Neural Network Model for Performance Evaluation of Academic Staff of Tertiary Institutions
Okoye-ubaka M N., Adewole A P., Folorunso O. and J O J Ezike. Article: Neural Network Model for Performance Evaluation of Academic Staff of Tertiary Institutions. International Journal of Applied Information Systems 5(1):1-9, January 2013. BibTeX
@article{key:article, author = "Okoye-ubaka M. N. and Adewole A. P. and Folorunso O. and J. O. J. Ezike", title = "Article: Neural Network Model for Performance Evaluation of Academic Staff of Tertiary Institutions", journal = "International Journal of Applied Information Systems", year = 2013, volume = 5, number = 1, pages = "1-9", month = "January", note = "Published by Foundation of Computer Science, New York, USA" }
Abstract
This paper presents a neural network model for accomplishing the task of performance evaluation of academic staff of tertiary institutions. Data was collected from 10 randomly selected institutions using the completed Annual/Appraisal Performance and Evaluation Report (APER) form for academic staff. Fifteen Human Resource Metrics were considered which were classified under three main factors namely: Research, Teaching and Service. These are the major Human Resource foci of the Tertiary Institutions. The datasets were divided into three: train, validation and test data. The train data was presented to the Supervised Neural Network to approximate the fifteen Human Resource variables. The learning parameters for the training and testing of the survey data varied from 0. 07 to 0. 1 and the momentum parameter approached zero value (0. 01 to 0. 03). Root Mean Square Error (RMSE) was computed for both the parametric models (Principal Component 0. 80 and Factor Analysis 0. 15). The result revealed that Multilayer Perceptron Neural Network (MPNN) with back propagation algorithm got better outcome when compared with those parametric models. Experimental results in this study demonstrated that MPNN based model can closely predict the Human Resource metrics, with minimum RSME at 90%.
Reference
- Leap T. L and Crino M. D, (2007): Personnel / Human Resource Management. Macmillan Publishing Company.
- [Uzoka and Akinyokun, (2005): Knowledge Based System for Human Resource Evaluation in a University Environment, Journal of Testing and Evaluation, Vol. 33, No. 1
- Liu P. H and Wei C. C, (2004): A group Decision Making Technique for Appraising the Performances of Organization. International Journal of the Computer, the Internet and Management Vol. 8, No2, Pages 39-49. Taiwan.
- Saaty T. L, and Vargas L. G, (2004): Diagnosis with Dependent Symptoms: Baye's Theorem and Analytic Hierarchy Process; Operation Research. Vol. 46, Issue 4, Pages 491-503.
- Akinyokun,O. C(2002):Neuro-Fuzzy Expert System for Human Resource Perform Evaluation, First Bank of Nigeria Plc Endowment Fund Public lecture, Series 1, Federal University of Technology, Akure, Nigeria.
- Marengo et al (2007): Principal Component Analysis: Neural Networks Architectures for content addressable Memory: IEE Proceedings P. 138, 33-39.
- [Massart et al (2000): Multivariate Statistical Computation Analysis. Published by John Wiley and sons Inc.
- Vandeginste et al, (2000): Multivariate Modeling Published by John Wiley and sons Inc.
- Garcia de Ceca and Moro, (2000): Neural Network Approach; Pages 330-340.
- Sarhan and Helalat, (2007): Error Propagation. MIT Press, Cambridge MA, Chapters 10.
- Akinyokun, O. C and Uzoka F. M (2007): Factor Analysis of the effects of Academic Staff Profile on the investment Portfolio of a university, International Journal of the Computer, the Internet and Management 15 (1), 51-62. (11)
- Aggarwal et al (2006): Novelty detection and Neural Networks Validation.
- Hansen (2001): Using Neural Network to Forecast Automobiles Sales. The twenty third annual Pittsburgh conferences on Modeling and Simulation, University of Pittsburgh, U. S. A.
Keywords
Neural Networks Model, Performance Evaluation, Tertiary Institutions, Factor Analysis, Principal Component Analysis