Siti Mariyam Shamsuddin

Application of Grey Relational Analysis for Multivariate Time Series

Grey relational analysis (GRA) has been widely applied in analysing multivariate time series data (MTS). It is an alternate solution to the traditional statistical limitations. GRA is employed to search for grey relational grade (GRG) which can be used to describe the relationships between the data attributes and to determine the important factors that significantly influence some defined objectives. This paper demonstrates how GRA has been successfully used in identifying the significant factors that affect the grain crop yield in China from 1990 to 2003. The results from analysing the sample data revealed that the main factor that affects the trend of crop yield is the consumption of pesticide and chemical fertilizer and the least important factor to be considered is the agricultural labour. Thus, by properly adjusting the significant affecting factors, the Chinas crop yield performance can be further improved. Furthermore, GRA can provide a ranking scheme that gives the order of the grey relationship among the dependent and independent factors which leads to essential information such as which input factor need to be considered to forecast grain crop yield more precisely when using artificial neural network (ANN). In order to evaluate the performance of GRA in ANN model, a comparison is made using multiple linear regression (MR) statistical method. The results from the experiment show that ANN using GRA has outperformed the MR model with 99.0% in forecasting accuracy.

Balanced the trade-offs problem of ANFIS using particle swarm optimization

Improving the approximation accuracy and interpretability of fuzzy systems is an important issue either in fuzzy systems theory or in its applications. It is known that simultaneous optimisation both issues was the trade-offs problem, but it will improve performance of the system and avoid overtraining of data. Particle swarm optimisation (PSO) is part of evolutionary algorithm that is good candidate algorithms to solve multiple optimal solution and better global search space. This paper introduces an integration of PSO for optimising the ANFIS learning especially for tuning membership function parameters and finding the optimal rule for better classification. The proposed method has been tested on four standard dataset from UCI machine learning i.e. Iris Flower, Haberman’s Survival Data, Balloon and Thyroid dataset. The results have shown better classification using the proposed PSO-ANFIS and the time complexity has reduced accordingly. Keywords: ANFIS, Interpretability, Accuracy, Evolutionary algorithms, Particle Swarm Optimisation;

Iris segmentation using an edge detector based on fuzzy sets theory and cellular learning automata.

Iris-based biometric systems identify individuals based on the characteristics of their iris, since they are proven to remain unique for a long time. An iris recognition system includes four phases, the most important of which is preprocessing in which the iris segmentation is performed. The accuracy of an iris biometric system critically depends on the segmentation system. In this paper, an iris segmentation system using edge detection techniques and Hough transforms is presented. The newly proposed edge detection system enhances the performance of the segmentation in a way that it performs much more efficiently than the other conventional iris segmentation methods.

Radial basis function Network based on multi-objective particle swarm optimization

The problem of unsupervised and supervised learning is discussed within the context of multi-objective optimization. In this paper, an evolutionary multi-objective selection method of RBF Networks structure is discussed. The candidates of RBF Network structure are encoded into the particles in PSO. Then, they evolve toward Pareto-optimal front defined by several objective functions concerning with model accuracy and model complexity. This study suggests an approach of RBF Network training through simultaneous optimization of architectures and weights with PSO-based multi-objective algorithm. Our goal is to determine whether Multi-objective PSO can train RBF Networks, and the performance is validated on accuracy and complexity. The experiments are conducted on benchmark datasets obtained from the UCI machine learning repository. The results show that our proposed method provides an effective means for training RBF Networks that is competitive with other evolutionary computational-based methods.

Quantum-Inspired Particle Swarm Optimization for Feature Selection and Parameter Optimization in Evolving Spiking Neural Networks for Classification Tasks

Particle Swarm Optimization (PSO) was introduced in 1995 by Russell Eberhart and James Kennedy (Eberhart & Kennedy, 1995). PSO is a biologically-inspired technique based around the study of collective behaviour in decentralized and self-organized animal society systems. The systems are typically made up from a population of candidates (particles) interacting with one another within their environment (swarm) to solve a given problem. Because of its efficiency and simplicity, PSO has been successfully applied as an optimizer in many applications such as function optimization, artificial neural network training, fuzzy system control. However, despite recent research and development, there is an opportunity to find the most effective methods for parameter optimization and feature selection tasks. This chapter deals with the problem of feature (variable) and parameter optimization for neural network models, utilising a proposed Quantum–inspired PSO (QiPSO) method. In this method the features of the model are represented probabilistically as a quantum bit (qubit) vector and the model parameter values as real numbers. The principles of quantum superposition and quantum probability are used to accelerate the search for an optimal set of features, that combined through co-evolution with a set of optimised parameter values, will result in a more accurate computational neural network model. The method has been applied to the problem of feature and parameter optimization in Evolving Spiking Neural Network (ESNN) for classification. A swarm of particles is used to find the most accurate classification model for a given classification task. The QiPSO will be integrated within ESNN where features and parameters are simultaneously and more efficiently optimized. A hybrid particle structure is required for the qubit and real number data types. In addition, an improved search strategy has been introduced to find the most relevant and eliminate the irrelevant features on a synthetic dataset. The method is tested on a benchmark classification problem. The proposed method results in the design of faster and more accurate neural network classification models than the ones optimised through the use of standard evolutionary optimization algorithms.

Hybrid Learning Enhancement of RBF Network with Particle Swarm Optimization

This study proposes RBF Network hybrid learning with Particle Swarm Optimization (PSO) for better convergence, error rates and classification results. In conventional RBF Network structure, different layers perform different tasks. Hence, it is useful to split the optimization process of hidden layer and output layer of the network accordingly. RBF Network hybrid learning involves two phases. The first phase is a structure identification, in which unsupervised learning is exploited to determine the RBF centers and widths. This is done by executing different algorithms such as k-mean clustering and standard derivation respectively. The second phase is parameters estimation, in which supervised learning is implemented to establish the connections weights between the hidden layer and the output layer. This is done by performing different algorithms such as Least Mean Squares (LMS) and gradient based methods. The incorporation of PSO in RBF Network hybrid learning is accomplished by optimizing the centers, the widths and the weights of RBF Network. The results for training, testing and validation of five datasets (XOR, Balloon, Cancer, Iris and Ionosphere) illustrates the effectiveness of PSO in enhancing RBF Network learning compared to conventional Backpropogation.

Rough Web Caching

The demand for Internet content rose dramatically in recent years. Servers became more and more powerful and the bandwidth of end user connections and backbones grew constantly during the last decade. Nevertheless users often experience poor performance when they access web sites or download files. Reasons for such problems are often performance problems, which occur directly on the servers (e.g. poor performance of server-side applications or during flash crowds) and problems concerning the network infrastructure (e.g. long geographical distances, network overloads, etc.). Web caching and prefetching have been recognized as the effective schemes to alleviate the service bottleneck and to minimize the user access latency and reduce the network traffic. In this chapter, we model the uncertainty in Web caching using the granularity of rough set (RS) and inductive learning. The proposed framework is illustrated using the trace-based experiments from Boston University Web trace data set.

Crowd analysis and its applications

Crowd is a unique group of individual or something involves community or society. The phenomena of the crowd are very familiar in a variety of research discipline such as sociology, civil and physic. Nowadays, it becomes the most active-oriented research and trendy topic in computer vision. Traditionally, three processing steps involve in crowd analysis, and these include pre-processing, object detection and event/behavior recognition. Meanwhile, the common process for analysis in video sequence of crowd information extraction consists of Pre-Processing, Object Tracking, and Event/Behavior Recognition. In terms of behavior detection, the crowd density estimation, crowd motion detection, crowd tracking and crowd behavior recognition are adopted. In this paper, we give the general framework and taxonomy of pattern in detecting abnormal behavior in a crowd scene. This study presents the state of art of crowd analysis, taxonomy of the common approach of the crowd analysis and it can be useful to researchers and would serve as a good introduction related to the field undertaken.

Rough Set Granularity in Mobile Web Pre-caching

Mobile Web pre-caching (Web prefetching and caching) is an explication of performance enhancement and storage limitation of mobile devices. In this paper, we present the granularity of rough sets (RS) and RS based inductive learning in reducing the size of rules to be stored in mobile devices. The conditional attributes such as timestamp, size document and object retrieval time are presented and the provided decision is granted. Decision rules are obtained using RS based inductive learning to grant the ultimate judgment either to cache or not to cache the conditional attributes and objects. However, in mobile clients, these rules need to be specified so as the specific sessions can be kept in their mobile storage as well as the proxy caching administrations. Consequently, these rules will notify the objects in Web application request and priority level to the clients accordingly. The results represent that the granularity of RS in mobile Web pre-caching is vital to improve the latest Web caching technology by providing virtual client and administrator feedback; hence making Web pre-caching technologies practical, efficient and powerful.

Intelligent Web Caching for E-learning Log Data

E-learning has been a common online service to support teaching and learning in education. Universiti Teknologi Malaysia (UTM) has been using such service that is known as e-Learning@UTM since 2005.xa0xa0The demand for e-learning content increases dramatically every semester. The performance of e-learning servers reduces when the number of users for each semester keeps growing. Hence users often experience poor performance in accessing the e-learning contents or downloading files. Such problems are due to the problem in the performance of servers, network infrastructure and majority of users tend to access the same piece of information repetitively. Web caching has been recognized as an effective scheme to reduce service bottleneck, users’ access latency andxa0xa0network traffic. Therefore this paper will discuss an alternative way to tackle these problems by implementing a log data detection tool. This tool is capable to automatically directing either to cache or not to cache the objects in a document based on the log data (number of object hits, script size of objects, and time to receive object) in e-Learning@UTM to enhance such Web access.