Min-Yu Huang

Accelerating the Kalman Filter on a GPU

For linear dynamic systems with hidden states, the Kalman filter can estimate the system state and its error covariance considering the uncertainties in transition and observation models. In each iteration of applying the Kalman filter, the two phases of predict and update contain a total of 18 matrix operations which include addition, subtraction, multiplication and inversion. As recent graphic processor units (GPU) have shown to provide high speedup in matrix operations, we implemented a GPU accelerated Kalman filter in this work. For general reference purposes, we tested the filter on typical large-scale over-determined systems with thousands of components in states and measurements. For the various combinations of configurations in our test, the GPU accelerated filter shows a scalable speedup as either the state or the measurement dimension increases. The obtained 2 to 3 orders of magnitude speedup over its single-threaded CPU counterpart shows a promising direction of using the GPU-based Kalman filter in large-scale time-critical applications.

Ensemble Empirical Mode Decomposition Parameters Optimization for Spectral Distance Measurement in Hyperspectral Remote Sensing Data

This study proposed a new approach to measure the similarity between spectra to discriminate materials and evaluate the performance of parameter-selection procedures. Many pure pixel vector-based similarity measurements have been developed in the past to calculate the distance between two pixel vectors. However, those methods may not be effective since they do not take full advantage of the spectral correlation. In this study, we adopt Ensemble Empirical Mode Decomposition (EEMD) to decompose the spectrum into serial components and employ these components to improve the performance of spectral discrimination. Performance evaluation was conducted with several commonly used measurements, and the spectral samples used for experimentation were provided by the spectral library of United States Geological Survey (USGS). The experimental results have demonstrated that EEMD can extract the spectral features more effectively than common spectral similarity measurements, and it better characterizes spectral properties. Our experimental results also suggest general rules for selecting noise standard deviation, the number of iterations for EEMD and the collection of Intrinsic Mode Functions (IMFs) for classification. Finally, since EEMD is a time-consuming algorithm, we also implement parallel processing with a Graphics Processing Unit (GPU) to increase the processing speed.

High-throughput GPU-based LDPC decoding

Low-density parity-check (LDPC) code is a linear block code known to approach the Shannon limit via the iterative sum-product algorithm. LDPC codes have been adopted in most current communication systems such as DVB-S2, WiMAX, WI-FI and 10GBASE-T. LDPC for the needs of reliable and flexible communication links for a wide variety of communication standards and configurations have inspired the demand for high-performance and flexibility computing. Accordingly, finding a fast and reconfigurable developing platform for designing the high-throughput LDPC decoder has become important especially for rapidly changing communication standards and configurations. In this paper, a new graphic-processing-unit (GPU) LDPC decoding platform with the asynchronous data transfer is proposed to realize this practical implementation. Experimental results showed that the proposed GPU-based decoder achieved 271x speedup compared to its CPU-based counterpart. It can serve as a high-throughput LDPC decoder.

Design of GPU-based platform for LDPC decoder

The needs for reliable and flexible downlink communications incorporated with high volume of satellite images in the ground station have inspired the demands for high performance and flexibility computing in the field of Earth remote sensing. Low-density parity-check (LDPC) codes have had a strong impact on achieving reliable communication links. Finding a fast and reconfigurable developing platform for designing high throughput LDPC decoders has become important. In this paper, a graphic processing unit (GPU) platform is proposed to realize this practical implementation. Experimental results show that the proposed GPU-based platform is compatible to serve as a high-throughput LDPC decoder.

Incenter-based nearest feature space method for hyperspectral image classification using GPU

In this paper a novel technique based on nearest feature space (NFS), known as incenter-based nearest feature space (INFS), is proposed for supervised hyperspectral image classification. Due to the class separability and neighborhood structure, the traditional NFS can perform well for classification of remote sensing images. However, in some instances, the overlapping training samples might cause classification errors in spite of the high classification accuracy of NFS for normal cases. In response, the INFS is proposed to overcome this problem in this paper. INFS method makes use of the incircle of a triangle which is tangent to its three sides and form a INFS. In addition, an incenter can be calculated by three training samples of the same class efficiently. Furthermore, in order to speed up the computation performance, this paper proposes a parallel computing version of INFS, namely parallel INFS (PINFS). It uses a modern graphics processing unit (GPU) architecture with NVIDIAs compute unified device architecture (CUDA) technology to improve the computational speed of INFS. Experimental results demonstrate the proposed INFS approach is suitable for land cover classification in earth remote sensing. It can achieve the better performance than NFS classifier when the class sample distribution overlaps. Through the computation of GPU by CUDA, we can also gain better speedup.

Multisource data fusion for image classification using fisher criterion based nearest feature space approach

In this paper, a novel technique, known as nearest feature space (NFS) approach, is proposed for supervised classification of multisource images for the purpose of landslide hazard assessment. It is developed for land cover classification based on the fusion of remotely sensed images of the same scene collected from multiple sources. This approach presents a framework for data fusion of multisource remotely sensed images, which consists of two approaches, referred to as band generation process (BGP) and Fisher criterion based NFS classifier. Compared to the original NFS, we propose an improve NFS classifier which uses the Fisher criterion of between-class and within-class discrimination to enhance the original one. In the training phase, the labeled samples are discriminated by the Fisher criterion, which can be treated as a pre-processing of NFS. Finally, the classification results can be obtained by NFS algorithm. In order for the proposed NFS to be effective for multispectral images, a multiple adaptation BGP is introduced to create a new set of additional bands especially accommodated to landslide classes. Experimental results demonstrate the proposed BGP/NFS approach is suitable for land cover classification in earth remote sensing and improves the precision of image classification.

Particle swarm optimization/impurity function class overlapping scheme based on multiple attribute decision making model for hyperspectral band selection

This paper presents a promising band selection algorithm, known as particle swarm optimization/impurity function class overlapping (PSO/IFCO) method, which adopts a novel multiple attribute decision making (MADM) model approach to the hyperspectral remote sensing images. The proposed MADM-based PSO/IFCO method can be divided into two steps: 1) PSO algorithm and 2) the IFCO scheme. With PSO band selection algorithm, the highly correlated bands of hyperspectral imagery can first be grouped into band modules, known as greedy modular eigenspace (GME), to coarsely reduce high-dimensional datasets in the first step. The more highly correlated small modules are further constructed with the statistics of impurity weights calculated by IFCO scheme in the second step. These statistics results of impurity weights are used to finely select the most important feature bands from the hyperspectral imagery. The proposed MADM-based PSO/IFCO makes use of the correlation coefficients matrix to cluster the highly correlated bands together and obtain GME in the first step. More specifically, we use the analytic hierarchy process (AHP) model, which is the most suitable implementation of MCDM for proposed method, to examine hierarchically the relations among different GME modules with the impurity weighted by IFCO in the second step. Finally, by accommodating the statistics of impurity weights, the proposed MADM-based PSO/IFCO method can effectively select the most representative features for hyperspectral band selection and reduction. The effectiveness of the proposed method is evaluated by MASTER and AVIRIS hyperspectral images. The experimental results demonstrate that the proposed method can not only enhance the high dimension reduction rate, but also offer a satisfactory classification performance.

Simulation of tsunami impact on Taiwan coastal area

The tsunami disaster triggered by a huge 9.0 magnitude earthquake strikes Japan on March 11th, 2011. It motivates us to get involved in a research work in tsunami topics of Taiwan and to simulate an impact of the tsunami on the coast of Taiwan. Tsunami propagation is often modeled by the shallow water equations. These equations are derived from conservation of mass and momentum equations. By adding friction slope to the conservation of momentum equations, it enables the system to simulate the propagation over the coastal area. This system is able to estimate inundation zone caused by the tsunami. By applying Neumann boundary condition and Hansen numerical filter, it brings more interesting complexities into this simulation system. The parallelizable two-step finite-difference MacCormack scheme is employed to simulate the tsunami. In this paper, the parallel implementation of the MacCormack scheme is proposed for the shallow water equations by using the modern graphics processing unit (GPU) which accommodates NVIDIA compute unified device architecture (CUDA) technology to speed up the computation of the assessment of tsunami inundation. Experimental results demonstrate that the proposed approach is an effective simulation method for evaluating the impact on land inundation in Taiwan coastal area. With this method, we can in real-time manner monitor the progress of the land inundation. The information is valuable for constructing and refining the further altering systems in a dynamic manner for minimizing impacts caused by tsunamis.

Particle Swarm Optimization-Based Impurity Function Band Prioritization Using Weighted Majority Voting for Feature Extraction of High Dimensional Data Sets

In recent years, with the improvement of sensor technologies, the volumes of remote sensing data are increased dramatically. The feature extraction of hyper spectral remotely sensed images can reduce such high-dimensional datasets, solve the big data problem, avoid the Hughes phenomena and improve the classification performance. Accordingly, this paper presents a framework for feature extraction of hyper spectral imagery, which consists of two approaches, referred to as parallel particle swarm optimization (PPSO) band selection and weighted voting impurity function (WVIF) band prioritization. The highly correlated bands of hyper spectral imagery can be grouped first into the some modules by PPSO band selection algorithm to coarsely reduce high-dimensional datasets, and these highly correlated band modules can then be analyzed with the statistical relationship between bands and classes by WVIF band prioritization method to finely select the most important feature bands form the datasets. Furthermore, a PPSO algorithm based on modern graphics processing unit (GPU) architecture using NVIDIA compute unified device architecture (CUDA) technology is using in this paper. It can improve the computational speed of PPSO band selection to group the high correlated band modules. The effectiveness of the proposed PPSO/WVIF framework is evaluated by MASTER and AVIRIS hyper spectral images. The experimental results demonstrated that the proposed method not only could reduction the dimension of datasets, but also can offer a satisfactory classification performance and computational speed.

GPU-based Ensemble Empirical Mode Decomposition approach to spectrum discrimination

Because of the improvement of optical remote sensing instrument, hyperspectral images now collect information of the ground with hundreds of wavelengths. This spectral information can be used to identify different materials, since each material should have its unique absorption spectrum. Traditionally the spectra was discriminated by measuring either the spectral distance or angle between two spectra directly. However, the remote spectra usually contain noises and interferences from other sources, and even the same material has various spectra. In this case, the conventional measurements may not have the capability enough to tolerate the distortions and to identify each material. In this study, the Ensemble Empirical Mode Decomposition (EEMD) is adopted to measure the similarity between the spectra and discriminate materials. EEMD not only can decompose the spectrum into several components as original Empirical Mode Decomposition (EMD), but also compensating the noises and interferences in the signal as an improved version. Although EEMD is a time-consuming process, its structure is suitable for parallel computing. In this paper we propose a graphic-processing-unit (GPU)-based EEMD on a cluster. Experimental results showed that it can extract the spectral features more effectively than common spectral similarity measures, and it has better ability in characterizing spectral properties. It also demonstrated that the proposed GPU-based high-throughput EEMD achieved a significant 60.62x speedup compared to its CPU-based single-threaded counterpart written in C language.