasks and gathering the responses, and modeling the responses in accordance with the constructs. The paper continues with a survey of the strands of validity evidence that need to be established, and a discussion of specific issues that are prominent in this context, such as the need to resolve issues of generality versus contextual specificity; the relationships of classroom to large-scale assessments; and the possible roles for technological advances in assessing these skills. There is also a brief segment discussing some issues that arise with respect to specific types of variables involved in the assessment of twenty-first century skills. The chapter concludes with a listing of particular challenges that are regarded as being prominent at the time of writing. There is an annexure that describes specific approaches to assessment design that are useful in the development of new assessments.
Article
The beginning of the 21st century marked an evolutionary "leap" in Internet technology - the transition from static web pages whose content was determined solely by their creator to dynamic, interactive user-created web pages and the emergence and proliferation of social networks as a special and multi-purpose cyber info-sphere. In such a new and dynamic environment, naturally the need for new ways of functioning of public relations has emerged, finding new approaches and methods that would successfully fit into the new digital environment and take advantage of all the newly created potential. This next evolutive stage of the Internet - Web 2.0 brought interactive access web-pages, blogs, social networks/media, targeted advertising and pod-casts have become new and vital fields of contemporary PR. The new interactive technologies have enabled not only more accurate identification of target groups but also direct access to the collection of unimaginable quantity and quality of data that describes not only groups but individuals as well. This quantum leap in knowledge of target audiences made possible more precise "tailoring" of messages for each of them, thus dramatically increasing the effectiveness of these messages. This paper will analyze the principles, functions and possibilities of modern digital public relations, the methods and tools for it`s application as well as practical examples.
Conference Paper
The security of online summative assessments goes beyond ensuring that the `right' student is authenticated at the initial login. More is required to ensure that the same authenticated student is present for the duration of the online test. In this paper, we explore the benefits and limitations of existing authentication methods as a technique to achieve presence verification. Additionally, we propose, a low-intrusive and low-resource intensive approach towards verifying a student's presence during summative e-assessments.
Article
An emerging tool of On Line Clinic Assessment Agent (OLCA) is proposed in this paper. OLCA allows the collaboration for four participants - assessment editor, investigator, examinee and domain expert. After assessments are authorized to an investigator by an assessment editor, the investigator can sells the assessments to examinees with OLCA tokens. The OLCA token allows the examinees to conduct the assessment on line and automatically generates the result with the clinic statistic norm. By passing the OLCA token to domain experts, the experts can comment the assessment result on line and pass the opinion to the examinee. OLCA keeps the examinee privacy among stages of clinic assessment because no central awareness of each participants. Finally, a practical on-line clinic assessment system is implemented to verify the feasibility of this model.
Article
This research work aims to investigate and evaluate ways of enhancing the learning process by the use of technology. The technology offers a pedagogical strategy to assess the students (online) by describing an evaluating strategy of student's assessment. The proposed system is being developed to provide an interactive web based learning environment. Three different types of assessment techniques have been introduced in this paper; Diagnostic Assessment, Self-Assessment and Summative Assessment which help the students and the teachers to improve teaching and learning capabilities. UML has been used to describe the proposed system specification while the whole system is implemented using .NET Framework. e-Learning and e-Assessment System with its web based features presents an equal opportunity of education for both the students in the classroom and the distant students. This is a student-centric system and the student's progress depends upon his/her own learning efforts. The proposed assessment system presented in this paper is aimed at supporting students in their learning by providing them with instant feedback.
Conference Paper
E-learning system is a web-based system which is exposed to computer threats. Services or asset of the e-learning system must be protected from any computer threats to ensure the users have peace of mind when using it. It is important to identify and understand the threats to the system in order develop a secure system. The main objectives of this paper are to discuss the computer security threats towards the e-learning system assets and to study the six categories of computer security threats to the e-learning assets. The activities which involve the e-learning assets will be analyzed and evaluated using the STRIDE model. The results show that the e-learning system assets are exposed to threats on availability, integrity and confidentiality .Our findings also show that the high risk assets are assessment and students’ assessment marks.
Article
Full-text available
Online student assessment features in many distance-learning programs. The prevention of plagiarism has been the subject of much attention, but insufficient attention has been given to other problems of dishonesty in online assessment. We survey the types of problems that can occur and what can be done about them. We believe many educators are unaware of these problems, and most countermeasures proposed are insufficient.
Article
The term biometrics has been hard to escape recently, with numerous articles being published discussing the advantages and disadvantages of the technology1 and 2. Much of this discussion has come about due to the level of research and interest shown in large scale implementations of the technology by the US and UK Governments3 and 4 and European Union.5 However, few articles to date have discussed the fundamental operation of biometrics and the subsequent issues that arise when developing a biometric technique. This article focuses upon describing the biometric process from a lower level of abstraction, and introduces a number of design features that play an inherent role in the security provided by a biometric approach.
Conference Paper
A wide spectrum of systems requires reliable personal recognition schemes to either confirm or determine the identity of an individual person. This paper considers multimodal biometric systems and their applicability to access control, authentication and security applications. Alternative strategies for feature extraction and sensor fusion are considered and contrasted. Issues related to performance assessment, deployment and standardisation are discussed. Finally future directions of biometric systems development are explored.
Online assessments and biometrics used in new immigration system
  • A Savvas
Savvas, A. "Online assessments and biometrics used in new immigration system". ComputerWeekly Section IT Management Politics and Law. 3/14/2006, pp. 10-10, 1/7p.
Tecnologías biométricas aplicadas a la seguridad
  • M Tapiador
  • J A Singüenza
Tapiador, M. and Singüenza, J. A. Tecnologías biométricas aplicadas a la seguridad. Alfaomega Grupo Editor S.A. de C.V. México, D.F. 2005.
Problems with online testing Northern Illinois University, Faculty Development and Instructional Design Center
  • G Ritter
Ritter, G. Problems with online testing Northern Illinois University, Faculty Development and Instructional Design Center 2006, Consulted in http://www.blackboard.niu.edu/blackboard/cheating.htm August 2006.
Consulted on line at http://www.reachoutmichigan.org/funexperiments/agesubject /lessons/prints_ext
  • Michigan Org
Michigan Org 2007. Consulted on line at http://www.reachoutmichigan.org/funexperiments/agesubject /lessons/prints_ext.html August 2007.
Griaule. Biometrics FAQ Consulted in http
  • Griaule
  • Griaule
Griaule. Biometrics FAQ Consulted in http://www.griaule.com/page/en-us/faq_biometrics August, 2006.
Cheating in Online Student Assessment: Beyond Plagiarism
  • N C Rove
Rove, N.C. "Cheating in Online Student Assessment: Beyond Plagiarism". Online Journal of Distance Learning Administration, Volume VII, Number II, Summer 2004 State University of West Georgia, Distance Education Center. 2004.
Verifying the Learner in distance learning
  • R Wisher
  • C Curnov
  • J Belanich
Wisher, R. Curnov, C. and Belanich, J. "Verifying the Learner in distance learning". 18 Annual Conference on Distance Teaching and Learning 2005.