Resumen de tesis doctoral

Design and Implementation of an Advanced Security Remote Assessment System for Universities Using Data Mining

Diseño e Implementación de un Sistema de Evaluación Remota con Seguridad Avanzada para Universidades Utilizando Minería de Datos

Graduated: José Alberto Hernández Aguilar
Centro de Investigación en Ingeniería y Ciencias Aplicadas (CIICAp) Universidad Autónoma del Estado de Morelos (UAEM). jose_hernandez@uaem.mx

Advisor: Gennadiy Burlak
Centro de Investigación en Ingeniería y Ciencias Aplicadas (CIICAp) Universidad Autónoma del Estado de Morelos (UAEM). gburlak@uaem.mx

Advisor: Bruno Lara
Facultad de Ciencias Universidad Autónoma del Estado de Morelos (UAEM). bruno.lara@uaem.mx

Graduated on November 28, 2008

Abstract

We develop the detailed application of the computer technology on testing the student's level of knowledge. We implemented a Java original code, client–server technology based on the natural process of evaluation where the college students (clients) are tested for an examiner (server). Later, we discuss the security measures implemented by leading suppliers of e–learning tools, and we distinguish an important opportunity area on the use of advanced security measures that we used to differentiate our tool. Then, we present a data mining methodology to analyze activities of students in online assessments to detect any suspicious behavior (cheating), and show the results of applying it on a real class. Finally, we propose an affordable biometric technology to recognize remote students in online assessments to solve the well–known problem of: "who's there".

Keywords: Online Aassessment System, Data Mining, Advanced Security, Biometry.

Resumen

Desarrollamos una aplicación de la tecnología computational en la evaluación del conocimiento de los estudiantes. Implementamos una tecnología cliente–servidor, de código original en Java, basada en el proceso natural de evaluación donde los estudiantes (clientes) universitarios son evaluados por un examinador (servidor). Mas adelante, discutimos las medidas de seguridad implementadas por los proveedores líderes en herramientas de e–aprendizaje, y distinguimos una importante área de oportunidad en el uso de medidas de seguridad avanzada que usamos para diferenciar a nuestra herramienta. Entonces, presentamos una metodología de minería de datos para analizar las actividades de los estudiantes en evaluaciones en línea para detectar cualquier comportamiento sospechoso (trampas), y mostramos los resultados obtenidos de aplicarla en una clase real. Finalmente, proponemos una tecnología biométrica asequible para identificar a los estudiantes remotos en evaluaciones en línea para solucionar el bien conocido problema de: "¿quién está ahí?".

Palabras clave: Sistema de Evaluación en Línea, Minería de Datos, Seguridad Avanzada, Biometría.

DESCARGAR ARTÍCULO EN FORMATO PDF

References

1. Blackboard (2006, agosto). Security. Retrieved from http://www.blackboard.com/us/index.aspx        [ Links ]

2. BSU Ball State University (2006, agosto). Technology assessment reports on The use of Biometrics in education. Retrieved from http://web.bsu.edu/dpmuller/biometrics/        [ Links ]

3. Bugai, Y., Burlak, G., Demchenko, A. & Kuz'menko, N. (1997). On Application of Computer Technology Testing In Educational Process, Conference Role of Universities in the Future Information Society RUFIS'97, Prague, Czech Republic, 141–144.        [ Links ]

4. Burlak, G.N., Hernández, J.A. & Zamudio–Lara, A. (2005). The Application Of Online Testing For Educational Process In Client–Server System. CONGRESS: IADIS International Conference, Lisbon, Portugal, vol. 2, 389–392.        [ Links ]

5. Burlak, G., Ochoa. A. & Hernández, J.A. (2005a). The application of learning objects and Client–Server technology in online testing to measure basic knowledge level. In CONGRESS: X. Simpósio de Informática, V Mostra de Software Academico da PUCRS, Uruguaiana, RS Brasil, 51–58.        [ Links ]

6. Burlak, G., Hernández, J.A., Ochoa, A. & Muñoz, J. (2006). The measurement of the Student's basic Knowledge obtained by means of computer assessments, Research in Computing Science, Special issue: Advances in Computer Science and Engineering. 23, 201–213.        [ Links ]

7. Cavalli, A., Magg, S., Papagiannaki, S. & Verigakis, G. (2005). From UML models to automatic generated tests for the dotLRN e–learning platform, Electronic Notes in Theoretical Computer Science 116, 133–144. Retrieved form http://www.elsevier.com/locate/entcs        [ Links ]

8. Hernández, J.A., Ochoa, A., Muñoz, J. & Burlak, G. (2006). Detecting cheats in online student assessments using Data Mining. Dmin06, Las Vegas Nevada, USA, 204–210.        [ Links ]

9. Hernández, J.A., Ochoa, A., Andaverde, A. & Burlak, G. (2008). Biometrics in online assessments: A Study Case in High School Students. 18th International Conference on Electronics, Communications and Computers Conielecomp, Puebla, Mexico, 111–116.        [ Links ]

10. Hunt, N., Hughes, J. & Rowe, G. (2002). Formative Automated Computer Testing (FACT). British Journal of Educational Technology, 33(5), 525–535        [ Links ]

11. Jing, L. & Derrick, J. (2005, December). Data Mining and Its applications in Higher Education. Retrieved from http://www.ebscohost.com/        [ Links ]

12. McCabe, D. L. & Trevino, L. K. (1996). What we know about cheating in college: Longitudinal trends and recent developments. Change, 28(1), 28–33.        [ Links ]

13. McCabe, D. L. & Trevino, L. K. (1997). Individual and contextual influences on academic dishonesty: A multi–campus investigation. Research in Higher Education, 38(3), 379–396.        [ Links ]

14. Michigan Org (2007, agosto). Fingerprint Classification. Retrieved from http://www.reachoutmichigan.org/funexperiments/agesubiect/lessons/prints_ext.html        [ Links ]

15. Morris, T. A. (2005, 30 de diciembre). Cheating and plagiarism in the information age. Retrieved from http://terrymorris.net/tohe2004/CPIA_morris.pdf         [ Links ]

16. Ochoa, A. (2006). Más allá del Razonamiento Basado en Casos y una aproximación al Modelado de Sociedades Utilizando Minería de Datos. Post Doctoral Thesis, State University of Campinas, Radamelli, SP Brazil.         [ Links ]

17. Ochoa, A., et al. (2006). Italianitá: Discovering a Pygmalion Effect on Italian Communities. Advances in Computer Science and Engineering, 19, 57–67.        [ Links ]

18. Ochoa, A., Hernández, J.A., González, S., Castro, A. & Ponce, J.C. (2008). Evaluating the Authority in a Weblog Community. Computación y Sistemas,11(4), 370–380.        [ Links ]

19. Pearson (2006, agosto). Pearson Online Assessment Software from Pearson Assessments. Retrieved from http://www.pearsonassessments.com        [ Links ]

20. QuestionMark (2006, agosto). QuestionMark Perception Product Information. Retrieved from http://www.questionmark.com/us/perception/        [ Links ]

21. Rove, N. C. (2005, 30 de diciembre). Cheating in Online Assessment: Beyond Plagiarism. Online Journal of Distance Learning Administration, 3(2), State University of West Georgia, Distance Education Center. Retrieved from http://www.westga.edu/~distance/ojdla/summer72/rowe72.html        [ Links ]

22. Tapiador, M. & Singüenza, J. A. (2005). Tecnologías biométricas aplicadas a la seguridad. México, D.F. : Alfaomega.        [ Links ]

23. Van Horn, Royal. (1998). Data Mining For Research and Evaluation. Phi–Delta–Kappan Technology Section, 251–252.         [ Links ]

24. Varughese, J. (2005, abril). Testing, Testing: Ensure the success of students with online assessment tools. Retrieved from http://www.universitybusiness.com/        [ Links ]

25. Weka (2005, 21 de diciembre). Data Mining Software in Java. Retrieved from http://www.cs.waikato.ac.nz/ml/weka/        [ Links ]

26. Wisher, R., Curnow, C. & Belanich, J. (2005). Verifying the Learner in distance learning. 18 Annual Conference on Distance Teaching and Learning. Wisconsin, USA.        [ Links ]