Hasliza Abu Hassan

Logical Effort using a Novel Discrete Particle Swarm Optimization algorithm

Designers often need to choose the gate sizes for logic circuit designs to estimate the delay of the circuit. Simulation and timing analysis are poor tools for this task because they cannot be modified for better results. Hence, the method of Logical Effort (LE) provides a simple method to overcome these design problems. We apply a novel Discrete Particle Swarm Optimization algorithm (DPSO) to solve the LE problem for electronic circuits. The method uses the rescaling function commonly used to scale datasets in neural networks to convert continuous-valued PSO values into discrete values. The proposed algorithm was successfully applied on a three-stage NAND gate circuit, and has been shown to work well, with 100% accuracy in all test runs.

Heat exchanger modeling using NARX model with binary PSO-based structure selection method

This paper explores the application of Non-Linear Autoregressive Model with Exogenous Inputs (NARX) system identification of heat exchanger system. Model structure selection was performed using the Binary Particle Swarm Optimization (BPSO) algorithm. The application of BPSO for model structure selection represents each particles position as binary values, which were used to select a set of regressors from the regressor matrix. Parameter estimation was then performed using Householder-based QR factorization method. Tests performed on the heat exchanger system defined the model with a maximum lag of five, while fulfilling all model validation criterions.

Adaptive filter based on NARX model for recorded audio noise removal

This paper presents system identification-based approach to create a Non-linear Auto-Regressive model with Exogenous (NARX)-based adaptive noise filter to remove noise from recorded audio signals. The NARX model was trained with noisy recorded signal as inputs, and clean signal (from the MP3 audio file) as the output. The system identification process then tries to relate between the input and the output so that the noise component from the input is removed in the output stage. The binary Particle Swarm Optimization (BPSO) algorithm was used to perform model structure selection (selection of input and output lagged signals that best explains the future values of the data). Parameter estimation of the NARX model was done using Householder Transform-based QR factorization. Fitting and residual tests results show that the NARX model was successful in estimating the model, and filtering out noise well.

System identification of essential oil extraction system using Non-Linear Autoregressive Model with Exogenous Inputs (NARX)

This paper explores the application of Non-Linear Autoregressive Model with Exogeneous Inputs (NARX) system identification of an essential oil extraction system. Model structure selection was performed using the Binary Particle Swarm Optimization (BPSO) algorithm by (J. Kennedy and R. Eberhart, 1997). The application of BPSO for model structure selection represents each particles position as binary values. Then, the binary values were used to select a set of regressors columns from the regressor matrix. QR factorization was used to estimate the parameters of the reduced regressor matrix. Tests performed on the essential oil extraction system by (Rahiman, 2009), defined the 2nd order model with three terms, while fulfilling all model validation criterions.

Optimizing filter parameters using Particle Swarm Optimization

Filter designers often have to calculate the best parameters to suit the filter specifications. Software is typically used to help estimate those values, but sometimes the parameter combination cannot yield perfect results. Calculating the filter parameters using transfer functions would be more challenging with filter that have high orders. This project presents an application of a Particle Swarm Optimization algorithm (PSO) for designing high order filter. The proposed algorithm was successfully applied on a six-order elliptic filter, and has been shown to work well.

Analysis of microsoft kinect depth perception for distance detection of vehicles

The Microsoft Kinect device is capable to perform object detection using its advanced depth sensors. In this project, the Kinect depth sensor is used for object detection for vehicle collision avoidance. Tests performed on several types of vehicles and environmental conditions indicate that the Kinect sensor is able to perform this task well under various conditions.

Logical circuit gate sizing using MPSO guided by Logical Effort - An examination of the 8-stage full adder circuit

Automated Complementary Metal Oxide Semiconductor (CMOS) logic circuit design leads to the reduction in costs associated with manpower and manufacturing time. Conventional methods use repetitive manual testing guided by Logical Effort (LE). LE provides an easy way to compare and select circuit topologies, choose the best number of stages for path and estimate path delay. In this paper, we propose the Particle Swarm Optimization (PSO) algorithm as a method to automate the process of CMOS circuit design by approaching the design process as an optimization problem. In our work, we choose gate widths inside the circuit as parameters to be optimized in order to achieve the target delay, and its fitness is guided by the LE method. Various parameters, such as swarm size and iterations were tested under different initialization conditions to verify PSOs performance on a 4-stage half-adder circuit. Results have indicated that the PSO algorithm was an effective method to apply to the circuit design problem, with high convergence rates observed.

Logical circuit gate sizing using PSO guided by Logical Effort - an examination of the 12-stage ripple carry adder circuit

Automated Complementary Metal Oxide Semiconductor (CMOS) logic circuit design leads to the reduction in costs associated with manpower and manufacturing time. Conventional methods use repetitive manual testing guided by Logical Effort (LE). LE provides an easy way to compare and select circuit topologies, choose the best number of stages for path and estimate path delay. In this paper, we propose the Particle Swarm Optimization (PSO) algorithm as a method to automate the process of CMOS circuit design by approaching the design process as an optimization problem. In our work, we choose gate widths inside the circuit as parameters to be optimized in order to achieve the target delay, and its fitness is guided by the LE method. Various parameters, such as swarm size and iterations were tested under different initialization conditions to verify PSOs performance on a 12-stage ripple carry adder circuit. Results have indicated that the PSO algorithm was an effective method to apply to the circuit design problem, with high convergence rates observed.

Visualisation of exudates in fundus images using radar chart and color auto correlogram technique

Fundus images provide an opportunity for early detection of diabetes. Generally, retina fundus images of diabetic patients exhibit exudates, which are lesions indicative of Diabetic Retinopathy (DR). Therefore, computational tools can be considered to be used in assisting ophthalmologists and medical doctor for the early screening of the disease. Hence in this paper, we proposed visualisation of exudates in fundus images using radar chart and Color Auto Correlogram (CAC) technique. The proposed technique requires that the Optic Disc (OD) from the fundus image be removed. Next, image normalisation was performed to standardise the colors in the fundus images. The exudates from the modified image are then extracted using Artificial Neural Network (ANN) and visualised using radar chart and CAC technique. The proposed technique was tested on 149 images of the publicly available MESSIDOR database. Experimental results suggest that the method has potential to be used for early indication of DR, by visualising the overlap between CAC features of the fundus images.

CRS: Registration extension of the OpenConf™ Conference Management System

Academic conferences provide a social platform for participants to present, learn and discuss about new and interesting findings of their research. Management of these conferences typically utilize Conference Management Systems (CMSs) to simplify its management. However, most CMSs lack the registration function, which is a key component apart from the submission and review process. We describe modifications of the popular OpenConf™ CMS to include participant registrations and payment acceptance. The process involves adding several new tables to the existing database structure, as well as to develop the new interface for the added functionality. The modifications are detailed in this paper.