Information Divergence Research Articles

The choice of spectral similarity algorithms influences suspected soil sample provenance

Similarity algorithms are commonly used in soil forensic applications to help identify similar samples from an existing reference library as possible source locations of unknown target samples. These algorithms are well-suited to compare soil spectra. However, different similarity algorithms may lead to different clusters of similar samples, and thus different strengths of evidence in forensic investigations. To quantify this, we conducted a study to evaluate the influence of seven similarity algorithms on soil provenance, using as a sample set a soil spectral library consisting of 280 soil profiles from Anhui Province, China. This library includes three spatial scales of datasets: provincial (DSp), county (DSc) and field (DSf). A set of ten samples covering a wide range of spectra variations were selected from the DSf dataset as the “unknown” samples, with the remaining being used as the reference samples. This study aimed to: (1) evaluate how several commonly-used similarity algorithms, namely Euclidean distance (ED), Mahalanobis distance (MD), Spectral angle mapper (SAM), and Spectral information divergence (SID), as well as variants of several of these measured in standardized principal component space computed from the spectra (ED_PCA, MD_PCA and SAM_PCA), influence the identification of the matched similar samples; (2) determine the overlap in sample selection between different similarity algorithms; (3) propose best practices for similarity algorithms applied to soil forensic analysis using spectroscopy. The use of different similarity algorithms did influence the selection of most similar samples. The similarity algorithms calculated in PC space (ED_PCA, MD_PCA and SAM_PCA) performed slightly better than their counterparts calculated in spectral space. Due to the availability of a detailed spectral library, regardless of the different similarity algorithms used, the matched most similar samples were all located close to the unknowns, mostly within 3 km, with one exception. That is, the varied choices of different similarity algorithms hardly influenced the conclusion of soil provenance in this case. In general, MD_PCA, SAM and ED were the best similarity algorithms overall. However, since there was no single best algorithms for all cases, we recommend the joint use of MD_PCA, SAM and ED as an ensemble. Indications of possible sample provenance from these similarity measured can be useful evidence to complement evidence from other methods in a forensic investigation.

Entropic Dynamics in a Theoretical Framework for Biosystems.

Central to an understanding of the physical nature of biosystems is an apprehension of their ability to control entropy dynamics in their environment. To achieve ongoing stability and survival, living systems must adaptively respond to incoming information signals concerning matter and energy perturbations in their biological continuum (biocontinuum). Entropy dynamics for the living system are then determined by the natural drive for reconciliation of these information divergences in the context of the constraints formed by the geometry of the biocontinuum information space. The configuration of this information geometry is determined by the inherent biological structure, processes and adaptive controls that are necessary for the stable functioning of the organism. The trajectory of this adaptive reconciliation process can be described by an information-theoretic formulation of the living system's procedure for actionable knowledge acquisition that incorporates the axiomatic inference of the Kullback principle of minimum information discrimination (a derivative of Jaynes' principle of maximal entropy). Utilizing relative information for entropic inference provides for the incorporation of a background of the adaptive constraints in biosystems within the operations of Fisher biologic replicator dynamics. This mathematical expression for entropic dynamics within the biocontinuum may then serve as a theoretical framework for the general analysis of biological phenomena.

Clarification of the Exceptional-Point Contribution to Photonic Sensing

Exceptional points, with simultaneous coalescence of eigenvalues and eigenvectors, can be realized with non-Hermitian photonic systems. With the enhanced response, exceptional points have been proposed to improve the performance of photonic sensing. Recently, there are intense debates about the actual sensing advantage of exceptional points. The major concern is that intrinsic noise is also increased at exceptional points. Here, we aim to clarify the contribution of exceptional points for photonic sensing. This is achieved by analyzing the condition to realize divergent quantum Fisher information in linear non-Hermitian photonic systems. We show that the divergence of quantum Fisher information is the result of lasing threshold, instead of exceptional points. However, exceptional points correspond to the condition that lasing threshold is simultaneously achieved across multiple photonic modes. Therefore, exceptional points can further improve the sensitivity on top of lasing threshold. On the other hand, exceptional points alone cannot provide sensing advantage.

Spectrum recovery from multispectral ocean color data using system spectral shape factor

Data from ocean color monitoring sensors at different spectral channels are available for remote sensing of radiation as seen in the given spectral windows, which is used for deriving information on various atmospheric parameters. However, recent studies have demonstrated the potential of hyperspectral (HS) data over multispectral ocean color (MSOC) data in accurately estimating phytoplankton concentration and in monitoring the coastal dynamics. We propose system spectral shape factor (SSSF)-based approach to recover the embedded HS top-of-atmosphere (TOA) radiance (TOARAD) from the MSOC data. SSSF is defined as convolution of normalized input spectrum and sensor spectral response function (SRF). The advantage of SSSF is that it decouples magnitude and spectral shape part of sensor output and enables recovery of TOARAD. To test this method, the airborne visible/infrared imaging spectrometer-next generation data are used to simulate inputs to MSOC. SRF of ocean color monitor simulated MSOC. SSSF of TOARAD is estimated using SSSF of model-based path radiance spectrum of the pixel, which is similar in spectral shape. Methodology, developed using data from five stations, is validated with data from other five stations. The procedure is successfully repeated using SRFs of sea-viewing wide-field-of-view sensor. The recovered HS data are found to be consistent with the original spectra with very small deviations in spectral angle map (<0.012 rad) spectral information divergence (<5.8 × 10 − 5), mean percentage relative error (MPRE) of TOARAD (<0.7 % ), and MPRE of TOA water leaving radiance (<5.8 % ). This approach possibly opens up research for application of HS analysis on MSOC recovered spectra and for optimization of sensor configurations.

Comparison of Information Criteria for Detection of Useful Signals in Noisy Environments.

This paper considers the appearance of indications of useful acoustic signals in the signal/noise mixture. Various information characteristics (information entropy, Jensen-Shannon divergence, spectral information divergence and statistical complexity) are investigated in the context of solving this problem. Both time and frequency domains are studied for the calculation of information entropy. The effectiveness of statistical complexity is shown in comparison with other information metrics for different signal-to-noise ratios. Two different approaches for statistical complexity calculations are also compared. In addition, analytical formulas for complexity and disequilibrium are obtained using entropy variation in the case of signal spectral distribution. The connection between the statistical complexity criterion and the Neyman-Pearson approach for hypothesis testing is discussed. The effectiveness of the proposed approach is shown for different types of acoustic signals and noise models, including colored noises, and different signal-to-noise ratios, especially when the estimation of additional noise characteristics is impossible.

Efficacy of AVIRIS-NG data for species-specific recognition towards a comparative analysis by hyperspectral classifiers

Due to increasing anthropogenic pressure on the forest ecosystem, many plant species face a threat, and many of them are rapidly getting extinct. Proper identification of tree species and understanding their geographical distribution are prerequisites towards its conservation and developing management plans. Species mapping and distribution have typically had restrict due to limitations in spectral information. Recently, hyperspectral imageries have solved this problem, but more satisfactory resolution and exact identification by different methods are still in discussion. Here, we used airborne AVIRIS-NG hyperspectral data to identify-five tree species, namely Butea monosperma, Diospyros melanoxylon, Tectona grandis, Terminalia bellirica, and Terminalia tomentosa. In this study, Spectral Angle Mapper (SAM) and Spectral Information Divergence (SID) classifiers identify these tree species using spectral signatures with 92.44% and 74.55% overall accuracy; and 0.89 and 0.67 kappa coefficient, respectively. A comparative analysis is executed for both applied species identification algorithms, which shows importance of used identification techniques for a specific dataset and a relationship was also stabilized between overall accuracy of tree species and number of ground samples.

SI2FM: SID Isolation Double Forest Model for Hyperspectral Anomaly Detection

Hyperspectral image (HSI) anomaly detection (HSI-AD) has become a hot issue in hyperspectral information processing as a method for detecting undesired targets without a priori information against unknown background and target information, which can be better adapted to the needs of practical applications. However, the demanding detection environment with no prior and small targets, as well as the large data and high redundancy of HSI itself, make the study of HSI-AD very challenging. First, we propose an HSI-AD method based on the nonsubsampled shearlet transform (NSST) domain spectral information divergence isolation double forest (SI2FM) in this paper. Further, the method excavates the intrinsic deep correlation properties between NSST subband coefficients of HSI in two ways to provide synergistic constraints and guidance on the prediction of abnormal target coefficients. On the one hand, with the “difference band” as a guide, the global isolation forest and local isolation forest models are constructed based on the spectral information divergence (SID) attribute values of the difference band and the low-frequency and high-frequency subbands, and the anomaly scores are determined by evaluating the path lengths of the isolation binary tree nodes in the forest model to obtain a progressively optimized anomaly detection map. On the other hand, based on the relationship of NSST high-frequency subband coefficients of spatial-spectral dimensions, the three-dimensional forest structure is constructed to realize the co-optimization of multiple anomaly detection maps obtained from the isolation forest. Finally, the guidance of the difference band suppresses the background noise and anomaly interference to a certain extent, enhancing the separability of target and background. The two-branch collaborative optimization based on the NSST subband coefficient correlation mining of HSI enables the prediction of anomaly sample coefficients to be gradually improved from multiple perspectives, which effectively improves the accuracy of anomaly detection. The effectiveness of the algorithm is verified by comparing real hyperspectral datasets captured in four different scenes with eleven typical anomaly detection algorithms currently available.

A Review on different ML Techniques used for Disease Detection in Sugarcane Crop

Latest improvements in precision agriculture through machine learning, deep learning, remote sensing has helped to come up with different methods to detect crop diseases. One of the main reasons for yield loss of a crop is non detection of disease early in time. This paper reviews the various methods and techniques that can be used to detect diseases in sugarcane crop. Firstly, we provide a review on the different types of input data w.r.t imagery -RGB, multispectral and hyperspectral. Then we highlight the different techniques applied for disease detection-machine learning, deep learning, transfer learning and spectral information divergence. We also give an overview of the results achieved by using the different techniques.

Bearing fault diagnosis method based on comprehensive information divergence and improved BP-AdaBoost algorithm

Bearings are an important part of rotating systems, and the long-term safe operation of mechanical equipment utilizing bearings is closely related to the bearing state; so, bearing fault diagnosis is of great significance. In this paper, a bearing fault diagnosis method based on comprehensive information divergence and improved BP (back propagation)-AdaBoost algorithm is proposed. First, the time domain, frequency domain, and time-frequency domain features under different states of the bearing are extracted to form a feature set. Then, the importance of each feature in fault classification is obtained by using the comprehensive information divergence index, and the feature sequence with decreasing importance is obtained. Finally, the most important features are selected as the input of the improved BP-AdaBoost classification model to train and obtain the bearing fault classification model. The experimental results show that the method has a good identification effect on bearing faults, and the stability of the model is high.

Entropy of credibility distribution for intuitionistic fuzzy variable

&lt;abstract&gt; &lt;p&gt;This paper handles the new information entropy measure and divergence measure associated with intuitionistic fuzzy variables (IFVs). Based on credibility distribution and credibility measure of intuitionistic fuzzy variable, the credibility entropy formulas of discrete and continuous IFVs are proposed and some of their properties are investigated. The cross-entropy of intuitionistic fuzzy variable and its relationship with credibility entropy are then discussed. Finally, some numerical examples are given to illustrate the practicability of the presented credibility entropy and cross-entropy of intuitionistic fuzzy variable. Also, we make some comparative analysis on the credibility cross-entropy measure and some existing distance measures of IFVs in the pattern recognition problem.&lt;/p&gt; &lt;/abstract&gt;

Adaptive Reference-Related Graph Embedding for Hyperspectral Anomaly Detection

Graph embedding provides an effective way to reveal intrinsic feature of high-dimensional data on the foundation of preserving topological properties. Under the framework of graph embedding, the hyperspectral image can be represented by a weighted graph, where pixels and similarities among them are treated as vertices and edge weights, respectively. In this article, an adaptive reference-related graph embedding (ARGE) method is proposed to efficaciously obtain the low-dimensional feature and improve computational efficiency. The ARGE method is composed of two primary processes. The key to connecting these two processes is reference vertices set, which is the abstraction of graph topological features. Firstly, the reference vertices are adaptively selected through a three-step adaptive reference set selection (ARSS) algorithm. Secondly, the original high-dimensional graph is embedded as a low-dimensional graph through preserving the reference-related structure. Specifically, the pairwise similarities between vertices and reference vertices are preserved in embedding space. In addition, a new hybrid dissimilarity measure of Rao distance and spectral information divergence (RD-SID) is designed to depict the spectral difference between pixels. To evaluate the effectiveness of the proposed method, the obtained low-dimensional feature is fed into the anomaly detector to detect anomalous pixels. The experimental results on five real and one synthetic hyperspectral datasets demonstrate the superiority of the proposed ARGE method over the compared feature extraction methods.

IVIU-Net: Implicit Variable Iterative Unrolling Network for Hyperspectral Sparse Unmixing

At present, an emerging technique called the algorithm unrolling approach has attracted wide attention, because it is capable of developing efficient and interpretable layers to eliminate the black-box nature of deep learning (DL). In this paper, inspired by the sparse unmixing model, we propose a model-driven DL approach, namely, an implicit variable iterative unrolling network (IVIU-Net). First of all, the unmixing performance and adaptive ability of the model are enhanced by introducing learnable parameters into the sparse unmixing algorithm. Then, a specific spatial convolution module is integrated into the network to promote the smoothness of the latent abundance map. Finally, a comprehensive loss function with three terms such as average spectral angle distance, HSIs reconstruction error, and spectral information divergence, is presented to train the IVIU-Net in an unsupervised way. Compared to the unmixing results of most existing data-driven DL algorithms, our network has significant advantages in two folds: 1) it is able to achieve better stability instead of relying heavily on the endmember initialization results; 2) it has better interpretability and robustness in the unmixing procedure. Experimental results on synthetic and real data show that the proposed network outperforms the state-of-the-art in terms of better convergence, faster unmixing speed as well as better accuracy.

Crop-specific hyperspectral band selection method using limited ground-truth data

ABSTRACT Hyperspectral imaging plays a significant role in crop classification and aims to separate various crop pixels from the imagery. It aids the government in deciding agricultural policies. However, high spectral dimensions in hyperspectral data require high computing power and time. This paper presents a new band selection method based on spectral information divergence and correlation (), which selects optimum bands to classify the crops. The requires only single ground-truth pixels having the least spectral information divergence value to select the bands. This method requires not only minimum ground truth data but also gives reduced computational complexity. We have evaluated the proposed method on three hyperspectral datasets, AVIRIS-NG, Indian Pines and Salinas. We have used overall accuracy and kappa coefficient as performance parameters from the support vector machine and k-nearest neighbours classifiers. The experimental findings reveal that the proposed band selection method achieves maximum overall accuracy of about 84.79% for Indian Pines and 93.08% for Salinas dataset. The proposed methodology exhibits an improvement in overall accuracy when the number of selected bands ranges from 35 to 50 when compared with the other competitive band selection approaches.

Minimum information divergence of Q-functions for dynamic treatment resumes

This paper aims at presenting a new application of information geometry to reinforcement learning focusing on dynamic treatment resumes. In a standard framework of reinforcement learning, a Q-function is defined as the conditional expectation of a reward given a state and an action for a single-stage situation. We introduce an equivalence relation, called the policy equivalence, in the space of all the Q-functions. A class of information divergence is defined in the Q-function space for every stage. The main objective is to propose an estimator of the optimal policy function by a method of minimum information divergence based on a dataset of trajectories. In particular, we discuss the \(\gamma \)-power divergence that is shown to have an advantageous property such that the \(\gamma \)-power divergence between policy-equivalent Q-functions vanishes. This property essentially works to seek the optimal policy, which is discussed in a framework of a semiparametric model for the Q-function. The specific choices of power index \(\gamma \) give interesting relationships of the value function, and the geometric and harmonic means of the Q-function. A numerical experiment demonstrates the performance of the minimum \(\gamma \)-power divergence method in the context of dynamic treatment regimes.

Toward Robust River Plastic Detection: Combining Lab and Field‐Based Hyperspectral Imagery

AbstractPlastic pollution in aquatic ecosystems has increased dramatically in the last five decades, with strong impacts on human and aquatic life. Recent studies endorse the need for innovative approaches to monitor the presence, abundance, and types of plastic in these ecosystems. One approach gaining rapid traction is the use of multi‐ and hyperspectral cameras. However, most experiments using this approach were in controlled environments, making findings challenging to apply in natural environments. We present a method linking lab‐ and field‐based identification of macroplastics using hyperspectral data (1,150–1,675 nm). Experiments using riverbank‐harvested macroplastics were set up in a laboratory environment, and on the banks of the Rhine River. Representative pixel selections of eleven lab‐based images (n = 786,264 pixels) and two field‐based images (n = 40,289 pixels) were used to analyze the differences between these environments. Next, classifier algorithms such as support vector machines (SVM), spectral angle mapper (SAM) and spectral information divergence (SID) were applied, because of their robustness to varying light conditions and high accuracies in mapping spectral similarities. Our results showed that SAM classifiers are most robust in separating plastic pixels from background elements. By applying lab‐based data for plastic detection in field‐based images, user accuracies for plastics to up to 93.6% (n = 8,370 plastic pixels) were attained. This study provides key fundamental insights in linking lab‐based data to plastic detection in the field. With this paper we aim to contribute to the development of future spectral missions to detect and monitor plastic pollution in aquatic ecosystems.

Blockchain-based verifiable and dynamic multi-keyword ranked searchable encryption scheme in cloud computing

Rational miners in the blockchain may admit the validity of search results directly to conserve calculation overhead without executing the validation. Such phenomenon is known as the Verifier's Dilemma that the search results of the blockchain-based searchable encryption scheme would be claimed to have been verified but devoid of valid verification. Besides, the top-k query technique utilized by most existing searchable encryption schemes fails to filter the search results from the user demands during retrieval, which results in massive ineffective access lists with high complexity. Aiming at the two problems, we present a blockchain-based multi-keyword ranked searchable encryption scheme and design a fair payment protocol for multi-user scenarios. Our scheme may achieve public verifiability and user fairness by leveraging the TrueBit network, while the data owner (DO) can withdraw search privileges from the authorized data user (DU). Also, we extend the searchable encryption scheme based on inverted index to multi-DO/multi-DU scenarios, and the HashMap index is used to diminish the response time and space complexity. Moreover, the proposed scheme supports the update of index keywords and files dynamically. To enhance retrieval accuracy, we modify the information divergence algorithm in machine learning and utilize the monotonically weighted aggregation function, which improves retrieval accuracy to around 97%. Finally, Security analysis illustrates correctness and resilience against typical attacks to verify the robustness and utility of the proposed scheme.

The GR2D2 estimator for the precision matrices.

Biological networks are important for the analysis of human diseases, which summarize the regulatory interactions and other relationships between different molecules. Understanding and constructing networks for molecules, such as DNA, RNA and proteins, can help elucidate the mechanisms of complex biological systems. The Gaussian Graphical Models (GGMs) are popular tools for the estimation of biological networks. Nonetheless, reconstructing GGMs from high-dimensional datasets is still challenging. The current methods cannot handle the sparsity and high-dimensionality issues arising from datasets very well. Here, we developed a new GGM, called the GR2D2 (Graphical $R^2$-induced Dirichlet Decomposition) model, based on the R2D2 priors for linear models. Besides, we provided a data-augmented block Gibbs sampler algorithm. The R code is available at https://github.com/RavenGan/GR2D2. The GR2D2 estimator shows superior performance in estimating the precision matrices compared with the existing techniques in various simulation settings. When the true precision matrix is sparse and of high dimension, the GR2D2 provides the estimates with smallest information divergence from the underlying truth. We also compare the GR2D2 estimator with the graphical horseshoe estimator in five cancer RNA-seq gene expression datasets grouped by three cancer types. Our results show that GR2D2 successfully identifies common cancer pathways and cancer-specific pathways for each dataset.

Detection of DLBCL by pixel purity index and iterative linearly constrained minimum variance into hyperspectral imaging analysis.

It is unclear whether a hyperspectral imaging-based approach can facilitate the diagnosis of diffuse large B-cell lymphoma (DLBCL), and further investigation is required. In this study, the pixel purity index (PPI) coupled with iterative linearly constrained minimum variance (ILCMV) was used to bridge this gap. We retrospectively reviewed 22 pathological DLBCL specimens. Ten normal lymph node specimens were used as controls. PPI endmember extraction was performed to identify seed-training samples. ILCMV was then used to classify cell regions. The 3D receiver operating characteristic (ROC) showed that the spectral information divergence possessed superior ability to distinguish between normal and abnormal lymphoid cells owing to its stronger background suppression compared with the spectral angle mapper and mean square error methods. An automated cell hyperspectral image classification approach that combined the PPI and ILCMV was used to improve DLBCL diagnosis. This strategy intelligently resolved critical problems arising in unsupervised classification.

Evaluation of effectiveness of supervised classification algorithms in land cover classification using ASTER images-A case study from the Mankweng (Turfloop) Area and its environs, Limpopo Province, South Africa

The production of land cover maps using supervised classification algorithms is one of the most common applications of remote sensing. In this study, the effectiveness of supervised classification algorithms in land cover classification using ASTER data was evaluated in the Mankweng Area and its environs. The false colour composite image generated from combination of band 1, 2 and 3 in red, green and blue, respectively, was used to generate training classes for six land cover types (waterbody, forest, vegetation, Duiwelskloof leucogranite, Turfloop granite and built-up land). These were used to construct land cover maps using eight supervised classification algorithms: Maximum Likelihood, Minimum Distance, Support Vector Machine, Mahalanobis Distance, Parallelepiped, Neural Network, Spectral Angle Mapper and Spectral Information Divergence. To evaluate the effectiveness of the algorithms, the land cover maps were subjected to accuracy assessment to determine precision of the algorithms in accurately classifying the land cover types and level of confidence that can be attributed to the land cover maps. Most algorithms poorly performed in classifying spatially overlapping land cover types without abrupt boundaries. This indicates that the environmental conditions and distribution of land cover types can affect the performance of certain classification algorithms, and thus need to be considered prior to selection of algorithms. However, Support Vector Machine and Minimum Distance proved to be the two most effective algorithms as they provided better producer’s and user’s accuracy in the range of 80-100% for all land cover types, which represent good classification.

Mapping of gold-related alteration minerals and linear structures using ASTER data in the Giyani Greenstone Belt, South Africa

This paper focuses on the mapping of alteration minerals and linear structures associated with gold mineralization in the Giyani Greenstone Belt (GGB). Spectral Information Divergence (SID) and Linear Spectral Unmixing (LSU) classification algorithms were applied to the ASTER data using image extracted endmember spectra which match the spectral profiles of predominant alteration minerals (biotite and calcite) related to gold mineralization in the GGB. Directional convolution filters were also applied to the ASTER data to extract structural lineaments that may be related to gold mineralization. In addition, Fry analysis of known gold occurrences in the GGB was conducted to determine the major distribution patterns along which gold mineralization have occurred. LSU and SID results show several pixels classified as alteration minerals corresponding to known gold occurrences. SID results also show minerals overlapping into the gneissic rock, which is a rare host of gold mineralization in the study area. On the other hand, LSU results show high abundances of calcite and biotite generally confined within the mafic-ultramafic greenstone rocks, which have been hypothesized as the source of gold-mineralized fluids in the GGB. In general, LSU show distinct broad regions classified as alteration minerals corresponding to known gold occurrences that have been previously reported to host these alteration minerals. Directional convolution filters enabled the extraction of predominately NE-SW oriented linear structures, including the major shear zone which is associated with gold mineralization in the GGB. Fry analysis revealed three major distribution patterns: N-S, NE-SW, ENE-WSW along which gold mineralization have occurred. These patterns correspond to major lineaments associated with gold mineralization reported in the previous structural studies of the GGB.