Data Structure For Representation Research Articles

Factorizers for distributed sparse block codes

Distributed sparse block codes (SBCs) exhibit compact representations for encoding and manipulating symbolic data structures using fixed-width vectors. One major challenge however is to disentangle, or factorize, the distributed representation of data structures into their constituent elements without having to search through all possible combinations. This factorization becomes more challenging when SBCs vectors are noisy due to perceptual uncertainty and approximations made by modern neural networks to generate the query SBCs vectors. To address these challenges, we first propose a fast and highly accurate method for factorizing a more flexible and hence generalized form of SBCs, dubbed GSBCs. Our iterative factorizer introduces a threshold-based nonlinear activation, conditional random sampling, and an ℓ ∞ -based similarity metric. Its random sampling mechanism, in combination with the search in superposition, allows us to analytically determine the expected number of decoding iterations, which matches the empirical observations up to the GSBC’s bundling capacity. Secondly, the proposed factorizer maintains a high accuracy when queried by noisy product vectors generated using deep convolutional neural networks (CNNs). This facilitates its application in replacing the large fully connected layer (FCL) in CNNs, whereby C trainable class vectors, or attribute combinations, can be implicitly represented by our factorizer having F-factor codebooks, each with C F fixed codevectors. We provide a methodology to flexibly integrate our factorizer in the classification layer of CNNs with a novel loss function. With this integration, the convolutional layers can generate a noisy product vector that our factorizer can still decode, whereby the decoded factors can have different interpretations based on downstream tasks. We demonstrate the feasibility of our method on four deep CNN architectures over CIFAR-100, ImageNet-1K, and RAVEN datasets. In all use cases, the number of parameters and operations are notably reduced compared to the FCL.

Leveraging Generative AI to Accelerate Biocuration of Medical Actions for Rare Disease.

Structured representations of clinical data can support computational analysis of individuals and cohorts, and ontologies representing disease entities and phenotypic abnormalities are now commonly used for translational research. The Medical Action Ontology (MAxO) provides a computational representation of treatments and other actions taken for the clinical management of patients. Currently, manual biocuration is used to assign MAxO terms to rare diseases, enabling clinical management of rare diseases to be described computationally for use in clinical decision support and mechanism discovery. However, it is challenging to scale manual curation to comprehensively capture information about medical actions for the more than 10,000 rare diseases. We present AutoMAxO, a semi-automated workflow that leverages Large Language Models (LLMs) to streamline MAxO biocuration for rare diseases. AutoMAxO first uses LLMs to retrieve candidate curations from abstracts of relevant publications. Next, the candidate curations are matched to ontology terms from MAxO, Human Phenotype Ontology (HPO), and MONDO disease ontology via a combination of LLMs and post-processing techniques. Finally, the matched terms are presented in a structured form to a human curator for approval. We used this approach to process 4,918 unique medical abstracts and identified annotations for 21 rare genetic diseases, we extracted 18,631 candidate disease-treatment curations, 538 of which were confirmed and transferred to the MAxO annotation dataset. The results of this project underscore the potential of generative AI to accelerate precision medicine by enabling a robust and comprehensive curation of the primary literature to represent information about diseases and procedures in a structured fashion. Although we focused on MAxO in this project, similar approaches could be taken for other biomedical curation tasks.

Flexible and reversible conversion between extensible records and overloading constraints for ML

Most ML-like functional languages provide records and overloading as unrelated features. Records not only represent data structures, but are also used to implement dictionary passing, whereas overloading produces type constraints that are basically dictionaries subject to compiler-driven dispatching. In this paper we explore how records and overloading constraints can be converted one into the other, allowing the programmer to switch between the two at a very reasonable cost in terms of syntactic overhead. To achieve this we introduce two language constructs, namely inject and eject, performing a type-driven syntactic transformation. The former literally injects constraints into the type and produces a function adding an extra record argument. The latter does the opposite, ejecting a record argument from a function and turning fields into type constraints. The conversion is reversible and can be restricted to a subset of symbols, granting additional control to the programmer. Although what we call inject has already been proposed in literature, making it a language operator and coupling it with its reverse counterpart represent a novel design. The goal is to allow the programmer to switch from a dictionary-passing style to compiler-assisted constraint resolution, and vice versa, enabling reuse between libraries that otherwise would not interoperate.

From Data to Action: A Graph-Based Approach for Decision Support in Civil Protection Operations Planning

In the face of increasing frequency and severity of crises such as natural disasters, pandemics, and geopolitical conflicts, civil protection organizations are crucial for recovery and support for affected populations. However, the efficiency and effectiveness of these organizations in crisis response are often hindered by the manual generation of operation plans, characterized by cognitive overload and limited analytic overview. Existing systems focus on detecting crises or post-crisis analysis, overlooking proactive planning. We present GRETA, a graph-based operational planning approach utilizing semantic historical data for better decision support. GRETA uses Operational Scenario Patterns to model operations, mapping them onto a knowledge graph in JSON-LD format, thus creating a structured representation of past data to improve future crisis response planning. We tested GRETA with Germany's Federal Agency for Technical Relief, analyzing over 157,450 historic operations from 2012-2022. Results show GRETA enhances plan efficiency, accuracy, and comprehensiveness, aiding especially inexperienced planners.

Handling Unstructured Image using Generative AI and Dev-Ops

Abstract: This study explores the application of generative artificial intelligence (AI) to convert unstructured medical image data into structured formats. Medical imaging is vital for diagnosis and treatment, yet handling the large volume of unstructured data presents challenges. Utilizing generative AI, particularly convolutional neural networks (CNNs), enables the transformation of raw medical images into structured data representations. By integrating AI techniques, this approach enhances the accessibility and interoperability of medical imaging data, providing valuable insights for healthcare professionals. The proposed methodology aims to streamline the process, optimizing scalability and reproducibility without extensive reliance on DevOps practices. This research signifies a significant step towards leveraging AI for efficient utilization of medical imaging data in healthcare applications

Enhancing the Vietoris–Rips simplicial complex for topological data analysis: applications in cancer gene expression datasets

AbstractThe aim of this study is to enhance the extraction of informative features from complex data through the application of topological data analysis (TDA) using novel topological overlapping measures. Topological data analysis has emerged as a promising methodology for extracting meaningful insights from complex datasets. Existing approaches in TDA often involve extrapolating data points using distance correlation measures, which subsequently constrain downstream predictive tasks. Our objective is to improve the construction of the Vietoris–Rips simplicial complex by introducing topological overlapping measures. These measures take into account the interplay of direct connection strengths and shared neighbours, leading to the identification of persistent topological features. We propose the utilisation of topological overlapping measures to optimise the construction of the Vietoris–Rips simplicial complex, offering a more refined representation of complex data structures. The application of topological overlapping measures results in the identification of plentiful persistent topological features. This enhancement contributes to an improvement of up to 20% in cancer phenotype prediction across different cancer types. Our study demonstrates the effectiveness of utilising topological overlapping measures in optimising the construction of the Vietoris–Rips simplicial complex. The identified persistent topological features significantly enhance the predictive accuracy of cancer phenotypes. This novel approach has the potential to advance the field of topological data analysis and improve our understanding of complex data structures, particularly in the context of cancer research and predictive modelling. Further exploration and application of these measures may yield valuable insights in various domains dealing with intricate datasets.

Image Segmentation and Classification Fields Are Generated Using Binary Random Fields Based on Planar Graph and Neighborhood Spanning Tree

Image analysis plays a pivotal role in computer vision, with image segmentation and classification being fundamental tasks in this domain. This abstract presents a novel approach to image processing that leverages Binary Random Fields (BRF) with a foundation in planar graphs and neighborhood spanning trees. This innovative methodology seeks to enhance the accuracy and efficiency of image segmentation and classification, addressing key challenges in computer vision applications. Binary Random Fields (BRF) is probabilistic graphical models that have proven effective in capturing spatial dependencies and contextual information within images. Our proposed method extends the utility of BRF by incorporating planar graph theory and neighborhood spanning trees to refine the segmentation and classification processes. Planar graphs offer a structured representation of image data, preserving topological relationships among pixels, while neighborhood spanning trees provide a hierarchical framework for modeling image regions

An Optimizing Business Process: A Comprehensive Analysis of Amazon Inc.’s Information Architecture

This analysis studies Amazon Inc.’s information system design in detail using context, use cases, test cases, class, and sequence diagrams. Our research aims to improve business processes by better understanding the system’s interactions, functionality, and data structure. The representation of data structure and entity relationships in class diagrams provides insights into the system’s component organization. Sequence diagrams also provide a clear picture of the sequential interactions between system elements, showing potential bottlenecks and optimization opportunities. It provides unique insights into Amazon’s approaches to keeping a competitive edge in the e-commerce industry, and it may be used as a resource for firms looking to improve their own information systems and procedures.

SPADA: A Sparse Approximate Data Structure Representation for Data Plane Per-flow Monitoring

Accurate per-flow monitoring is critical for precise network diagnosis, performance analysis, and network operation and management in general. However, the limited amount of memory available on modern programmable devices and the large number of active flows force practitioners to monitor only the most relevant flows with approximate data structures, limiting their view of network traffic. We argue that, due to the skewed nature of network traffic, such data structures are, in practice, heavily underutilized, i.e. sparse, thus wasting a significant amount of memory. This paper proposes a Sparse Approximate Data Structure (SPADA) representation that leverages sparsity to reduce the memory footprint of per-flow monitoring systems in the data plane while preserving their original accuracy. SPADA representation can be integrated into a generic per-flow monitoring system and is suitable for several measurement use cases. We prototype SPADA in P4 for a commercial FPGA target and test our approach with a custom simulator that we make publicly available, on four real network traces over three different monitoring tasks. Our results show that SPADA achieves 2× to 11× memory footprint reduction with respect to the state-of-the-art while maintaining the same accuracy, or even improving it.

Normalization of drug and therapeutic concepts with Thera-Py.

The diversity of nomenclature and naming strategies makes therapeutic terminology difficult to manage and harmonize. As the number and complexity of available therapeutic ontologies continues to increase, the need for harmonized cross-resource mappings is becoming increasingly apparent. This study creates harmonized concept mappings that enable the linking together of like-concepts despite source-dependent differences in data structure or semantic representation. For this study, we created Thera-Py, a Python package and web API that constructs searchable concepts for drugs and therapeutic terminologies using 9 public resources and thesauri. By using a directed graph approach, Thera-Py captures commonly used aliases, trade names, annotations, and associations for any given therapeutic and combines them under a single concept record. We highlight the creation of 16069 unique merged therapeutic concepts from 9 distinct sources using Thera-Py and observe an increase in overlap of therapeutic concepts in 2 or more knowledge bases after harmonization using Thera-Py (9.8%-41.8%). We observe that Thera-Py tends to normalize therapeutic concepts to their underlying active ingredients (excluding nondrug therapeutics, eg, radiation therapy, biologics), and unifies all available descriptors regardless of ontological origin.

Insecurity of Quantum Blockchains Based on Entanglement in Time.

In this study, the security implications of utilizing the concept of entanglement in time in the quantum representation of a blockchain data structure are investigated. The analysis reveals that the fundamental idea underlying this representation relies on an uncertain interpretation of experimental results. A different perspective is provided by adopting the Copenhagen interpretation, which explains the observed correlations in the experiment without invoking the concept of entanglement in time. According to this interpretation, the qubits responsible for these correlations are not entangled, posing a challenge to the security foundation of the data structure. The study incorporates theoretical analysis, numerical simulations, and experiments using real quantum hardware. By employing a dedicated circuit for detecting genuine entanglement, the existence of entanglement in the process of generating a quantum blockchain is conclusively excluded.

A Reinforcement Learning List Recommendation Model Fused with Graph Neural Networks

Existing list recommendation methods present a list consisting of multiple items for feedback recommendation to user requests, which has the advantages of high flexibility and direct user feedback. However, the structured representation of state data limits the embedding of users and items, making them isolated from each other, missing some useful infomation for recommendation. In addition, the traditional non-end-to-end learning series takes a long time and accumulates errors. During the model training process, the results of each task can easily affect the next calculation, thus affecting the entire training effect. Aiming at the above problems, this paper proposes a Reinforcement Learning List Recommendation Model Fused with a Graph Neural Network, GNLR. The goal of this model is to maximize the recommendation effect while ensuring that the list recommendation system accurately analyzes user preferences to improve user experience. To this end, firstly, we use an user–item bipartite graph and Graph Neural Network to aggregate neighborhood information for users and items to generate graph structured representation; secondly, we adopt an attention mechanism to assign corresponding weights to neighborhood information to reduce the influence of noise nodes in heterogeneous information networks; finally, we alleviate the problems of traditional non-end-to-end methods through end-to-end training methods. The experimental results show that the method proposed in this paper can alleviate the above problems, and the recommendation hit rate and accuracy rate increase by about 10%.

Local Cluster-Aware Attention for Non-Euclidean Structure Data

Meaningful representation of large-scale non-Euclidean structured data, especially in complex domains like network security and IoT system, is one of the critical problems of contemporary machine learning and deep learning. Many successful cases of graph-based models and algorithms deal with non-Euclidean structured data. However, It is often undesirable to derive node representations by walking through the complete topology of a system or network (graph) when it has a very big or complicated structure. An important issue is using neighborhood knowledge to deduce the symmetric network’s topology or graph. The traditional approach to solving the graph representation learning issue is surveyed from machine learning and deep learning perspectives. Second, include local neighborhood data encoded to the attention mechanism to define node solidarity and enhance node capture and interactions. The performance of the proposed model is then assessed for transduction and induction tasks that include downstream node categorization. The attention model taking clustering into account has successfully equaled or reached the state-of-the-art performance of several well-established node classification benchmarks and does not depend on previous knowledge of the complete network structure, according to experiments. Following a summary of the research, we discuss problems and difficulties that must be addressed for developing future graph signal processing algorithms and graph deep learning models, such as graph embeddings’ interpretability and adversarial resilience. At the same time, it has a very positive impact on network security and artificial intelligence security.

Estimating CSI for Future Generation MIMO Networks Using Deep Learning Techniques and its Applicability to Varied Environments

Massive Multiple-Input Multiple-Output (MIMO) approach consists of high potential to achieve high data rate and one of the most favourable method to exploit channel feedback efficiency. Thus, a deep learning-based CSI feedback mechanism is proposed in this article to ensure high channel estimation efficiency with minimum CSI feedback overhead. Along with that, auto-encoders are adopted to study low dimensional representation of varied data structures. Moreover, CSI matrices are compressed at encoder side and recovered CSI matrices are obtained at decoder side. Further, convolution layers are utilized to get high quality features and fully linked layer is utilized to compress dimensions in CSI feedback matrices. The CSI feedback efficiency is enhanced using 𝐃𝐮𝐚𝐥𝐍𝐞𝐭−𝐍𝐂𝐂 Architecture by exploiting magnitude correlation between downlink and uplink medium. Here, data of two varied environments such as indoor and outdoor cellular environment considering the Cost 2100 database is utilized and simulation is performed in cloud platform. An investigation is carried out to compare performance results of proposed DLAE model in terms of NMSE and correlation efficiency against varied traditional channel estimation approaches. Performance results shows higher channel estimation accuracy and spectral efficiency enhancement.

Structure enhanced deep clustering network via a weighted neighbourhood auto-encoder

Structural deep clustering involves the use of neural networks for fusing semantic and structural representations for clustering tasks, and it has been receiving increasing attention. In some pioneering works, auto-encoder (AE)-specific representations were integrated with a graph convolutional network (GCN)-specific representation by delivering semantic information to the GCN module layer-by-layer. Although promising performance has been achieved in various applications, we observed that a vital aspect was overlooked in these works: the structural information may vanish in the learning process because of the over-smoothing problem of the GCN module, leading to non-representative features and, thus, deteriorating clustering performance. In this study, we address this issue by proposing a structure enhanced deep clustering network. The GCN-specific structural data representation is enhanced and supervised by its structural information. Specifically, the GCN-specific structural data representation is strengthened during the learning process by combining it with a structure enhanced semantic (SES) representation. A novel structure enhanced AE, named the weighted neighbourhood AE (wNAE), is employed to learn the SES representation for each data sample. Finally, we design a joint supervision strategy to uniformly guide the simultaneous learning of the wNAE and GCN modules and the clustering assignment. Experimental results for different datasets empirically validate the importance of semantic and neighbour-wise structure learning.

Применение миварного подхода при создании систем поддержки принятия решений для сферы государственных услуг

Currently, there is an active digitalization of the processes of providing public services and performing public functions by state authorities. In the field of public services, the task of their proactive provision has been set, as a result of which there is a need to develop decision-making support systems for providing services to the population in a proactive form and their information support. Such systems should be able to adapt to changes in legislation in the provision of public services, and in addition have such a logical inference mechanism that could determine the public services that an applicant is entitled to based on limited information about him. The purpose of the study was to investigate the possibility of using the mivar approach in creating such decision support systems. The essence of the mivar approach as a mathematical tool for the development of artificial intelligence systems created by combining the production approach and "Petri nets" is characterized. The model and methods of the mivar approach are considered, the analysis of models for representing data structures, as well as methods for finding the route of inference on the network of rules, is carried out. A technological and technical description of the decision support system based on the mivar approach is presented. The stages of building a logical network of hyper-rules with multiactivators created using expert systems are proposed, and its implementation is shown on the example of the provision of public services.

Index Matrix Representation of Big Data Structures

It is shown that the apparatus of the Index Matrices (IM) can be used for representation of a BigData (BD) structure. An algorithm for searching of facts in the IM-form of a given BD is described. Ideas for further extensions of the BD-structure and of its facts, are formulated.

Shared Data and Algorithms for Deep Learning in Fundamental Physics

We introduce a Python package that provides simple and unified access to a collection of datasets from fundamental physics research—including particle physics, astroparticle physics, and hadron- and nuclear physics—for supervised machine learning studies. The datasets contain hadronic top quarks, cosmic-ray-induced air showers, phase transitions in hadronic matter, and generator-level histories. While public datasets from multiple fundamental physics disciplines already exist, the common interface and provided reference models simplify future work on cross-disciplinary machine learning and transfer learning in fundamental physics. We discuss the design and structure and line out how additional datasets can be submitted for inclusion. As showcase application, we present a simple yet flexible graph-based neural network architecture that can easily be applied to a wide range of supervised learning tasks. We show that our approach reaches performance close to dedicated methods on all datasets. To simplify adaptation for various problems, we provide easy-to-follow instructions on how graph-based representations of data structures, relevant for fundamental physics, can be constructed and provide code implementations for several of them. Implementations are also provided for our proposed method and all reference algorithms.

Scale-invariant representation of machine learning.

The success of machine learning has resulted from its structured representation of data. Similar data have close internal representations as compressed codes for classification or emerged labels for clustering. We observe that the frequency of internal codes or labels follows power laws in both supervised and unsupervised learning models. This scale-invariant distribution implies that machine learning largely compresses frequent typical data, and simultaneously, differentiates many atypical data as outliers. In this study, we derive the process by which these power laws can naturally arise in machine learning. In terms of information theory, the scale-invariant representation corresponds to a maximally uncertain data grouping among possible representations that guarantee a given learning accuracy.

Representation of structured data of the text genre as a technique for automatic text processing

The present article was developed in the field of Natural Language Processing and Language Studies based on a corpus compiled by computational tools. This study is based on the assumption that it is helpful to trace a close relationship between corpus generation/annotation and the assessment of the constitutive elements of the text genre source. It aims to demonstrate, through specific studies of structured data from the text genre ‘scientific article’, alternatives to automatic text processing techniques. In order to reach the intended goal, the authors created a computational model for the compilation of a linguistic, specialized Corpus, representative of the genre Scientific Article - CorpACE. The object of study includes the constitutive elements of scientific articles, marked in XML, extracted and collected from the SciELO-Scientific Electronic Library On-line database. The final product was a database obtained with information extracted and structured in XML format, which designates and identifies the markups of the genre being analyzed and is available for many tools and applications. The results demonstrate how the representation of constitutive elements of the genre can condense available information with hierarchical and dynamic processes built during the compilation. At the end of the study, it is believed that more research will be required for bringing Language Science and Computer Science closer with emphasis on NLP in the attempt to represent and manipulate linguistic knowledge in its many levels – morphological, syntactic, semantic and discursive – in order to improve implementation and manipulation of automatic text processing.