Bhattacharyya Distance Research Articles

Investigating the Potential Use of RADARSAT-2 and UAS imagery for Monitoring the Restoration of Peatlands

The restoration of peatlands is critical to help reduce the effects of climate change and further prevent the loss of habitat for many species of flora and fauna. The objective of this research was to evaluate RADARSAT-2 satellite imagery and high-resolution Unmanned Aerial Systems (UASs) to determine if they could be used as surrogates for monitoring the success of peatland restoration. Areas of peatland that were being actively harvested, had been restored from past years (1994–2003), and natural shrub bog in Lac St. Jean, Quebec were used as a test case. We compared the Freeman–Durden and Touzi decompositions by applying the Bhattacharyya Distance (BD) statistic to see if the spectral signatures of restored peatland could be separated from harvested peat and natural shrub bog. We flew Unmanned Aerial Surveys (UASs) over the study site to identify Sphagnum and Polytrichum strictum, two indicator species of early peatland restoration success. Results showed that the Touzi decomposition was better able to separate the spectral signatures of harvested, restored, and natural shrub bog (BD values closer to 9). Symmetric scattering type αs1, Helicity |τ1,2,3|, a steep incidence angle, and peak growing season appear to be important for separating the spectral signatures. We had moderate success in detecting Sphagnum and Polytrichum strictum visually by using texture and pattern but were unable to use colour due to differences in sun angle and clouds during the UAS flights. Results suggest that RADARSAT-2 data using the Touzi decomposition and UAS imagery show potential for monitoring peatland restoration success over time.

An optimization-based deep belief network for the detection of phishing e-mails

PurposePhishing is a serious cybersecurity problem, which is widely available through multimedia, such as e-mail and Short Messaging Service (SMS) to collect the personal information of the individual. However, the rapid growth of the unsolicited and unwanted information needs to be addressed, raising the necessity of the technology to develop any effective anti-phishing methods.Design/methodology/approachThe primary intention of this research is to design and develop an approach for preventing phishing by proposing an optimization algorithm. The proposed approach involves four steps, namely preprocessing, feature extraction, feature selection and classification, for dealing with phishing e-mails. Initially, the input data set is subjected to the preprocessing, which removes stop words and stemming in the data and the preprocessed output is given to the feature extraction process. By extracting keyword frequency from the preprocessed, the important words are selected as the features. Then, the feature selection process is carried out using the Bhattacharya distance such that only the significant features that can aid the classification are selected. Using the selected features, the classification is done using the deep belief network (DBN) that is trained using the proposed fractional-earthworm optimization algorithm (EWA). The proposed fractional-EWA is designed by the integration of EWA and fractional calculus to determine the weights in the DBN optimally.FindingsThe accuracy of the methods, naive Bayes (NB), DBN, neural network (NN), EWA-DBN and fractional EWA-DBN is 0.5333, 0.5455, 0.5556, 0.5714 and 0.8571, respectively. The sensitivity of the methods, NB, DBN, NN, EWA-DBN and fractional EWA-DBN is 0.4558, 0.5631, 0.7035, 0.7045 and 0.8182, respectively. Likewise, the specificity of the methods, NB, DBN, NN, EWA-DBN and fractional EWA-DBN is 0.5052, 0.5631, 0.7028, 0.7040 and 0.8800, respectively. It is clear from the comparative table that the proposed method acquired the maximal accuracy, sensitivity and specificity compared with the existing methods.Originality/valueThe e-mail phishing detection is performed in this paper using the optimization-based deep learning networks. The e-mails include a number of unwanted messages that are to be detected in order to avoid the storage issues. The importance of the method is that the inclusion of the historical data in the detection process enhances the accuracy of detection.

Comparing Arctic Sea Ice Model Simulations to Satellite Observations by Multiscale Directional Analysis of Linear Kinematic Features

AbstractSea ice models have become essential components of weather, climate, and ocean models. A realistic representation of sea ice affects the reliability of process representation, environmental forecast, and climate projections. Realistic simulations of sea ice kinematics require the consideration of both large-scale and finescale geomorphological structures such as linear kinematic features (LKF). We propose a multiscale directional analysis (MDA) that diagnoses the spatial characteristics of LKFs. The MDA is different from previous analyses in that it (i) does not detect LKFs as objects, (ii) takes into account the width of LKFs, and (iii) estimates scale-dependent orientation and intersection angles. The MDA is applied to pairs of deformation fields derived from satellite remote sensing data and from a numerical model simulation with a horizontal grid spacing of ~4.5 km. The orientation and intersection angles of LKFs agree with the observations and confirm the visual impression that the intersection angles tend to be smaller in the satellite data compared to the model data. The MDA distributions can be used to compare satellite data and numerical model fields using conventional metrics such as a Euclidean distance, the Bhattacharyya coefficient, or the Earth mover’s distance. The latter is found to be the most meaningful metric to compare distributions of LKF orientations and intersection angles. The MDA proposed here provides a tool to diagnose if modified sea ice rheologies lead to more realistic simulations of LKFs.

EMUCF: Enhanced multistage user-based collaborative filtering through non-linear similarity for recommendation systems

The data sparsity is an acute challenge in most of the collaborative filterings (CFs) as their performance is affected by the known ratings of target users. Recently, active learning has become a prevalent and straight forward approach to cope with the data sparsity. In this approach, the newly entered users are requested to rate certain items while they signup to the underlying recommendation system. This work proposes an Enhanced Multistage User-based CF (EMUCF) algorithm, which uses the concept of active learning and predicts the unknown ratings for target users in two stages. Here, the anonymous ratings of each intermediary stage are predicted with traditional User_CF algorithm. However, the similarity models commonly used in User_CF are not adequate to compute the similarity among users. Therefore, the most recently introduced Bhattacharyya Coefficient based nonlinear similarity model Bhat_sim is used for similarity computations; it utilizes all rating pairs of items in the final estimates of users similarities. Later, an extension of simple EMUCF, the (n > 2)-stage EMUCF is proposed to increase the prediction accuracy by progressively increasing the density of the original rating matrix. The performance of simple EMUCF and its extension is evaluated on two benchmark Movielens-100K and Movielens-1M datasets. They obtain far superior results for prediction accuracy and recommendation precision compared to several prominent competing algorithms. Finally, the potential improvement in the n-stage EMUCF algorithm is assessed by establishing the connection between rating prediction accuracy and matrix density.

Incremental learning for text categorization using rough set boundary based optimized Support Vector Neural Network

PurposeText mining has been used for various knowledge discovery based applications, and thus, a lot of research has been contributed towards it. Latest trending research in the text mining is adopting the incremental learning data, as it is economical while dealing with large volume of information.Design/methodology/approachThe primary intention of this research is to design and develop a technique for incremental text categorization using optimized Support Vector Neural Network (SVNN). The proposed technique involves four major steps, such as pre-processing, feature selection, classification and feature extraction. Initially, the data is pre-processed based on stop word removal and stemming. Then, the feature extraction is done by extracting semantic word-based features and Term Frequency and Inverse Document Frequency (TF-IDF). From the extracted features, the important features are selected using Bhattacharya distance measure and the features are subjected as the input to the proposed classifier. The proposed classifier performs incremental learning using SVNN, wherein the weights are bounded in a limit using rough set theory. Moreover, for the optimal selection of weights in SVNN, Moth Search (MS) algorithm is used. Thus, the proposed classifier, named Rough set MS-SVNN, performs the text categorization for the incremental data, given as the input.FindingsFor the experimentation, the 20 News group dataset, and the Reuters dataset are used. Simulation results indicate that the proposed Rough set based MS-SVNN has achieved 0.7743, 0.7774 and 0.7745 for the precision, recall and F-measure, respectively.Originality/valueIn this paper, an online incremental learner is developed for the text categorization. The text categorization is done by developing the Rough set MS-SVNN classifier, which classifies the incoming texts based on the boundary condition evaluated by the Rough set theory, and the optimal weights from the MS. The proposed online text categorization scheme has the basic steps, like pre-processing, feature extraction, feature selection and classification. The pre-processing is carried out to identify the unique words from the dataset, and the features like semantic word-based features and TF-IDF are obtained from the keyword set. Feature selection is done by setting a minimum Bhattacharya distance measure, and the selected features are provided to the proposed Rough set MS-SVNN for the classification.

Accuracy of strain measurement systems on a non-isotropic material and its uncertainty on finite element analysis

The application of strain gauges as recommended by the ASTM standards provides accurate strain measurements in isotropic materials. However, their use in composite materials becomes more challenging due to their anisotropic nature. In this study, we hypothesized that the use of the distributed sensing system and the three-dimensional digital image correlation, which can average strain along a line and surface, respectively, may account for strain variability in composite materials. This study shows an investigation on the mechanical properties of unidirectional, cross-ply, and angle-ply carbon-epoxy specimens using strain gauges, distributed sensing system, and digital image correlation. The Bhattacharyya distance method was used to provide a preliminary evaluation of the closeness of the three different measurement techniques while the B-basis statistical method was used to analyze the experimental data in order to obtain a more conservative and reliable material parameter compared to the conventional averaged value, recommended by ASTM standards. Finally, a finite element model was created in Ansys Workbench™ as a means of evaluating the implication of a single point strain gauges measurement, versus a line or a surface strain measurement. The finite element analysis investigation was performed at a laminae level using the measured experimental elastic modulus and at a lamina–lamina level in which the elastic modulus of the unidirectional case was used as input in all the laminate configurations. The former analysis showed good agreement between the finite element analysis and all the strain measurement systems with an averaged percentage difference below 5%. The latter analysis showed a higher discrepancy in the measured percentage difference. A comparison between the finite element analysis and the strain gauges measurements showed an overall percentage difference between the range of 10% and 26%. Distributed sensing system and three-dimensional digital image correlation measurements provided an overall percentage difference below 10% for all the specimen configurations with a maximum percentage difference recorded for the longitudinal angle-ply case of approximately 9%.

Remaining Useful Life Prediction by Fusing Expert Knowledge and Condition Monitoring Information

In this article, we develop a mixture of Gaussians-evidential hidden Markov model (MoG-EHMM) to fuse expert knowledge and condition monitoring information for remaining useful life (RUL) prediction under the belief function theory framework. The evidential expectation-maximization algorithm is implemented in the offline phase to train the MoG-EHMM based on historical data. In the online phase, the trained model is used to recursively update the health state and reliability of a particular individual system. The predicted RUL is, then, represented in the form of its probability mass function. A numerical metric is defined based on the Bhattacharyya distance to measure the RUL prediction accuracy of the developed methods. We applied the developed methods on a simulation experiment and a real-world dataset from a bearing degradation test. The results demonstrate that despite imprecisions in expert knowledge, the performance of RUL prediction can be substantially improved by fusing expert knowledge with condition monitoring information.

Parametric PCA for unsupervised metric learning

In pattern recognition, the problem of quantifying a suitable similarity measure between different objects in a collection is a challenging task, especially in cases where the standard Euclidean distance is not a reasonable choice. In this context, dimensionality reduction algorithms are powerful tools for unsupervised metric learning. In this paper, we propose a framework to build dimensionality reduction methods for unsupervised metric learning based on the mapping of local neighborhoods of the KNN graph to a parametric feature space, defined in terms of a statistical model. By incorporating a non-Euclidean metric based on the Bhattacharyya coefficient, we define the parametric kernel matrix, a surrogate for the covariance matrix of the parametric feature vectors. Inspired by PCA, we use the eigenvalues of the parametric kernel matrix to learn features for the original data. Numerical experiments with real datasets show that Parametric PCA is capable of producing better defined clusters and also more discriminant features in comparison to regular PCA, kernel PCA, sparse PCA, robust PCA and manifold learning algorithms, making the proposed method a promising alternative for unsupervised metric learning.

Forewarning method of downburst based on feature recognition and extrapolation

Currently, using common meteorological data for downburst identification and early warning lacks feasibility. Therefore, a method based on the Doppler weather radar is proposed in this paper to identify, track and predict the downburst. The method is outlined as follows. Firstly, by using the optical flow method, optical flow fields of the reflectivity factors in vertical section are analyzed. The temporal evolution rule of the thunderstorm core is found. Secondly, the Lagrangian mechanical model is used for function fitting of the thunderstorm-core top’s sinking process. Lastly, by adopting histogram and the Bhattacharyya coefficient (BC), the statistical analysis is carried out to match and identify the positive and negative velocity pairs in the middle-level radial velocity field of the thunderstorm core. Moreover, a series of thresholds are also analyzed to achieve the intelligent forewarning of the downburst. In this paper, the local constraint algorithm featuring multi-layer iteration is introduced, which effectively improves the inapplicability issue in the traditional method of analyzing non-rigid moving targets such as echo. Furthermore, the measure based on the histogram and the BC are proposed to solve the image matching problem due to the asymmetric structure of positive and negative velocity pair images in the radial direction. The experiment results show that the method is able to identify the potential downburst at the early stage of the thunderstorm-core rising or sinking processes. Meanwhile, the descent velocity and time of the thunderstorm core reaching near surface can be estimated, and then, the intelligent identification and early warning of downbursts can be realized.

SUR-FeatNet: Predicting the satisfied user ratio curve for image compression with deep feature learning

The satisfied user ratio (SUR) curve for a lossy image compression scheme, e.g., JPEG, characterizes the complementary cumulative distribution function of the just noticeable difference (JND), the smallest distortion level that can be perceived by a subject when a reference image is compared to a distorted one. A sequence of JNDs can be defined with a suitable successive choice of reference images. We propose the first deep learning approach to predict SUR curves. We show how to apply maximum likelihood estimation and the Anderson-Darling test to select a suitable parametric model for the distribution function. We then use deep feature learning to predict samples of the SUR curve and apply the method of least squares to fit the parametric model to the predicted samples. Our deep learning approach relies on a siamese convolutional neural network, transfer learning, and deep feature learning, using pairs consisting of a reference image and a compressed image for training. Experiments on the MCL-JCI dataset showed state-of-the-art performance. For example, the mean Bhattacharyya distances between the predicted and ground truth first, second, and third JND distributions were 0.0810, 0.0702, and 0.0522, respectively, and the corresponding average absolute differences of the peak signal-to-noise ratio at a median of the first JND distribution were 0.58, 0.69, and 0.58 dB. Further experiments on the JND-Pano dataset showed that the method transfers well to high resolution panoramic images viewed on head-mounted displays.

Identification system by Tongue based on Bhattacharyya distance

Tongue recognition is a biometric technique that can be applied to different areas of expression of human identity. Recognition of the tongue is a difficult and complex problem that is important for surveillance, security, and intelligent interaction between computers and humans.The main idea of proposed system rely that on that any image of a person’s tongue has multiple unique features. Those features vary from on tongue to another. The system proposed in this paper uses group, the Extract the characteristics based on the wavelet Transform where it uses information color (color space RGB) at a certain form of detailed wavelet transforms (discrete wavelet transform), and use of Bhattacharyya distance for comparison between persons.The tongue datasets that are used for of the suggested system are gathered from 30 volunteers of various samples; 4 have been from every individual, images have been captured in various expressions, illuminations, orientations, skin colors, backgrounds, varied in the age) from male and female, results indicated the discrimination rate for waveleting 72%, persons were recognized using Bhattacharyya distance by 93%.

Evaluating Onset Times of Acoustic Emission Signals Using Histogram Distances

Determining the onset of a transient signal, for example in seismograms, acoustic emission (AE) signals, or ultrasonic signals is very important in non-destructive process monitoring and geophysics. In some cases, the AE from a malfunction is relatively weak, with a low signal-to-noise ratio. Thus, the signals are often hidden, making it rather difficult to separate them from the background noise. The present work proposes a new method of evaluating onset times based on bin-to-bin histogram distances measured with the Bhattacharyya coefficient. A criterion and a standard procedure for determining an onset are formulated. A key parameter, window length, was discussed in detail. Tests on AE signals from a pencil-lead break, single-grit scratching, and filament breakage reveal the feasibility and effectiveness of the proposed method. This method is believed to be especially appropriate when the emission signal strength of the target malfunction is lower than environmental AE signals generated by other stationary sources. It can also be used as an alternative method for identifying onsets in AE signals in process monitoring and other fields.

Accuracy and limitations for spectroscopic prediction of leaf traits in seasonally dry tropical environments

Generalized assessments of the accuracy of spectroscopic estimates of ecologically important leaf traits such as leaf mass per area (LMA) and leaf dry matter content (LDMC) are still lacking for most ecosystems, and particularly for non-forested and/or seasonally dry tropical vegetation. Here, we tested the ability of using leaf reflectance spectra to estimate LMA and LDMC and classify plant growth forms within the cerrado and campo rupestre seasonally dry non-forest vegetation types of Southeastern Brazil, filling an existing gap in published assessments of leaf optical properties and plant traits in such environments. We measured leaf reflectance spectra from 1648 individual plants comprising grasses, herbs, shrubs, and trees, developed partial least squares regression (PLSR) models linking LMA and LDMC to leaf spectra (400–2500 nm), and identified the spectral regions with the greatest discriminatory power among growth forms using Bhattacharyya distances. We accurately predicted leaf functional traits and identified different growth forms. LMA was overall more accurately predicted (RMSE = 8.58%) than LDMC (RMSE = 9.75%). Our model including all sampled plants was not biased towards any particular growth form, but growth-form specific models yielded higher accuracies and showed that leaf traits from woody plants can be more accurately estimated than for grasses and forbs, independently of the trait measured. We observed a large range of LMA values (31.80–620.81 g/m2) rarely observed in tropical or temperate forests, and demonstrated that values above 300 g/m2 could not be accurately estimated. Our results suggest that spectroscopy may have an intrinsic saturation point, and/or that PLSR, the current approach of choice for estimating traits from plant spectra, is not able to model the entire range of LMA values. This finding has very important implications to our ability to use field, airborne, and orbital spectroscopic methods to derive generalizable functional information. We thus highlight the need for increasing spectroscopic sampling and research efforts in drier non-forested environments, where environmental pressures lead to leaf adaptations and allocation strategies that are very different from forested ecosystems. Our findings also confirm that leaf reflectance spectra can provide important information regarding differences in leaf metabolism, structure, and chemical composition. Such information enabled us to accurately discriminate plant growth forms in these environments regardless of lack of variation in leaf economic traits, encouraging further adoption of remote sensing methods by ecologists and allowing a more comprehensive assessment of plant functional diversity.

Adaptive Causal Network Coding With Feedback

We propose a novel adaptive and causal random linear network coding (AC-RLNC) algorithm with forward error correction (FEC) for a point-to-point communication channel with delayed feedback. AC-RLNC is adaptive to the channel condition, that the algorithm estimates, and is causal, as coding depends on the particular erasure realizations, as reflected in the feedback acknowledgments. Specifically, the proposed model can learn the erasure pattern of the channel via feedback acknowledgments, and adaptively adjust its retransmission rates using a priori and posteriori algorithms. By those adjustments, AC-RLNC achieves the desired delay and throughput, and enables transmission with zero error probability. We upper bound the throughput and the mean and maximum in order delivery delay of AC-RLNC, and prove that for the point to point communication channel in the non-asymptotic regime the proposed code may achieve more than 90% of the channel capacity. To upper bound the throughput we utilize the minimum Bhattacharyya distance for the AC-RLNC code. We validate those results via simulations. We contrast the performance of AC-RLNC with the one of selective repeat (SR)-ARQ, which is causal but not adaptive, and is a posteriori. Via a study on experimentally obtained commercial traces, we demonstrate that a protocol based on AC-RLNC can, vis-a-vis SR-ARQ, double the throughput gains, and triple the gain in terms of mean in order delivery delay when the channel is bursty. Furthermore, the difference between the maximum and mean in order delivery delay is much smaller than that of SR-ARQ. Closing the delay gap along with boosting the throughput is very promising for enabling ultra-reliable low-latency communications (URLLC) applications.

Accurate extraction of offshore raft aquaculture areas based on a 3D-CNN model

ABSTRACT Offshore aquaculture plays an important role in China’s marine fishery economy. The research on the extraction of offshore aquaculture areas based on remote sensing technology is of great significance for the regulation of offshore fishery resources and the protection of the marine ecological environment. This paper uses the Gaofen-2 series multispectral remote sensing image to extract the offshore aquaculture areas of Lianyungang City. We use the optimum index factor to extract the spectral features of the aquaculture areas and the grey-level co-occurrence matrix to extract their texture features. We use the Bhattacharyya distance to select the spatial and spectrum features and construct the characteristic data set of the aquaculture areas. In this paper, we propose a method to construct a uniform distributed disturbance term to optimize the cross entropy loss function. We employ it in the three-dimensional convolutional neural network (3D-CNN) model, extract the extended feature data set of aquaculture areas, and input it into the radial basis function support vector machine (RBF-SVM) classifier for classification. Within the study area of 150 km2, the experimental results show that the extraction model has high extraction accuracy and strong spatial migration despite complex water backgrounds. The F 1-score values in the training area and the four random test areas were 0.939 or above for 2017 data. In addition, the extraction model also has stable time migration. We used the extraction model on remote sensing data for the same study area in 2018 and 2019. The F 1-scores for all test areas are 0.866 or higher. Therefore, the model proposed in this paper is suitable for the extraction of large-scale and multi-temporal offshore raft aquaculture areas from remote sensing images.

A probabilistic approach for calibration time reduction in hybrid EEG\u2013fTCD brain\u2013computer interfaces

BackgroundGenerally, brain–computer interfaces (BCIs) require calibration before usage to ensure efficient performance. Therefore, each BCI user has to attend a certain number of calibration sessions to be able to use the system. However, such calibration requirements may be difficult to fulfill especially for patients with disabilities. In this paper, we introduce a probabilistic transfer learning approach to reduce the calibration requirements of our EEG–fTCD hybrid BCI designed using motor imagery (MI) and flickering mental rotation (MR)/word generation (WG) paradigms. The proposed approach identifies the top similar datasets from previous BCI users to a small training dataset collected from a current BCI user and uses these datasets to augment the training data of the current BCI user. To achieve such an aim, EEG and fTCD feature vectors of each trial were projected into scalar scores using support vector machines. EEG and fTCD class conditional distributions were learnt separately using the scores of each class. Bhattacharyya distance was used to identify similarities between class conditional distributions obtained using training trials of the current BCI user and those obtained using trials of previous users.ResultsExperimental results showed that the performance obtained using the proposed transfer learning approach outperforms the performance obtained without transfer learning for both MI and flickering MR/WG paradigms. In particular, it was found that the calibration requirements can be reduced by at least 60.43% for the MI paradigm, while at most a reduction of 17.31% can be achieved for the MR/WG paradigm.ConclusionsData collected using the MI paradigm show better generalization across subjects.

Detection of distributed denial of service attack in cloud computing using the optimization-based deep networks

ABSTRACT Cloud computing services provide a wide range of resource pool for maintaining a large amount of data. Cloud services are commonly used as the private or public data forum based on the demand, and the increase in usage has lead to security concerns. The information in the cloud comes under threat due to hackers, and the most common attack on the cloud data is considered as the Distributed Denial of Service (DDoS) attack. This work has concentrated on detecting the DDoS attack by developing the deep learning-based classifier. The service request from the users is collected and grouped as the log information. From the log file, some important features are selected for the classification using the Bhattacharya distance measure to reduce the training time of the classifier. Here, Taylor-Elephant Herd Optimisation based Deep Belief Network (TEHO-DBN), is developed by modifying the Elephant Herd Optimisation (EHO) with the Taylor series and the algorithm thus developed is adopted to train the Deep Belief Network (DBN) for the DDoS attack detection. From the simulation results, it can be concluded that the proposed TEHO based DBN classifier has improved performance with a maximum accuracy of 0.830.

Adaptive Digital Image Watermarking Using DWT-PCA

With the growing demand for sharing digital content over the internet, the need for multimedia security has been significant. Digital media contents like images, audio, video can be easily manipulated by computer to perceptible with original content. Advancement in Digital Watermarking techniques has been a solution to protect digital media content from copyright infringement. Digital Watermarking is the process of concealing messages in digital contents in order to verify the rightful owner of the copyright protection. In this paper we have proposed a method that would assist its users to embed a watermark to the cover image based on an adaptive approach in a much robust way while maintaining the quality of the cover image. The implementation of this algorithm is based upon cascading the features of DWT and PCA using Bhattacharyya distance and Kurtosis. PCA decompose and compress the watermark, which results in better PSNR and NCC values for the tested images. The proposed algorithm uses Bhattacharyya distance and Kurtosis to detect the scaling and embedding factors making it adaptive to the input image rather than providing constant value. The main motivation for creating an adaptive mechanism is the fact that not all images are the same and hence a static embedding factor will not result in a robust embedding of watermark in the cover image in all cases. Experimental results show the efficiency and robustness of the proposed technique.

Learning from Positive and Unlabeled Data without Explicit Estimation of Class Prior

Learning a classifier from positive and unlabeled data may occur in various applications. It differs from the standard classification problems by the absence of labeled negative examples in the training set. So far, two main strategies have typically been used for this issue: the likely negative examplesbased strategy and the class prior-based strategy, in which the likely negative examples or the class prior is required to be obtained in a preprocessing step. In this paper, a new strategy based on the Bhattacharyya coefficient is put forward, which formalizes this learning problem as an optimization problem and does not need a preprocessing step. We first show that with the given positive class conditional probability density function (PDF) and the mixture PDF of both the positive class and the negative class, the class prior can be estimated by minimizing the Bhattacharyya coefficient of the positive class with respect to the negative class. We then show how to use this result in an implicit mixture model of restricted Boltzmann machines to estimate the positive class conditional PDF and the negative class conditional PDF directly to obtain a classifier without the explicit estimation of the class prior. Many experiments on real and synthetic datasets illustrated the superiority of the proposed approach.

MATLAB Tool for Color Comparative Analysis in Fixed Specimens. A Five Solution Single Blind Controlled Trial

Formaldehyde fixation avoids decomposition process of cadaveric specimens 1, making them useful for anatomy teaching and research 2. However, formaldehyde leads to fresh appearance loss in the tissue, which reduces its academical value. Although some color recovery solutions have been presented 3, 4, no standardized method for quantitative color assessment in fixed tissues has been proposed.Our aim of is to present a MATLAB tool for color recovery analysis in formaldehyde fixed tissues.Four different animal tissues (cardiac and skeletal muscle, kidney and liver), previously fixed with 10% formaldehyde (v/v) were treated in five different solutions (mineral staining, sodium bisulfite, sodium bicarbonate, GERDEX and modified Chilean solution 3). Tissues were photographed at different stages of preservation. Analysis was carried out in two different spaces of chromatic representation (RGB and HSV).A computerized color comparison tool was developed allowing visualization of the chromatic presence in RGB color space through a three‐dimensional distribution (color cloud). Besides color cloud intersection percentage, frequency histograms of RGB distributions and the color saturation (S) distribution were used to generate performance metrics based on the Bhattacharyya distance. Each metric addressed one specific desired characteristic of a color recuperated specimen.Mineral staining proved to be the solution with the best overall performance across most of the proposed metrics, significantly recovering the color compared to fresh tissue. Although significant results were obtained, future works implementing more robust methods of comparison, that involve metrics based on multiple desirable characteristics of a specimen are necessary.The MATLAB tool developed showed to be useful for the quantitative color analysis and comparison in formaldehyde fixed tissues. Further studies should be done to standardize quality metrics of existing and upcoming preservation techniques.Support or Funding InformationAnatomy Laboratory, School of Medicine, Universidad de los Andes.