Heavy metals that are present in soil are poisonous to both plants and animals. Measuring the heavy metal concentrations in wetland soil are of great significance for the assessment of wetland ecosystem health. This study was conducted in the Taihu Lake wetland region of China, and is aimed at comparing the partial least squares regression (PLSR) as well as support vector machine regression (SVMR) methods for estimating the zinc (Zn), arsenic (As) and copper (Cu) concentrations present in wetland soil utilizing hyperspectral technology. In total, there were 100 homogeneous wetland soil samples collected, and their Zn, As and Cu concentration models were developed based on laboratory-based hyperspectral data (350-2500 nm). According to independent validation, the SVMR method achieved better accuracies, which had determination coefficients of 0.61, 0.66 and 0.72 for Zn, As and Cu, respectively. It was concluded that the SVMR method combined with laboratory-based hyperspectral data has the cumulative potential to estimate heavy metal concentrations within homogeneous wetland soil.

Support Vector Machines (SVMs) are powerful classification tools. However, the model training is very time-consuming when meeting large scale data sets. Some efforts have been devoted to screening out non-support vectors (non-SVs) to accelerate the training. But their processes rely on prior knowledge of other classifiers with different parameters to screen out non-SVs. In this paper, we propose Directional Indicator Support Vector Machines (DISVMs) to efficiently identify non-SVs. DISVMs employs a directional indicator, which points to the approximately orthogonal direction of the separating hyperplane, to qualitatively define the location of different samples and thus identify non-SVs. Furthermore, DISVMs leverages a two-stage algorithm: the first stage is to compute the directional indicator. The second stage is to identify non-SVs using the indicator. To avoid misjudgement, we propose CnSV method for non-SVs based on the majority rule. DISVMs screens out non-SVs with light computation and little accuracy loss. Experiments show that our approach significantly reduces the total computation cost.

In this paper, we develop a novel genome compression framework based on distributed source coding (DSC)[3], which is specially tailored to the need of miniaturized devices. At the encoder side, subsequences with adaptive code length can be compressed flexibly through either low complexity DSC based syndrome coding or hash coding with the decision determined by the existence of variations between source and reference known from the decoder feedback. Moreover, to tackle the variations between source and reference at the decoder, we carefully designed a factor graph based low-density parity-check (LDPC) decoder, which automatically detects insertion, deletion and substitution.

Estimating accurately channel noise has significant impact on the performance of channel coding. In this paper, we present a low complexity online estimator at the decoder side for low-density parity check (LDPC) codes over additive white Gaussian noise (AWGN) channels with a time-varying noise. The proposed algorithm is obtained by modeling the channel statistic as a Bayesian inference problem on a factor graph. Since BP algorithm cannot adapt efficiently to the statistical change of SNR in an AWGN channel, we apply the Laplace propagation (LP) algorithm on the proposed algorithm. Through simulations, we show that the proposed algorithm can simultaneously decode LDPC codes and estimate the time-varying SNR at the bit-level, which enhance the BP decoding performance. Moreover, the proposed LP estimator shows a very low computational complexity.

Distributed video coding (DVC) is rapidly gaining popularity as a low cost, robust video coding solution, that reduces video encoding complexity. DVC is built on distributed source coding (DSC) principles where correlation between sources to be compressed is exploited at the decoder side. In the case of DVC, a current frame available only at the encoder is estimated at the decoder with side information generated from other frames available at the decoder. One of the main challenges in DVC design is that correlation among the source and side information needs to be estimated online and as accurately as possible. Since correlation dynamically changes with the scene, in order to exploit the robustness of DSC code designs, we integrate particle filtering (PF) with standard belief propagation (BP) decoding for inference on one joint factor graph to estimate correlation among source and side information. Correlation estimation is performed online as it is carried out jointly with decoding of the graph-based DSC code. Moreover, we demonstrate our joint bit-plane decoding with adaptive correlation estimation schemes within state-of-the-art DVC systems, which are transform-domain based with a feedback channel for rate adaptation. Experimental results show that our proposed system gives a significant performance improvement compared to the benchmark state-of-the-art DISCOVER codec (including correlation estimation) and the case without dynamic PF tracking, due to improved knowledge of timely correlation statistics via the combination of joint bit-plane decoding and particle-based BP (PBP) tracking.

We propose an adaptive distributed compression solution using particle filtering that tracks correlation, as well as performing disparity estimation, at the decoder side. The proposed algorithm is tested on the stereo solar images captured by the twin satellites system of NASA's Solar TErrestrial RElations Observatory (STEREO) project. Our experimental results show improved compression performance w.r.t. to a benchmark compression scheme, accurate correlation estimation by our proposed particle-based belief propagation algorithm, and significant peak signal-to-noise ratio improvement over traditional separate bit-plane decoding without dynamic correlation and disparity estimation.

In this paper, we propose a system using video cameras to perform vehicle identification. We tackle this problem by reconstructing an input by using multiple linear regression models and compressed sensing, which provide new ways to deal with three crucial issues in vehicle identification, namely, feature extraction, online vehicle identification database buildup , and robustness to occlusions and misalignment. The results show the capability of the proposed approach.

Belief propagation (BP) is a powerful algorithm to decode low- density parity check (LDPC) codes over additive white Gaussian noise (AWGN) channels. However, the traditional BP algorithm cannot adapt efficiently to the statistical change of SNR in an AWGN channel. This paper proposes an adaptive scheme that incorporates expectation propagation (EP) into the BP based LDPC decoding process. The proposed scheme is able to perform online estimation of both stationary and time-varying SNR at the bit-level, and enhance the BP decoding performance simultaneously. Moreover, the proposed EP estimator shows a very fast convergence speed, and the additional computational overhead of the proposed decoder is less than 10% of the standard BP decoder.

Acquiring and processing astronomical images is becoming increasingly important for accurate space weather prediction and expanding our understanding about the Sun and the Universe. These images are often rich in content, large in size and dynamic range. Efficient, low-complexity compression solutions are essential to reduce onboard storage, processing, and communication resources. Distributed compression is a promising technique for onboard coding of solar images by exploiting correlation between successively acquired images. In this paper we propose an adaptive distributed compression solution using particle filtering that tracks correlation, as well as performing disparity estimation, at the decoder side. The proposed algorithm is tested on the stereo solar images captured by the twin satellites system of NASA's STEREO project. Our experimental results show the significant PSNR improvement over traditional separate bit-plane decoding without dynamic correlation and disparity estimation.

A major difficulty that plagues the practical use of Slepian-Wolf (SW) coding (and distributed source coding in general) is that the precise correlation among sources needs to be known a priori. To resolve this problem, we propose an adaptive asymmetric SW decoding scheme using particle based belief propagation (PBP). We explain the adaptive scheme for asymmetric setup in detail and then further extend it to the non-asymmetric setup based on the code partitioning approach. Moreover, we introduce a Metropolis-Hastings (MH) algorithm in the resampling step, which efficiently decreases the number of simulation iterations. We show through experiments that the proposed algorithm can simultaneously reconstruct the compressed sources and estimate the joint correlation among sources. Further, comparing to the conventional SW decoder based on standard belief propagation, the proposed approach can achieve higher compression under varying correlation statistics.

Belief propagation (BP) is a powerful algorithm to decode low-density parity check (LDPC) codes over additive white Gaussian noise (AWGN) channels. However, the traditional BP algorithm cannot adapt efficiently to the statistical change of SNR in an AWGN channel. This paper proposes an adaptive scheme that incorporates a particle filtering (PF) algorithm into the BP based LDPC decoding process. The proposed scheme is capable to perform online estimation of time-varying SNR at the bit-level and enhance the BP decoding performance simultaneously.

This paper addresses the problem of distributed source coding (DSC) of binary sources with unknown varying correlation statistics over erasure channels. We propose an adaptive asymmetric Slepian-Wolf (SW) decoding scheme using particle-based belief propagation (BP) based on Raptor codes. We show through the experiments that the proposed algorithm can simultaneously reconstruct the compressed sources and estimate the correlation between source and side information. Moreover, compared to the conventional Raptor decoder, the proposed approach can achieve a higher compression ratio and provide stronger erasure protection under unknown varying correlation statistics. The ability to estimate the statistical correlation in the code structure makes our approach very useful for real applications.

In this paper we propose an adaptive Wyner-Ziv (WZ) coding scheme for non-binary correlated sources with side information at the decoder. At the encoder, a low density parity check (LDPC) code is employed to implement Slepian-Wolf (SW) coding for each bit-plane independently. The joint "source-channel" decoder, which combines SW decoding and dequantizing in a single step, preserves the symbol-domain correlation and decreases the distortion. Moreover, the incorporation of particle-based belief propagation (BP) in the decoder can extend the scheme to perform an online estimation of the correlation and enhance the BP decoding performance simultaneously. Our proposed framework is universal and can be applied to any parametric correlation model.

A major difficulty that plagues the practical use of Slepian-Wolf coding (and distributed source coding in general) is that the precise correlation among sources need to be known a priori. To resolve this problem, we have proposed an adaptive asymmetric Slepian-Wolf decoding scheme using particle filtering based belief propagation in our recent work. In this paper, we extend the adaptive scheme to the non-asymmetric setup based on the code partitioning approach. We show through experiments that the proposed algorithm can simultaneously reconstruct the compressed sources and estimate the joint correlation among sources. Further, comparing to the conventional Slepian-Wolf decoder based on standard belief propagation, the proposed approach can achieve higher compression under varying correlation statistics.