Knowledge Extraction Framework Research Articles

GPU Accelerated MapReduce-Based Distributed Framework for Knowledge Extraction from Large Uncertain Data

GPU Accelerated MapReduce-Based Distributed Framework for Knowledge Extraction from Large Uncertain Data

A GPT-enhanced framework on knowledge extraction and reuse for geographic analysis models in Google Earth Engine

ABSTRACT Geographic analysis models are becoming increasingly important in the era of geospatial big data. As a cloud platform that combines massive geospatial data resources with powerful computational capabilities, the Google Earth Engine (GEE) gathers a large number of workflow scripts for different geographic analysis tasks and gradually evolves into a comprehensive knowledge repository. However, due to the complexity nature of GEE workflow scripts, extracting modeling knowledge from these GEE workflow scripts remains a challenge. Besides, these GEE workflow scripts are often tightly coupled with the GEE environment, which limits their reuse in the broader geospatial community. To address these issues, this paper proposes a GEE knowledge extraction and reuse framework, which uncovers factual meta-information and modeling processes embedded within the GEE workflow script by leveraging ChatGPT and the abstract syntax tree (AST). A GEE knowledge encapsulation template is developed to systematically describe this modeling knowledge. Through case studies, we demonstrate that this framework can be integrated with existing geospatial service technologies, simplify the extraction of modeling knowledge from GEE workflow scripts, and enhance their application in different modeling environments. Moreover, by incorporating ChatGPT, this framework exhibits the potential for intelligent generation of geographic analysis models.

Cost-Effective Knowledge Extraction Framework for Low-Resource Environments

Cost-Effective Knowledge Extraction Framework for Low-Resource Environments

A sequential cross-product knowledge accumulation, extraction and transfer framework for machine learning-based production process modelling

ABSTRACT Machine learning is a promising method to model production processes and predict product quality. It is challenging to accurately model complex systems due to data scarcity, as mass customisation leads to various high-variety low-volume products. This study conceptualised knowledge accumulation, extraction, and transfer (KAET) to exploit the knowledge embedded in similar entities to address data scarcity. A sequential cross-product KAET (SeqTrans) is proposed to conduct KAET, integrating data preparation and preprocessing, feature selection (FS), feature learning (FL), and transfer learning (TL). The FS and FL modules conduct knowledge extraction and help address various practical challenges such as changing operating conditions and unbalanced datasets. In this paper, sequential TL is introduced to production modelling to conduct knowledge transfer among multiple entities. The first case study of auxetic material performance prediction demonstrates the effectiveness of sequential TL. Compared with conventional TL, sequential TL can achieve the same test mean square errors with 300 fewer training examples when facing data scarcity. In the second case study, balancing anomaly detection models were constructed for two gas turbines in the same series using real-world production data. With SeqTrans, the F1-score of the anomaly detection model of the data-poor engine was improved from 0.769 to 0.909.

A data-driven model for predicting the mixed-mode stress intensity factors of a crack in composites

A data-driven model is trained to predict mixed-mode stress intensity factors (SIFs) of composites through an artificial neural network (ANN) method. The model is based on a database generated by combining the interaction integral and the extended finite element method (XFEM). To reduce the input dimensionality and improve predictive performance, feature engineering is performed on the input data, and principal component analysis is conducted. Hyperparameters of the model are adjusted by using K-fold cross-validation and Bayesian optimization algorithm (BOA) to enhance the adaptability and generalization of the model. To overcome the data scarcity issue, an active learning knowledge extraction framework is constructed, which allows for accurate knowledge extraction even with limited data. By utilizing data-driven models to solve mixed-mode SIFs, the computational cost and complexity are greatly reduced compared to numerical simulations, while computational stability and ability to deal with high-dimensional nonlinear problems are significantly improved.

Design knowledge extraction framework and its application in multi-objective ship optimization

Currently, hull form optimization performs design space searches through an optimization algorithm to find the optimal solution and discusses the optimal result only while ignoring a large amount of optimized data. In the optimized data, there are implicit relationships between variables and between the variables and objective function, which can contribute to a better understanding of optimization problems. For the above problems, this paper studies the optimized data in hull form optimization and proposes a set of design knowledge extraction methods suitable for multi-objective ship optimization; in addition, we study the optimization of ship form lines under various working conditions using a 7500-ton inland twin-skeg bulk carrier as the research object. On this basis, the design knowledge is extracted via sensitivity analysis and self-organizing mapping neural network in data mining, and the effectiveness of the rule extraction technology is verified through a comparative analysis of the results. The concluded rules play a significant role in guiding hull form optimization.

A Study on a Knowledge Graph Construction Method of Safety Reports for Process Industries

There are some representative reports in industrial safety engineering, such as the Hazard and Operability Analysis and Pre-Hazard Analysis; however, a large amount of industrial safety knowledge in the report has not been fully explored. In order to reuse and release the value of industrial safety knowledge, this paper constructs a new industrial safety knowledge extraction framework. The framework combines the asset management shell to summarize the knowledge concept entities of machine description language and model description language. According to the safety report template, the framework also constructs a new industrial safety knowledge-mapping standard structure. Specifically, firstly, considering that the knowledge structure of safety reports is different in different processes of the process industry, this paper innovatively proposes a general industrial safety knowledge-mapping standard structure, which provides a practical solution for the integration of industrial knowledge representation problems in different processes. Secondly, based on the research progress of named entities, this paper presents an industrial named entity extraction method (INERM) for the process industry. This method designs an entity weight model to calculate the entity weight of each sentence, and adds part-of-speech weight to improve the entity extraction algorithm, which alleviates the problem that the existing entity extraction methods cannot reasonably use the semantic information and context of word. Finally, we construct a triple of industrial safety knowledge based on the rules and store it in Neo4j. In this paper, four semantic-type templates and five semantic relation templates are constructed based on the new industrial safety knowledge map standardization construction process of the process industry. The comparative experiments show that the accuracy of the INERM on the test set is improved by 17 percentage points on average compared with other key entity extraction algorithms. A total of 1329 entities are constructed in the directional application example of the fluid transportation process, which provides a large number of references for the safety of the fluid transportation process and is more conducive to improving the safety guarantee of the fluid transport process.

Attack Behavior Extraction Based on Heterogeneous Cyberthreat Intelligence and Graph Convolutional Networks

The continuous improvement of the cyber threat intelligence sharing mechanism provides new ideas to deal with Advanced Persistent Threats (APT). Extracting attack behaviors, i.e., Tactics, Techniques, Procedures (TTP) from Cyber Threat Intelligence (CTI) can facilitate APT actors’ profiling for an immediate response. However, it is difficult for traditional manual methods to analyze attack behaviors from cyber threat intelligence due to its heterogeneous nature. Based on the Adversarial Tactics, Techniques and Common Knowledge (ATT&CK) of threat behavior description, this paper proposes a threat behavioral knowledge extraction framework that integrates Heterogeneous Text Network (HTN) and Graph Convolutional Network (GCN) to solve this issue. It leverages the hierarchical correlation relationships of attack techniques and tactics in the ATT&CK to construct a text network of heterogeneous cyber threat intelligence. With the help of the Bidirectional Encoder Representation from Transformers (BERT) pretraining model to analyze the contextual semantics of cyber threat intelligence, the task of threat behavior identification is transformed into a text classification task, which automatically extracts attack behavior in CTI, then identifies the malware and advanced threat actors. The experimental results show that F1 achieve 94.86% and 92.15% for the multi-label classification tasks of tactics and techniques. Extend the experiment to verify the method’s effectiveness in identifying the malware and threat actors in APT attacks. The F1 for malware and advanced threat actors identification task reached 98.45% and 99.48%, which are better than the benchmark model in the experiment and achieve state of the art. The model can effectively model threat intelligence text data and acquire knowledge and experience migration by correlating implied features with a priori knowledge to compensate for insufficient sample data and improve the classification performance and recognition ability of threat behavior in text.

NEARSIDE: Structured kNowledge Extraction frAmework from SpecIes DEscriptions

Species descriptions are stored in textual form in corpora such as in floras and faunas, but this large amount of information cannot be used directly by algorithms, nor can it be linked to other data sources. The production of knowledge bases expressing structured data can benefit from collaborative and easy-to-use platforms like Xper3 (Vignes-Lebbe et al. 2017, Kerner and Vignes 2019, Saucède et al. 2021) but is very time-consuming at the human level. It is therefore mandatory for this task to make the information contained in species descriptions measurable and compatible with computer techniques. One of the most used data structures on the web and by the deep learning community is the triplet structure. Each piece of information is represented by a set of 3 elements (subject, predicate, object). One of the first steps towards species information accessibility is developing a text-to-triplet model, also known as text-to-graph, for monograph descriptions. In this work, we developed NEARSIDE, a text-to-graph model adapted to biology corpora to create normalized morphological characteristic knowledge bases for species descriptions. In Natural Language Processing, deep learning models have proven to be effective in extracting knowledge from open domain corpora (Lample et al. 2016, Sutskever et al. 2014), especially since the emergence of attention-based models (Devlin et al. 2019b, Devlin et al. 2019a). Several works have been made also on biomedical corpora (Fries et al. 2017,Cho and Lee 2019). In our case, we propose a model adapted to floras. Fully supervised deep learning models require a large amount of annotated data for training, nevertheless, the annotation process for the text-to-triplet task implies an expensive human intervention. Distant supervision is a technique that can be used to reduce this cost. This paradigm uses a small annotated glossary to project classes at the word level on a new complex and longer text (see Fig. 1). Named Entity Recognition (NER) is an Natural Language Processing (NLP) task that consists of extracting and classifying words of interest from a text (Sutskever et al. 2014, Devlin et al. 2019b, Lample et al. 2016), while triplet extraction can be compared to the Relation Extraction task (RE) which consists of extracting the words and the semantic relations between pairs of words. Distantly supervised NER is an often studied subject in the literature in comparison to distantly supervised RE (Liang et al. 2020, Meng et al. 2021) simply because NER is a subtask to RE and distant annotations generation is less expensive for the NER task (see Fig. 2). Our first contribution is creating a distantly annotated species description dataset for Named Entity Recognition with a well-balanced test set that allows us to bypass several biases that can be induced by the distant annotation and that are often observed in NER datasets (Taillé et al. 2021). In this dataset, each word of interest will be classified into one of 15 classes, each class being a specific kind of organ or descriptor. Our second contribution is proposing a distantly supervised model trained on our dataset, since fauna and flora corpora are particularly long and use a very specific technical vocabulary. We develop a context-oriented model adapted to this data by pretraining the language model. Thus the encoder of our model provides contextualized vectors for each extracted word that can be used to measure description similarities between different species. Our model reaches 96% accuracy in named entity classification on the test set. Our third contribution is the triplet construction module that can directly be applied to our model's outputs. This module is based on class dependency rules that are inspired by Xper3’s data representation format (see Fig. 3). Finally, NEARSIDE is an end-to-end structured knowledge extraction framework from unstructured species description corpora, that can be applied to several data sources. Thus making species descriptions from different corpora easily linked, compared and measured.

High Reporting Rate Smart Metering Data for Enhanced Grid Monitoring and Services for Energy Communities

Capturing the dynamic behavior of the power distribution grids, especially under high penetration of renewables, is of high interest for grid operators. The distribution power grids are not fully observable due to lack of sufficient metering infrastructure, especially downstream of medium-voltage substations. Therefore, fusion of data recorded at significantly different reporting rates is proposed to increase the situational awareness of the system with non-negligible effect on the accuracy of the monitoring tool. Higher reporting rates are possible for next generation smart meters (SM), but they raise higher concerns about data privacy, already an issue for SM rollout. This article proposes a framework for knowledge extraction from high reporting-rate SM data. The process takes place at SM level and with low computation and communication costs and preserving user privacy, with the scope to increase the accuracy of the monitoring tools for distribution power grids. The methodology makes use of statistical metrics able to capture system dynamics relevant for network diagnosis. The proposed approach is validated on a three-phase low-voltage power flow model applied to a realistic testbed microgrid and real field measurements synchronized at 1 s.

A knowledge extraction framework for domain-specific application with simplified pre-trained language model and attention-based feature extractor

A knowledge extraction framework for domain-specific application with simplified pre-trained language model and attention-based feature extractor

A spatio-temporal emotional framework for knowledge extraction and mining in digital humanities

PurposeThis paper aims to construct a spatio-temporal emotional framework (STEF) for digital humanities from a quantitative perspective, applying knowledge extraction and mining technology to promote innovation of humanities research paradigm and method.Design/methodology/approachThe proposed STEF uses methods of information extraction, sentiment analysis and geographic information system to achieve knowledge extraction and mining. STEF integrates time, space and emotional elements to visualize the spatial and temporal evolution of emotions, which thus enriches the analytical paradigm in digital humanities.FindingsThe case study shows that STEF can effectively extract knowledge from unstructured texts in the field of Chinese Qing Dynasty novels. First, STEF introduces the knowledge extraction tools – MARKUS and DocuSky – to profile character entities and perform plots extraction. Second, STEF extracts the characters' emotional evolutionary trajectory from the temporal and spatial perspective. Finally, the study draws a spatio-temporal emotional path figure of the leading characters and integrates the corresponding plots to analyze the causes of emotion fluctuations.Originality/valueThe STEF is constructed based on the “spatio-temporal narrative theory” and “emotional narrative theory”. It is the first framework to integrate elements of time, space and emotion to analyze the emotional evolution trajectories of characters in novels. The execuability and operability of the framework is also verified with a case novel to suggest a new path for quantitative analysis of other novels.

Semi-Automatic Systematic Literature Reviews and Information Extraction of COVID-19 Scientific Evidence: Description and Preliminary Results of the COKE Project

The COVID-19 pandemic highlighted the importance of validated and updated scientific information to help policy makers, healthcare professionals, and the public. The speed in disseminating reliable information and the subsequent guidelines and policy implementation are also essential to save as many lives as possible. Trustworthy guidelines should be based on a systematic evidence review which uses reproducible analytical methods to collect secondary data and analyse them. However, the guidelines’ drafting process is time consuming and requires a great deal of resources. This paper aims to highlight the importance of accelerating and streamlining the extraction and synthesis of scientific evidence, specifically within the systematic review process. To do so, this paper describes the COKE (COVID-19 Knowledge Extraction framework for next generation discovery science) Project, which involves the use of machine reading and deep learning to design and implement a semi-automated system that supports and enhances the systematic literature review and guideline drafting processes. Specifically, we propose a framework for aiding in the literature selection and navigation process that employs natural language processing and clustering techniques for selecting and organizing the literature for human consultation, according to PICO (Population/Problem, Intervention, Comparison, and Outcome) elements. We show some preliminary results of the automatic classification of sentences on a dataset of abstracts related to COVID-19.

Hybrid Knowledge Extraction Framework Using Modified Adaptive Genetic Algorithm and BPNN

Fault diagnosis based on the expert system (ES) is still a research topic of manufacturing in the Industry 4.0 because of the stronger interpretability. As the core component of the ES, fault diagnosis accuracy is positively correlated to the precise of the knowledge base. But it is difficult for users to understand the knowledge obtained from the original dataset utilizing the existing knowledge extraction method. Therefore, it is of great significance to extract easy-to-understand and exact rules from the NN framework. This paper proposes a hybrid extraction framework to perform the rule extraction for overcoming this drawback. First, an improved adaptive genetic algorithm (GA) using a logistic function, namely LAGA, is proposed to solve the traditional GA’s insufficient prediction performance issue. Compared with the other three mainstream adaptive GAs, the experiment results of optimizing six selected test functions by these GA variants show that the LAGA algorithm’s convergence accuracy and speed have been greatly improved, especially for high latitude functions. On this basis, a rule extraction method based on symbol rule and NN, namely the LAGA-BP framework, is discussed in this manuscript to classify the real-valued attributes. This framework obtains hidden knowledge (knowledge refinement process) by NN and further transforms the acquired hidden knowledge into more easy-to-understand rule knowledge (rule extraction process). The execution of the LAGA-BP framework could be separated into two phases. The first phase is to optimize a back propagation NN (BPNN) using the LAGA and refine prediction classification knowledge over the optimized BPNN. In the second phase, an attribute reduction algorithm using multi-layered NN (SD algorithm) based on two different superposed networks is used on this framework to reduce data-set attributes and then uses the K-means clustering algorithm to extract the if-then rule from the simplified attributes. the Wisconsin breast cancer data-set is used as a case study to reveal the correctness and robustness of the proposed LAGA-BP method. Consulting relevant medical personnel and referencing relevant data shows that the rules extracted using this method help verify the diagnosis results, thus verifying the proposed framework’s feasibility and practicality.

A practical approach towards causality mining in clinical text using active transfer learning

ObjectiveCausality mining is an active research area, which requires the application of state-of-the-art natural language processing techniques. In the healthcare domain, medical experts create clinical text to overcome the limitation of well-defined and schema driven information systems. The objective of this research work is to create a framework, which can convert clinical text into causal knowledge. MethodsA practical approach based on term expansion, phrase generation, BERT based phrase embedding and semantic matching, semantic enrichment, expert verification, and model evolution has been used to construct a comprehensive causality mining framework. This active transfer learning based framework along with its supplementary services, is able to extract and enrich, causal relationships and their corresponding entities from clinical text. ResultsThe multi-model transfer learning technique when applied over multiple iterations, gains substantial performance improvements. We also present a comparative analysis of the presented techniques with their common alternatives, which demonstrate the correctness of our approach and its ability to capture most causal relationships. ConclusionThe presented framework has provided cutting-edge results in the healthcare domain. However, the framework can be tweaked to provide causality detection in other domains, as well. SignificanceThe presented framework is generic enough to be utilized in any domain, healthcare services can gain massive benefits due to the voluminous and various nature of its data. This causal knowledge extraction framework can be used to summarize clinical text, create personas, discover medical knowledge, and provide evidence to clinical decision making.

A PSO Based Cloud Framework for Knowledge Extraction

Many industries, such as oil, construction, banking, and insurance, have substantial historical physical data. Companies store this data in physical warehouses that are geographically distributed and usually taken care of by record management companies. Storing large volumes of historical physical data poses many critical challenges, such as increased maintenance cost, high time for recovery, and unsearchable data. Many companies digitize this data and consolidate this data into cloud repositories as part of their Digital Transformation (DT) journey to address these challenges. This DT process introduces many other technical challenges while dealing with poor scans, huge file size, geographically distributed files, and confidential documents. Though there are options to resolve each of these limitations individually, there are no frameworks that deal with digitization and historical data storage in its entirety. Moreover, they cannot handle a large number of documents having variable file sizes. This paper presents a generic cloud-based high-performance computing framework for knowledge extraction, comprising document classification based on neural networks and particle swarm optimization (PSO), data extraction, metadata enrichment, image enhancement using image processing (IP) techniques, and high data availability to users using cloud-based search. The proposed framework is executed on two cloud providers, i.e., Azure and AWS, to test its efficacy.

Knowledge extraction and transfer in data-driven fracture mechanics

Data-driven approaches promise to usher in a new phase of development in fracture mechanics, but very little is currently known about how data-driven knowledge extraction and transfer can be accomplished in this field. As in many other fields, data scarcity presents a major challenge for knowledge extraction, and knowledge transfer among different fracture problems remains largely unexplored. Here, a data-driven framework for knowledge extraction with rigorous metrics for accuracy assessments is proposed and demonstrated through a nontrivial linear elastic fracture mechanics problem encountered in small-scale toughness measurements. It is shown that a tailored active learning method enables accurate knowledge extraction even in a data-limited regime. The viability of knowledge transfer is demonstrated through mining the hidden connection between the selected three-dimensional benchmark problem and a well-established auxiliary two-dimensional problem. The combination of data-driven knowledge extraction and transfer is expected to have transformative impact in this field over the coming decades.

Towards an adapted PHM approach: Data quality requirements methodology for fault detection applications

Increasingly, extracting knowledge from data has become an important task in organizations for performance improvements. To accomplish this task, data-driven Prognostics and Health Management (PHM) is introduced as an asset performance management framework for data management and knowledge extraction. However, acquired data come generally with quality issues that affect the PHM process. In this context, data quality problems in the PHM context still an understudied domain. Indeed, the quality of the used data, their quantification, their improvement techniques and their adequacy to the desired PHM tasks are marginalized in the majority of studies. Moreover, many PHM applications are based on the development of very sophisticated data analysis algorithms without taking into account the adaptability of the used data to the fixed objectives. This paper aims to propose a set of data quality requirements for PHM applications and in particular for the fault detection task. The conducted developments in this study are applied to Scoder enterprise, which is a French SME. The feedback on the first results is reported and discussed.

Web Radio Automation for Audio Stream Management in the Era of Big Data

Radio is evolving in a changing digital media ecosystem. Audio-on-demand has shaped the landscape of big unstructured audio data available online. In this paper, a framework for knowledge extraction is introduced, to improve discoverability and enrichment of the provided content. A web application for live radio production and streaming is developed. The application offers typical live mixing and broadcasting functionality, while performing real-time annotation as a background process by logging user operation events. For the needs of a typical radio station, a supervised speaker classification model is trained for the recognition of 24 known speakers. The model is based on a convolutional neural network (CNN) architecture. Since not all speakers are known in radio shows, a CNN-based speaker diarization method is also proposed. The trained model is used for the extraction of fixed-size identity d-vectors. Several clustering algorithms are evaluated, having the d-vectors as input. The supervised speaker recognition model for 24 speakers scores an accuracy of 88.34%, while unsupervised speaker diarization scores a maximum accuracy of 87.22%, as tested on an audio file with speech segments from three unknown speakers. The results are considered encouraging regarding the applicability of the proposed methodology.

A cooperative crowdsourcing framework for knowledge extraction in digital humanities – cases on Tang poetry

PurposeThe purpose of this paper is to propose a knowledge extraction framework to extract knowledge, including entities and relationships between them, from unstructured texts in digital humanities (DH).Design/methodology/approachThe proposed cooperative crowdsourcing framework (CCF) uses both human–computer cooperation and crowdsourcing to achieve high-quality and scalable knowledge extraction. CCF integrates active learning with a novel category-based crowdsourcing mechanism to facilitate domain experts labeling and verifying extracted knowledge.FindingsThe case study shows that CCF can effectively and efficiently extract knowledge from multi-sourced heterogeneous data in the field of Tang poetry. Specifically, CCF achieves higher accuracy of knowledge extraction than the state-of-the-art methods, the contribution of feedbacks to the training model can be maximized by the active learning mechanism and the proposed category-based crowdsourcing mechanism can scale up the effective human–computer collaboration by considering the specialization of workers in different categories of tasks.Research limitations/implicationsThis research proposes CCF to enable high-quality and scalable knowledge extraction in the field of Tang poetry. CCF can be generalized to other fields of DH by introducing domain knowledge and experts.Practical implicationsThe extracted knowledge is machine-understandable and can support the research of Tang poetry and knowledge-driven intelligent applications in DH.Originality/valueCCF is the first human-in-the-loop knowledge extraction framework that integrates active learning and crowdsourcing mechanisms; he human–computer cooperation method uses the feedback of domain experts through the active learning mechanism; the category-based crowdsourcing mechanism considers the matching of categories of DH data and especially of domain experts.