Intrinsic Information Research Articles

Assessment of Risk and Social Impact on Groundwater Pollution by Nitrates. Implementation in the Gallocanta Groundwater Body (NE Spain)

Groundwater is an essential resource for humans concerning freshwater supply; therefore, preserving and protecting its quality is necessary. Risk assessment, based on hazard, intrinsic vulnerability information and mapping, may be considered as a key aspect of sustainable groundwater management. An approach has been made by combining the Nitrogen Input Hazard Index and the hydrogeological parameters considered in a modified DRASTIC method. A three-level classification has been used to determine the degree of risk, and the thresholds have been established following measurable criteria related to the potential nitrate concentration in groundwater. The second part of the study focused on estimating the socioeconomic impact of groundwater pollution by relating the degree of risk and social vulnerability to groundwater pollution. The method has been tested in the Gallocanta Groundwater Body (Spain). As a result, a risk map and an impact map are provided. The risk map shows that 67% of the study area can be classified as moderate and high-risk areas, corresponding to high hazard sources located in moderate and high vulnerability zones, whereas the impact of groundwater pollution is classified as moderate in the whole groundwater body. The proposed analysis allows comparison between aquifers in different areas and the results required by water authorities to implement control and mitigation measures.

Accelerated Adaptive Feature Balance Technique Based on TEMD for Hyperspectral Classification

Tridimensional empirical mode decomposition (TEMD) has been successfully employed as a powerful tool for hyperspectral classification. It achieves good performance to analyze nonlinear/non-stationary data and capture abstract features of hyperspectral images (HSIs). However, the major challenge is how to adequately exploit and balance decomposed edge-wise (EW) and trend-wise (TW) features. To address this issue, we propose an accelerated adaptive feature balance technique (A²FBT) based on TEMD. Due to complex discriminant information, A²FBT initially decomposes the HSI into varying oscillations adequately, including several tridimensional intrinsic mode functions (TIMFs) and one residual (RES). They contain high frequency EW and low frequency TW features, respectively. To further accelerate the decomposition, a k-d tree based search strategy is proposed for filter size selection. To bridge the gaps between the RES and all TIMFs, a novel adaptive feature balance strategy is presented by assigning adaptive trade-offs. We aim to balance multiple features adequately according to the intrinsic discriminant information. A combined metric based strategy is provided for trade-off calculation, measuring the mutual similarities between oscillations comprehensively. A²FBT pays more attention to these similarities, reinforcing the respective contributions of EW and TW features. Experiments on four typical hyperspectral datasets illustrate the effectiveness of A²FBT compared with several state-of-the-art techniques.

The LINC Complex Assists the Nuclear Import of Mechanosensitive Transcriptional Regulators.

Mechanical forces play pivotal roles in directing cell functions and fate. To elicit gene expression, either intrinsic or extrinsic mechanical information are transmitted into the nucleus beyond the nuclear envelope via at least two distinct pathways, possibly more. The first and well-known pathway utilizes the canonical nuclear transport of mechanoresponsive transcriptional regulators through the nuclear pore complex, which is an exclusive route for macromolecular trafficking between the cytoplasm and nucleoplasm. The second pathway depends on the linker of the nucleoskeleton and cytoskeleton (LINC) complex, which is a molecular bridge traversing the nuclear envelope between the cytoskeleton and nucleoskeleton. This protein complex is a central component in mechanotransduction at the nuclear envelope that transmits mechanical information from the cytoskeleton into the nucleus to influence the nuclear structure, nuclear stiffness, chromatin organization, and gene expression. Besides the mechanical force transducing function, recent increasing evidence shows that the LINC complex plays a role in controlling nucleocytoplasmic transport of mechanoresponsive transcriptional regulators. Here we discuss recent findings regarding the contribution of the LINC complex to the regulation of intracellular localization of the most-notable mechanosensitive transcriptional regulators, β-catenin, YAP, and TAZ.

Multi-Attribute Subspace Clustering via Auto-Weighted Tensor Nuclear Norm Minimization.

Self-expressiveness based subspace clustering methods have received wide attention for unsupervised learning tasks. However, most existing subspace clustering methods consider data features as a whole and then focus only on one single self-representation. These approaches ignore the intrinsic multi-attribute information embedded in the original data feature and result in one-attribute self-representation. This paper proposes a novel multi-attribute subspace clustering (MASC) model that understands data from multiple attributes. MASC simultaneously learns multiple subspace representations corresponding to each specific attribute by exploiting the intrinsic multi-attribute features drawn from original data. In order to better capture the high-order correlation among multi-attribute representations, we represent them as a tensor in low-rank structure and propose the auto-weighted tensor nuclear norm (AWTNN) as a superior low-rank tensor approximation. Especially, the non-convex AWTNN fully considers the difference between singular values through the implicit and adaptive weights splitting during the AWTNN optimization procedure. We further develop an efficient algorithm to optimize the non-convex and multi-block MASC model and establish the convergence guarantees. A more comprehensive subspace representation can be obtained via aggregating these multi-attribute representations, which can be used to construct a clustering-friendly affinity matrix. Extensive experiments on eight real-world databases reveal that the proposed MASC exhibits superior performance over other subspace clustering methods.

Cross-Modality Contrastive Learning for Hyperspectral Image Classification

Deep learning has attracted much attention in the field of hyperspectral image classification recently, due to its powerful representation and generalization abilities. Most of current deep learning models are trained in a supervised manner, which require large amounts of labeled samples to achieve state-of-the-art performance. Unfortunately, pixel-level labeling in hyperspectral imageries is difficult, time-consuming, and human-dependent. To address this issue, we propose an unsupervised feature learning model using multi-modal data, hyperspectral and LiDAR in particular. It takes advantage of the relationship between hyperspectral and LiDAR data to extract features, without using any label information. After that, we design a dual fine-tuning strategy to transfer the extracted features for hyperspectral image classification with small numbers of training samples. Such strategy is able to explore not only the semantic information but also the intrinsic structure information of training samples. In order to test the performance of our proposed model, we conduct comprehensive experiments on three hyperspectral and LiDAR datasets. Experimental results show that our proposed model can achieve better performance than several state-of-the-art deep learning models.

Locality-Aware Discriminative Subspace Learning for Image Classification

Projection learning is an effective and widely used technique for extracting discriminative features for pattern recognition and classification. In projection learning, it is essential to preserve the global and local structure of the data while extracting discriminative features. However, transforming the source data directly to a target i.e., the strict binary label matrix, using a projection matrix may result in the loss of some intrinsic information. We propose a locality-aware discriminative subspace learning (LADSL) method to address these limitations. In LADSL, the original data is transformed into a latent space instead of a restrictive label space. The latent space seamlessly integrates the original visual features and the class labels to improve the classification performance. The projection matrix and classification parameters are jointly optimized to supervise the discriminative subspace learning. Additionally, LADSL exploits the adaptive local structure to preserve the nearest neighbor relationship among the data samples while learning more projections to achieve superior classification performance. Experiments have been carried out on various data sets for face and object recognition, and the results achieved are compared with the state-of-the-art methods to validate the effectiveness of the proposed LADSL method.

Second harmonic scattering multipole analysis of ligand-decorated gold nanoparticles

Ligand decoration of noble metallic nanoparticles is often needed for some applications, such as biochemical sensing, catalysis and nanotechnology, and the understanding of its process is of great importance. The second harmonic scattering (SHS) technique with advantages of surface-sensitivity and label-free detection, provides intrinsic information for such a research. In this work, the second harmonic(SH) scattering patterns of two types of ligands (cetyltrimethylammonium chloride and L-cysteine) capped gold nanoparticles (GNPs) with the same radii are measured. Both the intensities and shapes of the SH scattering patterns are changed after the ligand exchange process. In order to explain the pattern changes, the analytic expressions of SH scattering are derived theoretically for a relatively large nanoparticle based on Dadap’s multipolar theory. Considering the derived relationship between the multipole (up to octopole) contributions and the power of the nanosphere radius, the effective size effect is introduced to express the SH scattering signal change for different ligand decorations and well explain the experimental results. This theory provides a new perspective of the SH scattering response to different capping ligands and offers a possible quantitative method to analyze interface physical chemistry for ligands on the surface of nanoparticles.

Infuse: A Data Quality Assessment Framework for the Completeness of Time Series Data Considering the Intrinsic Integrality of Intrinsic Information and Practical Usage

Infuse: A Data Quality Assessment Framework for the Completeness of Time Series Data Considering the Intrinsic Integrality of Intrinsic Information and Practical Usage

Fast Adaptive Local Subspace Learning With Regressive Regularization

<i>L,ineaT</i> Discriminant Analysis (LDA) has been widely used in supervised dimensionality reduction fields. How- ever, LDA is usually weak in tackling data with Non-Gaussian distribution due to its incapability of extracting the intrinsic structure of data. In order to learn the intrinsic information more effectively, some dimensionality reduction methods incorporate the adaptive full-connected graph into the algorithm frame, but the defect is that the calculation of each pairwise distance is very time-consuming. In this paper, we propose a novel fast adaptive local subspace learning with regressive regularization model to solve the supervised dimensional reduction problem. Firstly, the adaptive anchor point graph is used to capture local structure information, which can greatly reduce computation complexity. Secondly, by using regressive regularization, the samples from different classes can be better separated in the projected space and the workload of selecting the optimal reduced dimension is easier. Moreover, entropy regularization is used to derive more appropriate weights. Finally, extensive experiments are conducted on real world data sets to verify the superiority of our model.

Situated Information Flow between Food Commodity and Regional Equity Markets: An EEMD‐Based Transfer Entropy Analysis

The intrinsic information shared by financial assets provides a means of assessing their mutual linkages. In times of crisis, spillovers and information flow between markets increase, and this drives empirical investigations into the degree of connectedness between financial assets. In the context of commodity markets, empirical evidence about the mutual information shared and its influence on portfolio management is largely unknown. This study examines the situated information between the food commodities (cereals, dairy, food, meat, vegetable oil, and sugar) of the FAO and regional stock markets’ returns. From the ensemble empirical mode decomposition (EEMD)‐based Rényian transfer entropy analysis employed, we find significant bidirectional information flow between the food commodities and regional equity markets. Our findings divulge that the diversification potentials of food commodities rest in the long term, with sugar being a consistent diversifier across all investment horizons. The investment and policy implications of our findings are further discussed.

Biometric Identification From ECG Signals Using Fourier Decomposition and Machine Learning

This paper investigates biometric identification systems based on ECG signals and their intra-subject and intrasession validity. We develop an efficient algorithm using Fourier decomposition method (FDM) and phase transform. Firstly, the ECG signal is divided into frames consisting of one or more beats. These frames capture both inter-beat and intra-beat variations. They are decomposed into a set of Fourier intrinsic band functions using FDM and relevant features are extracted from them. In addition to this, phase transform has been employed to highlight the intrinsic information hidden in the phase of ECG signals. The effects of variations in size of the frame, the decomposition levels, and the number of sessions used for training and testing, on the performance of the algorithm are analyzed. Random forest, ensemble subspace discriminant and support vector machine are applied as classifiers to evaluate the performance on three datasets, MIT-BIH, ECG-ID and CYBHi, where MIT-BIH is acquired in an on-the-person setting and the other two are off-the-person datasets. The proposed method achieved identification accuracies of 91.07% for CYBHi dataset, 97.92% for MIT-BIH dataset and 98.45% for ECG-ID dataset, which are better than most of the existing state-of-the-art algorithms.

A Review of Intelligent Sensor-Based Systems for Pressure Ulcer Prevention

Pressure ulcers are a critical issue not only for patients, decreasing their quality of life, but also for healthcare professionals, contributing to burnout from continuous monitoring, with a consequent increase in healthcare costs. Due to the relevance of this problem, many hardware and software approaches have been proposed to ameliorate some aspects of pressure ulcer prevention and monitoring. In this article, we focus on reviewing solutions that use sensor-based data, possibly in combination with other intrinsic or extrinsic information, processed by some form of intelligent algorithm, to provide healthcare professionals with knowledge that improves the decision-making process when dealing with a patient at risk of developing pressure ulcers. We used a systematic approach to select 21 studies that were thoroughly reviewed and summarized, considering which sensors and algorithms were used, the most relevant data features, the recommendations provided, and the results obtained after deployment. This review allowed us not only to describe the state of the art regarding the previous items, but also to identify the three main stages where intelligent algorithms can bring meaningful improvement to pressure ulcer prevention and mitigation. Finally, as a result of this review and following discussion, we drew guidelines for a general architecture of an intelligent pressure ulcer prevention system.

Digital electronics using dielectric elastomer structures as transistors

Dielectric elastomers (DEs) are soft and stretchable structures that are typically used as actuators, sensors, and energy harvesters and can perform basic signal processing tasks. Thus, they can be used to create multi-functional and autonomous DE structures, with intrinsic information processing capabilities, that require fewer external components. This contribution introduces how to assemble electronic circuits with DEs, in a similar way to how transistors are employed in conventional electronics. The focus is on the design of digital circuits. At first, parallels between digital signal processing with DEs and with conventional transistors are shown. After describing the differences in the working conditions (e.g., working voltages) of the two structures, it is demonstrated that various design techniques, commonly adopted in conventional electronics, can be used to build DE electronics. The functioning is demonstrated by presenting alternative ways of designing NOR and XOR gates, reducing, in the latter case, the number of components required. Moreover, pass transistor logic is employed to realize a DE multiplexer. This work illustrates a consistent method to realize digital circuits with DEs, and it demonstrates how electronic design techniques can be adapted to work with DEs. It shows that DE circuits can be built starting from their conventional counterpart, obtaining improved devices.

Monitoring Weeder Robots and Anticipating Their Functioning by Using Advanced Topological Data Analysis.

The present paper aims at analyzing the topological content of the complex trajectories that weeder-autonomous robots follow in operation. We will prove that the topological descriptors of these trajectories are affected by the robot environment as well as by the robot state, with respect to maintenance operations. Most of existing methodologies enabling efficient diagnosis are based on the data analysis, and in particular on some statistical quantities derived from the data. The present work explores the use of an original approach that instead of analyzing quantities derived from the data, analyzes the “shape” of the data, that is, the time series topology based on the homology persistence. We will prove that this procedure is able to extract valuable patterns able to discriminate the trajectories that the robot follows depending on the particular patch in which it operates, as well as to differentiate the robot behavior before and after undergoing a maintenance operation. Even if it is a preliminary work, and it does not pretend to compare its performances with respect to other existing technologies, this work opens new perspectives in considering quite natural and simple descriptors based on the intrinsic information that data contains, with the aim of performing efficient diagnosis and prognosis.

Semi-supervised graph regularized nonnegative matrix factorization with local coordinate for image representation

Nonnegative matrix factorization(NMF) is a powerful image representation algorithm in pattern recognition and data mining. However, the traditional NMF does not utilize any label information, or fail to guarantee the sparse parts-based representation. In this paper, we put forward a semi-supervised local coordinate NMF (SLNMF) algorithm, which incorporate the available label information and the local coordinate constraint into NMF. Particularly, SLNMF makes the learned coefficients sparse by adding the coordinate constraint, and enhance the discriminative ability of different classes by using the label information constraint. Furthermore, in order to extract the geometric structure of the data space, we propose a new semi-supervised graph regularized NMF with local coordinate constraint (SGLNMF) method, which incorporates the graph regularization into SLNMF to enhance the discriminative abilities of data representations. SGLNMF not only reveals the intrinsic geometrical information of the data space, but also takes into account the local coordinate constraint and the label information. Clustering experiments on several standard image datasets demonstrate the effectiveness of our proposed SLNMF and SGLNMF methods compared to the state-of-the-art methods.

ProficiencyRank: Automatically ranking expertise in online collaborative social networks

Users of online collaborative social networks (e.g., StackExchange, Yahoo! Answers, and Yask, among others) are distributed across a continuous range of expertise, ranging from beginners to experts. However, only a minority of users contribute to their communities by posting questions and answers, while the majority (lurkers) only contribute by voting up or down on others’ posts. Since current methods for ranking expertise are based mainly on user submitted posts, their results are limited to that minority. We introduce ProficiencyRank, a wrapping method on top of PageRank that leverages voting information to determine user expertise for both contributors and lurkers. We validated our method to measure the proficiency of English Language Learners in the Yask social network. The new data set is naturally annotated with self-assessments of proficiency given by the users themselves, providing ground truth for all users. Experimental validation showed that ProficiencyRank produces a meaningful ranking of users that overcame various baselines based on intrinsic and extrinsic information. We conclude that this technology can benefit these communities by expanding the coverage of user expertise/reputation measurement and providing a re-ranking method for the expert finding task.

Uncertainty instructed multi-granularity decision for large-scale hierarchical classification

Hierarchical classification identifies a sample from the root node to a leaf node along the hierarchical structures of labels. It is often difficult to perform leaf-node prediction owing to ambiguous or incomplete information In such scenarios, a multi-granularity decision needs to be designed to stop the sample at a coarse-grained node rather than going rashly to a wrong leaf node. Conventionally, the probabilities of assigning the sample to its child nodes are regarded as evidence to decide whether to let the sample stop or go. However, the fact that the output of an unreliable classifier cannot be used to appropriately form the basis of decision making, especially with the existence of data uncertainties, is overlooked by existing methods. Therefore, we model the multi-granularity decision problem from an uncertainty perspective and consider that the uncertainties of multi-granularity decision emanate from the prediction of the classifier and the intrinsic information of the data. Inspired by the theory of fuzzy rough sets, a new measure is proposed to describe the intrinsic uncertainty in data. Integrating with the prediction uncertainty of the classifier, the hierarchical structure is used to design an effective optimization method that ensures proper multi-granularity decisions. Experiments show that the proposed algorithm achieves state-of-the-art performance.

Research on compound fault diagnosis of rolling bearing based on intrinsic time scale decomposition and information fusion

In view of the difficulty to effectively extract compound faults of rolling bearing from aero-engine and precisely identify their types, the paper has proposed a method integrating signal separation algorithm and information fusion. Firstly, the method decomposes the vibration acceleration signals collected by sensors from different positions at the same moment based on intrinsic time scale decomposition algorithm. Secondly, cross correlation analysis is given to the proper rotation component (PRC) of the same layer, which are obtained after decomposition and correspond to the sensors from different positions and cross-correlation function is introduced to embody information fusion. Thirdly, signals are reconstructed according to cross-correlation function of each PRC. Finally, based on the frequency spectrum of reconstructed signal, extract the characteristics of rolling bearing and identify the type of faults under different sensor combinations and multiple compound fault types. The result shows, the proposed method can effectively extract the characteristics of compound faults of bearing and precisely identify the type of faults under different sensor combinations and multiple compound fault types of rolling bearing.

Finding most informative common ancestor in cross-ontological semantic similarity assessment: An intrinsic information content-based approach

Semantic Similarity (SS) has become a long-standing research domain in artificial intelligence and cognitive science for measuring the strength of the semantic relationship between entities (e.g., words, documents). Several ontology-based SS measures have been proposed in the recent time due to their ability of mimicking the cognitive process of humans. Among them, intrinsic information content (IC) based approaches have shown a significant correlation with human assessment. The design principle of the existing intrinsic IC-based SS measures constrain themselves to be applicable in a single ontology. However, such SS measures can be leveraged within two ontologies with the help of identifying the most informative common ancestors (MICA) across the ontologies. Existing IC-based MICA identification algorithms follow string matching of the labels of the concepts. In this paper, we propose a novel intrinsic IC-based MICA finding algorithm that exploits two domain-ontologies for finding SS without using string matching of the labels. The proposed approach has been evaluated using a widely used benchmark dataset of medical terms. The experimental results show that the proposed IC-based approach can be a stepping stone to a new direction in the process of finding MICA over two ontologies.

Anatomically constrained squeeze-and-excitation graph attention network for cortical surface parcellation

In order to understand the organizational structures of healthy cerebral cortex and the abnormalities in neurological and psychiatric diseases, it is significant to parcellate the cortical surface. The cortical surface, however, is a highly folded complex geometric structure which challenges automatic cortical surface parcellation. Nowadays, the parcellation methods of cerebral cortex are mostly based on geometric simplification, i.e., iteratively inflating and mapping the cortical surface to a spherical surface for processing, which is time-consuming and cannot make full use of the intrinsic structural information of the original cortical surface. In this study, we proposed an anatomically constrained squeeze-and-excitation graph attention network (ASEGAT) for an end-to-end brain cortical surface parcellation on the original cortical surface manifold. The ASEGAT is formed by two graph attention modules and a squeeze-and-excitation module that incorporate self-attention and head attention for rendering features of each node. Furthermore, we designed an anatomic constraint loss to introduce the anatomical priori of regional adjacency relationships, which could improve the consistency of region labeling. We evaluated our model on a public dataset of 100 manually labeled brain surfaces. Compared with several advanced methods, the results showed that our proposed approach achieved state-of-the-art performance, obtaining an accuracy of 90.65% and a dice score of 89.00%.