Browsing by Author "Sediono, Wahju"
Now showing 1 - 2 of 2
Results Per Page
Sort Options
Item Hybrid technique using singular value decomposition (SVD) and support vector machine (SVM) approach for earthquake prediction(IEEE, 2014-06-06) Astuti, Winda; Akmeliawati, Rini; Sediono, Wahju; Salami, Momoh-Jimoh E.Most of the existing earthquake (EQ) prediction techniques involve a combination of signal processing and geophysics techniques which are relatively complex in computation for analysis of the Earth's electric field data. This paper proposes a relatively simpler and faster method that involves only signal processing procedures. The prediction of the EQ occurrence estimation using a combination of singular value decomposition (SVD)-based technique for feature extraction and support vector machine (SVM) classifier is presented in this paper. Using the proposed method, the Earth's electric field signal is transformed into a new domain using SVD-based approach. In this approach, the time domain signal is projected on the left eigenvectors of impulse response matrix of the linear prediction coefficient (LPC) filter. Several features have been extracted from the transformed signal. These features are used as input for the SVM classifier in order to predict the location of the forthcoming EQ. Once the location is determined, a similar approach is used to estimate its magnitude. Finally, the time estimation of the forthcoming EQ is estimated based on the statistical observation. The occurred EQs during 2008 in Greece are used to train the classifiers, whereas those occurred from 2003 to 2010 in the same region are used to evaluate the performance of the proposed system. In predicting the location of the future EQs, the proposed system could achieve 77% accuracy. As for the magnitude prediction, the proposed system provides an accuracy of 66.67%. Moreover, the predicted time for the EQ with magnitude greater than Ms = 5 is 2 days ahead, whereas for magnitude greater than Ms = 6 is up to 7 days ahead.Item LIPS TRACKING IDENTIFICATION OF A CORRECT QURANIC LETTERS PRONUNCIATION FOR TAJWEED TEACHING AND LEARNING(IIUM Engineering Journal, 2017-05-30) Ahmad, Tareq A.; Jamil, Muhammad A.; Ahmad, Salmiah; Sediono, Wahju; Salami, Momoh-Jimoh E.; Hassan, Surur S.; Embong, Abdul H.Mastering the recitation of the holy Quran is an obligation among Muslims. It is an important task to fulfill other Ibadat like prayer, pilgrimage and zikr. However, the traditional way of teaching Quran recitation is a hard task due to the extensive training time and effort required from both teacher and learner. In fact, learning the correct pronunciation of the Quranic letters is the first step in mastering Tajweed (Rules and Guidance) in Quranic recitation. The pronunciation of Arabic letters is based on its points of articulation and the characteristics of a particular letter. In this paper we implement the lip identification technique from video signal acquired from expert to extract the movement data of the lips while pronouncing the correct Quranic letters. The extracted lip movement data from expert helps in categorizing the letters into 5 groups and in deciding the final shape of the lips. Later the technique was then tested among a public reciter and then compared for similarity verification between the public and the professional reciter. The system is able to extract the lips movement of the random user and draw the displacement graph and compared with the pronunciation of the expert. The error will be shown if the user has mistakenly pronounced the letter and suggested for improvement. More subjects with different background will be tested in very near future with feedback instructions. Machine learning techniques will be implemented at later stage for the real time application for learning process.