Norfarariyanti Parimon

BMA Performance of Video Coding for Motion Estimation

The major advantages of Block Matching Algorithm is it can reduce the temporal redundancy by placing a direction and magnitude of a Motion Vector (MV) instead of an image block. There are various type of BMA for motion estimation technique have been proposed to enhance the accuracy of the MV of the image block and also to reduce the computational complexity of the BMA for time consuming. This paper investigate and presents a very brief introduction to seven type of famous BMA that are Exhaustive Search, Three Step Search, New Three Step Search, Simple and Efficient Three Step Search, Four Step Search, Diamond Search and Adaptive Rood Pattern Search. This paper also performs all of the seven BMA techniques with different parameter of I and P mode sequence, different search range and also different block size.

Optoelectronic properties of improved GaN semiconductor on Si (111) using growth approaches and different interlayer's

The crystalline quality of wider direct band gap semiconductor (3.4 eV) h-GaN epilayer grown on Si (111) is evaluated by different growth approaches and by using different interlayers. The investigations of GaN epilayer crystal quality for the template of converted porous GaN layer formed by novel nitridation process of thin (2 and 0.5 μm) GaAs layer on Si (111) and on C+ ion implanted very thin SiC layer formed on Si (111) and grown ambient effect are made. Epilayer grown on thinner non-isoelectronic converted SiC templates is found to broaden its PL line width whereas epilayer grown on porously converted GaN layer fromed from iso- electronic GaAs (111) layer on Si (111) is found narrow line width. H2 ambient grown film better crystalline quality and higher PL Ex. peak energy is found as compared to N2 ambient grown film. Low temperature PL measurement, similarity between defect related donor-acceptor peaks (DAP) to defect related yellow band luminescence at the room temperature PL measurement is also f...

An Adaptive Learning Radial Basis Function Neural Network for Online Time Series Forecasting

Most of the neural network based forecaster operated in offline mode, in which the neural network is trained by using the same training data repeatedly. After the neural network reaches its optimized condition, the training process stop and the neural network is ready for real forecasting. Different from this, an online time series forecasting by using an adaptive learning Radial Basis Function neural network is presented in this paper. The parameters of the Radial Basis Function neural network are updated continuously with the latest data while conducting the desired forecasting. The adaptive learning was achieved using the Exponential Weighted Recursive Least Square and Adaptive Fuzzy C-Means Clustering algorithms. The results show that the online Radial Basis Function forecaster was able to produce reliable forecasting results up to several steps ahead with high accuracy to compare with the offline Radial Basis Function forecaster.

Mandarin syllables speech trainer based on F1 and F2 formant frequencies

Computer based speech training system is one of the applications in speech technology that aims to provide a facility to learn foreign language. Language teaching nowadays increasingly focuses on pronunciation skills since the teaching standard within language teaching has shifted towards more emphasis on the ability to communicate orally. In this project, a system was developed to train user on pronouncing Mandarin syllables, by observing the first two formant frequencies, F1 and F2. These two values are obtained from Linear Prediction Coefficients and are affected by jaw opening and position of tongue, respectively. The user is requested to adjust these two aspects in order to improve the pronunciation. The level of accuracy of the syllable pronounced by user was obtained by comparing the formant frequencies with the standard pronunciation, which was pronounced by three Mandarin lecturers. The system was tested on a group of students and the result shows that these students can pronounce the syllables correctly in less trial compared to another group of students who were trying to imitate the syllable by just listening to the sample pronunciation.

Two Dimensional Human Pose Estimation for the Upper Body Using Histogram and Template Matching Techniques

The main purpose of human pose estimation is to estimate the size, position or orientation of the human body parts within the digital scene information. The estimation technique is directly influenced by the type of image feature to be used, its model representation and also the application of the system. This work focuses on estimating the size and position of the upper human body parts (head, torso and arms) in image sequences. Silhouette, edge and colour are selected as input features and are extracted using wavelet-based feature extraction. The pose of the head and the torso are estimated using histogram technique while the pose of the arms are estimated using template matching technique. The estimated pose of the upper body parts are then represented using rectangle shape. The performance of the pose estimation is measured in terms of correct size and correct position.