Browsing by Author "Amart Sulong"

In modern world of high technologies today, biometric types, now are becoming popular in various applications in which to build up password based authentication system. Traditional password approach is simply not practical since it can be forgoted and stollen. Keystroke biometrics is adopted in this thesis to extend and enhance the life of password technique for authentication solution. The system generates template of individual typing characteristics for typed password by considering three types of feature extraction; maximum force typing pressure, time latency, overall typing speed for improvement of the measurement accuracy and durability against intrusion to security system. An intelligent classification program based on Artificial Neural Network (ANN) is adopted. Learning Vector Quantization (LVQ) Network, Multilayer Feedforward Network (MFN), and Radial Basis Function (RBF) Network are used as classifier to verify ligitimate user and reject imposter attacks using the feature extraction module of individual traits. The performance of the proposed system is evaluated based on False Rejection Rate (FRR) and False Acceptance Rate (FAR). Experiments have been conducted to test the performance of overall keystroke biometrics system and the results obtained showed that the proposed systems can verify a user's identity with FRR and FAR; FRR is 2.25%, FAR close set and FAR open set are 0.167% and 2.45% respectively.

Due to the advanced technologies, speech enhancement has become one of the prominent driving force in communication. Currently, there is a strong need for innovative single-channel speech enhancement algorithms that perform well at various types of noise levels. In this thesis, the compressive sensing technique was examined and evaluated for its suitability to be incorporated in speech enhancement algorithms due to its ability to recover signal from far fewer samples. Two novel speech enhancement algorithms have been proposed. The first algorithm was developed based on the modification of Wiener filter approach and compressive sensing. While the second algorithm added post-processing method using Gammatone filter to further improve the previous algorithm. Objective assessment test using Perceptual Evaluation of Speech Quality (PESQ), i.e. ITU-T P.862 standard, demonstrates that the first algorithm achieves around 15.19% improvement which outperforms other 16 traditional algorithms across 15 speech signals, 8 types of noise, and 0 to 15 dB SNR levels from NOIZEUS database. Moreover, the second algorithm further enhances the results to 16.38% improvement on average. Hence, the proposed speech enhancement algorithms based on compressive sensing have good potential across many types and intensities of environmental noise.