Binary image steganographic techniques classification based on multi-class steganalysis

In this paper, we propose a new multi-class steganalysis for binary image. The proposed method can identify the type of steganographic technique used by examining on the given binary image. In addition, our proposed method is also capable of differentiating an image with hidden message from the one without hidden message. In order to do that, we will extract some features from the binary image. The feature extraction method used is a combination of the method extended from our previous work and some new methods proposed in this paper. Based on the extracted feature sets, we construct our multi-class steganalysis from the SVM classifier. We also present the empirical works to demonstrate that the proposed method can effectively identify five different types of steganography.

Automated classification of limb fractures from free-text radiology reports using a clinician-informed gazetteer methodology

Background Timely diagnosis and reporting of patient symptoms in hospital emergency departments (ED) is a critical component of health services delivery. However, due to dispersed information resources and a vast amount of manual processing of unstructured information, accurate point-of-care diagnosis is often difficult. Aims The aim of this research is to report initial experimental evaluation of a clinician-informed automated method for the issue of initial misdiagnoses associated with delayed receipt of unstructured radiology reports. Method A method was developed that resembles clinical reasoning for identifying limb abnormalities. The method consists of a gazetteer of keywords related to radiological findings; the method classifies an X-ray report as abnormal if it contains evidence contained in the gazetteer. A set of 99 narrative reports of radiological findings was sourced from a tertiary hospital. Reports were manually assessed by two clinicians and discrepancies were validated by a third expert ED clinician; the final manual classification generated by the expert ED clinician was used as ground truth to empirically evaluate the approach. Results The automated method that attempts to individuate limb abnormalities by searching for keywords expressed by clinicians achieved an F-measure of 0.80 and an accuracy of 0.80. Conclusion While the automated clinician-driven method achieved promising performances, a number of avenues for improvement were identified using advanced natural language processing (NLP) and machine learning techniques.

Classification of cancer-related death certificates using machine learning

Background Cancer monitoring and prevention relies on the critical aspect of timely notification of cancer cases. However, the abstraction and classification of cancer from the free-text of pathology reports and other relevant documents, such as death certificates, exist as complex and time-consuming activities. Aims In this paper, approaches for the automatic detection of notifiable cancer cases as the cause of death from free-text death certificates supplied to Cancer Registries are investigated. Method A number of machine learning classifiers were studied. Features were extracted using natural language techniques and the Medtex toolkit. The numerous features encompassed stemmed words, bi-grams, and concepts from the SNOMED CT medical terminology. The baseline consisted of a keyword spotter using keywords extracted from the long description of ICD-10 cancer related codes. Results Death certificates with notifiable cancer listed as the cause of death can be effectively identified with the methods studied in this paper. A Support Vector Machine (SVM) classifier achieved best performance with an overall F-measure of 0.9866 when evaluated on a set of 5,000 free-text death certificates using the token stem feature set. The SNOMED CT concept plus token stem feature set reached the lowest variance (0.0032) and false negative rate (0.0297) while achieving an F-measure of 0.9864. The SVM classifier accounts for the first 18 of the top 40 evaluated runs, and entails the most robust classifier with a variance of 0.001141, half the variance of the other classifiers. Conclusion The selection of features significantly produced the most influences on the performance of the classifiers, although the type of classifier employed also affects performance. In contrast, the feature weighting schema created a negligible effect on performance. Specifically, it is found that stemmed tokens with or without SNOMED CT concepts create the most effective feature when combined with an SVM classifier.

Soil moisture monitoring at the field scale using neutron probe

Measurement of the moisture variation in soils is required for geotechnical design and research because soil properties and behavior can vary as moisture content changes. The neutron probe, which was developed more than 40 years ago, is commonly used to monitor soil moisture variation in the field. This study reports a full-scale field monitoring of soil moisture using a neutron moisture probe for a period of more than 2 years in the Melbourne (Australia) region. On the basis of soil types available in the Melbourne region, 23 sites were chosen for moisture monitoring down to a depth of 1500 mm. The field calibration method was used to develop correlations relating the volumetric moisture content and neutron counts. Observed results showed that the deepest “wetting front” during the wet season was limited to the top 800 to 1000 mm of soil whilst the top soil layer down to about 550mmresponded almost immediately to the rainfall events. At greater depths (550 to 800mmand below 800 mm), the moisture variations were relatively low and displayed predominantly periodic fluctuations. This periodic nature was captured with Fourier analysis to develop a cyclic moisture model on the basis of an analytical solution of a one-dimensional moisture flow equation for homogeneous soils. It is argued that the model developed can be used to predict the soil moisture variations as applicable to buried structures such as pipes.

Calibration functions for estimating soil moisture from GPR dielectric constant measurements

Ground-penetrating radar (GPR) is widely used for assessment of soil moisture variability in field soils. Because GPR does not measure soil water content directly, it is common practice to use calibration functions that describe its relationship with the soil dielectric properties and textural parameters. However, the large variety of models complicates the selection of the appropriate function. In this article an overview is presented of the different functions available, including volumetric models, empirical functions, effective medium theories, and frequency-specific functions. Using detailed information presented in summary tables, the choice for which calibration function to use can be guided by the soil variables available to the user, the frequency of the GPR equipment, and the desired level of detail of the output. This article can thus serve as a guide for GPR practitioners to obtain soil moisture values and to estimate soil dielectric properties.

Random projections on manifolds of symmetric positive definite matrices for image classification

Recent advances suggest that encoding images through Symmetric Positive Definite (SPD) matrices and then interpreting such matrices as points on Riemannian manifolds can lead to increased classification performance. Taking into account manifold geometry is typically done via (1) embedding the manifolds in tangent spaces, or (2) embedding into Reproducing Kernel Hilbert Spaces (RKHS). While embedding into tangent spaces allows the use of existing Euclidean-based learning algorithms, manifold shape is only approximated which can cause loss of discriminatory information. The RKHS approach retains more of the manifold structure, but may require non-trivial effort to kernelise Euclidean-based learning algorithms. In contrast to the above approaches, in this paper we offer a novel solution that allows SPD matrices to be used with unmodified Euclidean-based learning algorithms, with the true manifold shape well-preserved. Specifically, we propose to project SPD matrices using a set of random projection hyperplanes over RKHS into a random projection space, which leads to representing each matrix as a vector of projection coefficients. Experiments on face recognition, person re-identification and texture classification show that the proposed approach outperforms several recent methods, such as Tensor Sparse Coding, Histogram Plus Epitome, Riemannian Locality Preserving Projection and Relational Divergence Classification.

Automatic classification of human epithelial type 2 cell indirect immunofluorescence images using cell pyramid matching

This paper describes a novel system for automatic classification of images obtained from Anti-Nuclear Antibody (ANA) pathology tests on Human Epithelial type 2 (HEp-2) cells using the Indirect Immunofluorescence (IIF) protocol. The IIF protocol on HEp-2 cells has been the hallmark method to identify the presence of ANAs, due to its high sensitivity and the large range of antigens that can be detected. However, it suffers from numerous shortcomings, such as being subjective as well as time and labour intensive. Computer Aided Diagnostic (CAD) systems have been developed to address these problems, which automatically classify a HEp-2 cell image into one of its known patterns (eg. speckled, homogeneous). Most of the existing CAD systems use handpicked features to represent a HEp-2 cell image, which may only work in limited scenarios. We propose a novel automatic cell image classification method termed Cell Pyramid Matching (CPM), which is comprised of regional histograms of visual words coupled with the Multiple Kernel Learning framework. We present a study of several variations of generating histograms and show the efficacy of the system on two publicly available datasets: the ICPR HEp-2 cell classification contest dataset and the SNPHEp-2 dataset.

Improved image set classification via joint sparse approximated nearest subspaces

Existing multi-model approaches for image set classification extract local models by clustering each image set individually only once, with fixed clusters used for matching with other image sets. However, this may result in the two closest clusters to represent different characteristics of an object, due to different undesirable environmental conditions (such as variations in illumination and pose). To address this problem, we propose to constrain the clustering of each query image set by forcing the clusters to have resemblance to the clusters in the gallery image sets. We first define a Frobenius norm distance between subspaces over Grassmann manifolds based on reconstruction error. We then extract local linear subspaces from a gallery image set via sparse representation. For each local linear subspace, we adaptively construct the corresponding closest subspace from the samples of a probe image set by joint sparse representation. We show that by minimising the sparse representation reconstruction error, we approach the nearest point on a Grassmann manifold. Experiments on Honda, ETH-80 and Cambridge-Gesture datasets show that the proposed method consistently outperforms several other recent techniques, such as Affine Hull based Image Set Distance (AHISD), Sparse Approximated Nearest Points (SANP) and Manifold Discriminant Analysis (MDA).

Hydrolysis of triasulfuron, metsulfuron-methyl and chlorsulfuron in alkaline soil and aqueous solutions

The hydrolysis of triasulfuron, metsulfuron-methyl and chlorsulfuron in aqueous buffer solutions and in soil suspensions at pH values ranging from 5.2 to 11.2 was investigated. Hydrolysis of all three compounds in both aqueous buffer and soil suspensions was highly pH-sensitive. The rate of hydrolysis was much faster in the acidic pH range (5.2-6.2) than under neutral and moderately alkaline conditions (8.2-9.4), but it increased rapidly as the pH exceeded 10.2. All three compounds degraded faster at pH 5.2 than at pH 11.2. Hydrolysis rates of all three compounds could be described well with pseudo-first-order kinetics. There were no significant differences (P =0.05) in the rate constants (k, day-1) of the three compounds in soil suspensions from those in buffer solutions within the pH ranges studied. A functional relationship based on the propensity of nonionic and anionic species of the herbicides to hydrolyse was used to describe the dependence of the 'rate constant' on pH. The hydrolysis involving attack by neutral water was at least 100-fold faster when the sulfonylurea herbicides were undissociated (acidic conditions) than when they were present as the anion at near neutral pH. In aqueous buffer solution at pH > 11, a prominent degradation pathway involved O-demethylation of metsulfuron-methyl to yield a highly polar degradate, and hydrolytic opening of the triazine ring. It is concluded that these herbicides are not likely to degrade substantially through hydrolysis in most agricultural (C) 2000 Society of Chemical Industry.

Impact of a change in tillage and crop residue management practice on soil chemical and microbiological properties in a cereal-producing red duplex soil in NSW, Australia

The effect of a change of tillage and crop residue management practice on the chemical and micro-biological properties of a cereal-producing red duplex soil was investigated by superimposing each of three management practices (CC: conventional cultivation, stubble burnt, crop conventionally sown; DD: direct-drilling, stubble retained, no cultivation, crop direct-drilled; SI: stubble incorporated with a single cultivation, crop conventionally sown), for a 3-year period on plots previously managed with each of the same three practices for 14 years. A change from DD to CC or SI practice resulted in a significant decline, in the top 0-5 cm of soil, in organic C, total N, electrical conductivity, NH4-N, NO3-N, soil moisture holding capacity, microbial biomass and CO2 respiration as well as a decline in the microbial quotient (the ratio of microbial biomass C to organic C; P <0.05). In contrast, a change from SI to DD or CC practice or a change from CC to DD or SI practice had only negligible impact on soil chemical properties (P >0.05). However, there was a significant increase in microbial biomass and the microbial quotient in the top 0-5 cm of soil following the change from CC to DD or SI practice and with the change from SI to DD practice (P <0.05). Analysis of ester-linked fatty acid methyl esters (EL-FAMEs) extracted from the 0- to 5-cm and 5- to 10-cm layers of the soils of the various treatments detected changes in the FAME profiles following a change in tillage practice. A change from DD practice to SI or CC practice was associated with a significant decline in the ratio of fungal to bacterial fatty acids in the 0- to 5-cm soil (P <0.05). The results show that a change in tillage practice, particularly the cultivation of a previously minimum-tilled (direct-drilled) soil, will result in significant changes in soil chemical and microbiological properties within a 3-year period. They also show that soil microbiological properties are sensitive indicators of a change in tillage practice.

Statistical analysis of reduction in tensile strength of cotton strips as a measure of soil microbial activity

The cotton strip assay (CSA) is an established technique for measuring soil microbial activity. The technique involves burying cotton strips and measuring their tensile strength after a certain time. This gives a measure of the rotting rate, R, of the cotton strips. R is then a measure of soil microbial activity. This paper examines properties of the technique and indicates how the assay can be optimised. Humidity conditioning of the cotton strips before measuring their tensile strength reduced the within and between day variance and enabled the distribution of the tensile strength measurements to approximate normality. The test data came from a three-way factorial experiment (two soils, two temperatures, three moisture levels). The cotton strips were buried in the soil for intervals of time ranging up to 6 weeks. This enabled the rate of loss of cotton tensile strength with time to be studied under a range of conditions. An inverse cubic model accounted for greater than 90% of the total variation within each treatment combination. This offers support for summarising the decomposition process by a single parameter R. The approximate variance of the decomposition rate was estimated from a function incorporating the variance of tensile strength and the differential of the function for the rate of decomposition, R, with respect to tensile strength. This variance function has a minimum when the measured strength is approximately 2/3 that of the original strength. The estimates of R are almost unbiased and relatively robust against the cotton strips being left in the soil for more or less than the optimal time. We conclude that the rotting rate X should be measured using the inverse cubic equation, and that the cotton strips should be left in the soil until their strength has been reduced to about 2/3.

Using the Gini coefficient with BIOLOG substrate utilisation data to provide an alternative quantitative measure for comparing bacterial soil communities

A measure quantifying unequal use of carbon sources, the Gini coefficient (G), has been developed to allow comparisons of the observed functional diversity of bacterial soil communities. This approach was applied to the analysis of substrate utilisation data obtained from using BIOLOG microtiter plates in a study which compared decomposition processes in two contrasting plant substrates in two different soils. The relevance of applying the Gini coefficient as a measure of observed functional diversity, for soil bacterial communities is evaluated against the Shannon index (H) and average well colour development (AWCD), a measure of the total microbial activity. Correlation analysis and analysis of variance of the experimental data show that the Gini coefficient, the Shannon index and AWCD provided similar information when used in isolation. However, analyses based on the Gini coefficient and the Shannon index, when total activity on the microtiter plates was maintained constant (i.e. AWCD as a covariate), indicate that additional information about the distribution of carbon sources being utilised can be obtained. We demonstrate that the Lorenz curve and its measure of inequality, the Gini coefficient, provides not only comparable information to AWCD and the Shannon index but when used together with AWCD encompasses measures of total microbial activity and absorbance inequality across all the carbon sources. This information is especially relevant for comparing the observed functional diversity of soil microbial communities.

Capacity of fatty acid profiles and substrate utilization patterns to describe differences in soil microbial communities associated with increased salinity or alkalinity at three locations in South Australia

Fatty acid methyl ester (FAME) profiles, together with Biolog substrate utilization patterns, were used in conjunction with measurements of other soil chemical and microbiological properties to describe differences in soil microbial communities induced by increased salinity and alkalinity in grass/legume pastures at three sites in SE South Australia. Total ester-linked FAMEs (EL-FAMEs) and phospholipid-linked FAMEs (PL-FAMEs), were also compared for their ability to detect differences between the soil microbial communities. The level of salinity and alkalinity in affected areas of the pastures showed seasonal variation, being greater in summer than in winter. At the time of sampling for the chemical and microbiological measurements (winter) only the affected soil at site 1 was significantly saline. The affected soils at all three sites had lower organic C and total N concentrations than the corresponding non-affected soils. At site 1 microbial biomass, CO 2-C respiration and the rate of cellulose decomposition was also lower in the affected soil compared to the non-affected soil. Biomarker fatty acids present in both the EL- and PL-FAME profiles indicated a lower ratio of fungal to bacterial fatty acids in the saline affected soil at site 1. Analysis of Biolog substrate utilization patterns indicated that the bacterial community in the affected soil at site 1 utilized fewer carbon substrates and had lower functional diversity than the corresponding community in the non-affected soil. In contrast, increased alkalinity, of major importance at sites 2 and 3, had no effect on microbial biomass, the rate of cellulose decomposition or functional diversity but was associated with significant differences in the relative amounts of several fatty acids in the PL-FAME profiles indicative of a shift towards a bacterial dominated community. Despite differences in the number and relative amounts of fatty acids detected, principal component analysis of the EL- and PL-FAME profiles were equally capable of separating the affected and non-affected soils at all three sites. Redundancy analysis of the FAME data showed that organic C, microbial biomass, electrical conductivity and bicarbonate-extractable P were significantly correlated with variation in the EL-FAME profiles, whereas pH, electrical conductivity, NH 4-N, CO 2-C respiration and the microbial quotient were significantly correlated with variation in the PL-FAME profiles. Redundancy analysis of the Biolog data indicated that cation exchange capacity and bicarbonate-extractable K were significantly correlated with the variation in Biolog substrate utilization patterns.

Polarization of forecast densities : a new approach to time series classification

Time series classification has been extensively explored in many fields of study. Most methods are based on the historical or current information extracted from data. However, if interest is in a specific future time period, methods that directly relate to forecasts of time series are much more appropriate. An approach to time series classification is proposed based on a polarization measure of forecast densities of time series. By fitting autoregressive models, forecast replicates of each time series are obtained via the bias-corrected bootstrap, and a stationarity correction is considered when necessary. Kernel estimators are then employed to approximate forecast densities, and discrepancies of forecast densities of pairs of time series are estimated by a polarization measure, which evaluates the extent to which two densities overlap. Following the distributional properties of the polarization measure, a discriminant rule and a clustering method are proposed to conduct the supervised and unsupervised classification, respectively. The proposed methodology is applied to both simulated and real data sets, and the results show desirable properties.