Speech recognition is a major topic in speech signal processing. Speech recognition is considered as one of the most popular and reliable biometric technologies used in automatic personal identification systems. Speech recognition systems are used for variety of applications such as multimedia browsing tool, access centre, security and finance. It allows people work in active environment to use computer. For a reliable and high accuracy of speech recognition, simple and efficient representation methods are required. In this paper, the zero crossing extraction and the energy level detection are applied to the recorded speech signal for voiced/unvoiced area detection. The detected voiced signals are applied for segmentation. Further, the MFCC method is applied to all of the segmented windows. The extracted MFCC data are further used as inputs for neural network training.

Lane detection is an essential component of autonomous mobile robot applications. Any lane detection method has to deal with the varying conditions of the lane and surrounding that the robot would encounter while moving. Lane detection procedure can provide estimates for the position and orientation of the robot within the lane and also can provide a reference system for locating other obstacles in the path of the robot. In this paper we present a method for lane detection in video frames of a camera mounted on top of the mobile robot. Given video input from the camera, the gradient of the current lane in the near field of view are automatically detected. Randomized Hough Transform is used for extracting parametric curves from the images acquired. A priori knowledge of the lane position is assumed for better accuracy of lane detection.

Path planning is an important issue as it allows a robot to get from start point to goal point. This work attempts to solve robot path planning problem iteratively using numerical technique. It is based on the use of Laplace's Equation to compute potential function in the configuration space of a mobile robot. This paper proposed a block iterative method known as Four Point-Explicit Group via Nine-Point Laplacian (4EG9L) for solving robot path planning problem. By employing a finite-difference technique, the experiment shows that it able to generate smooth path between the start and goal points. The simulation results show that 4EG9L performs faster than the previous method in generating path for mobile robot motion.

This paper presents our study on a simulation of path planning for indoor robot that relies on the use of Laplace’s equation to constrain the generation of Harmonic Potential Fields (HPF). The computation of HPF requires immense amount of computing resources, particularly when the size of environment is large. In the past, fast iterative methods that apply the use of half-sweep iteration and block technique are suggested. In this study, faster iterative method known as Four Point-Explicit Decoupled Group Successive Over relaxation via 9-Point Laplacian (4-EDGSOR-9L) is introduced. Essentially, the 4-EDGSOR-9L is actually a variant of block SOR iterative method based on four points that employs half-sweep iteration and utilizes 9-Point Laplacian discretization scheme. Once the HPF is obtained, the standard Gradient Descent Search (GDS) technique is performed for path tracing to the goal point.

The aim of this paper is to investigate the effectiveness of the Full-Sweep AOR Iterative method by using Full-Sweep Caputo's approximation equation to solve space-fractional diffusion equations. The governing space-fractional diffusion equations were discretized by using Full-Sweep Caputo's implicit finite difference scheme to generate a system of linear equations. Then, the Full-Sweep AOR iterative method is applied to solve the generated linear system To examine the application of FSAOR method two numerical tests are conducted to show that the FSAOR method is superior to the FSSOR and FSGS methods.