Nor Hidayati Abdul Aziz

A Kalman Filter approach to PCB drill path optimization problem

Drill path optimization problem is an important problem in holes drilling with computer numerically controlled (CNC) machine. Due to the exponential increase in the number of possible solutions when the number of holes to be drilled increase, the metaheuristic optimization algorithm seems to be a good choice in solving this type of optimization problem. This paper presents a Kalman Filter approach in solving printed circuit board (PCB) routing problem by using the Simulated Kalman Filter (SKF) algorithm. The experimental results are compared with those obtained by swarm intelligence approach, which are the Particle Swarm Optimization (PSO) variants, Ant Colony System (ACS) and Cuckoo Search (CS). The implementation proves to be effortless with good global convergence capability.

Single-Solution Simulated Kalman Filter Algorithm for Routing in Printed Circuit Board Drilling Process

Optimal drilling path for printed circuit board is crucial in increasing productivity and reduce production costs. Single-solution Simulated Kalman Filter (ssSKF) is a new optimizer inspired by the Kalman filtering process. It uses only a single agent to solve optimization process by finding the estimate of the optimal solution. Principally, ssSKF algorithm uses the standard Kalman filter framework, aided by a local neighborhood technique during its prediction step. This paper reveals the potential of ssSKF as a good routing method in printed circuit board (PCB) drilling process. Experimental results indicate that the ssSKF algorithm outperforms the existing methods in searching a good route to speed up a PCB drilling process.

Review on the Usage of Swarm Intelligence in Gene Expression Data

This paper presents a review of the recent usage of swarm intelligence for optimizing feature selection in microarray data focusing on its application for cancer detection and classification. The feature selection technique is used in the analysis of microarray so that only useful data is trained for further analysis and prediction. The process of feature selection would affect the effectiveness of the classification. This is due to the enormous quantity of genes being expressed at the same time. An optimized feature selection would ensure a high accuracy of classification. Swarm intelligence has been effective in solving feature selection and classification problems. This paper also gives overview on the sources of microarray data which are used in the literature.

Finite state machine approach for STOP codon detection during protein synthesis

STOP codon detection is an important problem in protein synthesis or DNA sequencing since it plays an important role in the identification of coding region where the genes are located in the sequence. In this paper, finite state machine based approach is proposed for STOP codon detection during protein synthesis. VHDL code is used to implement the design of the proposed method. Simulation studies for different sequences from GenBank were carried out using the proposed method and the results are presented. This approach not only detects the STOP codons but also provides a count of number of STOP codons in a given sequence irrespective of its length.

Ant-colony algorithm with interference cancellation for cooperative transmission

Despite the large bandwidth available for all users in high-speed wireless networks, resources allocation and user scheduling remain essential to combat interference, increase throughput and reduce complexity. As the number of users increases, the computational complexity tends to increase significantly. The trade-off between the complexity reduction and capacity improvement is the challenge. Hence a unique ant-colony optimisation method is implemented with successive interference cancellation to reduce complexity and provide higher capacity to more users. The incurred complexity is at least 50% less than other schemes. The average mean square error achieved is around 4 dB smaller than that of the existing scheme.

BTFriend: Bluetooth Security Alert System

Bluetooth, as the most popular end user choice of wireless connection, have its own security issues till now. In this paper, we introduce the proof-of-concept of BTFriend, the only Bluetooth Security Alert System designed for end users. We also discuss the development of first version BTFriends prototype including the creation of Bluetooth device threat classification database and the usage of vNote file format for alert messages to most of mobile phones and notebooks. Finally, the paper highlight the performance of the prototype in terms of device detection time, detection distance, and alert response time, under multiple scenarios.