Google+ Followers

15 February 2012

Predicting Students’ Academic Success Using Artificial Neural Network

PREDICTING STUDENTS’ ACADEMIC SUCCESS USING ARTIFICIAL NEURAL NETWORK

A THESIS SUBMITTED TO THE GRADUATE SCHOOL OF TELKOM INSTITUTE OF TECHNOLOGY

BY ALDI RAMDHANI HERAWAN 213100001

Prof. The Houw Liong, Ph.D Supervisor

Shaufiah, M.T. Co-Supervisor

ABSTRACT

Predicting Students’ Academic Success Using Artificial Neural Network

Aldi Ramdhani Herawan

Supervisor : Prof. The Houw Liong, Ph.D

Co-Supervisor : Syaufiah, M.T

In an effort to improve the quality and competitiveness of scholars, universities must have specific strategies to achieve its objectives. Implementation of these strategies would require preparation and adjustments to the problem at hand. For that matter, need early identification what factors affect the success of a student's study. The success of a student's study can be viewed with a grade point average (GPA) student. This study seeks to identify what factors are affecting the success of a student's study indicated by the GPA. These factors are then used as input in the GPA prediction model using Artificial Neural Network (ANN). This study was also conducted on the reduction of data dimension using Principal Component Analysis (PCA). Finally, this study compares the results of predicted GPA, with the input data that has not been reduced and data have been reduced. For variables JUMLAH MATA KULIAH (number of courses) , JUMLAH SKS (sum of credits taken), JUMLAH SKS LULUS (sum of credits passed), and JUMLAH MUTU (average grades in the first year), component coefficients which measure correlations with GPA(average grades in the second year) are extracted. Component coefficient values for each variable are greater than 0.50, and the highest value is 0.958 for JUMLAH SKS LULUS. This shows that component extracted is evenly affected by these variables.

Keywords: Students’ Success, GPA, Prediction, Artificial Neural Network (ANN), Principal Component Analysis (PCA)

Prediction System of Economic Crisis in Indonesia using Time Series Analysis and System Dynamic Optimized by Genetic Algorithm

Master Technology in Informatics, IT Telkom, Bandung , 2012

Prediction System of Economic Crisis in Indonesia using Time Series Analysis and System Dynamic Optimized by Genetic Algorithm

Siti Sa’adah. Supervisor: Prof. The Houw Liong, Co-Supervisor: Adiwijaya, MSi

Abstract

Economic crisis that had happened at 1997-1998 in Indonesia stimulate the researchers to study further because economic that came from words ‘ecos’ and ‘nomos’ means value of life can be used as economic indicators. The economic indicators are GDP (Gross Domestic Product), inflation, population, and oil import per year from 1980-2011, will be tested using time series analysis and system dynamic optimized by algorithm genetic. The results are 93% - 99% accuracy in training and up to 90% accuracy for testing. These results proved that, the prediction system able to fit data in finding historical optimal and small error. Error that had been gotten in this system was caused by the time series data that been used is too short and economic is a chaotic complex system, so the error cannot be avoided.

7 Fakta Mengejutkan Dari Gempa Bumi ~ SERUPEDIA ZONE

7 Fakta Mengejutkan Dari Gempa Bumi ~ SERUPEDIA ZONE:

'via Blog this'

13 February 2012

INDONESIAN SPEECH RECOGNITION SYSTEM USING DISCRIMINANT FEATURE EXTRACTION – NEURAL PREDICTIVE CODING (DFE-NPC) AND PROBABILISTIC NEURAL NETWORK

FEBRUARY 2012 INDONESIAN SPEECH RECOGNITION SYSTEM USING DISCRIMINANT FEATURE EXTRACTION – NEURAL PREDICTIVE CODING (DFE-NPC) AND PROBABILISTIC NEURAL NETWORK
A THESIS SUBMITTED TO THE GRADUATE SCHOOL OF TELKOM INSTITUTE OF TECHNOLOGY
BY UNTARI NOVIA WISESTY 213100004
Prof. Dr. The Houw Liong Supervisor
Adiwijaya, SSi., MSi Co-Supervisor
IN PARTIAL FULFILLMENT OF THE REQUIREMENTS FOR THE DEGREE OF MASTER OF INFORMATICS IN THE INFORMATICS STUDY PROGRAM
ABSTRACT
Along with advances in information technology, it has been developed the technology to facilitate human life, one of which is speech recognition. Speech recognition is widely applied to speech to text, speech to emotion, in order to make gadget and computer easier to use, or to help people with hearing disability. However, the development of speech recognition to produce the text from the input voice has not well developed because of time processing. This is certainly going to make the animators and engineers need more time using speech recognition. Therefore, it needs a method to solve the time processing problem and with a good accuracy. In this study proposes a speech recognition system using Discriminant Feature Extraction – Neural Predictive Coding (DFE-NPC) as feature extraction and Probabilistic Neural Network as recognition method. This system can accelerate time processing because it only uses one iteration in training process. Time processing of proposed method is decrease significantly until 1:95 compared to Fuzzy Hidden Markov Model. The best accuracy of the system is 100% when number of class is 2 and 3, and the worst one is 56% when number of class is 10. Keywords: Speech Recognition System, DFE-NPC, PNN, time processing.