Fadzilah Siraj

Uncovering Hidden Information Within University's Student Enrollment Data Using Data Mining

To date, higher educational organizations are placed in a very high competitive environment. To remain competitive, one approach is to tackle the student and administration challenges through the analysis and presentation of data, or data mining. This study presents the results of applying data mining to enrollment data of Sebha University in Libya. The results can be used as a guideline or roadmap to identify which part of the processes can be enhanced through data mining technology and how the technology could improve the conventional processes by getting advantages of it. Two main approaches were used in this study, namely the descriptive and predictive approaches. Cluster analysis was performed to group the data into clusters based on its similarities. For predictive analysis, three techniques have been used Neural Network, Logistic regression and the Decision Tree. The study shows that Neural Network obtains the highest results accuracy among the three techniques.

Malaysian Vowel Recognition Based on Spectral Envelope Using Bandwidth Approach

Automatic speech recognition (ASR) has made great strides with the development of digital signal processing hardware and software especially using English as the language of choice. In this paper, a new feature extraction method is presented to identify vowels recorded from 80 Malaysian speakers. The features are obtained from Vocal Tract Model based on Bandwidth (BW) approach. The bandwidth is determined by finding the frequency where the spectral energy is 3dB below the peak. Average gain was calculated from these bandwidths. Classification results from Bandwidth Approach were then compared with results from 14 MFCC Coefficients using BPNN (Backpropagation Neural Network), MLR (Multinomial Logistic Regression) and LDA (Linear Discriminative Analysis). Classification accuracy obtained shows Bandwidth Approach performs better than MFCC using all these classifiers.