Kanokmon Rujirakul

Recent advances in wireless sensor network technology have enabled the implementation of a variety of reliable, and distributed monitoring and controlling systems used in several sectors such as environment, healthcare, civil, and military. This has in turn led to the development of many of their features and optimizations for the purpose of efficiency, reliability, and scalability but with the key constraint of limited power supply sensor nodes. Several efficient power control and management schemes have been explored to keep the sensor nodes in the network operational for a long period in order to increase network lifetime. One of the more promising techniques is based on a hierarchical architecture or cluster-based routing that can be employed to enable the sensor networks to be deployed in a large-scale area. Low Energy Adaptive Clustering Hierarchy (LEACH) is a hierarchical scheme that provides simplicity and distributed operations with power-aware clustering. It is also widely used as a baseline for several further LEACH derivations. This research comparatively investigates the performance of LEACH's recent optimizations, especially the clustering criteria for selecting a proper set of cluster heads. To further enhance the probability criteria of the selected nodes, this research also recommends the modification of using adaptive moving window average and selection probability into an energy factor during the threshold selection stage. The results of this modification show an improvement of overall system energy usage.

With high performance characteristic in recognition precision, Principal Component Analysis is widely used in face recognition systems; however, the computational time may be huge, especially during Eigen Vector Decomposition of high matrix and vector manipulation operations in addition to a precision effect on multi-expression of human faces. Thus, this research investigates the possibility to utilize the parallelism of optimized expectation maximization on EVD to mitigate the random affect and then improve the recognition speed-up. We also proposed the recognition optimization utilizing histogram equalization and weighted Euclidean Distance classification derived from Eigenvalues to enhance the recognition precision. These mechanisms, the so-called Weighted Histogram Equalized PEM-PCA or whe-PEM-PCA, result in higher accuracy and lower complexity compared to a traditional PCA and its derivatives leading to a high speed face recognition system.

This paper presented a new methodology to determine the population, a set of feasible paths, chromosomes of genetic algorithms (GA) given multi-constraints, i.e., distance, deadline, and budget, in a shortest path and modified vehicle routing problem. Several aspects of GA have been explored and optimized including population generation, crossover, mutation, ranking, and path selection criteria. Our GA optimization proposal was evaluated with benchmark instances and compared with other heuristics in the literature resulting in the outstanding performance in terms of quality and computational time complexity given a heterogeneous of network sizes.

Due to a rapid growth of Internet, the number of network attacks has risen leading to the essentials of network intrusion detection systems (IDS) to secure the network. With heterogeneous accesses and huge traffic volumes, several pattern identification techniques have been brought into the research community. Data Mining is one of the analyses which many IDSs have adopted as an attack recognition scheme. Thus, in this paper, the classification methodology including attribute and data selections was drawn based on the well-known classification schemes, i.e., Decision Tree, Ripper Rule, Neural Networks, Naïve Bayes, k-Nearest-Neighbour, and Support Vector Machine, for intrusion detection analysis using both KDD CUP dataset and recent HTTP BOTNET attacks. Performance of the evaluation was measured using recent Weka tools with a standard cross-validation and confusion matrix.

Principal component analysis or PCA has been traditionally used as one of the feature extraction techniques in face recognition systems yielding high accuracy when requiring a small number of features. However, the covariance matrix and eigenvalue decomposition stages cause high computational complexity, especially for a large database. Thus, this research presents an alternative approach utilizing an Expectation-Maximization algorithm to reduce the determinant matrix manipulation resulting in the reduction of the stages’ complexity. To improve the computational time, a novel parallel architecture was employed to utilize the benefits of parallelization of matrix computation during feature extraction and classification stages including parallel preprocessing, and their combinations, so-called a Parallel Expectation-Maximization PCA architecture. Comparing to a traditional PCA and its derivatives, the results indicate lower complexity with an insignificant difference in recognition precision leading to high speed face recognition systems, that is, the speed-up over nine and three times over PCA and Parallel PCA.