Yen-Chieh Ouyang

A New Growing Method for Simplex-Based Endmember Extraction Algorithm

A new growing method for simplex-based endmember extraction algorithms (EEAs), called simplex growing algorithm (SGA), is presented in this paper. It is a sequential algorithm to find a simplex with the maximum volume every time a new vertex is added. In order to terminate this algorithm a recently developed concept, virtual dimensionality (VD), is implemented as a stopping rule to determine the number of vertices required for the algorithm to generate. The SGA improves one commonly used EEA, the N-finder algorithm (N-FINDR) developed by Winter, by including a process of growing simplexes one vertex at a time until it reaches a desired number of vertices estimated by the VD, which results in a tremendous reduction of computational complexity. Additionally, it also judiciously selects an appropriate initial vector to avoid a dilemma caused by the use of random vectors as its initial condition in the N-FINDR where the N-FINDR generally produces different sets of final endmembers if different sets of randomly generated initial endmembers are used. In order to demonstrate the performance of the proposed SGA, the N-FINDR and two other EEAs, pixel purity index, and vertex component analysis are used for comparison

Band Expansion-Based Over-Complete Independent Component Analysis for Multispectral Processing of Magnetic Resonance Images

Independent component analysis (ICA) has found great promise in magnetic resonance (MR) image analysis. Unfortunately, two key issues have been overlooked and not investigated. One is the lack of MR images to be used to unmix signal sources of interest. Another is the use of random initial projection vectors by ICA, which causes inconsistent results. In order to address the first issue, this paper introduces a band-expansion process (BEP) to generate an additional new set of images from the original MR images via nonlinear functions. These newly generated images are then combined with the original MR images to provide sufficient MR images for ICA analysis. In order to resolve the second issue, a prioritized ICA (PICA) is designed to rank the ICA-generated independent components (ICs) so that MR brain tissue substances can be unmixed and separated by different ICs in a prioritized order. Finally, BEP and PICA are combined to further develop a new ICA-based approach, referred to as PICA-BEP to perform MR image analysis.

Spectral derivative feature coding for hyperspectral signature analysis

This paper presents a new approach to hyperspectral signature analysis, called spectral derivative feature coding (SDFC). It is derived from texture features used in texture classification to dictate gradient changes among adjacent bands in characterizing spectral variations so as to improve better spectral discrimination and classification. In order to evaluate its performance, two known binary coding methods, spectral analysis manager (SPAM) and spectral feature-based binary coding (SFBC) are used to conduct comparative analysis. Experimental results demonstrate that the proposed SDFC performs more effectively in capturing spectral characteristics than do SPAM and SFBC.

An Efficient Green Control Algorithm in Cloud Computing for Cost Optimization

Cloud computing is a new paradigm for delivering remote computing resources through a network. However, achieving an energy-efficiency control and simultaneously satisfying a performance guarantee have become critical issues for cloud providers. In this paper, three power-saving policies are implemented in cloud systems to mitigate server idle power. The challenges of controlling service rates and applying the N-policy to optimize operational cost within a performance guarantee are first studied. A cost function has been developed in which the costs of power consumption, system congestion and server startup are all taken into consideration. The effect of energy-efficiency controls on response times, operating modes and incurred costs are all demonstrated. Our objectives are to find the optimal service rate and mode-switching restriction, so as to minimize cost within a response time guarantee under varying arrival rates. An efficient green control (EGC) algorithm is first proposed for solving constrained optimization problems and making costs/performances tradeoffs in systems with different power-saving policies. Simulation results show that the benefits of reducing operational costs and improving response times can be verified by applying the power-saving policies combined with the proposed algorithm as compared to a typical system under a same performance guarantee.

A Secure Scheme Against Power Exhausting Attacks in Hierarchical Wireless Sensor Networks

Security and energy efficiency are critical concerns in wireless sensor network (WSN) design. This paper aims to develop an energy-efficient secure scheme against power exhausting attacks, especially the denial-of-sleep attacks, which can shorten the lifetime of WSNs rapidly. Although various media access control (MAC) protocols have been proposed to save the power and extend the lifetime of WSNs, the existing designs of MAC protocol are insufficient to protect the WSNs from denial-of-sleep attacks in MAC layer. This is attributed to the fact that the well-known security mechanisms usually awake the sensor nodes before these nodes are allowed to execute the security processes. Therefore, the practical design is to simplify the authenticating process in order to reduce the energy consumption of sensor nodes and enhance the performance of the MAC protocol in countering the power exhausting attacks. This paper proposes a cross-layer design of secure scheme integrating the MAC protocol. The analyses show that the proposed scheme can counter the replay attack and forge attack in an energy-efficient way. The detailed analysis of energy distribution shows a reasonable decision rule of coordination between energy conservation and security requirements for WSNs.

PPI-SVM-Iterative FLDA Approach to Unsupervised Multispectral Image Classification

This paper presents a new approach to unsupervised classification for multispectral imagery. It first implements the pixel purity index (PPI) which is commonly used in hyperspectral imaging for endmember extraction to find seed samples without prior knowledge, then uses the PPI-found samples as support vectors for a kernel-based support vector machine (SVM) to generate a set of initial training samples. In order to mitigate randomness caused by PPI and sensitivity of support vectors used by SVM it further develops an iterative Fishers linear discriminate analysis (IFLDA) that performs FLDA classification iteratively to produce a final set of training samples that will be used to perform a follow-up supervised classification. However, when the image is very large, which is usually the case in multispectral imagery, the computational complexity will be very high for PPI to process the entire image. To resolve this issue a Gaussian pyramid image processing is introduced to reduce image size. The experimental results show the proposed approach has great promise in unsupervised multispectral classification.

Quantitative analysis in clinical applications of brain MRI using independent component analysis coupled with support vector machine

To effectively perform quantification of brain normal tissues and pathologies simultaneously, independent component analysis (ICA) coupled with support vector machine (SVM) is investigated and evaluated for effective volumetric measurements of normal and lesion tissues using multispectral MR images.

Independent component analysis for magnetic resonance image analysis

Independent component analysis (ICA) has recently received considerable interest in applications of magnetic resonance (MR) image analysis. However, unlike its applications to functional magnetic resonance imaging (fMRI) where the number of data samples is greater than the number of signal sources to be separated, a dilemma encountered in MR image analysis is that the number of MR images is usually less than the number of signal sources to be blindly separated. As a result, at least two or more brain tissue substances are forced into a single independent component (IC) in which none of these brain tissue substances can be discriminated from another. In addition, since the ICA is generally initialized by random initial conditions, the final generated ICs are different. In order to resolve this issue, this paper presents an approach which implements the over-complete ICA in conjunction with spatial domain-based classification so as to achieve better classification in each of ICA-demixed ICs. In order to demonstrate the proposed over-complete ICA, (OC-ICA) experiments are conducted for performance analysis and evaluation. Results show that the OC-ICA implemented with classification can be very effective, provided the training samples are judiciously selected.

A new security key exchange channel for 802.11 WLANs

Recently, public wireless local area network systems based on IEEE 802.11 are becoming popular in hot spot areas such as airports, department store, etc. The 802.1X and 802.11i were proposed to resolve some problems in 802.11. However, the 802. 1x still has some drawbacks and could be hijacked through middle of communication session. The main problems in the wireless LANs security standards are the key distribution and mutual authentication between the supplicant and the access point (AP). We propose another scheme to construct a secure channel for regular communication security. To aim at above, we propose a security key exchange scheme to avoid flaws and drawbacks. The prime purpose is to create a secure channel between supplicant and AP. Therefore, supplicant and AP need to compute session key individually. This scheme needs three phases and all steps of the phases are finished by public-key encryption. Thus, no information will be gotten between supplicant and server or between AP and server.

A secure scheme for power exhausting attacks in wireless sensor networks

Security and energy efficiency are the most important concerns in wireless sensor networks (WSNs) design. To save the power and extend the lifetime of WSNs, various media access control (MAC) protocols are proposed. Most traditional security solutions can not be applied in the WSNs due to the limitation of power supply. The well-known security mechanisms usually awake the sensor nodes before the sensor nodes can execute the security processes. However, the Denial-of-Sleep attacks can exhaust the energy of sensor nodes and shorten the lifetime of WSNs rapidly. Therefore, the existing designs of MAC protocol are insufficient to protect the WSNs from Denial-of-Sleep attack in MAC l ayer. The practical design is to simplify the authenticating process in order to enhance the performance of the MAC protocol in countering the power exhausting attacks. This paper proposes a cross-layer design of secure scheme integrating the MAC protocol. The analyses show that the proposed scheme can counter the replay attack and forge attack in an energy-efficient way.