Residual Histogram Research Articles

RWRM: Residual Wasserstein regularization model for image restoration

<p style='text-indent:20px;'>Existing image restoration methods mostly make full use of various image prior information. However, they rarely exploit the potential of residual histograms, especially their role as ensemble regularization constraint. In this paper, we propose a residual Wasserstein regularization model (RWRM), in which a residual histogram constraint is subtly embedded into a type of variational minimization problems. Specifically, utilizing the Wasserstein distance from the optimal transport theory, this scheme is achieved by enforcing the observed image residual histogram as close as possible to the reference residual histogram. Furthermore, the RWRM unifies the residual Wasserstein regularization and image prior regularization to improve image restoration performance. The robustness of parameter selection in the RWRM makes the proposed algorithms easier to implement. Finally, extensive experiments have confirmed that our RWRM applied to Gaussian denoising and non-blind deconvolution is effective.</p>

Outlier Detection Based on Residual Histogram Preference for Geometric Multi-Model Fitting.

Geometric model fitting is a fundamental issue in computer vision, and the fitting accuracy is affected by outliers. In order to eliminate the impact of the outliers, the inlier threshold or scale estimator is usually adopted. However, a single inlier threshold cannot satisfy multiple models in the data, and scale estimators with a certain noise distribution model work poorly in geometric model fitting. It can be observed that the residuals of outliers are big for all true models in the data, which makes the consensus of the outliers. Based on this observation, we propose a preference analysis method based on residual histograms to study the outlier consensus for outlier detection in this paper. We have found that the outlier consensus makes the outliers gather away from the inliers on the designed residual histogram preference space, which is quite convenient to separate outliers from inliers through linkage clustering. After the outliers are detected and removed, a linkage clustering with permutation preference is introduced to segment the inliers. In addition, in order to make the linkage clustering process stable and robust, an alternative sampling and clustering framework is proposed in both the outlier detection and inlier segmentation processes. The experimental results also show that the outlier detection scheme based on residual histogram preference can detect most of the outliers in the data sets, and the fitting results are better than most of the state-of-the-art methods in geometric multi-model fitting.

Fault Plane Estimation Through Hypocentres Distribution of the July-August 2018 Lombok Earthquakes Relocated by using Double Difference Method

Indonesia is actually located in collisions between three large plates of Eurasia, Indo-Australia, and Pacific. It causes earthquakes to occur frequently in several regions, one of which occurs sequentially the 5 big shocks in Lombok in period of July-August 2018. There is a Flores thrust fault in the North of the Lombok Island region. The objective of study is determining whether the earthquakes sequence is related to the fault. The study is done through the analysis of relocated 321 of 489 hypocentres of the earthquakes acquired from 13 BMKG stations in July-October 2018. The hypocentres are relocated by using the double-difference method. The events are focused only with magnitude > 3.5 M. The relocation result is validated by the RMS residual histograms with the average value close to 0. The results show that the seismic activity mostly spread in the northern part of the Island of Lombok. The distribution of the epicenter points tends to form a pattern oriented from West to East in the northern region of the island which is thought to be the zone of the faults. The events most likely have not generated and not laid along the Flores Fault.

Multiple Batches of Motion History Images (MB-MHIs) for Multi-view Human Action Recognition

The recognition of human actions recorded in a multi-camera environment faces the challenging issue of viewpoint variation. Multi-view methods employ videos from different views to generate a compact view-invariant representation of human actions. This paper proposes a novel multi-view human action recognition approach that uses multiple low-dimensional temporal templates and a reconstruction-based encoding scheme. The proposed approach is based upon the extraction of multiple 2D motion history images (MHIs) of human action videos over non-overlapping temporal windows, constructing multiple batches of motion history images (MB-MHIs). Then, two kinds of descriptions are computed for these MHIs batches based on (1) a deep residual network (ResNet) and (2) histogram of oriented gradients (HOG) to effectively quantify a change in gradient. ResNet descriptions are average pooled at each batch. HOG descriptions are processed independently at each batch to learn a class-based dictionary using a K-spectral value decomposition algorithm. Later, the sparse codes of feature descriptions are obtained using an orthogonal matching pursuit approach. These sparse codes are average pooled to extract encoded feature vectors. Then, encoded feature vectors at each batch are fused to form a final view-invariant feature representation. Finally, a linear support vector machine classifier is trained for action recognition. Experimental results are given on three versions of a multi-view dataset: MuHAVi-8, MuHAVi-14, and MuHAVi-uncut. The proposed approach shows promising results when tested for a novel camera. Results on deep features indicate that action representation by MB-MHIs is more view-invariant than single MHIs.

Analysis of Residuals for the Elimination of total Suspended Solids Simulation of wastewater through Rotating Biological Contactor

Increased attention towards substitute water resources has become unavoidable, as the world’s freshwater supply becomes gradually scarcer. Reuse of Greywater is a hopeful alternative water source for non-potable uses, which could be exploited on a continuous basis and treated. Getting average removal% of Total Suspended Solids from greywater through Rotating Biological Contactor following experiment was conducted to evaluate the significance Hydraulic Retention Time with numbers of discs. Consequences reveal that linear as well as quadratic estimate of HRT and number of discs have are highly significant effect as their corresponding p-values are even less than 0.01.By using coefficients of the table the regression equation is Removal = Removal% = -26.74 + 20.14 Time + 1.253 Disc, where the sample standard deviation is 4.82. Lack of fit of the equation is insignificant i.e. 0.155, which implies that the regression equation is fit for prediction. The probability plot of the residuals is roughly straight which demonstrate that errors distributions are around normal. Furthermore, Residual plot shows the linearity assumption appear to be met with constant standard deviations. Histogram of Residuals make obvious normality assumptions as the plot resembles an example of a sample from a normal distribution centered at zero and normally and independently distributed NID (0, σ2) assumptions on errors are accomplished as standardized residuals are approximately normal with mean zero and unit variance.

Towards feature representation for steganalysis of spatial steganography

Feature separability analysis supports the feature selection and reduction and also guides the feature construction. This paper addresses the feature representation for steganalysis of spatial steganography. The paper analyzes the effects of spatial steganography on image residual histogram, and gives the feature separability of histogram features represented in both spatial and frequential domains, which explains the effectiveness of the typical spatial features, such as SRM and TLBP features. Based on the feature separability analysis, TLBP feature is improved by using a new texture pattern mapping to replace the ‘riu2’ mapping in the feature construction. Besides, features in the frequency domain are constructed by applying DFT to the submodels of SRM. Experimental results show that both the two schemes improved the steganalysis performances. Furthermore, features in spatial and frequency domains are merged, which obtains better results than the corresponding single type features for steganalysis of S-UNIWARD, HILL, and MiPOD. For example, using HILL for information embedding with payload 0.4 bpp on BOSSbase dataset, the detection accuracy of the best merged feature is 3.64% and 1.13% higher than the corresponding single type features.

PSI-18 Rumen fluid metabolites associated with feed efficiency in Angus steers

Abstract The functional capacity of the rumen is central to ruminant feed efficiency, and therefore,differences in ruminal metabolism may contribute to cattle feed efficiency variations. The objective of this study was to determine differences in rumen metabolites associated withvariations in feed efficiency. Fifty steers were utilized and maintained on a backgrounding diet (11.57% CP; 76.93% TDN DM basis; 28 mg monensin/kg DM) for 70 days following a two-week diet adaptation. Feed intake was monitored using the GrowSafe system. Following the 70-day trial, steers were ranked by residual feed intake (RFI) and divided into low- (n = 14) and high-RFI (n = 15) based on RFI ±0.5 SD around the mean. On day 70, rumen fluid was collected viaorogastric tubing and filtered through a 0.22 μM syringe filter. Untargeted metabolomics wasconducted utilizing the Dionex UltiMate 3000 UPLC system and electrospray ionization used tointroduce samples into an Exactive Plus Orbitrap MS. Eighty-eight known metabolites wereidentified using MAVEN. Metabolites were median-centered, log-transformed, and pareto-scaled using Metaboanalyst 4.0. Normality was assessed using the SAS 9.4 PROC UNIVARIATE procedure. Normal distribution was considered based on a Shapiro-Wilk score of ≥ 0.85 andvisual analysis of histogram and plots of residuals. Normally distributed metabolites wereanalyzed using one-way ANOVA in SAS with Tukey’s HSD post-hoc test, whereas non-normally distributed variables were analyzed using Wilcoxon Rank Sum and Kruskal Wallis H test. Significance was set at P ≤ 0.05. Eight metabolites differed between high- and low-RFI steers. Twelve metabolites identified as having > two-fold change between low- and high-RFI steers, including 3,4-Dihydroxyphenylacetate and sulfolactate. Orthogonal PLSDA revealed overlap ofrumen fluid metabolites from high- and low-RFI steers. Understanding rumen metabolites in high- and low-RFI steers will provide researchers with information to identify more efficient cattle.

Implementation of Block-Based Hierarchical Prediction for Developing an Error-Propagation-Free Reversible Data Hiding Scheme

This paper proposes a reversible data hiding technique based on the residual histogram shifting technique. To improve the hiding capacity, this study proposes a multiple-round hierarchical prediction mechanism that generates the prediction errors of each image block. The prediction errors of each block are collected to produce the residual histogram and the secret data are then embedded into the residual histogram to obtain the embedded image. Experimental results demonstrate that the proposed technique not only provides good hiding capacity, but also maintains good image quality of the embedded image. In addition, this technique can be easily extended for image integrity protection as it is capable of resisting error propagation.

Statistical improvement in detection level of gravitational microlensing events from their light curves

In astronomy, the brightness of a source is typically expressed in terms of magnitude. Conventionally, the magnitude is defined by the logarithm of received flux. This relationship is known as the Pogson formula. For received flux with a small signal to noise ratio (S/N), however, the formula gives a large magnitude error. We investigate whether the use of Inverse Hyperbolic Sine function (hereafter referred to as the Asinh magnitude) in the modified formulae could allow for an alternative calculation of magnitudes for small S/N flux, and whether the new approach is better for representing the brightness of that region. We study the possibility of increasing the detection level of gravitational microlensing using 40 selected microlensing light curves from the 2013 and 2014 seasons and by using the Asinh magnitude. Photometric data of the selected events are obtained from the Optical Gravitational Lensing Experiment (OGLE). We found that utilization of the Asinh magnitude makes the events brighter compared to using the logarithmic magnitude, with an average of about 3.42 × 10−2 magnitude and an average in the difference of error between the logarithmic and the Asinh magnitude of about 2.21 × 10−2 magnitude. The microlensing events OB140847 and OB140885 are found to have the largest difference values among the selected events. Using a Gaussian fit to find the peak for OB140847 and OB140885, we conclude statistically that the Asinh magnitude gives better mean squared values of the regression and narrower residual histograms than the Pogson magnitude. Based on these results, we also attempt to propose a limit in magnitude value for which use of the Asinh magnitude is optimal with small S/N data.

Comparison between Cascade Forward and Multi-Layer Perceptron Neural Networks for NARX Functional Electrical Stimulation (FES)-Based Muscle Model

This paper presents the development and comparison of muscle models based on Functional Electrical Stimulation (FES) stimulation parameters using the Nonlinear Auto-Regressive model with Exogenous Inputs (NARX) using Multi-Layer Perceptron and Cascade Forward Neural Network (CFNN). FES stimulations with varying frequency, pulse width and pulse duration were used to estimate the muscle torque. About 722 data points were used to create muscle model. One Step Ahead (OSA) prediction, correlation tests and residual histogram analysis were performed to validate the model. The optimal Multi-Layer Perceptron (MLP) results were obtained from input lag space of 1, output lag space of 43 and hidden units 30. The MLP selected a total of three terms were selected to construct the final model, which producing a final Mean Square Error (MSE) of 1.1299. The optimal CFNN results were obtained from input lag space of 1, output lag space of 5 and hidden units 20 with similar terms selected. The final MSE produced was 1.0320. The proposed approach managed to approximate the behavior of the system well with unbiased residuals, which CFNN showing 8.66% MSE improvement over MLP with 33.33% less hidden units.

Binary Particle Swarm Optimization Structure Selection of Nonlinear Autoregressive Moving Average with Exogenous Inputs (NARMAX) Model of a Flexible Robot Arm

The Nonlinear Auto-Regressive Moving Average with Exogenous Inputs (NARMAX) model is a powerful, efficient and unified representation of a variety of nonlinear models. The model’s construction involves structure selection and parameter estimation, which can be simultaneously performed using the established Orthogonal Least Squares (OLS) algorithm. However, several criticisms have been directed towards OLS for its tendency to select excessive or sub-optimal terms leading to nonparsimonious models. This paper proposes the application of the Binary Particle Swarm Optimization (BPSO) algorithm for structure selection of NARMAX models. The selection process searches for the optimal structure using binary bits to accept or reject the terms to form the reduced regressor matrix. Construction of the model is done by first estimating the NARX model, then continues with the estimation of the MA model based on the residuals produced by NARX. One Step Ahead (OSA) prediction, Mean Squared Error (MSE) and residual histogram analysis were performed to validate the model. The proposed optimization algorithm was tested on the Flexible Robot Arm (FRA) dataset. Results show the success of BPSO structure selection for NARMAX when applied to the FRA dataset. The final NARMAX model combines the NARX and MA models to produce a model with improved predictive ability compared to the NARX model.

HEVC early termination methods for optimal CU decision utilizing encoding residual information

High-efficiency video coding (HEVC) utilizes a quadtree-structured coding unit (CU) for more possible sizes of basic blocks for later prediction. The exhaustive search for the optimal CU depth requires high complexity, which causes difficulties for real-time streaming. In the proposed method, we make use of the residual statistics of prediction units (PUs) in the current encoded CU to make a decision on CU early termination. The residual histogram is discussed, and the optimal early termination (ET) zone is designed; if the PU residual statistics fall in the ET zone, the early termination is triggered. The optimal parameters for the ET zone are solved and analyzed in the training stage, and can be estimated with table lookup and simple computations in the testing stage. Another early termination method using the neighboring SKIP information is also proposed. We use SKIP information from more meaningful CU neighbors defined and used in HEVC. We combine the proposed residual-based and SKIP-based algorithms with a state-of-the-art method. The experimental results show that compared to two state-of-the-art methods in both low delay (LP) and random access (RA) configurations, our preferred proposed combination can achieve the best BDBR results (0.737 % in LP and 0.471 % in RA) with a good corresponding TS performances (49.87 % in LP and 54.96 % in RA), making HEVC more suitable for real-time applications.

High capacity reversible steganography in encrypted images based on feature mining in plaintext domain

A reversible steganographic scheme in encrypted images with high capacity based on feature mining in plaintext domain is proposed in this paper. Two techniques are used: multi-granularity encryption and residual histogram shifting. Firstly, a cover image is encrypted both on fine-grained level and coarse-grained level with content-owner key. Then, the additional data can be embedded into the encrypted image by exploring both the similarity of neighbouring pixels in local level and residual histogram in global level with data-hiding key. For legal receivers, image decryption and data extraction can be free to choose. If content-owner key and data-hiding key are both adopted at the same time, the cover image can be restored error-free along with data extraction. Experimental results show that the proposed scheme significantly outperforms the previous approaches both in terms of embedding quality and embedding capacity.

A novel hierarchical Bag-of-Words model for compact action representation

Bag-of-Words (BoW) histogram of local space-time features is very popular for action representation due to its high compactness and robustness. However, its discriminant ability is limited since it only depends on the occurrence statistics of local features. Alternative models such as Vector of Locally Aggregated Descriptors (VLAD) and Fisher Vectors (FV) include more information by aggregating high-dimensional residual vectors, but they suffer from the problem of high dimensionality for final representation. To solve this problem, we novelly propose to compress residual vectors into low-dimensional residual histograms by the simple but efficient BoW quantization. To compensate the information loss of this quantization, we iteratively collect higher-order residual vectors to produce high-order residual histograms. Concatenating these histograms yields a hierarchical BoW (HBoW) model which is not only compact but also informative. In experiments, the performances of HBoW are evaluated on four benchmark datasets: HMDB51, Olympic Sports, UCF Youtube and Hollywood2. Experiment results show that HBoW yields much more compact action representation than VLAD and FV, without sacrificing recognition accuracy. Comparisons with state-of-the-art works confirm its superiority further.

A histogram approach to the quality of fit in sedimentation velocity analyses

The quality of fit of sedimentation velocity data is critical to judge the veracity of the sedimentation model and accuracy of the derived macromolecular parameters. Absolute statistical measures are usually complicated by the presence of characteristic systematic errors and run-to-run variation in the stochastic noise of data acquisition. We present a new graphical approach to visualize systematic deviations between data and model in the form of a histogram of residuals. In comparison with the ideally expected Gaussian distribution, it can provide a robust measure of fit quality and be used to flag poor models.

PREDICTING FACTORS THAT INFLUENCE FISH GUILD COMPOSITION IN FOUR COASTAL RIVERS (SOUTHEAST IVORY COAST) USING ARTIFICIAL NEURAL NETWORKS

The present study is focused on small coastal rivers in southeast Ivory Coast, aimed to predict species richness of fish guilds and to test contribution of environmental variables for explaining guild structure with Self-Organizing Map (SOM) and Backpropagation (BP) algorithms. The former method was applied to pattern the samples based on the richness of six major fish guilds observed (benthivores, invertivores, detritivores, piscivores, herbivores and omnivores). Four clusters were identified: cluster I was characterised by benthivores, cluster II was distinguished by invertivores, detritivores, piscivores and omnivores, cluster III had high richness of benthivores, invertivores and herbivores, and cluster IV had high numbers of omnivore, detritivore and piscivore species. The BP showed high predictability (0.89 for benthivores, 0.85 for omnivores and Odonata, 0.84 for herbivores). There was high correlation between observed and estimated values for piscivores (0.77) and detritivores (0.72); the poorest fit was for invertivores (0.63). The frequency histogram of residuals showed that most residuals lie around zero for all guilds. The most contributing variables in predicting the six fish trophic guilds were water temperature, conductivity, total dissolved solids, dissolved oxygen, depth, width, canopy and distance from source. This underlines the crucial influence of both instream characteristics and riparian environment.

High capacity reversible data hiding scheme based on residual histogram shifting for block truncation coding

A reversible data hiding scheme based on residual histogram shifting for the compressed images of block truncation coding (BTC) is proposed. This scheme employs an iterative approach to embed the secret data into the compressed codes of BTC. In each round, the quantization levels are processed by the block-based prediction technique to generate the residual values. Then, the residual values are used to embed the secret data. Multiple rounds of the data embedding process can be executed to increase the hiding capacity of the proposed scheme. Experimental results reveal that the proposed scheme provides good image qualities of the embedded images. In addition, the hiding capacity of the proposed scheme is greater than that of the comparative scheme. Furthermore, the embedded compressed codes still follow the standard format of BTC after the proposed data embedding procedure is executed.

Lobe-specific Functions of Ca2+·Calmodulin in αCa2+·Calmodulin-dependent Protein Kinase II Activation

N-Methyl-d-aspartic acid receptor-dependent long term potentiation (LTP), a model of memory formation, requires Ca2+·calmodulin-dependent protein kinase II (αCaMKII) activity and Thr286 autophosphorylation via both global and local Ca2+ signaling, but the mechanisms of signal transduction are not understood. We tested the hypothesis that the Ca2+-binding activator protein calmodulin (CaM) is the primary decoder of Ca2+ signals, thereby determining the output, e.g. LTP. Thus, we investigated the function of CaM mutants, deficient in Ca2+ binding at sites 1 and 2 of the N-terminal lobe or sites 3 and 4 of the C-terminal CaM lobe, in the activation of αCaMKII. Occupancy of CaM Ca2+ binding sites 1, 3, and 4 is necessary and sufficient for full activation. Moreover, the N- and C-terminal CaM lobes have distinct functions. Ca2+ binding to N lobe Ca2+ binding site 1 increases the turnover rate of the enzyme 5-fold, whereas the C lobe plays a dual role; it is required for full activity, but in addition, via Ca2+ binding site 3, it stabilizes ATP binding to αCaMKII 4-fold. Thr286 autophosphorylation is also dependent on Ca2+ binding sites on both the N and the C lobes of CaM. As the CaM C lobe sites are populated by low amplitude/low frequency (global) Ca2+ signals, but occupancy of N lobe site 1 and thus activation of αCaMKII requires high amplitude/high frequency (local) Ca2+ signals, lobe-specific sensing of Ca2+-signaling patterns by CaM is proposed to explain the requirement for both global and local Ca2+ signaling in the induction of LTP via αCaMKII.

Reversible image hiding scheme using predictive coding and histogram shifting

In this paper, a reversible image hiding scheme based on histogram shifting for medical images is proposed. As we know, the histogram-based reversible data hiding is limited by the hiding capacity, which is influenced by the overhead of position information that has to be embedded in the host image. To solve this problem, the similarity of neighboring pixels in the images was explored by using the prediction technique and the residual histogram of the predicted errors of the host image was used to hide the secret data in the proposed scheme. In addition, the overlapping between peak and zero pairs was used to further increase the hiding capacity. According to the experimental results, a higher hiding capacity was obtained and a good quality stego-image was preserved in the proposed scheme. The hiding capacity provided by the proposed scheme was approximately three times that of the original histogram-based method. Compared to the histogram-based method, the quality of the stego-image improved about 1.5 dB when the same amounts of secret data were embedded.

More Than Numbers: The Power of Graphs in Meta-Analysis

In meta-analysis, the assessment of graphs is widely used in an attempt to identify or rule out heterogeneity and publication bias. A variety of graphs are available for this purpose. To date, however, there has been no comparative evaluation of the performance of these graphs. With the objective of assessing the reproducibility and validity of graph ratings, the authors simulated 100 meta-analyses from 4 scenarios that covered situations with and without heterogeneity and publication bias. From each meta-analysis, the authors produced 11 types of graphs (box plot, weighted box plot, standardized residual histogram, normal quantile plot, forest plot, 3 kinds of funnel plots, trim-and-fill plot, Galbraith plot, and L'Abbé plot), and 3 reviewers assessed the resulting 1,100 plots. The intraclass correlation coefficients (ICCs) for reproducibility of the graph ratings ranged from poor (ICC = 0.34) to high (ICC = 0.91). Ratings of the forest plot and the standardized residual histogram were best associated with parameter heterogeneity. Association between graph ratings and publication bias (censorship of studies) was poor. Meta-analysts should be selective in the graphs they choose for the exploration of their data.