Representation Of Structural Information Research Articles

SimRE: Simple contrastive learning with soft logical rule for knowledge graph embedding

Knowledge graphs serve as a pivotal framework for the structured representation of information regarding entities and relations. However, in the real world, these knowledge graphs are often incomplete and harboring missing facts. Knowledge graph completion (KGC) has emerged as a central research focus, entailing the automated prediction of these missing facts and garnering substantial scholarly attention in recent years. Text-based knowledge graph embedding methods have demonstrated considerable potential for tackling the challenges associated with KGC by employing pre-trained language models. However, their limitation lies in the lack of logical features, which constrains the efficacy of capturing intricate patterns within knowledge graphs. This paper proposed SimRE, a straightforward contrastive learning framework augmented with soft logic rules. SimRE introduces a self-supervised framework that leverages the input rule bodies to predict the corresponding rule heads through a contrastive objective. We introduced two rule sampling techniques to enhance the efficiency and accuracy of the model: in-batch rule negatives and pre-batch rule negatives. SimRE employs a simple method for integrating logical features with the text-based model. The experimental results on benchmark datasets demonstrate that the proposed approach outperforms state-of-the-art methods.

Knowledge Representation Learning Method Based on Semantic Enhancement of External Information

Background: Knowledge representation learning aims at mapping entity and relational data in knowledge graphs to a low-dimensional space in the form of vectors. The existing work has mainly focused on structured information representation of triples or introducing only one additional kind of information, which has large limitations and reduces the representation efficiency. Objective: This study aims to combine entity description information and textual relationship description information with triadic structure information, and then use the linear mapping method to linearly transform the structure vector and text vector to obtain the joint representation vector. Methods: A knowledge representation learning (DRKRL) model that fuses external information for semantic enhancement is proposed, which combines entity descriptions and textual relations with a triadic structure. For entity descriptions, a vector representation is performed using a bi-directional long- and short-term memory network (Bi-LSTM) model and an attention mechanism. For the textual relations, a convolutional neural network is used to vectorially encode the relations between entities, and then an attention mechanism is used to obtain valuable information as complementary information to the triad. Results: Link prediction and triadic group classification experiments were conducted on the FB15K, FB15K-237, WN18, WN18RR, and NELL-995 datasets. Theoretical analysis and experimental results show that the DRKRL model proposed in this paper has higher accuracy and efficiency compared with existing models. Conclusion: Combining entity description information and textual relationship description information with triadic structure information can make the model have better performance and effectively improve the knowledge representation learning ability.

Semantic alignment of ontologies meaningful categories with the generalization of descriptive structures

The presented work addresses the issue of semantic alignment of ontology components with a generalized structured corpus. The field of research refers to the sphere of determining the features of trust in artificial intelligence. An alignment method is proposed at the level of semantic components of the general alignment system. The method is a component of a broader alignment system and compares entities at the level of meaningful correspondence. Moreover, only the alignment entities’ descriptive content is considered within the proposed technique. Descriptive contents can be represented by variously named id and semantic relations. The method defines a fundamental ontol- ogy and a specific alignment structure. Semantic correspondence in the form of information scope is formed from the alignment structure. In this way, an entity is formed on the side of the alignment structure, which would correspond in the best meaningful way to the entity from the ontology in terms of meaningful descriptiveness. Meaningful descriptiveness is the filling of information scope. Information scopes are formed as a final form of generalization and can consist of entities, a set of entities, and their partial union. In turn, entities are a generalization of properties that are located at a lower level of the hierarchy and, in turn, are a combination of descriptors. Descriptors are a fundamental element of generalization that represent principal content. Descriptors can define atomic content within a knowledge base and represent only a particular aspect of the content. Thus, the element of meaningfulness is not self-sufficient and can manifest as separate meaningfulness in the form of a property, as a minimal representation of the meaningfulness of an alignment. Descriptors can also supplement the content at the level of information frameworks, entities, and properties. The essence of the alignment in the form of information scope cannot be represented as a descriptor or their combination. It happens because the descriptive descriptor does not represent the content in the completed form of the correspondence unit. The minimum structure of representation of information scope is in the form of properties. This form of organization of establishing the correspondence of the semantic level of alignment allows you to structure and formalize the information content for areas with a complex form of semantic mapping. The hierarchical representation of the generalization not only allows simplifying the formalization of semantic alignment but also enables the formation of information entities with the possibility of discretization of content at the level of descriptors. In turn, descriptors can expand meaningfulness at an arbitrary level of the generalization hierarchy. This provides quantization of informational content and flexibility of the alignment system with discretization at the level of descriptors. The proposed method is used to formalize the semantic alignment of ontology entities and areas of structured representation of information.

Aspect of the Knowledge Representation Framework (KR Framework) for Offering the Basis for a Number of Research Activities in the Caisor

The representation of knowledge refers to the technical challenge of capturing human understanding and thinking in a conceptual framework that enables computer networks to handle information. This research study is aimed to critically analyse the impact of the knowledge representation framework on the efficiency level of CAISOR activity. The research study has provided a sustainable viewpoint about the way KRF presents visualization data that is easy to understand for the human as well as the CAISOR agenda. A wide variety of different initiatives are founded on the CAISOR agenda through the Knowledge Representation Framework. The KR model covers many features of structured information representation ranging from simple facts to sophisticated formulations and programs. In addition, the research study has followed a secondary qualitative data collection method to collect the secondary sources of data regarding the research topic. Keyword : CAISOR, framework, AI system, Knowledge representation framework.

Report on the Workshop on Personal Knowledge Graphs (PKG 2021) at AKBC 2021

The term personal knowledge graph (PKG) has been broadly used to refer to structured representation of information about a given user, primarily in the form of entities that are personally related to the user. The potential of personal knowledge graphs as a means of managing and organizing personal data, as well as a source of background knowledge for personalizing downstream services, has recently gained increasing attention from researchers in multiple fields, including that of Information Retrieval, Natural Language Processing, and the Semantic Web. The goal of the PKG'21 workshop was to create a forum for researchers and practitioners from diverse areas to present and discuss methods, tools, techniques, and experiences related to the construction and use of personal knowledge graphs, identify open questions, and create a shared research agenda. It successfully brought about a diverse workshop program, comprising an invited keynote, paper presentations, and breakout discussions, as a half-day event at the 3rd Automated Knowledge Base Construction (AKBC'21) conference. The workshop demonstrated that while the concept and research field of personal knowledge graphs is still in its early stages, there are many promising avenues of future development and research that already, and independently, have attracted the interest of several different communities. Date: October 8, 2021. Website: https://pkgs.ws.

Theta rhythm supports hippocampus-dependent integrative encoding in schematic/semantic memory networks

Integrating new information into existing schematic/semantic structures of knowledge is the basis of learning in our everyday life as it enables structured representation of information and goal-directed behaviour in an ever-changing environment. However, how schematic/semantic mnemonic structures aid the integration of novel elements remains poorly understood. Here, we showed that the ability to integrate novel picture information into learned structures of picture associations that overlapped by the same picture scene (i.e., simple network) or by a conceptually related picture scene (i.e., schematic/semantic network) is hippocampus-dependent, as patients with lesions at the medial temporal lobe (including the hippocampus) were impaired in inferring novel relations between pictures within these memory networks. We also found more persistent and widespread scalp EEG theta oscillations (3–5 Hz) while participants integrated novel pictures into schematic/semantic memory networks than into simple networks. On the other hand, greater neural similarity was observed between EEG patterns elicited by novel and related events within simple networks than between novel and related events within schematic/semantic memory networks. These findings have important implications for our understanding of the neural mechanisms that support the development and organization of structures of knowledge.

A local structural information representation method for image quality assessment

Image is a typical example of visual data, and its quality inevitably affects its application. Hence, measuring image quality accurately is a beneficial task. In practical application, there are different image types e.g. natural image and screen content image (SCIs). And the distortion types contained in images are various. Most image quality assessment (IQA) methods concentrate on a single image type with limited distortion types. In this paper, we present a no-reference IQA method which can accurately measure the quality for both natural image and SCI, and is robust for various distortion types. Human visual system is sensitive to the changes in image structural information which are usually caused by image quality degradation. Therefore, the new method employs local structural information representation for IQA. We first analyze the gray-scale fluctuation of each pixel in four detection directions to obtain four gray-scale fluctuation maps (GFMs) and one gray-scale fluctuation direction map (GFD). And then, the structural features extracted from GFMs and GFD are used for representing local structural information. Finally, the mapping function from the features to image subjective scores is trained by support vector regression (SVR). The experimental results on the public databases demonstrate that SVR is suitable for IQA and the proposed method can accurately predict the quality of both natural images and SCIs with various distortion types.

A Model for Structured Information Representation in Neural Networks of the Brain.

Humans can reason at an abstract level and structure information into abstract categories, but the underlying neural processes have remained unknown. Recent experimental data provide the hint that this is likely to involve specific subareas of the brain from which structural information can be decoded. Based on this data, we introduce the concept of assembly projections, a general principle for attaching structural information to content in generic networks of spiking neurons. According to the assembly projections principle, structure-encoding assemblies emerge and are dynamically attached to content representations through Hebbian plasticity mechanisms. This model provides the basis for explaining a number of experimental data and provides a basis for modeling abstract computational operations of the brain.

A Review of Geospatial Semantic Information Modeling and Elicitation Approaches

The present paper provides a review of two research topics that are central to geospatial semantics: information modeling and elicitation. The first topic deals with the development of ontologies at different levels of generality and formality, tailored to various needs and uses. The second topic involves a set of processes that aim to draw out latent knowledge from unstructured or semi-structured content: semantic-based extraction, enrichment, search, and analysis. These processes focus on eliciting a structured representation of information in various forms such as: semantic metadata, links to ontology concepts, a collection of topics, etc. The paper reviews the progress made over the last five years in these two very active areas of research. It discusses the problems and the challenges faced, highlights the types of semantic information formalized and extracted, as well as the methodologies and tools used, and identifies directions for future research.

MVCLN: Multi-View Convolutional LSTM Network for Cross-Media 3D Shape Recognition

Cross-media 3D model recognition is an important and challenging task in computer vision, which can be utilized in many applications such as landmark detection, image set classification, etc. In recent years, with the development of deep learning, many approaches have been proposed to handle the 3D model recognition problem. However, all of these methods focus on the structure information representation and the multi-view information fusion, and ignore the spatial and temporal information. So that it is not suitable for the cross-media 3D model recognition. In this paper, we utilize the sequence views to represent each 3D model and propose a novel Multi-view Convolutional LSTM Network (MVCLN), which utilizes the LSTM structure to extract temporal information and applies the convolutional operation to extract spatial information. More especially, the spatial and temporal information both are considered during the training process, which can effectively utilize the differences between the view's spatial information to improve the final performance. Meanwhile, we also introduce the classic attention model to define the weight of each view, which can reduce the redundant information of view's spatial information in the information fusion step. We evaluate the proposed method on the ModelNet40 for 3D model classification and retrieval task. We also construct a dataset utilizing the overlap categories of MV-RED, ShapenetCore and ModelNet to demonstrate the effectiveness of our approach for the cross-media 3D model recognition. Experimental results and comparisons with the state-of-the-art methods demonstrate that our framework can achieve superior performance.

A discrete dynamics approach to sparse calculation and applied in ontology science

ABSTRACT In the era of big data, with the increase of data processing information and the increase of data complexity, higher requirements are put on the tools and algorithms of data processing. As a tool for structured information representation, ontology has been used in engineering fields such as chemistry, biology, pharmacy, and materials. As a dynamic structure, the increasing concepts contributes to a gradual increase of a single ontology. In order to solve the problem of computational complexity decreasing in the procedure of similarity calculating, the techniques of dimensionality reduction and sparse computing are applied to ontology learning. This article presents discrete dynamics approach showing several tricks on applying the sparse computing method to ontology learning, and verify its efficiency through experiments.

New colour morphological operators on hypergraph

New colour morphological operators on hypergraph are proposed to avoid the loss of details caused by fixed structure element effectively. Hypergraph, the most general structure in discrete mathematics, is also a subset of a finite set. Being a structured representation of information, the ordinary image can be transformed into a hypergraph model, which can integrate hypergraph theory with mathematical morphology theory. As hypergraphs have good performance in structuring information, first of all, this study designs a reasonable algorithm for turning colour images into hypergraph space. Then based on hypergraph theory and colour distance, new colour morphological operators on hypergraph are defined. Experiments show that using the new operator can avoid the loss of detail information and the destruction of colour topology, which improve the precision of image processing.

Understanding Sustainability Data through Unit Manufacturing Process Representations: A Case Study on Stone Production

Efficiency of natural stone production processes in quarries directly affects the economic output and environmental performances, such as production lead times and energy consumptions. Knowledge on stone production processes is crucial in making responsible decisions in this business. Having a structured representation of information characterizing the stone production processes will support stakeholders in better assessing production resources in terms of sustainability and productivity. Value stream mapping can provide an overview and guidance for sustainability performance evaluation, but its application is limited. The challenges arise when trying to specifically map and relate sustainability data between processes e.g., variability in lead time and CO2 emissions. Manufacturing process characterization standards currently being developed by ASTM International manifest the potential to not only fill this gap but also to provide opportunities to characterize and compose manufacturing processes with relevant environmental information and description. This paper shows the application and lessons learned from deploying one such effort towards standardization.

Automatic Generation of Design Scheme Based on Improved Segmentation Genetic Algorithm

Research on composition and quantitative representation of the function unit structural information, seeking the combination process effectively, is the key technology to generate product design schemes. Full life cycle assessment properties of structure is introduced into expression of design scheme. The gene model of life cycle assessment properties of structure is established, and the variable length coding is converted to equal length coding to realize the quantitative representation of structure information. The fitness function is established for life cycle assessment of structure with Analytic Hierarchy Process. The improved segmentation genetic algorithm is studied. The gene sequence of design scheme is segmented. Genetic operators such as across and mutate is designed for structure information the segmented gene fragment. Life cycle assessment gene of structure as attribute does not participate in the genetic operation. Design schemes automatic generation is achieved based on improved segmented genetic operators, reflecting life cycle assessment properties of design schemes.

Scheme Automatic Generation Based on Full Life Cycle Assessment Gene Model of Structure

Considering the inheritance and hereditary of product structure life cycle assessment, full life cycle assessment properties of structure is introduced into expression of design scheme. Scheme evolution design is presented based on gene model of full life cycle assessment properties of structure. The gene model of life cycle assessment properties of structure is established. The variable length coding is converted to equal length coding to realize the quantitative representation of structure information. The fitness function is established for life cycle assessment of structure by Analytic Hierarchy Process. The genetic operators are designed. Scheme evolution design is realized based on gene model of life cycle assessment of structure, reflecting life cycle assessment properties of design schemes, improving the efficiency of product design generation. The evolution design example of multi-rope diamond wire saw verifies the feasibility of the imposed method.

Biometric identification based on the eye movements and graph matching techniques

The last few years a growing research interest has aroused in the field of biometrics, concerning the use of brain dependent characteristics generally known as behavioral features. Human eyes, often referred as the gates to the soul, can possibly comprise a rich source of idiosyncratic information which may be used for the recognition of an individual’s identity. In this paper an innovative experiment and a novel processing approach for the human eye movements is implemented, ultimately aiming at the biometric segregation of individual persons. In our experiment, the subjects observe face images while their eye movements are being monitored, providing information about each participant’s attention spots. The implemented method treats eye trajectories as 2-D distributions of points on the image plane. The efficiency of graph objects in the representation of structural information motivated us on the utilization of a non-parametric multivariate graph-based measure for the comparison of eye movement signals, yielding promising results at the task of identification according to behavioral characteristics of an individual.

Face Super-resolution based-on Non-negative Matrix Factorization

Principal Component Analysis (PCA) is a classical method which is commonly used for human face images representation in face super-resolution. But the features extracted by PCA are holistic and difficult to have semantic interpretation. In order to synthesize a high-resolution face image with structural details, we propose a face super-resolution algorithm based on non-negative matrix factorization (NMF). This algorithm uses the NMF to obtain structural information representation of face images, and then the target image is regularized by Markov random fields, with maximum a posteriori probability approach. Finally, the steepest descent method is used to optimize NMF coefficient of high-resolution image. Experiment results demonstrate that the NMF-based face super-resolution algorithm performs better than PCA-based algorithms, in the subjective and objective quality.

Robust object tracking using a spatial pyramid heat kernel structural information representation

In this paper, we propose an object tracking framework based on a spatial pyramid heat kernel structural information representation. In the tracking framework, we take advantage of heat kernel structural information (HKSI) matrices to represent object appearance, because HKSI matrices perform well in characterizing the edge flow (or structural) information on the object appearance graph. To further capture the multi-level spatial layout information of the HKSI matrices, a spatial pyramid division strategy is adopted. Then, multi-scale HKSI subspace analysis is applied to each spatial pyramid grid at different levels. As a result, several grid-specific HKSI subspace models are obtained and updated by the incremental PCA algorithm. Based on the multi-scale grid-specific HKSI subspace models, we propose a tracking framework using a particle filter to propagate sample distributions over time. Theoretical analysis and experimental evaluations demonstrate the effectiveness of the proposed tracking framework.

Automatic prediction of catalytic residues by modeling residue structural neighborhood.

BackgroundPrediction of catalytic residues is a major step in characterizing the function of enzymes. In its simpler formulation, the problem can be cast into a binary classification task at the residue level, by predicting whether the residue is directly involved in the catalytic process. The task is quite hard also when structural information is available, due to the rather wide range of roles a functional residue can play and to the large imbalance between the number of catalytic and non-catalytic residues.ResultsWe developed an effective representation of structural information by modeling spherical regions around candidate residues, and extracting statistics on the properties of their content such as physico-chemical properties, atomic density, flexibility, presence of water molecules. We trained an SVM classifier combining our features with sequence-based information and previously developed 3D features, and compared its performance with the most recent state-of-the-art approaches on different benchmark datasets. We further analyzed the discriminant power of the information provided by the presence of heterogens in the residue neighborhood.ConclusionsOur structure-based method achieves consistent improvements on all tested datasets over both sequence-based and structure-based state-of-the-art approaches. Structural neighborhood information is shown to be responsible for such results, and predicting the presence of nearby heterogens seems to be a promising direction for further improvements.

Prediction of HPLC Retention Index Using Artificial Neural Networks and IGroup E-State Indices

A back-propagation artificial neural network (ANN) was used to create a 10-fold leave-10%-out cross-validated ensemble model of high performance liquid chromatography retention index (HPLC-RI) for a data set of 498 diverse druglike compounds. A 10-fold multiple linear regression (MLR) ensemble model of the same data was developed for comparison. Molecular structure was described using IGroup E-state indices, a novel set of structure-information representation (SIR) descriptors, along with molecular connectivity chi and kappa indices and other SIR descriptors previously reported. The same input descriptors were used to develop models by both learning algorithms. The MLR model yielded marginally acceptable statistics with training correlation r(2) = 0.65, mean absolute error (MAE) = 83 RI units. External validation of 104 compounds not used for model development yielded validation v(2) = 0.49 and MAE = 73 RI units. The distribution of residuals for the fit and validate data sets suggest a nonlinear relationship between retention index and molecular structure as described by the SIR indices. Not surprisingly, the ANN model was significantly more accurate for both training and validation with training set r(2) = 0.93, MAE = 30 RI units and validation v(2) = 0.84, MAE = 41 RI units. For the ANN model, a total of 91% of validation predictions were within 100 RI units of the experimental value.