Nur'Aini Abdul Rashid

Data Mining for Medical Systems: A Review

Data mining is a growing area of research that intersects with many disciplines such as Artificial Intelligence (AI), databases, statistics, visualization, and high-performance and parallel computing. The goal of data mining is to turn data that are facts, numbers, or text which can be processed by a computer into knowledge. Nowadays, the reliance of health care on data is increasing. Therefore, this paper aims to allow the readers to understand about data mining and its importance in

Fast Dynamic Programming Based Sequence Alignment Algorithm

Protein sequence alignment is basic operation mostly used in protein sequence analysis. The most optimal algorithm used in sequence alignment is based on the dynamic programming method. Smith-Waterman algorithm is the most commonly used dynamic programming based sequence alignment algorithm. However the algorithm uses quadratic time and space. Heuristic algorithm such as FASTA and BLAST were introduced to speed up the sequence alignment algorithm. FASTA is based on word search whereas BLAST is based on maximum segment pairs. In word search algorithm, lists of words from the query and database sequence are being compared to determine if two sequences have a region of sufficient similarity to merit further alignment using the Smith-Waterman Algorithm. All the different algorithms use the substitutions matrix based on the twenty alphabet amino acids. However research shows that reducing the number of amino acids to 10 does not affect the similarity measure. Our proposed algorithm uses the reduced amino acids alphabet to transform the protein sequences into a sequence of integer and uses n-gram to reduce the length of the sequence. Then the Smith-Waterman algorithm is used to get the similarity measure between two sequences. Result shows that the new proposed algorithm is as sensitive as the Smith-Waterman algorithm yet uses less space and performs better

Thermodynamic Heuristics with Case-Based Reasoning: Combined Insights for RNA Pseudoknot Secondary Structure

Abstract The secondary structure of RNA pseudoknots has been extensively inferred and scrutinized by computational approaches. Experimental methods for determining RNA structure are time consuming and tedious; therefore, predictive computational approaches are required. Predicting the most accurate and energy-stable pseudoknot RNA secondary structure has been proven to be an NP-hard problem. In this paper, a new RNA folding approach, termed MSeeker, is presented; it includes KnotSeeker (a heuristic method) and Mfold (a thermo- dynamic algorithm). The global optimization of this thermodynamic heuristic approach was further enhanced by using a case-based reasoning technique as a local optimization method. MSeeker is a proposed algorithm for predicting RNA pseudoknot structure from individual sequences, especially long ones. This research demonstrates that MSeeker improves the sensitivity and specificity of existing RNA pseudoknot structure predictions. The performance and structural results from this proposed method were evaluated against seven other state- of-the-art pseudoknot prediction methods. The MSeeker method had better sensitivity than the DotKnot, FlexStem, HotKnots, pknotsRG, ILM, NUPACK and pknotsRE methods, with 79% of the predicted pseudoknot base-pairs being correct.

Parallel K-Means Clustering Algorithm on DNA Dataset

Clustering is a division of data into groups of similar objects. K-means has been used in many clustering work because of the ease of the algorithm. Our main effort is to parallelize the k-means clustering algorithm. The parallel version is implemented based on the inherent parallelism during the Distance Calculation and Centroid Update phases. The parallel K-means algorithm is designed in such a way that each P participating node is responsible for handling n/P data points. We run the program on a Linux Cluster with a maximum of eight nodes using message-passing programming model. We examined the performance based on the percentage of correct answers and its speed-up performance. The outcome shows that our parallel K-means program performs relatively well on large datasets.

Multiple sequence alignment using genetic algorithm and simulated annealing

This paper presents the combination of genetic algorithm and simulated annealing to solve multiple sequence alignment (MSA) assignment. Genetic algorithm will try to find a new region of feasible solution while simulated annealing will act as an aligning improver. There are several aspects that must be taken into consideration such as the representation, evaluation function and operator. Simulated annealing also helps to prevent local minima problem. Sequence similarity plays a major role in Bioinformatics and molecular biology. Significant results were produced from the prealignment and genetic algorithm phase.

A framework for childhood obesity classifications and predictions using NBtree

Obesity is a common issue nowadays. The numbers of obese people are increasing every year. There are evidences that childhood obesity persists into adulthood. Predicting obesity at an early age is both useful and important because preventive measures and proper interventions can be applied if the children indicated a high risk of obesity. However, the prediction of childhood obesity is a difficult task. Many ways and techniques such as assessment of body composition, data mining techniques, and logistic regression have been applied to predict childhood obesity, but only a few managed to produce accurate results. The numbers of efforts on childhood obesity prediction need to be increased and the techniques used should be improvised. The initial stage of this study involves collecting data from primary sources: parents, children and caretaker. Then, we identify risk factors such as parental obesity and education, children lifestyle and habits, and environment influences, and proposes a framework of childhood obesity prediction using NBtree.

A Comparative Taxonomy of Parallel Algorithms for RNA Secondary Structure Prediction

RNA molecules have been discovered playing crucial roles in numerous biological and medical procedures and processes. RNA structures determination have become a major problem in the biology context. Recently, computer scientists have empowered the biologists with RNA secondary structures that ease an understanding of the RNA functions and roles. Detecting RNA secondary structure is an NP-hard problem, especially in pseudoknotted RNA structures. The detection process is also time-consuming; as a result, an alternative approach such as using parallel architectures is a desirable option. The main goal in this paper is to do an intensive investigation of parallel methods used in the literature to solve the demanding issues, related to the RNA secondary structure prediction methods. Then, we introduce a new taxonomy for the parallel RNA folding methods. Based on this proposed taxonomy, a systematic and scientific comparison is performed among these existing methods.

Hajj-QAES: A Knowledge-Based Expert System to Support Hajj Pilgrims in Decision Making

Most Muslim countries provide trainings to their pilgrims before departing for Mecca in order to assist them in achieving a perfect or mabrur hajj. However they probably encounter hajj related problems that require them to make immediate decisions especially while performing hajj. In such situations they may refer to hajj guide books or their fellow pilgrims. Besides, they may need to refer to hajj experts in the decision making process pertaining to more complex problems. Nevertheless, experts may not be around all the time especially while performing hajj rituals. We propose a knowledge-based approach that can capture possible problems and solutions from the experts in a prototype known as hajj Q&A expert system or Hajj-QAES. It provides an interface that enables experts to capture both simple and advanced questions. Thus, we anticipate Hajj-QAES can support pilgrims both in learning process and most importantly while performing hajj in Mecca. Such systems would be more accessible should it be installed in handheld devices such as a hand phone or a personal digital assistant (PDA).

An enhanced meta-scheduling system for grid computing that considers the job type and priority

Meta-scheduling systems play a crucial role in scheduling jobs that are submitted for execution and require special attention because an increasing number of jobs are being executed using a limited number of resources. The primary problem of meta-scheduling is selecting the best resources (sites) to use to execute the underlying jobs while still achieving the following objectives: reducing the mean job turnaround time, ensuring site load balance, and considering job priorities. We introduce an enhanced meta-scheduling system, called Job Nature Meta-scheduling over Grid (JNMgrid), that achieves these objectives. JNMgrid consists of three components: (1) Job Analyzer and Monitor, which is responsible for determining the types of jobs in specific ratios; (2) Job Decider, which is responsible for matching the jobs with the appropriate resources; and (3) Job Batcher, which is responsible for determining the best number of jobs for execution. The performance of JNMgrid is compared with similar existing systems, such as Random, Queue Length, File Access Cost, and File Access Cost + Job Queue Access Cost. The simulation results demonstrate that JNMgrid outperforms these systems and can thus be deployed in any grid middleware to improve sharing of limited resources among grid users.

Fast decision tree-based method to index large DNA-protein sequence databases using hybrid distributed-shared memory programming model

In recent times, the size of biological databases has increased significantly, with the continuous growth in the number of users and rate of queries; such that some databases have reached the terabyte size. There is therefore, the increasing need to access databases at the fastest rates possible. In this paper, the decision tree indexing model (PDTIM) was parallelised, using a hybrid of distributed and shared memory on resident database; with horizontal and vertical growth through Message Passing Interface (MPI) and POSIX Thread (PThread), to accelerate the index building time. The PDTIM was implemented using 1, 2, 4 and 5 processors on 1, 2, 3 and 4 threads respectively. The results show that the hybrid technique improved the speedup, compared to a sequential version. It could be concluded from results that the proposed PDTIM is appropriate for large data sets, in terms of index building time.