David F. W. Yap

Medical image compression using block-based PCA algorithm

PCA algorithm can be employed to aid in image compression. In this paper, two extended-PCA algorithms that manipulate the block information of the image are tested and compared. The first algorithm is termed as block-by-block PCA in which general PCA algorithm are applied on each block of the image. In the second algorithm- the block-to-row PCA, all block information are first concatenated into row before general PCA algorithm is then applied on the transformed matrix. Digital fundus image is used as the input image in this work. Using the newly-derived compression ratios, the result shows that block-to-row PCA outperforms block-by-block PCA in terms of image quality and compression rate. At equal block size and compression ratio, block-to-row PCA can achieve higher PSNR than block-to-block PCA. Blocking effects are discernible on the reconstructed image using block-to-block PCA with block size = 16 and compression ratio as low as 0.25 while no apparent distortion are seen on the reconstructed image using block-to-row PCA with block size = 32 and compression ratio as high as 0.90.

A hybrid artificial immune systems for multimodal function optimization and its application in engineering problem

Lately, the field of Artificial Immune Systems (AIS) has attracted wide attention among researchers as the algorithm is able to improve local searching ability and efficiency. However, the rate of convergence for AIS is rather slow as compared to other Evolutionary Algorithms. Alternatively, Particle Swarm Optimization (PSO) has been used effectively in solving complicated optimization problems with simple coding and lesser parameters, but it tends to converge prematurely. Thus, the good features of AIS and PSO are combined in order to reduce their shortcomings. By comparing the optimization results of the mathematical functions and the engineering problem using hybrid AIS (HAIS) and AIS, it is observed that HAIS has better performances in terms of accuracy, convergence rate and stability.

Hybrid Artificial Immune System-Genetic Algorithm optimization based on mathematical test functions

This paper demonstrates a hybrid between two optimization methods that are Artificial Immune System (AIS) and Genetic Algorithm (GA). The capability of overcoming the shortcomings of individual algorithms without losing their advantages makes the hybrid techniques superior to the stand-alone ones based on the dominant purpose of hybridization. The improvement of the results that enable to get it if GA and AIS work separately is the main objective of this hybrid. The hybrid includes two processes; firstly, AIS is the attraction among the researchers as the algorithm. This enables it to develop local searching ability and efficiency yet the convergence rate for AIS is preferably not precise compared to the GA. Secondly, a Genetic Algorithm is typically initializing population randomly. The last generation of AIS will be the input to the next process of the hybrid which is the GA in this hybrid AIS-GA. Hybrid makes GA enters the stage of standard solutions more rapidly and more accurate compared with GA initialized population at random. To differentiate between the results in terms of achieving the minimum value for these functions, eight mathematical test functions are being used to make comparison.

Grayscale medical image compression using feedforward neural networks

In this paper, feedforward neural network trained with the backpropagation algorithm is proposed to compress grayscale medical images. In this new method, a three hidden layer feedforward network (FFN) is applied directly as the main compression algorithm to compress an MRI image. After training with sufficient sample images, the compression process will be carried out on the target image. The coupling weights and activation values of each neuron in the hidden layer will be stored after training. Compression is then achieved by using smaller number of hidden neurons as compare to the number of image pixels due to lesser information being stored. Experimental results show that the FFN is able to achieve comparable compression performance to popular existing medical image compression schemes such as JPEG2000 and JPEG-LS.

A GUI system for region-based image compression using Principal Component Analysis

Medical image compression has received great attention due to its increasing need to reduce the image size without compromising the diagnostically important medical information exhibited on the image. Region-based image compression based on Principal Component Analysis (PCA) has not widely been studied. Hence, in this paper, a GUI system that investigates the efficiency of the region-based compression was proposed. In this system, the user is able to trace the desired ROI on the image and the particular ROI selected will be preserved. From this work, it is found that region-based PCA performs better than PCA algorithm in terms of image quality, yielding comparable compression ratio as the PCA algorithm. The GUI system works as a user-friendly tool to compress the image upon the choice of the user to select the ROI and the compression range.

Bandwidth widening strategies for piezoelectric based energy harvesting from ambient vibration sources

Due to the fact that the ambient vibration sources are random and unpredictable, therefore a vibration based energy harvesting device is desirable to be able to operate at wider bandwidth in an envelop of frequency range to generate maximum electrical output. In this paper, various ambient vibration from household appliances, machineries, vehicle and moving vehicle were measured and investigated. The second part of the paper will discuss the strategies to harvest these ambient vibration sources. An array of piezoelectric multi-cantilever is proposed to address the issue of single piezoelectric cantilever with high Q-factor. Two configurations of multi-cantilever were fabricated in a form that elevated from the substrate as free-standing structures. One with six cantilevers of constant width but different lengths and another with five cantilevers of constant length but different widths. The measurement and experimental results show a frequency band of 200 Hz to 300 Hz as a common bandwith between the vibration sources and the capability of miniature piezoelectric energy harvester in harvesting maximum electrical energy.

A SWARM-BASED ARTIFICIAL IMMUNE SYSTEM FOR SOLVING MULTIMODAL FUNCTIONS

Artificial Immune Systems (AIS) have attracted enormous attention among researchers because the algorithms are able to improve global searching ability and efficiency. Nevertheless, the rate of convergence for AIS is relatively slow compared to other metaheuristic algorithms. On the other hand, genetic algorithms (GAs) and particle swarm optimization (PSO) have been used successfully in solving optimization problems, although they tend to converge prematurely. Therefore, the good attributes of AIS and PSO are merged in order to reduce this limitation. It is observed that the proposed hybrid AIS (HAIS) achieved better performances in terms of convergence rate, accuracy, and stability against GA and AIS by comparing the optimization results of the mathematical functions. A similar result was achieved by HAIS in the engineering problem when compared to GA, PSO, and AIS.

Enhancing telemedicine application: Feasible solution from 802.16 MAC layer

Telemedicine has become interesting field of research since decades ago. Rapid development of telecommunication technologies have opened up opportunities for further exploring the use of wireless technology to attains the objectives of telemedicine. In this paper, we explore the feasible solution to enhance telemedicine application performance with the use of wireless broadband technology viz. IEEE 802.16 Wireless Interoperability Microwave Access (WiMAX). Specifically, we try to outline the relevance of key technology residing in WiMAX Media Access Control (MAC) Layer with the fulfillment of medical data transfer requirements, especially for medical image. Thus, the aim of this paper is also to suggest the researches direction in the field of wireless broadband technology in conjunction with telemedicine purpose issues

An improved artificial immune system based on antibody remainder method for mathematical function optimization

Artificial immune system (AIS) is one of the nature-inspired algorithm for optimization problem. In AIS, clonal selection algorithm (CSA) is able to improve global searching ability. However, the CSA convergence and accuracy can be improved further because the hypermutation in CSA itself cannot always guarantee a better solution. Alternatively, Genetic Algorithms (GAs) and Particle Swarm Optimization (PSO) have been used efficiently in solving complex optimization problems, but they have a tendency to converge prematurely. In this study, the CSA is modified using the best solutions for each exposure (iteration) namely Remainder-CSA. The results show that the proposed algorithm is able to improve the conventional CSA in terms of accuracy and stability for single objective functions.

Artificial immune algorithm based gravimetric fluid dispensing machine

One of the most prominent methods used in handling the end process for materials-mixing is by having a dispensing system. An effective dispensing method using Pulse Width Modulation (PWM) at the end of the dispensing sequence with Artificial Immune System (AIS) automatic dispensing parameter fine tuning capability is proposed by optimizing the components of Dispensing Time and Stopping Time Delay to obtain constant and accurate reading from the precision balance scale. Based on the new dispensing sequence, experimental tests had been carried out using different materials with varying viscosities. The results denote that the combination of both PWM and AIS techniques would minimize the error rate for overshooting while exhibiting better accuracy. These are important in order to overcome the limitations of the conventional volumetric dispensing and manual parameter tuning presently applied in the dispensing system used in the coatings industry.